Differences From Artifact [a5e2b1d398]:
- File gc_lang/fr/modules/gce_suggestions.py — part of check-in [023f83bc15] at 2018-06-06 10:36:26 on branch rg — [core][fr] end of lemma is now a slash instead of a space (user: olr, size: 16206) [annotate] [blame] [check-ins using]
To Artifact [2926468975]:
- File gc_lang/fr/modules/gce_suggestions.py — part of check-in [48056be413] at 2018-06-24 14:16:22 on branch rg — [core] code cleaning (pylint) (user: olr, size: 17275) [annotate] [blame] [check-ins using]
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 |
#### GRAMMAR CHECKING ENGINE PLUGIN: Suggestion mechanisms
from . import conj
from . import mfsp
from . import phonet
## Verbs
def suggVerb (sFlex, sWho, funcSugg2=None):
aSugg = set()
for sStem in _oSpellChecker.getLemma(sFlex):
tTags = conj._getTags(sStem)
if tTags:
# we get the tense
aTense = set()
for sMorph in _oSpellChecker.getMorph(sFlex):
| > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 |
#### GRAMMAR CHECKING ENGINE PLUGIN: Suggestion mechanisms
from . import conj
from . import mfsp
from . import phonet
## Verbs
def suggVerb (sFlex, sWho, funcSugg2=None):
"change <sFlex> conjugation according to <sWho>"
aSugg = set()
for sStem in _oSpellChecker.getLemma(sFlex):
tTags = conj._getTags(sStem)
if tTags:
# we get the tense
aTense = set()
for sMorph in _oSpellChecker.getMorph(sFlex):
|
| ︙ | ︙ | |||
36 37 38 39 40 41 42 |
if aSugg2:
aSugg.add(aSugg2)
if aSugg:
return "|".join(aSugg)
return ""
| | > | | | | | | | > > > > | 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
if aSugg2:
aSugg.add(aSugg2)
if aSugg:
return "|".join(aSugg)
return ""
def suggVerbPpas (sFlex, sPattern=None):
"suggest past participles for <sFlex>"
aSugg = set()
for sStem in _oSpellChecker.getLemma(sFlex):
tTags = conj._getTags(sStem)
if tTags:
if not sPattern:
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q2"))
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q3"))
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q4"))
aSugg.discard("")
elif sPattern == ":m:s":
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
elif sPattern == ":m:p":
if conj._hasConjWithTags(tTags, ":PQ", ":Q2"):
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q2"))
else:
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
elif sPattern == ":f:s":
if conj._hasConjWithTags(tTags, ":PQ", ":Q3"):
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q3"))
else:
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
elif sPattern == ":f:p":
if conj._hasConjWithTags(tTags, ":PQ", ":Q4"):
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q4"))
else:
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
elif sPattern == ":s":
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q3"))
aSugg.discard("")
elif sPattern == ":p":
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q2"))
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q4"))
aSugg.discard("")
else:
aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
if aSugg:
return "|".join(aSugg)
return ""
def suggVerbTense (sFlex, sTense, sWho):
"change <sFlex> to a verb according to <sTense> and <sWho>"
aSugg = set()
for sStem in _oSpellChecker.getLemma(sFlex):
if conj.hasConj(sStem, sTense, sWho):
aSugg.add(conj.getConj(sStem, sTense, sWho))
if aSugg:
return "|".join(aSugg)
return ""
def suggVerbImpe (sFlex):
"change <sFlex> to a verb at imperative form"
aSugg = set()
for sStem in _oSpellChecker.getLemma(sFlex):
tTags = conj._getTags(sStem)
if tTags:
if conj._hasConjWithTags(tTags, ":E", ":2s"):
aSugg.add(conj._getConjWithTags(sStem, tTags, ":E", ":2s"))
if conj._hasConjWithTags(tTags, ":E", ":1p"):
