mirror of
https://github.com/apache/impala.git
synced 2025-12-19 18:12:08 -05:00
IMPALA-9362: Upgrade sqlparse 0.1.19 -> 0.3.1
Upgrades the impala-shell's bundled version of sqlparse to 0.3.1. There were some API changes in 0.2.0+ that required a re-write of the StripLeadingCommentFilter in impala_shell.py. A slight perf optimization was also added to avoid using the filter altogether if no leading comment is readily discernible. As 0.1.19 was the last version of sqlparse to support python 2.6, this patch also breaks Impala's compatibility with python 2.6. No new tests were added, but all existing tests passed without modification. Change-Id: I77a1fd5ae311634a18ee04b8c389d8a3f3a6e001 Reviewed-on: http://gerrit.cloudera.org:8080/15642 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
This commit is contained in:
David Knupp
committed by
Impala Public Jenkins
Impala Public Jenkins
parent
327ec29c48
commit
c26e3db4bd
61
LICENSE.txt
61
LICENSE.txt
@@ -613,30 +613,33 @@ CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
|
||||
--------------------------------------------------------------------------------
|
||||
|
||||
shell/ext-py/sqlparse-0.1.19 (most parts): 3-clause BSD
|
||||
shell/ext-py/sqlparse-0.3.1: 3-clause BSD
|
||||
|
||||
Copyright (c) 2009, Andi Albrecht <albrecht.andi@gmail.com>
|
||||
Copyright (c) 2016, Andi Albrecht <albrecht.andi@gmail.com>
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
Redistribution and use in source and binary forms, with or without modification,
|
||||
are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above copyright notice,
|
||||
this list of conditions and the following disclaimer in the documentation
|
||||
and/or other materials provided with the distribution.
|
||||
* The name of the author may not be used to endorse or promote products
|
||||
derived from this software without specific prior written permission.
|
||||
* Neither the name of the authors nor the names of its contributors may be
|
||||
used to endorse or promote products derived from this software without
|
||||
specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
|
||||
EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
||||
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
|
||||
THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
|
||||
OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||
LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
|
||||
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
||||
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
--------------------------------------------------------------------------------
|
||||
|
||||
@@ -665,34 +668,6 @@ THE SOFTWARE.
|
||||
|
||||
--------------------------------------------------------------------------------
|
||||
|
||||
shell/ext-py/sqlparse-0.1.19/sqlparse/pipeline.py:
|
||||
|
||||
Copyright (C) 2011 Jesus Leganes "piranna", piranna@gmail.com
|
||||
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification, are
|
||||
permitted provided that the following conditions are met:
|
||||
|
||||
1. Redistributions of source code must retain the above copyright notice, this list of
|
||||
conditions and the following disclaimer.
|
||||
|
||||
2. Redistributions in binary form must reproduce the above copyright notice, this list of
|
||||
conditions and the following disclaimer in the documentation and/or other materials
|
||||
provided with the distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
|
||||
EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
||||
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
|
||||
COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
||||
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
|
||||
TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
--------------------------------------------------------------------------------
|
||||
|
||||
be/src/thirdparty/mustache: Apache 2.0 license
|
||||
be/src/thirdparty/pcg-cpp-0.98: Apache 2.0 license
|
||||
be/src/expr/hll-bias.h: Apache 2.0 license
|
||||
|
||||
@@ -72,7 +72,7 @@ can do so through the environment variables and scripts listed below.
|
||||
| JAVA_VERSION | "java-7-oracle-amd64" | Can override to set a local Java version. |
|
||||
| JAVA | "${JAVA_HOME}/bin/java" | Java binary location. |
|
||||
| CLASSPATH | | See bin/set-classpath.sh for details. |
|
||||
| PYTHONPATH | Will be changed to include: "${IMPALA_HOME}/shell/gen-py" "${IMPALA_HOME}/testdata" "${THRIFT_HOME}/python/lib/python2.7/site-packages" "${HIVE_HOME}/lib/py" "${IMPALA_HOME}/shell/ext-py/prettytable-0.7.1/dist/prettytable-0.7.1" "${IMPALA_HOME}/shell/ext-py/sasl-0.1.1/dist/sasl-0.1.1-py2.7-linux-x "${IMPALA_HOME}/shell/ext-py/sqlparse-0.1.19/dist/sqlparse-0.1.19-py2 |
|
||||
| PYTHONPATH | Will be changed to include: "${IMPALA_HOME}/shell/gen-py" "${IMPALA_HOME}/testdata" "${THRIFT_HOME}/python/lib/python2.7/site-packages" "${HIVE_HOME}/lib/py" |
|
||||
|
||||
##### Source Directories for Impala
|
||||
|
||||
|
||||
@@ -45,7 +45,7 @@ shell/ext-py/bitarray-0.9.0/*
|
||||
shell/ext-py/prettytable-0.7.1/*
|
||||
shell/ext-py/sasl-0.1.1/*
|
||||
shell/ext-py/six-1.14.0/*
|
||||
shell/ext-py/sqlparse-0.1.19/*
|
||||
shell/ext-py/sqlparse-0.3.1/*
|
||||
shell/ext-py/thrift_sasl-0.4.2/*
|
||||
www/d3.v3.min.js
|
||||
www/jquery/jquery-3.4.1.min.js
|
||||
|
||||
@@ -56,10 +56,7 @@ setuptools == 36.8.0
|
||||
setuptools-scm == 1.15.4
|
||||
sh == 1.11
|
||||
six == 1.14.0
|
||||
# Note: This version for sqlparse is not what is used for the shell. The shell uses
|
||||
# a checked-in version of sqlparse (see shell/ext-py). This version is used primarily
|
||||
# for dataload.
|
||||
sqlparse == 0.1.19
|
||||
sqlparse == 0.3.1
|
||||
texttable == 0.8.3
|
||||
|
||||
# For dev purposes, not used in scripting. Version 1.2.1 is the latest that supports 2.6.
|
||||
|
||||
9
shell/.gitignore
vendored
9
shell/.gitignore
vendored
@@ -8,9 +8,9 @@ ext-py/six-1.14.0/six.egg-info/
|
||||
ext-py/prettytable-0.7.1/dist/
|
||||
ext-py/prettytable-0.7.1/build
|
||||
ext-py/prettytable-0.7.1/prettytable.egg-info
|
||||
ext-py/sqlparse-0.1.19/dist/
|
||||
ext-py/sqlparse-0.1.19/build/
|
||||
ext-py/sqlparse-0.1.19/sqlparse.egg-info/
|
||||
ext-py/sqlparse-0.3.1/dist/
|
||||
ext-py/sqlparse-0.3.1/build/
|
||||
ext-py/sqlparse-0.3.1/sqlparse.egg-info/
|
||||
ext-py/bitarray-0.9.0/bitarray.egg-info/
|
||||
ext-py/bitarray-0.9.0/dist/
|
||||
ext-py/thrift_sasl-0.4.2/dist/
|
||||
@@ -21,4 +21,7 @@ ext-py/thrift_sasl-0.4.2/six.egg-info/
|
||||
# clean phase. Previous version of deps should be kept here for cleaning otherwise they
|
||||
# may cause a build failure. Also the ignore path must be changed to the root folder
|
||||
# so "git clean -Xdf" will work.
|
||||
ext-py/six-1.11.0/
|
||||
ext-py/sqlparse-0.1.7/
|
||||
ext-py/sqlparse-0.1.19/
|
||||
ext-py/thrift_sasl-0.4.1/
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
language: python
|
||||
python: 2.7
|
||||
env:
|
||||
- TOX_ENV=py26
|
||||
- TOX_ENV=py27
|
||||
- TOX_ENV=py33
|
||||
- TOX_ENV=py34
|
||||
- TOX_ENV=pypy
|
||||
before_install:
|
||||
- sudo apt-get install pypy
|
||||
install:
|
||||
- pip install tox
|
||||
script:
|
||||
- tox -e $TOX_ENV
|
||||
@@ -1,31 +0,0 @@
|
||||
python-sqlparse is written and maintained by Andi Albrecht <albrecht.andi@gmail.com>.
|
||||
|
||||
This module contains code (namely the lexer and filter mechanism) from
|
||||
the pygments project that was written by Georg Brandl.
|
||||
|
||||
Alphabetical list of contributors:
|
||||
* Alexander Beedie <ayembee@gmail.com>
|
||||
* Alexey Malyshev <nostrict@gmail.com>
|
||||
* casey <casey@cloudera.com>
|
||||
* Cristian Orellana <cristiano@groupon.com>
|
||||
* Darik Gamble <darik.gamble@gmail.com>
|
||||
* Florian Bauer <florian.bauer@zmdi.com>
|
||||
* Gavin Wahl <gwahl@fusionbox.com>
|
||||
* JacekPliszka <Jacek.Pliszka@gmail.com>
|
||||
* Jesús Leganés Combarro "Piranna" <piranna@gmail.com>
|
||||
* Kevin Jing Qiu <kevin.jing.qiu@gmail.com>
|
||||
* Michael Schuller <chick@mschuller.net>
|
||||
* Mike Amy <cocoade@googlemail.com>
|
||||
* mulos <daniel.strackbein@gmail.com>
|
||||
* Piet Delport <pjdelport@gmail.com>
|
||||
* Prudhvi Vatala <pvatala@gmail.com>
|
||||
* quest <quest@wonky.windwards.net>
|
||||
* Robert Nix <com.github@rnix.org>
|
||||
* Rocky Meza <rmeza@fusionbox.com>
|
||||
* Ryan Wooden <rygwdn@gmail.com>
|
||||
* spigwitmer <itgpmc@gmail.com>
|
||||
* Tim Graham <timograham@gmail.com>
|
||||
* Victor Hahn <info@victor-hahn.de>
|
||||
* vthriller <farreva232@yandex.ru>
|
||||
* wayne.wuw <wayne.wuw@alibaba-inc.com>
|
||||
* Yago Riveiro <yago.riveiro@gmail.com>
|
||||
@@ -1,302 +0,0 @@
|
||||
Release 0.1.19 (Mar 07, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix IndexError when statement contains WITH clauses (issue205).
|
||||
|
||||
|
||||
Release 0.1.18 (Oct 25, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Remove universal wheel support, added in 0.1.17 by mistake.
|
||||
|
||||
|
||||
Release 0.1.17 (Oct 24, 2015)
|
||||
-----------------------------
|
||||
|
||||
Enhancements
|
||||
* Speed up parsing of large SQL statements (pull request: issue201, fixes the
|
||||
following issues: issue199, issue135, issue62, issue41, by Ryan Wooden).
|
||||
|
||||
Bug Fixes
|
||||
* Fix another splitter bug regarding DECLARE (issue194).
|
||||
|
||||
Misc
|
||||
* Packages on PyPI are signed from now on.
|
||||
|
||||
|
||||
Release 0.1.16 (Jul 26, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix a regression in get_alias() introduced in 0.1.15 (issue185).
|
||||
* Fix a bug in the splitter regarding DECLARE (issue193).
|
||||
* sqlformat command line tool doesn't duplicat newlines anymore (issue191).
|
||||
* Don't mix up MySQL comments starting with hash and MSSQL
|
||||
temp tables (issue192).
|
||||
* Statement.get_type() now ignores comments at the beginning of
|
||||
a statement (issue186).
|
||||
|
||||
|
||||
Release 0.1.15 (Apr 15, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix a regression for identifiers with square bracktes
|
||||
notation (issue153, by darikg).
|
||||
* Add missing SQL types (issue154, issue155, issue156, by jukebox).
|
||||
* Fix parsing of multi-line comments (issue172, by JacekPliszka).
|
||||
* Fix parsing of escaped backslashes (issue174, by caseyching).
|
||||
* Fix parsing of identifiers starting with underscore (issue175).
|
||||
* Fix misinterpretation of IN keyword (issue183).
|
||||
|
||||
Enhancements
|
||||
* Improve formatting of HAVING statements.
|
||||
* Improve parsing of inline comments (issue163).
|
||||
* Group comments to parent object (issue128, issue160).
|
||||
* Add double precision builtin (issue169, by darikg).
|
||||
* Add support for square bracket array indexing (issue170, issue176,
|
||||
issue177 by darikg).
|
||||
* Improve grouping of aliased elements (issue167, by darikg).
|
||||
* Support comments starting with '#' character (issue178).
|
||||
|
||||
|
||||
Release 0.1.14 (Nov 30, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Floats in UPDATE statements are now handled correctly (issue145).
|
||||
* Properly handle string literals in comparisons (issue148, change proposed
|
||||
by aadis).
|
||||
* Fix indentation when using tabs (issue146).
|
||||
|
||||
Enhancements
|
||||
* Improved formatting in list when newlines precede commas (issue140).
|
||||
|
||||
|
||||
Release 0.1.13 (Oct 09, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix a regression in handling of NULL keywords introduced in 0.1.12.
|
||||
|
||||
|
||||
Release 0.1.12 (Sep 20, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix handling of NULL keywords in aliased identifiers.
|
||||
* Fix SerializerUnicode to split unquoted newlines (issue131, by Michael Schuller).
|
||||
* Fix handling of modulo operators without spaces (by gavinwahl).
|
||||
|
||||
Enhancements
|
||||
* Improve parsing of identifier lists containing placeholders.
|
||||
* Speed up query parsing of unquoted lines (by Michael Schuller).
|
||||
|
||||
|
||||
Release 0.1.11 (Feb 07, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix incorrect parsing of string literals containing line breaks (issue118).
|
||||
* Fix typo in keywords, add MERGE, COLLECT keywords (issue122/124,
|
||||
by Cristian Orellana).
|
||||
* Improve parsing of string literals in columns.
|
||||
* Fix parsing and formatting of statements containing EXCEPT keyword.
|
||||
* Fix Function.get_parameters() (issue126/127, by spigwitmer).
|
||||
|
||||
Enhancements
|
||||
* Classify DML keywords (issue116, by Victor Hahn).
|
||||
* Add missing FOREACH keyword.
|
||||
* Grouping of BEGIN/END blocks.
|
||||
|
||||
Other
|
||||
* Python 2.5 isn't automatically tested anymore, neither Travis nor Tox
|
||||
still support it out of the box.
|
||||
|
||||
|
||||
Release 0.1.10 (Nov 02, 2013)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Removed buffered reading again, it obviously causes wrong parsing in some rare
|
||||
cases (issue114).
|
||||
* Fix regression in setup.py introduced 10 months ago (issue115).
|
||||
|
||||
Enhancements
|
||||
* Improved support for JOINs, by Alexander Beedie.
|
||||
|
||||
|
||||
Release 0.1.9 (Sep 28, 2013)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix an regression introduced in 0.1.5 where sqlparse didn't properly
|
||||
distinguished between single and double quoted strings when tagging
|
||||
identifier (issue111).
|
||||
|
||||
Enhancements
|
||||
* New option to truncate long string literals when formatting.
|
||||
* Scientific numbers are pares correctly (issue107).
|
||||
* Support for arithmetic expressions (issue109, issue106; by prudhvi).
|
||||
|
||||
|
||||
Release 0.1.8 (Jun 29, 2013)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Whitespaces within certain keywords are now allowed (issue97, patch proposed
|
||||
by xcombelle).
|
||||
|
||||
Enhancements
|
||||
* Improve parsing of assignments in UPDATE statements (issue90).
|
||||
* Add STRAIGHT_JOIN statement (by Yago Riveiro).
|
||||
* Function.get_parameters() now returns the parameter if only one parameter is
|
||||
given (issue94, by wayne.wuw).
|
||||
* sqlparse.split() now removes leading and trailing whitespaces from splitted
|
||||
statements.
|
||||
* Add USE as keyword token (by mulos).
|
||||
* Improve parsing of PEP249-style placeholders (issue103).
|
||||
|
||||
|
||||
Release 0.1.7 (Apr 06, 2013)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fix Python 3 compatibility of sqlformat script (by Piet Delport).
|
||||
* Fix parsing of SQL statements that contain binary data (by Alexey
|
||||
Malyshev).
|
||||
* Fix a bug where keywords were identified as aliased identifiers in
|
||||
invalid SQL statements.
|
||||
* Fix parsing of identifier lists where identifiers are keywords too
|
||||
(issue10).
|
||||
|
||||
Enhancements
|
||||
* Top-level API functions now accept encoding keyword to parse
|
||||
statements in certain encodings more reliable (issue20).
|
||||
* Improve parsing speed when SQL contains CLOBs or BLOBs (issue86).
|
||||
* Improve formatting of ORDER BY clauses (issue89).
|
||||
* Formatter now tries to detect runaway indentations caused by
|
||||
parsing errors or invalid SQL statements. When re-indenting such
|
||||
statements the formatter flips back to column 0 before going crazy.
|
||||
|
||||
Other
|
||||
* Documentation updates.
|
||||
|
||||
|
||||
Release 0.1.6 (Jan 01, 2013)
|
||||
----------------------------
|
||||
|
||||
sqlparse is now compatible with Python 3 without any patches. The
|
||||
Python 3 version is generated during install by 2to3. You'll need
|
||||
distribute to install sqlparse for Python 3.
|
||||
|
||||
Bug Fixes
|
||||
* Fix parsing error with dollar-quoted procedure bodies (issue83).
|
||||
|
||||
Other
|
||||
* Documentation updates.
|
||||
* Test suite now uses tox and py.test.
|
||||
* py3k fixes (by vthriller).
|
||||
* py3k fixes in setup.py (by Florian Bauer).
|
||||
* setup.py now requires distribute (by Florian Bauer).
|
||||
|
||||
|
||||
Release 0.1.5 (Nov 13, 2012)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Improve handling of quoted identifiers (issue78).
|
||||
* Improve grouping and formatting of identifiers with operators (issue53).
|
||||
* Improve grouping and formatting of concatenated strings (issue53).
|
||||
* Improve handling of varchar() (by Mike Amy).
|
||||
* Clean up handling of various SQL elements.
|
||||
* Switch to py.test and clean up tests.
|
||||
* Several minor fixes.
|
||||
|
||||
Other
|
||||
* Deprecate sqlparse.SQLParseError. Please use
|
||||
sqlparse.exceptions.SQLParseError instead.
|
||||
* Add caching to speed up processing.
|
||||
* Add experimental filters for token processing.
|
||||
* Add sqlformat.parsestream (by quest).
|
||||
|
||||
|
||||
Release 0.1.4 (Apr 20, 2012)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Avoid "stair case" effects when identifiers, functions,
|
||||
placeholders or keywords are mixed in identifier lists (issue45,
|
||||
issue49, issue52) and when asterisks are used as operators
|
||||
(issue58).
|
||||
* Make keyword detection more restrict (issue47).
|
||||
* Improve handling of CASE statements (issue46).
|
||||
* Fix statement splitting when parsing recursive statements (issue57,
|
||||
thanks to piranna).
|
||||
* Fix for negative numbers (issue56, thanks to kevinjqiu).
|
||||
* Pretty format comments in identifier lists (issue59).
|
||||
* Several minor bug fixes and improvements.
|
||||
|
||||
|
||||
Release 0.1.3 (Jul 29, 2011)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Improve parsing of floats (thanks to Kris).
|
||||
* When formatting a statement a space before LIMIT was removed (issue35).
|
||||
* Fix strip_comments flag (issue38, reported by ooberm...@gmail.com).
|
||||
* Avoid parsing names as keywords (issue39, reported by djo...@taket.org).
|
||||
* Make sure identifier lists in subselects are grouped (issue40,
|
||||
reported by djo...@taket.org).
|
||||
* Split statements with IF as functions correctly (issue33 and
|
||||
issue29, reported by charles....@unige.ch).
|
||||
* Relax detection of keywords, esp. when used as function names
|
||||
(issue36, nyuhu...@gmail.com).
|
||||
* Don't treat single characters as keywords (issue32).
|
||||
* Improve parsing of stand-alone comments (issue26).
|
||||
* Detection of placeholders in paramterized queries (issue22,
|
||||
reported by Glyph Lefkowitz).
|
||||
* Add parsing of MS Access column names with braces (issue27,
|
||||
reported by frankz...@gmail.com).
|
||||
|
||||
Other
|
||||
* Replace Django by Flask in App Engine frontend (issue11).
|
||||
|
||||
|
||||
Release 0.1.2 (Nov 23, 2010)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Fixed incorrect detection of keyword fragments embed in names (issue7,
|
||||
reported and initial patch by andyboyko).
|
||||
* Stricter detection of identfier aliases (issue8, reported by estama).
|
||||
* WHERE grouping consumed closing parenthesis (issue9, reported by estama).
|
||||
* Fixed an issue with trailing whitespaces (reported by Kris).
|
||||
* Better detection of escaped single quotes (issue13, reported by
|
||||
Martin Brochhaus, patch by bluemaro with test case by Dan Carley).
|
||||
* Ignore identifier in double-quotes when changing cases (issue 21).
|
||||
* Lots of minor fixes targeting encoding, indentation, statement
|
||||
parsing and more (issues 12, 14, 15, 16, 18, 19).
|
||||
* Code cleanup with a pinch of refactoring.
|
||||
|
||||
|
||||
Release 0.1.1 (May 6, 2009)
|
||||
---------------------------
|
||||
|
||||
Bug Fixes
|
||||
* Lexers preserves original line breaks (issue1).
|
||||
* Improved identifier parsing: backtick quotes, wildcards, T-SQL variables
|
||||
prefixed with @.
|
||||
* Improved parsing of identifier lists (issue2).
|
||||
* Recursive recognition of AS (issue4) and CASE.
|
||||
* Improved support for UPDATE statements.
|
||||
|
||||
Other
|
||||
* Code cleanup and better test coverage.
|
||||
|
||||
|
||||
Release 0.1.0 (Apr 8, 2009)
|
||||
---------------------------
|
||||
* Initial release.
|
||||
@@ -1,56 +0,0 @@
|
||||
python-sqlparse - Parse SQL statements
|
||||
======================================
|
||||
|
||||
sqlparse is a non-validating SQL parser module for Python.
|
||||
|
||||
|buildstatus|_
|
||||
|
||||
|
||||
Install
|
||||
-------
|
||||
|
||||
Run::
|
||||
|
||||
python setup.py install
|
||||
|
||||
to install python-sqlparse on your system.
|
||||
|
||||
python-sqlparse is compatible with Python 2 (>= 2.5) and Python 3 (>= 3.2).
|
||||
|
||||
|
||||
Run Tests
|
||||
---------
|
||||
|
||||
To run the test suite run::
|
||||
|
||||
tox
|
||||
|
||||
Note, you'll need tox installed, of course.
|
||||
|
||||
|
||||
Links
|
||||
-----
|
||||
|
||||
Project Page
|
||||
https://github.com/andialbrecht/sqlparse
|
||||
|
||||
Documentation
|
||||
http://readthedocs.org/docs/sqlparse/en/latest/
|
||||
|
||||
Discussions
|
||||
http://groups.google.com/group/sqlparse
|
||||
|
||||
Issues/Bugs
|
||||
https://github.com/andialbrecht/sqlparse/issues
|
||||
|
||||
Online Demo
|
||||
http://sqlformat.org
|
||||
|
||||
|
||||
python-sqlparse is licensed under the BSD license.
|
||||
|
||||
Parts of the code are based on pygments written by Georg Brandl and others.
|
||||
pygments-Homepage: http://pygments.org/
|
||||
|
||||
.. |buildstatus| image:: https://secure.travis-ci.org/andialbrecht/sqlparse.png?branch=master
|
||||
.. _buildstatus: http://travis-ci.org/#!/andialbrecht/sqlparse
|
||||
@@ -1,109 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
|
||||
import optparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
import sqlparse
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
|
||||
|
||||
_CASE_CHOICES = ['upper', 'lower', 'capitalize']
|
||||
|
||||
|
||||
parser = optparse.OptionParser(usage='%prog [OPTIONS] FILE, ...',
|
||||
version='%%prog %s' % sqlparse.__version__)
|
||||
parser.set_description(('Format FILE according to OPTIONS. Use "-" as FILE '
|
||||
'to read from stdin.'))
|
||||
parser.add_option('-v', '--verbose', dest='verbose', action='store_true')
|
||||
parser.add_option('-o', '--outfile', dest='outfile', metavar='FILE',
|
||||
help='write output to FILE (defaults to stdout)')
|
||||
group = parser.add_option_group('Formatting Options')
|
||||
group.add_option('-k', '--keywords', metavar='CHOICE',
|
||||
dest='keyword_case', choices=_CASE_CHOICES,
|
||||
help=('change case of keywords, CHOICE is one of %s'
|
||||
% ', '.join('"%s"' % x for x in _CASE_CHOICES)))
|
||||
group.add_option('-i', '--identifiers', metavar='CHOICE',
|
||||
dest='identifier_case', choices=_CASE_CHOICES,
|
||||
help=('change case of identifiers, CHOICE is one of %s'
|
||||
% ', '.join('"%s"' % x for x in _CASE_CHOICES)))
|
||||
group.add_option('-l', '--language', metavar='LANG',
|
||||
dest='output_format', choices=['python', 'php'],
|
||||
help=('output a snippet in programming language LANG, '
|
||||
'choices are "python", "php"'))
|
||||
group.add_option('--strip-comments', dest='strip_comments',
|
||||
action='store_true', default=False,
|
||||
help='remove comments')
|
||||
group.add_option('-r', '--reindent', dest='reindent',
|
||||
action='store_true', default=False,
|
||||
help='reindent statements')
|
||||
group.add_option('--indent_width', dest='indent_width', default=2,
|
||||
help='indentation width (defaults to 2 spaces)')
|
||||
|
||||
_FORMATTING_GROUP = group
|
||||
|
||||
|
||||
def _error(msg, exit_=None):
|
||||
"""Print msg and optionally exit with return code exit_."""
|
||||
sys.stderr.write('[ERROR] %s\n' % msg)
|
||||
if exit_ is not None:
|
||||
sys.exit(exit_)
|
||||
|
||||
|
||||
def _build_formatter_opts(options):
|
||||
"""Convert command line options to dictionary."""
|
||||
d = {}
|
||||
for option in _FORMATTING_GROUP.option_list:
|
||||
d[option.dest] = getattr(options, option.dest)
|
||||
return d
|
||||
|
||||
|
||||
def main():
|
||||
options, args = parser.parse_args()
|
||||
if options.verbose:
|
||||
sys.stderr.write('Verbose mode\n')
|
||||
|
||||
if len(args) != 1:
|
||||
_error('No input data.')
|
||||
parser.print_usage()
|
||||
sys.exit(1)
|
||||
|
||||
if '-' in args: # read from stdin
|
||||
data = sys.stdin.read()
|
||||
else:
|
||||
try:
|
||||
data = ''.join(open(args[0]).readlines())
|
||||
except OSError:
|
||||
err = sys.exc_info()[1] # Python 2.5 compatibility
|
||||
_error('Failed to read %s: %s' % (args[0], err), exit_=1)
|
||||
|
||||
if options.outfile:
|
||||
try:
|
||||
stream = open(options.outfile, 'w')
|
||||
except OSError:
|
||||
err = sys.exc_info()[1] # Python 2.5 compatibility
|
||||
_error('Failed to open %s: %s' % (options.outfile, err), exit_=1)
|
||||
else:
|
||||
stream = sys.stdout
|
||||
|
||||
formatter_opts = _build_formatter_opts(options)
|
||||
try:
|
||||
formatter_opts = sqlparse.formatter.validate_options(formatter_opts)
|
||||
except SQLParseError:
|
||||
err = sys.exc_info()[1] # Python 2.5 compatibility
|
||||
_error('Invalid options: %s' % err, exit_=1)
|
||||
|
||||
s = sqlparse.format(data, **formatter_opts)
|
||||
if sys.version_info < (3,):
|
||||
s = s.encode('utf-8', 'replace')
|
||||
stream.write(s)
|
||||
stream.flush()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,64 +0,0 @@
|
||||
.. _analyze:
|
||||
|
||||
Analyzing the Parsed Statement
|
||||
==============================
|
||||
|
||||
When the :meth:`~sqlparse.parse` function is called the returned value
|
||||
is a tree-ish representation of the analyzed statements. The returned
|
||||
objects can be used by applications to retrieve further information about
|
||||
the parsed SQL.
|
||||
|
||||
|
||||
Base Classes
|
||||
------------
|
||||
|
||||
All returned objects inherit from these base classes.
|
||||
The :class:`~sqlparse.sql.Token` class represents a single token and
|
||||
:class:`~sqlparse.sql.TokenList` class is a group of tokens.
|
||||
The latter provides methods for inspecting it's child tokens.
|
||||
|
||||
.. autoclass:: sqlparse.sql.Token
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.TokenList
|
||||
:members:
|
||||
|
||||
|
||||
SQL Representing Classes
|
||||
------------------------
|
||||
|
||||
The following classes represent distinct parts of a SQL statement.
|
||||
|
||||
.. autoclass:: sqlparse.sql.Statement
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Comment
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Identifier
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.IdentifierList
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Where
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Case
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Parenthesis
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.If
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.For
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Assignment
|
||||
:members:
|
||||
|
||||
.. autoclass:: sqlparse.sql.Comparison
|
||||
:members:
|
||||
|
||||
@@ -1,57 +0,0 @@
|
||||
:mod:`sqlparse` -- Parse SQL statements
|
||||
=======================================
|
||||
|
||||
.. module:: sqlparse
|
||||
:synopsis: Parse SQL statements.
|
||||
|
||||
The :mod:`sqlparse` module provides the following functions on module-level.
|
||||
|
||||
.. autofunction:: sqlparse.split
|
||||
|
||||
.. autofunction:: sqlparse.format
|
||||
|
||||
.. autofunction:: sqlparse.parse
|
||||
|
||||
In most cases there's no need to set the `encoding` parameter. If
|
||||
`encoding` is not set, sqlparse assumes that the given SQL statement
|
||||
is encoded either in utf-8 or latin-1.
|
||||
|
||||
|
||||
.. _formatting:
|
||||
|
||||
Formatting of SQL Statements
|
||||
----------------------------
|
||||
|
||||
The :meth:`~sqlparse.format` function accepts the following keyword arguments.
|
||||
|
||||
``keyword_case``
|
||||
Changes how keywords are formatted. Allowed values are "upper", "lower"
|
||||
and "capitalize".
|
||||
|
||||
``identifier_case``
|
||||
Changes how identifiers are formatted. Allowed values are "upper", "lower",
|
||||
and "capitalize".
|
||||
|
||||
``strip_comments``
|
||||
If ``True`` comments are removed from the statements.
|
||||
|
||||
``truncate_strings``
|
||||
If ``truncate_strings`` is a positive integer, string literals longer than
|
||||
the given value will be truncated.
|
||||
|
||||
``truncate_char`` (default: "[...]")
|
||||
If long string literals are truncated (see above) this value will be append
|
||||
to the truncated string.
|
||||
|
||||
``reindent``
|
||||
If ``True`` the indentations of the statements are changed.
|
||||
|
||||
``indent_tabs``
|
||||
If ``True`` tabs instead of spaces are used for indentation.
|
||||
|
||||
``indent_width``
|
||||
The width of the indentation, defaults to 2.
|
||||
|
||||
``output_format``
|
||||
If given the output is additionally formatted to be used as a variable
|
||||
in a programming language. Allowed values are "python" and "php".
|
||||
@@ -1,13 +0,0 @@
|
||||
.. _changes:
|
||||
|
||||
Changes in python-sqlparse
|
||||
==========================
|
||||
|
||||
Upcoming Deprecations
|
||||
---------------------
|
||||
|
||||
* ``sqlparse.SQLParseError`` is deprecated (version 0.1.5), use
|
||||
``sqlparse.exceptions.SQLParseError`` instead.
|
||||
|
||||
.. include:: ../../CHANGES
|
||||
|
||||
@@ -1,200 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# python-sqlparse documentation build configuration file, created by
|
||||
# sphinx-quickstart on Thu Feb 26 08:19:28 2009.
|
||||
#
|
||||
# This file is execfile()d with the current directory set to its containing dir.
|
||||
#
|
||||
# Note that not all possible configuration values are present in this
|
||||
# autogenerated file.
|
||||
#
|
||||
# All configuration values have a default; values that are commented out
|
||||
# serve to show the default.
|
||||
|
||||
import datetime
|
||||
import sys, os
|
||||
|
||||
# If extensions (or modules to document with autodoc) are in another directory,
|
||||
# add these directories to sys.path here. If the directory is relative to the
|
||||
# documentation root, use os.path.abspath to make it absolute, like shown here.
|
||||
#sys.path.append(os.path.abspath('.'))
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '../../'))
|
||||
|
||||
import sqlparse
|
||||
|
||||
# -- General configuration -----------------------------------------------------
|
||||
|
||||
# Add any Sphinx extension module names here, as strings. They can be extensions
|
||||
# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
|
||||
extensions = ['sphinx.ext.autodoc', 'sphinx.ext.todo', 'sphinx.ext.coverage',
|
||||
'sphinx.ext.autosummary']
|
||||
|
||||
# Add any paths that contain templates here, relative to this directory.
|
||||
templates_path = ['_templates']
|
||||
|
||||
# The suffix of source filenames.
|
||||
source_suffix = '.rst'
|
||||
|
||||
# The encoding of source files.
|
||||
#source_encoding = 'utf-8'
|
||||
|
||||
# The master toctree document.
|
||||
master_doc = 'index'
|
||||
|
||||
# General information about the project.
|
||||
project = u'python-sqlparse'
|
||||
copyright = u'%s, Andi Albrecht' % datetime.date.today().strftime('%Y')
|
||||
|
||||
# The version info for the project you're documenting, acts as replacement for
|
||||
# |version| and |release|, also used in various other places throughout the
|
||||
# built documents.
|
||||
#
|
||||
# The short X.Y version.
|
||||
version = sqlparse.__version__
|
||||
# The full version, including alpha/beta/rc tags.
|
||||
release = sqlparse.__version__
|
||||
|
||||
# The language for content autogenerated by Sphinx. Refer to documentation
|
||||
# for a list of supported languages.
|
||||
#language = None
|
||||
|
||||
# There are two options for replacing |today|: either, you set today to some
|
||||
# non-false value, then it is used:
|
||||
#today = ''
|
||||
# Else, today_fmt is used as the format for a strftime call.
|
||||
#today_fmt = '%B %d, %Y'
|
||||
|
||||
# List of documents that shouldn't be included in the build.
|
||||
#unused_docs = []
|
||||
|
||||
# List of directories, relative to source directory, that shouldn't be searched
|
||||
# for source files.
|
||||
exclude_trees = []
|
||||
|
||||
# The reST default role (used for this markup: `text`) to use for all documents.
|
||||
#default_role = None
|
||||
|
||||
# If true, '()' will be appended to :func: etc. cross-reference text.
|
||||
#add_function_parentheses = True
|
||||
|
||||
# If true, the current module name will be prepended to all description
|
||||
# unit titles (such as .. function::).
|
||||
#add_module_names = True
|
||||
|
||||
# If true, sectionauthor and moduleauthor directives will be shown in the
|
||||
# output. They are ignored by default.
|
||||
#show_authors = False
|
||||
|
||||
# The name of the Pygments (syntax highlighting) style to use.
|
||||
pygments_style = 'tango'
|
||||
|
||||
# A list of ignored prefixes for module index sorting.
|
||||
#modindex_common_prefix = []
|
||||
|
||||
|
||||
# -- Options for HTML output ---------------------------------------------------
|
||||
|
||||
# The theme to use for HTML and HTML Help pages. Major themes that come with
|
||||
# Sphinx are currently 'default' and 'sphinxdoc'.
|
||||
#html_theme = 'agogo'
|
||||
|
||||
# Theme options are theme-specific and customize the look and feel of a theme
|
||||
# further. For a list of options available for each theme, see the
|
||||
# documentation.
|
||||
#html_theme_options = {}
|
||||
|
||||
# Add any paths that contain custom themes here, relative to this directory.
|
||||
#html_theme_path = [os.path.abspath('../')]
|
||||
|
||||
# The name for this set of Sphinx documents. If None, it defaults to
|
||||
# "<project> v<release> documentation".
|
||||
#html_title = None
|
||||
|
||||
# A shorter title for the navigation bar. Default is the same as html_title.
|
||||
#html_short_title = None
|
||||
|
||||
# The name of an image file (relative to this directory) to place at the top
|
||||
# of the sidebar.
|
||||
#html_logo = None
|
||||
|
||||
# The name of an image file (within the static path) to use as favicon of the
|
||||
# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
|
||||
# pixels large.
|
||||
#html_favicon = None
|
||||
|
||||
# Add any paths that contain custom static files (such as style sheets) here,
|
||||
# relative to this directory. They are copied after the builtin static files,
|
||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||
#html_static_path = ['_static']
|
||||
|
||||
# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
|
||||
# using the given strftime format.
|
||||
#html_last_updated_fmt = '%b %d, %Y'
|
||||
|
||||
# If true, SmartyPants will be used to convert quotes and dashes to
|
||||
# typographically correct entities.
|
||||
#html_use_smartypants = True
|
||||
|
||||
# Custom sidebar templates, maps document names to template names.
|
||||
#html_sidebars = {}
|
||||
|
||||
# Additional templates that should be rendered to pages, maps page names to
|
||||
# template names.
|
||||
#html_additional_pages = {}
|
||||
|
||||
# If false, no module index is generated.
|
||||
#html_use_modindex = True
|
||||
|
||||
# If false, no index is generated.
|
||||
#html_use_index = True
|
||||
|
||||
# If true, the index is split into individual pages for each letter.
|
||||
#html_split_index = False
|
||||
|
||||
# If true, links to the reST sources are added to the pages.
|
||||
#html_show_sourcelink = True
|
||||
|
||||
# If true, an OpenSearch description file will be output, and all pages will
|
||||
# contain a <link> tag referring to it. The value of this option must be the
|
||||
# base URL from which the finished HTML is served.
|
||||
#html_use_opensearch = ''
|
||||
|
||||
# If nonempty, this is the file name suffix for HTML files (e.g. ".xhtml").
|
||||
#html_file_suffix = ''
|
||||
|
||||
# Output file base name for HTML help builder.
|
||||
htmlhelp_basename = 'python-sqlparsedoc'
|
||||
|
||||
|
||||
# -- Options for LaTeX output --------------------------------------------------
|
||||
|
||||
# The paper size ('letter' or 'a4').
|
||||
#latex_paper_size = 'letter'
|
||||
|
||||
# The font size ('10pt', '11pt' or '12pt').
|
||||
#latex_font_size = '10pt'
|
||||
|
||||
# Grouping the document tree into LaTeX files. List of tuples
|
||||
# (source start file, target name, title, author, documentclass [howto/manual]).
|
||||
latex_documents = [
|
||||
('index', 'python-sqlparse.tex', ur'python-sqlparse Documentation',
|
||||
ur'Andi Albrecht', 'manual'),
|
||||
]
|
||||
|
||||
# The name of an image file (relative to this directory) to place at the top of
|
||||
# the title page.
|
||||
#latex_logo = None
|
||||
|
||||
# For "manual" documents, if this is true, then toplevel headings are parts,
|
||||
# not chapters.
|
||||
#latex_use_parts = False
|
||||
|
||||
# Additional stuff for the LaTeX preamble.
|
||||
#latex_preamble = ''
|
||||
|
||||
# Documents to append as an appendix to all manuals.
|
||||
#latex_appendices = []
|
||||
|
||||
# If false, no module index is generated.
|
||||
#latex_use_modindex = True
|
||||
todo_include_todos = True
|
||||
@@ -1,61 +0,0 @@
|
||||
.. python-sqlparse documentation master file, created by
|
||||
sphinx-quickstart on Thu Feb 26 08:19:28 2009.
|
||||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
python-sqlparse
|
||||
===============
|
||||
|
||||
:mod:`sqlparse` is a non-validating SQL parser for Python.
|
||||
It provides support for parsing, splitting and formatting SQL statements.
|
||||
|
||||
The module is compatible with Python 2 (>= 2.5) and Python 3 (>= 3.2)
|
||||
and released under the terms of the `New BSD license
|
||||
<http://www.opensource.org/licenses/bsd-license.php>`_.
|
||||
|
||||
Visit the project page at https://github.com/andialbrecht/sqlparse for
|
||||
further information about this project.
|
||||
|
||||
|
||||
tl;dr
|
||||
-----
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
$ pip install sqlparse
|
||||
$ python
|
||||
>>> import sqlparse
|
||||
>>> print(sqlparse.format('select * from foo', reindent=True))
|
||||
select *
|
||||
from foo
|
||||
>>> parsed = sqlparse.parse('select * from foo')[0]
|
||||
>>> parsed.tokens
|
||||
[<DML 'select' at 0x7f22c5e15368>, <Whitespace ' ' at 0x7f22c5e153b0>, <Wildcard '*' … ]
|
||||
>>>
|
||||
|
||||
|
||||
Contents
|
||||
--------
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
||||
intro
|
||||
api
|
||||
analyzing
|
||||
ui
|
||||
changes
|
||||
indices
|
||||
|
||||
|
||||
Resources
|
||||
---------
|
||||
|
||||
Project page
|
||||
https://github.com/andialbrecht/sqlparse
|
||||
|
||||
Bug tracker
|
||||
https://github.com/andialbrecht/sqlparse/issues
|
||||
|
||||
Documentation
|
||||
http://sqlparse.readthedocs.org/
|
||||
@@ -1,7 +0,0 @@
|
||||
Indices and tables
|
||||
==================
|
||||
|
||||
* :ref:`genindex`
|
||||
* :ref:`modindex`
|
||||
* :ref:`search`
|
||||
|
||||
@@ -1,143 +0,0 @@
|
||||
Introduction
|
||||
============
|
||||
|
||||
|
||||
Download & Installation
|
||||
-----------------------
|
||||
|
||||
The latest released version can be obtained from the `Python Package
|
||||
Index (PyPI) <http://pypi.python.org/pypi/sqlparse/>`_. To extract the
|
||||
install the module system-wide run
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
$ tar cvfz python-sqlparse-VERSION.tar.gz
|
||||
$ cd python-sqlparse/
|
||||
$ sudo python setup.py install
|
||||
|
||||
Alternatively you can install :mod:`sqlparse` using :command:`pip`:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
$ pip install sqlparse
|
||||
|
||||
|
||||
Getting Started
|
||||
---------------
|
||||
|
||||
The :mod:`sqlparse` module provides three simple functions on module level
|
||||
to achieve some common tasks when working with SQL statements.
|
||||
This section shows some simple usage examples of these functions.
|
||||
|
||||
Let's get started with splitting a string containing one or more SQL
|
||||
statements into a list of single statements using :meth:`~sqlparse.split`:
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
>>> import sqlparse
|
||||
>>> sql = 'select * from foo; select * from bar;'
|
||||
>>> sqlparse.split(sql)
|
||||
[u'select * from foo; ', u'select * from bar;']
|
||||
|
||||
The end of a statement is identified by the occurrence of a semicolon.
|
||||
Semicolons within certain SQL constructs like ``BEGIN ... END`` blocks
|
||||
are handled correctly by the splitting mechanism.
|
||||
|
||||
SQL statements can be beautified by using the :meth:`~sqlarse.format` function.
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
>>> sql = 'select * from foo where id in (select id from bar);'
|
||||
>>> print sqlparse.format(sql, reindent=True, keyword_case='upper')
|
||||
SELECT *
|
||||
FROM foo
|
||||
WHERE id IN
|
||||
(SELECT id
|
||||
FROM bar);
|
||||
|
||||
In this case all keywords in the given SQL are uppercased and the
|
||||
indentation is changed to make it more readable. Read :ref:`formatting` for
|
||||
a full reference of supported options given as keyword arguments
|
||||
to that function.
|
||||
|
||||
Before proceeding with a closer look at the internal representation of
|
||||
SQL statements, you should be aware that this SQL parser is intentionally
|
||||
non-validating. It assumes that the given input is at least some kind
|
||||
of SQL and then it tries to analyze as much as possible without making
|
||||
too much assumptions about the concrete dialect or the actual statement.
|
||||
At least it's up to the user of this API to interpret the results right.
|
||||
|
||||
When using the :meth:`~sqlparse.parse` function a tuple of
|
||||
:class:`~sqlparse.sql.Statement` instances is returned:
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
>>> sql = 'select * from "someschema"."mytable" where id = 1'
|
||||
>>> parsed = sqlparse.parse(sql)
|
||||
>>> parsed
|
||||
(<Statement 'select...' at 0x9ad08ec>,)
|
||||
|
||||
Each item of the tuple is a single statement as identified by the above
|
||||
mentioned :meth:`~sqlparse.split` function. So let's grab the only element
|
||||
from that list and have a look at the ``tokens`` attribute.
|
||||
Sub-tokens are stored in this attribute.
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
>>> stmt = parsed[0] # grab the Statement object
|
||||
>>> stmt.tokens
|
||||
(<DML 'select' at 0x9b63c34>,
|
||||
<Whitespace ' ' at 0x9b63e8c>,
|
||||
<Operator '*' at 0x9b63e64>,
|
||||
<Whitespace ' ' at 0x9b63c5c>,
|
||||
<Keyword 'from' at 0x9b63c84>,
|
||||
<Whitespace ' ' at 0x9b63cd4>,
|
||||
<Identifier '"somes...' at 0x9b5c62c>,
|
||||
<Whitespace ' ' at 0x9b63f04>,
|
||||
<Where 'where ...' at 0x9b5caac>)
|
||||
|
||||
Each object can be converted back to a string at any time:
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
>>> unicode(stmt) # str(stmt) for Python 3
|
||||
u'select * from "someschema"."mytable" where id = 1'
|
||||
>>> unicode(stmt.tokens[-1]) # or just the WHERE part
|
||||
u'where id = 1'
|
||||
|
||||
Details of the returned objects are described in :ref:`analyze`.
|
||||
|
||||
|
||||
Development & Contributing
|
||||
--------------------------
|
||||
|
||||
To check out the latest sources of this module run
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
$ git clone git://github.com/andialbrecht/sqlparse.git
|
||||
|
||||
|
||||
to check out the latest sources from the repository.
|
||||
|
||||
:mod:`sqlparse` is currently tested under Python 2.5, 2.6, 2.7, 3.2 and
|
||||
pypy. Tests are automatically run on each commit and for each pull
|
||||
request on Travis: https://travis-ci.org/andialbrecht/sqlparse
|
||||
|
||||
Make sure to run the test suite before sending a pull request by running
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
$ tox
|
||||
|
||||
It's ok, if :command:`tox` doesn't find all interpreters listed
|
||||
above. Ideally a Python 2 and a Python 3 version should be tested
|
||||
locally.
|
||||
|
||||
Please file bug reports and feature requests on the project site at
|
||||
https://github.com/andialbrecht/sqlparse/issues/new or if you have
|
||||
code to contribute upload it to http://codereview.appspot.com and
|
||||
add albrecht.andi@googlemail.com as reviewer.
|
||||
|
||||
For more information about the review tool and how to use it visit
|
||||
it's project page: http://code.google.com/p/rietveld.
|
||||
@@ -1,15 +0,0 @@
|
||||
User Interfaces
|
||||
===============
|
||||
|
||||
``sqlformat``
|
||||
The ``sqlformat`` command line script ist distributed with the module.
|
||||
Run :command:`sqlformat --help` to list available options and for usage
|
||||
hints.
|
||||
|
||||
``sqlformat.appspot.com``
|
||||
An example `Google App Engine <http://code.google.com/appengine/>`_
|
||||
application that exposes the formatting features using a web front-end.
|
||||
See http://sqlformat.appspot.com for details.
|
||||
The source for this application is available from a source code check out
|
||||
of the :mod:`sqlparse` module (see :file:`extras/appengine`).
|
||||
|
||||
@@ -1,65 +0,0 @@
|
||||
.\" Based on template /usr/share/man-db/examples/manpage.example provided by
|
||||
.\" Tom Christiansen <tchrist@jhereg.perl.com>.
|
||||
.TH SQLFORMAT "1" "December 2010" "python-sqlparse version: 0.1.2" "User Commands"
|
||||
.SH NAME
|
||||
sqlformat \- reformat SQL
|
||||
.SH SYNOPSIS
|
||||
.PP
|
||||
.B sqlformat
|
||||
[
|
||||
.I "OPTION"
|
||||
] ... [
|
||||
.I "FILE"
|
||||
] ...
|
||||
.SH DESCRIPTION
|
||||
.\" Putting a newline after each sentence can generate better output.
|
||||
The `sqlformat' command-line tool can be used to reformat SQL file according to
|
||||
specified options or prepare a snippet in in some programming language (only
|
||||
Python and PHP currently supported).
|
||||
Use "-" for
|
||||
.I FILE
|
||||
to read from stdin.
|
||||
.SH OPTIONS
|
||||
.TP
|
||||
\fB\-i\fR \fICHOICE\fR|\fB\-\-identifiers\fR=\fIFORMAT\fR
|
||||
Change case of identifiers.
|
||||
.I FORMAT
|
||||
is one of "upper", "lower", "capitalize".
|
||||
.TP
|
||||
\fB\-k\fR \fICHOICE\fR|\fB\-\-keywords\fR=\fIFORMAT\fR
|
||||
Change case of keywords.
|
||||
.I FORMAT
|
||||
is one of "upper", "lower", "capitalize".
|
||||
.TP
|
||||
\fB\-l\fR \fICHOICE\fR|\fB\-\-language\fR=\fILANG\fR
|
||||
Output a snippet in programming language LANG.
|
||||
.I LANG
|
||||
can be "python", "php".
|
||||
.TP
|
||||
\fB\-o\fR \fIFILE\fR|\fB\-\-outfile\fR=\fIFILE\fR
|
||||
Write output to
|
||||
.I FILE
|
||||
(defaults to stdout).
|
||||
.TP
|
||||
.BR \-r | \-\-reindent
|
||||
Reindent statements.
|
||||
.TP
|
||||
\fB\-\-indent_width\fR=\fIINDENT_WIDTH\fR
|
||||
Set indent width to
|
||||
.IR INDENT_WIDTH .
|
||||
Default is 2 spaces.
|
||||
.TP
|
||||
\fB\-\-strip\-comments
|
||||
Remove comments.
|
||||
.TP
|
||||
.BR \-h | \-\-help
|
||||
Print a short help message and exit.
|
||||
All subsequent options are ignored.
|
||||
.TP
|
||||
.BR --verbose
|
||||
Verbose output.
|
||||
.TP
|
||||
.BR \-\-version
|
||||
Print program's version number and exit.
|
||||
.SH AUTHORS
|
||||
This man page was written by Andriy Senkovych <jolly_roger@itblog.org.ua>
|
||||
@@ -1,6 +0,0 @@
|
||||
[pytest]
|
||||
pep8ignore =
|
||||
extras/* ALL
|
||||
examples/* ALL
|
||||
docs/* ALL
|
||||
* E125 E127
|
||||
@@ -1,80 +0,0 @@
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
|
||||
"""filter"""
|
||||
|
||||
from sqlparse import lexer
|
||||
from sqlparse.engine import grouping
|
||||
from sqlparse.engine.filter import StatementFilter
|
||||
|
||||
# XXX remove this when cleanup is complete
|
||||
Filter = object
|
||||
|
||||
|
||||
class FilterStack(object):
|
||||
|
||||
def __init__(self):
|
||||
self.preprocess = []
|
||||
self.stmtprocess = []
|
||||
self.postprocess = []
|
||||
self.split_statements = False
|
||||
self._grouping = False
|
||||
|
||||
def _flatten(self, stream):
|
||||
for token in stream:
|
||||
if token.is_group():
|
||||
for t in self._flatten(token.tokens):
|
||||
yield t
|
||||
else:
|
||||
yield token
|
||||
|
||||
def enable_grouping(self):
|
||||
self._grouping = True
|
||||
|
||||
def full_analyze(self):
|
||||
self.enable_grouping()
|
||||
|
||||
def run(self, sql, encoding=None):
|
||||
stream = lexer.tokenize(sql, encoding)
|
||||
# Process token stream
|
||||
if self.preprocess:
|
||||
for filter_ in self.preprocess:
|
||||
stream = filter_.process(self, stream)
|
||||
|
||||
if (self.stmtprocess or self.postprocess or self.split_statements
|
||||
or self._grouping):
|
||||
splitter = StatementFilter()
|
||||
stream = splitter.process(self, stream)
|
||||
|
||||
if self._grouping:
|
||||
|
||||
def _group(stream):
|
||||
for stmt in stream:
|
||||
grouping.group(stmt)
|
||||
yield stmt
|
||||
stream = _group(stream)
|
||||
|
||||
if self.stmtprocess:
|
||||
|
||||
def _run1(stream):
|
||||
ret = []
|
||||
for stmt in stream:
|
||||
for filter_ in self.stmtprocess:
|
||||
filter_.process(self, stmt)
|
||||
ret.append(stmt)
|
||||
return ret
|
||||
stream = _run1(stream)
|
||||
|
||||
if self.postprocess:
|
||||
|
||||
def _run2(stream):
|
||||
for stmt in stream:
|
||||
stmt.tokens = list(self._flatten(stmt.tokens))
|
||||
for filter_ in self.postprocess:
|
||||
stmt = filter_.process(self, stmt)
|
||||
yield stmt
|
||||
stream = _run2(stream)
|
||||
|
||||
return stream
|
||||
@@ -1,112 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
from sqlparse.sql import Statement, Token
|
||||
from sqlparse import tokens as T
|
||||
|
||||
|
||||
class StatementFilter:
|
||||
"Filter that split stream at individual statements"
|
||||
|
||||
def __init__(self):
|
||||
self._in_declare = False
|
||||
self._in_dbldollar = False
|
||||
self._is_create = False
|
||||
self._begin_depth = 0
|
||||
|
||||
def _reset(self):
|
||||
"Set the filter attributes to its default values"
|
||||
self._in_declare = False
|
||||
self._in_dbldollar = False
|
||||
self._is_create = False
|
||||
self._begin_depth = 0
|
||||
|
||||
def _change_splitlevel(self, ttype, value):
|
||||
"Get the new split level (increase, decrease or remain equal)"
|
||||
# PostgreSQL
|
||||
if (ttype == T.Name.Builtin
|
||||
and value.startswith('$') and value.endswith('$')):
|
||||
if self._in_dbldollar:
|
||||
self._in_dbldollar = False
|
||||
return -1
|
||||
else:
|
||||
self._in_dbldollar = True
|
||||
return 1
|
||||
elif self._in_dbldollar:
|
||||
return 0
|
||||
|
||||
# ANSI
|
||||
if ttype not in T.Keyword:
|
||||
return 0
|
||||
|
||||
unified = value.upper()
|
||||
|
||||
if unified == 'DECLARE' and self._is_create and self._begin_depth == 0:
|
||||
self._in_declare = True
|
||||
return 1
|
||||
|
||||
if unified == 'BEGIN':
|
||||
self._begin_depth += 1
|
||||
if self._in_declare or self._is_create:
|
||||
# FIXME(andi): This makes no sense.
|
||||
return 1
|
||||
return 0
|
||||
|
||||
if unified in ('END IF', 'END FOR'):
|
||||
return -1
|
||||
|
||||
if unified == 'END':
|
||||
# Should this respect a preceeding BEGIN?
|
||||
# In CASE ... WHEN ... END this results in a split level -1.
|
||||
self._begin_depth = max(0, self._begin_depth - 1)
|
||||
return -1
|
||||
|
||||
if ttype is T.Keyword.DDL and unified.startswith('CREATE'):
|
||||
self._is_create = True
|
||||
return 0
|
||||
|
||||
if (unified in ('IF', 'FOR')
|
||||
and self._is_create and self._begin_depth > 0):
|
||||
return 1
|
||||
|
||||
# Default
|
||||
return 0
|
||||
|
||||
def process(self, stack, stream):
|
||||
"Process the stream"
|
||||
consume_ws = False
|
||||
splitlevel = 0
|
||||
stmt = None
|
||||
stmt_tokens = []
|
||||
|
||||
# Run over all stream tokens
|
||||
for ttype, value in stream:
|
||||
# Yield token if we finished a statement and there's no whitespaces
|
||||
if consume_ws and ttype not in (T.Whitespace, T.Comment.Single):
|
||||
stmt.tokens = stmt_tokens
|
||||
yield stmt
|
||||
|
||||
# Reset filter and prepare to process next statement
|
||||
self._reset()
|
||||
consume_ws = False
|
||||
splitlevel = 0
|
||||
stmt = None
|
||||
|
||||
# Create a new statement if we are not currently in one of them
|
||||
if stmt is None:
|
||||
stmt = Statement()
|
||||
stmt_tokens = []
|
||||
|
||||
# Change current split level (increase, decrease or remain equal)
|
||||
splitlevel += self._change_splitlevel(ttype, value)
|
||||
|
||||
# Append the token to the current statement
|
||||
stmt_tokens.append(Token(ttype, value))
|
||||
|
||||
# Check if we get the end of a statement
|
||||
if splitlevel <= 0 and ttype is T.Punctuation and value == ';':
|
||||
consume_ws = True
|
||||
|
||||
# Yield pending statement (if any)
|
||||
if stmt is not None:
|
||||
stmt.tokens = stmt_tokens
|
||||
yield stmt
|
||||
@@ -1,461 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import itertools
|
||||
|
||||
from sqlparse import sql
|
||||
from sqlparse import tokens as T
|
||||
|
||||
try:
|
||||
next
|
||||
except NameError: # Python < 2.6
|
||||
next = lambda i: i.next()
|
||||
|
||||
|
||||
def _group_left_right(tlist, ttype, value, cls,
|
||||
check_right=lambda t: True,
|
||||
check_left=lambda t: True,
|
||||
include_semicolon=False):
|
||||
[_group_left_right(sgroup, ttype, value, cls, check_right, check_left,
|
||||
include_semicolon) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, cls)]
|
||||
idx = 0
|
||||
token = tlist.token_next_match(idx, ttype, value)
|
||||
while token:
|
||||
right = tlist.token_next(tlist.token_index(token))
|
||||
left = tlist.token_prev(tlist.token_index(token))
|
||||
if right is None or not check_right(right):
|
||||
token = tlist.token_next_match(tlist.token_index(token) + 1,
|
||||
ttype, value)
|
||||
elif left is None or not check_left(left):
|
||||
token = tlist.token_next_match(tlist.token_index(token) + 1,
|
||||
ttype, value)
|
||||
else:
|
||||
if include_semicolon:
|
||||
sright = tlist.token_next_match(tlist.token_index(right),
|
||||
T.Punctuation, ';')
|
||||
if sright is not None:
|
||||
# only overwrite "right" if a semicolon is actually
|
||||
# present.
|
||||
right = sright
|
||||
tokens = tlist.tokens_between(left, right)[1:]
|
||||
if not isinstance(left, cls):
|
||||
new = cls([left])
|
||||
new_idx = tlist.token_index(left)
|
||||
tlist.tokens.remove(left)
|
||||
tlist.tokens.insert(new_idx, new)
|
||||
left = new
|
||||
left.tokens.extend(tokens)
|
||||
for t in tokens:
|
||||
tlist.tokens.remove(t)
|
||||
token = tlist.token_next_match(tlist.token_index(left) + 1,
|
||||
ttype, value)
|
||||
|
||||
|
||||
def _find_matching(idx, tlist, start_ttype, start_value, end_ttype, end_value):
|
||||
depth = 1
|
||||
for tok in tlist.tokens[idx:]:
|
||||
if tok.match(start_ttype, start_value):
|
||||
depth += 1
|
||||
elif tok.match(end_ttype, end_value):
|
||||
depth -= 1
|
||||
if depth == 1:
|
||||
return tok
|
||||
return None
|
||||
|
||||
|
||||
def _group_matching(tlist, start_ttype, start_value, end_ttype, end_value,
|
||||
cls, include_semicolon=False, recurse=False):
|
||||
|
||||
[_group_matching(sgroup, start_ttype, start_value, end_ttype, end_value,
|
||||
cls, include_semicolon) for sgroup in tlist.get_sublists()
|
||||
if recurse]
|
||||
if isinstance(tlist, cls):
|
||||
idx = 1
|
||||
else:
|
||||
idx = 0
|
||||
token = tlist.token_next_match(idx, start_ttype, start_value)
|
||||
while token:
|
||||
tidx = tlist.token_index(token)
|
||||
end = _find_matching(tidx, tlist, start_ttype, start_value,
|
||||
end_ttype, end_value)
|
||||
if end is None:
|
||||
idx = tidx + 1
|
||||
else:
|
||||
if include_semicolon:
|
||||
next_ = tlist.token_next(tlist.token_index(end))
|
||||
if next_ and next_.match(T.Punctuation, ';'):
|
||||
end = next_
|
||||
group = tlist.group_tokens(cls, tlist.tokens_between(token, end))
|
||||
_group_matching(group, start_ttype, start_value,
|
||||
end_ttype, end_value, cls, include_semicolon)
|
||||
idx = tlist.token_index(group) + 1
|
||||
token = tlist.token_next_match(idx, start_ttype, start_value)
|
||||
|
||||
|
||||
def group_if(tlist):
|
||||
_group_matching(tlist, T.Keyword, 'IF', T.Keyword, 'END IF', sql.If, True)
|
||||
|
||||
|
||||
def group_for(tlist):
|
||||
_group_matching(tlist, T.Keyword, 'FOR', T.Keyword, 'END LOOP',
|
||||
sql.For, True)
|
||||
|
||||
|
||||
def group_foreach(tlist):
|
||||
_group_matching(tlist, T.Keyword, 'FOREACH', T.Keyword, 'END LOOP',
|
||||
sql.For, True)
|
||||
|
||||
|
||||
def group_begin(tlist):
|
||||
_group_matching(tlist, T.Keyword, 'BEGIN', T.Keyword, 'END',
|
||||
sql.Begin, True)
|
||||
|
||||
|
||||
def group_as(tlist):
|
||||
|
||||
def _right_valid(token):
|
||||
# Currently limited to DML/DDL. Maybe additional more non SQL reserved
|
||||
# keywords should appear here (see issue8).
|
||||
return not token.ttype in (T.DML, T.DDL)
|
||||
|
||||
def _left_valid(token):
|
||||
if token.ttype is T.Keyword and token.value in ('NULL',):
|
||||
return True
|
||||
return token.ttype is not T.Keyword
|
||||
|
||||
_group_left_right(tlist, T.Keyword, 'AS', sql.Identifier,
|
||||
check_right=_right_valid,
|
||||
check_left=_left_valid)
|
||||
|
||||
|
||||
def group_assignment(tlist):
|
||||
_group_left_right(tlist, T.Assignment, ':=', sql.Assignment,
|
||||
include_semicolon=True)
|
||||
|
||||
|
||||
def group_comparison(tlist):
|
||||
|
||||
def _parts_valid(token):
|
||||
return (token.ttype in (T.String.Symbol, T.String.Single,
|
||||
T.Name, T.Number, T.Number.Float,
|
||||
T.Number.Integer, T.Literal,
|
||||
T.Literal.Number.Integer, T.Name.Placeholder)
|
||||
or isinstance(token, (sql.Identifier, sql.Parenthesis))
|
||||
or (token.ttype is T.Keyword
|
||||
and token.value.upper() in ['NULL', ]))
|
||||
_group_left_right(tlist, T.Operator.Comparison, None, sql.Comparison,
|
||||
check_left=_parts_valid, check_right=_parts_valid)
|
||||
|
||||
|
||||
def group_case(tlist):
|
||||
_group_matching(tlist, T.Keyword, 'CASE', T.Keyword, 'END', sql.Case,
|
||||
include_semicolon=True, recurse=True)
|
||||
|
||||
|
||||
def group_identifier(tlist):
|
||||
def _consume_cycle(tl, i):
|
||||
# TODO: Usage of Wildcard token is ambivalent here.
|
||||
x = itertools.cycle((
|
||||
lambda y: (y.match(T.Punctuation, '.')
