Coverage for oc_meta/lib/master_of_regex.py: 100%

19 statements  

« prev     ^ index     » next       coverage.py v6.5.0, created at 2025-07-14 14:06 +0000

1# Split by ';' outside '[]' (any spaces before and after ';'). 

2semicolon_in_people_field = r'\s*;\s*(?=[^\]]*(?:\[|$))' 

3 

4# It gets string inside '[]' ignoring any space between (ex: [ TARGET ] --> TARGET). 

5# An id schema must be present, followed by a colon. 

6# Before the colon, there must be any character that is not a square bracket  

7# to prevent that in strings like 'Boezaart, Andr[eacute] [omid:123]' the id captured is '[eacute] [omid:123]'. 

8# Alternatively, empty square brackets containing one or more spaces also represent a valid match. 

9ids_inside_square_brackets = r'\[\s*((?:[^\s]+:[^\s]+)?(?:\s+[^\s]+:[^\s]+)*)\s*\]' 

10 

11# It gets the name and ids in two capturing groups. 

12# As for ids, it gets the string inside '[]' ignoring any space between (ex: [ TARGET ] --> TARGET). 

13# An id schema must be present, followed by a colon. 

14name_and_ids = fr'\s*(.*?)\s*{ids_inside_square_brackets}' 

15 

16# It captures a colon preceded and followed by zero or more spaces. 

17colon_and_spaces = r'\s*:\s*' 

18 

19# It captures a comma preceded and followed by zero or more spaces. 

20comma_and_spaces = r'\s*,\s*' 

21 

22# It captures one or more spaces. 

23one_or_more_spaces = r'\s+' 

24 

25# It captures any pages range separator. 

26pages_separator = r'[^A-Za-z\d]+(?=[A-Za-z\d]+)' 

27 

28# It captures an ORCID 

29orcid_pattern = r'([0-9]{4}-){3}[0-9]{3}[0-9X]' 

30 

31# A series of patterns useful to clean invalid "volume" and "issue" fields 

32good_sep = r'\-' 

33bad_sep = r'&\/_,\.:+;\(\[\|' 

34separators = good_sep + bad_sep 

35alphabets = r'a-zà-öø-ÿ\u0430-я\u0391-ω' # basic latin, latin-1 supplement, cyrillic, greek 

36vi_pattern = fr'((?:[{alphabets}]*\d[{alphabets}\d]*|[ivxlcdm]+)(?:\s?(?:[{separators}]|and|\()\s?[{alphabets}\d]+\)?)*?)' 

37numero = r'(?:№|no?(?!v)\.?|n[º°]\.?|n[uú]m(?:[eé]ro)?|number)' 

38year_pattern = r'(\d{4})' 

39valid_vi_patterns = [ 

40 vi_pattern, 

41 fr'[‹<\()]?[{alphabets}]+?([{separators}\s]?[{alphabets}])*[\)›>]?', 

42 fr'[{alphabets}{separators}\s]+{vi_pattern}', 

43 fr"[{alphabets}\d\-'/]*\d[{alphabets}\d\-'/]*(,?\s[{alphabets}\d\-'/]+)+", 

44 fr'\(?s(uppl([eéi]ment(ary|um)?))?\)?\s?(part)?\s?(s?{vi_pattern})?', 

45 fr'({vi_pattern}_)?({vi_pattern}\s)?[\(_]?supp?(plement|pl)?l?[\s\._]*({vi_pattern}|[{alphabets}])?\)?\.?', 

46 fr'{vi_pattern}*,?\s?part[\s_]{vi_pattern}(\sof\s{vi_pattern})?(,\sno?\.\s?{vi_pattern})?', 

47 fr'{vi_pattern}*[_\s]?pt?[_\s\.]{vi_pattern}', 

48 '(ed|pt|d)\sinside(d|r)', 

49 'p(ublish\s)?a(head\sof\s)?p(rint)?', 

50 '預刊文章', 

51 '[\u0621-\u064A]+', 

52 fr'\[{year_pattern}\]\s(\d\s)?[{alphabets}]+', 

53 fr'{vi_pattern}\s\[\+CDROM\]', 

54 fr'{vi_pattern}[{separators}\s]?\({vi_pattern}\)(\s{vi_pattern})?', 

55 fr'([{alphabets}]+\.)?[{alphabets}]+\.?', 

56 fr'[{alphabets}]+-\d+', 

57 fr'[{alphabets}]+(_[{alphabets}]+)+', 

58 fr'{numero}:?\s?{vi_pattern}(,?\s({year_pattern}|\({vi_pattern}\)))?', 

59 'historica\svol\.\s\d+(,\d+(-\d+)?)?', 

60 '\d+\(\d+\)\d{2,4}', 

61 fr'(\[{year_pattern}\]\s)?(\d+\s)?vl?r(\s\([a-z]+\))?', 

62 fr'\({vi_pattern}\/{vi_pattern}\)\s[{alphabets}]+(-[{alphabets}]+)?' 