aSugg.add(conj._getConjWithTags(sStem, tTags, ":E", ":1p"))
if conj._hasConjWithTags(tTags, ":E", ":2p"):
aSugg.add(conj._getConjWithTags(sStem, tTags, ":E", ":2p"))
if aSugg:
return "|".join(aSugg)
return ""
def suggVerbInfi (sFlex):
"returns infinitive forms of <sFlex>"
return "|".join([ sStem for sStem in _oSpellChecker.getLemma(sFlex) if conj.isVerb(sStem) ])
_dQuiEst = { "je": ":1s", "j’": ":1s", "j’en": ":1s", "j’y": ":1s", \
"tu": ":2s", "il": ":3s", "on": ":3s", "elle": ":3s", "nous": ":1p", "vous": ":2p", "ils": ":3p", "elles": ":3p" }
_lIndicatif = [":Ip", ":Iq", ":Is", ":If"]
_lSubjonctif = [":Sp", ":Sq"]
def suggVerbMode (sFlex, cMode, sSuj):
"returns other conjugations of <sFlex> acconding to <cMode> and <sSuj>"
if cMode == ":I":
lMode = _lIndicatif
elif cMode == ":S":
lMode = _lSubjonctif
elif cMode.startswith((":I", ":S")):
lMode = [cMode]
else:
|
| ︙ | ︙ | |||
296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 |
aSugg.add(e)
if aSugg:
return "|".join(aSugg)
return ""
def hasFemForm (sFlex):
for sStem in _oSpellChecker.getLemma(sFlex):
if mfsp.isFemForm(sStem) or conj.hasConj(sStem, ":PQ", ":Q3"):
return True
if phonet.hasSimil(sFlex, ":f"):
return True
return False
def hasMasForm (sFlex):
for sStem in _oSpellChecker.getLemma(sFlex):
if mfsp.isFemForm(sStem) or conj.hasConj(sStem, ":PQ", ":Q1"):
# what has a feminine form also has a masculine form
return True
if phonet.hasSimil(sFlex, ":m"):
return True
return False
def switchGender (sFlex, bPlur=None):
aSugg = set()
if bPlur == None:
for sMorph in _oSpellChecker.getMorph(sFlex):
if ":f" in sMorph:
if ":s" in sMorph:
aSugg.add(suggMasSing(sFlex))
elif ":p" in sMorph:
| > > > | 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
aSugg.add(e)
if aSugg:
return "|".join(aSugg)
return ""
def hasFemForm (sFlex):
"return True if there is a feminine form of <sFlex>"
for sStem in _oSpellChecker.getLemma(sFlex):
if mfsp.isFemForm(sStem) or conj.hasConj(sStem, ":PQ", ":Q3"):
return True
if phonet.hasSimil(sFlex, ":f"):
return True
return False
def hasMasForm (sFlex):
"return True if there is a masculine form of <sFlex>"
for sStem in _oSpellChecker.getLemma(sFlex):
if mfsp.isFemForm(sStem) or conj.hasConj(sStem, ":PQ", ":Q1"):
# what has a feminine form also has a masculine form
return True
if phonet.hasSimil(sFlex, ":m"):
return True
return False
def switchGender (sFlex, bPlur=None):
"return feminine or masculine form(s) of <sFlex>"
aSugg = set()
if bPlur == None:
for sMorph in _oSpellChecker.getMorph(sFlex):
if ":f" in sMorph:
if ":s" in sMorph:
aSugg.add(suggMasSing(sFlex))
elif ":p" in sMorph:
|
| ︙ | ︙ | |||
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 |
aSugg.add(suggFemSing(sFlex))
if aSugg:
return "|".join(aSugg)
return ""
def switchPlural (sFlex):
aSugg = set()
for sMorph in _oSpellChecker.getMorph(sFlex):
if ":s" in sMorph:
aSugg.add(suggPlur(sFlex))
elif ":p" in sMorph:
aSugg.add(suggSing(sFlex))
if aSugg:
return "|".join(aSugg)
return ""
def hasSimil (sWord, sPattern=None):
return phonet.hasSimil(sWord, sPattern)
def suggSimil (sWord, sPattern=None, bSubst=False):
"return list of words phonetically similar to sWord and whom POS is matching sPattern"
aSugg = phonet.selectSimil(sWord, sPattern)
for sMorph in _oSpellChecker.getMorph(sWord):
aSugg.update(conj.getSimil(sWord, sMorph, bSubst))
break
if aSugg:
return "|".join(aSugg)
return ""
def suggCeOrCet (sWord):
if re.match("(?i)[aeéèêiouyâîï]", sWord):
return "cet"
if sWord[0:1] == "h" or sWord[0:1] == "H":
return "ce|cet"
return "ce"
def suggLesLa (sWord):
if any( ":p" in sMorph for sMorph in _oSpellChecker.getMorph(sWord) ):
return "les|la"
return "la"
_zBinary = re.compile("^[01]+$")