|
||||
or y.ttype in (T.Operator,
|
||||
T.Wildcard,
|
||||
T.Name)
|
||||
or isinstance(y, sql.SquareBrackets)),
|
||||
lambda y: (y.ttype in (T.String.Symbol,
|
||||
T.Name,
|
||||
T.Wildcard,
|
||||
T.Literal.String.Single,
|
||||
T.Literal.Number.Integer,
|
||||
T.Literal.Number.Float)
|
||||
or isinstance(y, (sql.Parenthesis,
|
||||
sql.SquareBrackets,
|
||||
sql.Function)))))
|
||||
for t in tl.tokens[i:]:
|
||||
# Don't take whitespaces into account.
|
||||
if t.ttype is T.Whitespace:
|
||||
yield t
|
||||
continue
|
||||
if next(x)(t):
|
||||
yield t
|
||||
else:
|
||||
if isinstance(t, sql.Comment) and t.is_multiline():
|
||||
yield t
|
||||
return
|
||||
|
||||
def _next_token(tl, i):
|
||||
# chooses the next token. if two tokens are found then the
|
||||
# first is returned.
|
||||
t1 = tl.token_next_by_type(
|
||||
i, (T.String.Symbol, T.Name, T.Literal.Number.Integer,
|
||||
T.Literal.Number.Float))
|
||||
|
||||
i1 = tl.token_index(t1, start=i) if t1 else None
|
||||
t2_end = None if i1 is None else i1 + 1
|
||||
t2 = tl.token_next_by_instance(i, (sql.Function, sql.Parenthesis), end=t2_end)
|
||||
|
||||
if t1 and t2:
|
||||
i2 = tl.token_index(t2, start=i)
|
||||
if i1 > i2:
|
||||
return t2
|
||||
else:
|
||||
return t1
|
||||
elif t1:
|
||||
return t1
|
||||
else:
|
||||
return t2
|
||||
|
||||
# bottom up approach: group subgroups first
|
||||
[group_identifier(sgroup) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, sql.Identifier)]
|
||||
|
||||
# real processing
|
||||
idx = 0
|
||||
token = _next_token(tlist, idx)
|
||||
while token:
|
||||
identifier_tokens = [token] + list(
|
||||
_consume_cycle(tlist,
|
||||
tlist.token_index(token, start=idx) + 1))
|
||||
# remove trailing whitespace
|
||||
if identifier_tokens and identifier_tokens[-1].ttype is T.Whitespace:
|
||||
identifier_tokens = identifier_tokens[:-1]
|
||||
if not (len(identifier_tokens) == 1
|
||||
and (isinstance(identifier_tokens[0], (sql.Function, sql.Parenthesis))
|
||||
or identifier_tokens[0].ttype in (T.Literal.Number.Integer,
|
||||
T.Literal.Number.Float))):
|
||||
group = tlist.group_tokens(sql.Identifier, identifier_tokens)
|
||||
idx = tlist.token_index(group, start=idx) + 1
|
||||
else:
|
||||
idx += 1
|
||||
token = _next_token(tlist, idx)
|
||||
|
||||
|
||||
def group_identifier_list(tlist):
|
||||
[group_identifier_list(sgroup) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, sql.IdentifierList)]
|
||||
# Allowed list items
|
||||
fend1_funcs = [lambda t: isinstance(t, (sql.Identifier, sql.Function,
|
||||
sql.Case)),
|
||||
lambda t: t.is_whitespace(),
|
||||
lambda t: t.ttype == T.Name,
|
||||
lambda t: t.ttype == T.Wildcard,
|
||||
lambda t: t.match(T.Keyword, 'null'),
|
||||
lambda t: t.match(T.Keyword, 'role'),
|
||||
lambda t: t.ttype == T.Number.Integer,
|
||||
lambda t: t.ttype == T.String.Single,
|
||||
lambda t: t.ttype == T.Name.Placeholder,
|
||||
lambda t: t.ttype == T.Keyword,
|
||||
lambda t: isinstance(t, sql.Comparison),
|
||||
lambda t: isinstance(t, sql.Comment),
|
||||
lambda t: t.ttype == T.Comment.Multiline,
|
||||
]
|
||||
tcomma = tlist.token_next_match(0, T.Punctuation, ',')
|
||||
start = None
|
||||
while tcomma is not None:
|
||||
# Go back one idx to make sure to find the correct tcomma
|
||||
idx = tlist.token_index(tcomma)
|
||||
before = tlist.token_prev(idx)
|
||||
after = tlist.token_next(idx)
|
||||
# Check if the tokens around tcomma belong to a list
|
||||
bpassed = apassed = False
|
||||
for func in fend1_funcs:
|
||||
if before is not None and func(before):
|
||||
bpassed = True
|
||||
if after is not None and func(after):
|
||||
apassed = True
|
||||
if not bpassed or not apassed:
|
||||
# Something's wrong here, skip ahead to next ","
|
||||
start = None
|
||||
tcomma = tlist.token_next_match(idx + 1,
|
||||
T.Punctuation, ',')
|
||||
else:
|
||||
if start is None:
|
||||
start = before
|
||||
after_idx = tlist.token_index(after, start=idx)
|
||||
next_ = tlist.token_next(after_idx)
|
||||
if next_ is None or not next_.match(T.Punctuation, ','):
|
||||
# Reached the end of the list
|
||||
tokens = tlist.tokens_between(start, after)
|
||||
group = tlist.group_tokens(sql.IdentifierList, tokens)
|
||||
start = None
|
||||
tcomma = tlist.token_next_match(tlist.token_index(group) + 1,
|
||||
T.Punctuation, ',')
|
||||
else:
|
||||
tcomma = next_
|
||||
|
||||
|
||||
def group_brackets(tlist):
|
||||
"""Group parentheses () or square brackets []
|
||||
|
||||
This is just like _group_matching, but complicated by the fact that
|
||||
round brackets can contain square bracket groups and vice versa
|
||||
"""
|
||||
|
||||
if isinstance(tlist, (sql.Parenthesis, sql.SquareBrackets)):
|
||||
idx = 1
|
||||
else:
|
||||
idx = 0
|
||||
|
||||
# Find the first opening bracket
|
||||
token = tlist.token_next_match(idx, T.Punctuation, ['(', '['])
|
||||
|
||||
while token:
|
||||
start_val = token.value # either '(' or '['
|
||||
if start_val == '(':
|
||||
end_val = ')'
|
||||
group_class = sql.Parenthesis
|
||||
else:
|
||||
end_val = ']'
|
||||
group_class = sql.SquareBrackets
|
||||
|
||||
tidx = tlist.token_index(token)
|
||||
|
||||
# Find the corresponding closing bracket
|
||||
end = _find_matching(tidx, tlist, T.Punctuation, start_val,
|
||||
T.Punctuation, end_val)
|
||||
|
||||
if end is None:
|
||||
idx = tidx + 1
|
||||
else:
|
||||
group = tlist.group_tokens(group_class,
|
||||
tlist.tokens_between(token, end))
|
||||
|
||||
# Check for nested bracket groups within this group
|
||||
group_brackets(group)
|
||||
idx = tlist.token_index(group) + 1
|
||||
|
||||
# Find the next opening bracket
|
||||
token = tlist.token_next_match(idx, T.Punctuation, ['(', '['])
|
||||
|
||||
|
||||
def group_comments(tlist):
|
||||
[group_comments(sgroup) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, sql.Comment)]
|
||||
idx = 0
|
||||
token = tlist.token_next_by_type(idx, T.Comment)
|
||||
while token:
|
||||
tidx = tlist.token_index(token)
|
||||
end = tlist.token_not_matching(tidx + 1,
|
||||
[lambda t: t.ttype in T.Comment,
|
||||
lambda t: t.is_whitespace()])
|
||||
if end is None:
|
||||
idx = tidx + 1
|
||||
else:
|
||||
eidx = tlist.token_index(end)
|
||||
grp_tokens = tlist.tokens_between(token,
|
||||
tlist.token_prev(eidx, False))
|
||||
group = tlist.group_tokens(sql.Comment, grp_tokens)
|
||||
idx = tlist.token_index(group)
|
||||
token = tlist.token_next_by_type(idx, T.Comment)
|
||||
|
||||
|
||||
def group_where(tlist):
|
||||
[group_where(sgroup) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, sql.Where)]
|
||||
idx = 0
|
||||
token = tlist.token_next_match(idx, T.Keyword, 'WHERE')
|
||||
stopwords = ('ORDER', 'GROUP', 'LIMIT', 'UNION', 'EXCEPT', 'HAVING')
|
||||
while token:
|
||||
tidx = tlist.token_index(token)
|
||||
end = tlist.token_next_match(tidx + 1, T.Keyword, stopwords)
|
||||
if end is None:
|
||||
end = tlist._groupable_tokens[-1]
|
||||
else:
|
||||
end = tlist.tokens[tlist.token_index(end) - 1]
|
||||
group = tlist.group_tokens(sql.Where,
|
||||
tlist.tokens_between(token, end),
|
||||
ignore_ws=True)
|
||||
idx = tlist.token_index(group)
|
||||
token = tlist.token_next_match(idx, T.Keyword, 'WHERE')
|
||||
|
||||
|
||||
def group_aliased(tlist):
|
||||
clss = (sql.Identifier, sql.Function, sql.Case)
|
||||
[group_aliased(sgroup) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, clss)]
|
||||
idx = 0
|
||||
token = tlist.token_next_by_instance(idx, clss)
|
||||
while token:
|
||||
next_ = tlist.token_next(tlist.token_index(token))
|
||||
if next_ is not None and isinstance(next_, clss):
|
||||
if not next_.value.upper().startswith('VARCHAR'):
|
||||
grp = tlist.tokens_between(token, next_)[1:]
|
||||
token.tokens.extend(grp)
|
||||
for t in grp:
|
||||
tlist.tokens.remove(t)
|
||||
idx = tlist.token_index(token) + 1
|
||||
token = tlist.token_next_by_instance(idx, clss)
|
||||
|
||||
|
||||
def group_typecasts(tlist):
|
||||
_group_left_right(tlist, T.Punctuation, '::', sql.Identifier)
|
||||
|
||||
|
||||
def group_functions(tlist):
|
||||
[group_functions(sgroup) for sgroup in tlist.get_sublists()
|
||||
if not isinstance(sgroup, sql.Function)]
|
||||
idx = 0
|
||||
token = tlist.token_next_by_type(idx, T.Name)
|
||||
while token:
|
||||
next_ = tlist.token_next(token)
|
||||
if not isinstance(next_, sql.Parenthesis):
|
||||
idx = tlist.token_index(token) + 1
|
||||
else:
|
||||
func = tlist.group_tokens(sql.Function,
|
||||
tlist.tokens_between(token, next_))
|
||||
idx = tlist.token_index(func) + 1
|
||||
token = tlist.token_next_by_type(idx, T.Name)
|
||||
|
||||
|
||||
def group_order(tlist):
|
||||
idx = 0
|
||||
token = tlist.token_next_by_type(idx, T.Keyword.Order)
|
||||
while token:
|
||||
prev = tlist.token_prev(token)
|
||||
if isinstance(prev, sql.Identifier):
|
||||
ido = tlist.group_tokens(sql.Identifier,
|
||||
tlist.tokens_between(prev, token))
|
||||
idx = tlist.token_index(ido) + 1
|
||||
else:
|
||||
idx = tlist.token_index(token) + 1
|
||||
token = tlist.token_next_by_type(idx, T.Keyword.Order)
|
||||
|
||||
|
||||
def align_comments(tlist):
|
||||
[align_comments(sgroup) for sgroup in tlist.get_sublists()]
|
||||
idx = 0
|
||||
token = tlist.token_next_by_instance(idx, sql.Comment)
|
||||
while token:
|
||||
before = tlist.token_prev(tlist.token_index(token))
|
||||
if isinstance(before, sql.TokenList):
|
||||
grp = tlist.tokens_between(before, token)[1:]
|
||||
before.tokens.extend(grp)
|
||||
for t in grp:
|
||||
tlist.tokens.remove(t)
|
||||
idx = tlist.token_index(before) + 1
|
||||
else:
|
||||
idx = tlist.token_index(token) + 1
|
||||
token = tlist.token_next_by_instance(idx, sql.Comment)
|
||||
|
||||
|
||||
def group(tlist):
|
||||
for func in [
|
||||
group_comments,
|
||||
group_brackets,
|
||||
group_functions,
|
||||
group_where,
|
||||
group_case,
|
||||
group_identifier,
|
||||
group_order,
|
||||
group_typecasts,
|
||||
group_as,
|
||||
group_aliased,
|
||||
group_assignment,
|
||||
group_comparison,
|
||||
align_comments,
|
||||
group_identifier_list,
|
||||
group_if,
|
||||
group_for,
|
||||
group_foreach,
|
||||
group_begin,
|
||||
]:
|
||||
func(tlist)
|
||||
@@ -1,728 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
|
||||
from os.path import abspath, join
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.engine import FilterStack
|
||||
from sqlparse.lexer import tokenize
|
||||
from sqlparse.pipeline import Pipeline
|
||||
from sqlparse.tokens import (Comment, Comparison, Keyword, Name, Punctuation,
|
||||
String, Whitespace)
|
||||
from sqlparse.utils import memoize_generator
|
||||
from sqlparse.utils import split_unquoted_newlines
|
||||
|
||||
|
||||
# --------------------------
|
||||
# token process
|
||||
|
||||
class _CaseFilter:
|
||||
|
||||
ttype = None
|
||||
|
||||
def __init__(self, case=None):
|
||||
if case is None:
|
||||
case = 'upper'
|
||||
assert case in ['lower', 'upper', 'capitalize']
|
||||
self.convert = getattr(unicode, case)
|
||||
|
||||
def process(self, stack, stream):
|
||||
for ttype, value in stream:
|
||||
if ttype in self.ttype:
|
||||
value = self.convert(value)
|
||||
yield ttype, value
|
||||
|
||||
|
||||
class KeywordCaseFilter(_CaseFilter):
|
||||
ttype = T.Keyword
|
||||
|
||||
|
||||
class IdentifierCaseFilter(_CaseFilter):
|
||||
ttype = (T.Name, T.String.Symbol)
|
||||
|
||||
def process(self, stack, stream):
|
||||
for ttype, value in stream:
|
||||
if ttype in self.ttype and not value.strip()[0] == '"':
|
||||
value = self.convert(value)
|
||||
yield ttype, value
|
||||
|
||||
|
||||
class TruncateStringFilter:
|
||||
|
||||
def __init__(self, width, char):
|
||||
self.width = max(width, 1)
|
||||
self.char = unicode(char)
|
||||
|
||||
def process(self, stack, stream):
|
||||
for ttype, value in stream:
|
||||
if ttype is T.Literal.String.Single:
|
||||
if value[:2] == '\'\'':
|
||||
inner = value[2:-2]
|
||||
quote = u'\'\''
|
||||
else:
|
||||
inner = value[1:-1]
|
||||
quote = u'\''
|
||||
if len(inner) > self.width:
|
||||
value = u''.join((quote, inner[:self.width], self.char,
|
||||
quote))
|
||||
yield ttype, value
|
||||
|
||||
|
||||
class GetComments:
|
||||
"""Get the comments from a stack"""
|
||||
def process(self, stack, stream):
|
||||
for token_type, value in stream:
|
||||
if token_type in Comment:
|
||||
yield token_type, value
|
||||
|
||||
|
||||
class StripComments:
|
||||
"""Strip the comments from a stack"""
|
||||
def process(self, stack, stream):
|
||||
for token_type, value in stream:
|
||||
if token_type not in Comment:
|
||||
yield token_type, value
|
||||
|
||||
|
||||
def StripWhitespace(stream):
|
||||
"Strip the useless whitespaces from a stream leaving only the minimal ones"
|
||||
last_type = None
|
||||
has_space = False
|
||||
ignore_group = frozenset((Comparison, Punctuation))
|
||||
|
||||
for token_type, value in stream:
|
||||
# We got a previous token (not empty first ones)
|
||||
if last_type:
|
||||
if token_type in Whitespace:
|
||||
has_space = True
|
||||
continue
|
||||
|
||||
# Ignore first empty spaces and dot-commas
|
||||
elif token_type in (Whitespace, Whitespace.Newline, ignore_group):
|
||||
continue
|
||||
|
||||
# Yield a whitespace if it can't be ignored
|
||||
if has_space:
|
||||
if not ignore_group.intersection((last_type, token_type)):
|
||||
yield Whitespace, ' '
|
||||
has_space = False
|
||||
|
||||
# Yield the token and set its type for checking with the next one
|
||||
yield token_type, value
|
||||
last_type = token_type
|
||||
|
||||
|
||||
class IncludeStatement:
|
||||
"""Filter that enable a INCLUDE statement"""
|
||||
|
||||
def __init__(self, dirpath=".", maxrecursive=10, raiseexceptions=False):
|
||||
if maxrecursive <= 0:
|
||||
raise ValueError('Max recursion limit reached')
|
||||
|
||||
self.dirpath = abspath(dirpath)
|
||||
self.maxRecursive = maxrecursive
|
||||
self.raiseexceptions = raiseexceptions
|
||||
|
||||
self.detected = False
|
||||
|
||||
@memoize_generator
|
||||
def process(self, stack, stream):
|
||||
# Run over all tokens in the stream
|
||||
for token_type, value in stream:
|
||||
# INCLUDE statement found, set detected mode
|
||||
if token_type in Name and value.upper() == 'INCLUDE':
|
||||
self.detected = True
|
||||
continue
|
||||
|
||||
# INCLUDE statement was found, parse it
|
||||
elif self.detected:
|
||||
# Omit whitespaces
|
||||
if token_type in Whitespace:
|
||||
continue
|
||||
|
||||
# Found file path to include
|
||||
if token_type in String.Symbol:
|
||||
# if token_type in tokens.String.Symbol:
|
||||
|
||||
# Get path of file to include
|
||||
path = join(self.dirpath, value[1:-1])
|
||||
|
||||
try:
|
||||
f = open(path)
|
||||
raw_sql = f.read()
|
||||
f.close()
|
||||
|
||||
# There was a problem loading the include file
|
||||
except IOError, err:
|
||||
# Raise the exception to the interpreter
|
||||
if self.raiseexceptions:
|
||||
raise
|
||||
|
||||
# Put the exception as a comment on the SQL code
|
||||
yield Comment, u'-- IOError: %s\n' % err
|
||||
|
||||
else:
|
||||
# Create new FilterStack to parse readed file
|
||||
# and add all its tokens to the main stack recursively
|
||||
try:
|
||||
filtr = IncludeStatement(self.dirpath,
|
||||
self.maxRecursive - 1,
|
||||
self.raiseexceptions)
|
||||
|
||||
# Max recursion limit reached
|
||||
except ValueError, err:
|
||||
# Raise the exception to the interpreter
|
||||
if self.raiseexceptions:
|
||||
raise
|
||||
|
||||
# Put the exception as a comment on the SQL code
|
||||
yield Comment, u'-- ValueError: %s\n' % err
|
||||
|
||||
stack = FilterStack()
|
||||
stack.preprocess.append(filtr)
|
||||
|
||||
for tv in stack.run(raw_sql):
|
||||
yield tv
|
||||
|
||||
# Set normal mode
|
||||
self.detected = False
|
||||
|
||||
# Don't include any token while in detected mode
|
||||
continue
|
||||
|
||||
# Normal token
|
||||
yield token_type, value
|
||||
|
||||
|
||||
# ----------------------
|
||||
# statement process
|
||||
|
||||
class StripCommentsFilter:
|
||||
|
||||
def _get_next_comment(self, tlist):
|
||||
# TODO(andi) Comment types should be unified, see related issue38
|
||||
token = tlist.token_next_by_instance(0, sql.Comment)
|
||||
if token is None:
|
||||
token = tlist.token_next_by_type(0, T.Comment)
|
||||
return token
|
||||
|
||||
def _process(self, tlist):
|
||||
token = self._get_next_comment(tlist)
|
||||
while token:
|
||||
tidx = tlist.token_index(token)
|
||||
prev = tlist.token_prev(tidx, False)
|
||||
next_ = tlist.token_next(tidx, False)
|
||||
# Replace by whitespace if prev and next exist and if they're not
|
||||
# whitespaces. This doesn't apply if prev or next is a paranthesis.
|
||||
if (prev is not None and next_ is not None
|
||||
and not prev.is_whitespace() and not next_.is_whitespace()
|
||||
and not (prev.match(T.Punctuation, '(')
|
||||
or next_.match(T.Punctuation, ')'))):
|
||||
tlist.tokens[tidx] = sql.Token(T.Whitespace, ' ')
|
||||
else:
|
||||
tlist.tokens.pop(tidx)
|
||||
token = self._get_next_comment(tlist)
|
||||
|
||||
def process(self, stack, stmt):
|
||||
[self.process(stack, sgroup) for sgroup in stmt.get_sublists()]
|
||||
self._process(stmt)
|
||||
|
||||
|
||||
class StripWhitespaceFilter:
|
||||
|
||||
def _stripws(self, tlist):
|
||||
func_name = '_stripws_%s' % tlist.__class__.__name__.lower()
|
||||
func = getattr(self, func_name, self._stripws_default)
|
||||
func(tlist)
|
||||
|
||||
def _stripws_default(self, tlist):
|
||||
last_was_ws = False
|
||||
for token in tlist.tokens:
|
||||
if token.is_whitespace():
|
||||
if last_was_ws:
|
||||
token.value = ''
|
||||
else:
|
||||
token.value = ' '
|
||||
last_was_ws = token.is_whitespace()
|
||||
|
||||
def _stripws_identifierlist(self, tlist):
|
||||
# Removes newlines before commas, see issue140
|
||||
last_nl = None
|
||||
for token in tlist.tokens[:]:
|
||||
if (token.ttype is T.Punctuation
|
||||
and token.value == ','
|
||||
and last_nl is not None):
|
||||
tlist.tokens.remove(last_nl)
|
||||
if token.is_whitespace():
|
||||
last_nl = token
|
||||
else:
|
||||
last_nl = None
|
||||
return self._stripws_default(tlist)
|
||||
|
||||
def _stripws_parenthesis(self, tlist):
|
||||
if tlist.tokens[1].is_whitespace():
|
||||
tlist.tokens.pop(1)
|
||||
if tlist.tokens[-2].is_whitespace():
|
||||
tlist.tokens.pop(-2)
|
||||
self._stripws_default(tlist)
|
||||
|
||||
def process(self, stack, stmt, depth=0):
|
||||
[self.process(stack, sgroup, depth + 1)
|
||||
for sgroup in stmt.get_sublists()]
|
||||
self._stripws(stmt)
|
||||
if (
|
||||
depth == 0
|
||||
and stmt.tokens
|
||||
and stmt.tokens[-1].is_whitespace()
|
||||
):
|
||||
stmt.tokens.pop(-1)
|
||||
|
||||
|
||||
class ReindentFilter:
|
||||
|
||||
def __init__(self, width=2, char=' ', line_width=None):
|
||||
self.width = width
|
||||
self.char = char
|
||||
self.indent = 0
|
||||
self.offset = 0
|
||||
self.line_width = line_width
|
||||
self._curr_stmt = None
|
||||
self._last_stmt = None
|
||||
|
||||
def _flatten_up_to_token(self, token):
|
||||
"""Yields all tokens up to token plus the next one."""
|
||||
# helper for _get_offset
|
||||
iterator = self._curr_stmt.flatten()
|
||||
for t in iterator:
|
||||
yield t
|
||||
if t == token:
|
||||
raise StopIteration
|
||||
|
||||
def _get_offset(self, token):
|
||||
raw = ''.join(map(unicode, self._flatten_up_to_token(token)))
|
||||
line = raw.splitlines()[-1]
|
||||
# Now take current offset into account and return relative offset.
|
||||
full_offset = len(line) - len(self.char * (self.width * self.indent))
|
||||
return full_offset - self.offset
|
||||
|
||||
def nl(self):
|
||||
# TODO: newline character should be configurable
|
||||
space = (self.char * ((self.indent * self.width) + self.offset))
|
||||
# Detect runaway indenting due to parsing errors
|
||||
if len(space) > 200:
|
||||
# something seems to be wrong, flip back
|
||||
self.indent = self.offset = 0
|
||||
space = (self.char * ((self.indent * self.width) + self.offset))
|
||||
ws = '\n' + space
|
||||
return sql.Token(T.Whitespace, ws)
|
||||
|
||||
def _split_kwds(self, tlist):
|
||||
split_words = ('FROM', 'STRAIGHT_JOIN$', 'JOIN$', 'AND', 'OR',
|
||||
'GROUP', 'ORDER', 'UNION', 'VALUES',
|
||||
'SET', 'BETWEEN', 'EXCEPT', 'HAVING')
|
||||
|
||||
def _next_token(i):
|
||||
t = tlist.token_next_match(i, T.Keyword, split_words,
|
||||
regex=True)
|
||||
if t and t.value.upper() == 'BETWEEN':
|
||||
t = _next_token(tlist.token_index(t) + 1)
|
||||
if t and t.value.upper() == 'AND':
|
||||
t = _next_token(tlist.token_index(t) + 1)
|
||||
return t
|
||||
|
||||
idx = 0
|
||||
token = _next_token(idx)
|
||||
added = set()
|
||||
while token:
|
||||
prev = tlist.token_prev(tlist.token_index(token), False)
|
||||
offset = 1
|
||||
if prev and prev.is_whitespace() and prev not in added:
|
||||
tlist.tokens.pop(tlist.token_index(prev))
|
||||
offset += 1
|
||||
uprev = unicode(prev)
|
||||
if (prev and (uprev.endswith('\n') or uprev.endswith('\r'))):
|
||||
nl = tlist.token_next(token)
|
||||
else:
|
||||
nl = self.nl()
|
||||
added.add(nl)
|
||||
tlist.insert_before(token, nl)
|
||||
offset += 1
|
||||
token = _next_token(tlist.token_index(nl) + offset)
|
||||
|
||||
def _split_statements(self, tlist):
|
||||
idx = 0
|
||||
token = tlist.token_next_by_type(idx, (T.Keyword.DDL, T.Keyword.DML))
|
||||
while token:
|
||||
prev = tlist.token_prev(tlist.token_index(token), False)
|
||||
if prev and prev.is_whitespace():
|
||||
tlist.tokens.pop(tlist.token_index(prev))
|
||||
# only break if it's not the first token
|
||||
if prev:
|
||||
nl = self.nl()
|
||||
tlist.insert_before(token, nl)
|
||||
token = tlist.token_next_by_type(tlist.token_index(token) + 1,
|
||||
(T.Keyword.DDL, T.Keyword.DML))
|
||||
|
||||
def _process(self, tlist):
|
||||
func_name = '_process_%s' % tlist.__class__.__name__.lower()
|
||||
func = getattr(self, func_name, self._process_default)
|
||||
func(tlist)
|
||||
|
||||
def _process_where(self, tlist):
|
||||
token = tlist.token_next_match(0, T.Keyword, 'WHERE')
|
||||
try:
|
||||
tlist.insert_before(token, self.nl())
|
||||
except ValueError: # issue121, errors in statement
|
||||
pass
|
||||
self.indent += 1
|
||||
self._process_default(tlist)
|
||||
self.indent -= 1
|
||||
|
||||
def _process_having(self, tlist):
|
||||
token = tlist.token_next_match(0, T.Keyword, 'HAVING')
|
||||
try:
|
||||
tlist.insert_before(token, self.nl())
|
||||
except ValueError: # issue121, errors in statement
|
||||
pass
|
||||
self.indent += 1
|
||||
self._process_default(tlist)
|
||||
self.indent -= 1
|
||||
|
||||
def _process_parenthesis(self, tlist):
|
||||
first = tlist.token_next(0)
|
||||
indented = False
|
||||
if first and first.ttype in (T.Keyword.DML, T.Keyword.DDL):
|
||||
self.indent += 1
|
||||
tlist.tokens.insert(0, self.nl())
|
||||
indented = True
|
||||
num_offset = self._get_offset(
|
||||
tlist.token_next_match(0, T.Punctuation, '('))
|
||||
self.offset += num_offset
|
||||
self._process_default(tlist, stmts=not indented)
|
||||
if indented:
|
||||
self.indent -= 1
|
||||
self.offset -= num_offset
|
||||
|
||||
def _process_identifierlist(self, tlist):
|
||||
identifiers = list(tlist.get_identifiers())
|
||||
if len(identifiers) > 1 and not tlist.within(sql.Function):
|
||||
first = list(identifiers[0].flatten())[0]
|
||||
if self.char == '\t':
|
||||
# when using tabs we don't count the actual word length
|
||||
# in spaces.
|
||||
num_offset = 1
|
||||
else:
|
||||
num_offset = self._get_offset(first) - len(first.value)
|
||||
self.offset += num_offset
|
||||
for token in identifiers[1:]:
|
||||
tlist.insert_before(token, self.nl())
|
||||
self.offset -= num_offset
|
||||
self._process_default(tlist)
|
||||
|
||||
def _process_case(self, tlist):
|
||||
is_first = True
|
||||
num_offset = None
|
||||
case = tlist.tokens[0]
|
||||
outer_offset = self._get_offset(case) - len(case.value)
|
||||
self.offset += outer_offset
|
||||
for cond, value in tlist.get_cases():
|
||||
if is_first:
|
||||
tcond = list(cond[0].flatten())[0]
|
||||
is_first = False
|
||||
num_offset = self._get_offset(tcond) - len(tcond.value)
|
||||
self.offset += num_offset
|
||||
continue
|
||||
if cond is None:
|
||||
token = value[0]
|
||||
else:
|
||||
token = cond[0]
|
||||
tlist.insert_before(token, self.nl())
|
||||
# Line breaks on group level are done. Now let's add an offset of
|
||||
# 5 (=length of "when", "then", "else") and process subgroups.
|
||||
self.offset += 5
|
||||
self._process_default(tlist)
|
||||
self.offset -= 5
|
||||
if num_offset is not None:
|
||||
self.offset -= num_offset
|
||||
end = tlist.token_next_match(0, T.Keyword, 'END')
|
||||
tlist.insert_before(end, self.nl())
|
||||
self.offset -= outer_offset
|
||||
|
||||
def _process_default(self, tlist, stmts=True, kwds=True):
|
||||
if stmts:
|
||||
self._split_statements(tlist)
|
||||
if kwds:
|
||||
self._split_kwds(tlist)
|
||||
[self._process(sgroup) for sgroup in tlist.get_sublists()]
|
||||
|
||||
def process(self, stack, stmt):
|
||||
if isinstance(stmt, sql.Statement):
|
||||
self._curr_stmt = stmt
|
||||
self._process(stmt)
|
||||
if isinstance(stmt, sql.Statement):
|
||||
if self._last_stmt is not None:
|
||||
if unicode(self._last_stmt).endswith('\n'):
|
||||
nl = '\n'
|
||||
else:
|
||||
nl = '\n\n'
|
||||
stmt.tokens.insert(
|
||||
0, sql.Token(T.Whitespace, nl))
|
||||
if self._last_stmt != stmt:
|
||||
self._last_stmt = stmt
|
||||
|
||||
|
||||
# FIXME: Doesn't work ;)
|
||||
class RightMarginFilter:
|
||||
|
||||
keep_together = (
|
||||
# sql.TypeCast, sql.Identifier, sql.Alias,
|
||||
)
|
||||
|
||||
def __init__(self, width=79):
|
||||
self.width = width
|
||||
self.line = ''
|
||||
|
||||
def _process(self, stack, group, stream):
|
||||
for token in stream:
|
||||
if token.is_whitespace() and '\n' in token.value:
|
||||
if token.value.endswith('\n'):
|
||||
self.line = ''
|
||||
else:
|
||||
self.line = token.value.splitlines()[-1]
|
||||
elif (token.is_group()
|
||||
and not token.__class__ in self.keep_together):
|
||||
token.tokens = self._process(stack, token, token.tokens)
|
||||
else:
|
||||
val = unicode(token)
|
||||
if len(self.line) + len(val) > self.width:
|
||||
match = re.search('^ +', self.line)
|
||||
if match is not None:
|
||||
indent = match.group()
|
||||
else:
|
||||
indent = ''
|
||||
yield sql.Token(T.Whitespace, '\n%s' % indent)
|
||||
self.line = indent
|
||||
self.line += val
|
||||
yield token
|
||||
|
||||
def process(self, stack, group):
|
||||
return
|
||||
group.tokens = self._process(stack, group, group.tokens)
|
||||
|
||||
|
||||
class ColumnsSelect:
|
||||
"""Get the columns names of a SELECT query"""
|
||||
def process(self, stack, stream):
|
||||
mode = 0
|
||||
oldValue = ""
|
||||
parenthesis = 0
|
||||
|
||||
for token_type, value in stream:
|
||||
# Ignore comments
|
||||
if token_type in Comment:
|
||||
continue
|
||||
|
||||
# We have not detected a SELECT statement
|
||||
if mode == 0:
|
||||
if token_type in Keyword and value == 'SELECT':
|
||||
mode = 1
|
||||
|
||||
# We have detected a SELECT statement
|
||||
elif mode == 1:
|
||||
if value == 'FROM':
|
||||
if oldValue:
|
||||
yield oldValue
|
||||
|
||||
mode = 3 # Columns have been checked
|
||||
|
||||
elif value == 'AS':
|
||||
oldValue = ""
|
||||
mode = 2
|
||||
|
||||
elif (token_type == Punctuation
|
||||
and value == ',' and not parenthesis):
|
||||
if oldValue:
|
||||
yield oldValue
|
||||
oldValue = ""
|
||||
|
||||
elif token_type not in Whitespace:
|
||||
if value == '(':
|
||||
parenthesis += 1
|
||||
elif value == ')':
|
||||
parenthesis -= 1
|
||||
|
||||
oldValue += value
|
||||
|
||||
# We are processing an AS keyword
|
||||
elif mode == 2:
|
||||
# We check also for Keywords because a bug in SQLParse
|
||||
if token_type == Name or token_type == Keyword:
|
||||
yield value
|
||||
mode = 1
|
||||
|
||||
|
||||
# ---------------------------
|
||||
# postprocess
|
||||
|
||||
class SerializerUnicode:
|
||||
|
||||
def process(self, stack, stmt):
|
||||
raw = unicode(stmt)
|
||||
lines = split_unquoted_newlines(raw)
|
||||
res = '\n'.join(line.rstrip() for line in lines)
|
||||
return res
|
||||
|
||||
|
||||
def Tokens2Unicode(stream):
|
||||
result = ""
|
||||
|
||||
for _, value in stream:
|
||||
result += unicode(value)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
class OutputFilter:
|
||||
varname_prefix = ''
|
||||
|
||||
def __init__(self, varname='sql'):
|
||||
self.varname = self.varname_prefix + varname
|
||||
self.count = 0
|
||||
|
||||
def _process(self, stream, varname, has_nl):
|
||||
raise NotImplementedError
|
||||
|
||||
def process(self, stack, stmt):
|
||||
self.count += 1
|
||||
if self.count > 1:
|
||||
varname = '%s%d' % (self.varname, self.count)
|
||||
else:
|
||||
varname = self.varname
|
||||
|
||||
has_nl = len(unicode(stmt).strip().splitlines()) > 1
|
||||
stmt.tokens = self._process(stmt.tokens, varname, has_nl)
|
||||
return stmt
|
||||
|
||||
|
||||
class OutputPythonFilter(OutputFilter):
|
||||
def _process(self, stream, varname, has_nl):
|
||||
# SQL query asignation to varname
|
||||
if self.count > 1:
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
yield sql.Token(T.Name, varname)
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Operator, '=')
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
if has_nl:
|
||||
yield sql.Token(T.Operator, '(')
|
||||
yield sql.Token(T.Text, "'")
|
||||
|
||||
# Print the tokens on the quote
|
||||
for token in stream:
|
||||
# Token is a new line separator
|
||||
if token.is_whitespace() and '\n' in token.value:
|
||||
# Close quote and add a new line
|
||||
yield sql.Token(T.Text, " '")
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
|
||||
# Quote header on secondary lines
|
||||
yield sql.Token(T.Whitespace, ' ' * (len(varname) + 4))
|
||||
yield sql.Token(T.Text, "'")
|
||||
|
||||
# Indentation
|
||||
after_lb = token.value.split('\n', 1)[1]
|
||||
if after_lb:
|
||||
yield sql.Token(T.Whitespace, after_lb)
|
||||
continue
|
||||
|
||||
# Token has escape chars
|
||||
elif "'" in token.value:
|
||||
token.value = token.value.replace("'", "\\'")
|
||||
|
||||
# Put the token
|
||||
yield sql.Token(T.Text, token.value)
|
||||
|
||||
# Close quote
|
||||
yield sql.Token(T.Text, "'")
|
||||
if has_nl:
|
||||
yield sql.Token(T.Operator, ')')
|
||||
|
||||
|
||||
class OutputPHPFilter(OutputFilter):
|
||||
varname_prefix = '$'
|
||||
|
||||
def _process(self, stream, varname, has_nl):
|
||||
# SQL query asignation to varname (quote header)
|
||||
if self.count > 1:
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
yield sql.Token(T.Name, varname)
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
if has_nl:
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Operator, '=')
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Text, '"')
|
||||
|
||||
# Print the tokens on the quote
|
||||
for token in stream:
|
||||
# Token is a new line separator
|
||||
if token.is_whitespace() and '\n' in token.value:
|
||||
# Close quote and add a new line
|
||||
yield sql.Token(T.Text, ' ";')
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
|
||||
# Quote header on secondary lines
|
||||
yield sql.Token(T.Name, varname)
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Operator, '.=')
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Text, '"')
|
||||
|
||||
# Indentation
|
||||
after_lb = token.value.split('\n', 1)[1]
|
||||
if after_lb:
|
||||
yield sql.Token(T.Whitespace, after_lb)
|
||||
continue
|
||||
|
||||
# Token has escape chars
|
||||
elif '"' in token.value:
|
||||
token.value = token.value.replace('"', '\\"')
|
||||
|
||||
# Put the token
|
||||
yield sql.Token(T.Text, token.value)
|
||||
|
||||
# Close quote
|
||||
yield sql.Token(T.Text, '"')
|
||||
yield sql.Token(T.Punctuation, ';')
|
||||
|
||||
|
||||
class Limit:
|
||||
"""Get the LIMIT of a query.
|
||||
|
||||
If not defined, return -1 (SQL specification for no LIMIT query)
|
||||
"""
|
||||
def process(self, stack, stream):
|
||||
index = 7
|
||||
stream = list(stream)
|
||||
stream.reverse()
|
||||
|
||||
# Run over all tokens in the stream from the end
|
||||
for token_type, value in stream:
|
||||
index -= 1
|
||||
|
||||
# if index and token_type in Keyword:
|
||||
if index and token_type in Keyword and value == 'LIMIT':
|
||||
return stream[4 - index][1]
|
||||
|
||||
return -1
|
||||
|
||||
|
||||
def compact(stream):
|
||||
"""Function that return a compacted version of the stream"""
|
||||
pipe = Pipeline()
|
||||
|
||||
pipe.append(StripComments())
|
||||
pipe.append(StripWhitespace)
|
||||
|
||||
return pipe(stream)
|
||||
@@ -1,137 +0,0 @@
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
|
||||
"""SQL formatter"""
|
||||
|
||||
from sqlparse import filters
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
|
||||
|
||||
def validate_options(options):
|
||||
"""Validates options."""
|
||||
kwcase = options.get('keyword_case', None)
|
||||
if kwcase not in [None, 'upper', 'lower', 'capitalize']:
|
||||
raise SQLParseError('Invalid value for keyword_case: %r' % kwcase)
|
||||
|
||||
idcase = options.get('identifier_case', None)
|
||||
if idcase not in [None, 'upper', 'lower', 'capitalize']:
|
||||
raise SQLParseError('Invalid value for identifier_case: %r' % idcase)
|
||||
|
||||
ofrmt = options.get('output_format', None)
|
||||
if ofrmt not in [None, 'sql', 'python', 'php']:
|
||||
raise SQLParseError('Unknown output format: %r' % ofrmt)
|
||||
|
||||
strip_comments = options.get('strip_comments', False)
|
||||
if strip_comments not in [True, False]:
|
||||
raise SQLParseError('Invalid value for strip_comments: %r'
|
||||
% strip_comments)
|
||||
|
||||
strip_ws = options.get('strip_whitespace', False)
|
||||
if strip_ws not in [True, False]:
|
||||
raise SQLParseError('Invalid value for strip_whitespace: %r'
|
||||
% strip_ws)
|
||||
|
||||
truncate_strings = options.get('truncate_strings', None)
|
||||
if truncate_strings is not None:
|
||||
try:
|
||||
truncate_strings = int(truncate_strings)
|
||||
except (ValueError, TypeError):
|
||||
raise SQLParseError('Invalid value for truncate_strings: %r'
|
||||
% truncate_strings)
|
||||
if truncate_strings <= 1:
|
||||
raise SQLParseError('Invalid value for truncate_strings: %r'
|
||||
% truncate_strings)
|
||||
options['truncate_strings'] = truncate_strings
|
||||
options['truncate_char'] = options.get('truncate_char', '[...]')
|
||||
|
||||
reindent = options.get('reindent', False)
|
||||
if reindent not in [True, False]:
|
||||
raise SQLParseError('Invalid value for reindent: %r'
|
||||
% reindent)
|
||||
elif reindent:
|
||||
options['strip_whitespace'] = True
|
||||
indent_tabs = options.get('indent_tabs', False)
|
||||
if indent_tabs not in [True, False]:
|
||||
raise SQLParseError('Invalid value for indent_tabs: %r' % indent_tabs)
|
||||
elif indent_tabs:
|
||||
options['indent_char'] = '\t'
|
||||
else:
|
||||
options['indent_char'] = ' '
|
||||
indent_width = options.get('indent_width', 2)
|
||||
try:
|
||||
indent_width = int(indent_width)
|
||||
except (TypeError, ValueError):
|
||||
raise SQLParseError('indent_width requires an integer')
|
||||
if indent_width < 1:
|
||||
raise SQLParseError('indent_width requires an positive integer')
|
||||
options['indent_width'] = indent_width
|
||||
|
||||
right_margin = options.get('right_margin', None)
|
||||
if right_margin is not None:
|
||||
try:
|
||||
right_margin = int(right_margin)
|
||||
except (TypeError, ValueError):
|
||||
raise SQLParseError('right_margin requires an integer')
|
||||
if right_margin < 10:
|
||||
raise SQLParseError('right_margin requires an integer > 10')
|
||||
options['right_margin'] = right_margin
|
||||
|
||||
return options
|
||||
|
||||
|
||||
def build_filter_stack(stack, options):
|
||||
"""Setup and return a filter stack.
|
||||
|
||||
Args:
|
||||
stack: :class:`~sqlparse.filters.FilterStack` instance
|
||||
options: Dictionary with options validated by validate_options.
|
||||
"""
|
||||
# Token filter
|
||||
if options.get('keyword_case', None):
|
||||
stack.preprocess.append(
|
||||
filters.KeywordCaseFilter(options['keyword_case']))
|
||||
|
||||
if options.get('identifier_case', None):
|
||||
stack.preprocess.append(
|
||||
filters.IdentifierCaseFilter(options['identifier_case']))
|
||||
|
||||
if options.get('truncate_strings', None) is not None:
|
||||
stack.preprocess.append(filters.TruncateStringFilter(
|
||||
width=options['truncate_strings'], char=options['truncate_char']))
|
||||
|
||||
# After grouping
|
||||
if options.get('strip_comments', False):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(filters.StripCommentsFilter())
|
||||
|
||||
if (options.get('strip_whitespace', False)
|
||||
or options.get('reindent', False)):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(filters.StripWhitespaceFilter())
|
||||
|
||||
if options.get('reindent', False):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(
|
||||
filters.ReindentFilter(char=options['indent_char'],
|
||||
width=options['indent_width']))
|
||||
|
||||
if options.get('right_margin', False):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(
|
||||
filters.RightMarginFilter(width=options['right_margin']))
|
||||
|
||||
# Serializer
|
||||
if options.get('output_format'):
|
||||
frmt = options['output_format']
|
||||
if frmt.lower() == 'php':
|
||||
fltr = filters.OutputPHPFilter()
|
||||
elif frmt.lower() == 'python':
|
||||
fltr = filters.OutputPythonFilter()
|
||||
else:
|
||||
fltr = None
|
||||
if fltr is not None:
|
||||
stack.postprocess.append(fltr)
|
||||
|
||||
return stack
|
||||
@@ -1,44 +0,0 @@
|
||||
'''
|
||||
Created on 17/05/2012
|
||||
|
||||
@author: piranna
|
||||
|
||||
Several utility functions to extract info from the SQL sentences
|
||||
'''
|
||||
|
||||
from sqlparse.filters import ColumnsSelect, Limit
|
||||
from sqlparse.pipeline import Pipeline
|
||||
from sqlparse.tokens import Keyword, Whitespace
|
||||
|
||||
|
||||
def getlimit(stream):
|
||||
"""Function that return the LIMIT of a input SQL """
|
||||
pipe = Pipeline()
|
||||
|
||||
pipe.append(Limit())
|
||||
|
||||
result = pipe(stream)
|
||||
try:
|
||||
return int(result)
|
||||
except ValueError:
|
||||
return result
|
||||
|
||||
|
||||
def getcolumns(stream):
|
||||
"""Function that return the colums of a SELECT query"""
|
||||
pipe = Pipeline()
|
||||
|
||||
pipe.append(ColumnsSelect())
|
||||
|
||||
return pipe(stream)
|
||||
|
||||
|
||||
class IsType(object):
|
||||
"""Functor that return is the statement is of a specific type"""
|
||||
def __init__(self, type):
|
||||
self.type = type
|
||||
|
||||
def __call__(self, stream):
|
||||
for token_type, value in stream:
|
||||
if token_type not in Whitespace:
|
||||
return token_type in Keyword and value == self.type
|
||||
@@ -1,363 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
|
||||
"""SQL Lexer"""
|
||||
|
||||
# This code is based on the SqlLexer in pygments.
|
||||
# http://pygments.org/
|
||||
# It's separated from the rest of pygments to increase performance
|
||||
# and to allow some customizations.
|
||||
|
||||
import re
|
||||
import sys
|
||||
|
||||
from sqlparse import tokens
|
||||
from sqlparse.keywords import KEYWORDS, KEYWORDS_COMMON
|
||||
from cStringIO import StringIO
|
||||
|
||||
|
||||
class include(str):
|
||||
pass
|
||||
|
||||
|
||||
class combined(tuple):
|
||||
"""Indicates a state combined from multiple states."""
|
||||
|
||||
def __new__(cls, *args):
|
||||
return tuple.__new__(cls, args)
|
||||
|
||||
def __init__(self, *args):
|
||||
# tuple.__init__ doesn't do anything
|
||||
pass
|
||||
|
||||
|
||||
def is_keyword(value):
|
||||
test = value.upper()
|
||||
return KEYWORDS_COMMON.get(test, KEYWORDS.get(test, tokens.Name)), value
|
||||
|
||||
|
||||
def apply_filters(stream, filters, lexer=None):
|
||||
"""
|
||||
Use this method to apply an iterable of filters to
|
||||
a stream. If lexer is given it's forwarded to the
|
||||
filter, otherwise the filter receives `None`.
|
||||
"""
|
||||
|
||||
def _apply(filter_, stream):
|
||||
for token in filter_.filter(lexer, stream):
|
||||
yield token
|
||||
|
||||
for filter_ in filters:
|
||||
stream = _apply(filter_, stream)
|
||||
return stream
|
||||
|
||||
|
||||
class LexerMeta(type):
|
||||
"""
|
||||
Metaclass for Lexer, creates the self._tokens attribute from
|
||||
self.tokens on the first instantiation.
|
||||
"""
|
||||
|
||||
def _process_state(cls, unprocessed, processed, state):
|
||||
assert type(state) is str, "wrong state name %r" % state
|
||||
assert state[0] != '#', "invalid state name %r" % state
|
||||
if state in processed:
|
||||
return processed[state]
|
||||
tokenlist = processed[state] = []
|
||||
rflags = cls.flags
|
||||
for tdef in unprocessed[state]:
|
||||
if isinstance(tdef, include):
|
||||
# it's a state reference
|
||||
assert tdef != state, "circular state reference %r" % state
|
||||
tokenlist.extend(cls._process_state(
|
||||
unprocessed, processed, str(tdef)))
|
||||
continue
|
||||
|
||||
assert type(tdef) is tuple, "wrong rule def %r" % tdef
|
||||
|
||||
try:
|
||||
rex = re.compile(tdef[0], rflags).match
|
||||
except Exception, err:
|
||||
raise ValueError(("uncompilable regex %r in state"
|
||||
" %r of %r: %s"
|
||||
% (tdef[0], state, cls, err)))
|
||||
|
||||
assert type(tdef[1]) is tokens._TokenType or callable(tdef[1]), \
|
||||
('token type must be simple type or callable, not %r'
|
||||
% (tdef[1],))
|
||||
|
||||
if len(tdef) == 2:
|
||||
new_state = None
|
||||
else:
|
||||
tdef2 = tdef[2]
|
||||
if isinstance(tdef2, str):
|
||||
# an existing state
|
||||
if tdef2 == '#pop':
|
||||
new_state = -1
|
||||
elif tdef2 in unprocessed:
|
||||
new_state = (tdef2,)
|
||||
elif tdef2 == '#push':
|
||||
new_state = tdef2
|
||||
elif tdef2[:5] == '#pop:':
|
||||
new_state = -int(tdef2[5:])
|
||||
else:
|
||||
assert False, 'unknown new state %r' % tdef2
|
||||
elif isinstance(tdef2, combined):
|
||||
# combine a new state from existing ones
|
||||
new_state = '_tmp_%d' % cls._tmpname
|
||||
cls._tmpname += 1
|
||||
itokens = []
|
||||
for istate in tdef2:
|
||||
assert istate != state, \
|
||||
'circular state ref %r' % istate
|
||||
itokens.extend(cls._process_state(unprocessed,
|
||||
processed, istate))
|
||||
processed[new_state] = itokens
|
||||
new_state = (new_state,)
|
||||
elif isinstance(tdef2, tuple):
|
||||
# push more than one state
|
||||
for state in tdef2:
|
||||
assert (state in unprocessed or
|
||||
state in ('#pop', '#push')), \
|
||||
'unknown new state ' + state
|
||||
new_state = tdef2
|
||||
else:
|
||||
assert False, 'unknown new state def %r' % tdef2
|
||||
tokenlist.append((rex, tdef[1], new_state))
|
||||
return tokenlist
|
||||
|
||||
def process_tokendef(cls):
|
||||
cls._all_tokens = {}
|
||||
cls._tmpname = 0
|
||||
processed = cls._all_tokens[cls.__name__] = {}
|
||||
#tokendefs = tokendefs or cls.tokens[name]
|
||||
for state in cls.tokens.keys():
|
||||
cls._process_state(cls.tokens, processed, state)
|
||||
return processed
|
||||
|
||||
def __call__(cls, *args, **kwds):
|
||||
if not hasattr(cls, '_tokens'):
|
||||
cls._all_tokens = {}
|
||||
cls._tmpname = 0
|
||||
if hasattr(cls, 'token_variants') and cls.token_variants:
|
||||
# don't process yet
|
||||
pass
|
||||
else:
|
||||
cls._tokens = cls.process_tokendef()
|
||||
|
||||
return type.__call__(cls, *args, **kwds)
|
||||
|
||||
|
||||
class Lexer(object):
|
||||
|
||||
__metaclass__ = LexerMeta
|
||||
|
||||
encoding = 'utf-8'
|
||||
stripall = False
|
||||
stripnl = False
|
||||
tabsize = 0
|
||||
flags = re.IGNORECASE | re.UNICODE
|
||||
|
||||
tokens = {
|
||||
'root': [
|
||||
(r'(--|# ).*?(\r\n|\r|\n)', tokens.Comment.Single),
|
||||
# $ matches *before* newline, therefore we have two patterns
|
||||
# to match Comment.Single
|
||||
(r'(--|# ).*?$', tokens.Comment.Single),
|
||||
(r'(\r\n|\r|\n)', tokens.Newline),
|
||||
(r'\s+', tokens.Whitespace),
|
||||
(r'/\*', tokens.Comment.Multiline, 'multiline-comments'),
|
||||
(r':=', tokens.Assignment),
|
||||
(r'::', tokens.Punctuation),
|
||||
(r'[*]', tokens.Wildcard),
|
||||
(r'CASE\b', tokens.Keyword), # extended CASE(foo)
|
||||
(r"`(``|[^`])*`", tokens.Name),
|
||||
(r"´(´´|[^´])*´", tokens.Name),
|
||||
(r'\$([^\W\d]\w*)?\$', tokens.Name.Builtin),
|
||||
(r'\?{1}', tokens.Name.Placeholder),
|
||||
(r'%\(\w+\)s', tokens.Name.Placeholder),
|
||||
(r'%s', tokens.Name.Placeholder),
|
||||
(r'[$:?]\w+', tokens.Name.Placeholder),
|
||||
# FIXME(andi): VALUES shouldn't be listed here
|
||||
# see https://github.com/andialbrecht/sqlparse/pull/64
|
||||
(r'VALUES', tokens.Keyword),
|
||||
(r'(@|##|#)[^\W\d_]\w+', tokens.Name),
|
||||
# IN is special, it may be followed by a parenthesis, but
|
||||
# is never a functino, see issue183
|
||||
(r'in\b(?=[ (])?', tokens.Keyword),
|
||||
(r'[^\W\d_]\w*(?=[.(])', tokens.Name), # see issue39
|
||||
(r'[-]?0x[0-9a-fA-F]+', tokens.Number.Hexadecimal),
|
||||
(r'[-]?[0-9]*(\.[0-9]+)?[eE][-]?[0-9]+', tokens.Number.Float),
|
||||
(r'[-]?[0-9]*\.[0-9]+', tokens.Number.Float),
|
||||
(r'[-]?[0-9]+', tokens.Number.Integer),
|
||||
(r"'(''|\\\\|\\'|[^'])*'", tokens.String.Single),
|
||||
# not a real string literal in ANSI SQL:
|
||||
# A patch based on: https://github.com/andialbrecht/sqlparse/pull/396
|
||||
(r'"(""|\\\\|\\"|[^"])*"', tokens.String.Symbol),
|
||||
# sqlite names can be escaped with [square brackets]. left bracket
|
||||
# cannot be preceded by word character or a right bracket --
|
||||
# otherwise it's probably an array index
|
||||
(r'(?<![\w\])])(\[[^\]]+\])', tokens.Name),
|
||||
(r'((LEFT\s+|RIGHT\s+|FULL\s+)?(INNER\s+|OUTER\s+|STRAIGHT\s+)?|(CROSS\s+|NATURAL\s+)?)?JOIN\b', tokens.Keyword),
|
||||
(r'END(\s+IF|\s+LOOP)?\b', tokens.Keyword),
|
||||
(r'NOT NULL\b', tokens.Keyword),
|
||||
(r'CREATE(\s+OR\s+REPLACE)?\b', tokens.Keyword.DDL),
|
||||
(r'DOUBLE\s+PRECISION\b', tokens.Name.Builtin),
|
||||
(r'(?<=\.)[^\W\d_]\w*', tokens.Name),
|
||||
(r'[^\W\d]\w*', is_keyword),
|
||||
(r'[;:()\[\],\.]', tokens.Punctuation),
|
||||
(r'[<>=~!]+', tokens.Operator.Comparison),
|
||||
(r'[+/@#%^&|`?^-]+', tokens.Operator),
|
||||
],
|
||||
'multiline-comments': [
|
||||
(r'/\*', tokens.Comment.Multiline, 'multiline-comments'),
|
||||
(r'\*/', tokens.Comment.Multiline, '#pop'),
|
||||
(r'[^/\*]+', tokens.Comment.Multiline),
|
||||
(r'[/*]', tokens.Comment.Multiline),
|
||||
]}
|
||||
|
||||
def __init__(self):
|
||||
self.filters = []
|
||||
|
||||
def add_filter(self, filter_, **options):
|
||||
from sqlparse.filters import Filter
|
||||
if not isinstance(filter_, Filter):
|
||||
filter_ = filter_(**options)
|
||||
self.filters.append(filter_)
|
||||
|
||||
def _decode(self, text):
|
||||
if sys.version_info[0] == 3:
|
||||
if isinstance(text, str):
|
||||
return text
|
||||
if self.encoding == 'guess':
|
||||
try:
|
||||
text = text.decode('utf-8')
|
||||
if text.startswith(u'\ufeff'):
|
||||
text = text[len(u'\ufeff'):]
|
||||
except UnicodeDecodeError:
|
||||
text = text.decode('latin1')
|
||||
else:
|
||||
try:
|
||||
text = text.decode(self.encoding)
|
||||
except UnicodeDecodeError:
|
||||
text = text.decode('unicode-escape')
|
||||
|
||||
if self.tabsize > 0:
|
||||
text = text.expandtabs(self.tabsize)
|
||||
return text
|
||||
|
||||
def get_tokens(self, text, unfiltered=False):
|
||||
"""
|
||||
Return an iterable of (tokentype, value) pairs generated from
|
||||
`text`. If `unfiltered` is set to `True`, the filtering mechanism
|
||||
is bypassed even if filters are defined.
|
||||
|
||||
Also preprocess the text, i.e. expand tabs and strip it if
|
||||
wanted and applies registered filters.
|
||||
"""
|
||||
if isinstance(text, basestring):
|
||||
if self.stripall:
|
||||
text = text.strip()
|
||||
elif self.stripnl:
|
||||
text = text.strip('\n')
|
||||
|
||||
if sys.version_info[0] < 3 and isinstance(text, unicode):
|
||||
text = StringIO(text.encode('utf-8'))
|
||||
self.encoding = 'utf-8'
|
||||
else:
|
||||
text = StringIO(text)
|
||||
|
||||
def streamer():
|
||||
for i, t, v in self.get_tokens_unprocessed(text):
|
||||
yield t, v
|
||||
stream = streamer()
|
||||
if not unfiltered:
|
||||
stream = apply_filters(stream, self.filters, self)
|
||||
return stream
|
||||
|
||||
def get_tokens_unprocessed(self, stream, stack=('root',)):
|
||||
"""
|
||||
Split ``text`` into (tokentype, text) pairs.
|
||||
|
||||
``stack`` is the inital stack (default: ``['root']``)
|
||||
"""
|
||||
pos = 0
|
||||
tokendefs = self._tokens # see __call__, pylint:disable=E1101
|
||||
statestack = list(stack)
|
||||
statetokens = tokendefs[statestack[-1]]
|
||||
known_names = {}
|
||||
|
||||
text = stream.read()
|
||||
text = self._decode(text)
|
||||
|
||||
while 1:
|
||||
for rexmatch, action, new_state in statetokens:
|
||||
m = rexmatch(text, pos)
|
||||
if m:
|
||||
value = m.group()
|
||||
if value in known_names:
|
||||
yield pos, known_names[value], value
|
||||
elif type(action) is tokens._TokenType:
|
||||
yield pos, action, value
|
||||
elif hasattr(action, '__call__'):
|
||||
ttype, value = action(value)
|
||||
known_names[value] = ttype
|
||||
yield pos, ttype, value
|
||||
else:
|
||||
for item in action(self, m):
|
||||
yield item
|
||||
pos = m.end()
|
||||
if new_state is not None:
|
||||
# state transition
|
||||
if isinstance(new_state, tuple):
|
||||
for state in new_state:
|
||||
if state == '#pop':
|
||||
statestack.pop()
|
||||
elif state == '#push':
|
||||
statestack.append(statestack[-1])
|
||||
elif (
|
||||
# Ugly hack - multiline-comments
|
||||
# are not stackable
|
||||
state != 'multiline-comments'
|
||||
or not statestack
|
||||
or statestack[-1] != 'multiline-comments'
|
||||
):
|
||||
statestack.append(state)
|
||||
elif isinstance(new_state, int):
|
||||
# pop
|
||||
del statestack[new_state:]
|
||||
elif new_state == '#push':
|
||||
statestack.append(statestack[-1])
|
||||
else:
|
||||
assert False, "wrong state def: %r" % new_state
|
||||
statetokens = tokendefs[statestack[-1]]
|
||||
break
|
||||
else:
|
||||
try:
|
||||
if text[pos] == '\n':
|
||||
# at EOL, reset state to "root"
|
||||
pos += 1
|
||||
statestack = ['root']
|
||||
statetokens = tokendefs['root']
|
||||
yield pos, tokens.Text, u'\n'
|
||||
continue
|
||||
yield pos, tokens.Error, text[pos]
|
||||
pos += 1
|
||||
except IndexError:
|
||||
break
|
||||
|
||||
|
||||
def tokenize(sql, encoding=None):
|
||||
"""Tokenize sql.
|
||||
|
||||
Tokenize *sql* using the :class:`Lexer` and return a 2-tuple stream
|
||||
of ``(token type, value)`` items.
|
||||
"""
|
||||
lexer = Lexer()
|
||||
if encoding is not None:
|
||||
lexer.encoding = encoding
|
||||
return lexer.get_tokens(sql)
|
||||
@@ -1,31 +0,0 @@
|
||||
# Copyright (C) 2011 Jesus Leganes "piranna", piranna@gmail.com
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
|
||||
from types import GeneratorType
|
||||
|
||||
|
||||
class Pipeline(list):
|
||||
"""Pipeline to process filters sequentially"""
|
||||
|
||||
def __call__(self, stream):
|
||||
"""Run the pipeline
|
||||
|
||||
Return a static (non generator) version of the result
|
||||
"""
|
||||
|
||||
# Run the stream over all the filters on the pipeline
|
||||
for filter in self:
|
||||
# Functions and callable objects (objects with '__call__' method)
|
||||
if callable(filter):
|
||||
stream = filter(stream)
|
||||
|
||||
# Normal filters (objects with 'process' method)
|
||||
else:
|
||||
stream = filter.process(None, stream)
|
||||
|
||||
# If last filter return a generator, staticalize it inside a list
|
||||
if isinstance(stream, GeneratorType):
|
||||
return list(stream)
|
||||
return stream
|
||||
@@ -1,684 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""This module contains classes representing syntactical elements of SQL."""
|
||||
|
||||
import re
|
||||
import sys
|
||||
|
||||
from sqlparse import tokens as T
|
||||
|
||||
|
||||
class Token(object):
|
||||
"""Base class for all other classes in this module.
|
||||
|
||||
It represents a single token and has two instance attributes:
|
||||
``value`` is the unchange value of the token and ``ttype`` is
|
||||
the type of the token.
|
||||
"""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'parent', 'normalized', 'is_keyword')
|
||||
|
||||
def __init__(self, ttype, value):
|
||||
self.value = value
|
||||
if ttype in T.Keyword:
|
||||
self.normalized = value.upper()
|
||||
else:
|
||||
self.normalized = value
|
||||
self.ttype = ttype
|
||||
self.is_keyword = ttype in T.Keyword
|
||||
self.parent = None
|
||||
|
||||
def __str__(self):
|
||||
if sys.version_info[0] == 3:
|
||||
return self.value
|
||||
else:
|
||||
return unicode(self).encode('utf-8')
|
||||
|
||||
def __repr__(self):
|
||||
short = self._get_repr_value()
|
||||
if sys.version_info[0] < 3:
|
||||
short = short.encode('utf-8')
|
||||
return '<%s \'%s\' at 0x%07x>' % (self._get_repr_name(),
|
||||
short, id(self))
|
||||
|
||||
def __unicode__(self):
|
||||
"""Returns a unicode representation of this object."""
|
||||
return self.value or ''
|
||||
|
||||
def to_unicode(self):
|
||||
"""Returns a unicode representation of this object.
|
||||
|
||||
.. deprecated:: 0.1.5
|
||||
Use ``unicode(token)`` (for Python 3: ``str(token)``) instead.
|
||||
"""
|
||||
return unicode(self)
|
||||
|
||||
def _get_repr_name(self):
|
||||
return str(self.ttype).split('.')[-1]
|
||||
|
||||
def _get_repr_value(self):
|
||||
raw = unicode(self)
|
||||
if len(raw) > 7:
|
||||
raw = raw[:6] + u'...'
|
||||
return re.sub('\s+', ' ', raw)
|
||||
|
||||
def flatten(self):
|
||||
"""Resolve subgroups."""
|
||||
yield self
|
||||
|
||||
def match(self, ttype, values, regex=False):
|
||||
"""Checks whether the token matches the given arguments.
|
||||
|
||||
*ttype* is a token type. If this token doesn't match the given token
|
||||
type.
|
||||
*values* is a list of possible values for this token. The values
|
||||
are OR'ed together so if only one of the values matches ``True``
|
||||
is returned. Except for keyword tokens the comparison is
|
||||
case-sensitive. For convenience it's ok to pass in a single string.
|
||||
If *regex* is ``True`` (default is ``False``) the given values are
|
||||
treated as regular expressions.
|
||||
"""
|
||||
type_matched = self.ttype is ttype
|
||||
if not type_matched or values is None:
|
||||
return type_matched
|
||||
|
||||
if regex:
|
||||
if isinstance(values, basestring):
|
||||
values = set([values])
|
||||
|
||||
if self.ttype is T.Keyword:
|
||||
values = set(re.compile(v, re.IGNORECASE) for v in values)
|
||||
else:
|
||||
values = set(re.compile(v) for v in values)
|
||||
|
||||
for pattern in values:
|
||||
if pattern.search(self.value):
|
||||
return True
|
||||
return False
|
||||
|
||||
if isinstance(values, basestring):
|
||||
if self.is_keyword:
|
||||
return values.upper() == self.normalized
|
||||
return values == self.value
|
||||
|
||||
if self.is_keyword:
|
||||
for v in values:
|
||||
if v.upper() == self.normalized:
|
||||
return True
|
||||
return False
|
||||
|
||||
return self.value in values
|
||||
|
||||
def is_group(self):
|
||||
"""Returns ``True`` if this object has children."""
|
||||
return False
|
||||
|
||||
def is_whitespace(self):
|
||||
"""Return ``True`` if this token is a whitespace token."""
|
||||
return self.ttype and self.ttype in T.Whitespace
|
||||
|
||||
def within(self, group_cls):
|
||||
"""Returns ``True`` if this token is within *group_cls*.
|
||||
|
||||
Use this method for example to check if an identifier is within
|
||||
a function: ``t.within(sql.Function)``.
|
||||
"""
|
||||
parent = self.parent
|
||||
while parent:
|
||||
if isinstance(parent, group_cls):
|
||||
return True
|
||||
parent = parent.parent
|
||||
return False
|
||||
|
||||
def is_child_of(self, other):
|
||||
"""Returns ``True`` if this token is a direct child of *other*."""
|
||||
return self.parent == other
|
||||
|
||||
def has_ancestor(self, other):
|
||||
"""Returns ``True`` if *other* is in this tokens ancestry."""
|
||||
parent = self.parent
|
||||
while parent:
|
||||
if parent == other:
|
||||
return True
|
||||
parent = parent.parent
|
||||
return False
|
||||
|
||||
|
||||
class TokenList(Token):
|
||||
"""A group of tokens.
|
||||
|
||||
It has an additional instance attribute ``tokens`` which holds a
|
||||
list of child-tokens.
|
||||
"""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def __init__(self, tokens=None):
|
||||
if tokens is None:
|
||||
tokens = []
|
||||
self.tokens = tokens
|
||||
Token.__init__(self, None, self._to_string())
|
||||
|
||||
def __unicode__(self):
|
||||
return self._to_string()
|
||||
|
||||
def __str__(self):
|
||||
str_ = self._to_string()
|
||||
if sys.version_info[0] < 2:
|
||||
str_ = str_.encode('utf-8')
|
||||
return str_
|
||||
|
||||
def _to_string(self):
|
||||
if sys.version_info[0] == 3:
|
||||
return ''.join(x.value for x in self.flatten())
|
||||
else:
|
||||
return ''.join(unicode(x) for x in self.flatten())
|
||||
|
||||
def _get_repr_name(self):
|
||||
return self.__class__.__name__
|
||||
|
||||
def _pprint_tree(self, max_depth=None, depth=0):
|
||||
"""Pretty-print the object tree."""
|
||||
indent = ' ' * (depth * 2)
|
||||
for idx, token in enumerate(self.tokens):
|
||||
if token.is_group():
|
||||
pre = ' +-'
|
||||
else:
|
||||
pre = ' | '
|
||||
print '%s%s%d %s \'%s\'' % (indent, pre, idx,
|
||||
token._get_repr_name(),
|
||||
token._get_repr_value())
|
||||
if (token.is_group() and (max_depth is None or depth < max_depth)):
|
||||
token._pprint_tree(max_depth, depth + 1)
|
||||
|
||||
def _remove_quotes(self, val):
|
||||
"""Helper that removes surrounding quotes from strings."""
|
||||
if not val:
|
||||
return val
|
||||
if val[0] in ('"', '\'') and val[-1] == val[0]:
|
||||
val = val[1:-1]
|
||||
return val
|
||||
|
||||
def get_token_at_offset(self, offset):
|
||||
"""Returns the token that is on position offset."""
|
||||
idx = 0
|
||||
for token in self.flatten():
|
||||
end = idx + len(token.value)
|
||||
if idx <= offset <= end:
|
||||
return token
|
||||
idx = end
|
||||
|
||||
def flatten(self):
|
||||
"""Generator yielding ungrouped tokens.
|
||||
|
||||
This method is recursively called for all child tokens.
|
||||
"""
|
||||
for token in self.tokens:
|
||||
if isinstance(token, TokenList):
|
||||
for item in token.flatten():
|
||||
yield item
|
||||
else:
|
||||
yield token
|
||||
|
||||
# def __iter__(self):
|
||||
# return self
|
||||
#
|
||||
# def next(self):
|
||||
# for token in self.tokens:
|
||||
# yield token
|
||||
|
||||
def is_group(self):
|
||||
return True
|
||||
|
||||
def get_sublists(self):
|
||||
# return [x for x in self.tokens if isinstance(x, TokenList)]
|
||||
for x in self.tokens:
|
||||
if isinstance(x, TokenList):
|
||||
yield x
|
||||
|
||||
@property
|
||||
def _groupable_tokens(self):
|
||||
return self.tokens
|
||||
|
||||
def token_first(self, ignore_whitespace=True, ignore_comments=False):
|
||||
"""Returns the first child token.
|
||||
|
||||
If *ignore_whitespace* is ``True`` (the default), whitespace
|
||||
tokens are ignored.
|
||||
|
||||
if *ignore_comments* is ``True`` (default: ``False``), comments are
|
||||
ignored too.
|
||||
"""
|
||||
for token in self.tokens:
|
||||
if ignore_whitespace and token.is_whitespace():
|
||||
continue
|
||||
if ignore_comments and isinstance(token, Comment):
|
||||
continue
|
||||
return token
|
||||
|
||||
def token_next_by_instance(self, idx, clss, end=None):
|
||||
"""Returns the next token matching a class.
