def test_determine_doc_number_annual(self, fetch_notice_json):
"""The _latest_ document number pre-effective date should be pulled
out of an annual edition of the reg"""
fetch_notice_json.return_value = [
{'document_number': '111-111', 'effective_on': '2011-01-01',
'publication_date': '2011-01-01'},
{'document_number': '222-222', 'effective_on': '2011-10-20',
'publication_date': '2011-02-02'},
{'document_number': '333-333', 'effective_on': '2011-10-20',
'publication_date': '2011-03-03'},
{'document_number': '444-444', 'effective_on': '2011-04-04',
'publication_date': '2011-04-04'}]
xml_str = """<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="cfr.xsl"?>
<CFRGRANULE xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="CFRMergedXML.xsd">
<FDSYS>
<CFRTITLE>12</CFRTITLE>
<DATE>2013-01-01</DATE>
<ORIGINALDATE>2012-01-01</ORIGINALDATE>
</FDSYS>
</CFRGRANULE>"""
xml = etree.fromstring(xml_str)
self.assertEqual(
'333-333', Builder.determine_doc_number(xml, '12', '34'))
args = fetch_notice_json.call_args
self.assertEqual(('12', '34'), args[0]) # positional args
self.assertEqual({'max_effective_date': '2012-01-01',
'only_final': True}, args[1]) # kw args
def test_determine_doc_number_annual(self, fetch_notice_json):
"""Verify that a document number can be pulled out of an annual
edition of the reg"""
fetch_notice_json.return_value = [{
'el': 1,
'document_number': '111-111'
}, {
'el': 2,
'document_number': '222-222'
}]
xml_str = """<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="cfr.xsl"?>
<CFRGRANULE xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="CFRMergedXML.xsd">
<FDSYS>
<CFRTITLE>12</CFRTITLE>
<DATE>2013-01-01</DATE>
<ORIGINALDATE>2012-01-01</ORIGINALDATE>
</FDSYS>
</CFRGRANULE>"""
self.assertEqual('111-111',
Builder.determine_doc_number(xml_str, '12', '34'))
args = fetch_notice_json.call_args
self.assertEqual(('12', '34'), args[0]) # positional args
self.assertEqual(
{
'max_effective_date': '2012-01-01',
'only_final': True
}, args[1]) # kw args
def test_determine_doc_number_fr(self):
"""Verify that a document number can be pulled out of an FR notice"""
xml_str = """
<RULE>
<FRDOC>[FR Doc. 2011-31715 Filed 12-21-11; 8:45 am]</FRDOC>
<BILCOD>BILLING CODE 4810-AM-P</BILCOD>
</RULE>"""
self.assertEqual('2011-31715',
Builder.determine_doc_number(xml_str, '00', '00'))
def test_determine_doc_number_fr(self):
"""Verify that a document number can be pulled out of an FR notice"""
xml_str = """
<RULE>
<FRDOC>[FR Doc. 2011-31715 Filed 12-21-11; 8:45 am]</FRDOC>
<BILCOD>BILLING CODE 4810-AM-P</BILCOD>
</RULE>"""
self.assertEqual(
'2011-31715', Builder.determine_doc_number(xml_str, '00', '00'))
def build_by_notice(filename,
title,
act_title,
act_section,
notice_doc_numbers,
doc_number=None,
checkpoint=None):
with codecs.open(filename, 'r', 'utf-8') as f:
reg = f.read()
file_digest = hashlib.sha256(reg.encode('utf-8')).hexdigest()
if checkpoint:
checkpointer = Checkpointer(checkpoint)
else:
checkpointer = NullCheckpointer()
# build the initial tree
reg_tree = checkpointer.checkpoint("init-tree-" + file_digest,
lambda: Builder.reg_tree(reg))
title_part = reg_tree.label_id()
if doc_number is None:
doc_number = Builder.determine_doc_number(reg, title, title_part)
checkpointer.suffix = ":".join(
["", title_part, str(args.title), doc_number])
# create the builder
builder = Builder(cfr_title=title,
cfr_part=title_part,
doc_number=doc_number,
checkpointer=checkpointer)
builder.fetch_notices_json()
for notice in notice_doc_numbers:
builder.build_notice_from_doc_number(notice)
builder.write_regulation(reg_tree)
layer_cache = LayerCacheAggregator()
act_title_and_section = [act_title, act_section]
builder.gen_and_write_layers(reg_tree, act_title_and_section, layer_cache)
layer_cache.replace_using(reg_tree)
if args.generate_diffs:
generate_diffs(reg_tree, act_title_and_section, builder, layer_cache)
def build_by_notice(filename, title, act_title, act_section,
notice_doc_numbers, doc_number=None, checkpoint=None):
with codecs.open(filename, 'r', 'utf-8') as f:
reg = f.read()
file_digest = hashlib.sha256(reg.encode('utf-8')).hexdigest()
if checkpoint:
checkpointer = Checkpointer(checkpoint)
else:
checkpointer = NullCheckpointer()
# build the initial tree
reg_tree = checkpointer.checkpoint(
"init-tree-" + file_digest,
lambda: Builder.reg_tree(reg))
title_part = reg_tree.label_id()
if doc_number is None:
doc_number = Builder.determine_doc_number(reg, title, title_part)
checkpointer.suffix = ":".join(
["", title_part, str(args.title), doc_number])
# create the builder
builder = Builder(cfr_title=title,
cfr_part=title_part,
doc_number=doc_number,
checkpointer=checkpointer)
builder.fetch_notices_json()
for notice in notice_doc_numbers:
builder.build_notice_from_doc_number(notice)
builder.write_regulation(reg_tree)
layer_cache = LayerCacheAggregator()
act_title_and_section = [act_title, act_section]
builder.gen_and_write_layers(reg_tree, act_title_and_section, layer_cache)
layer_cache.replace_using(reg_tree)
if args.generate_diffs:
generate_diffs(reg_tree, act_title_and_section, builder, layer_cache)
def parse_regulation(args):
""" Run the parser on the specified command-line arguments. Broken out into
separate function to assist in profiling.
