Grammalecte  Check-in [05a7a5fb8e]

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:[lo] text formatter: fix strange bugs with replacements (again)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | lo
Files: files | file ages | folders
SHA3-256:05a7a5fb8e5412f9ff1ec8748f611e0ad73b4bf97fa18688b0474c9a6977d791
User & Date: olr 2019-07-24 06:59:44
Context
2019-07-24
07:50
[lo] text formatter: fix strange bugs with replacements (again) check-in: df2bb268e4 user: olr tags: lo, trunk
06:59
[lo] text formatter: fix strange bugs with replacements (again) check-in: 05a7a5fb8e user: olr tags: lo, trunk
06:58
[fr] tests et ajustements check-in: 010d9c0ace user: olr tags: fr, trunk
Changes

Changes to gc_lang/fr/oxt/TextFormatter/tf_tabrep.py.

   117    117       "nnbsp4": [
   118    118                       ("([:digit:])[  ]([:digit:])",      "$1 $2",        True,   True)
   119    119       ],
   120    120       "nbsp5": [
   121    121                       ("(?<=[0-9⁰¹²³⁴⁵⁶⁷⁸⁹]) ?([kcmµnd]?(?:[slgJKΩΩℓ]|m[²³]?|Wh?|Hz|dB)|[%‰]|°C)\\b", " $1", True, True)
   122    122       ],
   123    123       "nbsp6": [
   124         -                    ("\\bM(mes?|ᵐᵉˢ?|grs?|ᵍʳˢ?|lles?|ˡˡᵉˢ?|rs?|ʳˢ?|M\\.) ", "M$1 ",     True,   True),
   125         -                    ("\\bD(re?s?|ʳᵉ?ˢ?) ",                                  "D$1 ",     True,   True),
   126         -                    ("\\bP(re?s?|ʳᵉ?ˢ?) ",                                  "P$1 ",     True,   True),
   127         -                    ("\\bV(ves?|ᵛᵉˢ?) ",                                    "V$1 ",     True,   True),
          124  +                    ("M(mes?|ᵐᵉˢ?|grs?|ᵍʳˢ?|lles?|ˡˡᵉˢ?|rs?|ʳˢ?|M\\.) ", "M$1 ",     True,   True),
          125  +                    ("D(re?s?|ʳᵉ?ˢ?) ",                                  "D$1 ",     True,   True),
          126  +                    ("P(re?s?|ʳᵉ?ˢ?) ",                                  "P$1 ",     True,   True),
          127  +                    ("V(ves?|ᵛᵉˢ?) ",                                    "V$1 ",     True,   True),
   128    128       ],
   129    129   
   130    130       # espaces manquants
   131    131       "space1": [
   132    132                       (";(?=[:alnum:])",                  "; ",           True,   True),
   133    133                       ("\\?(?=[A-ZÉÈÊÂÀÎ])",              "? ",           True,   True),
   134    134                       ("!(?=[:alnum:])",                  "! ",           True,   True),
................................................................................
   251    251                       ("\\bJ\\.kg(?=-1)\\b",                  "J·kg",         True,   True),
   252    252                       ("\\bJ\\.m(?=-3)\\b",                   "J·m",          True,   True),
   253    253                       ("\\bm[2²]\\.s\\b",                     "m²·s",         True,   True),
   254    254                       ("\\bm[3³]\\.s(?=-1)\\b",               "m³·s",         True,   True),
   255    255                       #("\\bJ.kg-1.K-1\\b",                   "J·kg-1·K-1",   True,   True),
   256    256                       #("\\bW.m-1.K-1\\b",                    "W·m-1·K-1",    True,   True),
   257    257                       #("\\bW.m-2.K-1\\b",                    "W·m-2·K-1",    True,   True),
   258         -                    ("\\b(Y|Z|E|P|T|G|M|k|h|da|d|c|m|µ|n|p|f|a|z|y)Ω\\b", "$1Ω", True, True)
          258  +                    ("(Y|Z|E|P|T|G|M|k|h|da|d|c|m|µ|n|p|f|a|z|y)Ω", "$1Ω", True, True)
   259    259       ],
   260    260       "typo7": [
   261    261                       # ligatures: pas de majuscules
   262    262                       ("coeur",                               "cœur",         False,  True),
   263    263                       ("coel([aeio])",                        "cœl$1",        True,   True),
   264    264                       ("choeur",                              "chœur",        False,  True),
   265    265                       ("foet",                                "fœt",          False,  True),
................................................................................
   293    293                       # mots communs avec diacritiques manquants
   294    294                       ("\\bCa\\b",                            "Ça",           True,   True),
   295    295                       (" ca\\b",                              " ça",          True,   True),
