Grammalecte  Check-in [cee9fdd1aa]

                    if sWord:
                        echo("* " + sWord)
                        for sMorph in oDict.getMorph(sWord):
                            echo("  {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
            elif sText.startswith("!"):
                for sWord in sText[1:].strip().split():
                    if sWord:

                        echo(" | ".join(oDict.suggest(sWord)))

            elif sText.startswith("/+ "):
                gce.setOptions({ opt:True  for opt in sText[3:].strip().split()  if opt in gce.getOptions() })
                echo("done")
            elif sText.startswith("/- "):
                gce.setOptions({ opt:False  for opt in sText[3:].strip().split()  if opt in gce.getOptions() })
                echo("done")
            elif sText.startswith("/-- "):

# list of similar chars
# useful for suggestion mechanism


# Method: Remove Useless Chars

_dUselessChar = {
    'a': '',  'e': '',  'i': '',  'o': '',  'u': '',  'y': '',
    'à': '',  'é': '',  'î': '',  'ô': '',  'û': '',  'ÿ': '',
    'â': '',  'è': '',  'ï': '',  'ö': '',  'ù': '',  'ŷ': '',
    'ä': '',  'ê': '',  'í': '',  'ó': '',  'ü': '',  'ý': '',
    'á': '',  'ë': '',  'ì': '',  'ò': '',  'ú': '',  'ỳ': '',
    'ā': '',  'ē': '',  'ī': '',  'ō': '',  'ū': '',  'ȳ': '',
    'h': '',  'œ': '',  'æ': ''
 }

_CHARMAP = str.maketrans(_dUselessChar)

aUselessChar = frozenset(_dUselessChar.keys())

def clearWord (sWord):
    "remove vovels and h"
    return sWord.translate(_CHARMAP)


# Similar chars

d1to1 = {
    "1": "li",
    "2": "e",
    "3": "e",
    "4": "aà",
    "5": "ge",
    "6": "bd",
    "7": "lt",
    "8": "b",
    "9": "gbd",

    "a": "aàâáäæ",
    "à": "aàâáäæ",
    "â": "aàâáäæ",
    "á": "aàâáäæ",
    "ä": "aàâáäæ",

    "æ": "éa",

    "c": "cçskqśŝ",
    "ç": "cçskqśŝ",

    "e": "eéèêëœ",
    "é": "eéèêëœ",
    "ê": "eéèêëœ",
    "è": "eéèêëœ",
    "ë": "eéèêëœ",

    "f": "fv",

    "g": "gjq",
    
    "i": "iîïylíìÿ",
    "î": "iîïylíìÿ",
    "ï": "iîïylíìÿ",
    "í": "iîïylíìÿ",
    "ì": "iîïylíìÿ",

    "j": "jg",

    "k": "kcq",

    "l": "li",

    "n": "nñr",

    "o": "oôóòöœ",
    "ô": "oôóòöœ",
    "ó": "oôóòöœ",
    "ò": "oôóòöœ",
    "ö": "oôóòöœ",

    "œ": "œoôeéèêë",

    "p": "pb",

    "q": "ckg",

    "r": "rn",

    "s": "sśŝcç",
    "ś": "sśŝcç",
    "ŝ": "sśŝcç",

    "u": "uûùüú",
    "û": "uûùüú",
    "ù": "uûùüú",
    "ü": "uûùüú",
    "ú": "uûùüú",

    "v": "vwf",

    "w": "wv",

    "x": "xck",

    "y": "yÿiîŷýỳ",
    "ÿ": "yÿiîŷýỳ",
    "ŷ": "yÿiîŷýỳ",
    "ý": "yÿiîŷýỳ",
    "ỳ": "yÿiîŷýỳ",

    "z": "zs",
}

d1toX = {
    "æ": ("ae",),
    "b": ("bb",),
    "c": ("cc", "ss", "qu", "ch"),
    "ç": ("ss", "cc", "qh", "ch"),
    "d": ("dd",),
    "f": ("ff", "ph"),
    "g": ("gu", "ge", "gg", "gh"),
    "i": ("ii",),
    "j": ("jj", "dj"),
    "k": ("qu", "ck", "ch", "cu", "kk", "kh"),
    "l": ("ll",),
    "m": ("mm", "mn"),
    "n": ("nn", "nm", "mn"),
    "o": ("au", "eau", "aut"),
    "œ": ("oe", "eu"),
    "p": ("pp", "ph"),
    "q": ("qu", "ch", "cq", "ck", "kk"),
    "r": ("rr",),
    "s": ("ss", "sh"),
    "t": ("tt", "th"),
    "x": ("cc", "ct", "xx"),
    "z": ("ss", "zh")
}

d2toX = {
    "an": ("en",),
    "en": ("an",),
    "ai": ("ei", "é", "è", "ê", "ë"),
    "ei": ("ai", "ait", "ais", "é", "è", "ê", "ë"),
    "ch": ("sh", "c", "ss"),
    "ct": ("x", "cc"),
    "oa": ("oi",),
    "oi": ("oa", "oie"),
    "qu": ("q", "cq", "ck", "c", "k"),
}