def formatNumber (s):
nLen = len(s)
if nLen < 4:
return s
sRes = ""
# nombre ordinaire
nEnd = nLen
while nEnd > 0:
| > > > > > | 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 |
aSugg.add(suggFemSing(sFlex))
if aSugg:
return "|".join(aSugg)
return ""
def switchPlural (sFlex):
"return plural or singular form(s) of <sFlex>"
aSugg = set()
for sMorph in _oSpellChecker.getMorph(sFlex):
if ":s" in sMorph:
aSugg.add(suggPlur(sFlex))
elif ":p" in sMorph:
aSugg.add(suggSing(sFlex))
if aSugg:
return "|".join(aSugg)
return ""
def hasSimil (sWord, sPattern=None):
"return True if there is words phonetically similar to <sWord> (according to <sPattern> if required)"
return phonet.hasSimil(sWord, sPattern)
def suggSimil (sWord, sPattern=None, bSubst=False):
"return list of words phonetically similar to sWord and whom POS is matching sPattern"
aSugg = phonet.selectSimil(sWord, sPattern)
for sMorph in _oSpellChecker.getMorph(sWord):
aSugg.update(conj.getSimil(sWord, sMorph, bSubst))
break
if aSugg:
return "|".join(aSugg)
return ""
def suggCeOrCet (sWord):
"suggest “ce” or “cet” or both according to the first letter of <sWord>"
if re.match("(?i)[aeéèêiouyâîï]", sWord):
return "cet"
if sWord[0:1] == "h" or sWord[0:1] == "H":
return "ce|cet"
return "ce"
def suggLesLa (sWord):
"suggest “les” or “la” according to <sWord>"
if any( ":p" in sMorph for sMorph in _oSpellChecker.getMorph(sWord) ):
return "les|la"
return "la"
_zBinary = re.compile("^[01]+$")
def formatNumber (s):
"add spaces or hyphens to big numbers"
nLen = len(s)
if nLen < 4:
return s
sRes = ""
# nombre ordinaire
nEnd = nLen
while nEnd > 0:
|
| ︙ | ︙ | |||
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 |
elif nLen == 9 and s.startswith("0"):
sRes += "|" + s[0:3] + " " + s[3:5] + " " + s[5:7] + " " + s[7:9] # fixe belge 1
sRes += "|" + s[0:2] + " " + s[2:5] + " " + s[5:7] + " " + s[7:9] # fixe belge 2
return sRes
def formatNF (s):
try:
m = re.match("NF[ -]?(C|E|P|Q|S|X|Z|EN(?:[ -]ISO|))[ -]?([0-9]+(?:[/‑-][0-9]+|))", s)
if not m:
return ""
return "NF " + m.group(1).upper().replace(" ", " ").replace("-", " ") + " " + m.group(2).replace("/", "‑").replace("-", "‑")
except:
traceback.print_exc()
return "# erreur #"
def undoLigature (c):
if c == "fi":
return "fi"
elif c == "fl":
return "fl"
elif c == "ff":
return "ff"
elif c == "ffi":
| > > | 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 |
elif nLen == 9 and s.startswith("0"):
sRes += "|" + s[0:3] + " " + s[3:5] + " " + s[5:7] + " " + s[7:9] # fixe belge 1
sRes += "|" + s[0:2] + " " + s[2:5] + " " + s[5:7] + " " + s[7:9] # fixe belge 2
return sRes
def formatNF (s):
"typography: format NF reference (norme française)"
try:
m = re.match("NF[ -]?(C|E|P|Q|S|X|Z|EN(?:[ -]ISO|))[ -]?([0-9]+(?:[/‑-][0-9]+|))", s)
if not m:
return ""
return "NF " + m.group(1).upper().replace(" ", " ").replace("-", " ") + " " + m.group(2).replace("/", "‑").replace("-", "‑")
except:
traceback.print_exc()
return "# erreur #"
def undoLigature (c):
"typography: split ligature character <c> in several chars"
if c == "fi":
return "fi"
elif c == "fl":
return "fl"
elif c == "ff":
return "ff"
elif c == "ffi":
|
| ︙ | ︙ | |||
461 462 463 464 465 466 467 |
_xNormalizedCharsForInclusiveWriting = str.maketrans({
'(': '_', ')': '_',
'.': '_', '·': '_',
'–': '_', '—': '_',
'/': '_'
| | > | 477 478 479 480 481 482 483 484 485 486 487 488 489 |
_xNormalizedCharsForInclusiveWriting = str.maketrans({
'(': '_', ')': '_',
'.': '_', '·': '_',
'–': '_', '—': '_',
'/': '_'
})
def normalizeInclusiveWriting (sToken):
"typography: replace word separators used in inclusive writing by underscore (_)"
return sToken.translate(_xNormalizedCharsForInclusiveWriting)
|