def output_keywords_for_sources(input_sources, taxonomy_name, output_mode="text",
output_limit=bconfig.CFG_BIBCLASSIFY_DEFAULT_OUTPUT_NUMBER, spires=False,
match_mode="full", no_cache=False, with_author_keywords=False,
rebuild_cache=False, only_core_tags=False, extract_acronyms=False,
api=False, **kwargs):
"""Outputs the keywords for each source in sources."""
# Inner function which does the job and it would be too much work to
# refactor the call (and it must be outside the loop, before it did
# not process multiple files)
def process_lines():
if output_mode == "text":
print("Input file: %s" % source)
output = get_keywords_from_text(text_lines,
taxonomy_name,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
no_cache=no_cache,
with_author_keywords=with_author_keywords,
rebuild_cache=rebuild_cache,
only_core_tags=only_core_tags,
extract_acronyms=extract_acronyms
)
if api:
return output
else:
if isinstance(output, dict):
for i in output:
print(output[i])
# Get the fulltext for each source.
for entry in input_sources:
log.info("Trying to read input file %s." % entry)
text_lines = None
source = ""
if os.path.isdir(entry):
for filename in os.listdir(entry):
filename = os.path.join(entry, filename)
if os.path.isfile(filename):
text_lines = extractor.text_lines_from_local_file(filename)
if text_lines:
source = filename
process_lines()
elif os.path.isfile(entry):
text_lines = extractor.text_lines_from_local_file(entry)
if text_lines:
source = os.path.basename(entry)
process_lines()
else:
# Treat as a URL.
text_lines = extractor.text_lines_from_url(entry,
user_agent=make_user_agent_string("BibClassify"))
if text_lines:
source = entry.split("/")[-1]
process_lines()
def get_keywords_from_local_file(
local_file,
taxonomy_name,
output_mode="text",
output_limit=bconfig.CFG_BIBCLASSIFY_DEFAULT_OUTPUT_NUMBER,
spires=False,
match_mode="full",
no_cache=False,
with_author_keywords=False,
rebuild_cache=False,
only_core_tags=False,
extract_acronyms=False,
api=False,
**kwargs):
"""Outputs keywords reading a local file. Arguments and output are the same
as for :see: get_keywords_from_text() """
log.info("Analyzing keywords for local file %s." % local_file)
text_lines = extractor.text_lines_from_local_file(local_file)
return get_keywords_from_text(text_lines,
taxonomy_name,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
no_cache=no_cache,
with_author_keywords=with_author_keywords,
rebuild_cache=rebuild_cache,
only_core_tags=only_core_tags,
extract_acronyms=extract_acronyms)
def get_keywords_from_local_file(local_file, taxonomy_name, output_mode="text",
output_limit=bconfig.CFG_BIBCLASSIFY_DEFAULT_OUTPUT_NUMBER, spires=False,
match_mode="full", no_cache=False, with_author_keywords=False,
rebuild_cache=False, only_core_tags=False, extract_acronyms=False, api=False,
**kwargs):
"""Outputs keywords reading a local file. Arguments and output are the same
as for :see: get_keywords_from_text() """
log.info("Analyzing keywords for local file %s." % local_file)
text_lines = extractor.text_lines_from_local_file(local_file)
return get_keywords_from_text(text_lines,
taxonomy_name,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
no_cache=no_cache,
with_author_keywords=with_author_keywords,
rebuild_cache=rebuild_cache,
only_core_tags=only_core_tags,
extract_acronyms=extract_acronyms)
def output_keywords_for_sources(
input_sources,
taxonomy_name,
output_mode="text",
output_limit=bconfig.CFG_BIBCLASSIFY_DEFAULT_OUTPUT_NUMBER,
spires=False,
match_mode="full",
no_cache=False,
with_author_keywords=False,
rebuild_cache=False,
only_core_tags=False,
extract_acronyms=False,
api=False,
**kwargs):
"""Output the keywords for each source in sources."""
# Inner function which does the job and it would be too much work to
# refactor the call (and it must be outside the loop, before it did
# not process multiple files)
def process_lines():
if output_mode == "text":
print("Input file: %s" % source)
output = get_keywords_from_text(
text_lines,
taxonomy_name,
output_mode=output_mode,
output_limit=output_limit,
spires=spires,
match_mode=match_mode,
no_cache=no_cache,
with_author_keywords=with_author_keywords,
rebuild_cache=rebuild_cache,
only_core_tags=only_core_tags,
extract_acronyms=extract_acronyms)
if api:
return output
else:
if isinstance(output, dict):
for i in output:
print(output[i])
# Get the fulltext for each source.
for entry in input_sources:
log.info("Trying to read input file %s." % entry)
text_lines = None
source = ""
if os.path.isdir(entry):
for filename in os.listdir(entry):
if filename.startswith('.'):
continue
filename = os.path.join(entry, filename)
if os.path.isfile(filename):
text_lines = extractor.text_lines_from_local_file(filename)
if text_lines:
source = filename
process_lines()
elif os.path.isfile(entry):
text_lines = extractor.text_lines_from_local_file(entry)
if text_lines:
source = os.path.basename(entry)
process_lines()
else:
# Treat as a URL.
text_lines = extractor.text_lines_from_url(
entry, user_agent=make_user_agent_string("BibClassify"))
if text_lines:
source = entry.split("/")[-1]
process_lines()
