Overview
| Comment: | [graphspell] code cleaning |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | graphspell | bdic_opt |
| Files: | files | file ages | folders |
| SHA3-256: |
9df0f3e6b2bb9d4c531ce09da69d2a9d |
| User & Date: | olr on 2020-09-12 12:54:44 |
| Other Links: | branch diff | manifest | tags |
Context
|
2020-09-14
| ||
| 13:29 | [graphspell] distance Jaro-Winkler check-in: 45fdbe84fa user: olr tags: graphspell, bdic_opt | |
|
2020-09-12
| ||
| 12:54 | [graphspell] code cleaning check-in: 9df0f3e6b2 user: olr tags: graphspell, bdic_opt | |
| 12:45 | [graphspell][py] ibdawg: code cleaning, remove version 2 and 3, never used check-in: 4fa9631623 user: olr tags: graphspell, bdic_opt | |
Changes
Modified graphspell-js/ibdawg.js from [baafc4cde1] to [8da6e7122c].
| ︙ | ︙ | |||
486 487 488 489 490 491 492 |
aTails.gl_update(this._getTails(jAddr, sTail+this.dCharVal.get(nVal), n-1));
}
}
}
return aTails;
}
| < < < < | 486 487 488 489 490 491 492 493 494 495 496 497 498 499 |
aTails.gl_update(this._getTails(jAddr, sTail+this.dCharVal.get(nVal), n-1));
}
}
}
return aTails;
}
getSimilarEntries (sWord, nSuggLimit=10) {
// return a list of tuples (similar word, stem, morphology)
if (sWord == "") {
return [];
}
let lResult = [];
for (let sSimilar of this.suggest(sWord, nSuggLimit)) {
|
| ︙ | ︙ |
Modified graphspell/ibdawg.py from [258f41f141] to [bda5a789eb].
| ︙ | ︙ | |||
139 140 141 142 143 144 145 |
nAcc = nAcc + 1
self.byDic = lTemp;
# masks
self._arcMask = (2 ** ((self.nBytesArc * 8) - 3)) - 1
self._finalNodeMask = 1 << ((self.nBytesArc * 8) - 1)
self._lastArcMask = 1 << ((self.nBytesArc * 8) - 2)
| < | 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
nAcc = nAcc + 1
self.byDic = lTemp;
# masks
self._arcMask = (2 ** ((self.nBytesArc * 8) - 3)) - 1
self._finalNodeMask = 1 << ((self.nBytesArc * 8) - 1)
self._lastArcMask = 1 << ((self.nBytesArc * 8) - 2)
# function to decode the affix/suffix code
if self.cStemming == "S":
self.funcStemming = st.changeWordWithSuffixCode
elif self.cStemming == "A":
self.funcStemming = st.changeWordWithAffixCode
else:
|
| ︙ | ︙ | |||
198 199 200 201 202 203 204 |
self.cStemming = l.pop(0)
self.nTag = self.nArcVal - self.nChar - self.nAff
# <dChar> to get the value of an arc, <dCharVal> to get the char of an arc with its value
self.dChar = {}
for i in range(1, self.nChar+1):
self.dChar[self.lArcVal[i]] = i
self.dCharVal = { v: k for k, v in self.dChar.items() }
| < | 197 198 199 200 201 202 203 204 205 206 207 208 209 210 |
self.cStemming = l.pop(0)
self.nTag = self.nArcVal - self.nChar - self.nAff
# <dChar> to get the value of an arc, <dCharVal> to get the char of an arc with its value
self.dChar = {}
for i in range(1, self.nChar+1):
self.dChar[self.lArcVal[i]] = i
self.dCharVal = { v: k for k, v in self.dChar.items() }
def _initJSON (self, oJSON):
"initialize with a JSON text file"
self.sByDic = "" # init to prevent pylint whining
self.__dict__.update(oJSON)
self.byDic = binascii.unhexlify(self.sByDic)
self.dCharVal = { v: k for k, v in self.dChar.items() }
|
| ︙ | ︙ | |||
242 243 244 245 246 247 248 |
"nNode": self.nNode,
"nArc": self.nArc,
"nArcVal": self.nArcVal,
"lArcVal": self.lArcVal,
"nCompressionMethod": self.nCompressionMethod,
"nBytesArc": self.nBytesArc,
"nBytesNodeAddress": self.nBytesNodeAddress,
| < | 240 241 242 243 244 245 246 247 248 249 250 251 252 253 |
"nNode": self.nNode,
"nArc": self.nArc,
"nArcVal": self.nArcVal,
"lArcVal": self.lArcVal,
"nCompressionMethod": self.nCompressionMethod,
"nBytesArc": self.nBytesArc,
"nBytesNodeAddress": self.nBytesNodeAddress,
# JavaScript is a pile of shit, so Mozilla’s JS parser don’t like file bigger than 4 Mb!
# So, if necessary, we use an hexadecimal string, that we will convert later in Firefox’s extension.
# https://github.com/mozilla/addons-linter/issues/1361
"sByDic": self.byDic.hex() if bBinaryDictAsHexString else [ e for e in self.byDic ],
"l2grams": list(self.a2grams)
}, ensure_ascii=False))
if bInJSModule:
|
| ︙ | ︙ |