# End of word

dFinal1 = {
    "a": ("as", "at", "ant"),

    "e": ("et", "er", "ets", "ée", "ez", "ai", "ais", "ait", "ent"),
    "é": ("et", "er", "ets", "ée", "ez", "ai", "ais", "ait"),
    "è": ("et", "er", "ets", "ée", "ez", "ai", "ais", "ait"),
    "ê": ("et", "er", "ets", "ée", "ez", "ai", "ais", "ait"),
    "ë": ("et", "er", "ets", "ée", "ez", "ai", "ais", "ait"),

    "i": ("is", "it", "ie", "in"),

    "n": ("nt", "nd", "ns"),

    "o": ("aut", "ot", "os"),
    "ô": ("aut", "ot", "os"),
    "ö": ("aut", "ot", "os"),

    "u": ("ut", "us"),
}

dFinal2 = {
    "an": ("ant", "ent"),
    "en": ("ent", "ant"),
    "ei": ("ait", "ais"),
    "on": ("ons", "ont"),
    "oi": ("ois", "oit", "oix"),
}


# Préfixes

aPfx = ("anti", "contre", "mé", "im", "in", "ir", "par", "pré", "re", "ré", "sans", "sous", "sur")


# Keyboards

dBépo = {
    # on présume que le bépoète est moins susceptible de faire des erreurs de frappe que l’azertyste.
    # ligne 2
    "b": "éa",
    "é": "bpu",
    "p": "éoi",
    "o": "pèe",
    "è": "o",
    "v": "dt",
    "d": "vls",
    "l": "djr",
    "j": "lzn",
    "z": "jmw",
    # ligne 3
    "a": "ubà",
    "u": "aiéy",
    "i": "uepx",
    "e": "io",
    "c": "t",
    "t": "csvq",
    "s": "trdg",
    "r": "snlh",
    "n": "rmjf",
    "m": "nzç",
    # ligne 4
    "à": "yêa",
    "y": "àxu",
    "x": "ywi",
    "w": "z",
    "k": "c",
    "q": "gt",
    "g": "qhs",
    "h": "gfr",
    "f": "hçn",
    "ç": "fm",
}

dAzerty = {
    # ligne 1
    "é": "az",
    "è": "yu",
    "ç": "àio",
    "à": "op",
    # ligne 2
    "a": "zéqs",
    "z": "aesqd",
    "e": "zrdsf",
    "r": "etfdg",
    "t": "rygfh",
    "y": "tuhgj",
    "u": "yijhk",
    "i": "uokjl",
    "o": "iplkm",
    "p": "oml",
    # ligne 3
    "q": "sawz",
    "s": "qdzwxe",
    "d": "sfexcr",
    "f": "dgrcvt",
    "g": "fhtvby",
    "h": "gjybnu",
    "j": "hkuni",
    "k": "jlio",
    "l": "kmop",
    "m": "lùp",
    "ù": "m",
    # ligne 4
    "w": "xqs",
    "x": "wcsd",
    "c": "xvdf",
    "v": "cbfg",
    "b": "vngh",
    "n": "bhj",
}

#!python3
# -*- coding: UTF-8 -*-

import os
import traceback
import pkgutil
from itertools import chain

from . import str_transform as st
from . import char_player as cp
from .echo import echo


def show (nDeep, sText):
    print(nDeep * "  " + sText)


class IBDAWG:
    """INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH"""

    def __init__ (self, sDicName):
        self.by = pkgutil.get_data(__package__, "_dictionaries/" + sDicName)
        if not self.by:

        if self.cStemming == "S":
            self.funcStemming = st.changeWordWithSuffixCode
        elif self.cStemming == "A":
            self.funcStemming = st.changeWordWithAffixCode
        else:
            self.funcStemming = st.noStemming
        self.nTag = self.nArcVal - self.nChar - self.nAff
        # <dChar> to get the value of an arc, <dVal> to get the char of an arc with its value
        self.dChar = {}
        for i in range(1, self.nChar):
            self.dChar[self.lArcVal[i]] = i
        self.dVal = { v: k  for k, v in self.dChar.items() }
            
        self._arcMask = (2 ** ((self.nBytesArc * 8) - 3)) - 1
        self._finalNodeMask = 1 << ((self.nBytesArc * 8) - 1)
        self._lastArcMask = 1 << ((self.nBytesArc * 8) - 2)
        self._addrBitMask = 1 << ((self.nBytesArc * 8) - 3)  # version 2