|
||||
|
||||
*idx* is where to start searching in the list of child tokens.
|
||||
*clss* is a list of classes the token should be an instance of.
|
||||
|
||||
If no matching token can be found ``None`` is returned.
|
||||
"""
|
||||
if not isinstance(clss, (list, tuple)):
|
||||
clss = (clss,)
|
||||
|
||||
for token in self.tokens[idx:end]:
|
||||
if isinstance(token, clss):
|
||||
return token
|
||||
|
||||
def token_next_by_type(self, idx, ttypes):
|
||||
"""Returns next matching token by it's token type."""
|
||||
if not isinstance(ttypes, (list, tuple)):
|
||||
ttypes = [ttypes]
|
||||
|
||||
for token in self.tokens[idx:]:
|
||||
if token.ttype in ttypes:
|
||||
return token
|
||||
|
||||
def token_next_match(self, idx, ttype, value, regex=False):
|
||||
"""Returns next token where it's ``match`` method returns ``True``."""
|
||||
if not isinstance(idx, int):
|
||||
idx = self.token_index(idx)
|
||||
|
||||
for n in xrange(idx, len(self.tokens)):
|
||||
token = self.tokens[n]
|
||||
if token.match(ttype, value, regex):
|
||||
return token
|
||||
|
||||
def token_not_matching(self, idx, funcs):
|
||||
for token in self.tokens[idx:]:
|
||||
passed = False
|
||||
for func in funcs:
|
||||
if func(token):
|
||||
passed = True
|
||||
break
|
||||
|
||||
if not passed:
|
||||
return token
|
||||
|
||||
def token_matching(self, idx, funcs):
|
||||
for token in self.tokens[idx:]:
|
||||
for func in funcs:
|
||||
if func(token):
|
||||
return token
|
||||
|
||||
def token_prev(self, idx, skip_ws=True):
|
||||
"""Returns the previous token relative to *idx*.
|
||||
|
||||
If *skip_ws* is ``True`` (the default) whitespace tokens are ignored.
|
||||
``None`` is returned if there's no previous token.
|
||||
"""
|
||||
if idx is None:
|
||||
return None
|
||||
|
||||
if not isinstance(idx, int):
|
||||
idx = self.token_index(idx)
|
||||
|
||||
while idx:
|
||||
idx -= 1
|
||||
if self.tokens[idx].is_whitespace() and skip_ws:
|
||||
continue
|
||||
return self.tokens[idx]
|
||||
|
||||
def token_next(self, idx, skip_ws=True):
|
||||
"""Returns the next token relative to *idx*.
|
||||
|
||||
If *skip_ws* is ``True`` (the default) whitespace tokens are ignored.
|
||||
``None`` is returned if there's no next token.
|
||||
"""
|
||||
if idx is None:
|
||||
return None
|
||||
|
||||
if not isinstance(idx, int):
|
||||
idx = self.token_index(idx)
|
||||
|
||||
while idx < len(self.tokens) - 1:
|
||||
idx += 1
|
||||
if self.tokens[idx].is_whitespace() and skip_ws:
|
||||
continue
|
||||
return self.tokens[idx]
|
||||
|
||||
def token_index(self, token, start=0):
|
||||
"""Return list index of token."""
|
||||
if start > 0:
|
||||
# Performing `index` manually is much faster when starting in the middle
|
||||
# of the list of tokens and expecting to find the token near to the starting
|
||||
# index.
|
||||
for i in xrange(start, len(self.tokens)):
|
||||
if self.tokens[i] == token:
|
||||
return i
|
||||
return -1
|
||||
return self.tokens.index(token)
|
||||
|
||||
def tokens_between(self, start, end, exclude_end=False):
|
||||
"""Return all tokens between (and including) start and end.
|
||||
|
||||
If *exclude_end* is ``True`` (default is ``False``) the end token
|
||||
is included too.
|
||||
"""
|
||||
# FIXME(andi): rename exclude_end to inlcude_end
|
||||
if exclude_end:
|
||||
offset = 0
|
||||
else:
|
||||
offset = 1
|
||||
end_idx = self.token_index(end) + offset
|
||||
start_idx = self.token_index(start)
|
||||
return self.tokens[start_idx:end_idx]
|
||||
|
||||
def group_tokens(self, grp_cls, tokens, ignore_ws=False):
|
||||
"""Replace tokens by an instance of *grp_cls*."""
|
||||
idx = self.token_index(tokens[0])
|
||||
if ignore_ws:
|
||||
while tokens and tokens[-1].is_whitespace():
|
||||
tokens = tokens[:-1]
|
||||
for t in tokens:
|
||||
self.tokens.remove(t)
|
||||
grp = grp_cls(tokens)
|
||||
for token in tokens:
|
||||
token.parent = grp
|
||||
grp.parent = self
|
||||
self.tokens.insert(idx, grp)
|
||||
return grp
|
||||
|
||||
def insert_before(self, where, token):
|
||||
"""Inserts *token* before *where*."""
|
||||
self.tokens.insert(self.token_index(where), token)
|
||||
|
||||
def insert_after(self, where, token, skip_ws=True):
|
||||
"""Inserts *token* after *where*."""
|
||||
next_token = self.token_next(where, skip_ws=skip_ws)
|
||||
if next_token is None:
|
||||
self.tokens.append(token)
|
||||
else:
|
||||
self.tokens.insert(self.token_index(next_token), token)
|
||||
|
||||
def has_alias(self):
|
||||
"""Returns ``True`` if an alias is present."""
|
||||
return self.get_alias() is not None
|
||||
|
||||
def get_alias(self):
|
||||
"""Returns the alias for this identifier or ``None``."""
|
||||
|
||||
# "name AS alias"
|
||||
kw = self.token_next_match(0, T.Keyword, 'AS')
|
||||
if kw is not None:
|
||||
return self._get_first_name(kw, keywords=True)
|
||||
|
||||
# "name alias" or "complicated column expression alias"
|
||||
if len(self.tokens) > 2 \
|
||||
and self.token_next_by_type(0, T.Whitespace) is not None:
|
||||
return self._get_first_name(reverse=True)
|
||||
|
||||
return None
|
||||
|
||||
def get_name(self):
|
||||
"""Returns the name of this identifier.
|
||||
|
||||
This is either it's alias or it's real name. The returned valued can
|
||||
be considered as the name under which the object corresponding to
|
||||
this identifier is known within the current statement.
|
||||
"""
|
||||
alias = self.get_alias()
|
||||
if alias is not None:
|
||||
return alias
|
||||
return self.get_real_name()
|
||||
|
||||
def get_real_name(self):
|
||||
"""Returns the real name (object name) of this identifier."""
|
||||
# a.b
|
||||
dot = self.token_next_match(0, T.Punctuation, '.')
|
||||
if dot is not None:
|
||||
return self._get_first_name(self.token_index(dot))
|
||||
|
||||
return self._get_first_name()
|
||||
|
||||
def get_parent_name(self):
|
||||
"""Return name of the parent object if any.
|
||||
|
||||
A parent object is identified by the first occuring dot.
|
||||
"""
|
||||
dot = self.token_next_match(0, T.Punctuation, '.')
|
||||
if dot is None:
|
||||
return None
|
||||
prev_ = self.token_prev(self.token_index(dot))
|
||||
if prev_ is None: # something must be verry wrong here..
|
||||
return None
|
||||
return self._remove_quotes(prev_.value)
|
||||
|
||||
def _get_first_name(self, idx=None, reverse=False, keywords=False):
|
||||
"""Returns the name of the first token with a name"""
|
||||
|
||||
if idx and not isinstance(idx, int):
|
||||
idx = self.token_index(idx) + 1
|
||||
|
||||
tokens = self.tokens[idx:] if idx else self.tokens
|
||||
tokens = reversed(tokens) if reverse else tokens
|
||||
types = [T.Name, T.Wildcard, T.String.Symbol]
|
||||
|
||||
if keywords:
|
||||
types.append(T.Keyword)
|
||||
|
||||
for tok in tokens:
|
||||
if tok.ttype in types:
|
||||
return self._remove_quotes(tok.value)
|
||||
elif isinstance(tok, Identifier) or isinstance(tok, Function):
|
||||
return tok.get_name()
|
||||
return None
|
||||
|
||||
class Statement(TokenList):
|
||||
"""Represents a SQL statement."""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def get_type(self):
|
||||
"""Returns the type of a statement.
|
||||
|
||||
The returned value is a string holding an upper-cased reprint of
|
||||
the first DML or DDL keyword. If the first token in this group
|
||||
isn't a DML or DDL keyword "UNKNOWN" is returned.
|
||||
|
||||
Whitespaces and comments at the beginning of the statement
|
||||
are ignored.
|
||||
"""
|
||||
first_token = self.token_first(ignore_comments=True)
|
||||
if first_token is None:
|
||||
# An "empty" statement that either has not tokens at all
|
||||
# or only whitespace tokens.
|
||||
return 'UNKNOWN'
|
||||
|
||||
elif first_token.ttype in (T.Keyword.DML, T.Keyword.DDL):
|
||||
return first_token.normalized
|
||||
|
||||
return 'UNKNOWN'
|
||||
|
||||
|
||||
class Identifier(TokenList):
|
||||
"""Represents an identifier.
|
||||
|
||||
Identifiers may have aliases or typecasts.
|
||||
"""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def is_wildcard(self):
|
||||
"""Return ``True`` if this identifier contains a wildcard."""
|
||||
token = self.token_next_by_type(0, T.Wildcard)
|
||||
return token is not None
|
||||
|
||||
def get_typecast(self):
|
||||
"""Returns the typecast or ``None`` of this object as a string."""
|
||||
marker = self.token_next_match(0, T.Punctuation, '::')
|
||||
if marker is None:
|
||||
return None
|
||||
next_ = self.token_next(self.token_index(marker), False)
|
||||
if next_ is None:
|
||||
return None
|
||||
return unicode(next_)
|
||||
|
||||
def get_ordering(self):
|
||||
"""Returns the ordering or ``None`` as uppercase string."""
|
||||
ordering = self.token_next_by_type(0, T.Keyword.Order)
|
||||
if ordering is None:
|
||||
return None
|
||||
return ordering.value.upper()
|
||||
|
||||
def get_array_indices(self):
|
||||
"""Returns an iterator of index token lists"""
|
||||
|
||||
for tok in self.tokens:
|
||||
if isinstance(tok, SquareBrackets):
|
||||
# Use [1:-1] index to discard the square brackets
|
||||
yield tok.tokens[1:-1]
|
||||
|
||||
|
||||
class IdentifierList(TokenList):
|
||||
"""A list of :class:`~sqlparse.sql.Identifier`\'s."""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def get_identifiers(self):
|
||||
"""Returns the identifiers.
|
||||
|
||||
Whitespaces and punctuations are not included in this generator.
|
||||
"""
|
||||
for x in self.tokens:
|
||||
if not x.is_whitespace() and not x.match(T.Punctuation, ','):
|
||||
yield x
|
||||
|
||||
|
||||
class Parenthesis(TokenList):
|
||||
"""Tokens between parenthesis."""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
@property
|
||||
def _groupable_tokens(self):
|
||||
return self.tokens[1:-1]
|
||||
|
||||
|
||||
class SquareBrackets(TokenList):
|
||||
"""Tokens between square brackets"""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
@property
|
||||
def _groupable_tokens(self):
|
||||
return self.tokens[1:-1]
|
||||
|
||||
class Assignment(TokenList):
|
||||
"""An assignment like 'var := val;'"""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
|
||||
class If(TokenList):
|
||||
"""An 'if' clause with possible 'else if' or 'else' parts."""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
|
||||
class For(TokenList):
|
||||
"""A 'FOR' loop."""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
|
||||
class Comparison(TokenList):
|
||||
"""A comparison used for example in WHERE clauses."""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
@property
|
||||
def left(self):
|
||||
return self.tokens[0]
|
||||
|
||||
@property
|
||||
def right(self):
|
||||
return self.tokens[-1]
|
||||
|
||||
|
||||
class Comment(TokenList):
|
||||
"""A comment."""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def is_multiline(self):
|
||||
return self.tokens and self.tokens[0].ttype == T.Comment.Multiline
|
||||
|
||||
|
||||
class Where(TokenList):
|
||||
"""A WHERE clause."""
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
|
||||
class Case(TokenList):
|
||||
"""A CASE statement with one or more WHEN and possibly an ELSE part."""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def get_cases(self):
|
||||
"""Returns a list of 2-tuples (condition, value).
|
||||
|
||||
If an ELSE exists condition is None.
|
||||
"""
|
||||
CONDITION = 1
|
||||
VALUE = 2
|
||||
|
||||
ret = []
|
||||
mode = CONDITION
|
||||
|
||||
for token in self.tokens:
|
||||
# Set mode from the current statement
|
||||
if token.match(T.Keyword, 'CASE'):
|
||||
continue
|
||||
|
||||
elif token.match(T.Keyword, 'WHEN'):
|
||||
ret.append(([], []))
|
||||
mode = CONDITION
|
||||
|
||||
elif token.match(T.Keyword, 'THEN'):
|
||||
mode = VALUE
|
||||
|
||||
elif token.match(T.Keyword, 'ELSE'):
|
||||
ret.append((None, []))
|
||||
mode = VALUE
|
||||
|
||||
elif token.match(T.Keyword, 'END'):
|
||||
mode = None
|
||||
|
||||
# First condition without preceding WHEN
|
||||
if mode and not ret:
|
||||
ret.append(([], []))
|
||||
|
||||
# Append token depending of the current mode
|
||||
if mode == CONDITION:
|
||||
ret[-1][0].append(token)
|
||||
|
||||
elif mode == VALUE:
|
||||
ret[-1][1].append(token)
|
||||
|
||||
# Return cases list
|
||||
return ret
|
||||
|
||||
|
||||
class Function(TokenList):
|
||||
"""A function or procedure call."""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
|
||||
def get_parameters(self):
|
||||
"""Return a list of parameters."""
|
||||
parenthesis = self.tokens[-1]
|
||||
for t in parenthesis.tokens:
|
||||
if isinstance(t, IdentifierList):
|
||||
return t.get_identifiers()
|
||||
elif isinstance(t, Identifier) or \
|
||||
isinstance(t, Function) or \
|
||||
t.ttype in T.Literal:
|
||||
return [t,]
|
||||
return []
|
||||
|
||||
|
||||
class Begin(TokenList):
|
||||
"""A BEGIN/END block."""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'tokens')
|
||||
@@ -1,137 +0,0 @@
|
||||
'''
|
||||
Created on 17/05/2012
|
||||
|
||||
@author: piranna
|
||||
'''
|
||||
|
||||
import re
|
||||
|
||||
try:
|
||||
from collections import OrderedDict
|
||||
except ImportError:
|
||||
OrderedDict = None
|
||||
|
||||
|
||||
if OrderedDict:
|
||||
class Cache(OrderedDict):
|
||||
"""Cache with LRU algorithm using an OrderedDict as basis
|
||||
"""
|
||||
def __init__(self, maxsize=100):
|
||||
OrderedDict.__init__(self)
|
||||
|
||||
self._maxsize = maxsize
|
||||
|
||||
def __getitem__(self, key, *args, **kwargs):
|
||||
# Get the key and remove it from the cache, or raise KeyError
|
||||
value = OrderedDict.__getitem__(self, key)
|
||||
del self[key]
|
||||
|
||||
# Insert the (key, value) pair on the front of the cache
|
||||
OrderedDict.__setitem__(self, key, value)
|
||||
|
||||
# Return the value from the cache
|
||||
return value
|
||||
|
||||
def __setitem__(self, key, value, *args, **kwargs):
|
||||
# Key was inserted before, remove it so we put it at front later
|
||||
if key in self:
|
||||
del self[key]
|
||||
|
||||
# Too much items on the cache, remove the least recent used
|
||||
elif len(self) >= self._maxsize:
|
||||
self.popitem(False)
|
||||
|
||||
# Insert the (key, value) pair on the front of the cache
|
||||
OrderedDict.__setitem__(self, key, value, *args, **kwargs)
|
||||
|
||||
else:
|
||||
class Cache(dict):
|
||||
"""Cache that reset when gets full
|
||||
"""
|
||||
def __init__(self, maxsize=100):
|
||||
dict.__init__(self)
|
||||
|
||||
self._maxsize = maxsize
|
||||
|
||||
def __setitem__(self, key, value, *args, **kwargs):
|
||||
# Reset the cache if we have too much cached entries and start over
|
||||
if len(self) >= self._maxsize:
|
||||
self.clear()
|
||||
|
||||
# Insert the (key, value) pair on the front of the cache
|
||||
dict.__setitem__(self, key, value, *args, **kwargs)
|
||||
|
||||
|
||||
def memoize_generator(func):
|
||||
"""Memoize decorator for generators
|
||||
|
||||
Store `func` results in a cache according to their arguments as 'memoize'
|
||||
does but instead this works on decorators instead of regular functions.
|
||||
Obviusly, this is only useful if the generator will always return the same
|
||||
values for each specific parameters...
|
||||
"""
|
||||
cache = Cache()
|
||||
|
||||
def wrapped_func(*args, **kwargs):
|
||||
# params = (args, kwargs)
|
||||
params = (args, tuple(sorted(kwargs.items())))
|
||||
|
||||
# Look if cached
|
||||
try:
|
||||
cached = cache[params]
|
||||
|
||||
# Not cached, exec and store it
|
||||
except KeyError:
|
||||
cached = []
|
||||
|
||||
for item in func(*args, **kwargs):
|
||||
cached.append(item)
|
||||
yield item
|
||||
|
||||
cache[params] = cached
|
||||
|
||||
# Cached, yield its items
|
||||
else:
|
||||
for item in cached:
|
||||
yield item
|
||||
|
||||
return wrapped_func
|
||||
|
||||
|
||||
# This regular expression replaces the home-cooked parser that was here before.
|
||||
# It is much faster, but requires an extra post-processing step to get the
|
||||
# desired results (that are compatible with what you would expect from the
|
||||
# str.splitlines() method).
|
||||
#
|
||||
# It matches groups of characters: newlines, quoted strings, or unquoted text,
|
||||
# and splits on that basis. The post-processing step puts those back together
|
||||
# into the actual lines of SQL.
|
||||
SPLIT_REGEX = re.compile(r"""
|
||||
(
|
||||
(?: # Start of non-capturing group
|
||||
(?:\r\n|\r|\n) | # Match any single newline, or
|
||||
[^\r\n'"]+ | # Match any character series without quotes or
|
||||
# newlines, or
|
||||
"(?:[^"\\]|\\.)*" | # Match double-quoted strings, or
|
||||
'(?:[^'\\]|\\.)*' # Match single quoted strings
|
||||
)
|
||||
)
|
||||
""", re.VERBOSE)
|
||||
|
||||
LINE_MATCH = re.compile(r'(\r\n|\r|\n)')
|
||||
|
||||
def split_unquoted_newlines(text):
|
||||
"""Split a string on all unquoted newlines.
|
||||
|
||||
Unlike str.splitlines(), this will ignore CR/LF/CR+LF if the requisite
|
||||
character is inside of a string."""
|
||||
lines = SPLIT_REGEX.split(text)
|
||||
outputlines = ['']
|
||||
for line in lines:
|
||||
if not line:
|
||||
continue
|
||||
elif LINE_MATCH.match(line):
|
||||
outputlines.append('')
|
||||
else:
|
||||
outputlines[-1] += line
|
||||
return outputlines
|
||||
@@ -1,78 +0,0 @@
|
||||
'''
|
||||
Created on 24/03/2012
|
||||
|
||||
@author: piranna
|
||||
'''
|
||||
import unittest
|
||||
|
||||
from sqlparse.filters import StripWhitespace, Tokens2Unicode
|
||||
from sqlparse.lexer import tokenize
|
||||
|
||||
|
||||
class Test__StripWhitespace(unittest.TestCase):
|
||||
sql = """INSERT INTO dir_entries(type)VALUES(:type);
|
||||
|
||||
INSERT INTO directories(inode)
|
||||
VALUES(:inode)
|
||||
LIMIT 1"""
|
||||
|
||||
sql2 = """SELECT child_entry,asdf AS inode, creation
|
||||
FROM links
|
||||
WHERE parent_dir == :parent_dir AND name == :name
|
||||
LIMIT 1"""
|
||||
|
||||
sql3 = """SELECT
|
||||
0 AS st_dev,
|
||||
0 AS st_uid,
|
||||
0 AS st_gid,
|
||||
|
||||
dir_entries.type AS st_mode,
|
||||
dir_entries.inode AS st_ino,
|
||||
COUNT(links.child_entry) AS st_nlink,
|
||||
|
||||
:creation AS st_ctime,
|
||||
dir_entries.access AS st_atime,
|
||||
dir_entries.modification AS st_mtime,
|
||||
|
||||
COALESCE(files.size,0) AS st_size,
|
||||
COALESCE(files.size,0) AS size
|
||||
|
||||
FROM dir_entries
|
||||
LEFT JOIN files
|
||||
ON dir_entries.inode == files.inode
|
||||
LEFT JOIN links
|
||||
ON dir_entries.inode == links.child_entry
|
||||
|
||||
WHERE dir_entries.inode == :inode
|
||||
|
||||
GROUP BY dir_entries.inode
|
||||
LIMIT 1"""
|
||||
|
||||
def test_StripWhitespace1(self):
|
||||
self.assertEqual(
|
||||
Tokens2Unicode(StripWhitespace(tokenize(self.sql))),
|
||||
'INSERT INTO dir_entries(type)VALUES(:type);INSERT INTO '
|
||||
'directories(inode)VALUES(:inode)LIMIT 1')
|
||||
|
||||
def test_StripWhitespace2(self):
|
||||
self.assertEqual(
|
||||
Tokens2Unicode(StripWhitespace(tokenize(self.sql2))),
|
||||
'SELECT child_entry,asdf AS inode,creation FROM links WHERE '
|
||||
'parent_dir==:parent_dir AND name==:name LIMIT 1')
|
||||
|
||||
def test_StripWhitespace3(self):
|
||||
self.assertEqual(
|
||||
Tokens2Unicode(StripWhitespace(tokenize(self.sql3))),
|
||||
'SELECT 0 AS st_dev,0 AS st_uid,0 AS st_gid,dir_entries.type AS '
|
||||
'st_mode,dir_entries.inode AS st_ino,COUNT(links.child_entry)AS '
|
||||
'st_nlink,:creation AS st_ctime,dir_entries.access AS st_atime,'
|
||||
'dir_entries.modification AS st_mtime,COALESCE(files.size,0)AS '
|
||||
'st_size,COALESCE(files.size,0)AS size FROM dir_entries LEFT JOIN'
|
||||
' files ON dir_entries.inode==files.inode LEFT JOIN links ON '
|
||||
'dir_entries.inode==links.child_entry WHERE dir_entries.inode=='
|
||||
':inode GROUP BY dir_entries.inode LIMIT 1')
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
#import sys;sys.argv = ['', 'Test.testName']
|
||||
unittest.main()
|
||||
@@ -1,346 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import pytest
|
||||
|
||||
from tests.utils import TestCaseBase
|
||||
|
||||
import sqlparse
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
|
||||
|
||||
class TestFormat(TestCaseBase):
|
||||
|
||||
def test_keywordcase(self):
|
||||
sql = 'select * from bar; -- select foo\n'
|
||||
res = sqlparse.format(sql, keyword_case='upper')
|
||||
self.ndiffAssertEqual(res, 'SELECT * FROM bar; -- select foo\n')
|
||||
res = sqlparse.format(sql, keyword_case='capitalize')
|
||||
self.ndiffAssertEqual(res, 'Select * From bar; -- select foo\n')
|
||||
res = sqlparse.format(sql.upper(), keyword_case='lower')
|
||||
self.ndiffAssertEqual(res, 'select * from BAR; -- SELECT FOO\n')
|
||||
self.assertRaises(SQLParseError, sqlparse.format, sql,
|
||||
keyword_case='foo')
|
||||
|
||||
def test_identifiercase(self):
|
||||
sql = 'select * from bar; -- select foo\n'
|
||||
res = sqlparse.format(sql, identifier_case='upper')
|
||||
self.ndiffAssertEqual(res, 'select * from BAR; -- select foo\n')
|
||||
res = sqlparse.format(sql, identifier_case='capitalize')
|
||||
self.ndiffAssertEqual(res, 'select * from Bar; -- select foo\n')
|
||||
res = sqlparse.format(sql.upper(), identifier_case='lower')
|
||||
self.ndiffAssertEqual(res, 'SELECT * FROM bar; -- SELECT FOO\n')
|
||||
self.assertRaises(SQLParseError, sqlparse.format, sql,
|
||||
identifier_case='foo')
|
||||
sql = 'select * from "foo"."bar"'
|
||||
res = sqlparse.format(sql, identifier_case="upper")
|
||||
self.ndiffAssertEqual(res, 'select * from "foo"."bar"')
|
||||
|
||||
def test_strip_comments_single(self):
|
||||
sql = 'select *-- statement starts here\nfrom foo'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select * from foo')
|
||||
sql = 'select * -- statement starts here\nfrom foo'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select * from foo')
|
||||
sql = 'select-- foo\nfrom -- bar\nwhere'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select from where')
|
||||
self.assertRaises(SQLParseError, sqlparse.format, sql,
|
||||
strip_comments=None)
|
||||
|
||||
def test_strip_comments_multi(self):
|
||||
sql = '/* sql starts here */\nselect'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select')
|
||||
sql = '/* sql starts here */ select'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select')
|
||||
sql = '/*\n * sql starts here\n */\nselect'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select')
|
||||
sql = 'select (/* sql starts here */ select 2)'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select (select 2)')
|
||||
sql = 'select (/* sql /* starts here */ select 2)'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
self.ndiffAssertEqual(res, 'select (select 2)')
|
||||
|
||||
def test_strip_ws(self):
|
||||
f = lambda sql: sqlparse.format(sql, strip_whitespace=True)
|
||||
s = 'select\n* from foo\n\twhere ( 1 = 2 )\n'
|
||||
self.ndiffAssertEqual(f(s), 'select * from foo where (1 = 2)')
|
||||
s = 'select -- foo\nfrom bar\n'
|
||||
self.ndiffAssertEqual(f(s), 'select -- foo\nfrom bar')
|
||||
self.assertRaises(SQLParseError, sqlparse.format, s,
|
||||
strip_whitespace=None)
|
||||
|
||||
def test_preserve_ws(self):
|
||||
# preserve at least one whitespace after subgroups
|
||||
f = lambda sql: sqlparse.format(sql, strip_whitespace=True)
|
||||
s = 'select\n* /* foo */ from bar '
|
||||
self.ndiffAssertEqual(f(s), 'select * /* foo */ from bar')
|
||||
|
||||
def test_notransform_of_quoted_crlf(self):
|
||||
# Make sure that CR/CR+LF characters inside string literals don't get
|
||||
# affected by the formatter.
|
||||
|
||||
s1 = "SELECT some_column LIKE 'value\r'"
|
||||
s2 = "SELECT some_column LIKE 'value\r'\r\nWHERE id = 1\n"
|
||||
s3 = "SELECT some_column LIKE 'value\\'\r' WHERE id = 1\r"
|
||||
s4 = "SELECT some_column LIKE 'value\\\\\\'\r' WHERE id = 1\r\n"
|
||||
|
||||
f = lambda x: sqlparse.format(x)
|
||||
|
||||
# Because of the use of
|
||||
self.ndiffAssertEqual(f(s1), "SELECT some_column LIKE 'value\r'")
|
||||
self.ndiffAssertEqual(f(s2), "SELECT some_column LIKE 'value\r'\nWHERE id = 1\n")
|
||||
self.ndiffAssertEqual(f(s3), "SELECT some_column LIKE 'value\\'\r' WHERE id = 1\n")
|
||||
self.ndiffAssertEqual(f(s4), "SELECT some_column LIKE 'value\\\\\\'\r' WHERE id = 1\n")
|
||||
|
||||
def test_outputformat(self):
|
||||
sql = 'select * from foo;'
|
||||
self.assertRaises(SQLParseError, sqlparse.format, sql,
|
||||
output_format='foo')
|
||||
|
||||
|
||||
class TestFormatReindent(TestCaseBase):
|
||||
|
||||
def test_option(self):
|
||||
self.assertRaises(SQLParseError, sqlparse.format, 'foo',
|
||||
reindent=2)
|
||||
self.assertRaises(SQLParseError, sqlparse.format, 'foo',
|
||||
indent_tabs=2)
|
||||
self.assertRaises(SQLParseError, sqlparse.format, 'foo',
|
||||
reindent=True, indent_width='foo')
|
||||
self.assertRaises(SQLParseError, sqlparse.format, 'foo',
|
||||
reindent=True, indent_width=-12)
|
||||
|
||||
def test_stmts(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select foo; select bar'
|
||||
self.ndiffAssertEqual(f(s), 'select foo;\n\nselect bar')
|
||||
s = 'select foo'
|
||||
self.ndiffAssertEqual(f(s), 'select foo')
|
||||
s = 'select foo; -- test\n select bar'
|
||||
self.ndiffAssertEqual(f(s), 'select foo; -- test\n\nselect bar')
|
||||
|
||||
def test_keywords(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select * from foo union select * from bar;'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select *',
|
||||
'from foo',
|
||||
'union',
|
||||
'select *',
|
||||
'from bar;']))
|
||||
|
||||
def test_keywords_between(self): # issue 14
|
||||
# don't break AND after BETWEEN
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'and foo between 1 and 2 and bar = 3'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['',
|
||||
'and foo between 1 and 2',
|
||||
'and bar = 3']))
|
||||
|
||||
def test_parenthesis(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select count(*) from (select * from foo);'
|
||||
self.ndiffAssertEqual(f(s),
|
||||
'\n'.join(['select count(*)',
|
||||
'from',
|
||||
' (select *',
|
||||
' from foo);',
|
||||
])
|
||||
)
|
||||
|
||||
def test_where(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select * from foo where bar = 1 and baz = 2 or bzz = 3;'
|
||||
self.ndiffAssertEqual(f(s), ('select *\nfrom foo\n'
|
||||
'where bar = 1\n'
|
||||
' and baz = 2\n'
|
||||
' or bzz = 3;'))
|
||||
s = 'select * from foo where bar = 1 and (baz = 2 or bzz = 3);'
|
||||
self.ndiffAssertEqual(f(s), ('select *\nfrom foo\n'
|
||||
'where bar = 1\n'
|
||||
' and (baz = 2\n'
|
||||
' or bzz = 3);'))
|
||||
|
||||
def test_join(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select * from foo join bar on 1 = 2'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select *',
|
||||
'from foo',
|
||||
'join bar on 1 = 2']))
|
||||
s = 'select * from foo inner join bar on 1 = 2'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select *',
|
||||
'from foo',
|
||||
'inner join bar on 1 = 2']))
|
||||
s = 'select * from foo left outer join bar on 1 = 2'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select *',
|
||||
'from foo',
|
||||
'left outer join bar on 1 = 2']
|
||||
))
|
||||
s = 'select * from foo straight_join bar on 1 = 2'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select *',
|
||||
'from foo',
|
||||
'straight_join bar on 1 = 2']
|
||||
))
|
||||
|
||||
def test_identifier_list(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select foo, bar, baz from table1, table2 where 1 = 2'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select foo,',
|
||||
' bar,',
|
||||
' baz',
|
||||
'from table1,',
|
||||
' table2',
|
||||
'where 1 = 2']))
|
||||
s = 'select a.*, b.id from a, b'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select a.*,',
|
||||
' b.id',
|
||||
'from a,',
|
||||
' b']))
|
||||
|
||||
def test_identifier_list_with_functions(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = ("select 'abc' as foo, coalesce(col1, col2)||col3 as bar,"
|
||||
"col3 from my_table")
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(
|
||||
["select 'abc' as foo,",
|
||||
" coalesce(col1, col2)||col3 as bar,",
|
||||
" col3",
|
||||
"from my_table"]))
|
||||
|
||||
def test_case(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'case when foo = 1 then 2 when foo = 3 then 4 else 5 end'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['case',
|
||||
' when foo = 1 then 2',
|
||||
' when foo = 3 then 4',
|
||||
' else 5',
|
||||
'end']))
|
||||
|
||||
def test_case2(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'case(foo) when bar = 1 then 2 else 3 end'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['case(foo)',
|
||||
' when bar = 1 then 2',
|
||||
' else 3',
|
||||
'end']))
|
||||
|
||||
def test_nested_identifier_list(self): # issue4
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = '(foo as bar, bar1, bar2 as bar3, b4 as b5)'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['(foo as bar,',
|
||||
' bar1,',
|
||||
' bar2 as bar3,',
|
||||
' b4 as b5)']))
|
||||
|
||||
def test_duplicate_linebreaks(self): # issue3
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select c1 -- column1\nfrom foo'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select c1 -- column1',
|
||||
'from foo']))
|
||||
s = 'select c1 -- column1\nfrom foo'
|
||||
r = sqlparse.format(s, reindent=True, strip_comments=True)
|
||||
self.ndiffAssertEqual(r, '\n'.join(['select c1',
|
||||
'from foo']))
|
||||
s = 'select c1\nfrom foo\norder by c1'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select c1',
|
||||
'from foo',
|
||||
'order by c1']))
|
||||
s = 'select c1 from t1 where (c1 = 1) order by c1'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select c1',
|
||||
'from t1',
|
||||
'where (c1 = 1)',
|
||||
'order by c1']))
|
||||
|
||||
def test_keywordfunctions(self): # issue36
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select max(a) b, foo, bar'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select max(a) b,',
|
||||
' foo,',
|
||||
' bar']))
|
||||
|
||||
def test_identifier_and_functions(self): # issue45
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select foo.bar, nvl(1) from dual'
|
||||
self.ndiffAssertEqual(f(s), '\n'.join(['select foo.bar,',
|
||||
' nvl(1)',
|
||||
'from dual']))
|
||||
|
||||
|
||||
class TestOutputFormat(TestCaseBase):
|
||||
|
||||
def test_python(self):
|
||||
sql = 'select * from foo;'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='python')
|
||||
self.ndiffAssertEqual(f(sql), "sql = 'select * from foo;'")
|
||||
f = lambda sql: sqlparse.format(sql, output_format='python',
|
||||
reindent=True)
|
||||
self.ndiffAssertEqual(f(sql), ("sql = ('select * '\n"
|
||||
" 'from foo;')"))
|
||||
|
||||
def test_php(self):
|
||||
sql = 'select * from foo;'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='php')
|
||||
self.ndiffAssertEqual(f(sql), '$sql = "select * from foo;";')
|
||||
f = lambda sql: sqlparse.format(sql, output_format='php',
|
||||
reindent=True)
|
||||
self.ndiffAssertEqual(f(sql), ('$sql = "select * ";\n'
|
||||
'$sql .= "from foo;";'))
|
||||
|
||||
def test_sql(self): # "sql" is an allowed option but has no effect
|
||||
sql = 'select * from foo;'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='sql')
|
||||
self.ndiffAssertEqual(f(sql), 'select * from foo;')
|
||||
|
||||
|
||||
def test_format_column_ordering(): # issue89
|
||||
sql = 'select * from foo order by c1 desc, c2, c3;'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
expected = '\n'.join(['select *',
|
||||
'from foo',
|
||||
'order by c1 desc,',
|
||||
' c2,',
|
||||
' c3;'])
|
||||
assert formatted == expected
|
||||
|
||||
|
||||
def test_truncate_strings():
|
||||
sql = 'update foo set value = \'' + 'x' * 1000 + '\';'
|
||||
formatted = sqlparse.format(sql, truncate_strings=10)
|
||||
assert formatted == 'update foo set value = \'xxxxxxxxxx[...]\';'
|
||||
formatted = sqlparse.format(sql, truncate_strings=3, truncate_char='YYY')
|
||||
assert formatted == 'update foo set value = \'xxxYYY\';'
|
||||
|
||||
|
||||
def test_truncate_strings_invalid_option():
|
||||
pytest.raises(SQLParseError, sqlparse.format,
|
||||
'foo', truncate_strings='bar')
|
||||
pytest.raises(SQLParseError, sqlparse.format,
|
||||
'foo', truncate_strings=-1)
|
||||
pytest.raises(SQLParseError, sqlparse.format,
|
||||
'foo', truncate_strings=0)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('sql', ['select verrrylongcolumn from foo',
|
||||
'select "verrrylongcolumn" from "foo"'])
|
||||
def test_truncate_strings_doesnt_truncate_identifiers(sql):
|
||||
formatted = sqlparse.format(sql, truncate_strings=2)
|
||||
assert formatted == sql
|
||||
|
||||
|
||||
def test_having_produces_newline():
|
||||
sql = (
|
||||
'select * from foo, bar where bar.id = foo.bar_id'
|
||||
' having sum(bar.value) > 100')
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
expected = [
|
||||
'select *',
|
||||
'from foo,',
|
||||
' bar',
|
||||
'where bar.id = foo.bar_id',
|
||||
'having sum(bar.value) > 100'
|
||||
]
|
||||
assert formatted == '\n'.join(expected)
|
||||
@@ -1,164 +0,0 @@
|
||||
'''
|
||||
Created on 13/02/2012
|
||||
|
||||
@author: piranna
|
||||
'''
|
||||
from unittest import main, TestCase
|
||||
|
||||
from sqlparse.filters import IncludeStatement, Tokens2Unicode
|
||||
from sqlparse.lexer import tokenize
|
||||
|
||||
import sys
|
||||
sys.path.insert(0, '..')
|
||||
|
||||
from sqlparse.filters import compact
|
||||
from sqlparse.functions import getcolumns, getlimit, IsType
|
||||
|
||||
|
||||
class Test_IncludeStatement(TestCase):
|
||||
sql = """-- type: script
|
||||
-- return: integer
|
||||
|
||||
INCLUDE "_Make_DirEntry.sql";
|
||||
|
||||
INSERT INTO directories(inode)
|
||||
VALUES(:inode)
|
||||
LIMIT 1"""
|
||||
|
||||
def test_includeStatement(self):
|
||||
stream = tokenize(self.sql)
|
||||
includeStatement = IncludeStatement('tests/files',
|
||||
raiseexceptions=True)
|
||||
stream = includeStatement.process(None, stream)
|
||||
stream = compact(stream)
|
||||
|
||||
result = Tokens2Unicode(stream)
|
||||
|
||||
self.assertEqual(
|
||||
result, (
|
||||
'INSERT INTO dir_entries(type)VALUES(:type);INSERT INTO '
|
||||
'directories(inode)VALUES(:inode)LIMIT 1'))
|
||||
|
||||
|
||||
class Test_SQL(TestCase):
|
||||
sql = """-- type: script
|
||||
-- return: integer
|
||||
|
||||
INSERT INTO directories(inode)
|
||||
VALUES(:inode)
|
||||
LIMIT 1"""
|
||||
|
||||
sql2 = """SELECT child_entry,asdf AS inode, creation
|
||||
FROM links
|
||||
WHERE parent_dir == :parent_dir AND name == :name
|
||||
LIMIT 1"""
|
||||
|
||||
sql3 = """SELECT
|
||||
0 AS st_dev,
|
||||
0 AS st_uid,
|
||||
0 AS st_gid,
|
||||
|
||||
dir_entries.type AS st_mode,
|
||||
dir_entries.inode AS st_ino,
|
||||
COUNT(links.child_entry) AS st_nlink,
|
||||
|
||||
:creation AS st_ctime,
|
||||
dir_entries.access AS st_atime,
|
||||
dir_entries.modification AS st_mtime,
|
||||
-- :creation AS st_ctime,
|
||||
-- CAST(STRFTIME('%s',dir_entries.access) AS INTEGER) AS st_atime,
|
||||
-- CAST(STRFTIME('%s',dir_entries.modification) AS INTEGER) AS st_mtime,
|
||||
|
||||
COALESCE(files.size,0) AS st_size, -- Python-FUSE
|
||||
COALESCE(files.size,0) AS size -- PyFilesystem
|
||||
|
||||
FROM dir_entries
|
||||
LEFT JOIN files
|
||||
ON dir_entries.inode == files.inode
|
||||
LEFT JOIN links
|
||||
ON dir_entries.inode == links.child_entry
|
||||
|
||||
WHERE dir_entries.inode == :inode
|
||||
|
||||
GROUP BY dir_entries.inode
|
||||
LIMIT 1"""
|
||||
|
||||
|
||||
class Test_Compact(Test_SQL):
|
||||
def test_compact1(self):
|
||||
stream = compact(tokenize(self.sql))
|
||||
|
||||
result = Tokens2Unicode(stream)
|
||||
|
||||
self.assertEqual(result,
|
||||
'INSERT INTO directories(inode)VALUES(:inode)LIMIT 1')
|
||||
|
||||
def test_compact2(self):
|
||||
stream = tokenize(self.sql2)
|
||||
|
||||
result = compact(stream)
|
||||
|
||||
self.assertEqual(
|
||||
Tokens2Unicode(result),
|
||||
'SELECT child_entry,asdf AS inode,creation FROM links WHERE '
|
||||
'parent_dir==:parent_dir AND name==:name LIMIT 1')
|
||||
|
||||
def test_compact3(self):
|
||||
stream = tokenize(self.sql3)
|
||||
|
||||
result = compact(stream)
|
||||
|
||||
self.assertEqual(
|
||||
Tokens2Unicode(result),
|
||||
'SELECT 0 AS st_dev,0 AS st_uid,0 AS st_gid,dir_entries.type AS '
|
||||
'st_mode,dir_entries.inode AS st_ino,COUNT(links.child_entry)AS '
|
||||
'st_nlink,:creation AS st_ctime,dir_entries.access AS st_atime,'
|
||||
'dir_entries.modification AS st_mtime,COALESCE(files.size,0)AS '
|
||||
'st_size,COALESCE(files.size,0)AS size FROM dir_entries LEFT JOIN'
|
||||
' files ON dir_entries.inode==files.inode LEFT JOIN links ON '
|
||||
'dir_entries.inode==links.child_entry WHERE dir_entries.inode=='
|
||||
':inode GROUP BY dir_entries.inode LIMIT 1')
|
||||
|
||||
|
||||
class Test_GetColumns(Test_SQL):
|
||||
def test_getcolumns1(self):
|
||||
columns = getcolumns(tokenize(self.sql))
|
||||
self.assertEqual(columns, [])
|
||||
|
||||
def test_getcolumns2(self):
|
||||
columns = getcolumns(tokenize(self.sql2))
|
||||
self.assertEqual(columns, ['child_entry', 'inode', 'creation'])
|
||||
|
||||
def test_getcolumns3(self):
|
||||
columns = getcolumns(tokenize(self.sql3))
|
||||
self.assertEqual(columns, ['st_dev', 'st_uid', 'st_gid', 'st_mode',
|
||||
'st_ino', 'st_nlink', 'st_ctime',
|
||||
'st_atime', 'st_mtime', 'st_size', 'size'])
|
||||
|
||||
|
||||
class Test_GetLimit(Test_SQL):
|
||||
def test_getlimit1(self):
|
||||
limit = getlimit(tokenize(self.sql))
|
||||
self.assertEqual(limit, 1)
|
||||
|
||||
def test_getlimit2(self):
|
||||
limit = getlimit(tokenize(self.sql2))
|
||||
self.assertEqual(limit, 1)
|
||||
|
||||
def test_getlimit3(self):
|
||||
limit = getlimit(tokenize(self.sql3))
|
||||
self.assertEqual(limit, 1)
|
||||
|
||||
|
||||
class Test_IsType(Test_SQL):
|
||||
def test_istype2(self):
|
||||
stream = tokenize(self.sql2)
|
||||
self.assertTrue(IsType('SELECT')(stream))
|
||||
|
||||
stream = tokenize(self.sql2)
|
||||
self.assertFalse(IsType('INSERT')(stream))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
#import sys;sys.argv = ['', 'Test.testName']
|
||||
main()
|
||||
@@ -1,399 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import sql
|
||||
from sqlparse import tokens as T
|
||||
|
||||
from tests.utils import TestCaseBase
|
||||
|
||||
|
||||
class TestGrouping(TestCaseBase):
|
||||
|
||||
def test_parenthesis(self):
|
||||
s = 'select (select (x3) x2) and (y2) bar'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, str(parsed))
|
||||
self.assertEqual(len(parsed.tokens), 7)
|
||||
self.assert_(isinstance(parsed.tokens[2], sql.Parenthesis))
|
||||
self.assert_(isinstance(parsed.tokens[-1], sql.Identifier))
|
||||
self.assertEqual(len(parsed.tokens[2].tokens), 5)
|
||||
self.assert_(isinstance(parsed.tokens[2].tokens[3], sql.Identifier))
|
||||
self.assert_(isinstance(parsed.tokens[2].tokens[3].tokens[0], sql.Parenthesis))
|
||||
self.assertEqual(len(parsed.tokens[2].tokens[3].tokens), 3)
|
||||
|
||||
def test_comments(self):
|
||||
s = '/*\n * foo\n */ \n bar'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(parsed))
|
||||
self.assertEqual(len(parsed.tokens), 2)
|
||||
|
||||
def test_assignment(self):
|
||||
s = 'foo := 1;'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.assertEqual(len(parsed.tokens), 1)
|
||||
self.assert_(isinstance(parsed.tokens[0], sql.Assignment))
|
||||
s = 'foo := 1'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.assertEqual(len(parsed.tokens), 1)
|
||||
self.assert_(isinstance(parsed.tokens[0], sql.Assignment))
|
||||
|
||||
def test_identifiers(self):
|
||||
s = 'select foo.bar from "myscheme"."table" where fail. order'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(parsed))
|
||||
self.assert_(isinstance(parsed.tokens[2], sql.Identifier))
|
||||
self.assert_(isinstance(parsed.tokens[6], sql.Identifier))
|
||||
self.assert_(isinstance(parsed.tokens[8], sql.Where))
|
||||
s = 'select * from foo where foo.id = 1'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(parsed))
|
||||
self.assert_(isinstance(parsed.tokens[-1].tokens[-1].tokens[0],
|
||||
sql.Identifier))
|
||||
s = 'select * from (select "foo"."id" from foo)'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(parsed))
|
||||
self.assert_(isinstance(parsed.tokens[-1].tokens[3], sql.Identifier))
|
||||
|
||||
s = "INSERT INTO `test` VALUES('foo', 'bar');"
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
types = [l.ttype for l in parsed.tokens if not l.is_whitespace()]
|
||||
self.assertEquals(types, [T.DML, T.Keyword, None,
|
||||
T.Keyword, None, T.Punctuation])
|
||||
|
||||
s = "select 1.0*(a+b) as col, sum(c)/sum(d) from myschema.mytable"
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
self.assertEqual(len(parsed.tokens), 7)
|
||||
self.assert_(isinstance(parsed.tokens[2], sql.IdentifierList))
|
||||
self.assertEqual(len(parsed.tokens[2].tokens), 4)
|
||||
identifiers = list(parsed.tokens[2].get_identifiers())
|
||||
self.assertEqual(len(identifiers), 2)
|
||||
self.assertEquals(identifiers[0].get_alias(), u"col")
|
||||
|
||||
def test_identifier_wildcard(self):
|
||||
p = sqlparse.parse('a.*, b.id')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.IdentifierList))
|
||||
self.assert_(isinstance(p.tokens[0].tokens[0], sql.Identifier))
|
||||
self.assert_(isinstance(p.tokens[0].tokens[-1], sql.Identifier))
|
||||
|
||||
def test_identifier_name_wildcard(self):
|
||||
p = sqlparse.parse('a.*')[0]
|
||||
t = p.tokens[0]
|
||||
self.assertEqual(t.get_name(), '*')
|
||||
self.assertEqual(t.is_wildcard(), True)
|
||||
|
||||
def test_identifier_invalid(self):
|
||||
p = sqlparse.parse('a.')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
self.assertEqual(p.tokens[0].has_alias(), False)
|
||||
self.assertEqual(p.tokens[0].get_name(), None)
|
||||
self.assertEqual(p.tokens[0].get_real_name(), None)
|
||||
self.assertEqual(p.tokens[0].get_parent_name(), 'a')
|
||||
|
||||
def test_identifier_as_invalid(self): # issue8
|
||||
p = sqlparse.parse('foo as select *')[0]
|
||||
self.assert_(len(p.tokens), 5)
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
self.assertEqual(len(p.tokens[0].tokens), 1)
|
||||
self.assertEqual(p.tokens[2].ttype, T.Keyword)
|
||||
|
||||
def test_identifier_function(self):
|
||||
p = sqlparse.parse('foo() as bar')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
self.assert_(isinstance(p.tokens[0].tokens[0], sql.Function))
|
||||
p = sqlparse.parse('foo()||col2 bar')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
self.assert_(isinstance(p.tokens[0].tokens[0], sql.Function))
|
||||
|
||||
def test_identifier_extended(self): # issue 15
|
||||
p = sqlparse.parse('foo+100')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
p = sqlparse.parse('foo + 100')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
p = sqlparse.parse('foo*100')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Identifier))
|
||||
|
||||
def test_identifier_list(self):
|
||||
p = sqlparse.parse('a, b, c')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.IdentifierList))
|
||||
p = sqlparse.parse('(a, b, c)')[0]
|
||||
self.assert_(isinstance(p.tokens[0].tokens[1], sql.IdentifierList))
|
||||
|
||||
def test_identifier_list_case(self):
|
||||
p = sqlparse.parse('a, case when 1 then 2 else 3 end as b, c')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.IdentifierList))
|
||||
p = sqlparse.parse('(a, case when 1 then 2 else 3 end as b, c)')[0]
|
||||
self.assert_(isinstance(p.tokens[0].tokens[1], sql.IdentifierList))
|
||||
|
||||
def test_identifier_list_other(self): # issue2
|
||||
p = sqlparse.parse("select *, null, 1, 'foo', bar from mytable, x")[0]
|
||||
self.assert_(isinstance(p.tokens[2], sql.IdentifierList))
|
||||
l = p.tokens[2]
|
||||
self.assertEqual(len(l.tokens), 13)
|
||||
|
||||
def test_identifier_list_with_inline_comments(self): # issue163
|
||||
p = sqlparse.parse('foo /* a comment */, bar')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.IdentifierList))
|
||||
self.assert_(isinstance(p.tokens[0].tokens[0], sql.Identifier))
|
||||
self.assert_(isinstance(p.tokens[0].tokens[3], sql.Identifier))
|
||||
|
||||
def test_where(self):
|
||||
s = 'select * from foo where bar = 1 order by id desc'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertTrue(len(p.tokens), 16)
|
||||
s = 'select x from (select y from foo where bar = 1) z'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertTrue(isinstance(p.tokens[-1].tokens[0].tokens[-2], sql.Where))
|
||||
|
||||
def test_typecast(self):
|
||||
s = 'select foo::integer from bar'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertEqual(p.tokens[2].get_typecast(), 'integer')
|
||||
self.assertEqual(p.tokens[2].get_name(), 'foo')
|
||||
s = 'select (current_database())::information_schema.sql_identifier'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertEqual(p.tokens[2].get_typecast(),
|
||||
'information_schema.sql_identifier')
|
||||
|
||||
def test_alias(self):
|
||||
s = 'select foo as bar from mytable'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertEqual(p.tokens[2].get_real_name(), 'foo')
|
||||
self.assertEqual(p.tokens[2].get_alias(), 'bar')
|
||||
s = 'select foo from mytable t1'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertEqual(p.tokens[6].get_real_name(), 'mytable')
|
||||
self.assertEqual(p.tokens[6].get_alias(), 't1')
|
||||
s = 'select foo::integer as bar from mytable'
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertEqual(p.tokens[2].get_alias(), 'bar')
|
||||
s = ('SELECT DISTINCT '
|
||||
'(current_database())::information_schema.sql_identifier AS view')
|
||||
p = sqlparse.parse(s)[0]
|
||||
self.ndiffAssertEqual(s, unicode(p))
|
||||
self.assertEqual(p.tokens[4].get_alias(), 'view')
|
||||
|
||||
def test_alias_case(self): # see issue46
|
||||
p = sqlparse.parse('CASE WHEN 1 THEN 2 ELSE 3 END foo')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assertEqual(p.tokens[0].get_alias(), 'foo')
|
||||
|
||||
def test_alias_returns_none(self): # see issue185
|
||||
p = sqlparse.parse('foo.bar')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assertEqual(p.tokens[0].get_alias(), None)
|
||||
|
||||
def test_idlist_function(self): # see issue10 too
|
||||
p = sqlparse.parse('foo(1) x, bar')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.IdentifierList))
|
||||
|
||||
def test_comparison_exclude(self):
|
||||
# make sure operators are not handled too lazy
|
||||
p = sqlparse.parse('(=)')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Parenthesis))
|
||||
self.assert_(not isinstance(p.tokens[0].tokens[1], sql.Comparison))
|
||||
p = sqlparse.parse('(a=1)')[0]
|
||||
self.assert_(isinstance(p.tokens[0].tokens[1], sql.Comparison))
|
||||
p = sqlparse.parse('(a>=1)')[0]
|
||||
self.assert_(isinstance(p.tokens[0].tokens[1], sql.Comparison))
|
||||
|
||||
def test_function(self):
|
||||
p = sqlparse.parse('foo()')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Function))
|
||||
p = sqlparse.parse('foo(null, bar)')[0]
|
||||
self.assert_(isinstance(p.tokens[0], sql.Function))
|
||||
self.assertEqual(len(list(p.tokens[0].get_parameters())), 2)
|
||||
|
||||
def test_function_not_in(self): # issue183
|
||||
p = sqlparse.parse('in(1, 2)')[0]
|
||||
self.assertEqual(len(p.tokens), 2)
|
||||
self.assertEqual(p.tokens[0].ttype, T.Keyword)
|
||||
self.assert_(isinstance(p.tokens[1], sql.Parenthesis))
|
||||
|
||||
def test_varchar(self):
|
||||
p = sqlparse.parse('"text" Varchar(50) NOT NULL')[0]
|
||||
self.assert_(isinstance(p.tokens[2], sql.Function))
|
||||
|
||||
|
||||
class TestStatement(TestCaseBase):
|
||||
|
||||
def test_get_type(self):
|
||||
f = lambda sql: sqlparse.parse(sql)[0]
|
||||
self.assertEqual(f('select * from foo').get_type(), 'SELECT')
|
||||
self.assertEqual(f('update foo').get_type(), 'UPDATE')
|
||||
self.assertEqual(f(' update foo').get_type(), 'UPDATE')
|
||||
self.assertEqual(f('\nupdate foo').get_type(), 'UPDATE')
|
||||
self.assertEqual(f('foo').get_type(), 'UNKNOWN')
|
||||
# Statements that have a whitespace after the closing semicolon
|
||||
# are parsed as two statements where later only consists of the
|
||||
# trailing whitespace.
|
||||
self.assertEqual(f('\n').get_type(), 'UNKNOWN')
|
||||
|
||||
|
||||
def test_identifier_with_operators(): # issue 53
|
||||
p = sqlparse.parse('foo||bar')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
# again with whitespaces
|
||||
p = sqlparse.parse('foo || bar')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_identifier_with_op_trailing_ws():
|
||||
# make sure trailing whitespace isn't grouped with identifier
|
||||
p = sqlparse.parse('foo || bar ')[0]
|
||||
assert len(p.tokens) == 2
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
assert p.tokens[1].ttype is T.Whitespace
|
||||
|
||||
|
||||
def test_identifier_with_string_literals():
|
||||
p = sqlparse.parse('foo + \'bar\'')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
# This test seems to be wrong. It was introduced when fixing #53, but #111
|
||||
# showed that this shouldn't be an identifier at all. I'm leaving this
|
||||
# commented in the source for a while.
|
||||
# def test_identifier_string_concat():
|
||||
# p = sqlparse.parse('\'foo\' || bar')[0]
|
||||
# assert len(p.tokens) == 1
|
||||
# assert isinstance(p.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_identifier_consumes_ordering(): # issue89
|
||||
p = sqlparse.parse('select * from foo order by c1 desc, c2, c3')[0]
|
||||
assert isinstance(p.tokens[-1], sql.IdentifierList)
|
||||
ids = list(p.tokens[-1].get_identifiers())
|
||||
assert len(ids) == 3
|
||||
assert ids[0].get_name() == 'c1'
|
||||
assert ids[0].get_ordering() == 'DESC'
|
||||
assert ids[1].get_name() == 'c2'
|
||||
assert ids[1].get_ordering() is None
|
||||
|
||||
|
||||
def test_comparison_with_keywords(): # issue90
|
||||
# in fact these are assignments, but for now we don't distinguish them
|
||||
p = sqlparse.parse('foo = NULL')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'foo'
|
||||
assert p.tokens[0].right.value == 'NULL'
|
||||
# make sure it's case-insensitive
|
||||
p = sqlparse.parse('foo = null')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
|
||||
|
||||
def test_comparison_with_floats(): # issue145
|
||||
p = sqlparse.parse('foo = 25.5')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'foo'
|
||||
assert p.tokens[0].right.value == '25.5'
|
||||
|
||||
|
||||
def test_comparison_with_parenthesis(): # issue23
|
||||
p = sqlparse.parse('(3 + 4) = 7')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
comp = p.tokens[0]
|
||||
assert isinstance(comp.left, sql.Parenthesis)
|
||||
assert comp.right.ttype is T.Number.Integer
|
||||
|
||||
|
||||
def test_comparison_with_strings(): # issue148
|
||||
p = sqlparse.parse('foo = \'bar\'')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert p.tokens[0].right.value == '\'bar\''
|
||||
assert p.tokens[0].right.ttype == T.String.Single
|
||||
|
||||
|
||||
@pytest.mark.parametrize('start', ['FOR', 'FOREACH'])
|
||||
def test_forloops(start):
|
||||
p = sqlparse.parse('%s foo in bar LOOP foobar END LOOP' % start)[0]
|
||||
assert (len(p.tokens)) == 1
|
||||
assert isinstance(p.tokens[0], sql.For)
|
||||
|
||||
|
||||
def test_nested_for():
|
||||
p = sqlparse.parse('FOR foo LOOP FOR bar LOOP END LOOP END LOOP')[0]
|
||||
assert len(p.tokens) == 1
|
||||
for1 = p.tokens[0]
|
||||
assert for1.tokens[0].value == 'FOR'
|
||||
assert for1.tokens[-1].value == 'END LOOP'
|
||||
for2 = for1.tokens[6]
|
||||
assert isinstance(for2, sql.For)
|
||||
assert for2.tokens[0].value == 'FOR'
|
||||
assert for2.tokens[-1].value == 'END LOOP'
|
||||
|
||||
|
||||
def test_begin():
|
||||
p = sqlparse.parse('BEGIN foo END')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Begin)
|
||||
|
||||
|
||||
def test_nested_begin():
|
||||
p = sqlparse.parse('BEGIN foo BEGIN bar END END')[0]
|
||||
assert len(p.tokens) == 1
|
||||
outer = p.tokens[0]
|
||||
assert outer.tokens[0].value == 'BEGIN'
|
||||
assert outer.tokens[-1].value == 'END'
|
||||
inner = outer.tokens[4]
|
||||
assert inner.tokens[0].value == 'BEGIN'
|
||||
assert inner.tokens[-1].value == 'END'
|
||||
assert isinstance(inner, sql.Begin)
|
||||
|
||||
|
||||
def test_aliased_column_without_as():
|
||||
p = sqlparse.parse('foo bar')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_real_name() == 'foo'
|
||||
assert p[0].get_alias() == 'bar'
|
||||
|
||||
p = sqlparse.parse('foo.bar baz')[0].tokens[0]
|
||||
assert p.get_parent_name() == 'foo'
|
||||
assert p.get_real_name() == 'bar'
|
||||
assert p.get_alias() == 'baz'
|
||||
|
||||
|
||||
def test_qualified_function():
|
||||
p = sqlparse.parse('foo()')[0].tokens[0]
|
||||
assert p.get_parent_name() is None
|
||||
assert p.get_real_name() == 'foo'
|
||||
|
||||
p = sqlparse.parse('foo.bar()')[0].tokens[0]
|
||||
assert p.get_parent_name() == 'foo'
|
||||
assert p.get_real_name() == 'bar'
|
||||
|
||||
|
||||
def test_aliased_function_without_as():
|
||||
p = sqlparse.parse('foo() bar')[0].tokens[0]
|
||||
assert p.get_parent_name() is None
|
||||
assert p.get_real_name() == 'foo'
|
||||
assert p.get_alias() == 'bar'
|
||||
|
||||
p = sqlparse.parse('foo.bar() baz')[0].tokens[0]
|
||||
assert p.get_parent_name() == 'foo'
|
||||
assert p.get_real_name() == 'bar'
|
||||
assert p.get_alias() == 'baz'
|
||||
|
||||
|
||||
def test_aliased_literal_without_as():
|
||||
p = sqlparse.parse('1 foo')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_alias() == 'foo'
|
||||
@@ -1,305 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""Tests sqlparse function."""
|
||||
|
||||
import pytest
|
||||
|
||||
from tests.utils import TestCaseBase
|
||||
|
||||
import sqlparse
|
||||
import sqlparse.sql
|
||||
|
||||
from sqlparse import tokens as T
|
||||
|
||||
|
||||
class SQLParseTest(TestCaseBase):
|
||||
"""Tests sqlparse.parse()."""
|
||||
|
||||
def test_tokenize(self):
|
||||
sql = 'select * from foo;'
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 1)
|
||||
self.assertEqual(str(stmts[0]), sql)
|
||||
|
||||
def test_multistatement(self):
|
||||
sql1 = 'select * from foo;'
|
||||
sql2 = 'select * from bar;'
|
||||
stmts = sqlparse.parse(sql1 + sql2)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
self.assertEqual(str(stmts[0]), sql1)
|
||||
self.assertEqual(str(stmts[1]), sql2)
|
||||
|
||||
def test_newlines(self):
|
||||
sql = u'select\n*from foo;'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
self.assertEqual(unicode(p), sql)
|
||||
sql = u'select\r\n*from foo'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
self.assertEqual(unicode(p), sql)
|
||||
sql = u'select\r*from foo'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
self.assertEqual(unicode(p), sql)
|
||||
sql = u'select\r\n*from foo\n'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
self.assertEqual(unicode(p), sql)
|
||||
|
||||
def test_within(self):
|
||||
sql = 'foo(col1, col2)'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
col1 = p.tokens[0].tokens[1].tokens[1].tokens[0]
|
||||
self.assert_(col1.within(sqlparse.sql.Function))
|
||||
|
||||
def test_child_of(self):
|
||||
sql = '(col1, col2)'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
self.assert_(p.tokens[0].tokens[1].is_child_of(p.tokens[0]))
|
||||
sql = 'select foo'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
self.assert_(not p.tokens[2].is_child_of(p.tokens[0]))
|
||||
self.assert_(p.tokens[2].is_child_of(p))
|
||||
|
||||
def test_has_ancestor(self):
|
||||
sql = 'foo or (bar, baz)'
|
||||
p = sqlparse.parse(sql)[0]
|
||||
baz = p.tokens[-1].tokens[1].tokens[-1]
|
||||
self.assert_(baz.has_ancestor(p.tokens[-1].tokens[1]))
|
||||
self.assert_(baz.has_ancestor(p.tokens[-1]))
|
||||
self.assert_(baz.has_ancestor(p))
|
||||
|
||||
def test_float(self):
|
||||
t = sqlparse.parse('.5')[0].tokens
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(t[0].ttype is sqlparse.tokens.Number.Float)
|
||||
t = sqlparse.parse('.51')[0].tokens
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(t[0].ttype is sqlparse.tokens.Number.Float)
|
||||
t = sqlparse.parse('1.5')[0].tokens
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(t[0].ttype is sqlparse.tokens.Number.Float)
|
||||
t = sqlparse.parse('12.5')[0].tokens
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(t[0].ttype is sqlparse.tokens.Number.Float)
|
||||
|
||||
def test_placeholder(self):
|
||||
def _get_tokens(sql):
|
||||
return sqlparse.parse(sql)[0].tokens[-1].tokens
|
||||
t = _get_tokens('select * from foo where user = ?')
|
||||
self.assert_(t[-1].ttype is sqlparse.tokens.Name.Placeholder)
|
||||
self.assertEqual(t[-1].value, '?')
|
||||
t = _get_tokens('select * from foo where user = :1')
|
||||
self.assert_(t[-1].ttype is sqlparse.tokens.Name.Placeholder)
|
||||
self.assertEqual(t[-1].value, ':1')
|
||||
t = _get_tokens('select * from foo where user = :name')
|
||||
self.assert_(t[-1].ttype is sqlparse.tokens.Name.Placeholder)
|
||||
self.assertEqual(t[-1].value, ':name')
|
||||
t = _get_tokens('select * from foo where user = %s')
|
||||
self.assert_(t[-1].ttype is sqlparse.tokens.Name.Placeholder)
|
||||
self.assertEqual(t[-1].value, '%s')
|
||||
t = _get_tokens('select * from foo where user = $a')
|
||||
self.assert_(t[-1].ttype is sqlparse.tokens.Name.Placeholder)
|
||||
self.assertEqual(t[-1].value, '$a')
|
||||
|
||||
def test_modulo_not_placeholder(self):
|
||||
tokens = list(sqlparse.lexer.tokenize('x %3'))
|
||||
self.assertEqual(tokens[2][0], sqlparse.tokens.Operator)
|
||||
|
||||
def test_access_symbol(self): # see issue27
|
||||
t = sqlparse.parse('select a.[foo bar] as foo')[0].tokens
|
||||
self.assert_(isinstance(t[-1], sqlparse.sql.Identifier))
|
||||
self.assertEqual(t[-1].get_name(), 'foo')
|
||||
self.assertEqual(t[-1].get_real_name(), '[foo bar]')
|
||||
self.assertEqual(t[-1].get_parent_name(), 'a')
|
||||
|
||||
def test_square_brackets_notation_isnt_too_greedy(self): # see issue153
|
||||
t = sqlparse.parse('[foo], [bar]')[0].tokens
|
||||
self.assert_(isinstance(t[0], sqlparse.sql.IdentifierList))
|
||||
self.assertEqual(len(t[0].tokens), 4)
|
||||
self.assertEqual(t[0].tokens[0].get_real_name(), '[foo]')
|
||||
self.assertEqual(t[0].tokens[-1].get_real_name(), '[bar]')
|
||||
|
||||
def test_keyword_like_identifier(self): # see issue47
|
||||
t = sqlparse.parse('foo.key')[0].tokens
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(isinstance(t[0], sqlparse.sql.Identifier))
|
||||
|
||||
def test_function_parameter(self): # see issue94
|
||||
t = sqlparse.parse('abs(some_col)')[0].tokens[0].get_parameters()
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(isinstance(t[0], sqlparse.sql.Identifier))
|
||||
|
||||
def test_function_param_single_literal(self):
|
||||
t = sqlparse.parse('foo(5)')[0].tokens[0].get_parameters()
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(t[0].ttype is T.Number.Integer)
|
||||
|
||||
def test_nested_function(self):
|
||||
t = sqlparse.parse('foo(bar(5))')[0].tokens[0].get_parameters()
|
||||
self.assertEqual(len(t), 1)
|
||||
self.assert_(type(t[0]) is sqlparse.sql.Function)
|
||||
|
||||
|
||||
def test_quoted_identifier():
|
||||
t = sqlparse.parse('select x.y as "z" from foo')[0].tokens
|
||||
assert isinstance(t[2], sqlparse.sql.Identifier)
|
||||
assert t[2].get_name() == 'z'
|
||||
assert t[2].get_real_name() == 'y'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('name', [
|
||||
'foo',
|
||||
'_foo',
|
||||
])
|
||||
def test_valid_identifier_names(name): # issue175
|
||||
t = sqlparse.parse(name)[0].tokens
|
||||
assert isinstance(t[0], sqlparse.sql.Identifier)
|
||||
|
||||
|
||||
def test_psql_quotation_marks(): # issue83
|
||||
# regression: make sure plain $$ work
|
||||
t = sqlparse.split("""
|
||||
CREATE OR REPLACE FUNCTION testfunc1(integer) RETURNS integer AS $$
|
||||
....
