def find_reference_section(docbody):
"""Search in document body for its reference section.
More precisely, find
the first line of the reference section. Effectively, the function starts
at the end of a document and works backwards, line-by-line, looking for
the title of a reference section. It stops when (if) it finds something
that it considers to be the first line of a reference section.
@param docbody: (list) of strings - the full document body.
@return: (dictionary) :
{ 'start_line' : (integer) - index in docbody of 1st reference line,
'title_string' : (string) - title of the reference section.
'marker' : (string) - the marker of the first reference line,
'marker_pattern' : (string) - regexp string used to find the marker,
'title_marker_same_line' : (integer) - flag to indicate whether the
reference section title was on the same
line as the first reference line's
marker or not. 1 if it was; 0 if not.
}
Much of this information is used by later functions to rebuild
a reference section.
-- OR --
(None) - when the reference section could not be found.
"""
ref_details = None
title_patterns = get_reference_section_title_patterns()
# Try to find refs section title:
for title_pattern in title_patterns:
# Look for title pattern in docbody
for reversed_index, line in enumerate(reversed(docbody)):
title_match = title_pattern.match(line)
if title_match:
title = title_match.group('title')
index = len(docbody) - 1 - reversed_index
temp_ref_details, found_title = find_numeration(docbody[index:index+6], title)
if temp_ref_details:
if ref_details and 'title' in ref_details \
and ref_details['title'] \
and not temp_ref_details['title']:
continue
if ref_details and 'marker' in ref_details \
and ref_details['marker'] \
and not temp_ref_details['marker']:
continue
ref_details = temp_ref_details
ref_details['start_line'] = index
ref_details['title_string'] = title
if found_title:
break
if ref_details:
break
return ref_details
def find_reference_section(docbody):
"""Search in document body for its reference section.
More precisely, find
the first line of the reference section. Effectively, the function starts
at the end of a document and works backwards, line-by-line, looking for
the title of a reference section. It stops when (if) it finds something
that it considers to be the first line of a reference section.
@param docbody: (list) of strings - the full document body.
@return: (dictionary) :
{ 'start_line' : (integer) - index in docbody of 1st reference line,
'title_string' : (string) - title of the reference section.
'marker' : (string) - the marker of the first reference line,
'marker_pattern' : (string) - regexp string used to find the marker,
'title_marker_same_line' : (integer) - flag to indicate whether the
reference section title was on the same
line as the first reference line's
marker or not. 1 if it was; 0 if not.
}
Much of this information is used by later functions to rebuild
a reference section.
-- OR --
(None) - when the reference section could not be found.
"""
ref_details = None
title_patterns = get_reference_section_title_patterns()
# Try to find refs section title:
for reversed_index, line in enumerate(reversed(docbody)):
title_match = regex_match_list(line, title_patterns)
if title_match:
title = title_match.group('title')
index = len(docbody) - 1 - reversed_index
temp_ref_details, found_title = find_numeration(docbody[index:index+6], title)
if temp_ref_details:
if ref_details and 'title' in ref_details \
and ref_details['title'] \
and not temp_ref_details['title']:
continue
if ref_details and 'marker' in ref_details \
and ref_details['marker'] \
and not temp_ref_details['marker']:
continue
ref_details = temp_ref_details
ref_details['start_line'] = index
ref_details['title_string'] = title
if found_title:
break
return ref_details
def test_reference_section_title_pattern(self):
r = refextract_re.get_reference_section_title_patterns()
self.assert_(len(r) > 2)
def test_reference_section_title_pattern(self):
r = refextract_re.get_reference_section_title_patterns()
self.assert_(len(r) > 2)
