Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/nameparser/config/regexes.py: 100%

1import re 

2 

3# emoji regex from https://stackoverflow.com/questions/26568722/remove-unicode-emoji-using-re-in-python 

4re_emoji = re.compile('[' # lgtm[py/overly-large-range] 

5 '\U0001F300-\U0001F64F' 

6 '\U0001F680-\U0001F6FF' 

7 '\u2600-\u26FF\u2700-\u27BF]+') 

8 

9# Invisible bidirectional formatting characters: ALM, LRM, RLM, the 

10# embedding/override marks (LRE/RLE/PDF/LRO/RLO) and the isolates 

11# (LRI/RLI/FSI/PDI). Copy-pasted RTL names often carry these; they render 

12# as nothing but stick to name parts and break equality/lookups. 

13re_bidi = re.compile('[\u061C\u200E\u200F\u202A-\u202E\u2066-\u2069]+') 

14 

15EMPTY_REGEX = re.compile('') 

16 

17REGEXES = { 

18 "spaces": re.compile(r"\s+"), 

19 "word": re.compile(r"(\w|\.)+"), 

20 "mac": re.compile(r'^(ma?c)(\w{2,})', re.I), 

21 "initial": re.compile(r'^(\w\.|[A-Z])?$'), 

22 "quoted_word": re.compile(r'(?<!\w)\'([^\s]*?)\'(?!\w)'), 

23 "double_quotes": re.compile(r'\"(.*?)\"'), 

24 "parenthesis": re.compile(r'\((.*?)\)'), 

25 "roman_numeral": re.compile(r'^(X|IX|IV|V?I{0,3})$', re.I), 

26 "no_vowels": re.compile(r'^[^aeyiuo]+$', re.I), 

27 "period_not_at_end": re.compile(r'.*\..+$', re.I), 

28 "emoji": re_emoji, 

29 "bidi": re_bidi, 

30 "phd": re.compile(r'\s(ph\.?\s+d\.?)', re.I), 

31 "space_before_comma": re.compile(r'\s+,'), 

32 # ASCII comma plus its Arabic (U+060C) and fullwidth CJK (U+FF0C) 

33 # counterparts, used to split "Last, First" format and to strip a 

34 # trailing comma before parsing (#265). 

35 "commas": re.compile(r'[,،，]'), 

36 "east_slavic_patronymic": re.compile( 

37 r'(ovich|ovna|evich|evna|ichna|ilyich|kuzmich|lukich|fomich|fokich)$', 

38 re.I, 

39 ), 

40 "east_slavic_patronymic_cyrillic": re.compile( 

41 r'(ович|овна|евич|евна|ична|ильич|кузьмич|лукич|фомич|фокич)$', 

42 re.I, 

43 ), 

44 "turkic_patronymic_marker": re.compile( 

45 r"^(oglu|oğlu|ogly|ogli|o['’ʻ]g['’ʻ]li" 

46 r"|qizi|qızı|kizi|kyzy|gyzy|uly|uulu)$", 

47 re.I, 

48 ), 

49 "turkic_patronymic_marker_cyrillic": re.compile( 

50 r'^(оглу|оглы|оғлу|ўғли|угли|кызы|гызы|қызы|қизи|улы|ұлы|уулу)$', 

51 re.I, 

52 ), 

53 "period_abbreviation": re.compile(r'^[^\W\d_]{2,}\.$'), 

54} 

55""" 

56All regular expressions used by the parser are precompiled and stored in the config. 

57"""