Grammalecte  Check-in [7fd21ca8e0]

    s = re.sub(r"isRealStart *\(\)", 'before(["<START>"])', s)
    s = re.sub(r"isStart0 *\(\)", 'before0(["<START>", ","])', s)
    s = re.sub(r"isRealStart0 *\(\)", 'before0(["<START>"])', s)
    s = re.sub(r"isEnd *\(\)", 'after(["<END>", ","])', s)
    s = re.sub(r"isRealEnd *\(\)", 'after(["<END>"])', s)
    s = re.sub(r"isEnd0 *\(\)", 'after0(["<END>", ","])', s)
    s = re.sub(r"isRealEnd0 *\(\)", 'after0(["<END>"])', s)
    s = re.sub(r"(select|exclude)[(][\\](\d+)", '\\1(lToken[\\2]', s)
    s = re.sub(r"(select|exclude|define)[(][\\](\d+)", 'g_\\1(lToken[\\2+nTokenOffset]', s)
    s = re.sub(r"define[(][\\](\d+)", 'define(lToken[\\1]', s)
    s = re.sub(r"(morph|morphex|displayInfo)[(]\\(\d+)", '\\1(lToken[\\2]', s)
    s = re.sub(r"(morph|morphex|displayInfo)[(]\\(\d+)", 'g_\\1(lToken[\\2+nTokenOffset]', s)
    s = re.sub(r"token\(\s*(\d)", 'nextToken(\\1', s)                                       # token(n)
    s = re.sub(r"token\(\s*-(\d)", 'prevToken(\\1', s)                                      # token(-n)
    s = re.sub(r"before\(\s*", 'look(s[:m.start()], ', s)                                   # before(s)
    s = re.sub(r"after\(\s*", 'look(s[m.end():], ', s)                                      # after(s)
    s = re.sub(r"textarea\(\s*", 'look(s, ', s)                                             # textarea(s)
    s = re.sub(r"before_chk1\(\s*", 'look_chk1(dDA, s[:m.start()], 0, ', s)                 # before_chk1(s)
    s = re.sub(r"after_chk1\(\s*", 'look_chk1(dDA, s[m.end():], m.end(), ', s)              # after_chk1(s)
    s = re.sub(r"textarea_chk1\(\s*", 'look_chk1(dDA, s, 0, ', s)                           # textarea_chk1(s)
    s = re.sub(r"isEndOfNG\(\s*\)", 'isEndOfNG(dDA, s[m.end():], m.end())', s)              # isEndOfNG(s)
    s = re.sub(r"isNextNotCOD\(\s*\)", 'isNextNotCOD(dDA, s[m.end():], m.end())', s)        # isNextNotCOD(s)
    s = re.sub(r"isNextVerb\(\s*\)", 'isNextVerb(dDA, s[m.end():], m.end())', s)            # isNextVerb(s)
    #s = re.sub(r"isEndOfNG\(\s*\)", 'isEndOfNG(dDA, s[m.end():], m.end())', s)              # isEndOfNG(s)
    #s = re.sub(r"isNextNotCOD\(\s*\)", 'isNextNotCOD(dDA, s[m.end():], m.end())', s)        # isNextNotCOD(s)
    #s = re.sub(r"isNextVerb\(\s*\)", 'isNextVerb(dDA, s[m.end():], m.end())', s)            # isNextVerb(s)
    s = re.sub(r"\bspell *[(]", '_oSpellChecker.isValid(', s)
    s = re.sub(r"[\\](\d+)", 'lToken[\\1]', s)
    return s


def genTokenLines (sTokenLine):
    "tokenize a string and return a list of lines of tokens"

    # creating file with all functions callable by rules
    print("  creating callables...")
    sPyCallables = "# generated code, do not edit\n"
    #sJSCallables = "// generated code, do not edit\nconst oEvalFunc = {\n"
    for sFuncName, sReturn in lFUNCTIONS:
        if sFuncName.startswith("g_c_"): # condition
            sParams = "lToken, sCountry, bCondMemo"
            sParams = "lToken, nTokenOffset, sCountry, bCondMemo"
        elif sFuncName.startswith("g_m_"): # message
            sParams = "lToken"
        elif sFuncName.startswith("g_s_"): # suggestion
            sParams = "lToken"
        elif sFuncName.startswith("g_p_"): # preprocessor
            sParams = "lToken"
        elif sFuncName.startswith("g_d_"): # disambiguator

            lPointer.extend(lNewPointer)
            # check arcs of first nodes
            for dNode in self._getNextMatchingNodes(dToken, dGraph[0]):
                lPointer.append({"nOffset": dToken["i"], "dNode": dNode})
            # check if there is rules to check for each pointer
            for dPointer in lPointer:
                if "<rules>" in dPointer["dNode"]:
                    bHasChanged, errs = self._executeActions(dPointer["dNode"]["<rules>"], dPointer["nOffset"]-1, dPriority, dOpt, bShowRuleId, bContext)
                    bHasChanged, errs = self._executeActions(dPointer["dNode"]["<rules>"], dPointer["nOffset"]-1, dPriority, dOpt, sCountry, bShowRuleId, bContext)
                    dErr.update(errs)
                    if bHasChanged:
                        bChange = True
        if dErr:
            print(dErr)
        return (bChange, dErr)

    def _executeActions (self, dNode, nTokenOffset, dPriority, dOpt, bShowRuleId, bContext):
    def _executeActions (self, dNode, nTokenOffset, dPriority, dOpt, sCountry, bShowRuleId, bContext):
        #print(locals())
        dErrs = {}
        bChange = False
        for sLineId, nextNodeKey in dNode.items():
            for sRuleId in dGraph[nextNodeKey]:
                print(sRuleId)
                bCondMemo = None
                sFuncCond, cActionType, sWhat, *eAct = dRule[sRuleId]
                # action in lActions: [ condition, action type, replacement/suggestion/action[, iTokenStart, iTokenEnd[, nPriority, message, URL]] ]
                try:
                    bCondMemo = not sFuncCond or globals()[sFuncCond](self, sCountry, bCondMemo)
                    bCondMemo = not sFuncCond or globals()[sFuncCond](self.lToken, nTokenOffset, sCountry, bCondMemo)
                    if bCondMemo:
                        if cActionType == "-":
                            # grammar error
                            print("-")
                            nTokenErrorStart = nTokenOffset + eAct[0]
                            nTokenErrorEnd = nTokenOffset + eAct[1]
                            nErrorStart = self.iStart + self.lToken[nTokenErrorStart]["nStart"]

    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)


#### Go outside the rule scope

def g_nextToken (i):
    pass

def g_prevToken (i):
    pass

def g_look ():
    pass

def g_lookAndCheck ():
    pass


#### Disambiguator

def g_select (dToken, sPattern, lDefault=None):
    "select morphologies for <dToken> according to <sPattern>, always return True"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph or len(lMorph) == 1: