def extract_abbreviations(fulltext):
"""Extract acronyms from the fulltext
@var fulltext: utf-8 string
@return: dictionary of matches in a formt {
<keyword object>, [matched skw or ckw object, ....]
}
or empty {}
"""
acronyms = {}
K = reader.KeywordToken
for k, v in acronymer.get_acronyms(fulltext).items():
acronyms[K(k, type='acronym')] = v
return acronyms
def extract_abbreviations(fulltext):
"""Extract acronyms from the fulltext
@var fulltext: utf-8 string
@return: dictionary of matches in a formt {
<keyword object>, [matched skw or ckw object, ....]
}
or empty {}
"""
acronyms = {}
K = reader.KeywordToken
for k, v in acronymer.get_acronyms(fulltext).items():
acronyms[K(k, type='acronym')] = v
return acronyms
def output_keywords_for_sources(input_sources, taxonomy, rebuild_cache=False,
output_mode="text", output_limit=CFG_BIBCLASSIFY_DEFAULT_OUTPUT_NUMBER,
match_mode="full", no_cache=False, with_author_keywords=False,
spires=False, verbose=None, only_core_tags=False, extract_acronyms=False):
"""Outputs the keywords for each source in sources."""
if verbose is not None:
set_verbose_level(verbose)
# Initialize cache
global _SKWS
global _CKWS
_SKWS, _CKWS = get_regular_expressions(taxonomy, rebuild=rebuild_cache,
no_cache=no_cache)
# Get the fulltext for each source.
for entry in input_sources:
write_message("INFO: Trying input file %s." % entry, stream=sys.stderr,
verbose=3)
text_lines = None
source = ""
if os.path.isdir(entry):
for filename in os.listdir(entry):
if os.path.isfile(entry + filename):
text_lines = text_lines_from_local_file(entry + filename)
if text_lines:
source = filename
elif os.path.isfile(entry):
text_lines = text_lines_from_local_file(entry)
if text_lines:
source = os.path.basename(entry)
else:
# Treat as a URL.
text_lines = text_lines_from_url(entry,
user_agent=CFG_BIBCLASSIFY_USER_AGENT)
if text_lines:
source = entry.split("/")[-1]
if source:
if output_mode == "text":
print "Input file: %s" % source
keywords = get_keywords_from_text(text_lines,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
with_author_keywords=with_author_keywords,
only_core_tags=only_core_tags)
if extract_acronyms:
acronyms = get_acronyms("\n".join(text_lines))
if acronyms:
acronyms_str = ["\nAcronyms:"]
for acronym, expansions in acronyms.iteritems():
expansions_str = ", ".join(["%s (%d)" % expansion
for expansion in expansions])
acronyms_str.append("%s %s" % (acronym, expansions_str))
acronyms_str = "\n".join(acronyms_str)
else:
acronyms_str = "\nNo acronyms."
print keywords + acronyms_str + "\n"
else:
print keywords
def output_keywords_for_sources(input_sources, taxonomy, rebuild_cache=False,
output_mode="text", output_limit=CFG_BIBCLASSIFY_DEFAULT_OUTPUT_NUMBER,
match_mode="full", no_cache=False, with_author_keywords=False,
spires=False, verbose=None, only_core_tags=False, extract_acronyms=False):
"""Outputs the keywords for each source in sources."""
if verbose is not None:
set_verbose_level(verbose)
# Initialize cache
global _SKWS
global _CKWS
_SKWS, _CKWS = get_regular_expressions(taxonomy, rebuild=rebuild_cache,
no_cache=no_cache)
# Get the fulltext for each source.
for entry in input_sources:
write_message("INFO: Trying input file %s." % entry, stream=sys.stderr,
verbose=3)
text_lines = None
source = ""
if os.path.isdir(entry):
for filename in os.listdir(entry):
if os.path.isfile(entry + filename):
text_lines = text_lines_from_local_file(entry + filename)
if text_lines:
source = filename
elif os.path.isfile(entry):
text_lines = text_lines_from_local_file(entry)
if text_lines:
source = os.path.basename(entry)
else:
# Treat as a URL.
text_lines = text_lines_from_url(entry,
user_agent=CFG_BIBCLASSIFY_USER_AGENT)
if text_lines:
source = entry.split("/")[-1]
if source:
if output_mode == "text":
print "Input file: %s" % source
keywords = get_keywords_from_text(text_lines,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
with_author_keywords=with_author_keywords,
only_core_tags=only_core_tags)
if extract_acronyms:
acronyms = get_acronyms("\n".join(text_lines))
if acronyms:
acronyms_str = ["\nAcronyms:"]
for acronym, expansions in acronyms.iteritems():
expansions_str = ", ".join(["%s (%d)" % expansion
for expansion in expansions])
acronyms_str.append("%s %s" % (acronym, expansions_str))
acronyms_str = "\n".join(acronyms_str)
else:
acronyms_str = "\nNo acronyms."
print keywords + acronyms_str + "\n"
else:
print keywords