Grammalecte  Check-in [f8019de85c]

import json
import os

import grammalecte.ibdawg as ibdawg
from grammalecte.echo import echo
from grammalecte.str_transform import defineSuffixCode
import grammalecte.fr.conj as conj
import grammalecte.tokenizer as tkz


class cd:
    """Context manager for changing the current working directory"""
    def __init__ (self, newPath):
        self.newPath = os.path.expanduser(newPath)

def makeLocutions (sp, bJS=False):
    "compile list of locutions in JSON"
    print("> Locutions ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    with open(sp+"/data/locutions.txt", 'r', encoding='utf-8') as hSrc:
        dLocutions = {}
        dLocGraph = {}
        oTokenizer = tkz.Tokenizer("fr")
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():
                lElem = sLine.strip().split()
                dCur = dLocutions
                for sWord in lElem:
                    if sWord not in dCur and not sWord.startswith(":"):
                dCur = dLocGraph
                sLoc, sTag = sLine.strip().split("\t")
                for oToken in oTokenizer.genTokens(sLoc.strip()):
                    sWord = oToken["sValue"]
                    if sWord not in dCur:
                        dCur[sWord] = {}
                    if sWord not in dCur and sWord.startswith(":"):
                        dCur[sWord] = ''
                    dCur = dCur[sWord]
                dCur[":"] = sTag

    sCode = "# generated data (do not edit)\n\n" + \
            "dLocutions = " + str(dLocutions) + "\n"
            "dLocutions = " + str(dLocGraph) + "\n"
    open(sp+"/modules/locutions_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
    if bJS:
        open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocutions, ensure_ascii=False))
        open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocGraph, ensure_ascii=False))


def before (spLaunch, dVars, bJS=False):
    print("========== Build Hunspell dictionaries ==========")
    makeDictionaries(spLaunch, dVars['oxt_version'])


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

                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    _unifyStr (sWord){
        return sWord.replace('’', 'e').toLowerCase();
    }

    getListOfTokensReduc (sText, bInfo = true) {
        let aTokenList = this.getListOfTokens(sText.replace("'", "’").trim(), false);
        let iKey = 0;
        let aElem = [];
        do {
            let oToken = aTokenList[iKey];
            let sTokenTmpKey = '';
            let sMorphLoc = '';
            let aTokenTempList = [oToken];
            if (oToken.sType == "WORD" || oToken.sType == "ELPFX"){
                let iKeyTree = iKey + 1;
                let oLocNode = this.oLocGraph[this._unifyStr(oToken.sValue)];
                let oLocNode = this.oLocGraph[oToken.sValue.toLowerCase()];
                while (oLocNode) {
                    let oTokenNext = aTokenList[iKeyTree];
                    iKeyTree++;
                    if (oTokenNext) {
                        oLocNode = oLocNode[this._unifyStr(oTokenNext.sValue)];
                        oLocNode = oLocNode[oTokenNext.sValue.toLowerCase()];
                    }
                    if (oLocNode && iKeyTree <= aTokenList.length) {
                        sTokenTmpKey = Object.keys(oLocNode)[0];
                        sMorphLoc = oLocNode[":"];
                        aTokenTempList.push(oTokenNext);
                    } else {
                        break;
                    }
                }
            }

            if (sTokenTmpKey.substring(0, 1) == ':') {
            if (sMorphLoc) {
                let sWord = '';
                for (let oTokenWord of aTokenTempList) {
                    sWord += oTokenWord.sValue+' ';
                }
                iKey = iKey + aTokenTempList.length-1;
                let oTokenLocution = {
                    'nEnd': aTokenTempList[aTokenTempList.length-1].nEnd,
                    'nStart': aTokenTempList[0].nStart,
                    'sType': "LOC",
                    'sValue': sWord.replace('’ ','’').trim()
                };
                if (bInfo) {
                    let aFormatedTag = [];
                    for (let sTagMulti of sTokenTmpKey.split('|') ){
                    for (let sTagMulti of sMorphLoc.split('|') ){
                        aFormatedTag.push( this._formatTags(sTagMulti).replace(/( \(él.\))/g,'') );
                    }
                    aElem.push({
                        sType: oTokenLocution.sType,
                        sValue: oTokenLocution.sValue,
                        aLabel: aFormatedTag
                    });