def parse_reference_line(ref_line, kbs, bad_titles_count={}):
"""Parse one reference line
@input a string representing a single reference bullet
@output parsed references (a list of elements objects)
"""
# Strip the 'marker' (e.g. [1]) from this reference line:
(line_marker, ref_line) = remove_reference_line_marker(ref_line)
# Find DOI sections in citation
(ref_line, identified_dois) = identify_and_tag_DOI(ref_line)
# Identify and replace URLs in the line:
(ref_line, identified_urls) = identify_and_tag_URLs(ref_line)
# Tag <cds.JOURNAL>, etc.
tagged_line, bad_titles_count = tag_reference_line(ref_line,
kbs,
bad_titles_count)
# Debug print tagging (authors, titles, volumes, etc.)
write_message('* tags %r' % tagged_line, verbose=9)
# Using the recorded information, create a MARC XML representation
# of the rebuilt line:
# At the same time, get stats of citations found in the reference line
# (titles, urls, etc):
citation_elements, line_marker, counts = \
parse_tagged_reference_line(line_marker,
tagged_line,
identified_dois,
identified_urls)
# Transformations on elements
citation_elements = split_volume_from_journal(citation_elements)
citation_elements = format_volume(citation_elements)
citation_elements = handle_special_journals(citation_elements, kbs)
citation_elements = format_report_number(citation_elements)
citation_elements = format_author_ed(citation_elements)
citation_elements = look_for_books(citation_elements, kbs)
citation_elements = format_hep(citation_elements)
citation_elements = remove_b_for_nucl_phys(citation_elements)
citation_elements = mangle_volume(citation_elements)
# Split the reference in multiple ones if needed
splitted_citations = split_citations(citation_elements)
# Remove references with only misc text
splitted_citations = remove_invalid_references(splitted_citations)
# Find year
splitted_citations = add_year_elements(splitted_citations)
# For debugging puposes
print_citations(splitted_citations, line_marker)
return splitted_citations, line_marker, counts, bad_titles_count
def parse_reference_line(ref_line, kbs, bad_titles_count={}):
"""Parse one reference line
@input a string representing a single reference bullet
@output parsed references (a list of elements objects)
"""
# Strip the 'marker' (e.g. [1]) from this reference line:
(line_marker, ref_line) = remove_reference_line_marker(ref_line)
# Find DOI sections in citation
(ref_line, identified_dois) = identify_and_tag_DOI(ref_line)
# Identify and replace URLs in the line:
(ref_line, identified_urls) = identify_and_tag_URLs(ref_line)
# Tag <cds.JOURNAL>, etc.
tagged_line, bad_titles_count = tag_reference_line(ref_line, kbs,
bad_titles_count)
# Debug print tagging (authors, titles, volumes, etc.)
write_message('* tags %r' % tagged_line, verbose=9)
# Using the recorded information, create a MARC XML representation
# of the rebuilt line:
# At the same time, get stats of citations found in the reference line
# (titles, urls, etc):
citation_elements, line_marker, counts = \
parse_tagged_reference_line(line_marker,
tagged_line,
identified_dois,
identified_urls)
# Transformations on elements
citation_elements = split_volume_from_journal(citation_elements)
citation_elements = format_volume(citation_elements)
citation_elements = handle_special_journals(citation_elements, kbs)
citation_elements = format_report_number(citation_elements)
citation_elements = format_author_ed(citation_elements)
citation_elements = look_for_books(citation_elements, kbs)
citation_elements = format_hep(citation_elements)
citation_elements = remove_b_for_nucl_phys(citation_elements)
citation_elements = mangle_volume(citation_elements)
# Split the reference in multiple ones if needed
splitted_citations = split_citations(citation_elements)
# Remove references with only misc text
splitted_citations = remove_invalid_references(splitted_citations)
# Find year
splitted_citations = add_year_elements(splitted_citations)
# For debugging puposes
print_citations(splitted_citations, line_marker)
return splitted_citations, line_marker, counts, bad_titles_count
def extract_journal_reference(line):
"""Extracts the journal reference from
MARC field 773 and parses for specific
journal information.
Parameter: line - field 773__x, the raw journal ref
Return: list of tuples with data values"""
tagged_line = tag_reference_line(line, get_kbs(), {})[0]
if tagged_line is None:
return None
elements, dummy_marker, dummy_stats = parse_tagged_reference_line("", tagged_line, [], [])
for element in elements:
if element["type"] == "JOURNAL":
return element
def extract_journal_reference(line):
"""Extracts the journal reference from
MARC field 773 and parses for specific
journal information.
Parameter: line - field 773__x, the raw journal ref
Return: list of tuples with data values"""
tagged_line = tag_reference_line(line, get_kbs(), {})[0]
if tagged_line is None:
return None
elements, dummy_marker, dummy_stats = parse_tagged_reference_line(
'', tagged_line, [], [])
for element in elements:
if element['type'] == 'JOURNAL':
return element
