Overview
| Comment: | [core] ibdawg: suggestion mechanism update |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | trunk | core |
| Files: | files | file ages | folders |
| SHA3-256: |
5cd4863db37b6c2eb8385e1c0f8567f7 |
| User & Date: | olr on 2017-06-26 08:29:50 |
| Other Links: | manifest | tags |
Context
|
2017-06-26
| ||
| 08:45 | [fr] + 2 tests check-in: 0ff766161c user: olr tags: trunk, fr | |
| 08:29 | [core] ibdawg: suggestion mechanism update check-in: 5cd4863db3 user: olr tags: trunk, core | |
| 07:36 | [core] ibdawg: variable renamed check-in: 6d320f3f8d user: olr tags: trunk, core | |
Changes
Modified gc_core/py/char_player.py from [b5981aec34] to [14cba73827].
| ︙ | ︙ | |||
23 24 25 26 27 28 29 |
return sWord.translate(_CHARMAP)
# Similar chars
d1to1 = {
"1": "li",
| | > | 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
return sWord.translate(_CHARMAP)
# Similar chars
d1to1 = {
"1": "li",
"2": "z",
"3": "e",
"4": "aà",
"5": "ge",
"6": "bd",
"7": "lt",
"8": "b",
"9": "gbd",
"0": "o",
"a": "aàâáäæ",
"à": "aàâáäæ",
"â": "aàâáäæ",
"á": "aàâáäæ",
"ä": "aàâáäæ",
|
| ︙ | ︙ | |||
135 136 137 138 139 140 141 |
"z": ("ss", "zh")
}
d2toX = {
"an": ("en",),
"en": ("an",),
"ai": ("ei", "é", "è", "ê", "ë"),
| | > | 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
"z": ("ss", "zh")
}
d2toX = {
"an": ("en",),
"en": ("an",),
"ai": ("ei", "é", "è", "ê", "ë"),
"ei": ("ai", "é", "è", "ê", "ë"),
"ch": ("sh", "c", "ss"),
"ct": ("x", "cc"),
"oa": ("oi",),
"oi": ("oa", "oie"),
"qu": ("q", "cq", "ck", "c", "k"),
"ss": ("c", "ç"),
}
# End of word
dFinal1 = {
"a": ("as", "at", "ant"),
|
| ︙ | ︙ |
Modified gc_core/py/ibdawg.py from [9784b032d7] to [303901f49a].
| ︙ | ︙ | |||
150 151 152 153 154 155 156 |
if "’" in sWord: # ugly hack
sWord = sWord.replace("’", "'")
if self.lookup(sWord):
return True
if sWord[0:1].isupper():
if len(sWord) > 1:
if sWord.istitle():
| | | | | | | > > > | 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
if "’" in sWord: # ugly hack
sWord = sWord.replace("’", "'")
if self.lookup(sWord):
return True
if sWord[0:1].isupper():
if len(sWord) > 1:
if sWord.istitle():
return self.lookup(sWord.lower())
if sWord.isupper():
if self.bOptNumSigle:
return True
return self.lookup(sWord.lower()) or self.lookup(sWord.capitalize())
return self.lookup(sWord[:1].lower() + sWord[1:])
else:
return self.lookup(sWord.lower())
return False
def lookup (self, sWord):
"returns True if <sWord> in dictionary (strict verification)"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return False
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr == None:
return False
return bool(int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask)
def suggest (self, sWord):
"returns a set of similar words"
# first, we check for similar words
#return set(self._suggestWithCrushedUselessChars(cp.clearWord(sWord)))
lSugg = self._suggest(sWord)
if not lSugg:
lSugg.extend(self._suggest(sWord[1:]))
lSugg.extend(self._suggest(sWord[:-1]))
lSugg.extend(self._suggest(sWord[1:-1]))
if not lSugg:
lSugg.extend(self._suggestWithCrushedUselessChars(cp.clearWord(sWord)))
return set(lSugg)
def _suggest (self, sWord, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
# RECURSIVE FUNCTION
if not sWord:
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
show(nDeep, "___" + sNewWord + "___")
return [sNewWord]
return []
#show(nDeep, "<" + sWord + "> ===> " + sNewWord)
lSugg = []
cCurrent = sWord[0:1]
for cChar, jAddr in self._getSimilarArcs(cCurrent, iAddr):
#show(nDeep, cChar)
lSugg.extend(self._suggest(sWord[1:], nDeep+1, jAddr, sNewWord+cChar))
if not bAvoidLoop: # avoid infinite loop
#show(nDeep, ":no loop:")
if cCurrent == sWord[1:2]:
# same char, we remove 1 char without adding 1 to <sNewWord>
lSugg.extend(self._suggest(sWord[1:], nDeep+1, iAddr, sNewWord))
for sRepl in cp.d1toX.get(cCurrent, ()):
#show(nDeep, sRepl)
lSugg.extend(self._suggest(sRepl + sWord[1:], nDeep+1, iAddr, sNewWord, True))
for sRepl in cp.d2toX.get(sWord[0:2], ()):
#show(nDeep, sRepl)
lSugg.extend(self._suggest(sRepl + sWord[2:], nDeep+1, iAddr, sNewWord, True))
if len(sWord) == 2:
for sRepl in cp.dFinal2.get(sWord, ()):
#show(nDeep, sRepl)
lSugg.extend(self._suggest(sRepl, nDeep+1, iAddr, sNewWord, True))
elif len(sWord) == 1:
#show(nDeep, ":end of word:")
# end of word
|
| ︙ | ︙ |