def __init__(self, anthology=None, anthology_dir=None):
# counts of how often each name appears
self.first_count = defaultdict(lambda: 0) # "Maria" "Victoria"
self.first_full_count = defaultdict(lambda: 0) # "Maria Victoria"
self.last_count = defaultdict(lambda: 0) # "van" "den" "Bosch"
self.last_full_count = defaultdict(lambda: 0) # "van den Bosch"
self.first_total = 0
self.last_total = 0
if os.path.exists("names.cache"):
self.load_cache()
else:
if anthology is None and anthology_dir is not None:
anthology = Anthology(os.path.join(anthology_dir, "data"))
self.count_names(anthology)
self.dump_cache()
for first_letter, people_list in people.items():
with open("{}/people/{}.yaml".format(outdir, first_letter),
"w") as f:
yaml.dump(people_list, Dumper=Dumper, stream=f)
progress.update()
progress.close()
if __name__ == "__main__":
args = docopt(__doc__)
scriptdir = os.path.dirname(os.path.abspath(__file__))
if "{scriptdir}" in args["--importdir"]:
args["--importdir"] = os.path.abspath(
args["--importdir"].format(scriptdir=scriptdir))
if "{scriptdir}" in args["--exportdir"]:
args["--exportdir"] = os.path.abspath(
args["--exportdir"].format(scriptdir=scriptdir))
log_level = log.DEBUG if args["--debug"] else log.INFO
log.basicConfig(format="%(levelname)-8s %(message)s", level=log_level)
tracker = SeverityTracker()
log.getLogger().addHandler(tracker)
log.info("Reading the Anthology data...")
anthology = Anthology(importdir=args["--importdir"])
log.info("Exporting to YAML...")
export_anthology(anthology, args["--exportdir"], dryrun=args["--dry-run"])
if tracker.highest >= log.ERROR:
exit(1)
def main(args):
scriptdir = os.path.join(os.path.dirname(os.path.abspath(__file__)), '..',
'data')
anthology = Anthology(importdir=scriptdir)
attachments = defaultdict(list)
revisions = []
errata = []
for line in sys.stdin:
if not line.startswith("+"):
continue
line = line[1:].strip()
if line.startswith("<attachment"):
try:
match_str = rf'<attachment type="(\w+)">({ANTHOLOGY_ID_REGEX}).*'
match = re.match(match_str, line)
attach_type, anthology_id = match.groups()
except:
print(f"* Couldn't match '{match_str}' to '{line}'",
file=sys.stderr)
attachments[attach_type].append((
anthology.papers[anthology_id].get_title('plain'),
ANTHOLOGY_URL.format(anthology_id),
))
elif line.startswith("<revision"):
try:
match_str = rf'<revision.*href="({ANTHOLOGY_ID_REGEX}).*>.*'
match = re.match(match_str, line)
anthology_id = match.group(1)
except:
print(f"* Couldn't match '{match_str}' to '{line}'",
file=sys.stderr)
paper = anthology.papers[anthology_id]
explanation = paper.attrib["revision"][-1]["explanation"]
revisions.append((
paper.get_title("plain"),
ANTHOLOGY_URL.format(anthology_id),
explanation,
))
elif line.startswith("<errat"):
try:
match_str = rf"<errat.*?>({ANTHOLOGY_ID_REGEX}).*"
match = re.match(match_str, line)
anthology_id = match.group(1)
except:
print(f"* Couldn't match '{match_str}' to '{line}'",
file=sys.stderr)
errata.append((
anthology.papers[anthology_id].get_title('plain'),
ANTHOLOGY_URL.format(anthology_id),
))
inflector = inflect.engine()
for attach_type, attachments in attachments.items():
phrase = inflector.a(attach_type)
print(f"\nAdded {phrase}:")
for title, url in attachments:
print("-", title, "\n ", url, "\n")
if len(revisions):
print(f"\nRevisions:")
for title, url, explanation in revisions:
print("-", title, "\n ", url, "\n ", explanation, "\n")
if len(errata):
print(f"\nErrata:")
for title, url in errata:
print("-", title, "\n ", url, "\n")
def checkVideo(paper):
