Grammalecte  Check-in [5b8ec019ea]

Overview
Comment:[core] function morphx for multi-token
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | mtok
Files: files | file ages | folders
SHA3-256: 5b8ec019ea5f6028e05d558912d0eabf9bc928c5cbb03dbc476ed75e65f2797c
User & Date: olr on 2021-03-12 15:49:47
Other Links: branch diff | manifest | tags
Context
2021-03-12
16:01
[core] morph0: remove useless parameter check-in: 5e7ea4059b user: olr tags: core, mtok
15:49
[core] function morphx for multi-token check-in: 5b8ec019ea user: olr tags: core, mtok
2021-03-10
20:02
[core] gc engine: better names for vars and functions check-in: 82ff352fc9 user: olr tags: core, mtok
Changes

Modified compile_rules_graph.py from [d24797f23b] to [06ce437ce4].

34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
def rewriteCode (sCode):
    "convert simple code syntax to a string of Python code"
    if sCode[0:1] == "=":
        sCode = sCode[1:]
    sCode = sCode.replace("__also__", "bCondMemo")
    sCode = sCode.replace("__else__", "not bCondMemo")
    sCode = sCode.replace("sContext", "_sAppContext")
    sCode = re.sub(r"\b(morph0?|morphVC|value|tag|meta|info)[(]\\(\d+)", 'g_\\1(lToken[nTokenOffset+\\2]', sCode)
    sCode = re.sub(r"\b(morph0?|morphVC|value|tag|meta|info)[(]\\-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', sCode)
    sCode = re.sub(r"\b(select|define|definefrom|rewrite|addmorph|setmeta)[(][\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2]', sCode)
    sCode = re.sub(r"\b(select|define|definefrom|rewrite|addmorph|setmeta)[(][\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\](\d+), *[\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2], lToken[nTokenOffset+\\3]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\](\d+), *[\\]-(\d+)", 'g_\\1(lToken[nTokenOffset+\\2], lToken[nLastToken-\\3+1]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\]-(\d+), *[\\](\d+)", 'g_\\1(lToken[nLastToken-\\2+1], lToken[nTokenOffset+\\3]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\]-(\d+), *[\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1], lToken[nLastToken-\\3+1]', sCode)
    sCode = re.sub(r"\b(tagbefore|tagafter)[(][\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2], dTags', sCode)







|
|







34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
def rewriteCode (sCode):
    "convert simple code syntax to a string of Python code"
    if sCode[0:1] == "=":
        sCode = sCode[1:]
    sCode = sCode.replace("__also__", "bCondMemo")
    sCode = sCode.replace("__else__", "not bCondMemo")
    sCode = sCode.replace("sContext", "_sAppContext")
    sCode = re.sub(r"\b(morph[02x]?|morphVC|value|tag|meta|info)[(]\\(\d+)", 'g_\\1(lToken[nTokenOffset+\\2]', sCode)
    sCode = re.sub(r"\b(morph[02x]?|morphVC|value|tag|meta|info)[(]\\-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', sCode)
    sCode = re.sub(r"\b(select|define|definefrom|rewrite|addmorph|setmeta)[(][\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2]', sCode)
    sCode = re.sub(r"\b(select|define|definefrom|rewrite|addmorph|setmeta)[(][\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\](\d+), *[\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2], lToken[nTokenOffset+\\3]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\](\d+), *[\\]-(\d+)", 'g_\\1(lToken[nTokenOffset+\\2], lToken[nLastToken-\\3+1]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\]-(\d+), *[\\](\d+)", 'g_\\1(lToken[nLastToken-\\2+1], lToken[nTokenOffset+\\3]', sCode)
    sCode = re.sub(r"\b(agreement|suggAgree)[(][\\]-(\d+), *[\\]-(\d+)", 'g_\\1(lToken[nLastToken-\\2+1], lToken[nLastToken-\\3+1]', sCode)
    sCode = re.sub(r"\b(tagbefore|tagafter)[(][\\](\d+)", 'g_\\1(lToken[nTokenOffset+\\2], dTags', sCode)

Modified gc_core/js/lang_core/gc_engine.js from [f3abee6b18] to [95c9d7785e].

776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
                                let nTokenEnd = (eAct[1] > 0) ? nTokenOffset + eAct[1] : nLastToken + eAct[1];
                                let oMultiToken = {
                                    "nTokenStart": nTokenStart,
                                    "nTokenEnd": nTokenEnd,
                                    "lTokens": this.lTokens.slice(nTokenStart, nTokenEnd+1),
                                    "lMorph": (sAction) ? sAction.split("|") : [":HM"]
                                }
                                this.lTokens[nTokenStart]["nMultiStartTo"] = nTokenEnd
                                this.lTokens[nTokenEnd]["nMultiEndFrom"] = nTokenStart
                                this.lTokens[nTokenStart]["dMultiToken"] = dMultiToken
                                this.lTokens[nTokenEnd]["dMultiToken"] = dMultiToken
                            }
                            else {
                                console.log("# error: unknown action at " + sLineId);
                            }
                        }
                        else if (cActionType == ">") {
                            if (bDebug) {







|
|
|
|







776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
                                let nTokenEnd = (eAct[1] > 0) ? nTokenOffset + eAct[1] : nLastToken + eAct[1];
                                let oMultiToken = {
                                    "nTokenStart": nTokenStart,
                                    "nTokenEnd": nTokenEnd,
                                    "lTokens": this.lTokens.slice(nTokenStart, nTokenEnd+1),
                                    "lMorph": (sAction) ? sAction.split("|") : [":HM"]
                                }
                                this.lTokens[nTokenStart]["nMultiStartTo"] = nTokenEnd;
                                this.lTokens[nTokenEnd]["nMultiEndFrom"] = nTokenStart;
                                this.lTokens[nTokenStart]["oMultiToken"] = oMultiToken;
                                this.lTokens[nTokenEnd]["oMultiToken"] = oMultiToken;
                            }
                            else {
                                console.log("# error: unknown action at " + sLineId);
                            }
                        }
                        else if (cActionType == ">") {
                            if (bDebug) {

Modified gc_core/js/lang_core/gc_functions.js from [d31e5f26d5] to [a39656dcfa].

217
218
219
220
221
222
223

























224
225
226
227
228
229
230
            }
        } else {
            lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
        }
    }
    if (lMorph.length == 0) {
        return false;

























    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







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
            }
        } else {
            lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
        }
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function g_morphx (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null) {
    // analyse a multi-token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    if (!oToken.hasOwnProperty("oMultiToken")) {
        return false;
    }
    let lMorph = oToken["oMultiToken"]["lMorph"];
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }

Modified gc_core/py/lang_core/gc_functions.py from [069bca6c44] to [f3b5d69c50].

196
197
198
199
200
201
202





















203
204
205
206
207
208
209
        if nLeft is not None:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
            if bMemorizeMorph:
                dToken["lMorph"] = lMorph
        else:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:





















        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
        if nLeft is not None:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
            if bMemorizeMorph:
                dToken["lMorph"] = lMorph
        else:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def g_morphx (dToken, sPattern, sNegPattern):
    "analyse a multi-token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies"
    if not "dMultiToken" in dToken:
        return False
    lMorph = dToken["dMultiToken"]["lMorph"]
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)