"""
with codecs.open(args.filename, 'r', 'utf-8') as f:
reg = f.read()
file_digest = hashlib.sha256(reg.encode('utf-8')).hexdigest()
act_title_and_section = [args.act_title, args.act_section]
if args.checkpoint:
checkpointer = Checkpointer(args.checkpoint)
else:
checkpointer = NullCheckpointer()
# First, the regulation tree
reg_tree = checkpointer.checkpoint(
"init-tree-" + file_digest,
lambda: Builder.reg_tree(reg))
title_part = reg_tree.label_id()
doc_number = checkpointer.checkpoint(
"doc-number-" + file_digest,
lambda: Builder.determine_doc_number(reg, args.title, title_part))
if not doc_number:
raise ValueError("Could not determine document number")
checkpointer.suffix = ":".join(
["", title_part, str(args.title), doc_number])
# Run Builder
builder = Builder(cfr_title=args.title,
cfr_part=title_part,
doc_number=doc_number,
checkpointer=checkpointer)
builder.write_notices()
# Always do at least the first reg
logger.info("Version %s", doc_number)
builder.write_regulation(reg_tree)
layer_cache = LayerCacheAggregator()
builder.gen_and_write_layers(reg_tree, act_title_and_section, layer_cache)
layer_cache.replace_using(reg_tree)
if args.generate_diffs:
generate_diffs(doc_number, reg_tree, act_title_and_section,
builder, layer_cache, checkpointer)
def test_determine_doc_number_annual(self, fetch_notice_json):
"""Verify that a document number can be pulled out of an annual
edition of the reg"""
fetch_notice_json.return_value = [
{'el': 1, 'document_number': '111-111'},
{'el': 2, 'document_number': '222-222'}]
xml_str = """<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="cfr.xsl"?>
<CFRGRANULE xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:noNamespaceSchemaLocation="CFRMergedXML.xsd">
<FDSYS>
<CFRTITLE>12</CFRTITLE>
<DATE>2013-01-01</DATE>
<ORIGINALDATE>2012-01-01</ORIGINALDATE>
</FDSYS>
</CFRGRANULE>"""
self.assertEqual(
'111-111', Builder.determine_doc_number(xml_str, '12', '34'))
args = fetch_notice_json.call_args
self.assertEqual(('12', '34'), args[0]) # positional args
self.assertEqual({'max_effective_date': '2012-01-01',
'only_final': True}, args[1]) # kw args
file_digest = hashlib.sha256(reg.encode('utf-8')).hexdigest()
act_title_and_section = [args.act_title, args.act_section]
if args.checkpoint:
checkpointer = Checkpointer(args.checkpoint)
else:
checkpointer = NullCheckpointer()
# First, the regulation tree
reg_tree = checkpointer.checkpoint(
"init-tree-" + file_digest,
lambda: Builder.reg_tree(reg))
title_part = reg_tree.label_id()
doc_number = checkpointer.checkpoint(
"doc-number-" + file_digest,
lambda: Builder.determine_doc_number(reg, args.title, title_part))
if not doc_number:
raise ValueError("Could not determine document number")
checkpointer.suffix = ":".join(
["", title_part, str(args.title), doc_number])
# Run Builder
builder = Builder(cfr_title=args.title,
cfr_part=title_part,
doc_number=doc_number,
checkpointer=checkpointer)
builder.write_notices()
# Always do at least the first reg
logger.info("Version %s", doc_number)
builder.write_regulation(reg_tree)