|
||||
$$ LANGUAGE plpgsql;
|
||||
CREATE OR REPLACE FUNCTION testfunc2(integer) RETURNS integer AS $$
|
||||
....
|
||||
$$ LANGUAGE plpgsql;""")
|
||||
assert len(t) == 2
|
||||
# make sure $SOMETHING$ works too
|
||||
t = sqlparse.split("""
|
||||
CREATE OR REPLACE FUNCTION testfunc1(integer) RETURNS integer AS $PROC_1$
|
||||
....
|
||||
$PROC_1$ LANGUAGE plpgsql;
|
||||
CREATE OR REPLACE FUNCTION testfunc2(integer) RETURNS integer AS $PROC_2$
|
||||
....
|
||||
$PROC_2$ LANGUAGE plpgsql;""")
|
||||
assert len(t) == 2
|
||||
|
||||
|
||||
def test_double_precision_is_builtin():
|
||||
sql = 'DOUBLE PRECISION'
|
||||
t = sqlparse.parse(sql)[0].tokens
|
||||
assert (len(t) == 1
|
||||
and t[0].ttype == sqlparse.tokens.Name.Builtin
|
||||
and t[0].value == 'DOUBLE PRECISION')
|
||||
|
||||
|
||||
@pytest.mark.parametrize('ph', ['?', ':1', ':foo', '%s', '%(foo)s'])
|
||||
def test_placeholder(ph):
|
||||
p = sqlparse.parse(ph)[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.Name.Placeholder
|
||||
|
||||
|
||||
@pytest.mark.parametrize('num', ['6.67428E-8', '1.988e33', '1e-12'])
|
||||
def test_scientific_numbers(num):
|
||||
p = sqlparse.parse(num)[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.Number.Float
|
||||
|
||||
|
||||
def test_single_quotes_are_strings():
|
||||
p = sqlparse.parse("'foo'")[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.String.Single
|
||||
|
||||
|
||||
def test_double_quotes_are_identifiers():
|
||||
p = sqlparse.parse('"foo"')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert isinstance(p[0], sqlparse.sql.Identifier)
|
||||
|
||||
|
||||
def test_single_quotes_with_linebreaks(): # issue118
|
||||
p = sqlparse.parse("'f\nf'")[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.String.Single
|
||||
|
||||
|
||||
def test_sqlite_identifiers():
|
||||
# Make sure we still parse sqlite style escapes
|
||||
p = sqlparse.parse('[col1],[col2]')[0].tokens
|
||||
assert (len(p) == 1
|
||||
and isinstance(p[0], sqlparse.sql.IdentifierList)
|
||||
and [id.get_name() for id in p[0].get_identifiers()]
|
||||
== ['[col1]', '[col2]'])
|
||||
|
||||
p = sqlparse.parse('[col1]+[col2]')[0]
|
||||
types = [tok.ttype for tok in p.flatten()]
|
||||
assert types == [T.Name, T.Operator, T.Name]
|
||||
|
||||
|
||||
def test_simple_1d_array_index():
|
||||
p = sqlparse.parse('col[1]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_name() == 'col'
|
||||
indices = list(p[0].get_array_indices())
|
||||
assert (len(indices) == 1 # 1-dimensional index
|
||||
and len(indices[0]) == 1 # index is single token
|
||||
and indices[0][0].value == '1')
|
||||
|
||||
|
||||
def test_2d_array_index():
|
||||
p = sqlparse.parse('col[x][(y+1)*2]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_name() == 'col'
|
||||
assert len(list(p[0].get_array_indices())) == 2 # 2-dimensional index
|
||||
|
||||
|
||||
def test_array_index_function_result():
|
||||
p = sqlparse.parse('somefunc()[1]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert len(list(p[0].get_array_indices())) == 1
|
||||
|
||||
|
||||
def test_schema_qualified_array_index():
|
||||
p = sqlparse.parse('schem.col[1]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_parent_name() == 'schem'
|
||||
assert p[0].get_name() == 'col'
|
||||
assert list(p[0].get_array_indices())[0][0].value == '1'
|
||||
|
||||
|
||||
def test_aliased_array_index():
|
||||
p = sqlparse.parse('col[1] x')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_alias() == 'x'
|
||||
assert p[0].get_real_name() == 'col'
|
||||
assert list(p[0].get_array_indices())[0][0].value == '1'
|
||||
|
||||
|
||||
def test_array_literal():
|
||||
# See issue #176
|
||||
p = sqlparse.parse('ARRAY[%s, %s]')[0]
|
||||
assert len(p.tokens) == 2
|
||||
assert len(list(p.flatten())) == 7
|
||||
|
||||
|
||||
def test_typed_array_definition():
|
||||
# array indices aren't grouped with builtins, but make sure we can extract
|
||||
# indentifer names
|
||||
p = sqlparse.parse('x int, y int[], z int')[0]
|
||||
names = [x.get_name() for x in p.get_sublists()
|
||||
if isinstance(x, sqlparse.sql.Identifier)]
|
||||
assert names == ['x', 'y', 'z']
|
||||
|
||||
|
||||
@pytest.mark.parametrize('sql', [
|
||||
'select 1 -- foo',
|
||||
'select 1 # foo' # see issue178
|
||||
])
|
||||
def test_single_line_comments(sql):
|
||||
p = sqlparse.parse(sql)[0]
|
||||
assert len(p.tokens) == 5
|
||||
assert p.tokens[-1].ttype == T.Comment.Single
|
||||
|
||||
|
||||
@pytest.mark.parametrize('sql', [
|
||||
'foo',
|
||||
'@foo',
|
||||
'#foo', # see issue192
|
||||
'##foo'
|
||||
])
|
||||
def test_names_and_special_names(sql):
|
||||
p = sqlparse.parse(sql)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sqlparse.sql.Identifier)
|
||||
@@ -1,70 +0,0 @@
|
||||
import unittest
|
||||
|
||||
from sqlparse.filters import ColumnsSelect
|
||||
from sqlparse.lexer import tokenize
|
||||
from sqlparse.pipeline import Pipeline
|
||||
|
||||
|
||||
class Test(unittest.TestCase):
|
||||
|
||||
def setUp(self):
|
||||
self.pipe = Pipeline()
|
||||
self.pipe.append(tokenize)
|
||||
self.pipe.append(ColumnsSelect())
|
||||
|
||||
def test_1(self):
|
||||
sql = """
|
||||
-- type: script
|
||||
-- return: integer
|
||||
|
||||
INCLUDE "Direntry.make.sql";
|
||||
|
||||
INSERT INTO directories(inode)
|
||||
VALUES(:inode)
|
||||
LIMIT 1"""
|
||||
self.assertEqual([], self.pipe(sql))
|
||||
|
||||
def test_2(self):
|
||||
sql = """
|
||||
SELECT child_entry,asdf AS inode, creation
|
||||
FROM links
|
||||
WHERE parent_dir == :parent_dir AND name == :name
|
||||
LIMIT 1"""
|
||||
self.assertEqual([u'child_entry', u'inode', u'creation'],
|
||||
self.pipe(sql))
|
||||
|
||||
def test_3(self):
|
||||
sql = """
|
||||
SELECT
|
||||
0 AS st_dev,
|
||||
0 AS st_uid,
|
||||
0 AS st_gid,
|
||||
|
||||
dir_entries.type AS st_mode,
|
||||
dir_entries.inode AS st_ino,
|
||||
COUNT(links.child_entry) AS st_nlink,
|
||||
|
||||
:creation AS st_ctime,
|
||||
dir_entries.access AS st_atime,
|
||||
dir_entries.modification AS st_mtime,
|
||||
-- :creation AS st_ctime,
|
||||
-- CAST(STRFTIME('%s',dir_entries.access) AS INTEGER) AS st_atime,
|
||||
-- CAST(STRFTIME('%s',dir_entries.modification) AS INTEGER) AS st_mtime,
|
||||
|
||||
COALESCE(files.size,0) AS st_size, -- Python-FUSE
|
||||
COALESCE(files.size,0) AS size -- PyFilesystem
|
||||
|
||||
FROM dir_entries
|
||||
LEFT JOIN files
|
||||
ON dir_entries.inode == files.inode
|
||||
LEFT JOIN links
|
||||
ON dir_entries.inode == links.child_entry
|
||||
|
||||
WHERE dir_entries.inode == :inode
|
||||
|
||||
GROUP BY dir_entries.inode
|
||||
LIMIT 1"""
|
||||
self.assertEqual([u'st_dev', u'st_uid', u'st_gid', u'st_mode',
|
||||
u'st_ino', u'st_nlink', u'st_ctime',
|
||||
u'st_atime', u'st_mtime', u'st_size', u'size'],
|
||||
self.pipe(sql))
|
||||
@@ -1,276 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import sys
|
||||
|
||||
from tests.utils import TestCaseBase, load_file
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import sql
|
||||
from sqlparse import tokens as T
|
||||
|
||||
|
||||
class RegressionTests(TestCaseBase):
|
||||
|
||||
def test_issue9(self):
|
||||
# make sure where doesn't consume parenthesis
|
||||
p = sqlparse.parse('(where 1)')[0]
|
||||
self.assert_(isinstance(p, sql.Statement))
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assert_(isinstance(p.tokens[0], sql.Parenthesis))
|
||||
prt = p.tokens[0]
|
||||
self.assertEqual(len(prt.tokens), 3)
|
||||
self.assertEqual(prt.tokens[0].ttype, T.Punctuation)
|
||||
self.assertEqual(prt.tokens[-1].ttype, T.Punctuation)
|
||||
|
||||
def test_issue13(self):
|
||||
parsed = sqlparse.parse(("select 'one';\n"
|
||||
"select 'two\\'';\n"
|
||||
"select 'three';"))
|
||||
self.assertEqual(len(parsed), 3)
|
||||
self.assertEqual(str(parsed[1]).strip(), "select 'two\\'';")
|
||||
|
||||
def test_issue26(self):
|
||||
# parse stand-alone comments
|
||||
p = sqlparse.parse('--hello')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assert_(p.tokens[0].ttype is T.Comment.Single)
|
||||
p = sqlparse.parse('-- hello')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assert_(p.tokens[0].ttype is T.Comment.Single)
|
||||
p = sqlparse.parse('--hello\n')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assert_(p.tokens[0].ttype is T.Comment.Single)
|
||||
p = sqlparse.parse('--')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assert_(p.tokens[0].ttype is T.Comment.Single)
|
||||
p = sqlparse.parse('--\n')[0]
|
||||
self.assertEqual(len(p.tokens), 1)
|
||||
self.assert_(p.tokens[0].ttype is T.Comment.Single)
|
||||
|
||||
def test_issue34(self):
|
||||
t = sqlparse.parse("create")[0].token_first()
|
||||
self.assertEqual(t.match(T.Keyword.DDL, "create"), True)
|
||||
self.assertEqual(t.match(T.Keyword.DDL, "CREATE"), True)
|
||||
|
||||
def test_issue35(self):
|
||||
# missing space before LIMIT
|
||||
sql = sqlparse.format("select * from foo where bar = 1 limit 1",
|
||||
reindent=True)
|
||||
self.ndiffAssertEqual(sql, "\n".join(["select *",
|
||||
"from foo",
|
||||
"where bar = 1 limit 1"]))
|
||||
|
||||
def test_issue38(self):
|
||||
sql = sqlparse.format("SELECT foo; -- comment",
|
||||
strip_comments=True)
|
||||
self.ndiffAssertEqual(sql, "SELECT foo;")
|
||||
sql = sqlparse.format("/* foo */", strip_comments=True)
|
||||
self.ndiffAssertEqual(sql, "")
|
||||
|
||||
def test_issue39(self):
|
||||
p = sqlparse.parse('select user.id from user')[0]
|
||||
self.assertEqual(len(p.tokens), 7)
|
||||
idt = p.tokens[2]
|
||||
self.assertEqual(idt.__class__, sql.Identifier)
|
||||
self.assertEqual(len(idt.tokens), 3)
|
||||
self.assertEqual(idt.tokens[0].match(T.Name, 'user'), True)
|
||||
self.assertEqual(idt.tokens[1].match(T.Punctuation, '.'), True)
|
||||
self.assertEqual(idt.tokens[2].match(T.Name, 'id'), True)
|
||||
|
||||
def test_issue40(self):
|
||||
# make sure identifier lists in subselects are grouped
|
||||
p = sqlparse.parse(('SELECT id, name FROM '
|
||||
'(SELECT id, name FROM bar) as foo'))[0]
|
||||
self.assertEqual(len(p.tokens), 7)
|
||||
self.assertEqual(p.tokens[2].__class__, sql.IdentifierList)
|
||||
self.assertEqual(p.tokens[-1].__class__, sql.Identifier)
|
||||
self.assertEqual(p.tokens[-1].get_name(), u'foo')
|
||||
sp = p.tokens[-1].tokens[0]
|
||||
self.assertEqual(sp.tokens[3].__class__, sql.IdentifierList)
|
||||
# make sure that formatting works as expected
|
||||
self.ndiffAssertEqual(
|
||||
sqlparse.format(('SELECT id, name FROM '
|
||||
'(SELECT id, name FROM bar)'),
|
||||
reindent=True),
|
||||
('SELECT id,\n'
|
||||
' name\n'
|
||||
'FROM\n'
|
||||
' (SELECT id,\n'
|
||||
' name\n'
|
||||
' FROM bar)'))
|
||||
self.ndiffAssertEqual(
|
||||
sqlparse.format(('SELECT id, name FROM '
|
||||
'(SELECT id, name FROM bar) as foo'),
|
||||
reindent=True),
|
||||
('SELECT id,\n'
|
||||
' name\n'
|
||||
'FROM\n'
|
||||
' (SELECT id,\n'
|
||||
' name\n'
|
||||
' FROM bar) as foo'))
|
||||
|
||||
|
||||
def test_issue78():
|
||||
# the bug author provided this nice examples, let's use them!
|
||||
def _get_identifier(sql):
|
||||
p = sqlparse.parse(sql)[0]
|
||||
return p.tokens[2]
|
||||
results = (('get_name', 'z'),
|
||||
('get_real_name', 'y'),
|
||||
('get_parent_name', 'x'),
|
||||
('get_alias', 'z'),
|
||||
('get_typecast', 'text'))
|
||||
variants = (
|
||||
'select x.y::text as z from foo',
|
||||
'select x.y::text as "z" from foo',
|
||||
'select x."y"::text as z from foo',
|
||||
'select x."y"::text as "z" from foo',
|
||||
'select "x".y::text as z from foo',
|
||||
'select "x".y::text as "z" from foo',
|
||||
'select "x"."y"::text as z from foo',
|
||||
'select "x"."y"::text as "z" from foo',
|
||||
)
|
||||
for variant in variants:
|
||||
i = _get_identifier(variant)
|
||||
assert isinstance(i, sql.Identifier)
|
||||
for func_name, result in results:
|
||||
func = getattr(i, func_name)
|
||||
assert func() == result
|
||||
|
||||
|
||||
def test_issue83():
|
||||
sql = """
|
||||
CREATE OR REPLACE FUNCTION func_a(text)
|
||||
RETURNS boolean LANGUAGE plpgsql STRICT IMMUTABLE AS
|
||||
$_$
|
||||
BEGIN
|
||||
...
|
||||
END;
|
||||
$_$;
|
||||
|
||||
CREATE OR REPLACE FUNCTION func_b(text)
|
||||
RETURNS boolean LANGUAGE plpgsql STRICT IMMUTABLE AS
|
||||
$_$
|
||||
BEGIN
|
||||
...
|
||||
END;
|
||||
$_$;
|
||||
|
||||
ALTER TABLE..... ;"""
|
||||
t = sqlparse.split(sql)
|
||||
assert len(t) == 3
|
||||
|
||||
|
||||
def test_comment_encoding_when_reindent():
|
||||
# There was an UnicodeEncodeError in the reindent filter that
|
||||
# casted every comment followed by a keyword to str.
|
||||
sql = u'select foo -- Comment containing Ümläuts\nfrom bar'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
assert formatted == sql
|
||||
|
||||
|
||||
def test_parse_sql_with_binary():
|
||||
# See https://github.com/andialbrecht/sqlparse/pull/88
|
||||
digest = '\x82|\xcb\x0e\xea\x8aplL4\xa1h\x91\xf8N{'
|
||||
sql = 'select * from foo where bar = \'%s\'' % digest
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = 'select *\nfrom foo\nwhere bar = \'%s\'' % digest
|
||||
if sys.version_info < (3,):
|
||||
tformatted = tformatted.decode('unicode-escape')
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_dont_alias_keywords():
|
||||
# The _group_left_right function had a bug where the check for the
|
||||
# left side wasn't handled correctly. In one case this resulted in
|
||||
# a keyword turning into an identifier.
|
||||
p = sqlparse.parse('FROM AS foo')[0]
|
||||
assert len(p.tokens) == 5
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
assert p.tokens[2].ttype is T.Keyword
|
||||
|
||||
|
||||
def test_format_accepts_encoding(): # issue20
|
||||
sql = load_file('test_cp1251.sql', 'cp1251')
|
||||
formatted = sqlparse.format(sql, reindent=True, encoding='cp1251')
|
||||
if sys.version_info < (3,):
|
||||
tformatted = u'insert into foo\nvalues (1); -- Песня про надежду\n'
|
||||
else:
|
||||
tformatted = 'insert into foo\nvalues (1); -- Песня про надежду\n'
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_issue90():
|
||||
sql = ('UPDATE "gallery_photo" SET "owner_id" = 4018, "deleted_at" = NULL,'
|
||||
' "width" = NULL, "height" = NULL, "rating_votes" = 0,'
|
||||
' "rating_score" = 0, "thumbnail_width" = NULL,'
|
||||
' "thumbnail_height" = NULL, "price" = 1, "description" = NULL')
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = '\n'.join(['UPDATE "gallery_photo"',
|
||||
'SET "owner_id" = 4018,',
|
||||
' "deleted_at" = NULL,',
|
||||
' "width" = NULL,',
|
||||
' "height" = NULL,',
|
||||
' "rating_votes" = 0,',
|
||||
' "rating_score" = 0,',
|
||||
' "thumbnail_width" = NULL,',
|
||||
' "thumbnail_height" = NULL,',
|
||||
' "price" = 1,',
|
||||
' "description" = NULL'])
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_except_formatting():
|
||||
sql = 'SELECT 1 FROM foo WHERE 2 = 3 EXCEPT SELECT 2 FROM bar WHERE 1 = 2'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = '\n'.join([
|
||||
'SELECT 1',
|
||||
'FROM foo',
|
||||
'WHERE 2 = 3',
|
||||
'EXCEPT',
|
||||
'SELECT 2',
|
||||
'FROM bar',
|
||||
'WHERE 1 = 2'
|
||||
])
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_null_with_as():
|
||||
sql = 'SELECT NULL AS c1, NULL AS c2 FROM t1'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = '\n'.join([
|
||||
'SELECT NULL AS c1,',
|
||||
' NULL AS c2',
|
||||
'FROM t1'
|
||||
])
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_issue193_splitting_function():
|
||||
sql = """CREATE FUNCTION a(x VARCHAR(20)) RETURNS VARCHAR(20)
|
||||
BEGIN
|
||||
DECLARE y VARCHAR(20);
|
||||
RETURN x;
|
||||
END;
|
||||
SELECT * FROM a.b;"""
|
||||
splitted = sqlparse.split(sql)
|
||||
assert len(splitted) == 2
|
||||
|
||||
def test_issue194_splitting_function():
|
||||
sql = """CREATE FUNCTION a(x VARCHAR(20)) RETURNS VARCHAR(20)
|
||||
BEGIN
|
||||
DECLARE y VARCHAR(20);
|
||||
IF (1 = 1) THEN
|
||||
SET x = y;
|
||||
END IF;
|
||||
RETURN x;
|
||||
END;
|
||||
SELECT * FROM a.b;"""
|
||||
splitted = sqlparse.split(sql)
|
||||
assert len(splitted) == 2
|
||||
|
||||
|
||||
def test_issue186_get_type():
|
||||
sql = "-- comment\ninsert into foo"
|
||||
p = sqlparse.parse(sql)[0]
|
||||
assert p.get_type() == 'INSERT'
|
||||
@@ -1,153 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Tests splitting functions.
|
||||
|
||||
import unittest
|
||||
|
||||
from tests.utils import load_file, TestCaseBase
|
||||
|
||||
import sqlparse
|
||||
|
||||
|
||||
class SQLSplitTest(TestCaseBase):
|
||||
"""Tests sqlparse.sqlsplit()."""
|
||||
|
||||
_sql1 = 'select * from foo;'
|
||||
_sql2 = 'select * from bar;'
|
||||
|
||||
def test_split_semicolon(self):
|
||||
sql2 = 'select * from foo where bar = \'foo;bar\';'
|
||||
stmts = sqlparse.parse(''.join([self._sql1, sql2]))
|
||||
self.assertEqual(len(stmts), 2)
|
||||
self.ndiffAssertEqual(unicode(stmts[0]), self._sql1)
|
||||
self.ndiffAssertEqual(unicode(stmts[1]), sql2)
|
||||
|
||||
def test_split_backslash(self):
|
||||
stmts = sqlparse.parse(r"select '\\'; select '\''; select '\\\'';")
|
||||
self.assertEqual(len(stmts), 3)
|
||||
|
||||
def test_create_function(self):
|
||||
sql = load_file('function.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 1)
|
||||
self.ndiffAssertEqual(unicode(stmts[0]), sql)
|
||||
|
||||
def test_create_function_psql(self):
|
||||
sql = load_file('function_psql.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 1)
|
||||
self.ndiffAssertEqual(unicode(stmts[0]), sql)
|
||||
|
||||
def test_create_function_psql3(self):
|
||||
sql = load_file('function_psql3.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 1)
|
||||
self.ndiffAssertEqual(unicode(stmts[0]), sql)
|
||||
|
||||
def test_create_function_psql2(self):
|
||||
sql = load_file('function_psql2.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 1)
|
||||
self.ndiffAssertEqual(unicode(stmts[0]), sql)
|
||||
|
||||
def test_dashcomments(self):
|
||||
sql = load_file('dashcomment.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 3)
|
||||
self.ndiffAssertEqual(''.join(unicode(q) for q in stmts), sql)
|
||||
|
||||
def test_dashcomments_eol(self):
|
||||
stmts = sqlparse.parse('select foo; -- comment\n')
|
||||
self.assertEqual(len(stmts), 1)
|
||||
stmts = sqlparse.parse('select foo; -- comment\r')
|
||||
self.assertEqual(len(stmts), 1)
|
||||
stmts = sqlparse.parse('select foo; -- comment\r\n')
|
||||
self.assertEqual(len(stmts), 1)
|
||||
stmts = sqlparse.parse('select foo; -- comment')
|
||||
self.assertEqual(len(stmts), 1)
|
||||
|
||||
def test_begintag(self):
|
||||
sql = load_file('begintag.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 3)
|
||||
self.ndiffAssertEqual(''.join(unicode(q) for q in stmts), sql)
|
||||
|
||||
def test_begintag_2(self):
|
||||
sql = load_file('begintag_2.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 1)
|
||||
self.ndiffAssertEqual(''.join(unicode(q) for q in stmts), sql)
|
||||
|
||||
def test_dropif(self):
|
||||
sql = 'DROP TABLE IF EXISTS FOO;\n\nSELECT * FROM BAR;'
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
self.ndiffAssertEqual(''.join(unicode(q) for q in stmts), sql)
|
||||
|
||||
def test_comment_with_umlaut(self):
|
||||
sql = (u'select * from foo;\n'
|
||||
u'-- Testing an umlaut: ä\n'
|
||||
u'select * from bar;')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
self.ndiffAssertEqual(''.join(unicode(q) for q in stmts), sql)
|
||||
|
||||
def test_comment_end_of_line(self):
|
||||
sql = ('select * from foo; -- foo\n'
|
||||
'select * from bar;')
|
||||
stmts = sqlparse.parse(sql)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
self.ndiffAssertEqual(''.join(unicode(q) for q in stmts), sql)
|
||||
# make sure the comment belongs to first query
|
||||
self.ndiffAssertEqual(unicode(stmts[0]), 'select * from foo; -- foo\n')
|
||||
|
||||
def test_casewhen(self):
|
||||
sql = ('SELECT case when val = 1 then 2 else null end as foo;\n'
|
||||
'comment on table actor is \'The actor table.\';')
|
||||
stmts = sqlparse.split(sql)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
|
||||
def test_cursor_declare(self):
|
||||
sql = ('DECLARE CURSOR "foo" AS SELECT 1;\n'
|
||||
'SELECT 2;')
|
||||
stmts = sqlparse.split(sql)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
|
||||
def test_if_function(self): # see issue 33
|
||||
# don't let IF as a function confuse the splitter
|
||||
sql = ('CREATE TEMPORARY TABLE tmp '
|
||||
'SELECT IF(a=1, a, b) AS o FROM one; '
|
||||
'SELECT t FROM two')
|
||||
stmts = sqlparse.split(sql)
|
||||
self.assertEqual(len(stmts), 2)
|
||||
|
||||
def test_split_stream(self):
|
||||
import types
|
||||
from cStringIO import StringIO
|
||||
|
||||
stream = StringIO("SELECT 1; SELECT 2;")
|
||||
stmts = sqlparse.parsestream(stream)
|
||||
self.assertEqual(type(stmts), types.GeneratorType)
|
||||
self.assertEqual(len(list(stmts)), 2)
|
||||
|
||||
def test_encoding_parsestream(self):
|
||||
from cStringIO import StringIO
|
||||
stream = StringIO("SELECT 1; SELECT 2;")
|
||||
stmts = list(sqlparse.parsestream(stream))
|
||||
self.assertEqual(type(stmts[0].tokens[0].value), unicode)
|
||||
|
||||
def test_split_quotes_with_new_line(self):
|
||||
stmts = sqlparse.split('select "foo\nbar"')
|
||||
assert len(stmts) == 1
|
||||
assert stmts[0] == 'select "foo\nbar"'
|
||||
|
||||
stmts = sqlparse.split("select 'foo\n\bar'")
|
||||
assert len(stmts) == 1
|
||||
assert stmts[0] == "select 'foo\n\bar'"
|
||||
|
||||
|
||||
def test_split_simple():
|
||||
stmts = sqlparse.split('select * from foo; select * from bar;')
|
||||
assert len(stmts) == 2
|
||||
assert stmts[0] == 'select * from foo;'
|
||||
assert stmts[1] == 'select * from bar;'
|
||||
@@ -1,190 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import sys
|
||||
import types
|
||||
import unittest
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import lexer
|
||||
from sqlparse import sql
|
||||
from sqlparse.tokens import *
|
||||
|
||||
|
||||
class TestTokenize(unittest.TestCase):
|
||||
|
||||
def test_simple(self):
|
||||
s = 'select * from foo;'
|
||||
stream = lexer.tokenize(s)
|
||||
self.assert_(isinstance(stream, types.GeneratorType))
|
||||
tokens = list(stream)
|
||||
self.assertEqual(len(tokens), 8)
|
||||
self.assertEqual(len(tokens[0]), 2)
|
||||
self.assertEqual(tokens[0], (Keyword.DML, u'select'))
|
||||
self.assertEqual(tokens[-1], (Punctuation, u';'))
|
||||
|
||||
def test_backticks(self):
|
||||
s = '`foo`.`bar`'
|
||||
tokens = list(lexer.tokenize(s))
|
||||
self.assertEqual(len(tokens), 3)
|
||||
self.assertEqual(tokens[0], (Name, u'`foo`'))
|
||||
|
||||
def test_linebreaks(self): # issue1
|
||||
s = 'foo\nbar\n'
|
||||
tokens = lexer.tokenize(s)
|
||||
self.assertEqual(''.join(str(x[1]) for x in tokens), s)
|
||||
s = 'foo\rbar\r'
|
||||
tokens = lexer.tokenize(s)
|
||||
self.assertEqual(''.join(str(x[1]) for x in tokens), s)
|
||||
s = 'foo\r\nbar\r\n'
|
||||
tokens = lexer.tokenize(s)
|
||||
self.assertEqual(''.join(str(x[1]) for x in tokens), s)
|
||||
s = 'foo\r\nbar\n'
|
||||
tokens = lexer.tokenize(s)
|
||||
self.assertEqual(''.join(str(x[1]) for x in tokens), s)
|
||||
|
||||
def test_inline_keywords(self): # issue 7
|
||||
s = "create created_foo"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
self.assertEqual(len(tokens), 3)
|
||||
self.assertEqual(tokens[0][0], Keyword.DDL)
|
||||
self.assertEqual(tokens[2][0], Name)
|
||||
self.assertEqual(tokens[2][1], u'created_foo')
|
||||
s = "enddate"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
self.assertEqual(len(tokens), 1)
|
||||
self.assertEqual(tokens[0][0], Name)
|
||||
s = "join_col"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
self.assertEqual(len(tokens), 1)
|
||||
self.assertEqual(tokens[0][0], Name)
|
||||
s = "left join_col"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
self.assertEqual(len(tokens), 3)
|
||||
self.assertEqual(tokens[2][0], Name)
|
||||
self.assertEqual(tokens[2][1], 'join_col')
|
||||
|
||||
def test_negative_numbers(self):
|
||||
s = "values(-1)"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
self.assertEqual(len(tokens), 4)
|
||||
self.assertEqual(tokens[2][0], Number.Integer)
|
||||
self.assertEqual(tokens[2][1], '-1')
|
||||
|
||||
# Somehow this test fails on Python 3.2
|
||||
@pytest.mark.skipif('sys.version_info >= (3,0)')
|
||||
def test_tab_expansion(self):
|
||||
s = "\t"
|
||||
lex = lexer.Lexer()
|
||||
lex.tabsize = 5
|
||||
tokens = list(lex.get_tokens(s))
|
||||
self.assertEqual(tokens[0][1], " " * 5)
|
||||
|
||||
|
||||
class TestToken(unittest.TestCase):
|
||||
|
||||
def test_str(self):
|
||||
token = sql.Token(None, 'FoO')
|
||||
self.assertEqual(str(token), 'FoO')
|
||||
|
||||
def test_repr(self):
|
||||
token = sql.Token(Keyword, 'foo')
|
||||
tst = "<Keyword 'foo' at 0x"
|
||||
self.assertEqual(repr(token)[:len(tst)], tst)
|
||||
token = sql.Token(Keyword, '1234567890')
|
||||
tst = "<Keyword '123456...' at 0x"
|
||||
self.assertEqual(repr(token)[:len(tst)], tst)
|
||||
|
||||
def test_flatten(self):
|
||||
token = sql.Token(Keyword, 'foo')
|
||||
gen = token.flatten()
|
||||
self.assertEqual(type(gen), types.GeneratorType)
|
||||
lgen = list(gen)
|
||||
self.assertEqual(lgen, [token])
|
||||
|
||||
|
||||
class TestTokenList(unittest.TestCase):
|
||||
|
||||
def test_repr(self):
|
||||
p = sqlparse.parse('foo, bar, baz')[0]
|
||||
tst = "<IdentifierList 'foo, b...' at 0x"
|
||||
self.assertEqual(repr(p.tokens[0])[:len(tst)], tst)
|
||||
|
||||
def test_token_first(self):
|
||||
p = sqlparse.parse(' select foo')[0]
|
||||
first = p.token_first()
|
||||
self.assertEqual(first.value, 'select')
|
||||
self.assertEqual(p.token_first(ignore_whitespace=False).value, ' ')
|
||||
self.assertEqual(sql.TokenList([]).token_first(), None)
|
||||
|
||||
def test_token_matching(self):
|
||||
t1 = sql.Token(Keyword, 'foo')
|
||||
t2 = sql.Token(Punctuation, ',')
|
||||
x = sql.TokenList([t1, t2])
|
||||
self.assertEqual(x.token_matching(0, [lambda t: t.ttype is Keyword]),
|
||||
t1)
|
||||
self.assertEqual(x.token_matching(0,
|
||||
[lambda t: t.ttype is Punctuation]),
|
||||
t2)
|
||||
self.assertEqual(x.token_matching(1, [lambda t: t.ttype is Keyword]),
|
||||
None)
|
||||
|
||||
|
||||
class TestStream(unittest.TestCase):
|
||||
def test_simple(self):
|
||||
from cStringIO import StringIO
|
||||
|
||||
stream = StringIO("SELECT 1; SELECT 2;")
|
||||
lex = lexer.Lexer()
|
||||
|
||||
tokens = lex.get_tokens(stream)
|
||||
self.assertEqual(len(list(tokens)), 9)
|
||||
|
||||
stream.seek(0)
|
||||
lex.bufsize = 4
|
||||
tokens = list(lex.get_tokens(stream))
|
||||
self.assertEqual(len(tokens), 9)
|
||||
|
||||
stream.seek(0)
|
||||
lex.bufsize = len(stream.getvalue())
|
||||
tokens = list(lex.get_tokens(stream))
|
||||
self.assertEqual(len(tokens), 9)
|
||||
|
||||
def test_error(self):
|
||||
from cStringIO import StringIO
|
||||
|
||||
stream = StringIO("FOOBAR{")
|
||||
|
||||
lex = lexer.Lexer()
|
||||
lex.bufsize = 4
|
||||
tokens = list(lex.get_tokens(stream))
|
||||
self.assertEqual(len(tokens), 2)
|
||||
self.assertEqual(tokens[1][0], Error)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('expr', ['JOIN', 'LEFT JOIN', 'LEFT OUTER JOIN',
|
||||
'FULL OUTER JOIN', 'NATURAL JOIN',
|
||||
'CROSS JOIN', 'STRAIGHT JOIN',
|
||||
'INNER JOIN', 'LEFT INNER JOIN'])
|
||||
def test_parse_join(expr):
|
||||
p = sqlparse.parse('%s foo' % expr)[0]
|
||||
assert len(p.tokens) == 3
|
||||
assert p.tokens[0].ttype is Keyword
|
||||
|
||||
|
||||
def test_parse_endifloop():
|
||||
p = sqlparse.parse('END IF')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is Keyword
|
||||
p = sqlparse.parse('END IF')[0]
|
||||
assert len(p.tokens) == 1
|
||||
p = sqlparse.parse('END\t\nIF')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is Keyword
|
||||
p = sqlparse.parse('END LOOP')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is Keyword
|
||||
p = sqlparse.parse('END LOOP')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is Keyword
|
||||
@@ -1,46 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""Helpers for testing."""
|
||||
|
||||
import codecs
|
||||
import difflib
|
||||
import os
|
||||
import unittest
|
||||
from StringIO import StringIO
|
||||
|
||||
import sqlparse.utils
|
||||
|
||||
NL = '\n'
|
||||
DIR_PATH = os.path.abspath(os.path.dirname(__file__))
|
||||
PARENT_DIR = os.path.dirname(DIR_PATH)
|
||||
FILES_DIR = os.path.join(DIR_PATH, 'files')
|
||||
|
||||
|
||||
def load_file(filename, encoding='utf-8'):
|
||||
"""Opens filename with encoding and return it's contents."""
|
||||
f = codecs.open(os.path.join(FILES_DIR, filename), 'r', encoding)
|
||||
data = f.read()
|
||||
f.close()
|
||||
return data
|
||||
|
||||
|
||||
class TestCaseBase(unittest.TestCase):
|
||||
"""Base class for test cases with some additional checks."""
|
||||
|
||||
# Adopted from Python's tests.
|
||||
def ndiffAssertEqual(self, first, second):
|
||||
"""Like failUnlessEqual except use ndiff for readable output."""
|
||||
if first != second:
|
||||
sfirst = unicode(first)
|
||||
ssecond = unicode(second)
|
||||
# Using the built-in .splitlines() method here will cause incorrect
|
||||
# results when splitting statements that have quoted CR/CR+LF
|
||||
# characters.
|
||||
sfirst = sqlparse.utils.split_unquoted_newlines(sfirst)
|
||||
ssecond = sqlparse.utils.split_unquoted_newlines(ssecond)
|
||||
diff = difflib.ndiff(sfirst, ssecond)
|
||||
fp = StringIO()
|
||||
fp.write(NL)
|
||||
fp.write(NL.join(diff))
|
||||
print fp.getvalue()
|
||||
raise self.failureException, fp.getvalue()
|
||||
@@ -1,37 +0,0 @@
|
||||
[tox]
|
||||
envlist=py26,py27,py32,py33,py34,pypy
|
||||
|
||||
[testenv]
|
||||
deps=
|
||||
pytest
|
||||
pytest-cov
|
||||
commands=
|
||||
sqlformat --version # Sanity check.
|
||||
py.test --cov=sqlparse/ tests
|
||||
|
||||
[testenv:py32]
|
||||
changedir={envdir}
|
||||
commands=
|
||||
sqlformat --version # Sanity check.
|
||||
rm -rf tests/
|
||||
cp -r {toxinidir}/tests/ tests/
|
||||
2to3 -w --no-diffs -n tests/
|
||||
py.test --cov={envdir}/lib/python3.2/site-packages/sqlparse/ tests
|
||||
|
||||
[testenv:py33]
|
||||
changedir={envdir}
|
||||
commands=
|
||||
sqlformat --version # Sanity check.
|
||||
rm -rf tests/
|
||||
cp -r {toxinidir}/tests/ tests/
|
||||
2to3 -w --no-diffs -n tests/
|
||||
py.test --cov={envdir}/lib/python3.3/site-packages/sqlparse/ tests
|
||||
|
||||
[testenv:py34]
|
||||
changedir={envdir}
|
||||
commands=
|
||||
sqlformat --version # Sanity check.
|
||||
rm -rf tests/
|
||||
cp -r {toxinidir}/tests/ tests/
|
||||
2to3 -w --no-diffs -n tests/
|
||||
py.test --cov={envdir}/lib/python3.4/site-packages/sqlparse/ tests
|
||||
67
shell/ext-py/sqlparse-0.3.1/AUTHORS
Normal file
67
shell/ext-py/sqlparse-0.3.1/AUTHORS
Normal file
@@ -0,0 +1,67 @@
|
||||
python-sqlparse is written and maintained by Andi Albrecht <albrecht.andi@gmail.com>.
|
||||
|
||||
This module contains code (namely the lexer and filter mechanism) from
|
||||
the pygments project that was written by Georg Brandl.
|
||||
|
||||
This module contains code (Python 2/3 compatibility) from the six
|
||||
project: https://bitbucket.org/gutworth/six.
|
||||
|
||||
Alphabetical list of contributors:
|
||||
* Adam Greenhall <agreenhall@lyft.com>
|
||||
* Alexander Beedie <ayembee@gmail.com>
|
||||
* Alexey Malyshev <nostrict@gmail.com>
|
||||
* andrew deryabin <github@djsf.com>
|
||||
* Andrew Tipton <andrew.tipton@compareglobalgroup.com>
|
||||
* atronah <atronah.ds@gmail.com>
|
||||
* casey <casey@cloudera.com>
|
||||
* Cauê Beloni <cbeloni@gmail.com>
|
||||
* circld <circld1@gmail.com>
|
||||
* Corey Zumar <corey.zumar@databricks.com>
|
||||
* Cristian Orellana <cristiano@groupon.com>
|
||||
* Dag Wieers <dag@wieers.com>
|
||||
* Darik Gamble <darik.gamble@gmail.com>
|
||||
* Demetrio92 <Demetrio.Rodriguez.T@gmail.com>
|
||||
* Dennis Taylor <dennis.taylor@clio.com>
|
||||
* Dvořák Václav <Vaclav.Dvorak@ysoft.com>
|
||||
* Florian Bauer <florian.bauer@zmdi.com>
|
||||
* Fredy Wijaya <fredy.wijaya@gmail.com>
|
||||
* Gavin Wahl <gwahl@fusionbox.com>
|
||||
* Ian Robertson <ian.robertson@capitalone.com>
|
||||
* JacekPliszka <Jacek.Pliszka@gmail.com>
|
||||
* Jesús Leganés Combarro "Piranna" <piranna@gmail.com>
|
||||
* Johannes Hoff <johshoff@gmail.com>
|
||||
* John Bodley <john.bodley@airbnb.com>
|
||||
* Jon Dufresne <jon.dufresne@gmail.com>
|
||||
* Josh Soref <jsoref@users.noreply.github.com>
|
||||
* Kevin Jing Qiu <kevin.jing.qiu@gmail.com>
|
||||
* koljonen <koljonen@outlook.com>
|
||||
* Likai Liu <liulk@likai.org>
|
||||
* mathilde.oustlant <mathilde.oustlant@ext.cdiscount.com>
|
||||
* Michael Schuller <chick@mschuller.net>
|
||||
* Mike Amy <cocoade@googlemail.com>
|
||||
* mulos <daniel.strackbein@gmail.com>
|
||||
* Oleg Broytman <phd@phdru.name>
|
||||
* Patrick Schemitz <patrick.schemitz@digitalbriefkasten.de>
|
||||
* Pi Delport <pjdelport@gmail.com>
|
||||
* Prudhvi Vatala <pvatala@gmail.com>
|
||||
* quest <quest@wonky.windwards.net>
|
||||
* Robert Nix <com.github@rnix.org>
|
||||
* Rocky Meza <rmeza@fusionbox.com>
|
||||
* Romain Rigaux <romain.rigaux@gmail.com>
|
||||
* Rowan Seymour <rowanseymour@gmail.com>
|
||||
* Ryan Wooden <rygwdn@gmail.com>
|
||||
* saaj <id@saaj.me>
|
||||
* Shen Longxing <shenlongxing2012@gmail.com>
|
||||
* Sjoerd Job Postmus
|
||||
* Soloman Weng <soloman1124@gmail.com>
|
||||
* spigwitmer <itgpmc@gmail.com>
|
||||
* Tao Wang <twang2218@gmail.com>
|
||||
* Tenghuan <tenghuanhe@gmail.com>
|
||||
* Tim Graham <timograham@gmail.com>
|
||||
* Victor Hahn <info@victor-hahn.de>
|
||||
* Victor Uriarte <vmuriart@gmail.com>
|
||||
* Ville Skyttä <ville.skytta@iki.fi>
|
||||
* vthriller <farreva232@yandex.ru>
|
||||
* wayne.wuw <wayne.wuw@alibaba-inc.com>
|
||||
* William Ivanski <william.ivanski@gmail.com>
|
||||
* Yago Riveiro <yago.riveiro@gmail.com>
|
||||
522
shell/ext-py/sqlparse-0.3.1/CHANGELOG
Normal file
522
shell/ext-py/sqlparse-0.3.1/CHANGELOG
Normal file
@@ -0,0 +1,522 @@
|
||||
Release 0.3.1 (Feb 29, 2020)
|
||||
----------------------------
|
||||
|
||||
Enhancements
|
||||
|
||||
* Add HQL keywords (pr475, by matwalk).
|
||||
* Add support for time zone casts (issue489).
|
||||
* Enhance formatting of AS keyword (issue507, by john-bodley).
|
||||
* Stabilize grouping engine when parsing invalid SQL statements.
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix splitting of SQL with multiple statements inside
|
||||
parentheses (issue485, pr486 by win39).
|
||||
* Correctly identify NULLS FIRST / NULLS LAST as keywords (issue487).
|
||||
* Fix splitting of SQL statements that contain dollar signs in
|
||||
identifiers (issue491).
|
||||
* Remove support for parsing double slash comments introduced in
|
||||
0.3.0 (issue456) as it had some side-effects with other dialects and
|
||||
doesn't seem to be widely used (issue476).
|
||||
* Restrict detection of alias names to objects that acutally could
|
||||
have an alias (issue455, adopted some parts of pr509 by john-bodley).
|
||||
* Fix parsing of date/time literals (issue438, by vashek).
|
||||
* Fix initialization of TokenList (issue499, pr505 by john-bodley).
|
||||
* Fix parsing of LIKE (issue493, pr525 by dbczumar).
|
||||
* Improve parsing of identifiers (pr527 by liulk).
|
||||
|
||||
|
||||
Release 0.3.0 (Mar 11, 2019)
|
||||
----------------------------
|
||||
|
||||
Notable Changes
|
||||
|
||||
* Remove support for Python 3.3.
|
||||
|
||||
Enhancements
|
||||
|
||||
* New formatting option "--indent_after_first" (pr345, by johshoff).
|
||||
* New formatting option "--indent_columns" (pr393, by digitalarbeiter).
|
||||
* Add UPSERT keyword (issue408).
|
||||
* Strip multiple whitespace within parentheses (issue473, by john-bodley).
|
||||
* Support double slash (//) comments (issue456, by theianrobertson).
|
||||
* Support for Calcite temporal keywords (pr468, by john-bodley).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix occasional IndexError (pr390, by circld, issue313).
|
||||
* Fix incorrect splitting of strings containing new lines (pr396, by fredyw).
|
||||
* Fix reindent issue for parenthesis (issue427, by fredyw).
|
||||
* Fix from( parsing issue (issue446, by fredyw) .
|
||||
* Fix for get_real_name() to return correct name (issue369, by fredyw).
|
||||
* Wrap function params when wrap_after is set (pr398, by soloman1124).
|
||||
* Fix parsing of "WHEN name" clauses (pr418, by andrew deryabin).
|
||||
* Add missing EXPLAIN keyword (issue421).
|
||||
* Fix issue with strip_comments causing a syntax error (issue425, by fredyw).
|
||||
* Fix formatting on INSERT which caused staircase effect on values (issue329,
|
||||
by fredyw).
|
||||
* Avoid formatting of psql commands (issue469).
|
||||
|
||||
Internal Changes
|
||||
|
||||
* Unify handling of GROUP BY/ORDER BY (pr457, by john-bodley).
|
||||
* Remove unnecessary compat shim for bytes (pr453, by jdufresne).
|
||||
|
||||
|
||||
Release 0.2.4 (Sep 27, 2017)
|
||||
----------------------------
|
||||
|
||||
Enhancements
|
||||
|
||||
* Add more keywords for MySQL table options (pr328, pr333, by phdru).
|
||||
* Add more PL/pgSQL keywords (pr357, by Demetrio92).
|
||||
* Improve parsing of floats (pr330, by atronah).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix parsing of MySQL table names starting with digits (issue337).
|
||||
* Fix detection of identifiers using comparisons (issue327).
|
||||
* Fix parsing of UNION ALL after WHERE (issue349).
|
||||
* Fix handling of semicolon in assignments (issue359, issue358).
|
||||
|
||||
|
||||
|
||||
Release 0.2.3 (Mar 02, 2017)
|
||||
----------------------------
|
||||
|
||||
Enhancements
|
||||
|
||||
* New command line option "--encoding" (by twang2218, pr317).
|
||||
* Support CONCURRENTLY keyword (issue322, by rowanseymour).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix some edge-cases when parsing invalid SQL statements.
|
||||
* Fix indentation of LIMIT (by romainr, issue320).
|
||||
* Fix parsing of INTO keyword (issue324).
|
||||
|
||||
Internal Changes
|
||||
|
||||
* Several improvements regarding encodings.
|
||||
|
||||
|
||||
Release 0.2.2 (Oct 22, 2016)
|
||||
----------------------------
|
||||
|
||||
Enhancements
|
||||
|
||||
* Add comma_first option: When splitting list "comma first" notation
|
||||
is used (issue141).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix parsing of incomplete AS (issue284, by vmuriart).
|
||||
* Fix parsing of Oracle names containing dollars (issue291).
|
||||
* Fix parsing of UNION ALL (issue294).
|
||||
* Fix grouping of identifiers containing typecasts (issue297).
|
||||
* Add Changelog to sdist again (issue302).
|
||||
|
||||
Internal Changes
|
||||
|
||||
* `is_whitespace` and `is_group` changed into properties
|
||||
|
||||
|
||||
Release 0.2.1 (Aug 13, 2016)
|
||||
----------------------------
|
||||
|
||||
Notable Changes
|
||||
|
||||
* PostgreSQL: Function bodys are parsed as literal string. Previously
|
||||
sqlparse assumed that all function bodys are parsable psql
|
||||
strings (see issue277).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix a regression to parse streams again (issue273, reported and
|
||||
test case by gmccreight).
|
||||
* Improve Python 2/3 compatibility when using parsestream (issue190,
|
||||
by phdru).
|
||||
* Improve splitting of PostgreSQL functions (issue277).
|
||||
|
||||
|
||||
Release 0.2.0 (Jul 20, 2016)
|
||||
----------------------------
|
||||
|
||||
IMPORTANT: The supported Python versions have changed with this release.
|
||||
sqlparse 0.2.x supports Python 2.7 and Python >= 3.3.
|
||||
|
||||
Thanks to the many contributors for writing bug reports and working
|
||||
on pull requests who made this version possible!
|
||||
|
||||
Internal Changes
|
||||
|
||||
* sqlparse.SQLParseError was removed from top-level module and moved to
|
||||
sqlparse.exceptions.
|
||||
* sqlparse.sql.Token.to_unicode was removed.
|
||||
* The signature of a filter's process method has changed from
|
||||
process(stack, stream) -> to process(stream). Stack was never used at
|
||||
all.
|
||||
* Lots of code cleanups and modernization (thanks esp. to vmuriart!).
|
||||
* Improved grouping performance. (sjoerdjob)
|
||||
|
||||
Enhancements
|
||||
|
||||
* Support WHILE loops (issue215, by shenlongxing).
|
||||
* Better support for CTEs (issue217, by Andrew Tipton).
|
||||
* Recognize USING as a keyword more consistently (issue236, by koljonen).
|
||||
* Improve alignment of columns (issue207, issue235, by vmuriat).
|
||||
* Add wrap_after option for better alignment when formatting
|
||||
lists (issue248, by Dennis Taylor).
|
||||
* Add reindent-aligned option for alternate formatting (Adam Greenhall)
|
||||
* Improved grouping of operations (issue211, by vmuriat).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Leading whitespaces are now removed when format() is called with
|
||||
strip_whitespace=True (issue213, by shenlongxing).
|
||||
* Fix typo in keywords list (issue229, by cbeloni).
|
||||
* Fix parsing of functions in comparisons (issue230, by saaj).
|
||||
* Fix grouping of identifiers (issue233).
|
||||
* Fix parsing of CREATE TABLE statements (issue242, by Tenghuan).
|
||||
* Minor bug fixes (issue101).
|
||||
* Improve formatting of CASE WHEN constructs (issue164, by vmuriat).
|
||||
|
||||
|
||||
Release 0.1.19 (Mar 07, 2016)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix IndexError when statement contains WITH clauses (issue205).
|
||||
|
||||
|
||||
Release 0.1.18 (Oct 25, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Remove universal wheel support, added in 0.1.17 by mistake.
|
||||
|
||||
|
||||
Release 0.1.17 (Oct 24, 2015)
|
||||
-----------------------------
|
||||
|
||||
Enhancements
|
||||
|
||||
* Speed up parsing of large SQL statements (pull request: issue201, fixes the
|
||||
following issues: issue199, issue135, issue62, issue41, by Ryan Wooden).
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix another splitter bug regarding DECLARE (issue194).
|
||||
|
||||
Misc
|
||||
|
||||
* Packages on PyPI are signed from now on.
|
||||
|
||||
|
||||
Release 0.1.16 (Jul 26, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix a regression in get_alias() introduced in 0.1.15 (issue185).
|
||||
* Fix a bug in the splitter regarding DECLARE (issue193).
|
||||
* sqlformat command line tool doesn't duplicate newlines anymore (issue191).
|
||||
* Don't mix up MySQL comments starting with hash and MSSQL
|
||||
temp tables (issue192).
|
||||
* Statement.get_type() now ignores comments at the beginning of
|
||||
a statement (issue186).
|
||||
|
||||
|
||||
Release 0.1.15 (Apr 15, 2015)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix a regression for identifiers with square bracktes
|
||||
notation (issue153, by darikg).
|
||||
* Add missing SQL types (issue154, issue155, issue156, by jukebox).
|
||||
* Fix parsing of multi-line comments (issue172, by JacekPliszka).
|
||||
* Fix parsing of escaped backslashes (issue174, by caseyching).
|
||||
* Fix parsing of identifiers starting with underscore (issue175).
|
||||
* Fix misinterpretation of IN keyword (issue183).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Improve formatting of HAVING statements.
|
||||
* Improve parsing of inline comments (issue163).
|
||||
* Group comments to parent object (issue128, issue160).
|
||||
* Add double precision builtin (issue169, by darikg).
|
||||
* Add support for square bracket array indexing (issue170, issue176,
|
||||
issue177 by darikg).
|
||||
* Improve grouping of aliased elements (issue167, by darikg).
|
||||
* Support comments starting with '#' character (issue178).
|
||||
|
||||
|
||||
Release 0.1.14 (Nov 30, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Floats in UPDATE statements are now handled correctly (issue145).
|
||||
* Properly handle string literals in comparisons (issue148, change proposed
|
||||
by aadis).
|
||||
* Fix indentation when using tabs (issue146).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Improved formatting in list when newlines precede commas (issue140).
|
||||
|
||||
|
||||
Release 0.1.13 (Oct 09, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix a regression in handling of NULL keywords introduced in 0.1.12.
|
||||
|
||||
|
||||
Release 0.1.12 (Sep 20, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix handling of NULL keywords in aliased identifiers.
|
||||
* Fix SerializerUnicode to split unquoted newlines (issue131, by Michael Schuller).
|
||||
* Fix handling of modulo operators without spaces (by gavinwahl).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Improve parsing of identifier lists containing placeholders.
|
||||
* Speed up query parsing of unquoted lines (by Michael Schuller).
|
||||
|
||||
|
||||
Release 0.1.11 (Feb 07, 2014)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix incorrect parsing of string literals containing line breaks (issue118).
|
||||
* Fix typo in keywords, add MERGE, COLLECT keywords (issue122/124,
|
||||
by Cristian Orellana).
|
||||
* Improve parsing of string literals in columns.
|
||||
* Fix parsing and formatting of statements containing EXCEPT keyword.
|
||||
* Fix Function.get_parameters() (issue126/127, by spigwitmer).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Classify DML keywords (issue116, by Victor Hahn).
|
||||
* Add missing FOREACH keyword.
|
||||
* Grouping of BEGIN/END blocks.
|
||||
|
||||
Other
|
||||
|
||||
* Python 2.5 isn't automatically tested anymore, neither Travis nor Tox
|
||||
still support it out of the box.
|
||||
|
||||
|
||||
Release 0.1.10 (Nov 02, 2013)
|
||||
-----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Removed buffered reading again, it obviously causes wrong parsing in some rare
|
||||
cases (issue114).
|
||||
* Fix regression in setup.py introduced 10 months ago (issue115).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Improved support for JOINs, by Alexander Beedie.
|
||||
|
||||
|
||||
Release 0.1.9 (Sep 28, 2013)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix an regression introduced in 0.1.5 where sqlparse didn't properly
|
||||
distinguished between single and double quoted strings when tagging
|
||||
identifier (issue111).
|
||||
|
||||
Enhancements
|
||||
|
||||
* New option to truncate long string literals when formatting.
|
||||
* Scientific numbers are pares correctly (issue107).
|
||||
* Support for arithmetic expressions (issue109, issue106; by prudhvi).
|
||||
|
||||
|
||||
Release 0.1.8 (Jun 29, 2013)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Whitespaces within certain keywords are now allowed (issue97, patch proposed
|
||||
by xcombelle).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Improve parsing of assignments in UPDATE statements (issue90).
|
||||
* Add STRAIGHT_JOIN statement (by Yago Riveiro).
|
||||
* Function.get_parameters() now returns the parameter if only one parameter is
|
||||
given (issue94, by wayne.wuw).
|
||||
* sqlparse.split() now removes leading and trailing whitespaces from split
|
||||
statements.
|
||||
* Add USE as keyword token (by mulos).
|
||||
* Improve parsing of PEP249-style placeholders (issue103).
|
||||
|
||||
|
||||
Release 0.1.7 (Apr 06, 2013)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix Python 3 compatibility of sqlformat script (by Pi Delport).
|
||||
* Fix parsing of SQL statements that contain binary data (by Alexey
|
||||
Malyshev).
|
||||
* Fix a bug where keywords were identified as aliased identifiers in
|
||||
invalid SQL statements.
|
||||
* Fix parsing of identifier lists where identifiers are keywords too
|
||||
(issue10).
|
||||
|
||||
Enhancements
|
||||
|
||||
* Top-level API functions now accept encoding keyword to parse
|
||||
statements in certain encodings more reliable (issue20).
|
||||
* Improve parsing speed when SQL contains CLOBs or BLOBs (issue86).
|
||||
* Improve formatting of ORDER BY clauses (issue89).
|
||||
* Formatter now tries to detect runaway indentations caused by
|
||||
parsing errors or invalid SQL statements. When re-indenting such
|
||||
statements the formatter flips back to column 0 before going crazy.
|
||||
|
||||
Other
|
||||
|
||||
* Documentation updates.
|
||||
|
||||
|
||||
Release 0.1.6 (Jan 01, 2013)
|
||||
----------------------------
|
||||
|
||||
sqlparse is now compatible with Python 3 without any patches. The
|
||||
Python 3 version is generated during install by 2to3. You'll need
|
||||
distribute to install sqlparse for Python 3.