   296    296                       ("\\bdej[aà]\\b",                       "déjà",         True,   True),
   297    297                       ("\\bDej[aà]\\b",                       "Déjà",         True,   True),
   298    298                       ("\\bplutot\\b",                        "plutôt",       True,   True),
   299    299                       ("\\bPlutot\\b",                        "Plutôt",       True,   True),
   300         -                    ("\\b([cC]e(?:ux|lles?|lui))-la\\b",    "$1-là",        True,   True),
          300  +                    ("\\b(ce(?:ux|lles?|lui))-la\\b",       "$1-là",        True,   True),
          301  +                    ("\\b(Ce(?:ux|lles?|lui))-la\\b",       "$1-là",        True,   True),
   301    302                       ("\\bmalgre\\b",                        "malgré",       True,   True),
   302    303                       ("\\bMalgre\\b",                        "Malgré",       True,   True),
   303    304                       ("\\betre\\b",                          "être",         True,   True),
   304    305                       ("\\bEtre\\b",                          "Être",         True,   True),
   305    306                       ("\\btres\\b",                          "très",         True,   True),
   306    307                       ("\\bTres\\b",                          "Très",         True,   True),
   307    308                       ("\\bEtai([ts]|ent)\\b",                "Étai$1",       True,   True),
................................................................................
   384    385                       ("(?<!,) etc[.]",                           ", etc.",       True,   True)
   385    386       ],
   386    387       "misc3": [
   387    388                       ("[ -]t[’'](?=il\\b|elle|on\\b)",           "-t-",          True,   True),
   388    389                       (" t-(?=il|elle|on)",                       "-t-",          True,   True),
   389    390                       ("[ -]t[’'-](?=ils|elles)",                 "-",            True,   True),
   390    391                       ("(?<=[td])-t-(?=il|elle|on)",              "-",            True,   True),
   391         -                    ("(celles?|celui|ceux) (ci|là)\\b",         "$1-$2",        True,   False),
   392         -                    ("\\bdix (sept|huit|neuf)",                 "dix-$1",       True,   False),
          392  +                    (" c(elles?|elui|eux) (ci|là)\\b",          " c$1-$2",      True,   True),
          393  +                    ("C(elles?|elui|eux) (ci|là)\\b",           "C$1-$2",       True,   True),
          394  +                    (" dix (sept|huit|neuf)",                   " dix-$1",      True,   True),
          395  +                    ("Dix (sept|huit|neuf)",                    "Dix-$1",       True,   True),
   393    396                       ("quatre vingt",                            "quatre-vingt", False,  True),
   394         -                    ("(soixante|quatre-vingt) dix",             "$1-dix",       True,   False),
   395         -                    ("(vingt|trente|quarante|cinquante|soixante(?:-dix|)|quatre-vingt(?:-dix|)) (deux|trois|quatre|cinq|six|sept|huit|neuf)", "$1-$2", True, False),
          397  +                    ("Quatre vingt",                            "Quatre-vingt", False,  True),
          398  +                    ("(soixante|quatre-vingt) (deux|trois|quatre|cinq|six|sept|huit|neuf|dix|onze|douze|treize|quatorze|quinze|seize|dix-sept|dix-huit|dix-neuf)", "$1-$2", True, False),
          399  +                    ("(vingt|trente|quarante|cinquante) (deux|trois|quatre|cinq|six|sept|huit|neuf)", "$1-$2", True, False),
   396    400                       ("(?<!-)\\b(ci) (joint|desso?us|contre|devant|avant|après|incluse|g[îi]t|gisent)", "$1-$2", True, False),
   397    401                       ("\\bvis à vis",                            "vis-à-vis",    False,  True),
   398    402                       ("\\bVis à vis",                            "Vis-à-vis",    False,  True),
   399    403                       ("week end",                                "week-end",     False,  True),
   400    404                       ("Week end",                                "Week-end",     False,  True),
   401    405                       ("(plus|moins) value",                      "$1-value",     True,   False)
   402    406       ],

Changes to tests/fr/formateur_de_texte.odt.

cannot compute difference between binary files