jprdonnelly/congress
1
0
Fork 0
mirror of https://github.com/unitedstates/congress.git synced 2025-12-23 20:00:01 -05:00
Code Issues Packages Projects Releases Wiki Activity

when parsing committees out of action line text, avoid warnings in cases where it's clearly not a committee reference

Browse Source
This commit is contained in:
Joshua Tauberer
2014-12-10 12:49:41 -05:00
parent 305dd8fd1d
commit ad92e1b63b
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tasks/bill_info.py
View File

@@ -1487,7 +1487,14 @@ def parse_bill_action(action_dict, prev_status, bill_id, title):
cmte_names.append(name)
cmte_reg = r"(House|Senate)?\s*(?:Committee)?\s*(?:on)?\s*(?:the)?\s*({0})".format("|".join(cmte_names))
m = re.search(cmte_reg, line, re.I)
# "Rules" occurs often in "suspend the rules" not referring to a committee, so
# wipe that out so that it doesn't get picked up as House Rules and subsequently
# generate an error for not, in lowercase?, actually matching a committee name.
# Likewise for "budgetary" triggering the budget committees.
line_for_cmte_reg = line.replace("suspend the rules", "XXX").replace("suspension of the rules", "XXX").replace("closed rule", "XXX")\
.replace("budgetary", "XXX")
m = re.search(cmte_reg, line_for_cmte_reg, re.I)
if m:
committees = []
chamber = m.groups()[0] # optional match