Overview
| Comment: | [build][core] regex for token value and token morphologies |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | core | build | rg |
| Files: | files | file ages | folders |
| SHA3-256: |
fea041c0de3be9452eb414a624da8f5e |
| User & Date: | olr on 2018-05-24 09:25:29 |
| Other Links: | branch diff | manifest | tags |
Context
|
2018-05-24
| ||
| 11:13 | [build][bug] darg: wrong statement check-in: c4ce706a6b user: olr tags: build, rg | |
| 09:25 | [build][core] regex for token value and token morphologies check-in: fea041c0de user: olr tags: core, build, rg | |
|
2018-05-23
| ||
| 12:19 | [build][core] rules graph: merge lemmas in key <lemmas> check-in: a5edfddfa8 user: olr tags: core, build, rg | |
Changes
Modified darg.py from [7e9f6a7653] to [e83ec424d3].
| ︙ | ︙ | |||
153 154 155 156 157 158 159 |
# 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 = {}
| | > > > | | | | > > | 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 |
# 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 = {}
dReMorph = {}
dRules = {}
dLemmas = {}
for sArc, oNode in self.dArcs.items():
if sArc.startswith("~~") and len(sArc) > 2:
dReMorph[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("~") and len(sArc) > 1:
dReValue[sArc[1:]] = oNode.__hash__()
elif sArc.startswith(">") and len(sArc) > 1:
dLemmas[sArc[1:]] = oNode.__hash__()
elif sArc.startswith("##"):
dRules[sArc[1:]] = oNode.__hash__()
else:
dNode[sArc] = oNode.__hash__()
if dReValue:
dNode["<re_value>"] = dReValue
il dReMorph:
dNode["<re_morph>"] = dReMorph
if dLemmas:
dNode["<lemmas>"] = dLemmas
if dRules:
dNode["<rules>"] = dRules
#if self.bFinal:
# dNode["<final>"] = 1
return dNode
|
Modified gc_core/py/lang_core/gc_engine.py from [de8dd5167f] to [db19c73d82].
| ︙ | ︙ | |||
612 613 614 615 616 617 618 |
if "<lemmas>" in dNode:
for sLemma in _oSpellChecker.getLemma(dToken["sValue"]):
if sLemma in dNode["<lemmas>"]:
yield dGraph[dNode["<lemmas>"][sLemma]]
# universal arc
if "*" in dNode:
yield dGraph[dNode["*"]]
| | | | > > > > > | | 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 |
if "<lemmas>" in dNode:
for sLemma in _oSpellChecker.getLemma(dToken["sValue"]):
if sLemma in dNode["<lemmas>"]:
yield dGraph[dNode["<lemmas>"][sLemma]]
# universal arc
if "*" in dNode:
yield dGraph[dNode["*"]]
# regex value arcs
if "<re_value>" in dNode:
for sRegex in dNode["<re_value>"]:
if re.search(sRegex, dToken["sValue"]):
yield dGraph[dNode["<re_value>"][sRegex]]
# regex morph arcs
if "<re_morph>" in dNode:
for sRegex in dNode["<re_morph>"]:
for sMorph in _oSpellChecker.getMorph(dToken["sValue"]):
if re.search(sRegex, sMorph):
yield dGraph[dNode["<re_morph>"][sRegex]]
def _executeActions (self, dNode, nOffset):
for sLineId, nextNodeKey in dNode.items():
for sArc in dGraph[nextNodeKey]:
print(sArc)
bCondMemo = None
sFuncCond, cActionType, sWhat, *eAct = dRule[sArc]
|
| ︙ | ︙ |