63] 

64volumes_valid_patterns = [ 

65 'original\sseries,\svolume\s\d+', 

66 fr'(vol(ume)?|tome|cilt)\s?[{separators}]?\s?{vi_pattern}' 

67] 

68issues_valid_patterns = [ 

69 fr'issue[\.,]?\s{vi_pattern}', 

70 fr'({vi_pattern}\s)?e?sp?e?(ecial)?[\s_\-\.](issue)?(_number_)?[\s_-]?({vi_pattern})?(["“][{alphabets}\s]+?["”])?', 

71 fr'ö(zel)?(\ss(ayı)?|\(special\))?(\s?{vi_pattern})?', 

72 fr'({numero}[{separators}\s]?)?hors[{separators}\s]série[{separators}\s]{vi_pattern}', 

73 '특별호', 

74 fr'([{alphabets}]+\s{year_pattern}\s)?\(?(jan(uary)?|feb(ruary)?|mar(ch)?|apr(il)?|may|jun(e)?|jul(y)?|aug(ust)?|sep(tember)?|oct(ober)?|(nov|dec)(ember)?|spring|summer|autumn|winter)(\s{year_pattern})?\)?', 

75 fr'{vi_pattern},\spart\s{vi_pattern}\sof\s{vi_pattern}', 

76 fr'sayı[{separators}\s]\s?{vi_pattern}', 

77 fr'issues?\s{vi_pattern},\s(supplement|part)\s{vi_pattern}', 

78 fr'issues?\s{vi_pattern}\.?\spp\.\s[a-z\d]+[^a-z\d]+[a-z\d]+' 

79] 

80invalid_vi_patterns = { 

81 fr'.*?(?:vol\.?(?:ume)?|tome)(?:[{separators}]?\s?){vi_pattern}[\-&\/_,\.:+;\(\)\[\]|\s]*(?:{numero}|issues?)[{separators}|\s]*(?:sp[eé]cial\s)?{vi_pattern}': 'vol_iss', 

82 fr'{vi_pattern},\s?{numero}\s?{vi_pattern}': 'vol_iss', 

83 fr'tập\s?{vi_pattern},?\s?số\s?{vi_pattern}': 'vol_iss', 

84 fr'issues?\s{vi_pattern}\svol\.?(?:ume)?\s{vi_pattern}(?:.*?{year_pattern}.*?)?': 'iss_vol_year', 

85 fr"{vi_pattern}\s?\({vi_pattern}'{year_pattern}\)": 'vol_iss_year', 

86 fr'cilt[{separators}\s]\s?{vi_pattern}[{separators}\s]sayı[{separators}\s]\s?{vi_pattern}(?:[{separators}\s]\s?temmuz\s{year_pattern})?': 'vol_iss_year', 

87 r'&na;|n\/a|not\savailable': 'del', 

88 r'[\:\-\.`ё/]': 'del', 

89 fr'\${{[{alphabets}]+(\.[{alphabets}]+)?}}': 'del', 

90 fr"[&\/_,:+;\|`'#]\s*{vi_pattern}": 'all', 

91 fr'[\->+]{vi_pattern}': 'do_nothing', 

92 fr"{vi_pattern}[\.+]": "do_nothing", 

93 fr"{numero}?[{separators}]?\s?{vi_pattern}[&\/_,:;\|`'\(\[\{{]": 'all', 

94 fr'{vi_pattern}\(\)': 'all', 

95 fr'n[�?]+{vi_pattern}': 'all', 

96 fr'{vi_pattern}(?:â\x80[\x92\x93\x94]|�+|â|\?+){vi_pattern}': 'sep', 

97 fr'{vi_pattern}\s?\(first\sserie': 's)' 

98}