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fix parsing error with dollar-quoted procedure bodies (issue83).
|
||||
|
||||
Other
|
||||
|
||||
* Documentation updates.
|
||||
* Test suite now uses tox and pytest.
|
||||
* py3k fixes (by vthriller).
|
||||
* py3k fixes in setup.py (by Florian Bauer).
|
||||
* setup.py now requires distribute (by Florian Bauer).
|
||||
|
||||
|
||||
Release 0.1.5 (Nov 13, 2012)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Improve handling of quoted identifiers (issue78).
|
||||
* Improve grouping and formatting of identifiers with operators (issue53).
|
||||
* Improve grouping and formatting of concatenated strings (issue53).
|
||||
* Improve handling of varchar() (by Mike Amy).
|
||||
* Clean up handling of various SQL elements.
|
||||
* Switch to pytest and clean up tests.
|
||||
* Several minor fixes.
|
||||
|
||||
Other
|
||||
|
||||
* Deprecate sqlparse.SQLParseError. Please use
|
||||
sqlparse.exceptions.SQLParseError instead.
|
||||
* Add caching to speed up processing.
|
||||
* Add experimental filters for token processing.
|
||||
* Add sqlformat.parsestream (by quest).
|
||||
|
||||
|
||||
Release 0.1.4 (Apr 20, 2012)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Avoid "stair case" effects when identifiers, functions,
|
||||
placeholders or keywords are mixed in identifier lists (issue45,
|
||||
issue49, issue52) and when asterisks are used as operators
|
||||
(issue58).
|
||||
* Make keyword detection more restrict (issue47).
|
||||
* Improve handling of CASE statements (issue46).
|
||||
* Fix statement splitting when parsing recursive statements (issue57,
|
||||
thanks to piranna).
|
||||
* Fix for negative numbers (issue56, thanks to kevinjqiu).
|
||||
* Pretty format comments in identifier lists (issue59).
|
||||
* Several minor bug fixes and improvements.
|
||||
|
||||
|
||||
Release 0.1.3 (Jul 29, 2011)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Improve parsing of floats (thanks to Kris).
|
||||
* When formatting a statement a space before LIMIT was removed (issue35).
|
||||
* Fix strip_comments flag (issue38, reported by ooberm...@gmail.com).
|
||||
* Avoid parsing names as keywords (issue39, reported by djo...@taket.org).
|
||||
* Make sure identifier lists in subselects are grouped (issue40,
|
||||
reported by djo...@taket.org).
|
||||
* Split statements with IF as functions correctly (issue33 and
|
||||
issue29, reported by charles....@unige.ch).
|
||||
* Relax detection of keywords, esp. when used as function names
|
||||
(issue36, nyuhu...@gmail.com).
|
||||
* Don't treat single characters as keywords (issue32).
|
||||
* Improve parsing of stand-alone comments (issue26).
|
||||
* Detection of placeholders in paramterized queries (issue22,
|
||||
reported by Glyph Lefkowitz).
|
||||
* Add parsing of MS Access column names with braces (issue27,
|
||||
reported by frankz...@gmail.com).
|
||||
|
||||
Other
|
||||
|
||||
* Replace Django by Flask in App Engine frontend (issue11).
|
||||
|
||||
|
||||
Release 0.1.2 (Nov 23, 2010)
|
||||
----------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Fixed incorrect detection of keyword fragments embed in names (issue7,
|
||||
reported and initial patch by andyboyko).
|
||||
* Stricter detection of identifier aliases (issue8, reported by estama).
|
||||
* WHERE grouping consumed closing parenthesis (issue9, reported by estama).
|
||||
* Fixed an issue with trailing whitespaces (reported by Kris).
|
||||
* Better detection of escaped single quotes (issue13, reported by
|
||||
Martin Brochhaus, patch by bluemaro with test case by Dan Carley).
|
||||
* Ignore identifier in double-quotes when changing cases (issue 21).
|
||||
* Lots of minor fixes targeting encoding, indentation, statement
|
||||
parsing and more (issues 12, 14, 15, 16, 18, 19).
|
||||
* Code cleanup with a pinch of refactoring.
|
||||
|
||||
|
||||
Release 0.1.1 (May 6, 2009)
|
||||
---------------------------
|
||||
|
||||
Bug Fixes
|
||||
|
||||
* Lexers preserves original line breaks (issue1).
|
||||
* Improved identifier parsing: backtick quotes, wildcards, T-SQL variables
|
||||
prefixed with @.
|
||||
* Improved parsing of identifier lists (issue2).
|
||||
* Recursive recognition of AS (issue4) and CASE.
|
||||
* Improved support for UPDATE statements.
|
||||
|
||||
Other
|
||||
|
||||
* Code cleanup and better test coverage.
|
||||
|
||||
|
||||
Release 0.1.0 (Apr 8, 2009)
|
||||
---------------------------
|
||||
|
||||
Initial release.
|
||||
@@ -1,4 +1,4 @@
|
||||
Copyright (c) 2009, Andi Albrecht <albrecht.andi@gmail.com>
|
||||
Copyright (c) 2016, Andi Albrecht <albrecht.andi@gmail.com>
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification,
|
||||
@@ -2,10 +2,10 @@ recursive-include docs source/*
|
||||
include docs/sqlformat.1
|
||||
include docs/Makefile
|
||||
recursive-include tests *.py *.sql
|
||||
include COPYING
|
||||
include LICENSE
|
||||
include TODO
|
||||
include AUTHORS
|
||||
include CHANGES
|
||||
include CHANGELOG
|
||||
include Makefile
|
||||
include pytest.ini
|
||||
include setup.cfg
|
||||
include tox.ini
|
||||
77
shell/ext-py/sqlparse-0.3.1/README.rst
Normal file
77
shell/ext-py/sqlparse-0.3.1/README.rst
Normal file
@@ -0,0 +1,77 @@
|
||||
python-sqlparse - Parse SQL statements
|
||||
======================================
|
||||
|
||||
|buildstatus|_
|
||||
|coverage|_
|
||||
|
||||
.. docincludebegin
|
||||
|
||||
sqlparse is a non-validating SQL parser for Python.
|
||||
It provides support for parsing, splitting and formatting SQL statements.
|
||||
|
||||
The module is compatible with Python 2.7 and Python 3 (>= 3.4)
|
||||
and released under the terms of the `New BSD license
|
||||
<https://opensource.org/licenses/BSD-3-Clause>`_.
|
||||
|
||||
.. note::
|
||||
|
||||
Support for Python<3.4 (including 2.x) will be dropped soon.
|
||||
|
||||
Visit the project page at https://github.com/andialbrecht/sqlparse for
|
||||
further information about this project.
|
||||
|
||||
|
||||
Quick Start
|
||||
-----------
|
||||
|
||||
.. code-block:: sh
|
||||
|
||||
$ pip install sqlparse
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
>>> import sqlparse
|
||||
|
||||
>>> # Split a string containing two SQL statements:
|
||||
>>> raw = 'select * from foo; select * from bar;'
|
||||
>>> statements = sqlparse.split(raw)
|
||||
>>> statements
|
||||
['select * from foo;', 'select * from bar;']
|
||||
|
||||
>>> # Format the first statement and print it out:
|
||||
>>> first = statements[0]
|
||||
>>> print(sqlparse.format(first, reindent=True, keyword_case='upper'))
|
||||
SELECT *
|
||||
FROM foo;
|
||||
|
||||
>>> # Parsing a SQL statement:
|
||||
>>> parsed = sqlparse.parse('select * from foo')[0]
|
||||
>>> parsed.tokens
|
||||
[<DML 'select' at 0x7f22c5e15368>, <Whitespace ' ' at 0x7f22c5e153b0>, <Wildcard '*' … ]
|
||||
>>>
|
||||
|
||||
Links
|
||||
-----
|
||||
|
||||
Project page
|
||||
https://github.com/andialbrecht/sqlparse
|
||||
|
||||
Bug tracker
|
||||
https://github.com/andialbrecht/sqlparse/issues
|
||||
|
||||
Documentation
|
||||
https://sqlparse.readthedocs.io/
|
||||
|
||||
Online Demo
|
||||
https://sqlformat.org/
|
||||
|
||||
|
||||
sqlparse is licensed under the BSD license.
|
||||
|
||||
Parts of the code are based on pygments written by Georg Brandl and others.
|
||||
pygments-Homepage: http://pygments.org/
|
||||
|
||||
.. |buildstatus| image:: https://secure.travis-ci.org/andialbrecht/sqlparse.png?branch=master
|
||||
.. _buildstatus: https://travis-ci.org/#!/andialbrecht/sqlparse
|
||||
.. |coverage| image:: https://coveralls.io/repos/andialbrecht/sqlparse/badge.svg?branch=master&service=github
|
||||
.. _coverage: https://coveralls.io/github/andialbrecht/sqlparse?branch=master
|
||||
@@ -2,6 +2,4 @@
|
||||
https://groups.google.com/d/msg/sqlparse/huz9lKXt0Lc/11ybIKPJWbUJ
|
||||
for some interesting hints and suggestions.
|
||||
* Provide a function to replace tokens. See this thread: https://groups.google.com/d/msg/sqlparse/5xmBL2UKqX4/ZX9z_peve-AJ
|
||||
* Fix bugs on issue tracker.
|
||||
* Document filter stack and processing phases.
|
||||
* See KnownIssues http://code.google.com/p/python-sqlparse/wiki/KnownIssues
|
||||
20
shell/ext-py/sqlparse-0.3.1/setup.cfg
Normal file
20
shell/ext-py/sqlparse-0.3.1/setup.cfg
Normal file
@@ -0,0 +1,20 @@
|
||||
[bdist_wheel]
|
||||
universal = 1
|
||||
|
||||
[metadata]
|
||||
license_file = LICENSE
|
||||
|
||||
[tool:pytest]
|
||||
xfail_strict = True
|
||||
|
||||
[flake8]
|
||||
exclude =
|
||||
sqlparse/compat.py
|
||||
ignore =
|
||||
W503,
|
||||
E731
|
||||
|
||||
[coverage:run]
|
||||
branch = False
|
||||
omit =
|
||||
sqlparse/__main__.py
|
||||
@@ -1,35 +1,27 @@
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This setup script is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
import re
|
||||
import sys
|
||||
|
||||
try:
|
||||
from setuptools import setup, find_packages
|
||||
packages = find_packages(exclude=('tests',))
|
||||
except ImportError:
|
||||
if sys.version_info[0] == 3:
|
||||
raise RuntimeError('distribute is required to install this package.')
|
||||
from distutils.core import setup
|
||||
packages = ['sqlparse', 'sqlparse.engine']
|
||||
from setuptools import setup, find_packages
|
||||
|
||||
|
||||
def get_version():
|
||||
"""parse __init__.py for version number instead of importing the file
|
||||
|
||||
see http://stackoverflow.com/questions/458550/standard-way-to-embed-version-into-python-package
|
||||
"""
|
||||
VERSIONFILE='sqlparse/__init__.py'
|
||||
verstrline = open(VERSIONFILE, "rt").read()
|
||||
"""Parse __init__.py for version number instead of importing the file."""
|
||||
VERSIONFILE = 'sqlparse/__init__.py'
|
||||
VSRE = r'^__version__ = [\'"]([^\'"]*)[\'"]'
|
||||
with open(VERSIONFILE) as f:
|
||||
verstrline = f.read()
|
||||
mo = re.search(VSRE, verstrline, re.M)
|
||||
if mo:
|
||||
return mo.group(1)
|
||||
else:
|
||||
raise RuntimeError('Unable to find version string in %s.'
|
||||
% (VERSIONFILE,))
|
||||
raise RuntimeError('Unable to find version in {fn}'.format(fn=VERSIONFILE))
|
||||
|
||||
|
||||
LONG_DESCRIPTION = """
|
||||
@@ -49,10 +41,10 @@ Splitting SQL statements::
|
||||
[u'select * from foo; ', u'select * from bar;']
|
||||
|
||||
|
||||
Formatting statemtents::
|
||||
Formatting statements::
|
||||
|
||||
>>> sql = 'select * from foo where id in (select id from bar);'
|
||||
>>> print sqlparse.format(sql, reindent=True, keyword_case='upper')
|
||||
>>> print(sqlparse.format(sql, reindent=True, keyword_case='upper'))
|
||||
SELECT *
|
||||
FROM foo
|
||||
WHERE id IN
|
||||
@@ -67,8 +59,8 @@ Parsing::
|
||||
>>> res
|
||||
(<Statement 'select...' at 0x9ad08ec>,)
|
||||
>>> stmt = res[0]
|
||||
>>> unicode(stmt) # converting it back to unicode
|
||||
u'select * from someschema.mytable where id = 1'
|
||||
>>> str(stmt) # converting it back to unicode
|
||||
'select * from someschema.mytable where id = 1'
|
||||
>>> # This is how the internal representation looks like:
|
||||
>>> stmt.tokens
|
||||
(<DML 'select' at 0x9b63c34>,
|
||||
@@ -83,41 +75,37 @@ Parsing::
|
||||
|
||||
"""
|
||||
|
||||
VERSION = get_version()
|
||||
|
||||
|
||||
kwargs = {}
|
||||
if sys.version_info[0] == 3:
|
||||
kwargs['use_2to3'] = True
|
||||
|
||||
|
||||
setup(
|
||||
name='sqlparse',
|
||||
version=VERSION,
|
||||
packages=packages,
|
||||
description='Non-validating SQL parser',
|
||||
version=get_version(),
|
||||
author='Andi Albrecht',
|
||||
author_email='albrecht.andi@gmail.com',
|
||||
url='https://github.com/andialbrecht/sqlparse',
|
||||
description='Non-validating SQL parser',
|
||||
long_description=LONG_DESCRIPTION,
|
||||
license='BSD',
|
||||
url='https://github.com/andialbrecht/sqlparse',
|
||||
python_requires=">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*",
|
||||
classifiers=[
|
||||
'Development Status :: 4 - Beta',
|
||||
'Development Status :: 5 - Production/Stable',
|
||||
'Intended Audience :: Developers',
|
||||
'License :: OSI Approved :: BSD License',
|
||||
'Operating System :: OS Independent',
|
||||
'Programming Language :: Python',
|
||||
'Programming Language :: Python :: 2',
|
||||
'Programming Language :: Python :: 2.4',
|
||||
'Programming Language :: Python :: 2.5',
|
||||
'Programming Language :: Python :: 2.6',
|
||||
'Programming Language :: Python :: 2.7',
|
||||
'Programming Language :: Python :: 3',
|
||||
'Programming Language :: Python :: 3.2',
|
||||
'Programming Language :: Python :: 3.3',
|
||||
'Programming Language :: Python :: 3.4',
|
||||
'Programming Language :: Python :: 3.5',
|
||||
'Programming Language :: Python :: 3.6',
|
||||
'Programming Language :: Python :: 3.7',
|
||||
'Programming Language :: Python :: 3.8',
|
||||
'Topic :: Database',
|
||||
'Topic :: Software Development'
|
||||
'Topic :: Software Development',
|
||||
],
|
||||
scripts=['bin/sqlformat'],
|
||||
**kwargs
|
||||
packages=find_packages(exclude=('tests',)),
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
'sqlformat = sqlparse.__main__:main',
|
||||
]
|
||||
},
|
||||
)
|
||||
@@ -1,27 +1,31 @@
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""Parse SQL statements."""
|
||||
|
||||
|
||||
__version__ = '0.1.19'
|
||||
|
||||
|
||||
# Setup namespace
|
||||
from sqlparse import sql
|
||||
from sqlparse import cli
|
||||
from sqlparse import engine
|
||||
from sqlparse import tokens
|
||||
from sqlparse import filters
|
||||
from sqlparse import formatter
|
||||
|
||||
# Deprecated in 0.1.5. Will be removed in 0.2.0
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
from sqlparse.compat import text_type
|
||||
|
||||
__version__ = '0.3.1'
|
||||
__all__ = ['engine', 'filters', 'formatter', 'sql', 'tokens', 'cli']
|
||||
|
||||
|
||||
def parse(sql, encoding=None):
|
||||
"""Parse sql and return a list of statements.
|
||||
|
||||
:param sql: A string containting one or more SQL statements.
|
||||
:param sql: A string containing one or more SQL statements.
|
||||
:param encoding: The encoding of the statement (optional).
|
||||
:returns: A tuple of :class:`~sqlparse.sql.Statement` instances.
|
||||
"""
|
||||
@@ -36,11 +40,11 @@ def parsestream(stream, encoding=None):
|
||||
:returns: A generator of :class:`~sqlparse.sql.Statement` instances.
|
||||
"""
|
||||
stack = engine.FilterStack()
|
||||
stack.full_analyze()
|
||||
stack.enable_grouping()
|
||||
return stack.run(stream, encoding)
|
||||
|
||||
|
||||
def format(sql, **options):
|
||||
def format(sql, encoding=None, **options):
|
||||
"""Format *sql* according to *options*.
|
||||
|
||||
Available options are documented in :ref:`formatting`.
|
||||
@@ -50,29 +54,19 @@ def format(sql, **options):
|
||||
|
||||
:returns: The formatted SQL statement as string.
|
||||
"""
|
||||
encoding = options.pop('encoding', None)
|
||||
stack = engine.FilterStack()
|
||||
options = formatter.validate_options(options)
|
||||
stack = formatter.build_filter_stack(stack, options)
|
||||
stack.postprocess.append(filters.SerializerUnicode())
|
||||
return ''.join(stack.run(sql, encoding))
|
||||
return u''.join(stack.run(sql, encoding))
|
||||
|
||||
|
||||
def split(sql, encoding=None):
|
||||
"""Split *sql* into single statements.
|
||||
|
||||
:param sql: A string containting one or more SQL statements.
|
||||
:param sql: A string containing one or more SQL statements.
|
||||
:param encoding: The encoding of the statement (optional).
|
||||
:returns: A list of strings.
|
||||
"""
|
||||
stack = engine.FilterStack()
|
||||
stack.split_statements = True
|
||||
return [unicode(stmt).strip() for stmt in stack.run(sql, encoding)]
|
||||
|
||||
|
||||
from sqlparse.engine.filter import StatementFilter
|
||||
|
||||
|
||||
def split2(stream):
|
||||
splitter = StatementFilter()
|
||||
return list(splitter.process(None, stream))
|
||||
return [text_type(stmt).strip() for stmt in stack.run(sql, encoding)]
|
||||
23
shell/ext-py/sqlparse-0.3.1/sqlparse/__main__.py
Normal file
23
shell/ext-py/sqlparse-0.3.1/sqlparse/__main__.py
Normal file
@@ -0,0 +1,23 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""Entrypoint module for `python -m sqlparse`.
|
||||
|
||||
Why does this file exist, and why __main__? For more info, read:
|
||||
- https://www.python.org/dev/peps/pep-0338/
|
||||
- https://docs.python.org/2/using/cmdline.html#cmdoption-m
|
||||
- https://docs.python.org/3/using/cmdline.html#cmdoption-m
|
||||
"""
|
||||
|
||||
import sys
|
||||
|
||||
from sqlparse.cli import main
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
202
shell/ext-py/sqlparse-0.3.1/sqlparse/cli.py
Executable file
202
shell/ext-py/sqlparse-0.3.1/sqlparse/cli.py
Executable file
@@ -0,0 +1,202 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""Module that contains the command line app.
|
||||
|
||||
Why does this file exist, and why not put this in __main__?
|
||||
You might be tempted to import things from __main__ later, but that will
|
||||
cause problems: the code will get executed twice:
|
||||
- When you run `python -m sqlparse` python will execute
|
||||
``__main__.py`` as a script. That means there won't be any
|
||||
``sqlparse.__main__`` in ``sys.modules``.
|
||||
- When you import __main__ it will get executed again (as a module) because
|
||||
there's no ``sqlparse.__main__`` in ``sys.modules``.
|
||||
Also see (1) from http://click.pocoo.org/5/setuptools/#setuptools-integration
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
from io import TextIOWrapper
|
||||
from codecs import open, getreader
|
||||
|
||||
import sqlparse
|
||||
from sqlparse.compat import PY2
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
|
||||
|
||||
# TODO: Add CLI Tests
|
||||
# TODO: Simplify formatter by using argparse `type` arguments
|
||||
def create_parser():
|
||||
_CASE_CHOICES = ['upper', 'lower', 'capitalize']
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
prog='sqlformat',
|
||||
description='Format FILE according to OPTIONS. Use "-" as FILE '
|
||||
'to read from stdin.',
|
||||
usage='%(prog)s [OPTIONS] FILE, ...',
|
||||
)
|
||||
|
||||
parser.add_argument('filename')
|
||||
|
||||
parser.add_argument(
|
||||
'-o', '--outfile',
|
||||
dest='outfile',
|
||||
metavar='FILE',
|
||||
help='write output to FILE (defaults to stdout)')
|
||||
|
||||
parser.add_argument(
|
||||
'--version',
|
||||
action='version',
|
||||
version=sqlparse.__version__)
|
||||
|
||||
group = parser.add_argument_group('Formatting Options')
|
||||
|
||||
group.add_argument(
|
||||
'-k', '--keywords',
|
||||
metavar='CHOICE',
|
||||
dest='keyword_case',
|
||||
choices=_CASE_CHOICES,
|
||||
help='change case of keywords, CHOICE is one of {0}'.format(
|
||||
', '.join('"{0}"'.format(x) for x in _CASE_CHOICES)))
|
||||
|
||||
group.add_argument(
|
||||
'-i', '--identifiers',
|
||||
metavar='CHOICE',
|
||||
dest='identifier_case',
|
||||
choices=_CASE_CHOICES,
|
||||
help='change case of identifiers, CHOICE is one of {0}'.format(
|
||||
', '.join('"{0}"'.format(x) for x in _CASE_CHOICES)))
|
||||
|
||||
group.add_argument(
|
||||
'-l', '--language',
|
||||
metavar='LANG',
|
||||
dest='output_format',
|
||||
choices=['python', 'php'],
|
||||
help='output a snippet in programming language LANG, '
|
||||
'choices are "python", "php"')
|
||||
|
||||
group.add_argument(
|
||||
'--strip-comments',
|
||||
dest='strip_comments',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='remove comments')
|
||||
|
||||
group.add_argument(
|
||||
'-r', '--reindent',
|
||||
dest='reindent',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='reindent statements')
|
||||
|
||||
group.add_argument(
|
||||
'--indent_width',
|
||||
dest='indent_width',
|
||||
default=2,
|
||||
type=int,
|
||||
help='indentation width (defaults to 2 spaces)')
|
||||
|
||||
group.add_argument(
|
||||
'--indent_after_first',
|
||||
dest='indent_after_first',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='indent after first line of statement (e.g. SELECT)')
|
||||
|
||||
group.add_argument(
|
||||
'--indent_columns',
|
||||
dest='indent_columns',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='indent all columns by indent_width instead of keyword length')
|
||||
|
||||
group.add_argument(
|
||||
'-a', '--reindent_aligned',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='reindent statements to aligned format')
|
||||
|
||||
group.add_argument(
|
||||
'-s', '--use_space_around_operators',
|
||||
action='store_true',
|
||||
default=False,
|
||||
help='place spaces around mathematical operators')
|
||||
|
||||
group.add_argument(
|
||||
'--wrap_after',
|
||||
dest='wrap_after',
|
||||
default=0,
|
||||
type=int,
|
||||
help='Column after which lists should be wrapped')
|
||||
|
||||
group.add_argument(
|
||||
'--comma_first',
|
||||
dest='comma_first',
|
||||
default=False,
|
||||
type=bool,
|
||||
help='Insert linebreak before comma (default False)')
|
||||
|
||||
group.add_argument(
|
||||
'--encoding',
|
||||
dest='encoding',
|
||||
default='utf-8',
|
||||
help='Specify the input encoding (default utf-8)')
|
||||
|
||||
return parser
|
||||
|
||||
|
||||
def _error(msg):
|
||||
"""Print msg and optionally exit with return code exit_."""
|
||||
sys.stderr.write(u'[ERROR] {0}\n'.format(msg))
|
||||
return 1
|
||||
|
||||
|
||||
def main(args=None):
|
||||
parser = create_parser()
|
||||
args = parser.parse_args(args)
|
||||
|
||||
if args.filename == '-': # read from stdin
|
||||
if PY2:
|
||||
data = getreader(args.encoding)(sys.stdin).read()
|
||||
else:
|
||||
wrapper = TextIOWrapper(sys.stdin.buffer, encoding=args.encoding)
|
||||
try:
|
||||
data = wrapper.read()
|
||||
finally:
|
||||
wrapper.detach()
|
||||
else:
|
||||
try:
|
||||
with open(args.filename, 'r', args.encoding) as f:
|
||||
data = ''.join(f.readlines())
|
||||
except IOError as e:
|
||||
return _error(
|
||||
u'Failed to read {0}: {1}'.format(args.filename, e))
|
||||
|
||||
close_stream = False
|
||||
if args.outfile:
|
||||
try:
|
||||
stream = open(args.outfile, 'w', args.encoding)
|
||||
close_stream = True
|
||||
except IOError as e:
|
||||
return _error(u'Failed to open {0}: {1}'.format(args.outfile, e))
|
||||
else:
|
||||
stream = sys.stdout
|
||||
|
||||
formatter_opts = vars(args)
|
||||
try:
|
||||
formatter_opts = sqlparse.formatter.validate_options(formatter_opts)
|
||||
except SQLParseError as e:
|
||||
return _error(u'Invalid options: {0}'.format(e))
|
||||
|
||||
s = sqlparse.format(data, **formatter_opts)
|
||||
stream.write(s)
|
||||
stream.flush()
|
||||
if close_stream:
|
||||
stream.close()
|
||||
return 0
|
||||
45
shell/ext-py/sqlparse-0.3.1/sqlparse/compat.py
Normal file
45
shell/ext-py/sqlparse-0.3.1/sqlparse/compat.py
Normal file
@@ -0,0 +1,45 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""Python 2/3 compatibility.
|
||||
|
||||
This module only exists to avoid a dependency on six
|
||||
for very trivial stuff. We only need to take care of
|
||||
string types, buffers and metaclasses.
|
||||
|
||||
Parts of the code is copied directly from six:
|
||||
https://bitbucket.org/gutworth/six
|
||||
"""
|
||||
|
||||
import sys
|
||||
from io import TextIOBase
|
||||
|
||||
PY2 = sys.version_info[0] == 2
|
||||
PY3 = sys.version_info[0] == 3
|
||||
|
||||
|
||||
if PY3:
|
||||
def unicode_compatible(cls):
|
||||
return cls
|
||||
|
||||
text_type = str
|
||||
string_types = (str,)
|
||||
from io import StringIO
|
||||
file_types = (StringIO, TextIOBase)
|
||||
|
||||
|
||||
elif PY2:
|
||||
def unicode_compatible(cls):
|
||||
cls.__unicode__ = cls.__str__
|
||||
cls.__str__ = lambda x: x.__unicode__().encode('utf-8')
|
||||
return cls
|
||||
|
||||
text_type = unicode
|
||||
string_types = (str, unicode,)
|
||||
from StringIO import StringIO
|
||||
file_types = (file, StringIO, TextIOBase)
|
||||
17
shell/ext-py/sqlparse-0.3.1/sqlparse/engine/__init__.py
Normal file
17
shell/ext-py/sqlparse-0.3.1/sqlparse/engine/__init__.py
Normal file
@@ -0,0 +1,17 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse.engine import grouping
|
||||
from sqlparse.engine.filter_stack import FilterStack
|
||||
from sqlparse.engine.statement_splitter import StatementSplitter
|
||||
|
||||
__all__ = [
|
||||
'grouping',
|
||||
'FilterStack',
|
||||
'StatementSplitter',
|
||||
]
|
||||
45
shell/ext-py/sqlparse-0.3.1/sqlparse/engine/filter_stack.py
Normal file
45
shell/ext-py/sqlparse-0.3.1/sqlparse/engine/filter_stack.py
Normal file
@@ -0,0 +1,45 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""filter"""
|
||||
|
||||
from sqlparse import lexer
|
||||
from sqlparse.engine import grouping
|
||||
from sqlparse.engine.statement_splitter import StatementSplitter
|
||||
|
||||
|
||||
class FilterStack(object):
|
||||
def __init__(self):
|
||||
self.preprocess = []
|
||||
self.stmtprocess = []
|
||||
self.postprocess = []
|
||||
self._grouping = False
|
||||
|
||||
def enable_grouping(self):
|
||||
self._grouping = True
|
||||
|
||||
def run(self, sql, encoding=None):
|
||||
stream = lexer.tokenize(sql, encoding)
|
||||
# Process token stream
|
||||
for filter_ in self.preprocess:
|
||||
stream = filter_.process(stream)
|
||||
|
||||
stream = StatementSplitter().process(stream)
|
||||
|
||||
# Output: Stream processed Statements
|
||||
for stmt in stream:
|
||||
if self._grouping:
|
||||
stmt = grouping.group(stmt)
|
||||
|
||||
for filter_ in self.stmtprocess:
|
||||
filter_.process(stmt)
|
||||
|
||||
for filter_ in self.postprocess:
|
||||
stmt = filter_.process(stmt)
|
||||
|
||||
yield stmt
|
||||
453
shell/ext-py/sqlparse-0.3.1/sqlparse/engine/grouping.py
Normal file
453
shell/ext-py/sqlparse-0.3.1/sqlparse/engine/grouping.py
Normal file
@@ -0,0 +1,453 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import sql
|
||||
from sqlparse import tokens as T
|
||||
from sqlparse.utils import recurse, imt
|
||||
|
||||
T_NUMERICAL = (T.Number, T.Number.Integer, T.Number.Float)
|
||||
T_STRING = (T.String, T.String.Single, T.String.Symbol)
|
||||
T_NAME = (T.Name, T.Name.Placeholder)
|
||||
|
||||
|
||||
def _group_matching(tlist, cls):
|
||||
"""Groups Tokens that have beginning and end."""
|
||||
opens = []
|
||||
tidx_offset = 0
|
||||
for idx, token in enumerate(list(tlist)):
|
||||
tidx = idx - tidx_offset
|
||||
|
||||
if token.is_whitespace:
|
||||
# ~50% of tokens will be whitespace. Will checking early
|
||||
# for them avoid 3 comparisons, but then add 1 more comparison
|
||||
# for the other ~50% of tokens...
|
||||
continue
|
||||
|
||||
if token.is_group and not isinstance(token, cls):
|
||||
# Check inside previously grouped (i.e. parenthesis) if group
|
||||
# of different type is inside (i.e., case). though ideally should
|
||||
# should check for all open/close tokens at once to avoid recursion
|
||||
_group_matching(token, cls)
|
||||
continue
|
||||
|
||||
if token.match(*cls.M_OPEN):
|
||||
opens.append(tidx)
|
||||
|
||||
elif token.match(*cls.M_CLOSE):
|
||||
try:
|
||||
open_idx = opens.pop()
|
||||
except IndexError:
|
||||
# this indicates invalid sql and unbalanced tokens.
|
||||
# instead of break, continue in case other "valid" groups exist
|
||||
continue
|
||||
close_idx = tidx
|
||||
tlist.group_tokens(cls, open_idx, close_idx)
|
||||
tidx_offset += close_idx - open_idx
|
||||
|
||||
|
||||
def group_brackets(tlist):
|
||||
_group_matching(tlist, sql.SquareBrackets)
|
||||
|
||||
|
||||
def group_parenthesis(tlist):
|
||||
_group_matching(tlist, sql.Parenthesis)
|
||||
|
||||
|
||||
def group_case(tlist):
|
||||
_group_matching(tlist, sql.Case)
|
||||
|
||||
|
||||
def group_if(tlist):
|
||||
_group_matching(tlist, sql.If)
|
||||
|
||||
|
||||
def group_for(tlist):
|
||||
_group_matching(tlist, sql.For)
|
||||
|
||||
|
||||
def group_begin(tlist):
|
||||
_group_matching(tlist, sql.Begin)
|
||||
|
||||
|
||||
def group_typecasts(tlist):
|
||||
def match(token):
|
||||
return token.match(T.Punctuation, '::')
|
||||
|
||||
def valid(token):
|
||||
return token is not None
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return pidx, nidx
|
||||
|
||||
valid_prev = valid_next = valid
|
||||
_group(tlist, sql.Identifier, match, valid_prev, valid_next, post)
|
||||
|
||||
|
||||
def group_tzcasts(tlist):
|
||||
def match(token):
|
||||
return token.ttype == T.Keyword.TZCast
|
||||
|
||||
def valid(token):
|
||||
return token is not None
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return pidx, nidx
|
||||
|
||||
_group(tlist, sql.Identifier, match, valid, valid, post)
|
||||
|
||||
|
||||
def group_typed_literal(tlist):
|
||||
# definitely not complete, see e.g.:
|
||||
# https://docs.microsoft.com/en-us/sql/odbc/reference/appendixes/interval-literal-syntax
|
||||
# https://docs.microsoft.com/en-us/sql/odbc/reference/appendixes/interval-literals
|
||||
# https://www.postgresql.org/docs/9.1/datatype-datetime.html
|
||||
# https://www.postgresql.org/docs/9.1/functions-datetime.html
|
||||
def match(token):
|
||||
return imt(token, m=sql.TypedLiteral.M_OPEN)
|
||||
|
||||
def match_to_extend(token):
|
||||
return isinstance(token, sql.TypedLiteral)
|
||||
|
||||
def valid_prev(token):
|
||||
return token is not None
|
||||
|
||||
def valid_next(token):
|
||||
return token is not None and token.match(*sql.TypedLiteral.M_CLOSE)
|
||||
|
||||
def valid_final(token):
|
||||
return token is not None and token.match(*sql.TypedLiteral.M_EXTEND)
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return tidx, nidx
|
||||
|
||||
_group(tlist, sql.TypedLiteral, match, valid_prev, valid_next,
|
||||
post, extend=False)
|
||||
_group(tlist, sql.TypedLiteral, match_to_extend, valid_prev, valid_final,
|
||||
post, extend=True)
|
||||
|
||||
|
||||
def group_period(tlist):
|
||||
def match(token):
|
||||
return token.match(T.Punctuation, '.')
|
||||
|
||||
def valid_prev(token):
|
||||
sqlcls = sql.SquareBrackets, sql.Identifier
|
||||
ttypes = T.Name, T.String.Symbol
|
||||
return imt(token, i=sqlcls, t=ttypes)
|
||||
|
||||
def valid_next(token):
|
||||
# issue261, allow invalid next token
|
||||
return True
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
# next_ validation is being performed here. issue261
|
||||
sqlcls = sql.SquareBrackets, sql.Function
|
||||
ttypes = T.Name, T.String.Symbol, T.Wildcard
|
||||
next_ = tlist[nidx] if nidx is not None else None
|
||||
valid_next = imt(next_, i=sqlcls, t=ttypes)
|
||||
|
||||
return (pidx, nidx) if valid_next else (pidx, tidx)
|
||||
|
||||
_group(tlist, sql.Identifier, match, valid_prev, valid_next, post)
|
||||
|
||||
|
||||
def group_as(tlist):
|
||||
def match(token):
|
||||
return token.is_keyword and token.normalized == 'AS'
|
||||
|
||||
def valid_prev(token):
|
||||
return token.normalized == 'NULL' or not token.is_keyword
|
||||
|
||||
def valid_next(token):
|
||||
ttypes = T.DML, T.DDL, T.CTE
|
||||
return not imt(token, t=ttypes) and token is not None
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return pidx, nidx
|
||||
|
||||
_group(tlist, sql.Identifier, match, valid_prev, valid_next, post)
|
||||
|
||||
|
||||
def group_assignment(tlist):
|
||||
def match(token):
|
||||
return token.match(T.Assignment, ':=')
|
||||
|
||||
def valid(token):
|
||||
return token is not None and token.ttype not in (T.Keyword)
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
m_semicolon = T.Punctuation, ';'
|
||||
snidx, _ = tlist.token_next_by(m=m_semicolon, idx=nidx)
|
||||
nidx = snidx or nidx
|
||||
return pidx, nidx
|
||||
|
||||
valid_prev = valid_next = valid
|
||||
_group(tlist, sql.Assignment, match, valid_prev, valid_next, post)
|
||||
|
||||
|
||||
def group_comparison(tlist):
|
||||
sqlcls = (sql.Parenthesis, sql.Function, sql.Identifier,
|
||||
sql.Operation)
|
||||
ttypes = T_NUMERICAL + T_STRING + T_NAME
|
||||
|
||||
def match(token):
|
||||
return token.ttype == T.Operator.Comparison
|
||||
|
||||
def valid(token):
|
||||
if imt(token, t=ttypes, i=sqlcls):
|
||||
return True
|
||||
elif token and token.is_keyword and token.normalized == 'NULL':
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return pidx, nidx
|
||||
|
||||
valid_prev = valid_next = valid
|
||||
_group(tlist, sql.Comparison, match,
|
||||
valid_prev, valid_next, post, extend=False)
|
||||
|
||||
|
||||
@recurse(sql.Identifier)
|
||||
def group_identifier(tlist):
|
||||
ttypes = (T.String.Symbol, T.Name)
|
||||
|
||||
tidx, token = tlist.token_next_by(t=ttypes)
|
||||
while token:
|
||||
tlist.group_tokens(sql.Identifier, tidx, tidx)
|
||||
tidx, token = tlist.token_next_by(t=ttypes, idx=tidx)
|
||||
|
||||
|
||||
def group_arrays(tlist):
|
||||
sqlcls = sql.SquareBrackets, sql.Identifier, sql.Function
|
||||
ttypes = T.Name, T.String.Symbol
|
||||
|
||||
def match(token):
|
||||
return isinstance(token, sql.SquareBrackets)
|
||||
|
||||
def valid_prev(token):
|
||||
return imt(token, i=sqlcls, t=ttypes)
|
||||
|
||||
def valid_next(token):
|
||||
return True
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return pidx, tidx
|
||||
|
||||
_group(tlist, sql.Identifier, match,
|
||||
valid_prev, valid_next, post, extend=True, recurse=False)
|
||||
|
||||
|
||||
def group_operator(tlist):
|
||||
ttypes = T_NUMERICAL + T_STRING + T_NAME
|
||||
sqlcls = (sql.SquareBrackets, sql.Parenthesis, sql.Function,
|
||||
sql.Identifier, sql.Operation, sql.TypedLiteral)
|
||||
|
||||
def match(token):
|
||||
return imt(token, t=(T.Operator, T.Wildcard))
|
||||
|
||||
def valid(token):
|
||||
return imt(token, i=sqlcls, t=ttypes) \
|
||||
or (token and token.match(
|
||||
T.Keyword,
|
||||
('CURRENT_DATE', 'CURRENT_TIME', 'CURRENT_TIMESTAMP')))
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
tlist[tidx].ttype = T.Operator
|
||||
return pidx, nidx
|
||||
|
||||
valid_prev = valid_next = valid
|
||||
_group(tlist, sql.Operation, match,
|
||||
valid_prev, valid_next, post, extend=False)
|
||||
|
||||
|
||||
def group_identifier_list(tlist):
|
||||
m_role = T.Keyword, ('null', 'role')
|
||||
sqlcls = (sql.Function, sql.Case, sql.Identifier, sql.Comparison,
|
||||
sql.IdentifierList, sql.Operation)
|
||||
ttypes = (T_NUMERICAL + T_STRING + T_NAME
|
||||
+ (T.Keyword, T.Comment, T.Wildcard))
|
||||
|
||||
def match(token):
|
||||
return token.match(T.Punctuation, ',')
|
||||
|
||||
def valid(token):
|
||||
return imt(token, i=sqlcls, m=m_role, t=ttypes)
|
||||
|
||||
def post(tlist, pidx, tidx, nidx):
|
||||
return pidx, nidx
|
||||
|
||||
valid_prev = valid_next = valid
|
||||
_group(tlist, sql.IdentifierList, match,
|
||||
valid_prev, valid_next, post, extend=True)
|
||||
|
||||
|
||||
@recurse(sql.Comment)
|
||||
def group_comments(tlist):
|
||||
tidx, token = tlist.token_next_by(t=T.Comment)
|
||||
while token:
|
||||
eidx, end = tlist.token_not_matching(
|
||||
lambda tk: imt(tk, t=T.Comment) or tk.is_whitespace, idx=tidx)
|
||||
if end is not None:
|
||||
eidx, end = tlist.token_prev(eidx, skip_ws=False)
|
||||
tlist.group_tokens(sql.Comment, tidx, eidx)
|
||||
|
||||
tidx, token = tlist.token_next_by(t=T.Comment, idx=tidx)
|
||||
|
||||
|
||||
@recurse(sql.Where)
|
||||
def group_where(tlist):
|
||||
tidx, token = tlist.token_next_by(m=sql.Where.M_OPEN)
|
||||
while token:
|
||||
eidx, end = tlist.token_next_by(m=sql.Where.M_CLOSE, idx=tidx)
|
||||
|
||||
if end is None:
|
||||
end = tlist._groupable_tokens[-1]
|
||||
else:
|
||||
end = tlist.tokens[eidx - 1]
|
||||
# TODO: convert this to eidx instead of end token.
|
||||
# i think above values are len(tlist) and eidx-1
|
||||
eidx = tlist.token_index(end)
|
||||
tlist.group_tokens(sql.Where, tidx, eidx)
|
||||
tidx, token = tlist.token_next_by(m=sql.Where.M_OPEN, idx=tidx)
|
||||
|
||||
|
||||
@recurse()
|
||||
def group_aliased(tlist):
|
||||
I_ALIAS = (sql.Parenthesis, sql.Function, sql.Case, sql.Identifier,
|
||||
sql.Operation, sql.Comparison)
|
||||
|
||||
tidx, token = tlist.token_next_by(i=I_ALIAS, t=T.Number)
|
||||
while token:
|
||||
nidx, next_ = tlist.token_next(tidx)
|
||||
if isinstance(next_, sql.Identifier):
|
||||
tlist.group_tokens(sql.Identifier, tidx, nidx, extend=True)
|
||||
tidx, token = tlist.token_next_by(i=I_ALIAS, t=T.Number, idx=tidx)
|
||||
|
||||
|
||||
@recurse(sql.Function)
|
||||
def group_functions(tlist):
|
||||
has_create = False
|
||||
has_table = False
|
||||
for tmp_token in tlist.tokens:
|
||||
if tmp_token.value == 'CREATE':
|
||||
has_create = True
|
||||
if tmp_token.value == 'TABLE':
|
||||
has_table = True
|
||||
if has_create and has_table:
|
||||
return
|
||||
|
||||
tidx, token = tlist.token_next_by(t=T.Name)
|
||||
while token:
|
||||
nidx, next_ = tlist.token_next(tidx)
|
||||
if isinstance(next_, sql.Parenthesis):
|
||||
tlist.group_tokens(sql.Function, tidx, nidx)
|
||||
tidx, token = tlist.token_next_by(t=T.Name, idx=tidx)
|
||||
|
||||
|
||||
def group_order(tlist):
|
||||
"""Group together Identifier and Asc/Desc token"""
|
||||
tidx, token = tlist.token_next_by(t=T.Keyword.Order)
|
||||
while token:
|
||||
pidx, prev_ = tlist.token_prev(tidx)
|
||||
if imt(prev_, i=sql.Identifier, t=T.Number):
|
||||
tlist.group_tokens(sql.Identifier, pidx, tidx)
|
||||
tidx = pidx
|
||||
tidx, token = tlist.token_next_by(t=T.Keyword.Order, idx=tidx)
|
||||
|
||||
|
||||
@recurse()
|
||||
def align_comments(tlist):
|
||||
tidx, token = tlist.token_next_by(i=sql.Comment)
|
||||
while token:
|
||||
pidx, prev_ = tlist.token_prev(tidx)
|
||||
if isinstance(prev_, sql.TokenList):
|
||||
tlist.group_tokens(sql.TokenList, pidx, tidx, extend=True)
|
||||
tidx = pidx
|
||||
tidx, token = tlist.token_next_by(i=sql.Comment, idx=tidx)
|
||||
|
||||
|
||||
def group_values(tlist):
|
||||
tidx, token = tlist.token_next_by(m=(T.Keyword, 'VALUES'))
|
||||
start_idx = tidx
|
||||
end_idx = -1
|
||||
while token:
|
||||
if isinstance(token, sql.Parenthesis):
|
||||
end_idx = tidx
|
||||
tidx, token = tlist.token_next(tidx)
|
||||
if end_idx != -1:
|
||||
tlist.group_tokens(sql.Values, start_idx, end_idx, extend=True)
|
||||
|
||||
|
||||
def group(stmt):
|
||||
for func in [
|
||||
group_comments,
|
||||
|
||||
# _group_matching
|
||||
group_brackets,
|
||||
group_parenthesis,
|
||||
group_case,
|
||||
group_if,
|
||||
group_for,
|
||||
group_begin,
|
||||
|
||||
group_functions,
|
||||
group_where,
|
||||
group_period,
|
||||
group_arrays,
|
||||
group_identifier,
|
||||
group_order,
|
||||
group_typecasts,
|
||||
group_tzcasts,
|
||||
group_typed_literal,
|
||||
group_operator,
|
||||
group_comparison,
|
||||
group_as,
|
||||
group_aliased,
|
||||
group_assignment,
|
||||
|
||||
align_comments,
|
||||
group_identifier_list,
|
||||
group_values,
|
||||
]:
|
||||
func(stmt)
|
||||
return stmt
|
||||
|
||||
|
||||
def _group(tlist, cls, match,
|
||||
valid_prev=lambda t: True,
|
||||
valid_next=lambda t: True,
|
||||
post=None,
|
||||
extend=True,
|
||||
recurse=True
|
||||
):
|
||||
"""Groups together tokens that are joined by a middle token. i.e. x < y"""
|
||||
|
||||
tidx_offset = 0
|
||||
pidx, prev_ = None, None
|
||||
for idx, token in enumerate(list(tlist)):
|
||||
tidx = idx - tidx_offset
|
||||
|
||||
if token.is_whitespace:
|
||||
continue
|
||||
|
||||
if recurse and token.is_group and not isinstance(token, cls):
|
||||
_group(token, cls, match, valid_prev, valid_next, post, extend)
|
||||
|
||||
if match(token):
|
||||
nidx, next_ = tlist.token_next(tidx)
|
||||
if prev_ and valid_prev(prev_) and valid_next(next_):
|
||||
from_idx, to_idx = post(tlist, pidx, tidx, nidx)
|
||||
grp = tlist.group_tokens(cls, from_idx, to_idx, extend=extend)
|
||||
|
||||
tidx_offset += to_idx - from_idx
|
||||
pidx, prev_ = from_idx, grp
|
||||
continue
|
||||
|
||||
pidx, prev_ = tidx, token
|
||||
@@ -0,0 +1,108 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
|
||||
|
||||
class StatementSplitter(object):
|
||||
"""Filter that split stream at individual statements"""
|
||||
|
||||
def __init__(self):
|
||||
self._reset()
|
||||
|
||||
def _reset(self):
|
||||
"""Set the filter attributes to its default values"""
|
||||
self._in_declare = False
|
||||
self._is_create = False
|
||||
self._begin_depth = 0
|
||||
|
||||
self.consume_ws = False
|
||||
self.tokens = []
|
||||
self.level = 0
|
||||
|
||||
def _change_splitlevel(self, ttype, value):
|
||||
"""Get the new split level (increase, decrease or remain equal)"""
|
||||
|
||||
# parenthesis increase/decrease a level
|
||||
if ttype is T.Punctuation and value == '(':
|
||||
return 1
|
||||
elif ttype is T.Punctuation and value == ')':
|
||||
return -1
|
||||
elif ttype not in T.Keyword: # if normal token return
|
||||
return 0
|
||||
|
||||
# Everything after here is ttype = T.Keyword
|
||||
# Also to note, once entered an If statement you are done and basically
|
||||
# returning
|
||||
unified = value.upper()
|
||||
|
||||
# three keywords begin with CREATE, but only one of them is DDL
|
||||
# DDL Create though can contain more words such as "or replace"
|
||||
if ttype is T.Keyword.DDL and unified.startswith('CREATE'):
|
||||
self._is_create = True
|
||||
return 0
|
||||
|
||||
# can have nested declare inside of being...
|
||||
if unified == 'DECLARE' and self._is_create and self._begin_depth == 0:
|
||||
self._in_declare = True
|
||||
return 1
|
||||
|
||||
if unified == 'BEGIN':
|
||||
self._begin_depth += 1
|
||||
if self._is_create:
|
||||
# FIXME(andi): This makes no sense.
|
||||
return 1
|
||||
return 0
|
||||
|
||||
# Should this respect a preceding BEGIN?
|
||||
# In CASE ... WHEN ... END this results in a split level -1.
|
||||
# Would having multiple CASE WHEN END and a Assignment Operator
|
||||
# cause the statement to cut off prematurely?
|
||||
if unified == 'END':
|
||||
self._begin_depth = max(0, self._begin_depth - 1)
|
||||
return -1
|
||||
|
||||
if (unified in ('IF', 'FOR', 'WHILE')
|
||||
and self._is_create and self._begin_depth > 0):
|
||||
return 1
|
||||
|
||||
if unified in ('END IF', 'END FOR', 'END WHILE'):
|
||||
return -1
|
||||
|
||||
# Default
|
||||
return 0
|
||||
|
||||
def process(self, stream):
|
||||
"""Process the stream"""
|
||||
EOS_TTYPE = T.Whitespace, T.Comment.Single
|
||||
|
||||
# Run over all stream tokens
|
||||
for ttype, value in stream:
|
||||
# Yield token if we finished a statement and there's no whitespaces
|
||||
# It will count newline token as a non whitespace. In this context
|
||||
# whitespace ignores newlines.
|
||||
# why don't multi line comments also count?
|
||||
if self.consume_ws and ttype not in EOS_TTYPE:
|
||||
yield sql.Statement(self.tokens)
|
||||
|
||||
# Reset filter and prepare to process next statement
|
||||
self._reset()
|
||||
|
||||
# Change current split level (increase, decrease or remain equal)
|
||||
self.level += self._change_splitlevel(ttype, value)
|
||||
|
||||
# Append the token to the current statement
|
||||
self.tokens.append(sql.Token(ttype, value))
|
||||
|
||||
# Check if we get the end of a statement
|
||||
if self.level <= 0 and ttype is T.Punctuation and value == ';':
|
||||
self.consume_ws = True
|
||||
|
||||
# Yield pending statement (if any)
|
||||
if self.tokens:
|
||||
yield sql.Statement(self.tokens)
|
||||
@@ -1,7 +1,10 @@
|
||||
# Copyright (C) 2012 Andi Albrecht, albrecht.andi@gmail.com
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""Exceptions used in this package."""
|
||||
|
||||
41
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/__init__.py
Normal file
41
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/__init__.py
Normal file
@@ -0,0 +1,41 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse.filters.others import SerializerUnicode
|
||||
from sqlparse.filters.others import StripCommentsFilter
|
||||
from sqlparse.filters.others import StripWhitespaceFilter
|
||||
from sqlparse.filters.others import SpacesAroundOperatorsFilter
|
||||
|
||||
from sqlparse.filters.output import OutputPHPFilter
|
||||
from sqlparse.filters.output import OutputPythonFilter
|
||||
|
||||
from sqlparse.filters.tokens import KeywordCaseFilter
|
||||
from sqlparse.filters.tokens import IdentifierCaseFilter
|
||||
from sqlparse.filters.tokens import TruncateStringFilter
|
||||
|
||||
from sqlparse.filters.reindent import ReindentFilter
|
||||
from sqlparse.filters.right_margin import RightMarginFilter
|
||||
from sqlparse.filters.aligned_indent import AlignedIndentFilter
|
||||
|
||||
__all__ = [
|
||||
'SerializerUnicode',
|
||||
'StripCommentsFilter',
|
||||
'StripWhitespaceFilter',
|
||||
'SpacesAroundOperatorsFilter',
|
||||
|
||||
'OutputPHPFilter',
|
||||
'OutputPythonFilter',
|
||||
|
||||
'KeywordCaseFilter',
|
||||
'IdentifierCaseFilter',
|
||||
'TruncateStringFilter',
|
||||
|
||||
'ReindentFilter',
|
||||
'RightMarginFilter',
|
||||
'AlignedIndentFilter',
|
||||
]
|
||||
138
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/aligned_indent.py
Normal file
138
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/aligned_indent.py
Normal file
@@ -0,0 +1,138 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import text_type
|
||||
from sqlparse.utils import offset, indent
|
||||
|
||||
|
||||
class AlignedIndentFilter(object):
|
||||
join_words = (r'((LEFT\s+|RIGHT\s+|FULL\s+)?'
|
||||
r'(INNER\s+|OUTER\s+|STRAIGHT\s+)?|'
|
||||
r'(CROSS\s+|NATURAL\s+)?)?JOIN\b')
|
||||
by_words = r'(GROUP|ORDER)\s+BY\b'
|
||||
split_words = ('FROM',
|
||||
join_words, 'ON', by_words,
|
||||
'WHERE', 'AND', 'OR',
|
||||
'HAVING', 'LIMIT',
|
||||
'UNION', 'VALUES',
|
||||
'SET', 'BETWEEN', 'EXCEPT')
|
||||
|
||||
def __init__(self, char=' ', n='\n'):
|
||||
self.n = n
|
||||
self.offset = 0
|
||||
self.indent = 0
|
||||
self.char = char
|
||||
self._max_kwd_len = len('select')
|
||||
|
||||
def nl(self, offset=1):
|
||||
# offset = 1 represent a single space after SELECT
|
||||
offset = -len(offset) if not isinstance(offset, int) else offset
|
||||
# add two for the space and parenthesis
|
||||
indent = self.indent * (2 + self._max_kwd_len)
|
||||
|
||||
return sql.Token(T.Whitespace, self.n + self.char * (
|
||||
self._max_kwd_len + offset + indent + self.offset))
|
||||
|
||||
def _process_statement(self, tlist):
|
||||
if len(tlist.tokens) > 0 and tlist.tokens[0].is_whitespace \
|
||||
and self.indent == 0:
|
||||
tlist.tokens.pop(0)
|
||||
|
||||
# process the main query body
|
||||
self._process(sql.TokenList(tlist.tokens))
|
||||
|
||||
def _process_parenthesis(self, tlist):
|
||||
# if this isn't a subquery, don't re-indent
|
||||
_, token = tlist.token_next_by(m=(T.DML, 'SELECT'))
|
||||
if token is not None:
|
||||
with indent(self):
|
||||
tlist.insert_after(tlist[0], self.nl('SELECT'))
|
||||
# process the inside of the parenthesis
|
||||
self._process_default(tlist)
|
||||
|
||||
# de-indent last parenthesis
|
||||
tlist.insert_before(tlist[-1], self.nl())
|
||||
|
||||
def _process_identifierlist(self, tlist):
|
||||
# columns being selected
|
||||
identifiers = list(tlist.get_identifiers())
|
||||
identifiers.pop(0)
|
||||
[tlist.insert_before(token, self.nl()) for token in identifiers]
|
||||
self._process_default(tlist)
|
||||
|
||||
def _process_case(self, tlist):
|
||||
offset_ = len('case ') + len('when ')
|
||||
cases = tlist.get_cases(skip_ws=True)
|
||||
# align the end as well
|
||||
end_token = tlist.token_next_by(m=(T.Keyword, 'END'))[1]
|
||||
cases.append((None, [end_token]))
|
||||
|
||||
condition_width = [len(' '.join(map(text_type, cond))) if cond else 0
|
||||
for cond, _ in cases]
|
||||
max_cond_width = max(condition_width)
|
||||
|
||||
for i, (cond, value) in enumerate(cases):
|
||||
# cond is None when 'else or end'
|
||||
stmt = cond[0] if cond else value[0]
|
||||
|
||||
if i > 0:
|
||||
tlist.insert_before(stmt, self.nl(
|
||||
offset_ - len(text_type(stmt))))
|
||||
if cond:
|
||||
ws = sql.Token(T.Whitespace, self.char * (
|
||||
max_cond_width - condition_width[i]))
|
||||
tlist.insert_after(cond[-1], ws)
|
||||
|
||||
def _next_token(self, tlist, idx=-1):
|
||||
split_words = T.Keyword, self.split_words, True
|
||||
tidx, token = tlist.token_next_by(m=split_words, idx=idx)
|
||||
# treat "BETWEEN x and y" as a single statement
|
||||
if token and token.normalized == 'BETWEEN':
|
||||
tidx, token = self._next_token(tlist, tidx)
|
||||
if token and token.normalized == 'AND':
|
||||
tidx, token = self._next_token(tlist, tidx)
|
||||
return tidx, token
|
||||
|
||||
def _split_kwds(self, tlist):
|
||||
tidx, token = self._next_token(tlist)
|
||||
while token:
|
||||
# joins, group/order by are special case. only consider the first
|
||||
# word as aligner
|
||||
if (
|
||||
token.match(T.Keyword, self.join_words, regex=True)
|
||||
or token.match(T.Keyword, self.by_words, regex=True)
|
||||
):
|
||||
token_indent = token.value.split()[0]
|
||||
else:
|
||||
token_indent = text_type(token)
|
||||
tlist.insert_before(token, self.nl(token_indent))
|
||||
tidx += 1
|
||||
tidx, token = self._next_token(tlist, tidx)
|
||||
|
||||
def _process_default(self, tlist):
|
||||
self._split_kwds(tlist)
|
||||
# process any sub-sub statements
|
||||
for sgroup in tlist.get_sublists():
|
||||
idx = tlist.token_index(sgroup)
|
||||
pidx, prev_ = tlist.token_prev(idx)
|
||||
# HACK: make "group/order by" work. Longer than max_len.
|
||||
offset_ = 3 if (
|
||||
prev_ and prev_.match(T.Keyword, self.by_words, regex=True)
|
||||
) else 0
|
||||
with offset(self, offset_):
|
||||
self._process(sgroup)
|
||||
|
||||
def _process(self, tlist):
|
||||
func_name = '_process_{cls}'.format(cls=type(tlist).__name__)
|
||||
func = getattr(self, func_name.lower(), self._process_default)
|
||||
func(tlist)
|
||||
|
||||
def process(self, stmt):
|
||||
self._process(stmt)
|
||||
return stmt
|
||||
125
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/others.py
Normal file
125
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/others.py
Normal file
@@ -0,0 +1,125 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.utils import split_unquoted_newlines
|
||||
|
||||
|
||||
class StripCommentsFilter(object):
|
||||
@staticmethod
|
||||
def _process(tlist):
|
||||
def get_next_comment():
|
||||
# TODO(andi) Comment types should be unified, see related issue38
|
||||
return tlist.token_next_by(i=sql.Comment, t=T.Comment)
|
||||
|
||||
tidx, token = get_next_comment()
|
||||
while token:
|
||||
pidx, prev_ = tlist.token_prev(tidx, skip_ws=False)
|
||||
nidx, next_ = tlist.token_next(tidx, skip_ws=False)
|
||||
# Replace by whitespace if prev and next exist and if they're not
|
||||
# whitespaces. This doesn't apply if prev or next is a parenthesis.
|
||||
if (prev_ is None or next_ is None
|
||||
or prev_.is_whitespace or prev_.match(T.Punctuation, '(')
|
||||
or next_.is_whitespace or next_.match(T.Punctuation, ')')):
|
||||
# Insert a whitespace to ensure the following SQL produces
|
||||
# a valid SQL (see #425). For example:
|
||||
#
|
||||
# Before: select a--comment\nfrom foo
|
||||
# After: select a from foo
|
||||
if prev_ is not None and next_ is None:
|
||||
tlist.tokens.insert(tidx, sql.Token(T.Whitespace, ' '))
|
||||
tlist.tokens.remove(token)
|
||||
else:
|
||||
tlist.tokens[tidx] = sql.Token(T.Whitespace, ' ')
|
||||
|
||||
tidx, token = get_next_comment()
|
||||
|
||||
def process(self, stmt):
|
||||
[self.process(sgroup) for sgroup in stmt.get_sublists()]
|
||||
StripCommentsFilter._process(stmt)
|
||||
return stmt
|
||||
|
||||
|
||||
class StripWhitespaceFilter(object):
|
||||
def _stripws(self, tlist):
|
||||
func_name = '_stripws_{cls}'.format(cls=type(tlist).__name__)
|
||||
func = getattr(self, func_name.lower(), self._stripws_default)
|
||||
func(tlist)
|
||||
|
||||
@staticmethod
|
||||
def _stripws_default(tlist):
|
||||
last_was_ws = False
|
||||
is_first_char = True
|
||||
for token in tlist.tokens:
|
||||
if token.is_whitespace:
|
||||
token.value = '' if last_was_ws or is_first_char else ' '
|
||||
last_was_ws = token.is_whitespace
|
||||
is_first_char = False
|
||||
|
||||
def _stripws_identifierlist(self, tlist):
|
||||
# Removes newlines before commas, see issue140
|
||||
last_nl = None
|
||||
for token in list(tlist.tokens):
|
||||
if last_nl and token.ttype is T.Punctuation and token.value == ',':
|
||||
tlist.tokens.remove(last_nl)
|
||||
last_nl = token if token.is_whitespace else None
|
||||
|
||||
# next_ = tlist.token_next(token, skip_ws=False)
|
||||
# if (next_ and not next_.is_whitespace and
|
||||
# token.ttype is T.Punctuation and token.value == ','):
|
||||
# tlist.insert_after(token, sql.Token(T.Whitespace, ' '))
|
||||
return self._stripws_default(tlist)
|
||||
|
||||
def _stripws_parenthesis(self, tlist):
|
||||
while tlist.tokens[1].is_whitespace:
|
||||
tlist.tokens.pop(1)
|
||||
while tlist.tokens[-2].is_whitespace:
|
||||
tlist.tokens.pop(-2)
|
||||
self._stripws_default(tlist)
|
||||
|
||||
def process(self, stmt, depth=0):
|
||||
[self.process(sgroup, depth + 1) for sgroup in stmt.get_sublists()]
|
||||
self._stripws(stmt)
|
||||
if depth == 0 and stmt.tokens and stmt.tokens[-1].is_whitespace:
|
||||
stmt.tokens.pop(-1)
|
||||
return stmt
|
||||
|
||||
|
||||
class SpacesAroundOperatorsFilter(object):
|
||||
@staticmethod
|
||||
def _process(tlist):
|
||||
|
||||
ttypes = (T.Operator, T.Comparison)
|
||||
tidx, token = tlist.token_next_by(t=ttypes)
|
||||
while token:
|
||||
nidx, next_ = tlist.token_next(tidx, skip_ws=False)
|
||||
if next_ and next_.ttype != T.Whitespace:
|
||||
tlist.insert_after(tidx, sql.Token(T.Whitespace, ' '))
|
||||
|
||||
pidx, prev_ = tlist.token_prev(tidx, skip_ws=False)
|
||||
if prev_ and prev_.ttype != T.Whitespace:
|
||||
tlist.insert_before(tidx, sql.Token(T.Whitespace, ' '))
|
||||
tidx += 1 # has to shift since token inserted before it
|
||||
|
||||
# assert tlist.token_index(token) == tidx
|
||||
tidx, token = tlist.token_next_by(t=ttypes, idx=tidx)
|
||||
|
||||
def process(self, stmt):
|
||||
[self.process(sgroup) for sgroup in stmt.get_sublists()]
|
||||
SpacesAroundOperatorsFilter._process(stmt)
|
||||
return stmt
|
||||
|
||||
|
||||
# ---------------------------
|
||||
# postprocess
|
||||
|
||||
class SerializerUnicode(object):
|
||||
@staticmethod
|
||||
def process(stmt):
|
||||
lines = split_unquoted_newlines(stmt)
|
||||
return '\n'.join(line.rstrip() for line in lines)
|
||||
124
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/output.py
Normal file
124
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/output.py
Normal file
@@ -0,0 +1,124 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import text_type
|
||||
|
||||
|
||||
class OutputFilter(object):
|
||||
varname_prefix = ''
|
||||
|
||||
def __init__(self, varname='sql'):
|
||||
self.varname = self.varname_prefix + varname
|
||||
self.count = 0
|
||||
|
||||
def _process(self, stream, varname, has_nl):
|
||||
raise NotImplementedError
|
||||
|
||||
def process(self, stmt):
|
||||
self.count += 1
|
||||
if self.count > 1:
|
||||
varname = u'{f.varname}{f.count}'.format(f=self)
|
||||
else:
|
||||
varname = self.varname
|
||||
|
||||
has_nl = len(text_type(stmt).strip().splitlines()) > 1
|
||||
stmt.tokens = self._process(stmt.tokens, varname, has_nl)
|
||||
return stmt
|
||||
|
||||
|
||||
class OutputPythonFilter(OutputFilter):
|
||||
def _process(self, stream, varname, has_nl):
|
||||
# SQL query assignation to varname
|
||||
if self.count > 1:
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
yield sql.Token(T.Name, varname)
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Operator, '=')
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
if has_nl:
|
||||
yield sql.Token(T.Operator, '(')
|
||||
yield sql.Token(T.Text, "'")
|
||||
|
||||
# Print the tokens on the quote
|
||||
for token in stream:
|
||||
# Token is a new line separator
|
||||
if token.is_whitespace and '\n' in token.value:
|
||||
# Close quote and add a new line
|
||||
yield sql.Token(T.Text, " '")
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
|
||||
# Quote header on secondary lines
|
||||
yield sql.Token(T.Whitespace, ' ' * (len(varname) + 4))
|
||||
yield sql.Token(T.Text, "'")
|
||||
|
||||
# Indentation
|
||||
after_lb = token.value.split('\n', 1)[1]
|
||||
if after_lb:
|
||||
yield sql.Token(T.Whitespace, after_lb)
|
||||
continue
|
||||
|
||||
# Token has escape chars
|
||||
elif "'" in token.value:
|
||||
token.value = token.value.replace("'", "\\'")
|
||||
|
||||
# Put the token
|
||||
yield sql.Token(T.Text, token.value)
|
||||
|
||||
# Close quote
|
||||
yield sql.Token(T.Text, "'")
|
||||
if has_nl:
|
||||
yield sql.Token(T.Operator, ')')
|
||||
|
||||
|
||||
class OutputPHPFilter(OutputFilter):
|
||||
varname_prefix = '$'
|
||||
|
||||
def _process(self, stream, varname, has_nl):
|
||||
# SQL query assignation to varname (quote header)
|
||||
if self.count > 1:
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
yield sql.Token(T.Name, varname)
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
if has_nl:
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Operator, '=')
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Text, '"')
|
||||
|
||||
# Print the tokens on the quote
|
||||
for token in stream:
|
||||
# Token is a new line separator
|
||||
if token.is_whitespace and '\n' in token.value:
|
||||
# Close quote and add a new line
|
||||
yield sql.Token(T.Text, ' ";')
|
||||
yield sql.Token(T.Whitespace, '\n')
|
||||
|
||||
# Quote header on secondary lines
|
||||
yield sql.Token(T.Name, varname)
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Operator, '.=')
|
||||
yield sql.Token(T.Whitespace, ' ')
|
||||
yield sql.Token(T.Text, '"')
|
||||
|
||||
# Indentation
|
||||
after_lb = token.value.split('\n', 1)[1]
|
||||
if after_lb:
|
||||
yield sql.Token(T.Whitespace, after_lb)
|
||||
continue
|
||||
|
||||
# Token has escape chars
|
||||
elif '"' in token.value:
|
||||
token.value = token.value.replace('"', '\\"')
|
||||
|
||||
# Put the token
|
||||
yield sql.Token(T.Text, token.value)
|
||||
|
||||
# Close quote
|
||||
yield sql.Token(T.Text, '"')
|
||||
yield sql.Token(T.Punctuation, ';')
|
||||
241
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/reindent.py
Normal file
241
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/reindent.py
Normal file
@@ -0,0 +1,241 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import text_type
|
||||
from sqlparse.utils import offset, indent
|
||||
|
||||
|
||||
class ReindentFilter(object):
|
||||
def __init__(self, width=2, char=' ', wrap_after=0, n='\n',
|
||||
comma_first=False, indent_after_first=False,
|
||||
indent_columns=False):
|
||||
self.n = n
|
||||
self.width = width
|
||||
self.char = char
|
||||
self.indent = 1 if indent_after_first else 0
|
||||
self.offset = 0
|
||||
self.wrap_after = wrap_after
|
||||
self.comma_first = comma_first
|
||||
self.indent_columns = indent_columns
|
||||
self._curr_stmt = None
|
||||
self._last_stmt = None
|
||||
self._last_func = None
|
||||
|
||||
def _flatten_up_to_token(self, token):
|
||||
"""Yields all tokens up to token but excluding current."""
|
||||
if token.is_group:
|
||||
token = next(token.flatten())
|
||||
|
||||
for t in self._curr_stmt.flatten():
|
||||
if t == token:
|
||||
break
|
||||
yield t
|
||||
|
||||
@property
|
||||
def leading_ws(self):
|
||||
return self.offset + self.indent * self.width
|
||||
|
||||
def _get_offset(self, token):
|
||||
raw = u''.join(map(text_type, self._flatten_up_to_token(token)))
|
||||
line = (raw or '\n').splitlines()[-1]
|
||||
# Now take current offset into account and return relative offset.
|
||||
return len(line) - len(self.char * self.leading_ws)
|
||||
|
||||
def nl(self, offset=0):
|
||||
return sql.Token(
|
||||
T.Whitespace,
|
||||
self.n + self.char * max(0, self.leading_ws + offset))
|
||||
|
||||
def _next_token(self, tlist, idx=-1):
|
||||
split_words = ('FROM', 'STRAIGHT_JOIN$', 'JOIN$', 'AND', 'OR',
|
||||
'GROUP BY', 'ORDER BY', 'UNION', 'VALUES',
|
||||
'SET', 'BETWEEN', 'EXCEPT', 'HAVING', 'LIMIT')
|
||||
m_split = T.Keyword, split_words, True
|
||||
tidx, token = tlist.token_next_by(m=m_split, idx=idx)
|
||||
|
||||
if token and token.normalized == 'BETWEEN':
|
||||
tidx, token = self._next_token(tlist, tidx)
|
||||
|
||||
if token and token.normalized == 'AND':
|
||||
tidx, token = self._next_token(tlist, tidx)
|
||||
|
||||
return tidx, token
|
||||
|
||||
def _split_kwds(self, tlist):
|
||||
tidx, token = self._next_token(tlist)
|
||||
while token:
|
||||
pidx, prev_ = tlist.token_prev(tidx, skip_ws=False)
|
||||
uprev = text_type(prev_)
|
||||
|
||||
if prev_ and prev_.is_whitespace:
|
||||
del tlist.tokens[pidx]
|
||||
tidx -= 1
|
||||
|
||||
if not (uprev.endswith('\n') or uprev.endswith('\r')):
|
||||
tlist.insert_before(tidx, self.nl())
|
||||
tidx += 1
|
||||
|
||||
tidx, token = self._next_token(tlist, tidx)
|
||||
|
||||
def _split_statements(self, tlist):
|
||||
ttypes = T.Keyword.DML, T.Keyword.DDL
|
||||
tidx, token = tlist.token_next_by(t=ttypes)
|
||||
while token:
|
||||
pidx, prev_ = tlist.token_prev(tidx, skip_ws=False)
|
||||
if prev_ and prev_.is_whitespace:
|
||||
del tlist.tokens[pidx]
|
||||
tidx -= 1
|
||||
# only break if it's not the first token
|
||||
if prev_:
|
||||
tlist.insert_before(tidx, self.nl())
|
||||
tidx += 1
|
||||
tidx, token = tlist.token_next_by(t=ttypes, idx=tidx)
|
||||
|
||||
def _process(self, tlist):
|
||||
func_name = '_process_{cls}'.format(cls=type(tlist).__name__)
|
||||
func = getattr(self, func_name.lower(), self._process_default)
|
||||
func(tlist)
|
||||
|
||||
def _process_where(self, tlist):
|
||||
tidx, token = tlist.token_next_by(m=(T.Keyword, 'WHERE'))
|
||||
# issue121, errors in statement fixed??
|
||||
tlist.insert_before(tidx, self.nl())
|
||||
|
||||
with indent(self):
|
||||
self._process_default(tlist)
|
||||
|
||||
def _process_parenthesis(self, tlist):
|
||||
ttypes = T.Keyword.DML, T.Keyword.DDL
|
||||
_, is_dml_dll = tlist.token_next_by(t=ttypes)
|
||||
fidx, first = tlist.token_next_by(m=sql.Parenthesis.M_OPEN)
|
||||
|
||||
with indent(self, 1 if is_dml_dll else 0):
|
||||
tlist.tokens.insert(0, self.nl()) if is_dml_dll else None
|
||||
with offset(self, self._get_offset(first) + 1):
|
||||
self._process_default(tlist, not is_dml_dll)
|
||||
|
||||
def _process_function(self, tlist):
|
||||
self._last_func = tlist[0]
|
||||
self._process_default(tlist)
|
||||
|
||||
def _process_identifierlist(self, tlist):
|
||||
identifiers = list(tlist.get_identifiers())
|
||||
if self.indent_columns:
|
||||
first = next(identifiers[0].flatten())
|
||||
num_offset = 1 if self.char == '\t' else self.width
|
||||
else:
|
||||
first = next(identifiers.pop(0).flatten())
|
||||
num_offset = 1 if self.char == '\t' else self._get_offset(first)
|
||||
|
||||
if not tlist.within(sql.Function) and not tlist.within(sql.Values):
|
||||
with offset(self, num_offset):
|
||||
position = 0
|
||||
for token in identifiers:
|
||||
# Add 1 for the "," separator
|
||||
position += len(token.value) + 1
|
||||
if position > (self.wrap_after - self.offset):
|
||||
adjust = 0
|
||||
if self.comma_first:
|
||||
adjust = -2
|
||||
_, comma = tlist.token_prev(
|
||||
tlist.token_index(token))
|
||||
if comma is None:
|
||||
continue
|
||||
token = comma
|
||||
tlist.insert_before(token, self.nl(offset=adjust))
|
||||
if self.comma_first:
|
||||
_, ws = tlist.token_next(
|
||||
tlist.token_index(token), skip_ws=False)
|
||||
if (ws is not None
|
||||
and ws.ttype is not T.Text.Whitespace):
|
||||
tlist.insert_after(
|
||||
token, sql.Token(T.Whitespace, ' '))
|
||||
position = 0
|
||||
else:
|
||||
# ensure whitespace
|
||||
for token in tlist:
|
||||
_, next_ws = tlist.token_next(
|
||||
tlist.token_index(token), skip_ws=False)
|
||||
if token.value == ',' and not next_ws.is_whitespace:
|
||||
tlist.insert_after(
|
||||
token, sql.Token(T.Whitespace, ' '))
|
||||
|
||||
end_at = self.offset + sum(len(i.value) + 1 for i in identifiers)
|
||||
adjusted_offset = 0
|
||||
if (self.wrap_after > 0
|
||||
and end_at > (self.wrap_after - self.offset)
|
||||
and self._last_func):
|
||||
adjusted_offset = -len(self._last_func.value) - 1
|
||||
|
||||
with offset(self, adjusted_offset), indent(self):
|
||||
if adjusted_offset < 0:
|
||||
tlist.insert_before(identifiers[0], self.nl())
|
||||
position = 0
|
||||
for token in identifiers:
|
||||
# Add 1 for the "," separator
|
||||
position += len(token.value) + 1
|
||||
if (self.wrap_after > 0
|
||||
and position > (self.wrap_after - self.offset)):
|
||||
adjust = 0
|
||||
tlist.insert_before(token, self.nl(offset=adjust))
|
||||
position = 0
|
||||
self._process_default(tlist)
|
||||
|
||||
def _process_case(self, tlist):
|
||||
iterable = iter(tlist.get_cases())
|
||||
cond, _ = next(iterable)
|
||||
first = next(cond[0].flatten())
|
||||
|
||||
with offset(self, self._get_offset(tlist[0])):
|
||||
with offset(self, self._get_offset(first)):
|
||||
for cond, value in iterable:
|
||||
token = value[0] if cond is None else cond[0]
|
||||
tlist.insert_before(token, self.nl())
|
||||
|
||||
# Line breaks on group level are done. let's add an offset of
|
||||
# len "when ", "then ", "else "
|
||||
with offset(self, len("WHEN ")):
|
||||
self._process_default(tlist)
|
||||
end_idx, end = tlist.token_next_by(m=sql.Case.M_CLOSE)
|
||||
if end_idx is not None:
|
||||
tlist.insert_before(end_idx, self.nl())
|
||||
|
||||
def _process_values(self, tlist):
|
||||
tlist.insert_before(0, self.nl())
|
||||
tidx, token = tlist.token_next_by(i=sql.Parenthesis)
|
||||
first_token = token
|
||||
while token:
|
||||
ptidx, ptoken = tlist.token_next_by(m=(T.Punctuation, ','),
|
||||
idx=tidx)
|
||||
if ptoken:
|
||||
if self.comma_first:
|
||||
adjust = -2
|
||||
offset = self._get_offset(first_token) + adjust
|
||||
tlist.insert_before(ptoken, self.nl(offset))
|
||||
else:
|
||||
tlist.insert_after(ptoken,
|
||||
self.nl(self._get_offset(token)))
|
||||
tidx, token = tlist.token_next_by(i=sql.Parenthesis, idx=tidx)
|
||||
|
||||
def _process_default(self, tlist, stmts=True):
|
||||
self._split_statements(tlist) if stmts else None
|
||||
self._split_kwds(tlist)
|
||||
for sgroup in tlist.get_sublists():
|
||||
self._process(sgroup)
|
||||
|
||||
def process(self, stmt):
|
||||
self._curr_stmt = stmt
|
||||
self._process(stmt)
|
||||
|
||||
if self._last_stmt is not None:
|
||||
nl = '\n' if text_type(self._last_stmt).endswith('\n') else '\n\n'
|
||||
stmt.tokens.insert(0, sql.Token(T.Whitespace, nl))
|
||||
|
||||
self._last_stmt = stmt
|
||||
return stmt
|
||||
50
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/right_margin.py
Normal file
50
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/right_margin.py
Normal file
@@ -0,0 +1,50 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
import re
|
||||
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import text_type
|
||||
|
||||
|
||||
# FIXME: Doesn't work
|
||||
class RightMarginFilter(object):
|
||||
keep_together = (
|
||||
# sql.TypeCast, sql.Identifier, sql.Alias,
|
||||
)
|
||||
|
||||
def __init__(self, width=79):
|
||||
self.width = width
|
||||
self.line = ''
|
||||
|
||||
def _process(self, group, stream):
|
||||
for token in stream:
|
||||
if token.is_whitespace and '\n' in token.value:
|
||||
if token.value.endswith('\n'):
|
||||
self.line = ''
|
||||
else:
|
||||
self.line = token.value.splitlines()[-1]
|
||||
elif token.is_group and type(token) not in self.keep_together:
|
||||
token.tokens = self._process(token, token.tokens)
|
||||
else:
|
||||
val = text_type(token)
|
||||
if len(self.line) + len(val) > self.width:
|
||||
match = re.search(r'^ +', self.line)
|
||||
if match is not None:
|
||||
indent = match.group()
|
||||
else:
|
||||
indent = ''
|
||||
yield sql.Token(T.Whitespace, '\n{0}'.format(indent))
|
||||
self.line = indent
|
||||
self.line += val
|
||||
yield token
|
||||
|
||||
def process(self, group):
|
||||
# return
|
||||
# group.tokens = self._process(group, group.tokens)
|
||||
raise NotImplementedError
|
||||
61
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/tokens.py
Normal file
61
shell/ext-py/sqlparse-0.3.1/sqlparse/filters/tokens.py
Normal file
@@ -0,0 +1,61 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
from sqlparse import tokens as T
|
||||
from sqlparse.compat import text_type
|
||||
|
||||
|
||||
class _CaseFilter(object):
|
||||
ttype = None
|
||||
|
||||
def __init__(self, case=None):
|
||||
case = case or 'upper'
|
||||
self.convert = getattr(text_type, case)
|
||||
|
||||
def process(self, stream):
|
||||
for ttype, value in stream:
|
||||
if ttype in self.ttype:
|
||||
value = self.convert(value)
|
||||
yield ttype, value
|
||||
|
||||
|
||||
class KeywordCaseFilter(_CaseFilter):
|
||||
ttype = T.Keyword
|
||||
|
||||
|
||||
class IdentifierCaseFilter(_CaseFilter):
|
||||
ttype = T.Name, T.String.Symbol
|
||||
|
||||
def process(self, stream):
|
||||
for ttype, value in stream:
|
||||
if ttype in self.ttype and value.strip()[0] != '"':
|
||||
value = self.convert(value)
|
||||
yield ttype, value
|
||||
|
||||
|
||||
class TruncateStringFilter(object):
|
||||
def __init__(self, width, char):
|
||||
self.width = width
|
||||
self.char = char
|
||||
|
||||
def process(self, stream):
|
||||
for ttype, value in stream:
|
||||
if ttype != T.Literal.String.Single:
|
||||
yield ttype, value
|
||||
continue
|
||||
|
||||
if value[:2] == "''":
|
||||
inner = value[2:-2]
|
||||
quote = "''"
|
||||
else:
|
||||
inner = value[1:-1]
|
||||
quote = "'"
|
||||
|
||||
if len(inner) > self.width:
|
||||
value = ''.join((quote, inner[:self.width], self.char, quote))
|
||||
yield ttype, value
|
||||
199
shell/ext-py/sqlparse-0.3.1/sqlparse/formatter.py
Normal file
199
shell/ext-py/sqlparse-0.3.1/sqlparse/formatter.py
Normal file
@@ -0,0 +1,199 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""SQL formatter"""
|
||||
|
||||
from sqlparse import filters
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
|
||||
|
||||
def validate_options(options):
|
||||
"""Validates options."""
|
||||
kwcase = options.get('keyword_case')
|
||||
if kwcase not in [None, 'upper', 'lower', 'capitalize']:
|
||||
raise SQLParseError('Invalid value for keyword_case: '
|
||||
'{0!r}'.format(kwcase))
|
||||
|
||||
idcase = options.get('identifier_case')
|
||||
if idcase not in [None, 'upper', 'lower', 'capitalize']:
|
||||
raise SQLParseError('Invalid value for identifier_case: '
|
||||
'{0!r}'.format(idcase))
|
||||
|
||||
ofrmt = options.get('output_format')
|
||||
if ofrmt not in [None, 'sql', 'python', 'php']:
|
||||
raise SQLParseError('Unknown output format: '
|
||||
'{0!r}'.format(ofrmt))
|
||||
|
||||
strip_comments = options.get('strip_comments', False)
|
||||
if strip_comments not in [True, False]:
|
||||
raise SQLParseError('Invalid value for strip_comments: '
|
||||
'{0!r}'.format(strip_comments))
|
||||
|
||||
space_around_operators = options.get('use_space_around_operators', False)
|
||||
if space_around_operators not in [True, False]:
|
||||
raise SQLParseError('Invalid value for use_space_around_operators: '
|
||||
'{0!r}'.format(space_around_operators))
|
||||
|
||||
strip_ws = options.get('strip_whitespace', False)
|
||||
if strip_ws not in [True, False]:
|
||||
raise SQLParseError('Invalid value for strip_whitespace: '
|
||||
'{0!r}'.format(strip_ws))
|
||||
|
||||
truncate_strings = options.get('truncate_strings')
|
||||
if truncate_strings is not None:
|
||||
try:
|
||||
truncate_strings = int(truncate_strings)
|
||||
except (ValueError, TypeError):
|
||||
raise SQLParseError('Invalid value for truncate_strings: '
|
||||
'{0!r}'.format(truncate_strings))
|
||||
if truncate_strings <= 1:
|
||||
raise SQLParseError('Invalid value for truncate_strings: '
|
||||
'{0!r}'.format(truncate_strings))
|
||||
options['truncate_strings'] = truncate_strings
|
||||
options['truncate_char'] = options.get('truncate_char', '[...]')
|
||||
|
||||
indent_columns = options.get('indent_columns', False)
|
||||
if indent_columns not in [True, False]:
|
||||
raise SQLParseError('Invalid value for indent_columns: '
|
||||
'{0!r}'.format(indent_columns))
|
||||
elif indent_columns:
|
||||
options['reindent'] = True # enforce reindent
|
||||
options['indent_columns'] = indent_columns
|
||||
|
||||
reindent = options.get('reindent', False)
|
||||
if reindent not in [True, False]:
|
||||
raise SQLParseError('Invalid value for reindent: '
|
||||
'{0!r}'.format(reindent))
|
||||
elif reindent:
|
||||
options['strip_whitespace'] = True
|
||||
|
||||
reindent_aligned = options.get('reindent_aligned', False)
|
||||
if reindent_aligned not in [True, False]:
|
||||
raise SQLParseError('Invalid value for reindent_aligned: '
|
||||
'{0!r}'.format(reindent))
|
||||
elif reindent_aligned:
|
||||
options['strip_whitespace'] = True
|
||||
|
||||
indent_after_first = options.get('indent_after_first', False)
|
||||
if indent_after_first not in [True, False]:
|
||||
raise SQLParseError('Invalid value for indent_after_first: '
|
||||
'{0!r}'.format(indent_after_first))
|
||||
options['indent_after_first'] = indent_after_first
|
||||
|
||||
indent_tabs = options.get('indent_tabs', False)
|
||||
if indent_tabs not in [True, False]:
|
||||
raise SQLParseError('Invalid value for indent_tabs: '
|
||||
'{0!r}'.format(indent_tabs))
|
||||
elif indent_tabs:
|
||||
options['indent_char'] = '\t'
|
||||
else:
|
||||
options['indent_char'] = ' '
|
||||
|
||||
indent_width = options.get('indent_width', 2)
|
||||
try:
|
||||
indent_width = int(indent_width)
|
||||
except (TypeError, ValueError):
|
||||
raise SQLParseError('indent_width requires an integer')
|
||||
if indent_width < 1:
|
||||
raise SQLParseError('indent_width requires a positive integer')
|
||||
options['indent_width'] = indent_width
|
||||
|
||||
wrap_after = options.get('wrap_after', 0)
|
||||
try:
|
||||
wrap_after = int(wrap_after)
|
||||
except (TypeError, ValueError):
|
||||
raise SQLParseError('wrap_after requires an integer')
|
||||
if wrap_after < 0:
|
||||
raise SQLParseError('wrap_after requires a positive integer')
|
||||
options['wrap_after'] = wrap_after
|
||||
|
||||
comma_first = options.get('comma_first', False)
|
||||
if comma_first not in [True, False]:
|
||||
raise SQLParseError('comma_first requires a boolean value')
|
||||
options['comma_first'] = comma_first
|
||||
|
||||
right_margin = options.get('right_margin')
|
||||
if right_margin is not None:
|
||||
try:
|
||||
right_margin = int(right_margin)
|
||||
except (TypeError, ValueError):
|
||||
raise SQLParseError('right_margin requires an integer')
|
||||
if right_margin < 10:
|
||||
raise SQLParseError('right_margin requires an integer > 10')
|
||||
options['right_margin'] = right_margin
|
||||
|
||||
return options
|
||||
|
||||
|
||||
def build_filter_stack(stack, options):
|
||||
"""Setup and return a filter stack.
|
||||
|
||||
Args:
|
||||
stack: :class:`~sqlparse.filters.FilterStack` instance
|
||||
options: Dictionary with options validated by validate_options.
|
||||
"""
|
||||
# Token filter
|
||||
if options.get('keyword_case'):
|
||||
stack.preprocess.append(
|
||||
filters.KeywordCaseFilter(options['keyword_case']))
|
||||
|
||||
if options.get('identifier_case'):
|
||||
stack.preprocess.append(
|
||||
filters.IdentifierCaseFilter(options['identifier_case']))
|
||||
|
||||
if options.get('truncate_strings'):
|
||||
stack.preprocess.append(filters.TruncateStringFilter(
|
||||
width=options['truncate_strings'], char=options['truncate_char']))
|
||||
|
||||
if options.get('use_space_around_operators', False):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(filters.SpacesAroundOperatorsFilter())
|
||||
|
||||
# After grouping
|
||||
if options.get('strip_comments'):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(filters.StripCommentsFilter())
|
||||
|
||||
if options.get('strip_whitespace') or options.get('reindent'):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(filters.StripWhitespaceFilter())
|
||||
|
||||
if options.get('reindent'):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(
|
||||
filters.ReindentFilter(
|
||||
char=options['indent_char'],
|
||||
width=options['indent_width'],
|
||||
indent_after_first=options['indent_after_first'],
|
||||
indent_columns=options['indent_columns'],
|
||||
wrap_after=options['wrap_after'],
|
||||
comma_first=options['comma_first']))
|
||||
|
||||
if options.get('reindent_aligned', False):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(
|
||||
filters.AlignedIndentFilter(char=options['indent_char']))
|
||||
|
||||
if options.get('right_margin'):
|
||||
stack.enable_grouping()
|
||||
stack.stmtprocess.append(
|
||||
filters.RightMarginFilter(width=options['right_margin']))
|
||||
|
||||
# Serializer
|
||||
if options.get('output_format'):
|
||||
frmt = options['output_format']
|
||||
if frmt.lower() == 'php':
|
||||
fltr = filters.OutputPHPFilter()
|
||||
elif frmt.lower() == 'python':
|
||||
fltr = filters.OutputPythonFilter()
|
||||
else:
|
||||
fltr = None
|
||||
if fltr is not None:
|
||||
stack.postprocess.append(fltr)
|
||||
|
||||
return stack
|
||||
@@ -1,5 +1,104 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
import re
|
||||
|
||||
from sqlparse import tokens
|
||||
|
||||
|
||||
def is_keyword(value):
|
||||
val = value.upper()
|
||||
return (KEYWORDS_COMMON.get(val)
|
||||
or KEYWORDS_ORACLE.get(val)
|
||||
or KEYWORDS_PLPGSQL.get(val)
|
||||
or KEYWORDS_HQL.get(val)
|
||||
or KEYWORDS.get(val, tokens.Name)), value
|
||||
|
||||
|
||||
SQL_REGEX = {
|
||||
'root': [
|
||||
(r'(--|# )\+.*?(\r\n|\r|\n|$)', tokens.Comment.Single.Hint),
|
||||
(r'/\*\+[\s\S]*?\*/', tokens.Comment.Multiline.Hint),
|
||||
|
||||
(r'(--|# ).*?(\r\n|\r|\n|$)', tokens.Comment.Single),
|
||||
(r'/\*[\s\S]*?\*/', tokens.Comment.Multiline),
|
||||
|
||||
(r'(\r\n|\r|\n)', tokens.Newline),
|
||||
(r'\s+?', tokens.Whitespace),
|
||||
|
||||
(r':=', tokens.Assignment),
|
||||
(r'::', tokens.Punctuation),
|
||||
|
||||
(r'\*', tokens.Wildcard),
|
||||
|
||||
(r"`(``|[^`])*`", tokens.Name),
|
||||
(r"´(´´|[^´])*´", tokens.Name),
|
||||
(r'((?<!\S)\$(?:[_A-ZÀ-Ü]\w*)?\$)[\s\S]*?\1', tokens.Literal),
|
||||
|
||||
(r'\?', tokens.Name.Placeholder),
|
||||
(r'%(\(\w+\))?s', tokens.Name.Placeholder),
|
||||
(r'(?<!\w)[$:?]\w+', tokens.Name.Placeholder),
|
||||
|
||||
(r'\\\w+', tokens.Command),
|
||||
|
||||
# FIXME(andi): VALUES shouldn't be listed here
|
||||
# see https://github.com/andialbrecht/sqlparse/pull/64
|
||||
# AS and IN are special, it may be followed by a parenthesis, but
|
||||
# are never functions, see issue183 and issue507
|
||||
(r'(CASE|IN|VALUES|USING|FROM|AS)\b', tokens.Keyword),
|
||||
|
||||
(r'(@|##|#)[A-ZÀ-Ü]\w+', tokens.Name),
|
||||
|
||||
# see issue #39
|
||||
# Spaces around period `schema . name` are valid identifier
|
||||
# TODO: Spaces before period not implemented
|
||||
(r'[A-ZÀ-Ü]\w*(?=\s*\.)', tokens.Name), # 'Name' .
|
||||
# FIXME(atronah): never match,
|
||||
# because `re.match` doesn't work with look-behind regexp feature
|
||||
(r'(?<=\.)[A-ZÀ-Ü]\w*', tokens.Name), # .'Name'
|
||||
(r'[A-ZÀ-Ü]\w*(?=\()', tokens.Name), # side effect: change kw to func
|
||||
(r'-?0x[\dA-F]+', tokens.Number.Hexadecimal),
|
||||
(r'-?\d*(\.\d+)?E-?\d+', tokens.Number.Float),
|
||||
(r'(?![_A-ZÀ-Ü])-?(\d+(\.\d*)|\.\d+)(?![_A-ZÀ-Ü])',
|
||||
tokens.Number.Float),
|
||||
(r'(?![_A-ZÀ-Ü])-?\d+(?![_A-ZÀ-Ü])', tokens.Number.Integer),
|
||||
(r"'(''|\\\\|\\'|[^'])*'", tokens.String.Single),
|
||||
# not a real string literal in ANSI SQL:
|
||||
(r'"(""|\\\\|\\"|[^"])*"', tokens.String.Symbol),
|
||||
(r'(""|".*?[^\\]")', tokens.String.Symbol),
|
||||
# sqlite names can be escaped with [square brackets]. left bracket
|
||||
# cannot be preceded by word character or a right bracket --
|
||||
# otherwise it's probably an array index
|
||||
(r'(?<![\w\])])(\[[^\]]+\])', tokens.Name),
|
||||
(r'((LEFT\s+|RIGHT\s+|FULL\s+)?(INNER\s+|OUTER\s+|STRAIGHT\s+)?'
|
||||
r'|(CROSS\s+|NATURAL\s+)?)?JOIN\b', tokens.Keyword),
|
||||
(r'END(\s+IF|\s+LOOP|\s+WHILE)?\b', tokens.Keyword),
|
||||
(r'NOT\s+NULL\b', tokens.Keyword),
|
||||
(r'NULLS\s+(FIRST|LAST)\b', tokens.Keyword),
|
||||
(r'UNION\s+ALL\b', tokens.Keyword),
|
||||
(r'CREATE(\s+OR\s+REPLACE)?\b', tokens.Keyword.DDL),
|
||||
(r'DOUBLE\s+PRECISION\b', tokens.Name.Builtin),
|
||||
(r'GROUP\s+BY\b', tokens.Keyword),
|
||||
(r'ORDER\s+BY\b', tokens.Keyword),
|
||||
(r'(LATERAL\s+VIEW\s+)'
|
||||
r'(EXPLODE|INLINE|PARSE_URL_TUPLE|POSEXPLODE|STACK)\b',
|
||||
tokens.Keyword),
|
||||
(r"(AT|WITH')\s+TIME\s+ZONE\s+'[^']+'", tokens.Keyword.TZCast),
|
||||
(r'(NOT\s+)?(LIKE|ILIKE)\b', tokens.Operator.Comparison),
|
||||
(r'[0-9_A-ZÀ-Ü][_$#\w]*', is_keyword),
|
||||
(r'[;:()\[\],\.]', tokens.Punctuation),
|
||||
(r'[<>=~!]+', tokens.Operator.Comparison),
|
||||
(r'[+/@#%^&|`?^-]+', tokens.Operator),
|
||||
]}
|
||||
|
||||
FLAGS = re.IGNORECASE | re.UNICODE
|
||||
SQL_REGEX = [(re.compile(rx, FLAGS).match, tt) for rx, tt in SQL_REGEX['root']]
|
||||
|
||||
KEYWORDS = {
|
||||
'ABORT': tokens.Keyword,
|
||||
'ABS': tokens.Keyword,
|
||||
@@ -16,6 +115,7 @@ KEYWORDS = {
|
||||
'ANALYSE': tokens.Keyword,
|
||||
'ANALYZE': tokens.Keyword,
|
||||
'ANY': tokens.Keyword,
|
||||
'ARRAYLEN': tokens.Keyword,
|
||||
'ARE': tokens.Keyword,
|
||||
'ASC': tokens.Keyword.Order,
|
||||
'ASENSITIVE': tokens.Keyword,
|
||||
@@ -24,7 +124,9 @@ KEYWORDS = {
|
||||
'ASYMMETRIC': tokens.Keyword,
|
||||
'AT': tokens.Keyword,
|
||||
'ATOMIC': tokens.Keyword,
|
||||
'AUDIT': tokens.Keyword,
|
||||
'AUTHORIZATION': tokens.Keyword,
|
||||
'AUTO_INCREMENT': tokens.Keyword,
|
||||
'AVG': tokens.Keyword,
|
||||
|
||||
'BACKWARD': tokens.Keyword,
|
||||
@@ -53,6 +155,7 @@ KEYWORDS = {
|
||||
'CHARACTER_SET_NAME': tokens.Keyword,
|
||||
'CHARACTER_SET_SCHEMA': tokens.Keyword,
|
||||
'CHAR_LENGTH': tokens.Keyword,
|
||||
'CHARSET': tokens.Keyword,
|
||||
'CHECK': tokens.Keyword,
|
||||
'CHECKED': tokens.Keyword,
|
||||
'CHECKPOINT': tokens.Keyword,
|
||||
@@ -71,12 +174,14 @@ KEYWORDS = {
|
||||
'COLLECT': tokens.Keyword,
|
||||
'COLUMN': tokens.Keyword,
|
||||
'COLUMN_NAME': tokens.Keyword,
|
||||
'COMPRESS': tokens.Keyword,
|
||||
'COMMAND_FUNCTION': tokens.Keyword,
|
||||
'COMMAND_FUNCTION_CODE': tokens.Keyword,
|
||||
'COMMENT': tokens.Keyword,
|
||||
'COMMIT': tokens.Keyword.DML,
|
||||
'COMMITTED': tokens.Keyword,
|
||||
'COMPLETION': tokens.Keyword,
|
||||
'CONCURRENTLY': tokens.Keyword,
|
||||
'CONDITION_NUMBER': tokens.Keyword,
|
||||
'CONNECT': tokens.Keyword,
|
||||
'CONNECTION': tokens.Keyword,
|
||||
@@ -92,7 +197,7 @@ KEYWORDS = {
|
||||
'CONVERSION': tokens.Keyword,
|
||||
'CONVERT': tokens.Keyword,
|
||||
'COPY': tokens.Keyword,
|
||||
'CORRESPONTING': tokens.Keyword,
|
||||
'CORRESPONDING': tokens.Keyword,
|
||||
'COUNT': tokens.Keyword,
|
||||
'CREATEDB': tokens.Keyword,
|
||||
'CREATEUSER': tokens.Keyword,
|
||||
@@ -133,6 +238,7 @@ KEYWORDS = {
|
||||
'DETERMINISTIC': tokens.Keyword,
|
||||
'DIAGNOSTICS': tokens.Keyword,
|
||||
'DICTIONARY': tokens.Keyword,
|
||||
'DISABLE': tokens.Keyword,
|
||||
'DISCONNECT': tokens.Keyword,
|
||||
'DISPATCH': tokens.Keyword,
|
||||
'DO': tokens.Keyword,
|
||||
@@ -142,25 +248,29 @@ KEYWORDS = {
|
||||
'DYNAMIC_FUNCTION_CODE': tokens.Keyword,
|
||||
|
||||
'EACH': tokens.Keyword,
|
||||
'ENABLE': tokens.Keyword,
|
||||
'ENCODING': tokens.Keyword,
|
||||
'ENCRYPTED': tokens.Keyword,
|
||||
'END-EXEC': tokens.Keyword,
|
||||
'ENGINE': tokens.Keyword,
|
||||
'EQUALS': tokens.Keyword,
|
||||
'ESCAPE': tokens.Keyword,
|
||||
'EVERY': tokens.Keyword,
|
||||
'EXCEPT': tokens.Keyword,
|
||||
'ESCEPTION': tokens.Keyword,
|
||||
'EXCEPTION': tokens.Keyword,
|
||||
'EXCLUDING': tokens.Keyword,
|
||||
'EXCLUSIVE': tokens.Keyword,
|
||||
'EXEC': tokens.Keyword,
|
||||
'EXECUTE': tokens.Keyword,
|
||||
'EXISTING': tokens.Keyword,
|
||||
'EXISTS': tokens.Keyword,
|
||||
'EXPLAIN': tokens.Keyword,
|
||||
'EXTERNAL': tokens.Keyword,
|
||||
'EXTRACT': tokens.Keyword,
|
||||
|
||||
'FALSE': tokens.Keyword,
|
||||
'FETCH': tokens.Keyword,
|
||||
'FILE': tokens.Keyword,
|
||||
'FINAL': tokens.Keyword,
|
||||
'FIRST': tokens.Keyword,
|
||||
'FORCE': tokens.Keyword,
|
||||
@@ -189,8 +299,10 @@ KEYWORDS = {
|
||||
'HAVING': tokens.Keyword,
|
||||
'HIERARCHY': tokens.Keyword,
|
||||
'HOLD': tokens.Keyword,
|
||||
'HOUR': tokens.Keyword,
|
||||
'HOST': tokens.Keyword,
|
||||
|
||||
'IDENTIFIED': tokens.Keyword,
|
||||
'IDENTITY': tokens.Keyword,
|
||||
'IGNORE': tokens.Keyword,
|
||||
'ILIKE': tokens.Keyword,
|
||||
@@ -206,6 +318,7 @@ KEYWORDS = {
|
||||
'INDITCATOR': tokens.Keyword,
|
||||
'INFIX': tokens.Keyword,
|
||||
'INHERITS': tokens.Keyword,
|
||||
'INITIAL': tokens.Keyword,
|
||||
'INITIALIZE': tokens.Keyword,
|
||||
'INITIALLY': tokens.Keyword,
|
||||
'INOUT': tokens.Keyword,
|
||||
@@ -249,12 +362,14 @@ KEYWORDS = {
|
||||
# 'M': tokens.Keyword,
|
||||
'MAP': tokens.Keyword,
|
||||
'MATCH': tokens.Keyword,
|
||||
'MAXEXTENTS': tokens.Keyword,
|
||||
'MAXVALUE': tokens.Keyword,
|
||||
'MESSAGE_LENGTH': tokens.Keyword,
|
||||
'MESSAGE_OCTET_LENGTH': tokens.Keyword,
|
||||
'MESSAGE_TEXT': tokens.Keyword,
|
||||
'METHOD': tokens.Keyword,
|
||||
'MINUTE': tokens.Keyword,
|
||||
'MINUS': tokens.Keyword,
|
||||
'MINVALUE': tokens.Keyword,
|
||||
'MOD': tokens.Keyword,
|
||||
'MODE': tokens.Keyword,
|
||||
@@ -273,13 +388,17 @@ KEYWORDS = {
|
||||
'NEW': tokens.Keyword,
|
||||
'NEXT': tokens.Keyword,
|
||||
'NO': tokens.Keyword,
|
||||
'NOAUDIT': tokens.Keyword,
|
||||
'NOCOMPRESS': tokens.Keyword,
|
||||
'NOCREATEDB': tokens.Keyword,
|
||||
'NOCREATEUSER': tokens.Keyword,
|
||||
'NONE': tokens.Keyword,
|
||||
'NOT': tokens.Keyword,
|
||||
'NOTFOUND': tokens.Keyword,
|
||||
'NOTHING': tokens.Keyword,
|
||||
'NOTIFY': tokens.Keyword,
|
||||
'NOTNULL': tokens.Keyword,
|
||||
'NOWAIT': tokens.Keyword,
|
||||
'NULL': tokens.Keyword,
|
||||
'NULLABLE': tokens.Keyword,
|
||||
'NULLIF': tokens.Keyword,
|
||||
@@ -288,9 +407,11 @@ KEYWORDS = {
|
||||
'OCTET_LENGTH': tokens.Keyword,
|
||||
'OF': tokens.Keyword,
|
||||
'OFF': tokens.Keyword,
|
||||
'OFFLINE': tokens.Keyword,
|
||||
'OFFSET': tokens.Keyword,
|
||||
'OIDS': tokens.Keyword,
|
||||
'OLD': tokens.Keyword,
|
||||
'ONLINE': tokens.Keyword,
|
||||
'ONLY': tokens.Keyword,
|
||||
'OPEN': tokens.Keyword,
|
||||
'OPERATION': tokens.Keyword,
|
||||
@@ -305,17 +426,20 @@ KEYWORDS = {
|
||||
'OVERRIDING': tokens.Keyword,
|
||||
'OWNER': tokens.Keyword,
|
||||
|
||||
'QUARTER': tokens.Keyword,
|
||||
|
||||
'PAD': tokens.Keyword,
|
||||
'PARAMETER': tokens.Keyword,
|
||||
'PARAMETERS': tokens.Keyword,
|
||||
'PARAMETER_MODE': tokens.Keyword,
|
||||
'PARAMATER_NAME': tokens.Keyword,
|
||||
'PARAMATER_ORDINAL_POSITION': tokens.Keyword,
|
||||
'PARAMETER_NAME': tokens.Keyword,
|
||||
'PARAMETER_ORDINAL_POSITION': tokens.Keyword,
|
||||
'PARAMETER_SPECIFIC_CATALOG': tokens.Keyword,
|
||||
'PARAMETER_SPECIFIC_NAME': tokens.Keyword,
|
||||
'PARAMATER_SPECIFIC_SCHEMA': tokens.Keyword,
|
||||
'PARAMETER_SPECIFIC_SCHEMA': tokens.Keyword,
|
||||
'PARTIAL': tokens.Keyword,
|
||||
'PASCAL': tokens.Keyword,
|
||||
'PCTFREE': tokens.Keyword,
|
||||
'PENDANT': tokens.Keyword,
|
||||
'PLACING': tokens.Keyword,
|
||||
'PLI': tokens.Keyword,
|
||||
@@ -334,6 +458,7 @@ KEYWORDS = {
|
||||
'PUBLIC': tokens.Keyword,
|
||||
|
||||
'RAISE': tokens.Keyword,
|
||||
'RAW': tokens.Keyword,
|
||||
'READ': tokens.Keyword,
|
||||
'READS': tokens.Keyword,
|
||||
'RECHECK': tokens.Keyword,
|
||||
@@ -346,6 +471,7 @@ KEYWORDS = {
|
||||
'RENAME': tokens.Keyword,
|
||||
'REPEATABLE': tokens.Keyword,
|
||||
'RESET': tokens.Keyword,
|
||||
'RESOURCE': tokens.Keyword,
|
||||
'RESTART': tokens.Keyword,
|
||||
'RESTRICT': tokens.Keyword,
|
||||
'RESULT': tokens.Keyword,
|
||||
@@ -353,6 +479,7 @@ KEYWORDS = {
|
||||
'RETURNED_LENGTH': tokens.Keyword,
|
||||
'RETURNED_OCTET_LENGTH': tokens.Keyword,
|
||||
'RETURNED_SQLSTATE': tokens.Keyword,
|
||||
'RETURNING': tokens.Keyword,
|
||||
'RETURNS': tokens.Keyword,
|
||||
'REVOKE': tokens.Keyword,
|
||||
'RIGHT': tokens.Keyword,
|
||||
@@ -379,6 +506,7 @@ KEYWORDS = {
|
||||
'SECURITY': tokens.Keyword,
|
||||
'SELF': tokens.Keyword,
|
||||
'SENSITIVE': tokens.Keyword,
|
||||
'SEQUENCE': tokens.Keyword,
|
||||
'SERIALIZABLE': tokens.Keyword,
|
||||
'SERVER_NAME': tokens.Keyword,
|
||||
'SESSION': tokens.Keyword,
|
||||
@@ -397,6 +525,7 @@ KEYWORDS = {
|
||||
'SPECIFICTYPE': tokens.Keyword,
|
||||
'SPECIFIC_NAME': tokens.Keyword,
|
||||
'SQL': tokens.Keyword,
|
||||
'SQLBUF': tokens.Keyword,
|
||||
'SQLCODE': tokens.Keyword,
|
||||
'SQLERROR': tokens.Keyword,
|
||||
'SQLEXCEPTION': tokens.Keyword,
|
||||
@@ -404,7 +533,7 @@ KEYWORDS = {
|
||||
'SQLWARNING': tokens.Keyword,
|
||||
'STABLE': tokens.Keyword,
|
||||
'START': tokens.Keyword.DML,
|
||||
'STATE': tokens.Keyword,
|
||||
# 'STATE': tokens.Keyword,
|
||||
'STATEMENT': tokens.Keyword,
|
||||
'STATIC': tokens.Keyword,
|
||||
'STATISTICS': tokens.Keyword,
|
||||
@@ -417,8 +546,10 @@ KEYWORDS = {
|
||||
'SUBCLASS_ORIGIN': tokens.Keyword,
|
||||
'SUBLIST': tokens.Keyword,
|
||||
'SUBSTRING': tokens.Keyword,
|
||||
'SUCCESSFUL': tokens.Keyword,
|
||||
'SUM': tokens.Keyword,
|
||||
'SYMMETRIC': tokens.Keyword,
|
||||
'SYNONYM': tokens.Keyword,
|
||||
'SYSID': tokens.Keyword,
|
||||
'SYSTEM': tokens.Keyword,
|
||||
'SYSTEM_USER': tokens.Keyword,
|
||||
@@ -455,6 +586,7 @@ KEYWORDS = {
|
||||
'TRUSTED': tokens.Keyword,
|
||||
'TYPE': tokens.Keyword,
|
||||
|
||||
'UID': tokens.Keyword,
|
||||
'UNCOMMITTED': tokens.Keyword,
|
||||
'UNDER': tokens.Keyword,
|
||||
'UNENCRYPTED': tokens.Keyword,
|
||||
@@ -476,6 +608,7 @@ KEYWORDS = {
|
||||
|
||||
'VACUUM': tokens.Keyword,
|
||||
'VALID': tokens.Keyword,
|
||||
'VALIDATE': tokens.Keyword,
|
||||
'VALIDATOR': tokens.Keyword,
|
||||
'VALUES': tokens.Keyword,
|
||||
'VARIABLE': tokens.Keyword,
|
||||
@@ -484,8 +617,9 @@ KEYWORDS = {
|
||||
'VIEW': tokens.Keyword,
|
||||
'VOLATILE': tokens.Keyword,
|
||||
|
||||
'WEEK': tokens.Keyword,
|
||||
'WHENEVER': tokens.Keyword,
|
||||
'WITH': tokens.Keyword,
|
||||
'WITH': tokens.Keyword.CTE,
|
||||
'WITHOUT': tokens.Keyword,
|
||||
'WORK': tokens.Keyword,
|
||||
'WRITE': tokens.Keyword,
|
||||
@@ -506,33 +640,50 @@ KEYWORDS = {
|
||||
'DATE': tokens.Name.Builtin,
|
||||
'DEC': tokens.Name.Builtin,
|
||||
'DECIMAL': tokens.Name.Builtin,
|
||||
'FILE_TYPE': tokens.Name.Builtin,
|
||||
'FLOAT': tokens.Name.Builtin,
|
||||
'INT': tokens.Name.Builtin,
|
||||
'INT8': tokens.Name.Builtin,
|
||||
'INTEGER': tokens.Name.Builtin,
|
||||
'INTERVAL': tokens.Name.Builtin,
|
||||
'LONG': tokens.Name.Builtin,
|
||||
'NATURALN': tokens.Name.Builtin,
|
||||
'NVARCHAR': tokens.Name.Builtin,
|
||||
'NUMBER': tokens.Name.Builtin,
|
||||
'NUMERIC': tokens.Name.Builtin,
|
||||
'PLS_INTEGER': tokens.Name.Builtin,
|
||||
'POSITIVE': tokens.Name.Builtin,
|
||||
'POSITIVEN': tokens.Name.Builtin,
|
||||
'REAL': tokens.Name.Builtin,
|
||||
'ROWID': tokens.Name.Builtin,
|
||||
'ROWLABEL': tokens.Name.Builtin,
|
||||
'ROWNUM': tokens.Name.Builtin,
|
||||
'SERIAL': tokens.Name.Builtin,
|
||||
'SERIAL8': tokens.Name.Builtin,
|
||||
'SIGNED': tokens.Name.Builtin,
|
||||
'SIGNTYPE': tokens.Name.Builtin,
|
||||
'SIMPLE_DOUBLE': tokens.Name.Builtin,
|
||||
'SIMPLE_FLOAT': tokens.Name.Builtin,
|
||||
'SIMPLE_INTEGER': tokens.Name.Builtin,
|
||||
'SMALLINT': tokens.Name.Builtin,
|
||||
'SYS_REFCURSOR': tokens.Name.Builtin,
|
||||
'SYSDATE': tokens.Name,
|
||||
'TEXT': tokens.Name.Builtin,
|
||||
'TINYINT': tokens.Name.Builtin,
|
||||
'UNSIGNED': tokens.Name.Builtin,
|
||||
'UROWID': tokens.Name.Builtin,
|
||||
'UTL_FILE': tokens.Name.Builtin,
|
||||
'VARCHAR': tokens.Name.Builtin,
|
||||
'VARCHAR2': tokens.Name.Builtin,
|
||||
'VARYING': tokens.Name.Builtin,
|
||||
}
|
||||
|
||||
|
||||
KEYWORDS_COMMON = {
|
||||
'SELECT': tokens.Keyword.DML,
|
||||
'INSERT': tokens.Keyword.DML,
|
||||
'DELETE': tokens.Keyword.DML,
|
||||
'UPDATE': tokens.Keyword.DML,
|
||||
'UPSERT': tokens.Keyword.DML,
|
||||
'REPLACE': tokens.Keyword.DML,
|
||||
'MERGE': tokens.Keyword.DML,
|
||||
'DROP': tokens.Keyword.DDL,
|
||||
@@ -565,6 +716,7 @@ KEYWORDS_COMMON = {
|
||||
'AS': tokens.Keyword,
|
||||
'ELSE': tokens.Keyword,
|
||||
'FOR': tokens.Keyword,
|
||||
'WHILE': tokens.Keyword,
|
||||
|
||||
'CASE': tokens.Keyword,
|
||||
'WHEN': tokens.Keyword,
|
||||
@@ -572,3 +724,232 @@ KEYWORDS_COMMON = {
|
||||
'MAX': tokens.Keyword,
|
||||
'DISTINCT': tokens.Keyword,
|
||||
}
|
||||
|
||||
KEYWORDS_ORACLE = {
|
||||
'ARCHIVE': tokens.Keyword,
|
||||
'ARCHIVELOG': tokens.Keyword,
|
||||
|
||||
'BACKUP': tokens.Keyword,
|
||||
'BECOME': tokens.Keyword,
|
||||
'BLOCK': tokens.Keyword,
|
||||
'BODY': tokens.Keyword,
|
||||
|
||||
'CANCEL': tokens.Keyword,
|
||||
'CHANGE': tokens.Keyword,
|
||||
'COMPILE': tokens.Keyword,
|
||||
'CONTENTS': tokens.Keyword,
|
||||
'CONTROLFILE': tokens.Keyword,
|
||||
|
||||
'DATAFILE': tokens.Keyword,
|
||||
'DBA': tokens.Keyword,
|
||||
'DISMOUNT': tokens.Keyword,
|
||||
'DOUBLE': tokens.Keyword,
|
||||
'DUMP': tokens.Keyword,
|
||||
|
||||
'EVENTS': tokens.Keyword,
|
||||
'EXCEPTIONS': tokens.Keyword,
|
||||
'EXPLAIN': tokens.Keyword,
|
||||
'EXTENT': tokens.Keyword,
|
||||
'EXTERNALLY': tokens.Keyword,
|
||||
|
||||
'FLUSH': tokens.Keyword,
|
||||
'FREELIST': tokens.Keyword,
|
||||
'FREELISTS': tokens.Keyword,
|
||||
|
||||
# groups seems too common as table name
|
||||
# 'GROUPS': tokens.Keyword,
|
||||
|
||||
'INDICATOR': tokens.Keyword,
|
||||
'INITRANS': tokens.Keyword,
|
||||
'INSTANCE': tokens.Keyword,
|
||||
|
||||
'LAYER': tokens.Keyword,
|
||||
'LINK': tokens.Keyword,
|
||||
'LISTS': tokens.Keyword,
|
||||
'LOGFILE': tokens.Keyword,
|
||||
|
||||
'MANAGE': tokens.Keyword,
|
||||
'MANUAL': tokens.Keyword,
|
||||
'MAXDATAFILES': tokens.Keyword,
|
||||
'MAXINSTANCES': tokens.Keyword,
|
||||
'MAXLOGFILES': tokens.Keyword,
|
||||
'MAXLOGHISTORY': tokens.Keyword,
|
||||
'MAXLOGMEMBERS': tokens.Keyword,
|
||||
'MAXTRANS': tokens.Keyword,
|
||||
'MINEXTENTS': tokens.Keyword,
|
||||
'MODULE': tokens.Keyword,
|
||||
'MOUNT': tokens.Keyword,
|
||||
|
||||
'NOARCHIVELOG': tokens.Keyword,
|
||||
'NOCACHE': tokens.Keyword,
|
||||
'NOCYCLE': tokens.Keyword,
|
||||
'NOMAXVALUE': tokens.Keyword,
|
||||
'NOMINVALUE': tokens.Keyword,
|
||||
'NOORDER': tokens.Keyword,
|
||||
'NORESETLOGS': tokens.Keyword,
|
||||
'NORMAL': tokens.Keyword,
|
||||
'NOSORT': tokens.Keyword,
|
||||
|
||||
'OPTIMAL': tokens.Keyword,
|
||||
'OWN': tokens.Keyword,
|
||||
|
||||
'PACKAGE': tokens.Keyword,
|
||||
'PARALLEL': tokens.Keyword,
|
||||
'PCTINCREASE': tokens.Keyword,
|
||||
'PCTUSED': tokens.Keyword,
|
||||
'PLAN': tokens.Keyword,
|
||||
'PRIVATE': tokens.Keyword,
|
||||
'PROFILE': tokens.Keyword,
|
||||
|
||||
'QUOTA': tokens.Keyword,
|
||||
|
||||
'RECOVER': tokens.Keyword,
|
||||
'RESETLOGS': tokens.Keyword,
|
||||
'RESTRICTED': tokens.Keyword,
|
||||
'REUSE': tokens.Keyword,
|
||||
'ROLES': tokens.Keyword,
|
||||
|
||||
'SAVEPOINT': tokens.Keyword,
|
||||
'SCN': tokens.Keyword,
|
||||
'SECTION': tokens.Keyword,
|
||||
'SEGMENT': tokens.Keyword,
|
||||
'SHARED': tokens.Keyword,
|
||||
'SNAPSHOT': tokens.Keyword,
|
||||
'SORT': tokens.Keyword,
|
||||
'STATEMENT_ID': tokens.Keyword,
|
||||
'STOP': tokens.Keyword,
|
||||
'SWITCH': tokens.Keyword,
|
||||
|
||||
'TABLES': tokens.Keyword,
|
||||
'TABLESPACE': tokens.Keyword,
|
||||
'THREAD': tokens.Keyword,
|
||||
'TIME': tokens.Keyword,
|
||||
'TRACING': tokens.Keyword,
|
||||
'TRANSACTION': tokens.Keyword,
|
||||
'TRIGGERS': tokens.Keyword,
|
||||
|
||||
'UNLIMITED': tokens.Keyword,
|
||||
'UNLOCK': tokens.Keyword,
|
||||
}
|
||||
|
||||
# PostgreSQL Syntax
|
||||
KEYWORDS_PLPGSQL = {
|
||||
'PARTITION': tokens.Keyword,
|
||||
'OVER': tokens.Keyword,
|
||||
'PERFORM': tokens.Keyword,
|
||||
'NOTICE': tokens.Keyword,
|
||||
'PLPGSQL': tokens.Keyword,
|
||||
'INHERIT': tokens.Keyword,
|
||||
'INDEXES': tokens.Keyword,
|
||||
|
||||
'BYTEA': tokens.Keyword,
|
||||
'BIGSERIAL': tokens.Keyword,
|
||||
'BIT VARYING': tokens.Keyword,
|
||||
'BOX': tokens.Keyword,
|
||||
'CHARACTER': tokens.Keyword,
|
||||
'CHARACTER VARYING': tokens.Keyword,
|
||||
'CIDR': tokens.Keyword,
|
||||
'CIRCLE': tokens.Keyword,
|
||||
'DOUBLE PRECISION': tokens.Keyword,
|
||||
'INET': tokens.Keyword,
|
||||
'JSON': tokens.Keyword,
|
||||
'JSONB': tokens.Keyword,
|
||||
'LINE': tokens.Keyword,
|
||||
'LSEG': tokens.Keyword,
|
||||
'MACADDR': tokens.Keyword,
|
||||
'MONEY': tokens.Keyword,
|
||||
'PATH': tokens.Keyword,
|
||||
'PG_LSN': tokens.Keyword,
|
||||
'POINT': tokens.Keyword,
|
||||
'POLYGON': tokens.Keyword,
|
||||
'SMALLSERIAL': tokens.Keyword,
|
||||
'TSQUERY': tokens.Keyword,
|
||||
'TSVECTOR': tokens.Keyword,
|
||||
'TXID_SNAPSHOT': tokens.Keyword,
|
||||
'UUID': tokens.Keyword,
|
||||
'XML': tokens.Keyword,
|
||||
|
||||
'FOR': tokens.Keyword,
|
||||
'IN': tokens.Keyword,
|
||||
'LOOP': tokens.Keyword,
|
||||
}
|
||||
|
||||
# Hive Syntax
|
||||
KEYWORDS_HQL = {
|
||||
'EXPLODE': tokens.Keyword,
|
||||
'DIRECTORY': tokens.Keyword,
|
||||
'DISTRIBUTE': tokens.Keyword,
|
||||
'INCLUDE': tokens.Keyword,
|
||||
'LOCATE': tokens.Keyword,
|
||||
'OVERWRITE': tokens.Keyword,
|
||||
'POSEXPLODE': tokens.Keyword,
|
||||
|
||||
'ARRAY_CONTAINS': tokens.Keyword,
|
||||
'CMP': tokens.Keyword,
|
||||
'COLLECT_LIST': tokens.Keyword,
|
||||
'CONCAT': tokens.Keyword,
|
||||
'CONDITION': tokens.Keyword,
|
||||
'DATE_ADD': tokens.Keyword,
|
||||
'DATE_SUB': tokens.Keyword,
|
||||
'DECODE': tokens.Keyword,
|
||||
'DBMS_OUTPUT': tokens.Keyword,
|
||||
'ELEMENTS': tokens.Keyword,
|
||||
'EXCHANGE': tokens.Keyword,
|
||||
'EXTENDED': tokens.Keyword,
|
||||
'FLOOR': tokens.Keyword,
|
||||
'FOLLOWING': tokens.Keyword,
|
||||
'FROM_UNIXTIME': tokens.Keyword,
|
||||
'FTP': tokens.Keyword,
|
||||
'HOUR': tokens.Keyword,
|
||||
'INLINE': tokens.Keyword,
|
||||
'INSTR': tokens.Keyword,
|
||||
'LEN': tokens.Keyword,
|
||||
'MAXELEMENT': tokens.Keyword,
|
||||
'MAXINDEX': tokens.Keyword,
|
||||
'MAX_PART_DATE': tokens.Keyword,
|
||||
'MAX_PART_INT': tokens.Keyword,
|
||||
'MAX_PART_STRING': tokens.Keyword,
|
||||
'MINELEMENT': tokens.Keyword,
|
||||
'MININDEX': tokens.Keyword,
|
||||
'MIN_PART_DATE': tokens.Keyword,
|
||||
'MIN_PART_INT': tokens.Keyword,
|
||||
'MIN_PART_STRING': tokens.Keyword,
|
||||
'NOW': tokens.Keyword,
|
||||
'NVL': tokens.Keyword,
|
||||
'NVL2': tokens.Keyword,
|
||||
'PARSE_URL_TUPLE': tokens.Keyword,
|
||||
'PART_LOC': tokens.Keyword,
|
||||
'PART_COUNT': tokens.Keyword,
|
||||
'PART_COUNT_BY': tokens.Keyword,
|
||||
'PRINT': tokens.Keyword,
|
||||
'PUT_LINE': tokens.Keyword,
|
||||
'RANGE': tokens.Keyword,
|
||||
'REDUCE': tokens.Keyword,
|
||||
'REGEXP_REPLACE': tokens.Keyword,
|
||||
'RESIGNAL': tokens.Keyword,
|
||||
'RTRIM': tokens.Keyword,
|
||||
'SIGN': tokens.Keyword,
|
||||
'SIGNAL': tokens.Keyword,
|
||||
'SIN': tokens.Keyword,
|
||||
'SPLIT': tokens.Keyword,
|
||||
'SQRT': tokens.Keyword,
|
||||
'STACK': tokens.Keyword,
|
||||
'STR': tokens.Keyword,
|
||||
'SUBSTR': tokens.Keyword,
|
||||
'SUMMARY': tokens.Keyword,
|
||||
'TBLPROPERTIES': tokens.Keyword,
|
||||
'TIMESTAMP_ISO': tokens.Keyword,
|
||||
'TO_CHAR': tokens.Keyword,
|
||||
'TO_DATE': tokens.Keyword,
|
||||
'TO_TIMESTAMP': tokens.Keyword,
|
||||
'TRUNC': tokens.Keyword,
|
||||
'UNBOUNDED': tokens.Keyword,
|
||||
'UNIQUEJOIN': tokens.Keyword,
|
||||
'UNIX_TIMESTAMP': tokens.Keyword,
|
||||
'UTC_TIMESTAMP': tokens.Keyword,
|
||||
'VIEWS': tokens.Keyword,
|
||||
|
||||
'EXIT': tokens.Keyword,
|
||||
'BREAK': tokens.Keyword,
|
||||
'LEAVE': tokens.Keyword,
|
||||
}
|
||||
82
shell/ext-py/sqlparse-0.3.1/sqlparse/lexer.py
Normal file
82
shell/ext-py/sqlparse-0.3.1/sqlparse/lexer.py
Normal file
@@ -0,0 +1,82 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""SQL Lexer"""
|
||||
|
||||
# This code is based on the SqlLexer in pygments.
|
||||
# http://pygments.org/
|
||||
# It's separated from the rest of pygments to increase performance
|
||||
# and to allow some customizations.
|
||||
|
||||
from sqlparse import tokens
|
||||
from sqlparse.keywords import SQL_REGEX
|
||||
from sqlparse.compat import text_type, file_types
|
||||
from sqlparse.utils import consume
|
||||
|
||||
|
||||
class Lexer(object):
|
||||
"""Lexer
|
||||
Empty class. Leaving for backwards-compatibility
|
||||
"""
|
||||
|
||||
@staticmethod
|
||||
def get_tokens(text, encoding=None):
|
||||
"""
|
||||
Return an iterable of (tokentype, value) pairs generated from
|
||||
`text`. If `unfiltered` is set to `True`, the filtering mechanism
|
||||
is bypassed even if filters are defined.
|
||||
|
||||
Also preprocess the text, i.e. expand tabs and strip it if
|
||||
wanted and applies registered filters.
|
||||
|
||||
Split ``text`` into (tokentype, text) pairs.
|
||||
|
||||
``stack`` is the initial stack (default: ``['root']``)
|
||||
"""
|
||||
if isinstance(text, file_types):
|
||||
text = text.read()
|
||||
|
||||
if isinstance(text, text_type):
|
||||
pass
|
||||
elif isinstance(text, bytes):
|
||||
if encoding:
|
||||
text = text.decode(encoding)
|
||||
else:
|
||||
try:
|
||||
text = text.decode('utf-8')
|
||||
except UnicodeDecodeError:
|
||||
text = text.decode('unicode-escape')
|
||||
else:
|
||||
raise TypeError(u"Expected text or file-like object, got {!r}".
|
||||
format(type(text)))
|
||||
|
||||
iterable = enumerate(text)
|
||||
for pos, char in iterable:
|
||||
for rexmatch, action in SQL_REGEX:
|
||||
m = rexmatch(text, pos)
|
||||
|
||||
if not m:
|
||||
continue
|
||||
elif isinstance(action, tokens._TokenType):
|
||||
yield action, m.group()
|
||||
elif callable(action):
|
||||
yield action(m.group())
|
||||
|
||||
consume(iterable, m.end() - pos - 1)
|
||||
break
|
||||
else:
|
||||
yield tokens.Error, char
|
||||
|
||||
|
||||
def tokenize(sql, encoding=None):
|
||||
"""Tokenize sql.
|
||||
|
||||
Tokenize *sql* using the :class:`Lexer` and return a 2-tuple stream
|
||||
of ``(token type, value)`` items.
|
||||
"""
|
||||
return Lexer().get_tokens(sql, encoding)
|
||||
650
shell/ext-py/sqlparse-0.3.1/sqlparse/sql.py
Normal file
650
shell/ext-py/sqlparse-0.3.1/sqlparse/sql.py
Normal file
@@ -0,0 +1,650 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
"""This module contains classes representing syntactical elements of SQL."""
|
||||
from __future__ import print_function
|
||||
|
||||
import re
|
||||
|
||||
from sqlparse import tokens as T
|
||||
from sqlparse.compat import string_types, text_type, unicode_compatible
|
||||
from sqlparse.utils import imt, remove_quotes
|
||||
|
||||
|
||||
class NameAliasMixin:
|
||||
"""Implements get_real_name and get_alias."""
|
||||
|
||||
def get_real_name(self):
|
||||
"""Returns the real name (object name) of this identifier."""
|
||||
# a.b
|
||||
dot_idx, _ = self.token_next_by(m=(T.Punctuation, '.'))
|
||||
return self._get_first_name(dot_idx, real_name=True)
|
||||
|
||||
def get_alias(self):
|
||||
"""Returns the alias for this identifier or ``None``."""
|
||||
|
||||
# "name AS alias"
|
||||
kw_idx, kw = self.token_next_by(m=(T.Keyword, 'AS'))
|
||||
if kw is not None:
|
||||
return self._get_first_name(kw_idx + 1, keywords=True)
|
||||
|
||||
# "name alias" or "complicated column expression alias"
|
||||
_, ws = self.token_next_by(t=T.Whitespace)
|
||||
if len(self.tokens) > 2 and ws is not None:
|
||||
return self._get_first_name(reverse=True)
|
||||
|
||||
|
||||
@unicode_compatible
|
||||
class Token(object):
|
||||
"""Base class for all other classes in this module.
|
||||
|
||||
It represents a single token and has two instance attributes:
|
||||
``value`` is the unchanged value of the token and ``ttype`` is
|
||||
the type of the token.
|
||||
"""
|
||||
|
||||
__slots__ = ('value', 'ttype', 'parent', 'normalized', 'is_keyword',
|
||||
'is_group', 'is_whitespace')
|
||||
|
||||
def __init__(self, ttype, value):
|
||||
value = text_type(value)
|
||||
self.value = value
|
||||
self.ttype = ttype
|
||||
self.parent = None
|
||||
self.is_group = False
|
||||
self.is_keyword = ttype in T.Keyword
|
||||
self.is_whitespace = self.ttype in T.Whitespace
|
||||
self.normalized = value.upper() if self.is_keyword else value
|
||||
|
||||
def __str__(self):
|
||||
return self.value
|
||||
|
||||
# Pending tokenlist __len__ bug fix
|
||||
# def __len__(self):
|
||||
# return len(self.value)
|
||||
|
||||
def __repr__(self):
|
||||
cls = self._get_repr_name()
|
||||
value = self._get_repr_value()
|
||||
|
||||
q = u'"' if value.startswith("'") and value.endswith("'") else u"'"
|
||||
return u"<{cls} {q}{value}{q} at 0x{id:2X}>".format(
|
||||
id=id(self), **locals())
|
||||
|
||||
def _get_repr_name(self):
|
||||
return str(self.ttype).split('.')[-1]
|
||||
|
||||
def _get_repr_value(self):
|
||||
raw = text_type(self)
|
||||
if len(raw) > 7:
|
||||
raw = raw[:6] + '...'
|
||||
return re.sub(r'\s+', ' ', raw)
|
||||
|
||||
def flatten(self):
|
||||
"""Resolve subgroups."""
|
||||
yield self
|
||||
|
||||
def match(self, ttype, values, regex=False):
|
||||
"""Checks whether the token matches the given arguments.
|
||||
|
||||
*ttype* is a token type. If this token doesn't match the given token
|
||||
type.
|
||||
*values* is a list of possible values for this token. The values
|
||||
are OR'ed together so if only one of the values matches ``True``
|
||||
is returned. Except for keyword tokens the comparison is
|
||||
case-sensitive. For convenience it's OK to pass in a single string.
|
||||
If *regex* is ``True`` (default is ``False``) the given values are
|
||||
treated as regular expressions.
|
||||
"""
|
||||
type_matched = self.ttype is ttype
|
||||
if not type_matched or values is None:
|
||||
return type_matched
|
||||
|
||||
if isinstance(values, string_types):
|
||||
values = (values,)
|
||||
|
||||
if regex:
|
||||
# TODO: Add test for regex with is_keyboard = false
|
||||
flag = re.IGNORECASE if self.is_keyword else 0
|
||||
values = (re.compile(v, flag) for v in values)
|
||||
|
||||
for pattern in values:
|
||||
if pattern.search(self.normalized):
|
||||
return True
|
||||
return False
|
||||
|
||||
if self.is_keyword:
|
||||
values = (v.upper() for v in values)
|
||||
|
||||
return self.normalized in values
|
||||
|
||||
def within(self, group_cls):
|
||||
"""Returns ``True`` if this token is within *group_cls*.
|
||||
|
||||
Use this method for example to check if an identifier is within
|
||||
a function: ``t.within(sql.Function)``.
|
||||
"""
|
||||
parent = self.parent
|
||||
while parent:
|
||||
if isinstance(parent, group_cls):
|
||||
return True
|
||||
parent = parent.parent
|
||||
return False
|
||||
|
||||
def is_child_of(self, other):
|
||||
"""Returns ``True`` if this token is a direct child of *other*."""
|
||||
return self.parent == other
|
||||
|
||||
def has_ancestor(self, other):
|
||||
"""Returns ``True`` if *other* is in this tokens ancestry."""
|
||||
parent = self.parent
|
||||
while parent:
|
||||
if parent == other:
|
||||
return True
|
||||
parent = parent.parent
|
||||
return False
|
||||
|
||||
|
||||
@unicode_compatible
|
||||
class TokenList(Token):
|
||||
"""A group of tokens.
|
||||
|
||||
It has an additional instance attribute ``tokens`` which holds a
|
||||
list of child-tokens.
|
||||
"""
|
||||
|
||||
__slots__ = 'tokens'
|
||||
|
||||
def __init__(self, tokens=None):
|
||||
self.tokens = tokens or []
|
||||
[setattr(token, 'parent', self) for token in self.tokens]
|
||||
super(TokenList, self).__init__(None, text_type(self))
|
||||
self.is_group = True
|
||||
|
||||
def __str__(self):
|
||||
return u''.join(token.value for token in self.flatten())
|
||||
|
||||
# weird bug
|
||||
# def __len__(self):
|
||||
# return len(self.tokens)
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self.tokens)
|
||||
|
||||
def __getitem__(self, item):
|
||||
return self.tokens[item]
|
||||
|
||||
def _get_repr_name(self):
|
||||
return type(self).__name__
|
||||
|
||||
def _pprint_tree(self, max_depth=None, depth=0, f=None, _pre=''):
|
||||
"""Pretty-print the object tree."""
|
||||
token_count = len(self.tokens)
|
||||
for idx, token in enumerate(self.tokens):
|
||||
cls = token._get_repr_name()
|
||||
value = token._get_repr_value()
|
||||
|
||||
last = idx == (token_count - 1)
|
||||
pre = u'`- ' if last else u'|- '
|
||||
|
||||
q = u'"' if value.startswith("'") and value.endswith("'") else u"'"
|
||||
print(u"{_pre}{pre}{idx} {cls} {q}{value}{q}"
|
||||
.format(**locals()), file=f)
|
||||
|
||||
if token.is_group and (max_depth is None or depth < max_depth):
|
||||
parent_pre = u' ' if last else u'| '
|
||||
token._pprint_tree(max_depth, depth + 1, f, _pre + parent_pre)
|
||||
|
||||
def get_token_at_offset(self, offset):
|
||||
"""Returns the token that is on position offset."""
|
||||
idx = 0
|
||||
for token in self.flatten():
|
||||
end = idx + len(token.value)
|
||||
if idx <= offset < end:
|
||||
return token
|
||||
idx = end
|
||||
|
||||
def flatten(self):
|
||||
"""Generator yielding ungrouped tokens.
|
||||
|
||||
This method is recursively called for all child tokens.
|
||||
"""
|
||||
for token in self.tokens:
|
||||
if token.is_group:
|
||||
for item in token.flatten():
|
||||
yield item
|
||||
else:
|
||||
yield token
|
||||
|
||||
def get_sublists(self):
|
||||
for token in self.tokens:
|
||||
if token.is_group:
|
||||
yield token
|
||||
|
||||
@property
|
||||
def _groupable_tokens(self):
|
||||
return self.tokens
|
||||
|
||||
def _token_matching(self, funcs, start=0, end=None, reverse=False):
|
||||
"""next token that match functions"""
|
||||
if start is None:
|
||||
return None
|
||||
|
||||
if not isinstance(funcs, (list, tuple)):
|
||||
funcs = (funcs,)
|
||||
|
||||
if reverse:
|
||||
assert end is None
|
||||
for idx in range(start - 2, -1, -1):
|
||||
token = self.tokens[idx]
|
||||
for func in funcs:
|
||||
if func(token):
|
||||
return idx, token
|
||||
else:
|
||||
for idx, token in enumerate(self.tokens[start:end], start=start):
|
||||
for func in funcs:
|
||||
if func(token):
|
||||
return idx, token
|
||||
return None, None
|
||||
|
||||
def token_first(self, skip_ws=True, skip_cm=False):
|
||||
"""Returns the first child token.
|
||||
|
||||
If *skip_ws* is ``True`` (the default), whitespace
|
||||
tokens are ignored.
|
||||
|
||||
if *skip_cm* is ``True`` (default: ``False``), comments are
|
||||
ignored too.
|
||||
"""
|
||||
# this on is inconsistent, using Comment instead of T.Comment...
|
||||
def matcher(tk):
|
||||
return not ((skip_ws and tk.is_whitespace)
|
||||
or (skip_cm and imt(tk, t=T.Comment, i=Comment)))
|
||||
return self._token_matching(matcher)[1]
|
||||
|
||||
def token_next_by(self, i=None, m=None, t=None, idx=-1, end=None):
|
||||
idx += 1
|
||||
return self._token_matching(lambda tk: imt(tk, i, m, t), idx, end)
|
||||
|
||||
def token_not_matching(self, funcs, idx):
|
||||
funcs = (funcs,) if not isinstance(funcs, (list, tuple)) else funcs
|
||||
funcs = [lambda tk: not func(tk) for func in funcs]
|
||||
return self._token_matching(funcs, idx)
|
||||
|
||||
def token_matching(self, funcs, idx):
|
||||
return self._token_matching(funcs, idx)[1]
|
||||
|
||||
def token_prev(self, idx, skip_ws=True, skip_cm=False):
|
||||
"""Returns the previous token relative to *idx*.
|
||||
|
||||
If *skip_ws* is ``True`` (the default) whitespace tokens are ignored.
|
||||
If *skip_cm* is ``True`` comments are ignored.
|
||||
``None`` is returned if there's no previous token.
|
||||
"""
|
||||
return self.token_next(idx, skip_ws, skip_cm, _reverse=True)
|
||||
|
||||
# TODO: May need to re-add default value to idx
|
||||
def token_next(self, idx, skip_ws=True, skip_cm=False, _reverse=False):
|
||||
"""Returns the next token relative to *idx*.
|
||||
|
||||
If *skip_ws* is ``True`` (the default) whitespace tokens are ignored.
|
||||
If *skip_cm* is ``True`` comments are ignored.
|
||||
``None`` is returned if there's no next token.
|
||||
"""
|
||||
if idx is None:
|
||||
return None, None
|
||||
idx += 1 # alot of code usage current pre-compensates for this
|
||||
|
||||
def matcher(tk):
|
||||
return not ((skip_ws and tk.is_whitespace)
|
||||
or (skip_cm and imt(tk, t=T.Comment, i=Comment)))
|
||||
return self._token_matching(matcher, idx, reverse=_reverse)
|
||||
|
||||
def token_index(self, token, start=0):
|
||||
"""Return list index of token."""
|
||||
start = start if isinstance(start, int) else self.token_index(start)
|
||||
return start + self.tokens[start:].index(token)
|
||||
|
||||
def group_tokens(self, grp_cls, start, end, include_end=True,
|
||||
extend=False):
|
||||
"""Replace tokens by an instance of *grp_cls*."""
|
||||
start_idx = start
|
||||
start = self.tokens[start_idx]
|
||||
|
||||
end_idx = end + include_end
|
||||
|
||||
# will be needed later for new group_clauses
|
||||
# while skip_ws and tokens and tokens[-1].is_whitespace:
|
||||
# tokens = tokens[:-1]
|
||||
|
||||
if extend and isinstance(start, grp_cls):
|
||||
subtokens = self.tokens[start_idx + 1:end_idx]
|
||||
|
||||
grp = start
|
||||
grp.tokens.extend(subtokens)
|
||||
del self.tokens[start_idx + 1:end_idx]
|
||||
grp.value = text_type(start)
|
||||
else:
|
||||
subtokens = self.tokens[start_idx:end_idx]
|
||||
grp = grp_cls(subtokens)
|
||||
self.tokens[start_idx:end_idx] = [grp]
|
||||
grp.parent = self
|
||||
|
||||
for token in subtokens:
|
||||
token.parent = grp
|
||||
|
||||
return grp
|
||||
|
||||
def insert_before(self, where, token):
|
||||
"""Inserts *token* before *where*."""
|
||||
if not isinstance(where, int):
|
||||
where = self.token_index(where)
|
||||
token.parent = self
|
||||
self.tokens.insert(where, token)
|
||||
|
||||
def insert_after(self, where, token, skip_ws=True):
|
||||
"""Inserts *token* after *where*."""
|
||||
if not isinstance(where, int):
|
||||
where = self.token_index(where)
|
||||
nidx, next_ = self.token_next(where, skip_ws=skip_ws)
|
||||
token.parent = self
|
||||
if next_ is None:
|
||||
self.tokens.append(token)
|
||||
else:
|
||||
self.tokens.insert(nidx, token)
|
||||
|
||||
def has_alias(self):
|
||||
"""Returns ``True`` if an alias is present."""
|
||||
return self.get_alias() is not None
|
||||
|
||||
def get_alias(self):
|
||||
"""Returns the alias for this identifier or ``None``."""
|
||||
return None
|
||||
|
||||
def get_name(self):
|
||||
"""Returns the name of this identifier.
|
||||
|
||||
This is either it's alias or it's real name. The returned valued can
|
||||
be considered as the name under which the object corresponding to
|
||||
this identifier is known within the current statement.
|
||||
"""
|
||||
return self.get_alias() or self.get_real_name()
|
||||
|
||||
def get_real_name(self):
|
||||
"""Returns the real name (object name) of this identifier."""
|
||||
return None
|
||||
|
||||
def get_parent_name(self):
|
||||
"""Return name of the parent object if any.
|
||||
|
||||
A parent object is identified by the first occurring dot.
|
||||
"""
|
||||
dot_idx, _ = self.token_next_by(m=(T.Punctuation, '.'))
|
||||
_, prev_ = self.token_prev(dot_idx)
|
||||
return remove_quotes(prev_.value) if prev_ is not None else None
|
||||
|
||||
def _get_first_name(self, idx=None, reverse=False, keywords=False,
|
||||
real_name=False):
|
||||
"""Returns the name of the first token with a name"""
|
||||
|
||||
tokens = self.tokens[idx:] if idx else self.tokens
|
||||
tokens = reversed(tokens) if reverse else tokens
|
||||
types = [T.Name, T.Wildcard, T.String.Symbol]
|
||||
|
||||
if keywords:
|
||||
types.append(T.Keyword)
|
||||
|
||||
for token in tokens:
|
||||
if token.ttype in types:
|
||||
return remove_quotes(token.value)
|
||||
elif isinstance(token, (Identifier, Function)):
|
||||
return token.get_real_name() if real_name else token.get_name()
|
||||
|
||||
|
||||
class Statement(TokenList):
|
||||
"""Represents a SQL statement."""
