Overview
| Comment: | [build] darg: regex for multi-token morphologies |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | build | mtok |
| Files: | files | file ages | folders |
| SHA3-256: |
1e120c280b156e231a4aaf70cece5e3f |
| User & Date: | olr on 2021-03-10 19:39:58 |
| Other Links: | branch diff | manifest | tags |
Context
|
2021-03-10
| ||
| 19:54 | [core] gc engine: regex for multi-tokens [fr] tests check-in: 3e55498f43 user: olr tags: fr, core, mtok | |
| 19:39 | [build] darg: regex for multi-token morphologies check-in: 1e120c280b user: olr tags: build, mtok | |
|
2021-03-09
| ||
| 17:23 | [fr] action du processeur de texte -> dans les règles par § uniquement check-in: 684b825f2a user: olr tags: fr, mtok | |
Changes
Modified darg.py from [f98928fa4d] to [6cee0c2543].
| ︙ | ︙ | |||
212 213 214 215 216 217 218 |
# Used as a key in a python dictionary.
# Nodes are equivalent if they have identical arcs, and each identical arc leads to identical states.
return self.__str__() == other.__str__()
def getNodeAsDict (self):
"returns the node as a dictionary structure"
dNode = {}
| | | | > > > > > | 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 |
# Used as a key in a python dictionary.
# Nodes are equivalent if they have identical arcs, and each identical arc leads to identical states.
return self.__str__() == other.__str__()
def getNodeAsDict (self):
"returns the node as a dictionary structure"
dNode = {}
dReValue = {} # regex for token values
dReMorph = {} # regex for morph
dMorph = {} # simple search in morph
dReMultiMorph = {} # regex for morph in multi-tokens
dLemma = {}
dPhonet = {}
dMeta = {}
dTag = {}
dRule = {}
for sArc, oNode in self.dArcs.items():
if sArc.startswith("@") and len(sArc) > 1:
dReMorph[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("$") and len(sArc) > 1:
dMorph[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("&") and len(sArc) > 1:
dReMultiMorph[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("~") and len(sArc) > 1:
dReValue[sArc[1:]] = oNode.__hash__()
elif sArc.startswith(">") and len(sArc) > 1:
dLemma[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("%") and len(sArc) > 1:
dPhonet[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("*") and len(sArc) > 1:
dMeta[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("/") and len(sArc) > 1:
dTag[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("##"):
dRule[sArc[1:]] = oNode.__hash__()
else:
dNode[sArc] = oNode.__hash__()
if dReValue:
dNode["<re_value>"] = dReValue
if dReMorph:
dNode["<re_morph>"] = dReMorph
if dReMultiMorph:
dNode["<re_mmorph>"] = dReMultiMorph
if dMorph:
dNode["<morph>"] = dMorph
if dLemma:
dNode["<lemmas>"] = dLemma
if dPhonet:
dNode["<phonet>"] = dPhonet
if dTag:
|
| ︙ | ︙ |