Overview
| Comment: | [graphspell][py] data memorization |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | graphspell | rg |
| Files: | files | file ages | folders |
| SHA3-256: |
3f84923104b978670536719804e050dc |
| User & Date: | olr on 2018-05-23 08:37:58 |
| Other Links: | branch diff | manifest | tags |
Context
|
2018-05-23
| ||
| 08:46 | [core][py] gc: use spellchecker storage check-in: 445405d362 user: olr tags: core, rg | |
| 08:37 | [graphspell][py] data memorization check-in: 3f84923104 user: olr tags: graphspell, rg | |
|
2018-05-21
| ||
| 13:08 | [build][core] small code cleaning check-in: 29461e1888 user: olr tags: core, build, rg | |
Changes
Modified graphspell/spellchecker.py from [cbd22d2c4d] to [b09975dd6b].
| ︙ | ︙ | |||
32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
self.oExtendedDic = self._loadDictionary(sfExtendedDic)
self.oCommunityDic = self._loadDictionary(sfCommunityDic)
self.oPersonalDic = self._loadDictionary(sfPersonalDic)
self.bExtendedDic = bool(self.oExtendedDic)
self.bCommunityDic = bool(self.oCommunityDic)
self.bPersonalDic = bool(self.oPersonalDic)
self.oTokenizer = None
def _loadDictionary (self, source, bNecessary=False):
"returns an IBDAWG object"
if not source:
return None
try:
return ibdawg.IBDAWG(source)
| > > > > | 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
self.oExtendedDic = self._loadDictionary(sfExtendedDic)
self.oCommunityDic = self._loadDictionary(sfCommunityDic)
self.oPersonalDic = self._loadDictionary(sfPersonalDic)
self.bExtendedDic = bool(self.oExtendedDic)
self.bCommunityDic = bool(self.oCommunityDic)
self.bPersonalDic = bool(self.oPersonalDic)
self.oTokenizer = None
# storage
self.bStorage = False
self._dMorphologies = {} # key: flexion, value: list of morphologies
self._dLemmas = {} # key: flexion, value: list of lemmas
def _loadDictionary (self, source, bNecessary=False):
"returns an IBDAWG object"
if not source:
return None
try:
return ibdawg.IBDAWG(source)
|
| ︙ | ︙ | |||
95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
def deactivateCommunityDictionary (self):
self.bCommunityDic = False
def deactivatePersonalDictionary (self):
self.bPersonalDic = False
# parse text functions
def parseParagraph (self, sText, bSpellSugg=False):
if not self.oTokenizer:
self.loadTokenizer()
aSpellErrs = []
| > > > > > > > > > > > > > | 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 |
def deactivateCommunityDictionary (self):
self.bCommunityDic = False
def deactivatePersonalDictionary (self):
self.bPersonalDic = False
# Storage
def activateStorage (self):
self.bStorage = True
def deactivateStorage (self):
self.bStorage = False
def clearStorage (self):
self._dLemmas.clear()
self._dMorphologies.clear()
# parse text functions
def parseParagraph (self, sText, bSpellSugg=False):
if not self.oTokenizer:
self.loadTokenizer()
aSpellErrs = []
|
| ︙ | ︙ | |||
167 168 169 170 171 172 173 |
return True
if self.bPersonalDic and self.oPersonalDic.lookup(sWord):
return True
return False
def getMorph (self, sWord):
"retrieves morphologies list, different casing allowed"
| > > | | | | > > > | > > > > > | 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
return True
if self.bPersonalDic and self.oPersonalDic.lookup(sWord):
return True
return False
def getMorph (self, sWord):
"retrieves morphologies list, different casing allowed"
if self.bStorage and sWord in self._dMorphologies:
return self._dMorphologies[sWord]
lMorph = self.oMainDic.getMorph(sWord)
if self.bExtendedDic:
lMorph.extend(self.oExtendedDic.getMorph(sWord))
if self.bCommunityDic:
lMorph.extend(self.oCommunityDic.getMorph(sWord))
if self.bPersonalDic:
lMorph.extend(self.oPersonalDic.getMorph(sWord))
if self.bStorage:
self._dMorphologies[sWord] = lMorph
self._dLemmas[sWord] = set([ s[1:s.find(" ")] for s in lMorph ])
return lMorph
def getLemma (self, sWord):
"retrieves lemmas (Warning: if <self.bStorage> then lemmas are returned with the preceding sign “>”)"
if self.bStorage:
if sWord not in self._dLemmas:
self.getMorph(sWord)
return self._dLemmas[sWord]
return set([ s[1:s.find(" ")] for s in self.getMorph(sWord) ])
def suggest (self, sWord, nSuggLimit=10):
"generator: returns 1, 2 or 3 lists of suggestions"
yield self.oMainDic.suggest(sWord, nSuggLimit)
if self.bExtendedDic:
yield self.oExtendedDic.suggest(sWord, nSuggLimit)
|
| ︙ | ︙ |