|
||||
|
||||
def get_type(self):
|
||||
"""Returns the type of a statement.
|
||||
|
||||
The returned value is a string holding an upper-cased reprint of
|
||||
the first DML or DDL keyword. If the first token in this group
|
||||
isn't a DML or DDL keyword "UNKNOWN" is returned.
|
||||
|
||||
Whitespaces and comments at the beginning of the statement
|
||||
are ignored.
|
||||
"""
|
||||
first_token = self.token_first(skip_cm=True)
|
||||
if first_token is None:
|
||||
# An "empty" statement that either has not tokens at all
|
||||
# or only whitespace tokens.
|
||||
return 'UNKNOWN'
|
||||
|
||||
elif first_token.ttype in (T.Keyword.DML, T.Keyword.DDL):
|
||||
return first_token.normalized
|
||||
|
||||
elif first_token.ttype == T.Keyword.CTE:
|
||||
# The WITH keyword should be followed by either an Identifier or
|
||||
# an IdentifierList containing the CTE definitions; the actual
|
||||
# DML keyword (e.g. SELECT, INSERT) will follow next.
|
||||
fidx = self.token_index(first_token)
|
||||
tidx, token = self.token_next(fidx, skip_ws=True)
|
||||
if isinstance(token, (Identifier, IdentifierList)):
|
||||
_, dml_keyword = self.token_next(tidx, skip_ws=True)
|
||||
|
||||
if dml_keyword is not None \
|
||||
and dml_keyword.ttype == T.Keyword.DML:
|
||||
return dml_keyword.normalized
|
||||
|
||||
# Hmm, probably invalid syntax, so return unknown.
|
||||
return 'UNKNOWN'
|
||||
|
||||
|
||||
class Identifier(NameAliasMixin, TokenList):
|
||||
"""Represents an identifier.
|
||||
|
||||
Identifiers may have aliases or typecasts.
|
||||
"""
|
||||
|
||||
def is_wildcard(self):
|
||||
"""Return ``True`` if this identifier contains a wildcard."""
|
||||
_, token = self.token_next_by(t=T.Wildcard)
|
||||
return token is not None
|
||||
|
||||
def get_typecast(self):
|
||||
"""Returns the typecast or ``None`` of this object as a string."""
|
||||
midx, marker = self.token_next_by(m=(T.Punctuation, '::'))
|
||||
nidx, next_ = self.token_next(midx, skip_ws=False)
|
||||
return next_.value if next_ else None
|
||||
|
||||
def get_ordering(self):
|
||||
"""Returns the ordering or ``None`` as uppercase string."""
|
||||
_, ordering = self.token_next_by(t=T.Keyword.Order)
|
||||
return ordering.normalized if ordering else None
|
||||
|
||||
def get_array_indices(self):
|
||||
"""Returns an iterator of index token lists"""
|
||||
|
||||
for token in self.tokens:
|
||||
if isinstance(token, SquareBrackets):
|
||||
# Use [1:-1] index to discard the square brackets
|
||||
yield token.tokens[1:-1]
|
||||
|
||||
|
||||
class IdentifierList(TokenList):
|
||||
"""A list of :class:`~sqlparse.sql.Identifier`\'s."""
|
||||
|
||||
def get_identifiers(self):
|
||||
"""Returns the identifiers.
|
||||
|
||||
Whitespaces and punctuations are not included in this generator.
|
||||
"""
|
||||
for token in self.tokens:
|
||||
if not (token.is_whitespace or token.match(T.Punctuation, ',')):
|
||||
yield token
|
||||
|
||||
|
||||
class TypedLiteral(TokenList):
|
||||
"""A typed literal, such as "date '2001-09-28'" or "interval '2 hours'"."""
|
||||
M_OPEN = [(T.Name.Builtin, None), (T.Keyword, "TIMESTAMP")]
|
||||
M_CLOSE = T.String.Single, None
|
||||
M_EXTEND = T.Keyword, ("DAY", "HOUR", "MINUTE", "MONTH", "SECOND", "YEAR")
|
||||
|
||||
|
||||
class Parenthesis(TokenList):
|
||||
"""Tokens between parenthesis."""
|
||||
M_OPEN = T.Punctuation, '('
|
||||
M_CLOSE = T.Punctuation, ')'
|
||||
|
||||
@property
|
||||
def _groupable_tokens(self):
|
||||
return self.tokens[1:-1]
|
||||
|
||||
|
||||
class SquareBrackets(TokenList):
|
||||
"""Tokens between square brackets"""
|
||||
M_OPEN = T.Punctuation, '['
|
||||
M_CLOSE = T.Punctuation, ']'
|
||||
|
||||
@property
|
||||
def _groupable_tokens(self):
|
||||
return self.tokens[1:-1]
|
||||
|
||||
|
||||
class Assignment(TokenList):
|
||||
"""An assignment like 'var := val;'"""
|
||||
|
||||
|
||||
class If(TokenList):
|
||||
"""An 'if' clause with possible 'else if' or 'else' parts."""
|
||||
M_OPEN = T.Keyword, 'IF'
|
||||
M_CLOSE = T.Keyword, 'END IF'
|
||||
|
||||
|
||||
class For(TokenList):
|
||||
"""A 'FOR' loop."""
|
||||
M_OPEN = T.Keyword, ('FOR', 'FOREACH')
|
||||
M_CLOSE = T.Keyword, 'END LOOP'
|
||||
|
||||
|
||||
class Comparison(TokenList):
|
||||
"""A comparison used for example in WHERE clauses."""
|
||||
|
||||
@property
|
||||
def left(self):
|
||||
return self.tokens[0]
|
||||
|
||||
@property
|
||||
def right(self):
|
||||
return self.tokens[-1]
|
||||
|
||||
|
||||
class Comment(TokenList):
|
||||
"""A comment."""
|
||||
|
||||
def is_multiline(self):
|
||||
return self.tokens and self.tokens[0].ttype == T.Comment.Multiline
|
||||
|
||||
|
||||
class Where(TokenList):
|
||||
"""A WHERE clause."""
|
||||
M_OPEN = T.Keyword, 'WHERE'
|
||||
M_CLOSE = T.Keyword, (
|
||||
'ORDER BY', 'GROUP BY', 'LIMIT', 'UNION', 'UNION ALL', 'EXCEPT',
|
||||
'HAVING', 'RETURNING', 'INTO')
|
||||
|
||||
|
||||
class Having(TokenList):
|
||||
"""A HAVING clause."""
|
||||
M_OPEN = T.Keyword, 'HAVING'
|
||||
M_CLOSE = T.Keyword, ('ORDER BY', 'LIMIT')
|
||||
|
||||
|
||||
class Case(TokenList):
|
||||
"""A CASE statement with one or more WHEN and possibly an ELSE part."""
|
||||
M_OPEN = T.Keyword, 'CASE'
|
||||
M_CLOSE = T.Keyword, 'END'
|
||||
|
||||
def get_cases(self, skip_ws=False):
|
||||
"""Returns a list of 2-tuples (condition, value).
|
||||
|
||||
If an ELSE exists condition is None.
|
||||
"""
|
||||
CONDITION = 1
|
||||
VALUE = 2
|
||||
|
||||
ret = []
|
||||
mode = CONDITION
|
||||
|
||||
for token in self.tokens:
|
||||
# Set mode from the current statement
|
||||
if token.match(T.Keyword, 'CASE'):
|
||||
continue
|
||||
|
||||
elif skip_ws and token.ttype in T.Whitespace:
|
||||
continue
|
||||
|
||||
elif token.match(T.Keyword, 'WHEN'):
|
||||
ret.append(([], []))
|
||||
mode = CONDITION
|
||||
|
||||
elif token.match(T.Keyword, 'THEN'):
|
||||
mode = VALUE
|
||||
|
||||
elif token.match(T.Keyword, 'ELSE'):
|
||||
ret.append((None, []))
|
||||
mode = VALUE
|
||||
|
||||
elif token.match(T.Keyword, 'END'):
|
||||
mode = None
|
||||
|
||||
# First condition without preceding WHEN
|
||||
if mode and not ret:
|
||||
ret.append(([], []))
|
||||
|
||||
# Append token depending of the current mode
|
||||
if mode == CONDITION:
|
||||
ret[-1][0].append(token)
|
||||
|
||||
elif mode == VALUE:
|
||||
ret[-1][1].append(token)
|
||||
|
||||
# Return cases list
|
||||
return ret
|
||||
|
||||
|
||||
class Function(NameAliasMixin, TokenList):
|
||||
"""A function or procedure call."""
|
||||
|
||||
def get_parameters(self):
|
||||
"""Return a list of parameters."""
|
||||
parenthesis = self.tokens[-1]
|
||||
for token in parenthesis.tokens:
|
||||
if isinstance(token, IdentifierList):
|
||||
return token.get_identifiers()
|
||||
elif imt(token, i=(Function, Identifier), t=T.Literal):
|
||||
return [token, ]
|
||||
return []
|
||||
|
||||
|
||||
class Begin(TokenList):
|
||||
"""A BEGIN/END block."""
|
||||
M_OPEN = T.Keyword, 'BEGIN'
|
||||
M_CLOSE = T.Keyword, 'END'
|
||||
|
||||
|
||||
class Operation(TokenList):
|
||||
"""Grouping of operations"""
|
||||
|
||||
|
||||
class Values(TokenList):
|
||||
"""Grouping of values"""
|
||||
|
||||
|
||||
class Command(TokenList):
|
||||
"""Grouping of CLI commands."""
|
||||
@@ -1,8 +1,11 @@
|
||||
# Copyright (C) 2008 Andi Albrecht, albrecht.andi@gmail.com
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: http://www.opensource.org/licenses/bsd-license.php.
|
||||
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
#
|
||||
# The Token implementation is based on pygment's token system written
|
||||
# by Georg Brandl.
|
||||
# http://pygments.org/
|
||||
@@ -13,31 +16,18 @@
|
||||
class _TokenType(tuple):
|
||||
parent = None
|
||||
|
||||
def split(self):
|
||||
buf = []
|
||||
node = self
|
||||
while node is not None:
|
||||
buf.append(node)
|
||||
node = node.parent
|
||||
buf.reverse()
|
||||
return buf
|
||||
def __contains__(self, item):
|
||||
return item is not None and (self is item or item[:len(self)] == self)
|
||||
|
||||
def __contains__(self, val):
|
||||
return val is not None and (self is val or val[:len(self)] == self)
|
||||
|
||||
def __getattr__(self, val):
|
||||
if not val or not val[0].isupper():
|
||||
return tuple.__getattribute__(self, val)
|
||||
new = _TokenType(self + (val,))
|
||||
setattr(self, val, new)
|
||||
def __getattr__(self, name):
|
||||
new = _TokenType(self + (name,))
|
||||
setattr(self, name, new)
|
||||
new.parent = self
|
||||
return new
|
||||
|
||||
def __hash__(self):
|
||||
return hash(tuple(self))
|
||||
|
||||
def __repr__(self):
|
||||
return 'Token' + (self and '.' or '') + '.'.join(self)
|
||||
# self can be False only if its the `root` i.e. Token itself
|
||||
return 'Token' + ('.' if self else '') + '.'.join(self)
|
||||
|
||||
|
||||
Token = _TokenType()
|
||||
@@ -61,12 +51,13 @@ Operator = Token.Operator
|
||||
Comparison = Operator.Comparison
|
||||
Wildcard = Token.Wildcard
|
||||
Comment = Token.Comment
|
||||
Assignment = Token.Assignement
|
||||
Assignment = Token.Assignment
|
||||
|
||||
# Generic types for non-source code
|
||||
Generic = Token.Generic
|
||||
Command = Generic.Command
|
||||
|
||||
# String and some others are not direct childs of Token.
|
||||
# String and some others are not direct children of Token.
|
||||
# alias them:
|
||||
Token.Token = Token
|
||||
Token.String = String
|
||||
@@ -75,9 +66,4 @@ Token.Number = Number
|
||||
# SQL specific tokens
|
||||
DML = Keyword.DML
|
||||
DDL = Keyword.DDL
|
||||
Command = Keyword.Command
|
||||
|
||||
Group = Token.Group
|
||||
Group.Parenthesis = Token.Group.Parenthesis
|
||||
Group.Comment = Token.Group.Comment
|
||||
Group.Where = Token.Group.Where
|
||||
CTE = Keyword.CTE
|
||||
123
shell/ext-py/sqlparse-0.3.1/sqlparse/utils.py
Normal file
123
shell/ext-py/sqlparse-0.3.1/sqlparse/utils.py
Normal file
@@ -0,0 +1,123 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2009-2018 the sqlparse authors and contributors
|
||||
# <see AUTHORS file>
|
||||
#
|
||||
# This module is part of python-sqlparse and is released under
|
||||
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
|
||||
|
||||
import itertools
|
||||
import re
|
||||
from collections import deque
|
||||
from contextlib import contextmanager
|
||||
from sqlparse.compat import text_type
|
||||
|
||||
# This regular expression replaces the home-cooked parser that was here before.
|
||||
# It is much faster, but requires an extra post-processing step to get the
|
||||
# desired results (that are compatible with what you would expect from the
|
||||
# str.splitlines() method).
|
||||
#
|
||||
# It matches groups of characters: newlines, quoted strings, or unquoted text,
|
||||
# and splits on that basis. The post-processing step puts those back together
|
||||
# into the actual lines of SQL.
|
||||
SPLIT_REGEX = re.compile(r"""
|
||||
(
|
||||
(?: # Start of non-capturing group
|
||||
(?:\r\n|\r|\n) | # Match any single newline, or
|
||||
[^\r\n'"]+ | # Match any character series without quotes or
|
||||
# newlines, or
|
||||
"(?:[^"\\]|\\.)*" | # Match double-quoted strings, or
|
||||
'(?:[^'\\]|\\.)*' # Match single quoted strings
|
||||
)
|
||||
)
|
||||
""", re.VERBOSE)
|
||||
|
||||
LINE_MATCH = re.compile(r'(\r\n|\r|\n)')
|
||||
|
||||
|
||||
def split_unquoted_newlines(stmt):
|
||||
"""Split a string on all unquoted newlines.
|
||||
|
||||
Unlike str.splitlines(), this will ignore CR/LF/CR+LF if the requisite
|
||||
character is inside of a string."""
|
||||
text = text_type(stmt)
|
||||
lines = SPLIT_REGEX.split(text)
|
||||
outputlines = ['']
|
||||
for line in lines:
|
||||
if not line:
|
||||
continue
|
||||
elif LINE_MATCH.match(line):
|
||||
outputlines.append('')
|
||||
else:
|
||||
outputlines[-1] += line
|
||||
return outputlines
|
||||
|
||||
|
||||
def remove_quotes(val):
|
||||
"""Helper that removes surrounding quotes from strings."""
|
||||
if val is None:
|
||||
return
|
||||
if val[0] in ('"', "'") and val[0] == val[-1]:
|
||||
val = val[1:-1]
|
||||
return val
|
||||
|
||||
|
||||
def recurse(*cls):
|
||||
"""Function decorator to help with recursion
|
||||
|
||||
:param cls: Classes to not recurse over
|
||||
:return: function
|
||||
"""
|
||||
def wrap(f):
|
||||
def wrapped_f(tlist):
|
||||
for sgroup in tlist.get_sublists():
|
||||
if not isinstance(sgroup, cls):
|
||||
wrapped_f(sgroup)
|
||||
f(tlist)
|
||||
|
||||
return wrapped_f
|
||||
|
||||
return wrap
|
||||
|
||||
|
||||
def imt(token, i=None, m=None, t=None):
|
||||
"""Helper function to simplify comparisons Instance, Match and TokenType
|
||||
:param token:
|
||||
:param i: Class or Tuple/List of Classes
|
||||
:param m: Tuple of TokenType & Value. Can be list of Tuple for multiple
|
||||
:param t: TokenType or Tuple/List of TokenTypes
|
||||
:return: bool
|
||||
"""
|
||||
clss = i
|
||||
types = [t, ] if t and not isinstance(t, list) else t
|
||||
mpatterns = [m, ] if m and not isinstance(m, list) else m
|
||||
|
||||
if token is None:
|
||||
return False
|
||||
elif clss and isinstance(token, clss):
|
||||
return True
|
||||
elif mpatterns and any(token.match(*pattern) for pattern in mpatterns):
|
||||
return True
|
||||
elif types and any(token.ttype in ttype for ttype in types):
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
|
||||
def consume(iterator, n):
|
||||
"""Advance the iterator n-steps ahead. If n is none, consume entirely."""
|
||||
deque(itertools.islice(iterator, n), maxlen=0)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def offset(filter_, n=0):
|
||||
filter_.offset += n
|
||||
yield
|
||||
filter_.offset -= n
|
||||
|
||||
|
||||
@contextmanager
|
||||
def indent(filter_, n=1):
|
||||
filter_.indent += n
|
||||
yield
|
||||
filter_.indent -= n
|
||||
49
shell/ext-py/sqlparse-0.3.1/tests/conftest.py
Normal file
49
shell/ext-py/sqlparse-0.3.1/tests/conftest.py
Normal file
@@ -0,0 +1,49 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""Helpers for testing."""
|
||||
|
||||
import io
|
||||
import os
|
||||
|
||||
import pytest
|
||||
|
||||
DIR_PATH = os.path.dirname(__file__)
|
||||
FILES_DIR = os.path.join(DIR_PATH, 'files')
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def filepath():
|
||||
"""Returns full file path for test files."""
|
||||
|
||||
def make_filepath(filename):
|
||||
# https://stackoverflow.com/questions/18011902/py-test-pass-a-parameter-to-a-fixture-function
|
||||
# Alternate solution is to use parametrization `indirect=True`
|
||||
# https://stackoverflow.com/questions/18011902/py-test-pass-a-parameter-to-a-fixture-function/33879151#33879151
|
||||
# Syntax is noisy and requires specific variable names
|
||||
return os.path.join(FILES_DIR, filename)
|
||||
|
||||
return make_filepath
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def load_file(filepath):
|
||||
"""Opens filename with encoding and return its contents."""
|
||||
|
||||
def make_load_file(filename, encoding='utf-8'):
|
||||
# https://stackoverflow.com/questions/18011902/py-test-pass-a-parameter-to-a-fixture-function
|
||||
# Alternate solution is to use parametrization `indirect=True`
|
||||
# https://stackoverflow.com/questions/18011902/py-test-pass-a-parameter-to-a-fixture-function/33879151#33879151
|
||||
# Syntax is noisy and requires specific variable names
|
||||
# And seems to be limited to only 1 argument.
|
||||
with io.open(filepath(filename), encoding=encoding) as f:
|
||||
return f.read().strip()
|
||||
|
||||
return make_load_file
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def get_stream(filepath):
|
||||
def make_stream(filename, encoding='utf-8'):
|
||||
return io.open(filepath(filename), encoding=encoding)
|
||||
|
||||
return make_stream
|
||||
3
shell/ext-py/sqlparse-0.3.1/tests/files/encoding_gbk.sql
Normal file
3
shell/ext-py/sqlparse-0.3.1/tests/files/encoding_gbk.sql
Normal file
@@ -0,0 +1,3 @@
|
||||
select *
|
||||
from foo
|
||||
where bar = '<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ϲ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Լ<EFBFBD><EFBFBD><EFBFBD>'
|
||||
@@ -0,0 +1,3 @@
|
||||
select *
|
||||
from foo
|
||||
where bar = '齐天大圣.カラフルな雲.사랑해요'
|
||||
12
shell/ext-py/sqlparse-0.3.1/tests/files/function_psql4.sql
Normal file
12
shell/ext-py/sqlparse-0.3.1/tests/files/function_psql4.sql
Normal file
@@ -0,0 +1,12 @@
|
||||
CREATE FUNCTION doubledollarinbody(var1 text) RETURNS text
|
||||
/* see issue277 */
|
||||
LANGUAGE plpgsql
|
||||
AS $_$
|
||||
DECLARE
|
||||
str text;
|
||||
BEGIN
|
||||
str = $$'foo'$$||var1;
|
||||
execute 'select '||str into str;
|
||||
return str;
|
||||
END
|
||||
$_$;
|
||||
2
shell/ext-py/sqlparse-0.3.1/tests/files/stream.sql
Normal file
2
shell/ext-py/sqlparse-0.3.1/tests/files/stream.sql
Normal file
@@ -0,0 +1,2 @@
|
||||
-- this file is streamed in
|
||||
insert into foo
|
||||
145
shell/ext-py/sqlparse-0.3.1/tests/test_cli.py
Normal file
145
shell/ext-py/sqlparse-0.3.1/tests/test_cli.py
Normal file
@@ -0,0 +1,145 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
|
||||
|
||||
def test_cli_main_empty():
|
||||
with pytest.raises(SystemExit):
|
||||
sqlparse.cli.main([])
|
||||
|
||||
|
||||
def test_parser_empty():
|
||||
with pytest.raises(SystemExit):
|
||||
parser = sqlparse.cli.create_parser()
|
||||
parser.parse_args([])
|
||||
|
||||
|
||||
def test_main_help():
|
||||
# Call with the --help option as a basic sanity check.
|
||||
with pytest.raises(SystemExit) as exinfo:
|
||||
sqlparse.cli.main(["--help", ])
|
||||
assert exinfo.value.code == 0
|
||||
|
||||
|
||||
def test_valid_args(filepath):
|
||||
# test doesn't abort
|
||||
path = filepath('function.sql')
|
||||
assert sqlparse.cli.main([path, '-r']) is not None
|
||||
|
||||
|
||||
def test_invalid_choice(filepath):
|
||||
path = filepath('function.sql')
|
||||
with pytest.raises(SystemExit):
|
||||
sqlparse.cli.main([path, '-l', 'Spanish'])
|
||||
|
||||
|
||||
def test_invalid_args(filepath, capsys):
|
||||
path = filepath('function.sql')
|
||||
sqlparse.cli.main([path, '-r', '--indent_width', '0'])
|
||||
_, err = capsys.readouterr()
|
||||
assert err == ("[ERROR] Invalid options: indent_width requires "
|
||||
"a positive integer\n")
|
||||
|
||||
|
||||
def test_invalid_infile(filepath, capsys):
|
||||
path = filepath('missing.sql')
|
||||
sqlparse.cli.main([path, '-r'])
|
||||
_, err = capsys.readouterr()
|
||||
assert err[:22] == "[ERROR] Failed to read"
|
||||
|
||||
|
||||
def test_invalid_outfile(filepath, capsys):
|
||||
path = filepath('function.sql')
|
||||
outpath = filepath('/missing/function.sql')
|
||||
sqlparse.cli.main([path, '-r', '-o', outpath])
|
||||
_, err = capsys.readouterr()
|
||||
assert err[:22] == "[ERROR] Failed to open"
|
||||
|
||||
|
||||
def test_stdout(filepath, load_file, capsys):
|
||||
path = filepath('begintag.sql')
|
||||
expected = load_file('begintag.sql')
|
||||
sqlparse.cli.main([path])
|
||||
out, _ = capsys.readouterr()
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_script():
|
||||
# Call with the --help option as a basic sanity check.
|
||||
cmd = "{0:s} -m sqlparse.cli --help".format(sys.executable)
|
||||
assert subprocess.call(cmd.split()) == 0
|
||||
|
||||
|
||||
def test_encoding_utf8_stdout(filepath, load_file, capfd):
|
||||
path = filepath('encoding_utf8.sql')
|
||||
expected = load_file('encoding_utf8.sql', 'utf-8')
|
||||
sys.stdout.encoding = 'utf-8'
|
||||
sqlparse.cli.main([path])
|
||||
out, _ = capfd.readouterr()
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_encoding_utf8_output_file(filepath, load_file, tmpdir):
|
||||
in_path = filepath('encoding_utf8.sql')
|
||||
expected = load_file('encoding_utf8.sql', 'utf-8')
|
||||
out_path = tmpdir.dirname + '/encoding_utf8.out.sql'
|
||||
sqlparse.cli.main([in_path, '-o', out_path])
|
||||
out = load_file(out_path, 'utf-8')
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_encoding_gbk_stdout(filepath, load_file, capfd):
|
||||
path = filepath('encoding_gbk.sql')
|
||||
expected = load_file('encoding_gbk.sql', 'gbk')
|
||||
sys.stdout.encoding = 'gbk'
|
||||
sqlparse.cli.main([path, '--encoding', 'gbk'])
|
||||
out, _ = capfd.readouterr()
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_encoding_gbk_output_file(filepath, load_file, tmpdir):
|
||||
in_path = filepath('encoding_gbk.sql')
|
||||
expected = load_file('encoding_gbk.sql', 'gbk')
|
||||
out_path = tmpdir.dirname + '/encoding_gbk.out.sql'
|
||||
sqlparse.cli.main([in_path, '--encoding', 'gbk', '-o', out_path])
|
||||
out = load_file(out_path, 'gbk')
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_encoding_stdin_utf8(filepath, load_file, capfd):
|
||||
path = filepath('encoding_utf8.sql')
|
||||
expected = load_file('encoding_utf8.sql', 'utf-8')
|
||||
old_stdin = sys.stdin
|
||||
with open(path, 'r') as f:
|
||||
sys.stdin = f
|
||||
sys.stdout.encoding = 'utf-8'
|
||||
sqlparse.cli.main(['-'])
|
||||
sys.stdin = old_stdin
|
||||
out, _ = capfd.readouterr()
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_encoding_stdin_gbk(filepath, load_file, capfd):
|
||||
path = filepath('encoding_gbk.sql')
|
||||
expected = load_file('encoding_gbk.sql', 'gbk')
|
||||
old_stdin = sys.stdin
|
||||
with open(path, 'r') as stream:
|
||||
sys.stdin = stream
|
||||
sys.stdout.encoding = 'gbk'
|
||||
sqlparse.cli.main(['-', '--encoding', 'gbk'])
|
||||
sys.stdin = old_stdin
|
||||
out, _ = capfd.readouterr()
|
||||
assert out == expected
|
||||
|
||||
|
||||
def test_encoding(filepath, capsys):
|
||||
path = filepath('test_cp1251.sql')
|
||||
expected = u'insert into foo values (1); -- Песня про надежду\n'
|
||||
sqlparse.cli.main([path, '--encoding=cp1251'])
|
||||
out, _ = capsys.readouterr()
|
||||
assert out == expected
|
||||
709
shell/ext-py/sqlparse-0.3.1/tests/test_format.py
Normal file
709
shell/ext-py/sqlparse-0.3.1/tests/test_format.py
Normal file
@@ -0,0 +1,709 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse.exceptions import SQLParseError
|
||||
|
||||
|
||||
class TestFormat(object):
|
||||
def test_keywordcase(self):
|
||||
sql = 'select * from bar; -- select foo\n'
|
||||
res = sqlparse.format(sql, keyword_case='upper')
|
||||
assert res == 'SELECT * FROM bar; -- select foo\n'
|
||||
res = sqlparse.format(sql, keyword_case='capitalize')
|
||||
assert res == 'Select * From bar; -- select foo\n'
|
||||
res = sqlparse.format(sql.upper(), keyword_case='lower')
|
||||
assert res == 'select * from BAR; -- SELECT FOO\n'
|
||||
|
||||
def test_keywordcase_invalid_option(self):
|
||||
sql = 'select * from bar; -- select foo\n'
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format(sql, keyword_case='foo')
|
||||
|
||||
def test_identifiercase(self):
|
||||
sql = 'select * from bar; -- select foo\n'
|
||||
res = sqlparse.format(sql, identifier_case='upper')
|
||||
assert res == 'select * from BAR; -- select foo\n'
|
||||
res = sqlparse.format(sql, identifier_case='capitalize')
|
||||
assert res == 'select * from Bar; -- select foo\n'
|
||||
res = sqlparse.format(sql.upper(), identifier_case='lower')
|
||||
assert res == 'SELECT * FROM bar; -- SELECT FOO\n'
|
||||
|
||||
def test_identifiercase_invalid_option(self):
|
||||
sql = 'select * from bar; -- select foo\n'
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format(sql, identifier_case='foo')
|
||||
|
||||
def test_identifiercase_quotes(self):
|
||||
sql = 'select * from "foo"."bar"'
|
||||
res = sqlparse.format(sql, identifier_case="upper")
|
||||
assert res == 'select * from "foo"."bar"'
|
||||
|
||||
def test_strip_comments_single(self):
|
||||
sql = 'select *-- statement starts here\nfrom foo'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select * from foo'
|
||||
sql = 'select * -- statement starts here\nfrom foo'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select * from foo'
|
||||
sql = 'select-- foo\nfrom -- bar\nwhere'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select from where'
|
||||
sql = 'select *-- statement starts here\n\nfrom foo'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select * from foo'
|
||||
sql = 'select * from foo-- statement starts here\nwhere'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select * from foo where'
|
||||
sql = 'select a-- statement starts here\nfrom foo'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select a from foo'
|
||||
sql = '--comment\nselect a-- statement starts here\n' \
|
||||
'from foo--comment\nf'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select a from foo f'
|
||||
|
||||
def test_strip_comments_invalid_option(self):
|
||||
sql = 'select-- foo\nfrom -- bar\nwhere'
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format(sql, strip_comments=None)
|
||||
|
||||
def test_strip_comments_multi(self):
|
||||
sql = '/* sql starts here */\nselect'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select'
|
||||
sql = '/* sql starts here */ select'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select'
|
||||
sql = '/*\n * sql starts here\n */\nselect'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select'
|
||||
sql = 'select (/* sql starts here */ select 2)'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select (select 2)'
|
||||
sql = 'select (/* sql /* starts here */ select 2)'
|
||||
res = sqlparse.format(sql, strip_comments=True)
|
||||
assert res == 'select (select 2)'
|
||||
|
||||
def test_strip_ws(self):
|
||||
f = lambda sql: sqlparse.format(sql, strip_whitespace=True)
|
||||
s = 'select\n* from foo\n\twhere ( 1 = 2 )\n'
|
||||
assert f(s) == 'select * from foo where (1 = 2)'
|
||||
s = 'select -- foo\nfrom bar\n'
|
||||
assert f(s) == 'select -- foo\nfrom bar'
|
||||
|
||||
def test_strip_ws_invalid_option(self):
|
||||
s = 'select -- foo\nfrom bar\n'
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format(s, strip_whitespace=None)
|
||||
|
||||
def test_preserve_ws(self):
|
||||
# preserve at least one whitespace after subgroups
|
||||
f = lambda sql: sqlparse.format(sql, strip_whitespace=True)
|
||||
s = 'select\n* /* foo */ from bar '
|
||||
assert f(s) == 'select * /* foo */ from bar'
|
||||
|
||||
def test_notransform_of_quoted_crlf(self):
|
||||
# Make sure that CR/CR+LF characters inside string literals don't get
|
||||
# affected by the formatter.
|
||||
|
||||
s1 = "SELECT some_column LIKE 'value\r'"
|
||||
s2 = "SELECT some_column LIKE 'value\r'\r\nWHERE id = 1\n"
|
||||
s3 = "SELECT some_column LIKE 'value\\'\r' WHERE id = 1\r"
|
||||
s4 = "SELECT some_column LIKE 'value\\\\\\'\r' WHERE id = 1\r\n"
|
||||
|
||||
f = lambda x: sqlparse.format(x)
|
||||
|
||||
# Because of the use of
|
||||
assert f(s1) == "SELECT some_column LIKE 'value\r'"
|
||||
assert f(s2) == "SELECT some_column LIKE 'value\r'\nWHERE id = 1\n"
|
||||
assert f(s3) == "SELECT some_column LIKE 'value\\'\r' WHERE id = 1\n"
|
||||
assert (f(s4)
|
||||
== "SELECT some_column LIKE 'value\\\\\\'\r' WHERE id = 1\n")
|
||||
|
||||
|
||||
class TestFormatReindentAligned(object):
|
||||
@staticmethod
|
||||
def formatter(sql):
|
||||
return sqlparse.format(sql, reindent_aligned=True)
|
||||
|
||||
def test_basic(self):
|
||||
sql = """
|
||||
select a, b as bb,c from table
|
||||
join (select a * 2 as a from new_table) other
|
||||
on table.a = other.a
|
||||
where c is true
|
||||
and b between 3 and 4
|
||||
or d is 'blue'
|
||||
limit 10
|
||||
"""
|
||||
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select a,',
|
||||
' b as bb,',
|
||||
' c',
|
||||
' from table',
|
||||
' join (',
|
||||
' select a * 2 as a',
|
||||
' from new_table',
|
||||
' ) other',
|
||||
' on table.a = other.a',
|
||||
' where c is true',
|
||||
' and b between 3 and 4',
|
||||
" or d is 'blue'",
|
||||
' limit 10'])
|
||||
|
||||
def test_joins(self):
|
||||
sql = """
|
||||
select * from a
|
||||
join b on a.one = b.one
|
||||
left join c on c.two = a.two and c.three = a.three
|
||||
full outer join d on d.three = a.three
|
||||
cross join e on e.four = a.four
|
||||
join f using (one, two, three)
|
||||
"""
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select *',
|
||||
' from a',
|
||||
' join b',
|
||||
' on a.one = b.one',
|
||||
' left join c',
|
||||
' on c.two = a.two',
|
||||
' and c.three = a.three',
|
||||
' full outer join d',
|
||||
' on d.three = a.three',
|
||||
' cross join e',
|
||||
' on e.four = a.four',
|
||||
' join f using (one, two, three)'])
|
||||
|
||||
def test_case_statement(self):
|
||||
sql = """
|
||||
select a,
|
||||
case when a = 0
|
||||
then 1
|
||||
when bb = 1 then 1
|
||||
when c = 2 then 2
|
||||
else 0 end as d,
|
||||
extra_col
|
||||
from table
|
||||
where c is true
|
||||
and b between 3 and 4
|
||||
"""
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select a,',
|
||||
' case when a = 0 then 1',
|
||||
' when bb = 1 then 1',
|
||||
' when c = 2 then 2',
|
||||
' else 0',
|
||||
' end as d,',
|
||||
' extra_col',
|
||||
' from table',
|
||||
' where c is true',
|
||||
' and b between 3 and 4'])
|
||||
|
||||
def test_case_statement_with_between(self):
|
||||
sql = """
|
||||
select a,
|
||||
case when a = 0
|
||||
then 1
|
||||
when bb = 1 then 1
|
||||
when c = 2 then 2
|
||||
when d between 3 and 5 then 3
|
||||
else 0 end as d,
|
||||
extra_col
|
||||
from table
|
||||
where c is true
|
||||
and b between 3 and 4
|
||||
"""
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select a,',
|
||||
' case when a = 0 then 1',
|
||||
' when bb = 1 then 1',
|
||||
' when c = 2 then 2',
|
||||
' when d between 3 and 5 then 3',
|
||||
' else 0',
|
||||
' end as d,',
|
||||
' extra_col',
|
||||
' from table',
|
||||
' where c is true',
|
||||
' and b between 3 and 4'])
|
||||
|
||||
def test_group_by(self):
|
||||
sql = """
|
||||
select a, b, c, sum(x) as sum_x, count(y) as cnt_y
|
||||
from table
|
||||
group by a,b,c
|
||||
having sum(x) > 1
|
||||
and count(y) > 5
|
||||
order by 3,2,1
|
||||
"""
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select a,',
|
||||
' b,',
|
||||
' c,',
|
||||
' sum(x) as sum_x,',
|
||||
' count(y) as cnt_y',
|
||||
' from table',
|
||||
' group by a,',
|
||||
' b,',
|
||||
' c',
|
||||
'having sum(x) > 1',
|
||||
' and count(y) > 5',
|
||||
' order by 3,',
|
||||
' 2,',
|
||||
' 1'])
|
||||
|
||||
def test_group_by_subquery(self):
|
||||
# TODO: add subquery alias when test_identifier_list_subquery fixed
|
||||
sql = """
|
||||
select *, sum_b + 2 as mod_sum
|
||||
from (
|
||||
select a, sum(b) as sum_b
|
||||
from table
|
||||
group by a,z)
|
||||
order by 1,2
|
||||
"""
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select *,',
|
||||
' sum_b + 2 as mod_sum',
|
||||
' from (',
|
||||
' select a,',
|
||||
' sum(b) as sum_b',
|
||||
' from table',
|
||||
' group by a,',
|
||||
' z',
|
||||
' )',
|
||||
' order by 1,',
|
||||
' 2'])
|
||||
|
||||
def test_window_functions(self):
|
||||
sql = """
|
||||
select a,
|
||||
SUM(a) OVER (PARTITION BY b ORDER BY c ROWS
|
||||
BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) as sum_a,
|
||||
ROW_NUMBER() OVER
|
||||
(PARTITION BY b, c ORDER BY d DESC) as row_num
|
||||
from table"""
|
||||
assert self.formatter(sql) == '\n'.join([
|
||||
'select a,',
|
||||
' SUM(a) OVER (PARTITION BY b ORDER BY c ROWS '
|
||||
'BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) as sum_a,',
|
||||
' ROW_NUMBER() OVER '
|
||||
'(PARTITION BY b, c ORDER BY d DESC) as row_num',
|
||||
' from table'])
|
||||
|
||||
|
||||
class TestSpacesAroundOperators(object):
|
||||
@staticmethod
|
||||
def formatter(sql):
|
||||
return sqlparse.format(sql, use_space_around_operators=True)
|
||||
|
||||
def test_basic(self):
|
||||
sql = ('select a+b as d from table '
|
||||
'where (c-d)%2= 1 and e> 3.0/4 and z^2 <100')
|
||||
assert self.formatter(sql) == (
|
||||
'select a + b as d from table '
|
||||
'where (c - d) % 2 = 1 and e > 3.0 / 4 and z ^ 2 < 100')
|
||||
|
||||
def test_bools(self):
|
||||
sql = 'select * from table where a &&b or c||d'
|
||||
assert self.formatter(
|
||||
sql) == 'select * from table where a && b or c || d'
|
||||
|
||||
def test_nested(self):
|
||||
sql = 'select *, case when a-b then c end from table'
|
||||
assert self.formatter(
|
||||
sql) == 'select *, case when a - b then c end from table'
|
||||
|
||||
def test_wildcard_vs_mult(self):
|
||||
sql = 'select a*b-c from table'
|
||||
assert self.formatter(sql) == 'select a * b - c from table'
|
||||
|
||||
|
||||
class TestFormatReindent(object):
|
||||
def test_option(self):
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', reindent=2)
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', indent_tabs=2)
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', reindent=True, indent_width='foo')
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', reindent=True, indent_width=-12)
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', reindent=True, wrap_after='foo')
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', reindent=True, wrap_after=-12)
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', reindent=True, comma_first='foo')
|
||||
|
||||
def test_stmts(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select foo; select bar'
|
||||
assert f(s) == 'select foo;\n\nselect bar'
|
||||
s = 'select foo'
|
||||
assert f(s) == 'select foo'
|
||||
s = 'select foo; -- test\n select bar'
|
||||
assert f(s) == 'select foo; -- test\n\nselect bar'
|
||||
|
||||
def test_keywords(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select * from foo union select * from bar;'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'union',
|
||||
'select *',
|
||||
'from bar;'])
|
||||
|
||||
def test_keywords_between(self):
|
||||
# issue 14
|
||||
# don't break AND after BETWEEN
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'and foo between 1 and 2 and bar = 3'
|
||||
assert f(s) == '\n'.join([
|
||||
'',
|
||||
'and foo between 1 and 2',
|
||||
'and bar = 3'])
|
||||
|
||||
def test_parenthesis(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select count(*) from (select * from foo);'
|
||||
assert f(s) == '\n'.join([
|
||||
'select count(*)',
|
||||
'from',
|
||||
' (select *',
|
||||
' from foo);'])
|
||||
assert f("select f(1)") == 'select f(1)'
|
||||
assert f("select f( 1 )") == 'select f(1)'
|
||||
assert f("select f(\n\n\n1\n\n\n)") == 'select f(1)'
|
||||
assert f("select f(\n\n\n 1 \n\n\n)") == 'select f(1)'
|
||||
assert f("select f(\n\n\n 1 \n\n\n)") == 'select f(1)'
|
||||
|
||||
def test_where(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select * from foo where bar = 1 and baz = 2 or bzz = 3;'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'where bar = 1',
|
||||
' and baz = 2',
|
||||
' or bzz = 3;'])
|
||||
|
||||
s = 'select * from foo where bar = 1 and (baz = 2 or bzz = 3);'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'where bar = 1',
|
||||
' and (baz = 2',
|
||||
' or bzz = 3);'])
|
||||
|
||||
def test_join(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select * from foo join bar on 1 = 2'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'join bar on 1 = 2'])
|
||||
s = 'select * from foo inner join bar on 1 = 2'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'inner join bar on 1 = 2'])
|
||||
s = 'select * from foo left outer join bar on 1 = 2'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'left outer join bar on 1 = 2'])
|
||||
s = 'select * from foo straight_join bar on 1 = 2'
|
||||
assert f(s) == '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'straight_join bar on 1 = 2'])
|
||||
|
||||
def test_identifier_list(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select foo, bar, baz from table1, table2 where 1 = 2'
|
||||
assert f(s) == '\n'.join([
|
||||
'select foo,',
|
||||
' bar,',
|
||||
' baz',
|
||||
'from table1,',
|
||||
' table2',
|
||||
'where 1 = 2'])
|
||||
s = 'select a.*, b.id from a, b'
|
||||
assert f(s) == '\n'.join([
|
||||
'select a.*,',
|
||||
' b.id',
|
||||
'from a,',
|
||||
' b'])
|
||||
|
||||
def test_identifier_list_with_wrap_after(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True, wrap_after=14)
|
||||
s = 'select foo, bar, baz from table1, table2 where 1 = 2'
|
||||
assert f(s) == '\n'.join([
|
||||
'select foo, bar,',
|
||||
' baz',
|
||||
'from table1, table2',
|
||||
'where 1 = 2'])
|
||||
|
||||
def test_identifier_list_comment_first(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True, comma_first=True)
|
||||
# not the 3: It cleans up whitespace too!
|
||||
s = 'select foo, bar, baz from table where foo in (1, 2,3)'
|
||||
assert f(s) == '\n'.join([
|
||||
'select foo',
|
||||
' , bar',
|
||||
' , baz',
|
||||
'from table',
|
||||
'where foo in (1',
|
||||
' , 2',
|
||||
' , 3)'])
|
||||
|
||||
def test_identifier_list_with_functions(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = ("select 'abc' as foo, coalesce(col1, col2)||col3 as bar,"
|
||||
"col3 from my_table")
|
||||
assert f(s) == '\n'.join([
|
||||
"select 'abc' as foo,",
|
||||
" coalesce(col1, col2)||col3 as bar,",
|
||||
" col3",
|
||||
"from my_table"])
|
||||
|
||||
def test_long_identifier_list_with_functions(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True, wrap_after=30)
|
||||
s = ("select 'abc' as foo, json_build_object('a', a,"
|
||||
"'b', b, 'c', c, 'd', d, 'e', e) as col2"
|
||||
"col3 from my_table")
|
||||
assert f(s) == '\n'.join([
|
||||
"select 'abc' as foo,",
|
||||
" json_build_object('a',",
|
||||
" a, 'b', b, 'c', c, 'd', d,",
|
||||
" 'e', e) as col2col3",
|
||||
"from my_table"])
|
||||
|
||||
def test_case(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'case when foo = 1 then 2 when foo = 3 then 4 else 5 end'
|
||||
assert f(s) == '\n'.join([
|
||||
'case',
|
||||
' when foo = 1 then 2',
|
||||
' when foo = 3 then 4',
|
||||
' else 5',
|
||||
'end'])
|
||||
|
||||
def test_case2(self):
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'case(foo) when bar = 1 then 2 else 3 end'
|
||||
assert f(s) == '\n'.join([
|
||||
'case(foo)',
|
||||
' when bar = 1 then 2',
|
||||
' else 3',
|
||||
'end'])
|
||||
|
||||
def test_nested_identifier_list(self):
|
||||
# issue4
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = '(foo as bar, bar1, bar2 as bar3, b4 as b5)'
|
||||
assert f(s) == '\n'.join([
|
||||
'(foo as bar,',
|
||||
' bar1,',
|
||||
' bar2 as bar3,',
|
||||
' b4 as b5)'])
|
||||
|
||||
def test_duplicate_linebreaks(self):
|
||||
# issue3
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select c1 -- column1\nfrom foo'
|
||||
assert f(s) == '\n'.join([
|
||||
'select c1 -- column1',
|
||||
'from foo'])
|
||||
s = 'select c1 -- column1\nfrom foo'
|
||||
r = sqlparse.format(s, reindent=True, strip_comments=True)
|
||||
assert r == '\n'.join([
|
||||
'select c1',
|
||||
'from foo'])
|
||||
s = 'select c1\nfrom foo\norder by c1'
|
||||
assert f(s) == '\n'.join([
|
||||
'select c1',
|
||||
'from foo',
|
||||
'order by c1'])
|
||||
s = 'select c1 from t1 where (c1 = 1) order by c1'
|
||||
assert f(s) == '\n'.join([
|
||||
'select c1',
|
||||
'from t1',
|
||||
'where (c1 = 1)',
|
||||
'order by c1'])
|
||||
|
||||
def test_keywordfunctions(self):
|
||||
# issue36
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select max(a) b, foo, bar'
|
||||
assert f(s) == '\n'.join([
|
||||
'select max(a) b,',
|
||||
' foo,',
|
||||
' bar'])
|
||||
|
||||
def test_identifier_and_functions(self):
|
||||
# issue45
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'select foo.bar, nvl(1) from dual'
|
||||
assert f(s) == '\n'.join([
|
||||
'select foo.bar,',
|
||||
' nvl(1)',
|
||||
'from dual'])
|
||||
|
||||
def test_insert_values(self):
|
||||
# issue 329
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True)
|
||||
s = 'insert into foo values (1, 2)'
|
||||
assert f(s) == '\n'.join([
|
||||
'insert into foo',
|
||||
'values (1, 2)'])
|
||||
|
||||
s = 'insert into foo values (1, 2), (3, 4), (5, 6)'
|
||||
assert f(s) == '\n'.join([
|
||||
'insert into foo',
|
||||
'values (1, 2),',
|
||||
' (3, 4),',
|
||||
' (5, 6)'])
|
||||
|
||||
s = 'insert into foo(a, b) values (1, 2), (3, 4), (5, 6)'
|
||||
assert f(s) == '\n'.join([
|
||||
'insert into foo(a, b)',
|
||||
'values (1, 2),',
|
||||
' (3, 4),',
|
||||
' (5, 6)'])
|
||||
|
||||
f = lambda sql: sqlparse.format(sql, reindent=True,
|
||||
comma_first=True)
|
||||
s = 'insert into foo values (1, 2)'
|
||||
assert f(s) == '\n'.join([
|
||||
'insert into foo',
|
||||
'values (1, 2)'])
|
||||
|
||||
s = 'insert into foo values (1, 2), (3, 4), (5, 6)'
|
||||
assert f(s) == '\n'.join([
|
||||
'insert into foo',
|
||||
'values (1, 2)',
|
||||
' , (3, 4)',
|
||||
' , (5, 6)'])
|
||||
|
||||
s = 'insert into foo(a, b) values (1, 2), (3, 4), (5, 6)'
|
||||
assert f(s) == '\n'.join([
|
||||
'insert into foo(a, b)',
|
||||
'values (1, 2)',
|
||||
' , (3, 4)',
|
||||
' , (5, 6)'])
|
||||
|
||||
|
||||
class TestOutputFormat(object):
|
||||
def test_python(self):
|
||||
sql = 'select * from foo;'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='python')
|
||||
assert f(sql) == "sql = 'select * from foo;'"
|
||||
f = lambda sql: sqlparse.format(sql, output_format='python',
|
||||
reindent=True)
|
||||
assert f(sql) == '\n'.join([
|
||||
"sql = ('select * '",
|
||||
" 'from foo;')"])
|
||||
|
||||
def test_python_multiple_statements(self):
|
||||
sql = 'select * from foo; select 1 from dual'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='python')
|
||||
assert f(sql) == '\n'.join([
|
||||
"sql = 'select * from foo; '",
|
||||
"sql2 = 'select 1 from dual'"])
|
||||
|
||||
@pytest.mark.xfail(reason="Needs fixing")
|
||||
def test_python_multiple_statements_with_formatting(self):
|
||||
sql = 'select * from foo; select 1 from dual'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='python',
|
||||
reindent=True)
|
||||
assert f(sql) == '\n'.join([
|
||||
"sql = ('select * '",
|
||||
" 'from foo;')",
|
||||
"sql2 = ('select 1 '",
|
||||
" 'from dual')"])
|
||||
|
||||
def test_php(self):
|
||||
sql = 'select * from foo;'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='php')
|
||||
assert f(sql) == '$sql = "select * from foo;";'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='php',
|
||||
reindent=True)
|
||||
assert f(sql) == '\n'.join([
|
||||
'$sql = "select * ";',
|
||||
'$sql .= "from foo;";'])
|
||||
|
||||
def test_sql(self):
|
||||
# "sql" is an allowed option but has no effect
|
||||
sql = 'select * from foo;'
|
||||
f = lambda sql: sqlparse.format(sql, output_format='sql')
|
||||
assert f(sql) == 'select * from foo;'
|
||||
|
||||
def test_invalid_option(self):
|
||||
sql = 'select * from foo;'
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format(sql, output_format='foo')
|
||||
|
||||
|
||||
def test_format_column_ordering():
|
||||
# issue89
|
||||
sql = 'select * from foo order by c1 desc, c2, c3;'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
expected = '\n'.join([
|
||||
'select *',
|
||||
'from foo',
|
||||
'order by c1 desc,',
|
||||
' c2,',
|
||||
' c3;'])
|
||||
assert formatted == expected
|
||||
|
||||
|
||||
def test_truncate_strings():
|
||||
sql = "update foo set value = '{0}';".format('x' * 1000)
|
||||
formatted = sqlparse.format(sql, truncate_strings=10)
|
||||
assert formatted == "update foo set value = 'xxxxxxxxxx[...]';"
|
||||
formatted = sqlparse.format(sql, truncate_strings=3, truncate_char='YYY')
|
||||
assert formatted == "update foo set value = 'xxxYYY';"
|
||||
|
||||
|
||||
@pytest.mark.parametrize('option', ['bar', -1, 0])
|
||||
def test_truncate_strings_invalid_option2(option):
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', truncate_strings=option)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('sql', [
|
||||
'select verrrylongcolumn from foo',
|
||||
'select "verrrylongcolumn" from "foo"'])
|
||||
def test_truncate_strings_doesnt_truncate_identifiers(sql):
|
||||
formatted = sqlparse.format(sql, truncate_strings=2)
|
||||
assert formatted == sql
|
||||
|
||||
|
||||
def test_having_produces_newline():
|
||||
sql = ('select * from foo, bar where bar.id = foo.bar_id '
|
||||
'having sum(bar.value) > 100')
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
expected = [
|
||||
'select *',
|
||||
'from foo,',
|
||||
' bar',
|
||||
'where bar.id = foo.bar_id',
|
||||
'having sum(bar.value) > 100']
|
||||
assert formatted == '\n'.join(expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('right_margin', ['ten', 2])
|
||||
def test_format_right_margin_invalid_option(right_margin):
|
||||
with pytest.raises(SQLParseError):
|
||||
sqlparse.format('foo', right_margin=right_margin)
|
||||
|
||||
|
||||
@pytest.mark.xfail(reason="Needs fixing")
|
||||
def test_format_right_margin():
|
||||
# TODO: Needs better test, only raises exception right now
|
||||
sqlparse.format('foo', right_margin="79")
|
||||
642
shell/ext-py/sqlparse-0.3.1/tests/test_grouping.py
Normal file
642
shell/ext-py/sqlparse-0.3.1/tests/test_grouping.py
Normal file
@@ -0,0 +1,642 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import sql, tokens as T
|
||||
|
||||
|
||||
def test_grouping_parenthesis():
|
||||
s = 'select (select (x3) x2) and (y2) bar'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert str(parsed) == s
|
||||
assert len(parsed.tokens) == 7
|
||||
assert isinstance(parsed.tokens[2], sql.Parenthesis)
|
||||
assert isinstance(parsed.tokens[-1], sql.Identifier)
|
||||
assert len(parsed.tokens[2].tokens) == 5
|
||||
assert isinstance(parsed.tokens[2].tokens[3], sql.Identifier)
|
||||
assert isinstance(parsed.tokens[2].tokens[3].tokens[0], sql.Parenthesis)
|
||||
assert len(parsed.tokens[2].tokens[3].tokens) == 3
|
||||
|
||||
|
||||
def test_grouping_comments():
|
||||
s = '/*\n * foo\n */ \n bar'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert str(parsed) == s
|
||||
assert len(parsed.tokens) == 2
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['foo := 1;', 'foo := 1'])
|
||||
def test_grouping_assignment(s):
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert len(parsed.tokens) == 1
|
||||
assert isinstance(parsed.tokens[0], sql.Assignment)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ["x > DATE '2020-01-01'", "x > TIMESTAMP '2020-01-01 00:00:00'"])
|
||||
def test_grouping_typed_literal(s):
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert isinstance(parsed[4], sql.TypedLiteral)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s, a, b', [
|
||||
('select a from b where c < d + e', sql.Identifier, sql.Identifier),
|
||||
('select a from b where c < d + interval \'1 day\'', sql.Identifier, sql.TypedLiteral),
|
||||
('select a from b where c < d + interval \'6\' month', sql.Identifier, sql.TypedLiteral),
|
||||
('select a from b where c < current_timestamp - interval \'1 day\'', sql.Token, sql.TypedLiteral),
|
||||
])
|
||||
def test_compare_expr(s, a, b):
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert str(parsed) == s
|
||||
assert isinstance(parsed.tokens[2], sql.Identifier)
|
||||
assert isinstance(parsed.tokens[6], sql.Identifier)
|
||||
assert isinstance(parsed.tokens[8], sql.Where)
|
||||
assert len(parsed.tokens) == 9
|
||||
where = parsed.tokens[8]
|
||||
assert isinstance(where.tokens[2], sql.Comparison)
|
||||
assert len(where.tokens) == 3
|
||||
comparison = where.tokens[2]
|
||||
assert isinstance(comparison.tokens[0], sql.Identifier)
|
||||
assert comparison.tokens[2].ttype is T.Operator.Comparison
|
||||
assert isinstance(comparison.tokens[4], sql.Operation)
|
||||
assert len(comparison.tokens) == 5
|
||||
operation = comparison.tokens[4]
|
||||
assert isinstance(operation.tokens[0], a)
|
||||
assert operation.tokens[2].ttype is T.Operator
|
||||
assert isinstance(operation.tokens[4], b)
|
||||
assert len(operation.tokens) == 5
|
||||
|
||||
|
||||
def test_grouping_identifiers():
|
||||
s = 'select foo.bar from "myscheme"."table" where fail. order'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert str(parsed) == s
|
||||
assert isinstance(parsed.tokens[2], sql.Identifier)
|
||||
assert isinstance(parsed.tokens[6], sql.Identifier)
|
||||
assert isinstance(parsed.tokens[8], sql.Where)
|
||||
s = 'select * from foo where foo.id = 1'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert str(parsed) == s
|
||||
assert isinstance(parsed.tokens[-1].tokens[-1].tokens[0], sql.Identifier)
|
||||
s = 'select * from (select "foo"."id" from foo)'
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert str(parsed) == s
|
||||
assert isinstance(parsed.tokens[-1].tokens[3], sql.Identifier)
|
||||
|
||||
for s in ["INSERT INTO `test` VALUES('foo', 'bar');",
|
||||
"INSERT INTO `test` VALUES(1, 2), (3, 4), (5, 6);",
|
||||
"INSERT INTO `test(a, b)` VALUES(1, 2), (3, 4), (5, 6);"]:
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
types = [l.ttype for l in parsed.tokens if not l.is_whitespace]
|
||||
assert types == [T.DML, T.Keyword, None, None, T.Punctuation]
|
||||
assert isinstance(parsed.tokens[6], sql.Values)
|
||||
|
||||
s = "select 1.0*(a+b) as col, sum(c)/sum(d) from myschema.mytable"
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert len(parsed.tokens) == 7
|
||||
assert isinstance(parsed.tokens[2], sql.IdentifierList)
|
||||
assert len(parsed.tokens[2].tokens) == 4
|
||||
identifiers = list(parsed.tokens[2].get_identifiers())
|
||||
assert len(identifiers) == 2
|
||||
assert identifiers[0].get_alias() == "col"
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', [
|
||||
'1 as f',
|
||||
'foo as f',
|
||||
'foo f',
|
||||
'1/2 as f',
|
||||
'1/2 f',
|
||||
'1<2 as f', # issue327
|
||||
'1<2 f',
|
||||
])
|
||||
def test_simple_identifiers(s):
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert isinstance(parsed.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', [
|
||||
'foo, bar',
|
||||
'sum(a), sum(b)',
|
||||
'sum(a) as x, b as y',
|
||||
'sum(a)::integer, b',
|
||||
'sum(a)/count(b) as x, y',
|
||||
'sum(a)::integer as x, y',
|
||||
'sum(a)::integer/count(b) as x, y', # issue297
|
||||
])
|
||||
def test_group_identifier_list(s):
|
||||
parsed = sqlparse.parse(s)[0]
|
||||
assert isinstance(parsed.tokens[0], sql.IdentifierList)
|
||||
|
||||
|
||||
def test_grouping_identifier_wildcard():
|
||||
p = sqlparse.parse('a.*, b.id')[0]
|
||||
assert isinstance(p.tokens[0], sql.IdentifierList)
|
||||
assert isinstance(p.tokens[0].tokens[0], sql.Identifier)
|
||||
assert isinstance(p.tokens[0].tokens[-1], sql.Identifier)
|
||||
|
||||
|
||||
def test_grouping_identifier_name_wildcard():
|
||||
p = sqlparse.parse('a.*')[0]
|
||||
t = p.tokens[0]
|
||||
assert t.get_name() == '*'
|
||||
assert t.is_wildcard() is True
|
||||
|
||||
|
||||
def test_grouping_identifier_invalid():
|
||||
p = sqlparse.parse('a.')[0]
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
assert p.tokens[0].has_alias() is False
|
||||
assert p.tokens[0].get_name() is None
|
||||
assert p.tokens[0].get_real_name() is None
|
||||
assert p.tokens[0].get_parent_name() == 'a'
|
||||
|
||||
|
||||
def test_grouping_identifier_invalid_in_middle():
|
||||
# issue261
|
||||
s = 'SELECT foo. FROM foo'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert isinstance(p[2], sql.Identifier)
|
||||
assert p[2][1].ttype == T.Punctuation
|
||||
assert p[3].ttype == T.Whitespace
|
||||
assert str(p[2]) == 'foo.'
|
||||
|
||||
@pytest.mark.parametrize('s', ['foo as (select *)', 'foo as(select *)'])
|
||||
def test_grouping_identifer_as(s):
|
||||
# issue507
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
token = p.tokens[0].tokens[2]
|
||||
assert token.ttype == T.Keyword
|
||||
assert token.normalized == 'AS'
|
||||
|
||||
def test_grouping_identifier_as_invalid():
|
||||
# issue8
|
||||
p = sqlparse.parse('foo as select *')[0]
|
||||
assert len(p.tokens), 5
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
assert len(p.tokens[0].tokens) == 1
|
||||
assert p.tokens[2].ttype == T.Keyword
|
||||
|
||||
|
||||
def test_grouping_identifier_function():
|
||||
p = sqlparse.parse('foo() as bar')[0]
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
assert isinstance(p.tokens[0].tokens[0], sql.Function)
|
||||
p = sqlparse.parse('foo()||col2 bar')[0]
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
assert isinstance(p.tokens[0].tokens[0], sql.Operation)
|
||||
assert isinstance(p.tokens[0].tokens[0].tokens[0], sql.Function)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['foo+100', 'foo + 100', 'foo*100'])
|
||||
def test_grouping_operation(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert isinstance(p.tokens[0], sql.Operation)
|
||||
|
||||
|
||||
def test_grouping_identifier_list():
|
||||
p = sqlparse.parse('a, b, c')[0]
|
||||
assert isinstance(p.tokens[0], sql.IdentifierList)
|
||||
p = sqlparse.parse('(a, b, c)')[0]
|
||||
assert isinstance(p.tokens[0].tokens[1], sql.IdentifierList)
|
||||
|
||||
|
||||
def test_grouping_identifier_list_subquery():
|
||||
"""identifier lists should still work in subqueries with aliases"""
|
||||
p = sqlparse.parse("select * from ("
|
||||
"select a, b + c as d from table) sub")[0]
|
||||
subquery = p.tokens[-1].tokens[0]
|
||||
idx, iden_list = subquery.token_next_by(i=sql.IdentifierList)
|
||||
assert iden_list is not None
|
||||
# all the identifiers should be within the IdentifierList
|
||||
_, ilist = subquery.token_next_by(i=sql.Identifier, idx=idx)
|
||||
assert ilist is None
|
||||
|
||||
|
||||
def test_grouping_identifier_list_case():
|
||||
p = sqlparse.parse('a, case when 1 then 2 else 3 end as b, c')[0]
|
||||
assert isinstance(p.tokens[0], sql.IdentifierList)
|
||||
p = sqlparse.parse('(a, case when 1 then 2 else 3 end as b, c)')[0]
|
||||
assert isinstance(p.tokens[0].tokens[1], sql.IdentifierList)
|
||||
|
||||
|
||||
def test_grouping_identifier_list_other():
|
||||
# issue2
|
||||
p = sqlparse.parse("select *, null, 1, 'foo', bar from mytable, x")[0]
|
||||
assert isinstance(p.tokens[2], sql.IdentifierList)
|
||||
assert len(p.tokens[2].tokens) == 13
|
||||
|
||||
|
||||
def test_grouping_identifier_list_with_inline_comments():
|
||||
# issue163
|
||||
p = sqlparse.parse('foo /* a comment */, bar')[0]
|
||||
assert isinstance(p.tokens[0], sql.IdentifierList)
|
||||
assert isinstance(p.tokens[0].tokens[0], sql.Identifier)
|
||||
assert isinstance(p.tokens[0].tokens[3], sql.Identifier)
|
||||
|
||||
|
||||
def test_grouping_identifiers_with_operators():
|
||||
p = sqlparse.parse('a+b as c from table where (d-e)%2= 1')[0]
|
||||
assert len([x for x in p.flatten() if x.ttype == T.Name]) == 5
|
||||
|
||||
|
||||
def test_grouping_identifier_list_with_order():
|
||||
# issue101
|
||||
p = sqlparse.parse('1, 2 desc, 3')[0]
|
||||
assert isinstance(p.tokens[0], sql.IdentifierList)
|
||||
assert isinstance(p.tokens[0].tokens[3], sql.Identifier)
|
||||
assert str(p.tokens[0].tokens[3]) == '2 desc'
|
||||
|
||||
|
||||
def test_grouping_where():
|
||||
s = 'select * from foo where bar = 1 order by id desc'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
assert len(p.tokens) == 12
|
||||
|
||||
s = 'select x from (select y from foo where bar = 1) z'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
assert isinstance(p.tokens[-1].tokens[0].tokens[-2], sql.Where)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', (
|
||||
'select 1 where 1 = 2 union select 2',
|
||||
'select 1 where 1 = 2 union all select 2',
|
||||
))
|
||||
def test_grouping_where_union(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert p.tokens[5].value.startswith('union')
|
||||
|
||||
|
||||
def test_returning_kw_ends_where_clause():
|
||||
s = 'delete from foo where x > y returning z'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert isinstance(p.tokens[6], sql.Where)
|
||||
assert p.tokens[7].ttype == T.Keyword
|
||||
assert p.tokens[7].value == 'returning'
|
||||
|
||||
|
||||
def test_into_kw_ends_where_clause(): # issue324
|
||||
s = 'select * from foo where a = 1 into baz'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert isinstance(p.tokens[8], sql.Where)
|
||||
assert p.tokens[9].ttype == T.Keyword
|
||||
assert p.tokens[9].value == 'into'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('sql, expected', [
|
||||
# note: typecast needs to be 2nd token for this test
|
||||
('select foo::integer from bar', 'integer'),
|
||||
('select (current_database())::information_schema.sql_identifier',
|
||||
'information_schema.sql_identifier'),
|
||||
])
|
||||
def test_grouping_typecast(sql, expected):
|
||||
p = sqlparse.parse(sql)[0]
|
||||
assert p.tokens[2].get_typecast() == expected
|
||||
|
||||
|
||||
def test_grouping_alias():
|
||||
s = 'select foo as bar from mytable'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
assert p.tokens[2].get_real_name() == 'foo'
|
||||
assert p.tokens[2].get_alias() == 'bar'
|
||||
s = 'select foo from mytable t1'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
assert p.tokens[6].get_real_name() == 'mytable'
|
||||
assert p.tokens[6].get_alias() == 't1'
|
||||
s = 'select foo::integer as bar from mytable'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
assert p.tokens[2].get_alias() == 'bar'
|
||||
s = ('SELECT DISTINCT '
|
||||
'(current_database())::information_schema.sql_identifier AS view')
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
assert p.tokens[4].get_alias() == 'view'
|
||||
|
||||
|
||||
def test_grouping_alias_case():
|
||||
# see issue46
|
||||
p = sqlparse.parse('CASE WHEN 1 THEN 2 ELSE 3 END foo')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].get_alias() == 'foo'
|
||||
|
||||
|
||||
def test_grouping_subquery_no_parens():
|
||||
# Not totally sure if this is the right approach...
|
||||
# When a THEN clause contains a subquery w/o parenthesis around it *and*
|
||||
# a WHERE condition, the WHERE grouper consumes END too.
|
||||
# This takes makes sure that it doesn't fail.
|
||||
p = sqlparse.parse('CASE WHEN 1 THEN select 2 where foo = 1 end')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Case)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['foo.bar', 'x, y', 'x > y', 'x / y'])
|
||||
def test_grouping_alias_returns_none(s):
|
||||
# see issue185 and issue445
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].get_alias() is None
|
||||
|
||||
|
||||
def test_grouping_idlist_function():
|
||||
# see issue10 too
|
||||
p = sqlparse.parse('foo(1) x, bar')[0]
|
||||
assert isinstance(p.tokens[0], sql.IdentifierList)
|
||||
|
||||
|
||||
def test_grouping_comparison_exclude():
|
||||
# make sure operators are not handled too lazy
|
||||
p = sqlparse.parse('(=)')[0]
|
||||
assert isinstance(p.tokens[0], sql.Parenthesis)
|
||||
assert not isinstance(p.tokens[0].tokens[1], sql.Comparison)
|
||||
p = sqlparse.parse('(a=1)')[0]
|
||||
assert isinstance(p.tokens[0].tokens[1], sql.Comparison)
|
||||
p = sqlparse.parse('(a>=1)')[0]
|
||||
assert isinstance(p.tokens[0].tokens[1], sql.Comparison)
|
||||
|
||||
|
||||
def test_grouping_function():
|
||||
p = sqlparse.parse('foo()')[0]
|
||||
assert isinstance(p.tokens[0], sql.Function)
|
||||
p = sqlparse.parse('foo(null, bar)')[0]
|
||||
assert isinstance(p.tokens[0], sql.Function)
|
||||
assert len(list(p.tokens[0].get_parameters())) == 2
|
||||
|
||||
|
||||
def test_grouping_function_not_in():
|
||||
# issue183
|
||||
p = sqlparse.parse('in(1, 2)')[0]
|
||||
assert len(p.tokens) == 2
|
||||
assert p.tokens[0].ttype == T.Keyword
|
||||
assert isinstance(p.tokens[1], sql.Parenthesis)
|
||||
|
||||
|
||||
def test_grouping_varchar():
|
||||
p = sqlparse.parse('"text" Varchar(50) NOT NULL')[0]
|
||||
assert isinstance(p.tokens[2], sql.Function)
|
||||
|
||||
|
||||
def test_statement_get_type():
|
||||
def f(sql):
|
||||
return sqlparse.parse(sql)[0]
|
||||
|
||||
assert f('select * from foo').get_type() == 'SELECT'
|
||||
assert f('update foo').get_type() == 'UPDATE'
|
||||
assert f(' update foo').get_type() == 'UPDATE'
|
||||
assert f('\nupdate foo').get_type() == 'UPDATE'
|
||||
assert f('foo').get_type() == 'UNKNOWN'
|
||||
# Statements that have a whitespace after the closing semicolon
|
||||
# are parsed as two statements where later only consists of the
|
||||
# trailing whitespace.
|
||||
assert f('\n').get_type() == 'UNKNOWN'
|
||||
|
||||
|
||||
def test_identifier_with_operators():
|
||||
# issue 53
|
||||
p = sqlparse.parse('foo||bar')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Operation)
|
||||
# again with whitespaces
|
||||
p = sqlparse.parse('foo || bar')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Operation)
|
||||
|
||||
|
||||
def test_identifier_with_op_trailing_ws():
|
||||
# make sure trailing whitespace isn't grouped with identifier
|
||||
p = sqlparse.parse('foo || bar ')[0]
|
||||
assert len(p.tokens) == 2
|
||||
assert isinstance(p.tokens[0], sql.Operation)
|
||||
assert p.tokens[1].ttype is T.Whitespace
|
||||
|
||||
|
||||
def test_identifier_with_string_literals():
|
||||
p = sqlparse.parse("foo + 'bar'")[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Operation)
|
||||
|
||||
|
||||
# This test seems to be wrong. It was introduced when fixing #53, but #111
|
||||
# showed that this shouldn't be an identifier at all. I'm leaving this
|
||||
# commented in the source for a while.
|
||||
# def test_identifier_string_concat():
|
||||
# p = sqlparse.parse("'foo' || bar")[0]
|
||||
# assert len(p.tokens) == 1
|
||||
# assert isinstance(p.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_identifier_consumes_ordering():
|
||||
# issue89
|
||||
p = sqlparse.parse('select * from foo order by c1 desc, c2, c3')[0]
|
||||
assert isinstance(p.tokens[-1], sql.IdentifierList)
|
||||
ids = list(p.tokens[-1].get_identifiers())
|
||||
assert len(ids) == 3
|
||||
assert ids[0].get_name() == 'c1'
|
||||
assert ids[0].get_ordering() == 'DESC'
|
||||
assert ids[1].get_name() == 'c2'
|
||||
assert ids[1].get_ordering() is None
|
||||
|
||||
|
||||
def test_comparison_with_keywords():
|
||||
# issue90
|
||||
# in fact these are assignments, but for now we don't distinguish them
|
||||
p = sqlparse.parse('foo = NULL')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'foo'
|
||||
assert p.tokens[0].right.value == 'NULL'
|
||||
# make sure it's case-insensitive
|
||||
p = sqlparse.parse('foo = null')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
|
||||
|
||||
def test_comparison_with_floats():
|
||||
# issue145
|
||||
p = sqlparse.parse('foo = 25.5')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'foo'
|
||||
assert p.tokens[0].right.value == '25.5'
|
||||
|
||||
|
||||
def test_comparison_with_parenthesis():
|
||||
# issue23
|
||||
p = sqlparse.parse('(3 + 4) = 7')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
comp = p.tokens[0]
|
||||
assert isinstance(comp.left, sql.Parenthesis)
|
||||
assert comp.right.ttype is T.Number.Integer
|
||||
|
||||
|
||||
@pytest.mark.parametrize('operator', (
|
||||
'=', '!=', '>', '<', '<=', '>=', '~', '~~', '!~~',
|
||||
'LIKE', 'NOT LIKE', 'ILIKE', 'NOT ILIKE',
|
||||
))
|
||||
def test_comparison_with_strings(operator):
|
||||
# issue148
|
||||
p = sqlparse.parse("foo {0} 'bar'".format(operator))[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert p.tokens[0].right.value == "'bar'"
|
||||
assert p.tokens[0].right.ttype == T.String.Single
|
||||
|
||||
|
||||
def test_like_and_ilike_comparison():
|
||||
def validate_where_clause(where_clause, expected_tokens):
|
||||
assert len(where_clause.tokens) == len(expected_tokens)
|
||||
for where_token, expected_token in zip(where_clause, expected_tokens):
|
||||
expected_ttype, expected_value = expected_token
|
||||
if where_token.ttype is not None:
|
||||
assert where_token.match(expected_ttype, expected_value, regex=True)
|
||||
else:
|
||||
# Certain tokens, such as comparison tokens, do not define a ttype that can be
|
||||
# matched against. For these tokens, we ensure that the token instance is of
|
||||
# the expected type and has a value conforming to specified regular expression
|
||||
import re
|
||||
assert (isinstance(where_token, expected_ttype)
|
||||
and re.match(expected_value, where_token.value))
|
||||
|
||||
[p1] = sqlparse.parse("select * from mytable where mytable.mycolumn LIKE 'expr%' limit 5;")
|
||||
[p1_where] = [token for token in p1 if isinstance(token, sql.Where)]
|
||||
validate_where_clause(p1_where, [
|
||||
(T.Keyword, "where"),
|
||||
(T.Whitespace, None),
|
||||
(sql.Comparison, r"mytable.mycolumn LIKE.*"),
|
||||
(T.Whitespace, None),
|
||||
])
|
||||
|
||||
[p2] = sqlparse.parse(
|
||||
"select * from mytable where mycolumn NOT ILIKE '-expr' group by othercolumn;")
|
||||
[p2_where] = [token for token in p2 if isinstance(token, sql.Where)]
|
||||
validate_where_clause(p2_where, [
|
||||
(T.Keyword, "where"),
|
||||
(T.Whitespace, None),
|
||||
(sql.Comparison, r"mycolumn NOT ILIKE.*"),
|
||||
(T.Whitespace, None),
|
||||
])
|
||||
|
||||
|
||||
def test_comparison_with_functions():
|
||||
# issue230
|
||||
p = sqlparse.parse('foo = DATE(bar.baz)')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'foo'
|
||||
assert p.tokens[0].right.value == 'DATE(bar.baz)'
|
||||
|
||||
p = sqlparse.parse('DATE(foo.bar) = DATE(bar.baz)')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'DATE(foo.bar)'
|
||||
assert p.tokens[0].right.value == 'DATE(bar.baz)'
|
||||
|
||||
p = sqlparse.parse('DATE(foo.bar) = bar.baz')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Comparison)
|
||||
assert len(p.tokens[0].tokens) == 5
|
||||
assert p.tokens[0].left.value == 'DATE(foo.bar)'
|
||||
assert p.tokens[0].right.value == 'bar.baz'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('start', ['FOR', 'FOREACH'])
|
||||
def test_forloops(start):
|
||||
p = sqlparse.parse('{0} foo in bar LOOP foobar END LOOP'.format(start))[0]
|
||||
assert (len(p.tokens)) == 1
|
||||
assert isinstance(p.tokens[0], sql.For)
|
||||
|
||||
|
||||
def test_nested_for():
|
||||
p = sqlparse.parse('FOR foo LOOP FOR bar LOOP END LOOP END LOOP')[0]
|
||||
assert len(p.tokens) == 1
|
||||
for1 = p.tokens[0]
|
||||
assert for1.tokens[0].value == 'FOR'
|
||||
assert for1.tokens[-1].value == 'END LOOP'
|
||||
for2 = for1.tokens[6]
|
||||
assert isinstance(for2, sql.For)
|
||||
assert for2.tokens[0].value == 'FOR'
|
||||
assert for2.tokens[-1].value == 'END LOOP'
|
||||
|
||||
|
||||
def test_begin():
|
||||
p = sqlparse.parse('BEGIN foo END')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Begin)
|
||||
|
||||
|
||||
def test_keyword_followed_by_parenthesis():
|
||||
p = sqlparse.parse('USING(somecol')[0]
|
||||
assert len(p.tokens) == 3
|
||||
assert p.tokens[0].ttype == T.Keyword
|
||||
assert p.tokens[1].ttype == T.Punctuation
|
||||
|
||||
|
||||
def test_nested_begin():
|
||||
p = sqlparse.parse('BEGIN foo BEGIN bar END END')[0]
|
||||
assert len(p.tokens) == 1
|
||||
outer = p.tokens[0]
|
||||
assert outer.tokens[0].value == 'BEGIN'
|
||||
assert outer.tokens[-1].value == 'END'
|
||||
inner = outer.tokens[4]
|
||||
assert inner.tokens[0].value == 'BEGIN'
|
||||
assert inner.tokens[-1].value == 'END'
|
||||
assert isinstance(inner, sql.Begin)
|
||||
|
||||
|
||||
def test_aliased_column_without_as():
|
||||
p = sqlparse.parse('foo bar')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_real_name() == 'foo'
|
||||
assert p[0].get_alias() == 'bar'
|
||||
|
||||
p = sqlparse.parse('foo.bar baz')[0].tokens[0]
|
||||
assert p.get_parent_name() == 'foo'
|
||||
assert p.get_real_name() == 'bar'
|
||||
assert p.get_alias() == 'baz'
|
||||
|
||||
|
||||
def test_qualified_function():
|
||||
p = sqlparse.parse('foo()')[0].tokens[0]
|
||||
assert p.get_parent_name() is None
|
||||
assert p.get_real_name() == 'foo'
|
||||
|
||||
p = sqlparse.parse('foo.bar()')[0].tokens[0]
|
||||
assert p.get_parent_name() == 'foo'
|
||||
assert p.get_real_name() == 'bar'
|
||||
|
||||
|
||||
def test_aliased_function_without_as():
|
||||
p = sqlparse.parse('foo() bar')[0].tokens[0]
|
||||
assert p.get_parent_name() is None
|
||||
assert p.get_real_name() == 'foo'
|
||||
assert p.get_alias() == 'bar'
|
||||
|
||||
p = sqlparse.parse('foo.bar() baz')[0].tokens[0]
|
||||
assert p.get_parent_name() == 'foo'
|
||||
assert p.get_real_name() == 'bar'
|
||||
assert p.get_alias() == 'baz'
|
||||
|
||||
|
||||
def test_aliased_literal_without_as():
|
||||
p = sqlparse.parse('1 foo')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_alias() == 'foo'
|
||||
|
||||
|
||||
def test_grouping_as_cte():
|
||||
p = sqlparse.parse('foo AS WITH apple AS 1, banana AS 2')[0].tokens
|
||||
assert len(p) > 4
|
||||
assert p[0].get_alias() is None
|
||||
assert p[2].value == 'AS'
|
||||
assert p[4].value == 'WITH'
|
||||
14
shell/ext-py/sqlparse-0.3.1/tests/test_keywords.py
Normal file
14
shell/ext-py/sqlparse-0.3.1/tests/test_keywords.py
Normal file
@@ -0,0 +1,14 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import pytest
|
||||
|
||||
from sqlparse import tokens
|
||||
from sqlparse.keywords import SQL_REGEX
|
||||
|
||||
|
||||
class TestSQLREGEX:
|
||||
@pytest.mark.parametrize('number', ['1.0', '-1.0',
|
||||
'1.', '-1.',
|
||||
'.1', '-.1'])
|
||||
def test_float_numbers(self, number):
|
||||
ttype = next(tt for action, tt in SQL_REGEX if action(number))
|
||||
assert tokens.Number.Float == ttype
|
||||
474
shell/ext-py/sqlparse-0.3.1/tests/test_parse.py
Normal file
474
shell/ext-py/sqlparse-0.3.1/tests/test_parse.py
Normal file
@@ -0,0 +1,474 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""Tests sqlparse.parse()."""
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import StringIO, text_type
|
||||
|
||||
|
||||
def test_parse_tokenize():
|
||||
s = 'select * from foo;'
|
||||
stmts = sqlparse.parse(s)
|
||||
assert len(stmts) == 1
|
||||
assert str(stmts[0]) == s
|
||||
|
||||
|
||||
def test_parse_multistatement():
|
||||
sql1 = 'select * from foo;'
|
||||
sql2 = 'select * from bar;'
|
||||
stmts = sqlparse.parse(sql1 + sql2)
|
||||
assert len(stmts) == 2
|
||||
assert str(stmts[0]) == sql1
|
||||
assert str(stmts[1]) == sql2
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['select\n*from foo;',
|
||||
'select\r\n*from foo',
|
||||
'select\r*from foo',
|
||||
'select\r\n*from foo\n'])
|
||||
def test_parse_newlines(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert str(p) == s
|
||||
|
||||
|
||||
def test_parse_within():
|
||||
s = 'foo(col1, col2)'
|
||||
p = sqlparse.parse(s)[0]
|
||||
col1 = p.tokens[0].tokens[1].tokens[1].tokens[0]
|
||||
assert col1.within(sql.Function)
|
||||
|
||||
|
||||
def test_parse_child_of():
|
||||
s = '(col1, col2)'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert p.tokens[0].tokens[1].is_child_of(p.tokens[0])
|
||||
s = 'select foo'
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert not p.tokens[2].is_child_of(p.tokens[0])
|
||||
assert p.tokens[2].is_child_of(p)
|
||||
|
||||
|
||||
def test_parse_has_ancestor():
|
||||
s = 'foo or (bar, baz)'
|
||||
p = sqlparse.parse(s)[0]
|
||||
baz = p.tokens[-1].tokens[1].tokens[-1]
|
||||
assert baz.has_ancestor(p.tokens[-1].tokens[1])
|
||||
assert baz.has_ancestor(p.tokens[-1])
|
||||
assert baz.has_ancestor(p)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['.5', '.51', '1.5', '12.5'])
|
||||
def test_parse_float(s):
|
||||
t = sqlparse.parse(s)[0].tokens
|
||||
assert len(t) == 1
|
||||
assert t[0].ttype is sqlparse.tokens.Number.Float
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s, holder', [
|
||||
('select * from foo where user = ?', '?'),
|
||||
('select * from foo where user = :1', ':1'),
|
||||
('select * from foo where user = :name', ':name'),
|
||||
('select * from foo where user = %s', '%s'),
|
||||
('select * from foo where user = $a', '$a')])
|
||||
def test_parse_placeholder(s, holder):
|
||||
t = sqlparse.parse(s)[0].tokens[-1].tokens
|
||||
assert t[-1].ttype is sqlparse.tokens.Name.Placeholder
|
||||
assert t[-1].value == holder
|
||||
|
||||
|
||||
def test_parse_modulo_not_placeholder():
|
||||
tokens = list(sqlparse.lexer.tokenize('x %3'))
|
||||
assert tokens[2][0] == sqlparse.tokens.Operator
|
||||
|
||||
|
||||
def test_parse_access_symbol():
|
||||
# see issue27
|
||||
t = sqlparse.parse('select a.[foo bar] as foo')[0].tokens
|
||||
assert isinstance(t[-1], sql.Identifier)
|
||||
assert t[-1].get_name() == 'foo'
|
||||
assert t[-1].get_real_name() == '[foo bar]'
|
||||
assert t[-1].get_parent_name() == 'a'
|
||||
|
||||
|
||||
def test_parse_square_brackets_notation_isnt_too_greedy():
|
||||
# see issue153
|
||||
t = sqlparse.parse('[foo], [bar]')[0].tokens
|
||||
assert isinstance(t[0], sql.IdentifierList)
|
||||
assert len(t[0].tokens) == 4
|
||||
assert t[0].tokens[0].get_real_name() == '[foo]'
|
||||
assert t[0].tokens[-1].get_real_name() == '[bar]'
|
||||
|
||||
|
||||
def test_parse_keyword_like_identifier():
|
||||
# see issue47
|
||||
t = sqlparse.parse('foo.key')[0].tokens
|
||||
assert len(t) == 1
|
||||
assert isinstance(t[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_parse_function_parameter():
|
||||
# see issue94
|
||||
t = sqlparse.parse('abs(some_col)')[0].tokens[0].get_parameters()
|
||||
assert len(t) == 1
|
||||
assert isinstance(t[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_parse_function_param_single_literal():
|
||||
t = sqlparse.parse('foo(5)')[0].tokens[0].get_parameters()
|
||||
assert len(t) == 1
|
||||
assert t[0].ttype is T.Number.Integer
|
||||
|
||||
|
||||
def test_parse_nested_function():
|
||||
t = sqlparse.parse('foo(bar(5))')[0].tokens[0].get_parameters()
|
||||
assert len(t) == 1
|
||||
assert type(t[0]) is sql.Function
|
||||
|
||||
|
||||
def test_quoted_identifier():
|
||||
t = sqlparse.parse('select x.y as "z" from foo')[0].tokens
|
||||
assert isinstance(t[2], sql.Identifier)
|
||||
assert t[2].get_name() == 'z'
|
||||
assert t[2].get_real_name() == 'y'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('name', [
|
||||
'foo', '_foo', # issue175
|
||||
'1_data', # valid MySQL table name, see issue337
|
||||
])
|
||||
def test_valid_identifier_names(name):
|
||||
t = sqlparse.parse(name)[0].tokens
|
||||
assert isinstance(t[0], sql.Identifier)
|
||||
assert t[0].get_name() == name
|
||||
|
||||
|
||||
def test_psql_quotation_marks():
|
||||
# issue83
|
||||
|
||||
# regression: make sure plain $$ work
|
||||
t = sqlparse.split("""
|
||||
CREATE OR REPLACE FUNCTION testfunc1(integer) RETURNS integer AS $$
|
||||
....
|
||||
$$ LANGUAGE plpgsql;
|
||||
CREATE OR REPLACE FUNCTION testfunc2(integer) RETURNS integer AS $$
|
||||
....
|
||||
$$ LANGUAGE plpgsql;""")
|
||||
assert len(t) == 2
|
||||
|
||||
# make sure $SOMETHING$ works too
|
||||
t = sqlparse.split("""
|
||||
CREATE OR REPLACE FUNCTION testfunc1(integer) RETURNS integer AS $PROC_1$
|
||||
....
|
||||
$PROC_1$ LANGUAGE plpgsql;
|
||||
CREATE OR REPLACE FUNCTION testfunc2(integer) RETURNS integer AS $PROC_2$
|
||||
....
|
||||
$PROC_2$ LANGUAGE plpgsql;""")
|
||||
assert len(t) == 2
|
||||
|
||||
|
||||
def test_double_precision_is_builtin():
|
||||
s = 'DOUBLE PRECISION'
|
||||
t = sqlparse.parse(s)[0].tokens
|
||||
assert len(t) == 1
|
||||
assert t[0].ttype == sqlparse.tokens.Name.Builtin
|
||||
assert t[0].value == 'DOUBLE PRECISION'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('ph', ['?', ':1', ':foo', '%s', '%(foo)s'])
|
||||
def test_placeholder(ph):
|
||||
p = sqlparse.parse(ph)[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.Name.Placeholder
|
||||
|
||||
|
||||
@pytest.mark.parametrize('num', ['6.67428E-8', '1.988e33', '1e-12'])
|
||||
def test_scientific_numbers(num):
|
||||
p = sqlparse.parse(num)[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.Number.Float
|
||||
|
||||
|
||||
def test_single_quotes_are_strings():
|
||||
p = sqlparse.parse("'foo'")[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.String.Single
|
||||
|
||||
|
||||
def test_double_quotes_are_identifiers():
|
||||
p = sqlparse.parse('"foo"')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert isinstance(p[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_single_quotes_with_linebreaks():
|
||||
# issue118
|
||||
p = sqlparse.parse("'f\nf'")[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].ttype is T.String.Single
|
||||
|
||||
|
||||
def test_sqlite_identifiers():
|
||||
# Make sure we still parse sqlite style escapes
|
||||
p = sqlparse.parse('[col1],[col2]')[0].tokens
|
||||
id_names = [id_.get_name() for id_ in p[0].get_identifiers()]
|
||||
assert len(p) == 1
|
||||
assert isinstance(p[0], sql.IdentifierList)
|
||||
assert id_names == ['[col1]', '[col2]']
|
||||
|
||||
p = sqlparse.parse('[col1]+[col2]')[0]
|
||||
types = [tok.ttype for tok in p.flatten()]
|
||||
assert types == [T.Name, T.Operator, T.Name]
|
||||
|
||||
|
||||
def test_simple_1d_array_index():
|
||||
p = sqlparse.parse('col[1]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_name() == 'col'
|
||||
indices = list(p[0].get_array_indices())
|
||||
assert len(indices) == 1 # 1-dimensional index
|
||||
assert len(indices[0]) == 1 # index is single token
|
||||
assert indices[0][0].value == '1'
|
||||
|
||||
|
||||
def test_2d_array_index():
|
||||
p = sqlparse.parse('col[x][(y+1)*2]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_name() == 'col'
|
||||
assert len(list(p[0].get_array_indices())) == 2 # 2-dimensional index
|
||||
|
||||
|
||||
def test_array_index_function_result():
|
||||
p = sqlparse.parse('somefunc()[1]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert len(list(p[0].get_array_indices())) == 1
|
||||
|
||||
|
||||
def test_schema_qualified_array_index():
|
||||
p = sqlparse.parse('schem.col[1]')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_parent_name() == 'schem'
|
||||
assert p[0].get_name() == 'col'
|
||||
assert list(p[0].get_array_indices())[0][0].value == '1'
|
||||
|
||||
|
||||
def test_aliased_array_index():
|
||||
p = sqlparse.parse('col[1] x')[0].tokens
|
||||
assert len(p) == 1
|
||||
assert p[0].get_alias() == 'x'
|
||||
assert p[0].get_real_name() == 'col'
|
||||
assert list(p[0].get_array_indices())[0][0].value == '1'
|
||||
|
||||
|
||||
def test_array_literal():
|
||||
# See issue #176
|
||||
p = sqlparse.parse('ARRAY[%s, %s]')[0]
|
||||
assert len(p.tokens) == 2
|
||||
assert len(list(p.flatten())) == 7
|
||||
|
||||
|
||||
def test_typed_array_definition():
|
||||
# array indices aren't grouped with built-ins, but make sure we can extract
|
||||
# identifier names
|
||||
p = sqlparse.parse('x int, y int[], z int')[0]
|
||||
names = [x.get_name() for x in p.get_sublists()
|
||||
if isinstance(x, sql.Identifier)]
|
||||
assert names == ['x', 'y', 'z']
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['select 1 -- foo', 'select 1 # foo'])
|
||||
def test_single_line_comments(s):
|
||||
# see issue178
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 5
|
||||
assert p.tokens[-1].ttype == T.Comment.Single
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['foo', '@foo', '#foo', '##foo'])
|
||||
def test_names_and_special_names(s):
|
||||
# see issue192
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
def test_get_token_at_offset():
|
||||
p = sqlparse.parse('select * from dual')[0]
|
||||
# 0123456789
|
||||
assert p.get_token_at_offset(0) == p.tokens[0]
|
||||
assert p.get_token_at_offset(1) == p.tokens[0]
|
||||
assert p.get_token_at_offset(6) == p.tokens[1]
|
||||
assert p.get_token_at_offset(7) == p.tokens[2]
|
||||
assert p.get_token_at_offset(8) == p.tokens[3]
|
||||
assert p.get_token_at_offset(9) == p.tokens[4]
|
||||
assert p.get_token_at_offset(10) == p.tokens[4]
|
||||
|
||||
|
||||
def test_pprint():
|
||||
p = sqlparse.parse('select a0, b0, c0, d0, e0 from '
|
||||
'(select * from dual) q0 where 1=1 and 2=2')[0]
|
||||
output = StringIO()
|
||||
|
||||
p._pprint_tree(f=output)
|
||||
pprint = '\n'.join([
|
||||
"|- 0 DML 'select'",
|
||||
"|- 1 Whitespace ' '",
|
||||
"|- 2 IdentifierList 'a0, b0...'",
|
||||
"| |- 0 Identifier 'a0'",
|
||||
"| | `- 0 Name 'a0'",
|
||||
"| |- 1 Punctuation ','",
|
||||
"| |- 2 Whitespace ' '",
|
||||
"| |- 3 Identifier 'b0'",
|
||||
"| | `- 0 Name 'b0'",
|
||||
"| |- 4 Punctuation ','",
|
||||
"| |- 5 Whitespace ' '",
|
||||
"| |- 6 Identifier 'c0'",
|
||||
"| | `- 0 Name 'c0'",
|
||||
"| |- 7 Punctuation ','",
|
||||
"| |- 8 Whitespace ' '",
|
||||
"| |- 9 Identifier 'd0'",
|
||||
"| | `- 0 Name 'd0'",
|
||||
"| |- 10 Punctuation ','",
|
||||
"| |- 11 Whitespace ' '",
|
||||
"| `- 12 Float 'e0'",
|
||||
"|- 3 Whitespace ' '",
|
||||
"|- 4 Keyword 'from'",
|
||||
"|- 5 Whitespace ' '",
|
||||
"|- 6 Identifier '(selec...'",
|
||||
"| |- 0 Parenthesis '(selec...'",
|
||||
"| | |- 0 Punctuation '('",
|
||||
"| | |- 1 DML 'select'",
|
||||
"| | |- 2 Whitespace ' '",
|
||||
"| | |- 3 Wildcard '*'",
|
||||
"| | |- 4 Whitespace ' '",
|
||||
"| | |- 5 Keyword 'from'",
|
||||
"| | |- 6 Whitespace ' '",
|
||||
"| | |- 7 Identifier 'dual'",
|
||||
"| | | `- 0 Name 'dual'",
|
||||
"| | `- 8 Punctuation ')'",
|
||||
"| |- 1 Whitespace ' '",
|
||||
"| `- 2 Identifier 'q0'",
|
||||
"| `- 0 Name 'q0'",
|
||||
"|- 7 Whitespace ' '",
|
||||
"`- 8 Where 'where ...'",
|
||||
" |- 0 Keyword 'where'",
|
||||
" |- 1 Whitespace ' '",
|
||||
" |- 2 Comparison '1=1'",
|
||||
" | |- 0 Integer '1'",
|
||||
" | |- 1 Comparison '='",
|
||||
" | `- 2 Integer '1'",
|
||||
" |- 3 Whitespace ' '",
|
||||
" |- 4 Keyword 'and'",
|
||||
" |- 5 Whitespace ' '",
|
||||
" `- 6 Comparison '2=2'",
|
||||
" |- 0 Integer '2'",
|
||||
" |- 1 Comparison '='",
|
||||
" `- 2 Integer '2'",
|
||||
""])
|
||||
assert output.getvalue() == pprint
|
||||
|
||||
|
||||
def test_wildcard_multiplication():
|
||||
p = sqlparse.parse('select * from dual')[0]
|
||||
assert p.tokens[2].ttype == T.Wildcard
|
||||
|
||||
p = sqlparse.parse('select a0.* from dual a0')[0]
|
||||
assert p.tokens[2][2].ttype == T.Wildcard
|
||||
|
||||
p = sqlparse.parse('select 1 * 2 from dual')[0]
|
||||
assert p.tokens[2][2].ttype == T.Operator
|
||||
|
||||
|
||||
def test_stmt_tokens_parents():
|
||||
# see issue 226
|
||||
s = "CREATE TABLE test();"
|
||||
stmt = sqlparse.parse(s)[0]
|
||||
for token in stmt.tokens:
|
||||
assert token.has_ancestor(stmt)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('sql, is_literal', [
|
||||
('$$foo$$', True),
|
||||
('$_$foo$_$', True),
|
||||
('$token$ foo $token$', True),
|
||||
# don't parse inner tokens
|
||||
('$_$ foo $token$bar$token$ baz$_$', True),
|
||||
('$A$ foo $B$', False) # tokens don't match
|
||||
])
|
||||
def test_dbldollar_as_literal(sql, is_literal):
|
||||
# see issue 277
|
||||
p = sqlparse.parse(sql)[0]
|
||||
if is_literal:
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype == T.Literal
|
||||
else:
|
||||
for token in p.tokens:
|
||||
assert token.ttype != T.Literal
|
||||
|
||||
|
||||
def test_non_ascii():
|
||||
_test_non_ascii = u"insert into test (id, name) values (1, 'тест');"
|
||||
|
||||
s = _test_non_ascii
|
||||
stmts = sqlparse.parse(s)
|
||||
assert len(stmts) == 1
|
||||
statement = stmts[0]
|
||||
assert text_type(statement) == s
|
||||
assert statement._pprint_tree() is None
|
||||
|
||||
s = _test_non_ascii.encode('utf-8')
|
||||
stmts = sqlparse.parse(s, 'utf-8')
|
||||
assert len(stmts) == 1
|
||||
statement = stmts[0]
|
||||
assert text_type(statement) == _test_non_ascii
|
||||
assert statement._pprint_tree() is None
|
||||
|
||||
|
||||
def test_get_real_name():
|
||||
# issue 369
|
||||
s = u"update a t set t.b=1"
|
||||
stmts = sqlparse.parse(s)
|
||||
assert len(stmts) == 1
|
||||
assert 'a' == stmts[0].tokens[2].get_real_name()
|
||||
assert 't' == stmts[0].tokens[2].get_alias()
|
||||
|
||||
|
||||
def test_from_subquery():
|
||||
# issue 446
|
||||
s = u'from(select 1)'
|
||||
stmts = sqlparse.parse(s)
|
||||
assert len(stmts) == 1
|
||||
assert len(stmts[0].tokens) == 2
|
||||
assert stmts[0].tokens[0].value == 'from'
|
||||
assert stmts[0].tokens[0].ttype == T.Keyword
|
||||
|
||||
s = u'from (select 1)'
|
||||
stmts = sqlparse.parse(s)
|
||||
assert len(stmts) == 1
|
||||
assert len(stmts[0].tokens) == 3
|
||||
assert stmts[0].tokens[0].value == 'from'
|
||||
assert stmts[0].tokens[0].ttype == T.Keyword
|
||||
assert stmts[0].tokens[1].ttype == T.Whitespace
|
||||
|
||||
|
||||
def test_parenthesis():
|
||||
tokens = sqlparse.parse("(\n\n1\n\n)")[0].tokens[0].tokens
|
||||
assert list(map(lambda t: t.ttype, tokens)) == [T.Punctuation,
|
||||
T.Newline,
|
||||
T.Newline,
|
||||
T.Number.Integer,
|
||||
T.Newline,
|
||||
T.Newline,
|
||||
T.Punctuation]
|
||||
tokens = sqlparse.parse("(\n\n 1 \n\n)")[0].tokens[0].tokens
|
||||
assert list(map(lambda t: t.ttype, tokens)) == [T.Punctuation,
|
||||
T.Newline,
|
||||
T.Newline,
|
||||
T.Whitespace,
|
||||
T.Number.Integer,
|
||||
T.Whitespace,
|
||||
T.Newline,
|
||||
T.Newline,
|
||||
T.Punctuation]
|
||||
408
shell/ext-py/sqlparse-0.3.1/tests/test_regressions.py
Normal file
408
shell/ext-py/sqlparse-0.3.1/tests/test_regressions.py
Normal file
@@ -0,0 +1,408 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import PY2
|
||||
|
||||
|
||||
def test_issue9():
|
||||
# make sure where doesn't consume parenthesis
|
||||
p = sqlparse.parse('(where 1)')[0]
|
||||
assert isinstance(p, sql.Statement)
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Parenthesis)
|
||||
prt = p.tokens[0]
|
||||
assert len(prt.tokens) == 3
|
||||
assert prt.tokens[0].ttype == T.Punctuation
|
||||
assert prt.tokens[-1].ttype == T.Punctuation
|
||||
|
||||
|
||||
def test_issue13():
|
||||
parsed = sqlparse.parse(("select 'one';\n"
|
||||
"select 'two\\'';\n"
|
||||
"select 'three';"))
|
||||
assert len(parsed) == 3
|
||||
assert str(parsed[1]).strip() == "select 'two\\'';"
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['--hello', '-- hello', '--hello\n',
|
||||
'--', '--\n'])
|
||||
def test_issue26(s):
|
||||
# parse stand-alone comments
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is T.Comment.Single
|
||||
|
||||
|
||||
@pytest.mark.parametrize('value', ['create', 'CREATE'])
|
||||
def test_issue34(value):
|
||||
t = sqlparse.parse("create")[0].token_first()
|
||||
assert t.match(T.Keyword.DDL, value) is True
|
||||
|
||||
|
||||
def test_issue35():
|
||||
# missing space before LIMIT. Updated for #321
|
||||
sql = sqlparse.format("select * from foo where bar = 1 limit 1",
|
||||
reindent=True)
|
||||
assert sql == "\n".join([
|
||||
"select *",
|
||||
"from foo",
|
||||
"where bar = 1",
|
||||
"limit 1"])
|
||||
|
||||
|
||||
def test_issue38():
|
||||
sql = sqlparse.format("SELECT foo; -- comment", strip_comments=True)
|
||||
assert sql == "SELECT foo;"
|
||||
sql = sqlparse.format("/* foo */", strip_comments=True)
|
||||
assert sql == ""
|
||||
|
||||
|
||||
def test_issue39():
|
||||
p = sqlparse.parse('select user.id from user')[0]
|
||||
assert len(p.tokens) == 7
|
||||
idt = p.tokens[2]
|
||||
assert idt.__class__ == sql.Identifier
|
||||
assert len(idt.tokens) == 3
|
||||
assert idt.tokens[0].match(T.Name, 'user') is True
|
||||
assert idt.tokens[1].match(T.Punctuation, '.') is True
|
||||
assert idt.tokens[2].match(T.Name, 'id') is True
|
||||
|
||||
|
||||
def test_issue40():
|
||||
# make sure identifier lists in subselects are grouped
|
||||
p = sqlparse.parse(('SELECT id, name FROM '
|
||||
'(SELECT id, name FROM bar) as foo'))[0]
|
||||
assert len(p.tokens) == 7
|
||||
assert p.tokens[2].__class__ == sql.IdentifierList
|
||||
assert p.tokens[-1].__class__ == sql.Identifier
|
||||
assert p.tokens[-1].get_name() == 'foo'
|
||||
sp = p.tokens[-1].tokens[0]
|
||||
assert sp.tokens[3].__class__ == sql.IdentifierList
|
||||
# make sure that formatting works as expected
|
||||
s = sqlparse.format('SELECT id == name FROM '
|
||||
'(SELECT id, name FROM bar)', reindent=True)
|
||||
assert s == '\n'.join([
|
||||
'SELECT id == name',
|
||||
'FROM',
|
||||
' (SELECT id,',
|
||||
' name',
|
||||
' FROM bar)'])
|
||||
|
||||
s = sqlparse.format('SELECT id == name FROM '
|
||||
'(SELECT id, name FROM bar) as foo', reindent=True)
|
||||
assert s == '\n'.join([
|
||||
'SELECT id == name',
|
||||
'FROM',
|
||||
' (SELECT id,',
|
||||
' name',
|
||||
' FROM bar) as foo'])
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['select x.y::text as z from foo',
|
||||
'select x.y::text as "z" from foo',
|
||||
'select x."y"::text as z from foo',
|
||||
'select x."y"::text as "z" from foo',
|
||||
'select "x".y::text as z from foo',
|
||||
'select "x".y::text as "z" from foo',
|
||||
'select "x"."y"::text as z from foo',
|
||||
'select "x"."y"::text as "z" from foo'])
|
||||
@pytest.mark.parametrize('func_name, result', [('get_name', 'z'),
|
||||
('get_real_name', 'y'),
|
||||
('get_parent_name', 'x'),
|
||||
('get_alias', 'z'),
|
||||
('get_typecast', 'text')])
|
||||
def test_issue78(s, func_name, result):
|
||||
# the bug author provided this nice examples, let's use them!
|
||||
p = sqlparse.parse(s)[0]
|
||||
i = p.tokens[2]
|
||||
assert isinstance(i, sql.Identifier)
|
||||
|
||||
func = getattr(i, func_name)
|
||||
assert func() == result
|
||||
|
||||
|
||||
def test_issue83():
|
||||
sql = """ CREATE OR REPLACE FUNCTION func_a(text)
|
||||
RETURNS boolean LANGUAGE plpgsql STRICT IMMUTABLE AS
|
||||
$_$
|
||||
BEGIN
|
||||
...
|
||||
END;
|
||||
$_$;
|
||||
|
||||
CREATE OR REPLACE FUNCTION func_b(text)
|
||||
RETURNS boolean LANGUAGE plpgsql STRICT IMMUTABLE AS
|
||||
$_$
|
||||
BEGIN
|
||||
...
|
||||
END;
|
||||
$_$;
|
||||
|
||||
ALTER TABLE..... ;"""
|
||||
t = sqlparse.split(sql)
|
||||
assert len(t) == 3
|
||||
|
||||
|
||||
def test_comment_encoding_when_reindent():
|
||||
# There was an UnicodeEncodeError in the reindent filter that
|
||||
# casted every comment followed by a keyword to str.
|
||||
sql = u'select foo -- Comment containing Ümläuts\nfrom bar'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
assert formatted == sql
|
||||
|
||||
|
||||
def test_parse_sql_with_binary():
|
||||
# See https://github.com/andialbrecht/sqlparse/pull/88
|
||||
# digest = '|ËêplL4¡høN{'
|
||||
digest = '\x82|\xcb\x0e\xea\x8aplL4\xa1h\x91\xf8N{'
|
||||
sql = "select * from foo where bar = '{0}'".format(digest)
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = "select *\nfrom foo\nwhere bar = '{0}'".format(digest)
|
||||
if PY2:
|
||||
tformatted = tformatted.decode('unicode-escape')
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_dont_alias_keywords():
|
||||
# The _group_left_right function had a bug where the check for the
|
||||
# left side wasn't handled correctly. In one case this resulted in
|
||||
# a keyword turning into an identifier.
|
||||
p = sqlparse.parse('FROM AS foo')[0]
|
||||
assert len(p.tokens) == 5
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
assert p.tokens[2].ttype is T.Keyword
|
||||
|
||||
|
||||
def test_format_accepts_encoding(load_file):
|
||||
# issue20
|
||||
sql = load_file('test_cp1251.sql', 'cp1251')
|
||||
formatted = sqlparse.format(sql, reindent=True, encoding='cp1251')
|
||||
tformatted = u'insert into foo\nvalues (1); -- Песня про надежду'
|
||||
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_stream(get_stream):
|
||||
with get_stream("stream.sql") as stream:
|
||||
p = sqlparse.parse(stream)[0]
|
||||
assert p.get_type() == 'INSERT'
|
||||
|
||||
|
||||
def test_issue90():
|
||||
sql = ('UPDATE "gallery_photo" SET "owner_id" = 4018, "deleted_at" = NULL,'
|
||||
' "width" = NULL, "height" = NULL, "rating_votes" = 0,'
|
||||
' "rating_score" = 0, "thumbnail_width" = NULL,'
|
||||
' "thumbnail_height" = NULL, "price" = 1, "description" = NULL')
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = '\n'.join([
|
||||
'UPDATE "gallery_photo"',
|
||||
'SET "owner_id" = 4018,',
|
||||
' "deleted_at" = NULL,',
|
||||
' "width" = NULL,',
|
||||
' "height" = NULL,',
|
||||
' "rating_votes" = 0,',
|
||||
' "rating_score" = 0,',
|
||||
' "thumbnail_width" = NULL,',
|
||||
' "thumbnail_height" = NULL,',
|
||||
' "price" = 1,',
|
||||
' "description" = NULL'])
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_except_formatting():
|
||||
sql = 'SELECT 1 FROM foo WHERE 2 = 3 EXCEPT SELECT 2 FROM bar WHERE 1 = 2'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = '\n'.join([
|
||||
'SELECT 1',
|
||||
'FROM foo',
|
||||
'WHERE 2 = 3',
|
||||
'EXCEPT',
|
||||
'SELECT 2',
|
||||
'FROM bar',
|
||||
'WHERE 1 = 2'])
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_null_with_as():
|
||||
sql = 'SELECT NULL AS c1, NULL AS c2 FROM t1'
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = '\n'.join([
|
||||
'SELECT NULL AS c1,',
|
||||
' NULL AS c2',
|
||||
'FROM t1'])
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_issue190_open_file(filepath):
|
||||
path = filepath('stream.sql')
|
||||
with open(path) as stream:
|
||||
p = sqlparse.parse(stream)[0]
|
||||
assert p.get_type() == 'INSERT'
|
||||
|
||||
|
||||
def test_issue193_splitting_function():
|
||||
sql = """ CREATE FUNCTION a(x VARCHAR(20)) RETURNS VARCHAR(20)
|
||||
BEGIN
|
||||
DECLARE y VARCHAR(20);
|
||||
RETURN x;
|
||||
END;
|
||||
SELECT * FROM a.b;"""
|
||||
statements = sqlparse.split(sql)
|
||||
assert len(statements) == 2
|
||||
|
||||
|
||||
def test_issue194_splitting_function():
|
||||
sql = """ CREATE FUNCTION a(x VARCHAR(20)) RETURNS VARCHAR(20)
|
||||
BEGIN
|
||||
DECLARE y VARCHAR(20);
|
||||
IF (1 = 1) THEN
|
||||
SET x = y;
|
||||
END IF;
|
||||
RETURN x;
|
||||
END;
|
||||
SELECT * FROM a.b;"""
|
||||
statements = sqlparse.split(sql)
|
||||
assert len(statements) == 2
|
||||
|
||||
|
||||
def test_issue186_get_type():
|
||||
sql = "-- comment\ninsert into foo"
|
||||
p = sqlparse.parse(sql)[0]
|
||||
assert p.get_type() == 'INSERT'
|
||||
|
||||
|
||||
def test_issue212_py2unicode():
|
||||
t1 = sql.Token(T.String, u'schöner ')
|
||||
t2 = sql.Token(T.String, 'bug')
|
||||
token_list = sql.TokenList([t1, t2])
|
||||
assert str(token_list) == 'schöner bug'
|
||||
|
||||
|
||||
def test_issue213_leadingws():
|
||||
sql = " select * from foo"
|
||||
assert sqlparse.format(sql, strip_whitespace=True) == "select * from foo"
|
||||
|
||||
|
||||
def test_issue227_gettype_cte():
|
||||
select_stmt = sqlparse.parse('SELECT 1, 2, 3 FROM foo;')
|
||||
assert select_stmt[0].get_type() == 'SELECT'
|
||||
with_stmt = sqlparse.parse('WITH foo AS (SELECT 1, 2, 3)'
|
||||
'SELECT * FROM foo;')
|
||||
assert with_stmt[0].get_type() == 'SELECT'
|
||||
with2_stmt = sqlparse.parse("""
|
||||
WITH foo AS (SELECT 1 AS abc, 2 AS def),
|
||||
bar AS (SELECT * FROM something WHERE x > 1)
|
||||
INSERT INTO elsewhere SELECT * FROM foo JOIN bar;""")
|
||||
assert with2_stmt[0].get_type() == 'INSERT'
|
||||
|
||||
|
||||
def test_issue207_runaway_format():
|
||||
sql = 'select 1 from (select 1 as one, 2 as two, 3 from dual) t0'
|
||||
p = sqlparse.format(sql, reindent=True)
|
||||
assert p == '\n'.join([
|
||||
"select 1",
|
||||
"from",
|
||||
" (select 1 as one,",
|
||||
" 2 as two,",
|
||||
" 3",
|
||||
" from dual) t0"])
|
||||
|
||||
|
||||
def test_token_next_doesnt_ignore_skip_cm():
|
||||
sql = '--comment\nselect 1'
|
||||
tok = sqlparse.parse(sql)[0].token_next(-1, skip_cm=True)[1]
|
||||
assert tok.value == 'select'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', [
|
||||
'SELECT x AS',
|
||||
'AS'
|
||||
])
|
||||
def test_issue284_as_grouping(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert s == str(p)
|
||||
|
||||
|
||||
def test_issue315_utf8_by_default():
|
||||
# Make sure the lexer can handle utf-8 string by default correctly
|
||||
# digest = '齐天大圣.カラフルな雲.사랑해요'
|
||||
# The digest contains Chinese, Japanese and Korean characters
|
||||
# All in 'utf-8' encoding.
|
||||
digest = (
|
||||
'\xe9\xbd\x90\xe5\xa4\xa9\xe5\xa4\xa7\xe5\x9c\xa3.'
|
||||
'\xe3\x82\xab\xe3\x83\xa9\xe3\x83\x95\xe3\x83\xab\xe3\x81\xaa\xe9'
|
||||
'\x9b\xb2.'
|
||||
'\xec\x82\xac\xeb\x9e\x91\xed\x95\xb4\xec\x9a\x94'
|
||||
)
|
||||
sql = "select * from foo where bar = '{0}'".format(digest)
|
||||
formatted = sqlparse.format(sql, reindent=True)
|
||||
tformatted = "select *\nfrom foo\nwhere bar = '{0}'".format(digest)
|
||||
if PY2:
|
||||
tformatted = tformatted.decode('utf-8')
|
||||
assert formatted == tformatted
|
||||
|
||||
|
||||
def test_issue322_concurrently_is_keyword():
|
||||
s = 'CREATE INDEX CONCURRENTLY myindex ON mytable(col1);'
|
||||
p = sqlparse.parse(s)[0]
|
||||
|
||||
assert len(p.tokens) == 12
|
||||
assert p.tokens[0].ttype is T.Keyword.DDL # CREATE
|
||||
assert p.tokens[2].ttype is T.Keyword # INDEX
|
||||
assert p.tokens[4].ttype is T.Keyword # CONCURRENTLY
|
||||
assert p.tokens[4].value == 'CONCURRENTLY'
|
||||
assert isinstance(p.tokens[6], sql.Identifier)
|
||||
assert p.tokens[6].value == 'myindex'
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', [
|
||||
'SELECT @min_price:=MIN(price), @max_price:=MAX(price) FROM shop;',
|
||||
'SELECT @min_price:=MIN(price), @max_price:=MAX(price) FROM shop',
|
||||
|
||||
])
|
||||
def test_issue359_index_error_assignments(s):
|
||||
sqlparse.parse(s)
|
||||
sqlparse.format(s, strip_comments=True)
|
||||
|
||||
|
||||
def test_issue469_copy_as_psql_command():
|
||||
formatted = sqlparse.format(
|
||||
'\\copy select * from foo',
|
||||
keyword_case='upper', identifier_case='capitalize')
|
||||
assert formatted == '\\copy SELECT * FROM Foo'
|
||||
|
||||
|
||||
@pytest.mark.xfail(reason='Needs to be fixed')
|
||||
def test_issue484_comments_and_newlines():
|
||||
formatted = sqlparse.format('\n'.join([
|
||||
'Create table myTable',
|
||||
'(',
|
||||
' myId TINYINT NOT NULL, --my special comment',
|
||||
' myName VARCHAR2(100) NOT NULL',
|
||||
')']),
|
||||
strip_comments=True)
|
||||
assert formatted == ('\n'.join([
|
||||
'Create table myTable',
|
||||
'(',
|
||||
' myId TINYINT NOT NULL,',
|
||||
' myName VARCHAR2(100) NOT NULL',
|
||||
')']))
|
||||
|
||||
|
||||
def test_issue485_split_multi():
|
||||
p_sql = '''CREATE OR REPLACE RULE ruled_tab_2rules AS ON INSERT
|
||||
TO public.ruled_tab
|
||||
DO instead (
|
||||
select 1;
|
||||
select 2;
|
||||
);'''
|
||||
assert len(sqlparse.split(p_sql)) == 1
|
||||
|
||||
|
||||
def test_issue489_tzcasts():
|
||||
p = sqlparse.parse('select bar at time zone \'UTC\' as foo')[0]
|
||||
assert p.tokens[-1].has_alias() is True
|
||||
assert p.tokens[-1].get_alias() == 'foo'
|
||||
151
shell/ext-py/sqlparse-0.3.1/tests/test_split.py
Normal file
151
shell/ext-py/sqlparse-0.3.1/tests/test_split.py
Normal file
@@ -0,0 +1,151 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Tests splitting functions.
|
||||
|
||||
import types
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse.compat import StringIO, text_type
|
||||
|
||||
|
||||
def test_split_semicolon():
|
||||
sql1 = 'select * from foo;'
|
||||
sql2 = "select * from foo where bar = 'foo;bar';"
|
||||
stmts = sqlparse.parse(''.join([sql1, sql2]))
|
||||
assert len(stmts) == 2
|
||||
assert str(stmts[0]) == sql1
|
||||
assert str(stmts[1]) == sql2
|
||||
|
||||
|
||||
def test_split_backslash():
|
||||
stmts = sqlparse.parse(r"select '\\'; select '\''; select '\\\'';")
|
||||
assert len(stmts) == 3
|
||||
|
||||
|
||||
@pytest.mark.parametrize('fn', ['function.sql',
|
||||
'function_psql.sql',
|
||||
'function_psql2.sql',
|
||||
'function_psql3.sql',
|
||||
'function_psql4.sql'])
|
||||
def test_split_create_function(load_file, fn):
|
||||
sql = load_file(fn)
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 1
|
||||
assert text_type(stmts[0]) == sql
|
||||
|
||||
|
||||
def test_split_dashcomments(load_file):
|
||||
sql = load_file('dashcomment.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 3
|
||||
assert ''.join(str(q) for q in stmts) == sql
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['select foo; -- comment\n',
|
||||
'select foo; -- comment\r',
|
||||
'select foo; -- comment\r\n',
|
||||
'select foo; -- comment'])
|
||||
def test_split_dashcomments_eol(s):
|
||||
stmts = sqlparse.parse(s)
|
||||
assert len(stmts) == 1
|
||||
|
||||
|
||||
def test_split_begintag(load_file):
|
||||
sql = load_file('begintag.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 3
|
||||
assert ''.join(str(q) for q in stmts) == sql
|
||||
|
||||
|
||||
def test_split_begintag_2(load_file):
|
||||
sql = load_file('begintag_2.sql')
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 1
|
||||
assert ''.join(str(q) for q in stmts) == sql
|
||||
|
||||
|
||||
def test_split_dropif():
|
||||
sql = 'DROP TABLE IF EXISTS FOO;\n\nSELECT * FROM BAR;'
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 2
|
||||
assert ''.join(str(q) for q in stmts) == sql
|
||||
|
||||
|
||||
def test_split_comment_with_umlaut():
|
||||
sql = (u'select * from foo;\n'
|
||||
u'-- Testing an umlaut: ä\n'
|
||||
u'select * from bar;')
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 2
|
||||
assert ''.join(text_type(q) for q in stmts) == sql
|
||||
|
||||
|
||||
def test_split_comment_end_of_line():
|
||||
sql = ('select * from foo; -- foo\n'
|
||||
'select * from bar;')
|
||||
stmts = sqlparse.parse(sql)
|
||||
assert len(stmts) == 2
|
||||
assert ''.join(str(q) for q in stmts) == sql
|
||||
# make sure the comment belongs to first query
|
||||
assert str(stmts[0]) == 'select * from foo; -- foo\n'
|
||||
|
||||
|
||||
def test_split_casewhen():
|
||||
sql = ("SELECT case when val = 1 then 2 else null end as foo;\n"
|
||||
"comment on table actor is 'The actor table.';")
|
||||
stmts = sqlparse.split(sql)
|
||||
assert len(stmts) == 2
|
||||
|
||||
|
||||
def test_split_cursor_declare():
|
||||
sql = ('DECLARE CURSOR "foo" AS SELECT 1;\n'
|
||||
'SELECT 2;')
|
||||
stmts = sqlparse.split(sql)
|
||||
assert len(stmts) == 2
|
||||
|
||||
|
||||
def test_split_if_function(): # see issue 33
|
||||
# don't let IF as a function confuse the splitter
|
||||
sql = ('CREATE TEMPORARY TABLE tmp '
|
||||
'SELECT IF(a=1, a, b) AS o FROM one; '
|
||||
'SELECT t FROM two')
|
||||
stmts = sqlparse.split(sql)
|
||||
assert len(stmts) == 2
|
||||
|
||||
|
||||
def test_split_stream():
|
||||
stream = StringIO("SELECT 1; SELECT 2;")
|
||||
stmts = sqlparse.parsestream(stream)
|
||||
assert isinstance(stmts, types.GeneratorType)
|
||||
assert len(list(stmts)) == 2
|
||||
|
||||
|
||||
def test_split_encoding_parsestream():
|
||||
stream = StringIO("SELECT 1; SELECT 2;")
|
||||
stmts = list(sqlparse.parsestream(stream))
|
||||
assert isinstance(stmts[0].tokens[0].value, text_type)
|
||||
|
||||
|
||||
def test_split_unicode_parsestream():
|
||||
stream = StringIO(u'SELECT ö')
|
||||
stmts = list(sqlparse.parsestream(stream))
|
||||
assert str(stmts[0]) == 'SELECT ö'
|
||||
|
||||
|
||||
def test_split_simple():
|
||||
stmts = sqlparse.split('select * from foo; select * from bar;')
|
||||
assert len(stmts) == 2
|
||||
assert stmts[0] == 'select * from foo;'
|
||||
assert stmts[1] == 'select * from bar;'
|
||||
|
||||
|
||||
def test_split_quotes_with_new_line():
|
||||
stmts = sqlparse.split('select "foo\nbar"')
|
||||
assert len(stmts) == 1
|
||||
assert stmts[0] == 'select "foo\nbar"'
|
||||
|
||||
stmts = sqlparse.split("select 'foo\n\bar'")
|
||||
assert len(stmts) == 1
|
||||
assert stmts[0] == "select 'foo\n\bar'"
|
||||
238
shell/ext-py/sqlparse-0.3.1/tests/test_tokenize.py
Normal file
238
shell/ext-py/sqlparse-0.3.1/tests/test_tokenize.py
Normal file
@@ -0,0 +1,238 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import types
|
||||
|
||||
import pytest
|
||||
|
||||
import sqlparse
|
||||
from sqlparse import lexer
|
||||
from sqlparse import sql, tokens as T
|
||||
from sqlparse.compat import StringIO
|
||||
|
||||
|
||||
def test_tokenize_simple():
|
||||
s = 'select * from foo;'
|
||||
stream = lexer.tokenize(s)
|
||||
assert isinstance(stream, types.GeneratorType)
|
||||
tokens = list(stream)
|
||||
assert len(tokens) == 8
|
||||
assert len(tokens[0]) == 2
|
||||
assert tokens[0] == (T.Keyword.DML, 'select')
|
||||
assert tokens[-1] == (T.Punctuation, ';')
|
||||
|
||||
|
||||
def test_tokenize_backticks():
|
||||
s = '`foo`.`bar`'
|
||||
tokens = list(lexer.tokenize(s))
|
||||
assert len(tokens) == 3
|
||||
assert tokens[0] == (T.Name, '`foo`')
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['foo\nbar\n', 'foo\rbar\r',
|
||||
'foo\r\nbar\r\n', 'foo\r\nbar\n'])
|
||||
def test_tokenize_linebreaks(s):
|
||||
# issue1
|
||||
tokens = lexer.tokenize(s)
|
||||
assert ''.join(str(x[1]) for x in tokens) == s
|
||||
|
||||
|
||||
def test_tokenize_inline_keywords():
|
||||
# issue 7
|
||||
s = "create created_foo"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
assert len(tokens) == 3
|
||||
assert tokens[0][0] == T.Keyword.DDL
|
||||
assert tokens[2][0] == T.Name
|
||||
assert tokens[2][1] == 'created_foo'
|
||||
s = "enddate"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
assert len(tokens) == 1
|
||||
assert tokens[0][0] == T.Name
|
||||
s = "join_col"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
assert len(tokens) == 1
|
||||
assert tokens[0][0] == T.Name
|
||||
s = "left join_col"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
assert len(tokens) == 3
|
||||
assert tokens[2][0] == T.Name
|
||||
assert tokens[2][1] == 'join_col'
|
||||
|
||||
|
||||
def test_tokenize_negative_numbers():
|
||||
s = "values(-1)"
|
||||
tokens = list(lexer.tokenize(s))
|
||||
assert len(tokens) == 4
|
||||
assert tokens[2][0] == T.Number.Integer
|
||||
assert tokens[2][1] == '-1'
|
||||
|
||||
|
||||
def test_token_str():
|
||||
token = sql.Token(None, 'FoO')
|
||||
assert str(token) == 'FoO'
|
||||
|
||||
|
||||
def test_token_repr():
|
||||
token = sql.Token(T.Keyword, 'foo')
|
||||
tst = "<Keyword 'foo' at 0x"
|
||||
assert repr(token)[:len(tst)] == tst
|
||||
token = sql.Token(T.Keyword, '1234567890')
|
||||
tst = "<Keyword '123456...' at 0x"
|
||||
assert repr(token)[:len(tst)] == tst
|
||||
|
||||
|
||||
def test_token_flatten():
|
||||
token = sql.Token(T.Keyword, 'foo')
|
||||
gen = token.flatten()
|
||||
assert isinstance(gen, types.GeneratorType)
|
||||
lgen = list(gen)
|
||||
assert lgen == [token]
|
||||
|
||||
|
||||
def test_tokenlist_repr():
|
||||
p = sqlparse.parse('foo, bar, baz')[0]
|
||||
tst = "<IdentifierList 'foo, b...' at 0x"
|
||||
assert repr(p.tokens[0])[:len(tst)] == tst
|
||||
|
||||
|
||||
def test_single_quotes():
|
||||
p = sqlparse.parse("'test'")[0]
|
||||
tst = "<Single \"'test'\" at 0x"
|
||||
assert repr(p.tokens[0])[:len(tst)] == tst
|
||||
|
||||
|
||||
def test_tokenlist_first():
|
||||
p = sqlparse.parse(' select foo')[0]
|
||||
first = p.token_first()
|
||||
assert first.value == 'select'
|
||||
assert p.token_first(skip_ws=False).value == ' '
|
||||
assert sql.TokenList([]).token_first() is None
|
||||
|
||||
|
||||
def test_tokenlist_token_matching():
|
||||
t1 = sql.Token(T.Keyword, 'foo')
|
||||
t2 = sql.Token(T.Punctuation, ',')
|
||||
x = sql.TokenList([t1, t2])
|
||||
assert x.token_matching([lambda t: t.ttype is T.Keyword], 0) == t1
|
||||
assert x.token_matching([lambda t: t.ttype is T.Punctuation], 0) == t2
|
||||
assert x.token_matching([lambda t: t.ttype is T.Keyword], 1) is None
|
||||
|
||||
|
||||
def test_stream_simple():
|
||||
stream = StringIO("SELECT 1; SELECT 2;")
|
||||
|
||||
tokens = lexer.tokenize(stream)
|
||||
assert len(list(tokens)) == 9
|
||||
|
||||
stream.seek(0)
|
||||
tokens = list(lexer.tokenize(stream))
|
||||
assert len(tokens) == 9
|
||||
|
||||
stream.seek(0)
|
||||
tokens = list(lexer.tokenize(stream))
|
||||
assert len(tokens) == 9
|
||||
|
||||
|
||||
def test_stream_error():
|
||||
stream = StringIO("FOOBAR{")
|
||||
|
||||
tokens = list(lexer.tokenize(stream))
|
||||
assert len(tokens) == 2
|
||||
assert tokens[1][0] == T.Error
|
||||
|
||||
|
||||
@pytest.mark.parametrize('expr', [
|
||||
'JOIN',
|
||||
'LEFT JOIN',
|
||||
'LEFT OUTER JOIN',
|
||||
'FULL OUTER JOIN',
|
||||
'NATURAL JOIN',
|
||||
'CROSS JOIN',
|
||||
'STRAIGHT JOIN',
|
||||
'INNER JOIN',
|
||||
'LEFT INNER JOIN'])
|
||||
def test_parse_join(expr):
|
||||
p = sqlparse.parse('{0} foo'.format(expr))[0]
|
||||
assert len(p.tokens) == 3
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
|
||||
|
||||
def test_parse_union(): # issue294
|
||||
p = sqlparse.parse('UNION ALL')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['END IF', 'END IF', 'END\t\nIF',
|
||||
'END LOOP', 'END LOOP', 'END\t\nLOOP'])
|
||||
def test_parse_endifloop(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', ['NULLS FIRST', 'NULLS LAST'])
|
||||
def test_parse_nulls(s): # issue487
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', [
|
||||
'foo',
|
||||
'Foo',
|
||||
'FOO',
|
||||
'v$name', # issue291
|
||||
])
|
||||
def test_parse_identifiers(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
token = p.tokens[0]
|
||||
assert str(token) == s
|
||||
assert isinstance(token, sql.Identifier)
|
||||
|
||||
|
||||
def test_parse_group_by():
|
||||
p = sqlparse.parse('GROUP BY')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
|
||||
|
||||
def test_parse_order_by():
|
||||
p = sqlparse.parse('ORDER BY')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype is T.Keyword
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', (
|
||||
"LIKE", "ILIKE", "NOT LIKE", "NOT ILIKE",
|
||||
"NOT LIKE", "NOT ILIKE",
|
||||
))
|
||||
def test_like_and_ilike_parsed_as_comparisons(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype == T.Operator.Comparison
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', (
|
||||
"LIKEaaa", "bILIKE", "aaILIKEbb", "NOTLIKE", "NOTILIKE",
|
||||
))
|
||||
def test_near_like_and_ilike_parsed_appropriately(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert isinstance(p.tokens[0], sql.Identifier)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('s', (
|
||||
'AT TIME ZONE \'UTC\'',
|
||||
))
|
||||
def test_parse_tzcast(s):
|
||||
p = sqlparse.parse(s)[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype == T.Keyword.TZCast
|
||||
|
||||
|
||||
def test_cli_commands():
|
||||
p = sqlparse.parse('\\copy')[0]
|
||||
assert len(p.tokens) == 1
|
||||
assert p.tokens[0].ttype == T.Command
|
||||
28
shell/ext-py/sqlparse-0.3.1/tox.ini
Normal file
28
shell/ext-py/sqlparse-0.3.1/tox.ini
Normal file
@@ -0,0 +1,28 @@
|
||||
[tox]
|
||||
skip_missing_interpreters = True
|
||||
envlist =
|
||||
py27
|
||||
py34
|
||||
py35
|
||||
py36
|
||||
py37
|
||||
py38
|
||||
pypy_54
|
||||
flake8
|
||||
|
||||
[testenv]
|
||||
deps =
|
||||
pytest
|
||||
pytest-cov
|
||||
pytest-travis-fold
|
||||
passenv =
|
||||
TRAVIS
|
||||
commands =
|
||||
sqlformat --version
|
||||
pytest --cov=sqlparse {posargs}
|
||||
|
||||
[testenv:flake8]
|
||||
deps =
|
||||
flake8
|
||||
commands =
|
||||
flake8 sqlparse tests setup.py
|
||||
@@ -1434,35 +1434,57 @@ class ImpalaShell(object, cmd.Cmd):
|
||||
command: select
|
||||
leading comment: /*first comment*/
|
||||
"""
|
||||
if ImpalaShell._has_leading_comment(line):
|
||||
leading_comment, line = ImpalaShell.strip_leading_comment(line.strip())
|
||||
line = line.encode('utf-8')
|
||||
if leading_comment:
|
||||
leading_comment = leading_comment.encode('utf-8')
|
||||
else:
|
||||
leading_comment, line = None, line.strip()
|
||||
if line and line[0] == '@':
|
||||
line = 'rerun ' + line[1:]
|
||||
return super(ImpalaShell, self).parseline(line) + (leading_comment,)
|
||||
|
||||
@staticmethod
|
||||
def _has_leading_comment(raw_line):
|
||||
"""
|
||||
Helper function that returns Boolean true if a query starts with a comment.
|
||||
This saves us from relying on sqlparse filtering, which can be slow.
|
||||
"""
|
||||
line = raw_line.lstrip()
|
||||
if line and (line.startswith('--') or line.startswith('/*')):
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def strip_leading_comment(sql):
|
||||
"""
|
||||
Filter a leading comment in the SQL statement. This function returns a tuple
|
||||
containing (leading comment, line without the leading comment).
|
||||
"""
|
||||
class StripLeadingCommentFilter:
|
||||
class StripLeadingCommentFilter(object):
|
||||
def __init__(self):
|
||||
self.comment = None
|
||||
|
||||
def _process(self, tlist):
|
||||
"""
|
||||
Iterate through the list of tokens, appending each leading commment
|
||||
to self.comment, and then popping that element off the list. When we
|
||||
hit the first non-comment and non-whitespace token, then we're done --
|
||||
the remainder after that point is the SQL statement.
|
||||
"""
|
||||
token = tlist.token_first()
|
||||
if self._is_comment(token):
|
||||
self.comment = ''
|
||||
while token:
|
||||
if self._is_comment(token) or self._is_whitespace(token):
|
||||
tidx = tlist.token_index(token)
|
||||
if self.comment is None:
|
||||
self.comment = token.value
|
||||
else:
|
||||
self.comment += token.value
|
||||
tlist.tokens.pop(tidx)
|
||||
tidx -= 1
|
||||
token = tlist.token_next(tidx, False)
|
||||
tlist.tokens.pop(0)
|
||||
|
||||
# skip_ws=False treats white space characters as tokens also
|
||||
token = tlist.token_first(skip_ws=False)
|
||||
else:
|
||||
break
|
||||
|
||||
@@ -1475,8 +1497,8 @@ class ImpalaShell(object, cmd.Cmd):
|
||||
return token.ttype == sqlparse.tokens.Whitespace or \
|
||||
token.ttype == sqlparse.tokens.Newline
|
||||
|
||||
def process(self, stack, stmt):
|
||||
[self.process(stack, sgroup) for sgroup in stmt.get_sublists()]
|
||||
def process(self, stmt):
|
||||
[self.process(sgroup) for sgroup in stmt.get_sublists()]
|
||||
self._process(stmt)
|
||||
|
||||
stack = sqlparse.engine.FilterStack()
|
||||
|
||||
@@ -3,6 +3,6 @@ prettytable==0.7.1
|
||||
sasl==0.2.1
|
||||
setuptools>=36.8.0
|
||||
six==1.14.0
|
||||
sqlparse==0.1.19
|
||||
sqlparse==0.3.1
|
||||
thrift==0.9.3
|
||||
thrift_sasl==0.4.2
|
||||
|
||||
@@ -134,8 +134,6 @@ class TestImpalaShell(ImpalaTestSuite):
|
||||
|
||||
def test_multiple_queries_with_escaped_backslash(self, vector):
|
||||
"""Regression test for string containing an escaped backslash.
|
||||
|
||||
This relies on the patch at thirdparty/patches/sqlparse/0001-....patch.
|
||||
"""
|
||||
run_impala_shell_cmd(vector, ['-q', r'''select '\\'; select '\'';''', '-B'])
|
||||
|
||||
|
||||
Reference in New Issue
Block a user