Grammalecte  Check-in [a5edfddfa8]

Overview
Comment:[build][core] rules graph: merge lemmas in key <lemmas>
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | build | rg
Files: files | file ages | folders
SHA3-256: a5edfddfa854273fcdac6d9054769ce38559d217c8c503cfc6c29a143764478e
User & Date: olr on 2018-05-23 12:19:37
Original Comment: [build][core] agregate lemmas in one node
Other Links: branch diff | manifest | tags
Context
2018-05-24
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
12:10
[graphspell][js][bug] remove prefix sign from lemmas check-in: 13109802df user: olr tags: graphspell, rg
Changes

Modified darg.py from [bf378d22b5] to [7e9f6a7653].

155
156
157
158
159
160
161

162
163
164
165
166







167
168

169
170


171
172
173
174
175
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







+
-
-
-
-
-
+
+
+
+
+
+
+

-
+


+
+





        return self.__str__() == other.__str__()        

    def getNodeAsDict (self):
        "returns the node as a dictionary structure"
        dNode = {}
        dRegex = {}
        dRules = {}
        dLemmas = {}
        for arc, oNode in self.dArcs.items():
            if type(arc) == str and arc.startswith("~"):
                dRegex[arc[1:]] = oNode.__hash__()
            elif arc.startswith("##"):
                dRules[arc[1:]] = oNode.__hash__()
        for sArc, oNode in self.dArcs.items():
            if sArc.startswith("~") and len(sArc) > 1:
                dRegex[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[arc] = oNode.__hash__()
                dNode[sArc] = oNode.__hash__()
        if dRegex:
            dNode["<regex>"] = dRegex
        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 [070a603bc6] to [de8dd5167f].

605
606
607
608
609
610
611

612
613
614



615
616
617
618
619

620
621
622
623

624
625
626
627
628
629
630
605
606
607
608
609
610
611
612



613
614
615
616
617
618
619

620
621
622
623

624
625
626
627
628
629
630
631







+
-
-
-
+
+
+




-
+



-
+







        return dErr

    def _getNextMatchingNodes (self, dToken, dNode):
        # token value
        if dToken["sValue"] in dNode:
            yield dGraph[dNode[dToken["sValue"]]]
        # token lemmas
        if "<lemmas>" in dNode:
        for sLemma in _oSpellChecker.getLemma(dToken["sValue"]):
            if sLemma in dNode:
                yield dGraph[dNode[sLemma]]
            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 arcs
        if "~" in dNode:
        if "<regex>" in dNode:
            for sRegex in dNode["~"]:
                for sMorph in _oSpellChecker.getMorph(dToken["sValue"]):
                    if re.search(sRegex, sMorph):
                        yield dGraph[dNode["~"][sRegex]]
                        yield dGraph[dNode["regex"][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]