Overview
| Comment: | [graphspell] char_player: cut also prefixes for better suggestions |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | trunk | graphspell |
| Files: | files | file ages | folders |
| SHA3-256: |
3955fe867647fb6a77e3dc111e4856ed |
| User & Date: | olr on 2018-05-02 10:29:58 |
| Other Links: | manifest | tags |
Context
|
2018-05-02
| ||
| 11:22 | [graphspell] use nDistLimit to truncate number of suggestions check-in: f3a3ed9041 user: olr tags: trunk, graphspell | |
| 10:29 | [graphspell] char_player: cut also prefixes for better suggestions check-in: 3955fe8676 user: olr tags: trunk, graphspell | |
|
2018-05-01
| ||
| 20:00 | [fr] faux positif: quelle doit/peut être +sujet check-in: ab0e7af2a4 user: olr tags: trunk, fr | |
Changes
Modified graphspell-js/char_player.js from [1bb2f8a481] to [c2f75d3e03].
| ︙ | ︙ | |||
359 360 361 362 363 364 365 |
aPfx2: new Set([
"belgo", "franco", "génito", "gynéco", "médico", "russo"
]),
cut: function (sWord) {
// returns an arry of strings (prefix, trimed_word, suffix)
| > > > > > > > | | > | | 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 |
aPfx2: new Set([
"belgo", "franco", "génito", "gynéco", "médico", "russo"
]),
cut: function (sWord) {
// returns an arry of strings (prefix, trimed_word, suffix)
let sPrefix = "";
let sSuffix = "";
let m = /^([ldmtsnjcç]|lorsqu|presqu|jusqu|puisqu|quoiqu|quelqu|qu)[’'‘`]([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]+)/i.exec(sWord);
if (m) {
sPrefix = m[1] + "’";
sWord = m[2];
}
m = /^([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st]+)(-(?:t-|)(?:ils?|elles?|on|je|tu|nous|vous|ce)$)/i.exec(sWord);
if (m) {
sWord = m[1];
sSuffix = m[2];
}
return [sPrefix, sWord, sSuffix];
},
// Other functions
filterSugg: function (aSugg) {
return aSugg.filter((sSugg) => { return !sSugg.endsWith("è") && !sSugg.endsWith("È"); });
}
|
| ︙ | ︙ |
Modified graphspell/char_player.py from [195969a6df] to [73eee3ee03].
| ︙ | ︙ | |||
348 349 350 351 352 353 354 |
"pseudo", "pré", "re", "ré", "sans", "sous", "supra", "sur", "ultra"
])
aPfx2 = frozenset([
"belgo", "franco", "génito", "gynéco", "médico", "russo"
])
| > | > > | > > > > | > | | 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 |
"pseudo", "pré", "re", "ré", "sans", "sous", "supra", "sur", "ultra"
])
aPfx2 = frozenset([
"belgo", "franco", "génito", "gynéco", "médico", "russo"
])
_zWordPrefixes = re.compile("(?i)^([ldmtsnjcç]|lorsqu|presqu|jusqu|puisqu|quoiqu|quelqu|qu)[’'‘`]([\\w-]+)")
_zWordSuffixes = re.compile("(?i)^(\\w+)(-(?:t-|)(?:ils?|elles?|on|je|tu|nous|vous|ce))$")
def cut (sWord):
"returns a tuple of strings (prefix, trimed_word, suffix)"
sPrefix = ""
sSuffix = ""
m = _zWordPrefixes.search(sWord)
if m:
sPrefix = m.group(1) + "’"
sWord = m.group(2)
m = _zWordSuffixes.search(sWord)
if m:
sWord = m.group(1)
sSuffix = m.group(2)
return (sPrefix, sWord, sSuffix)
# Other functions
def filterSugg (aSugg):
"exclude suggestions"
return filter(lambda sSugg: not sSugg.endswith(("è", "È")), aSugg)
|