Grammalecte  Diff

import platform

import graphspell.ibdawg as ibdawg
from graphspell.echo import echo
from graphspell.str_transform import defineSuffixCode
import graphspell.tokenizer as tkz

import gc_lang.fr.modules.conj as conj


oDict = None


class cd:
    """Context manager for changing the current working directory"""
    def __init__ (self, newPath):

        open(sp+"/modules-js/mfsp_data.json", "w", encoding="utf-8", newline="\n").write(sCode)


def makePhonetTable (sp, bJS=False):
    print("> Correspondances phonétiques ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")



    loadDictionary()

    # set of homophonic words
    lSet = []
    for sLine in readFile(sp+"/data/phonet_simil.txt"):
        lWord = sLine.split()

        for sWord in lWord:
            if sWord.endswith("er") and conj.isVerb(sWord):
                lWord.extend(conj.getConjSimilInfiV1(sWord))

        lSet.append(set(lWord))

    # dictionary of words
    dWord = {}
    aMultiSetWord = set()
    lNewSet = []
    nAppend = 0
    for i, aSet in enumerate(lSet):
        for sWord in aSet:
            if oDict.lookup(sWord):
                if sWord not in dWord:
                    dWord[sWord] = i
                else:
                    # word in several set
                    aMultiSetWord.add(sWord)
                    iSet = dWord[sWord]
                    lNewSet.append(lSet[iSet].union(aSet))
                    dWord[sWord] = len(lSet) + nAppend
                    nAppend += 1
            else:
                echo(f"  Mot inconnu : <{sWord}>")
    lSet.extend(lNewSet)
    lSet = [ sorted(aSet) for aSet in lSet ]
    print("  Mots appartenant à plusieurs ensembles: ", ", ".join(aMultiSetWord))

    # dictionary of morphologies
    dMorph = {}
    for sWord in dWord:
        dMorph[sWord] = oDict.getMorph(sWord)

    # write file for Python
    sCode = "# generated data built in build_data.py (do not edit)\n\n" + \
            "dWord = " + str(dWord) + "\n\n" + \
            "lSet = " + str(lSet) + "\n\n" + \
            "dMorph = " + str(dMorph) + "\n"
    open(sp+"/modules/phonet_data.py", "w", encoding="utf-8", newline="\n").write(sCode)

    if bJS:
        ## write file for JavaScript

    print("========== Build Hunspell dictionaries ==========")
    makeDictionaries(spLaunch, dVars['oxt_version'])


def after (spLaunch, dVars, bJS=False):
    print("========== Build French data ==========")
    makeMfsp(spLaunch, bJS)
    makePhonetTable(spLaunch, bJS)
    makeConj(spLaunch, bJS)
    makeLocutions(spLaunch, bJS)