for elem in paper.attachments:
if elem["type"] == "video":
return True
return False
args = docopt(__doc__)
fromYear = int(args["--from-year"])
cacheVimeo = args["--cache-vimeo"]
cacheMatchings = args["--cache-matchings"]
v = vimeo.VimeoClient(token=personalAccessToken, key=clientId, secret=apiSecret)
allpapers = Anthology(importdir="../data/").papers
print("number of papers in anthology: ", len(allpapers))
papers = {k: v for k, v in allpapers.items() if int(v.attrib["year"]) > fromYear}
print(
"number of papers in anthology without video after " + str(fromYear) + ": ",
len(papers),
)
requestUrl = "/users/46432367/videos?per_page=100"
cont = True
nameUrls = {}
numRequests = 0
contents = paper.as_bibtex()
print(contents, file=file_paper)
print(contents, file=file_anthology_with_abstracts)
concise_contents = paper.as_bibtex(concise=True)
print(concise_contents, file=file_volume)
print(concise_contents, file=file_anthology)
print(concise_contents, file=file_anthology_raw)
if __name__ == "__main__":
args = docopt(__doc__)
scriptdir = os.path.dirname(os.path.abspath(__file__))
if "{scriptdir}" in args["--importdir"]:
args["--importdir"] = os.path.abspath(
args["--importdir"].format(scriptdir=scriptdir))
if "{scriptdir}" in args["--exportdir"]:
args["--exportdir"] = os.path.abspath(
args["--exportdir"].format(scriptdir=scriptdir))
log_level = log.DEBUG if args["--debug"] else log.INFO
log.basicConfig(format="%(levelname)-8s %(message)s", level=log_level)
tracker = SeverityTracker()
log.getLogger().addHandler(tracker)
anthology = Anthology(importdir=args["--importdir"], fast_load=True)
create_bibtex(anthology, args["--exportdir"], clean=args["--clean"])
if tracker.highest >= log.ERROR:
exit(1)
import os
import sys
from anthology import Anthology
from anthology.people import PersonName
from anthology.utils import deconstruct_anthology_id
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("collections", nargs="+")
args = parser.parse_args()
anthology = Anthology(
importdir=os.path.join(os.path.dirname(sys.argv[0]), "..", "data"))
# header
print("name", "id", "title", sep="\t")
for id_, paper in anthology.papers.items():
collection_id, volume_name, paper_id = deconstruct_anthology_id(id_)
if collection_id in args.collections:
authors = paper.attrib.get("author", [])
if len(authors) > 0:
# "authors" is a list of ("last name || first name", name-id or None) tuples
first_author = authors[0][0]
authors_papers = list(
anthology.people.name_to_papers[first_author].values())
authors_papers = authors_papers[0] + authors_papers[1]
if len(authors_papers) == 1:
if __name__ == "__main__":
args = docopt(__doc__)
scriptdir = os.path.dirname(os.path.abspath(__file__))
if "{scriptdir}" in args["--importdir"]:
args["--importdir"] = os.path.abspath(
args["--importdir"].format(scriptdir=scriptdir))
log_level = log.DEBUG if args["--debug"] else log.INFO
log.basicConfig(format="%(levelname)-8s %(message)s", level=log_level)
tracker = SeverityTracker()
log.getLogger().addHandler(tracker)
log.info("Instantiating the Anthology...")
anthology = Anthology(importdir=args["--importdir"], require_bibkeys=False)
log.info("Scanning for papers without <bibkey> tags...")
write_bibkeys(anthology,
args["--importdir"],
commit=bool(args["--commit"]))
if not args["--commit"]:
if tracker.highest >= log.ERROR:
log.warning(
"There were errors! Please check them carefully before re-running this script with -c/--commit."
)
else:
log.warning(
"Re-run this script with -c/--commit to save these changes to the XML files."
)
