41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
-
+
|
# common
"nbsp_titles": [("\\bM(mes?|ᵐᵉˢ?|grs?|ᵍʳˢ?|lles?|ˡˡᵉˢ?|rs?|ʳˢ?|M\\.) ", "M\\1 "),
("\\bP(re?s?|ʳᵉ?ˢ?) ", "P\\1 "),
("\\bD(re?s?|ʳᵉ?ˢ?) ", "D\\1 "),
("\\bV(ves?|ᵛᵉˢ?) ", "V\\1 ")],
"nbsp_before_symbol": [("(\\d) ?([%‰€$£¥˚Ω℃])", "\\1 \\2")],
"nbsp_before_units": [("(?<=[0-9⁰¹²³⁴⁵⁶⁷⁸⁹]) ?([kcmµn]?(?:[slgJKΩ]|m[²³]?|Wh?|Hz|dB)|[%‰]|°C)\\b", " \\1")],
"nbsp_repair": [("(?<=[[(])[ ]([!?:;])", "\\1"),
"nbsp_repair": [("(?<=[\\[(])[ ]([!?:;])", "\\1"),
("(https?|ftp)[ ]:(?=//)", "\\1:"),
("&([a-z]+)[ ];", "&\\1;"),
("&#([0-9]+|x[0-9a-fA-F]+)[ ];", "&#\\1;")],
## missing spaces
"add_space_after_punctuation": [("([;!…])(?=\\w)", "\\1 "),
("[?](?=[A-ZÉÈÊÂÀÎ])", "? "),
("\\.(?=[A-ZÉÈÎ][a-zA-ZàâÂéÉèÈêÊîÎïÏôÔöÖûÛüÜùÙ])", ". "),
|
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
|
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
|
-
+
|
"erase_non_breaking_hyphens": [("", "")],
## typographic signs
"ts_apostrophe": [ ("(?i)\\b([ldnjmtscç])['´‘′`](?=\\w)", "\\1’"),
("(?i)(qu|jusqu|lorsqu|puisqu|quoiqu|quelqu|presqu|entr|aujourd|prud)['´‘′`]", "\\1’") ],
"ts_ellipsis": [ ("\\.\\.\\.", "…"),
("(?<=…)[.][.]", "…"),
("…[.](?![.])", "…") ],
"ts_n_dash_middle": [ (" [-—] ", " – "),
"ts_n_dash_middle": [ (" [-—] ", " – "),
(" [-—],", " –,") ],
"ts_m_dash_middle": [ (" [-–] ", " — "),
(" [-–],", " —,") ],
"ts_n_dash_start": [ ("^[-—][ ]", "– "),
("^– ", "– "),
("^[-–—](?=[\\w.…])", "– ") ],
"ts_m_dash_start": [ ("^[-–][ ]", "— "),
|