        self.nBytesOffset = 1 # version 3

        # Configuring DAWG functions according to nVersion
        if self.nVersion == 1:
            self.morph = self._morph1
            self.stem = self._stem1
            self._lookupArcNode = self._lookupArcNode1
            self._getArcs = self._getArcs1
            self._writeNodes = self._writeNodes1
        elif self.nVersion == 2:
            self.morph = self._morph2
            self.stem = self._stem2
            self._lookupArcNode = self._lookupArcNode2
            self._getArcs = self._getArcs2
            self._writeNodes = self._writeNodes2
        elif self.nVersion == 3:
            self.morph = self._morph3
            self.stem = self._stem3
            self._getArcs = self._getArcs3
            self._lookupArcNode = self._lookupArcNode3
            self._writeNodes = self._writeNodes3
        else:
            raise ValueError("  # Error: unknown code: {}".format(self.nVersion))

        self.bOptNumSigle = False
        self.bOptNumAtLast = False

            if c not in self.dChar:
                return False
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return False
        return int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask

    def suggest (self, sWord):
        "returns a set of similar words"
        # first, we check for similar words
        return set(self._suggestWithCrushedUselessChars(cp.clearWord(sWord)))
        lSugg = self._suggest(sWord)
        if not lSugg:
            lSugg.extend(self._suggest(sWord[1:]))
            lSugg.extend(self._suggest(sWord[:-1]))
            lSugg.extend(self._suggest(sWord[1:-1]))
            if not lSugg:
                lSugg.extend(self._suggestWithCrushedUselessChars(cp.clearWord(sWord)))
        return set(lSugg)

    def _suggest (self, sWord, cPrevious='', nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
        # RECURSIVE FUNCTION
        if not sWord:
            if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
                show(nDeep, "!!! " + sNewWord + " !!!")
                return [sNewWord]
            return []
        #show(nDeep, "<" + sWord + ">  ===>  " + sNewWord)
        lSugg = []
        cCurrent = sWord[0:1]
        for cChar, jAddr in self._getSimilarArcs(cCurrent, iAddr):
            #show(nDeep, cChar)
            lSugg.extend(self._suggest(sWord[1:], cCurrent, nDeep+1, jAddr, sNewWord+cChar))
        if not bAvoidLoop: # avoid infinite loop
            #show(nDeep, ":no loop:")
            if cPrevious == cCurrent:
                # same char, we remove 1 char without adding 1 to <sNewWord>
                lSugg.extend(self._suggest(sWord[1:], cCurrent, nDeep+1, iAddr, sNewWord))
            for sRepl in cp.d1toX.get(cCurrent, ()):
                #show(nDeep, sRepl)
                lSugg.extend(self._suggest(sRepl + sWord[1:], cCurrent, nDeep+1, iAddr, sNewWord, True))
            if len(sWord) == 1:
                #show(nDeep, ":end of word:")
                # end of word
                for sRepl in cp.dFinal1.get(sWord, ()):
                    #show(nDeep, sRepl)
                    lSugg.extend(self._suggest(sRepl, cCurrent, nDeep+1, iAddr, sNewWord, True))
        return lSugg

    def _getSimilarArcs (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for c in cp.d1to1.get(cChar, [cChar]):
            if c in self.dChar:
                jAddr = self._lookupArcNode(self.dChar[c], iAddr)
                if jAddr:
                    yield (c, jAddr)

    def _suggestWithCrushedUselessChars (self, sWord, cPrevious='', nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
        if not sWord:
            if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
                show(nDeep, "!!! " + sNewWord + " !!!")
                return [sNewWord]
            return []
        lSugg = []
        cCurrent = sWord[0:1]
        for cChar, jAddr in self._getSimilarArcsAndCrushedChars(cCurrent, iAddr):
            show(nDeep, cChar)
            lSugg.extend(self._suggestWithCrushedUselessChars(sWord[1:], cCurrent, nDeep+1, jAddr, sNewWord+cChar))
        return lSugg

    def _getSimilarArcsAndCrushedChars (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for nVal, jAddr in self._getArcs(iAddr):
            if self.dVal.get(nVal, "") in cp.aUselessChar:
                yield (self.dVal[nVal], jAddr)
        for c in cp.d1to1.get(cChar, [cChar]):
            if c in self.dChar:
                jAddr = self._lookupArcNode(self.dChar[c], iAddr)
                if jAddr:
                    yield (c, jAddr)

    def getMorph (self, sWord):
        "retrieves morphologies list, different casing allowed"

                return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
            else:
                # value not found
                if (nRawArc & self._lastArcMask):
                    return None
                iAddr = iEndArcAddr+self.nBytesNodeAddress

    def _getArcs1 (self, iAddr):
        "generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)"
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            yield (nRawArc & self._arcMask, int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big'))
            if (nRawArc & self._lastArcMask):
                break
            iAddr = iEndArcAddr+self.nBytesNodeAddress

    def _writeNodes1 (self, spfDest):
        "for debugging only"
        print(" > Write binary nodes")
        with codecs.open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
            iAddr = 0
            hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
            while iAddr < len(self.byDic):