jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2025-12-25 02:03:09 -05:00
Code Issues Projects Releases Wiki Activity

Fix parquet test setup.

Browse Source
This commit is contained in:
Nong Li
2013-04-11 21:56:28 -07:00
committed by Henry Robinson
parent 189575f23f
commit 1f6481382e
6 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
be/src/exec/hdfs-table-sink.h
View File

@@ -130,7 +130,7 @@ class HdfsTableSink : public DataSink {
// Get the block size of the current file opened for this partition.
// This is a utility routine that can be called by specific table
// writers. Currently used by the Trevni writer.
// writers. Currently used by the parquet writer.
static Status GetFileBlockSize(OutputPartition* output_partition, int64_t* size);
virtual RuntimeProfile* profile() { return runtime_profile_; }

2
be/src/exec/read-write-util.h
View File

@@ -25,7 +25,7 @@ namespace impala {
#define RETURN_IF_FALSE(x) if (UNLIKELY(!(x))) return false
// Class for reading and writing various data types supported by Trevni and Avro.
// Class for reading and writing various data types.
class ReadWriteUtil {
public:
// Maximum length for Writeable VInt

2
be/src/exec/scanner-context.inline.h
View File

@@ -25,7 +25,7 @@ using namespace impala;
#define RETURN_IF_FALSE(x) if (UNLIKELY(!(x))) return false
// Handle the fast common path where all the bytes are in the first buffer. This
// is the path used by sequence/rc/trevni file formats to read a very small number
// is the path used by sequence/rc/parquet file formats to read a very small number
// (i.e. single int) of bytes.
inline bool ScannerContext::Stream::GetBytes(int requested_len, uint8_t** buffer,
int* out_len, bool* eos, Status* status) {

3
bin/load-data.py
View File

@@ -2,7 +2,8 @@
# Copyright (c) 2012 Cloudera, Inc. All rights reserved.
#
# This script is used to load the proper datasets for the specified workloads. It loads
# all data via Hive except for Trevni data which needs to be loaded via Impala.
# all data via Hive except for parquet data which needs to be loaded via Impala.
# Most ddl commands are executed by Impala.
import collections
import os
import re

2
common/thrift/Descriptors.thrift
View File

@@ -54,7 +54,7 @@ enum THdfsCompression {
SNAPPY_BLOCKED // Used by sequence and rc files but not stored in the metadata.
}
// Mapping from names defined by Trevni to the enum.
// Mapping from names defined by Avro to the enum.
// We permit gzip and bzip2 in addition.
const map<string, THdfsCompression> COMPRESSION_MAP = {
"": THdfsCompression.NONE,

2
tests/query_test/test_queries.py
View File

@@ -57,7 +57,7 @@ class TestQueries(ImpalaTestSuite):
table_format = vector.get_value('table_format')
# TODO: Skip these vector combinations due to IMP-624, IMP-503
if table_format.file_format in ['trevni', 'rc'] or\
if table_format.file_format in ['parquet', 'rc'] or\
(table_format.file_format == 'seq' and table_format.compression_codec == 'none'):
return
self.run_test_case('QueryTest/misc', vector)