Overview
| Comment: | [graphspell] deprecated code |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | trunk | graphspell |
| Files: | files | file ages | folders |
| SHA3-256: |
c915d50f4a27d7f9a93029b73584b1c6 |
| User & Date: | olr on 2018-01-02 10:30:48 |
| Other Links: | manifest | tags |
Context
|
2018-01-03
| ||
| 15:47 | [build] fix build check-in: ba196f2521 user: olr tags: trunk, build | |
|
2018-01-02
| ||
| 10:30 | [graphspell] deprecated code check-in: c915d50f4a user: olr tags: trunk, graphspell | |
|
2017-12-31
| ||
| 13:24 | [fr] màj: impératif check-in: d1c4b065e9 user: olr tags: trunk, fr | |
Changes
Modified graphspell/dawg.py from [eb4c8506bd] to [1a8e51e627].
| ︙ | ︙ | |||
25 26 27 28 29 30 31 |
for sLine in hSrc:
sLine = sLine.strip()
if sLine and not sLine.startswith("#"):
yield sLine
else:
raise OSError("# Error. File not found or not loadable: " + spf)
| < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
for sLine in hSrc:
sLine = sLine.strip()
if sLine and not sLine.startswith("#"):
yield sLine
else:
raise OSError("# Error. File not found or not loadable: " + spf)
class DAWG:
"""DIRECT ACYCLIC WORD GRAPH"""
# This code is inspired from Steve Hanov’s DAWG, 2011. (http://stevehanov.ca/blog/index.php?id=115)
# We store suffix/affix codes and tags within the graph after the “real” word.
# A word is a list of numbers [ c1, c2, c3 . . . cN, iAffix, iTags]
|
| ︙ | ︙ | |||
101 102 103 104 105 106 107 |
lEntry = []
lChar = ['']; dChar = {}; nChar = 1; dCharOccur = {}
lAff = []; dAff = {}; nAff = 0; dAffOccur = {}
lTag = []; dTag = {}; nTag = 0; dTagOccur = {}
nErr = 0
# read lexicon
| > | | 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
lEntry = []
lChar = ['']; dChar = {}; nChar = 1; dCharOccur = {}
lAff = []; dAff = {}; nAff = 0; dAffOccur = {}
lTag = []; dTag = {}; nTag = 0; dTagOccur = {}
nErr = 0
# read lexicon
for sLine in readFile(spfSrc):
sFlex, sStem, sTag = sLine.split("\t")
addWordToCharDict(sFlex)
# chars
for c in sFlex:
if c not in dChar:
dChar[c] = nChar
lChar.append(c)
nChar += 1
|
| ︙ | ︙ |