def build_from(filename, title, act_title, act_section, generate_diffs,
checkpoint, version_identifier):
"""Build all data from provided xml. Reads the provided file and builds
all versions of the regulation, its layers, etc. that follow.
\b
FILENAME: XML file containing the regulation
TITLE: CFR title
"""
act_title_and_section = [act_title, act_section]
# First, the regulation tree
reg_tree, builder = tree_and_builder(filename, title, checkpoint,
version_identifier)
builder.write_notices()
# Always do at least the first reg
logger.info("Version %s", builder.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 generate_diffs:
gen_diffs(reg_tree, act_title_and_section, builder, layer_cache)
def ecfr_all(title, file, act_title, act_section,
with_all_versions=False, without_versions=False,
without_notices=False, only_notice=None):
""" Parse eCFR into RegML """
# Get the tree and layers
reg_tree, builder = tree_and_builder(
file, title, writer_type='XML')
layer_cache = LayerCacheAggregator()
layers = builder.generate_layers(reg_tree,
[act_title, act_section],
layer_cache)
# Do the first version
last_version = builder.doc_number
print("Version {}".format(last_version))
if (only_notice is not None and builder.doc_number == only_notice) \
or only_notice is None:
if not without_versions:
builder.write_regulation(reg_tree, layers=layers)
for last_notice, old, new_tree, notices in builder.revision_generator(
reg_tree):
version = last_notice['document_number']
print("Version {}".format(version))
builder.doc_number = version
layers = builder.generate_layers(new_tree,
[act_title, act_section],
layer_cache,
notices)
if (only_notice is not None and version == only_notice) or \
only_notice is None:
if with_all_versions:
builder.write_regulation(new_tree, layers=layers)
if not without_notices:
builder.write_notice(version,
old_tree=old,
reg_tree=new_tree,
layers=layers,
last_version=last_version)
layer_cache.invalidate_by_notice(last_notice)
layer_cache.replace_using(new_tree)
last_version = version
del last_notice, old, new_tree, notices # free some memory
def parse_regulation(args):
""" Run the parser on the specified command-line arguments. Broken out
into separate function to assist in profiling.
"""
act_title_and_section = [args.act_title, args.act_section]
# First, the regulation tree
reg_tree, builder = tree_and_builder(args.filename, args.title,
args.checkpoint_dir, args.doc_number)
builder.write_notices()
# Always do at least the first reg
logger.info("Version %s", builder.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(reg_tree, act_title_and_section, builder, layer_cache)
def watch_node(node_label, filename, title):
"""Follow changes to a particular label.
\b
NODE_LABEL: Label for the node you wish to watch. e.g. 1026-5-a
FILENAME: XML file containing the regulation
TITLE: Title number"""
initial_tree, builder = tree_and_builder(filename, title)
initial_node = find(initial_tree, node_label)
if initial_node:
click.echo("> " + builder.doc_number)
click.echo("\t" + pretty_change(
{'action': 'POST', 'node': node_to_dict(initial_node)}))
# search for label
for version, changes in builder.changes_in_sequence():
if node_label in changes:
click.echo("> " + version)
for change in changes[node_label]:
click.echo("\t" + pretty_change(change))
def generate_xml(filename,
title,
act_title,
act_section,
notice_doc_numbers,
doc_number=None,
checkpoint=None):
act_title_and_section = [act_title, act_section]
# First, the regulation tree
reg_tree, builder = tree_and_builder(filename,
title,
checkpoint,
writer_type='XML')
layer_cache = LayerCacheAggregator()
layers = builder.generate_layers(reg_tree, act_title_and_section,
layer_cache)
# Always do at least the first reg
logger.info("Version", builder.doc_number)
builder.write_regulation(reg_tree, layers=layers)
all_versions = {doc_number: FrozenNode.from_node(reg_tree)}
for last_notice, old, new_tree, notices in builder.revision_generator(
reg_tree):
version = last_notice['document_number']
logger.info("Version %s", version)
all_versions[version] = FrozenNode.from_node(new_tree)
builder.doc_number = version
layers = builder.generate_layers(new_tree, act_title_and_section,
layer_cache, notices)
builder.write_regulation(new_tree, layers=layers)
builder.write_notice(version,
old_tree=old,
reg_tree=new_tree,
layers=layers)
layer_cache.invalidate_by_notice(last_notice)
layer_cache.replace_using(new_tree)
del last_notice, old, new_tree, notices # free some memory
def parse_regulation(args):
""" Run the parser on the specified command-line arguments. Broken out
into separate function to assist in profiling.
"""
act_title_and_section = [args.act_title, args.act_section]
# First, the regulation tree
reg_tree, builder = tree_and_builder(args.filename, args.title,
args.checkpoint)
builder.write_notices()
# Always do at least the first reg
logger.info("Version %s", builder.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(reg_tree, act_title_and_section, builder, layer_cache)
def watch_node(node_label, filename, title):
"""Follow changes to a particular label.
\b
NODE_LABEL: Label for the node you wish to watch. e.g. 1026-5-a
FILENAME: XML file containing the regulation
TITLE: Title number"""
initial_tree, builder = tree_and_builder(filename, title)
initial_node = find(initial_tree, node_label)
if initial_node:
click.echo("> " + builder.doc_number)
click.echo("\t" + pretty_change({
'action': 'POST',
'node': node_to_dict(initial_node)
}))
# search for label
for version, changes in builder.changes_in_sequence():
if node_label in changes:
click.echo("> " + version)
for change in changes[node_label]:
click.echo("\t" + pretty_change(change))
pass
from regparser.builder import tree_and_builder
from regparser.notice.changes import node_to_dict, pretty_change
from regparser.tree.struct import find
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Node Watcher")
parser.add_argument(
'node_label',
help='Label for the node you wish to watch. e.g. 1026-5-a')
parser.add_argument('filename',
help='XML file containing the regulation')
parser.add_argument('title', type=int, help='Title number')
args = parser.parse_args()
initial_tree, builder = tree_and_builder(args.filename, args.title)
initial_node = find(initial_tree, args.node_label)
if initial_node:
print("> " + builder.doc_number)
print("\t" + pretty_change(
{'action': 'POST', 'node': node_to_dict(initial_node)}))
# search for label
for version, changes in builder.changes_in_sequence():
if args.node_label in changes:
print("> " + version)
for change in changes[args.node_label]:
print("\t" + pretty_change(change))
pass
from regparser.builder import tree_and_builder
from regparser.notice.changes import node_to_dict, pretty_change
from regparser.tree.struct import find
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Node Watcher")
parser.add_argument(
'node_label',
help='Label for the node you wish to watch. e.g. 1026-5-a')
parser.add_argument('filename', help='XML file containing the regulation')
parser.add_argument('title', type=int, help='Title number')
args = parser.parse_args()
initial_tree, builder = tree_and_builder(args.filename, args.title)
initial_node = find(initial_tree, args.node_label)
if initial_node:
print("> " + builder.doc_number)
print("\t" + pretty_change({
'action': 'POST',
'node': node_to_dict(initial_node)
}))
# search for label
for version, changes in builder.changes_in_sequence():
if args.node_label in changes:
print("> " + version)
for change in changes[args.node_label]:
print("\t" + pretty_change(change))