How to use the refextract.references.regexs.get_reference_line_numeration_marker_patterns function in refextract

To help you get started, we’ve selected a few refextract examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github inspirehep / refextract / tests / View on Github external
def test_get_reference_line_numeration_marker_patterns():
    r = regexs.get_reference_line_numeration_marker_patterns()
    assert len(r) > 2
github inspirehep / refextract / refextract / references / View on Github external
def find_numeration_in_title(docbody, title):
    ref_details = None
    found_title = False

        first_line = docbody[0]
    except IndexError:
        return ref_details, found_title

    # Need to escape to avoid problems like 'References['
    title = re.escape(title)

    mk_with_title_ptns = \
    mk_with_title_match = \
        regex_match_list(first_line, mk_with_title_ptns)
    if mk_with_title_match:
        mk ='mark')
        mk_ptn =
        m_num =
        if m_num and == '1':
            # Mark found
            found_title = True
            ref_details = {
                'marker': mk,
                'marker_pattern': mk_ptn,
                'title_marker_same_line': True
            ref_details = {
github inspirehep / refextract / refextract / references / View on Github external
def find_numeration_in_body(docbody):
    marker_patterns = get_reference_line_numeration_marker_patterns()
    ref_details = None
    found_title = False

    # No numeration unless we find one
    ref_details = {
        'title_marker_same_line': False,
        'marker': None,
        'marker_pattern': None,

    for line in docbody:
        # Move past blank lines
        if line.isspace():

        # Is this line numerated like a reference line?
github inspirehep / refextract / refextract / references / View on Github external
x = ref_start_line
    if type(x) is not int or x < 0 or \
            x > len(docbody) or len(docbody) < 1:
        # The provided 'first line' of the reference section was invalid.
        # Either it was out of bounds in the document body, or it was not a
        # valid integer.
        # Can't safely find end of refs with this info - quit.
        return None
    # Get patterns for testing line:
    t_patterns = get_post_reference_section_title_patterns()
    kw_patterns = get_post_reference_section_keyword_patterns()

    if None not in (ref_line_marker, ref_line_marker_ptn):
        mk_patterns = [re.compile(ref_line_marker_ptn, re.I | re.UNICODE)]
        mk_patterns = get_reference_line_numeration_marker_patterns()

    current_reference_count = 0
    while x < len(docbody) and not section_ended:
        # save the reference count
        num_match = regex_match_list(docbody[x].strip(), mk_patterns)
        if num_match:
                current_reference_count = int('marknum'))
            except (ValueError, IndexError):
                # non numerical references marking
        # look for a likely section title that would follow a reference
        # section:
        end_match = regex_match_list(docbody[x].strip(), t_patterns)
        if not end_match:
            # didn't match a section title - try looking for keywords that
github inspirehep / refextract / refextract / references / View on Github external
def remove_reference_line_marker(line):
    """Trim a reference line's 'marker' from the beginning of the line.
       @param line: (string) - the reference line.
       @return: (tuple) containing two strings:
                 + The reference line's marker (or if there was not one,
                   a 'space' character.
                 + The reference line with it's marker removed from the
    # Get patterns to identify reference-line marker patterns:
    marker_patterns = get_reference_line_numeration_marker_patterns()
    line = line.lstrip()

    marker_match = regex_match_list(line, marker_patterns)

    if marker_match is not None:
        # found a marker:
        marker_val ='mark')
        # trim the marker from the start of the line:
        line = line[marker_match.end():].lstrip()
        marker_val = u" "
    return (marker_val, line)