Grammalecte  Check-in [e7f46d5ce1]

            lTemp.push(iTag+nChar+nAff)
            lWord.push(lTemp);
        }
        lEntry.length = 0; // clear the array
        
        // Dictionary of arc values occurrency, to sort arcs of each node
        let lKeyVal = [];
        for (let c of dChar.keys()) { lKeyVal.push([dChar[c], dCharOccur[c]]); }
        for (let sAff of dAff.keys()) { lKeyVal.push([dAff[sAff]+nChar, dAffOccur[sAff]]); }
        for (let sTag in dTag.keys()) { lKeyVal.push([dTag[sTag]+nChar+nAff, dTagOccur[sTag]]); }
        let dValOccur = new Map(lKeyVal);
        lKeyVal.length = 0; // clear the array

        //with open(spfSrc[:-8]+".valuesfreq.txt", 'w', encoding='utf-8') as hFreqDst:  # DEBUG
        //    for iKey, nOcc in sorted(dValOccur.entries(), key=lambda t: t[1], reverse=True):
        //        hFreqDst.write("{}: {}\n".format(lVal[iKey], nOcc))
        //    hFreqDst.close()
        
        this.sLang = sLangName;
        this.nEntry = lWord.length;
        this.aPreviousEntry = [];
        oNodeCounter.reset();
        this.oRoot = new DawgNode();
        this.lUncheckedNodes = [];          // list of nodes that have not been checked for duplication.
        this.dMinimizedNodes = new Map();   // list of unique nodes that have been checked for duplication.
        this.lSortedNodes = [];             // version 2 and 3
        this.nNode = 0;
        this.nArc = 0;
        this.dChar = dChar;
        this.nChar = dChar.length;
        this.nAff = nAff;
        this.lArcVal = lVal;
        this.nArcVal = lVal.length;
        this.nTag = this.nArcVal - this.nChar - nAff;
        this.cStemming = cStemming;
        if (cStemming == "A") {
            this.funcStemming = str_transform.changeWordWithAffixCode;

        lWord.sort();
        if (xProgressBarNode) {
            xProgressBarNode.value = 0;
            xProgressBarNode.max = lWord.length;
        }
        let i = 0;
        for (let aEntry of lWord) {

            this.insert(aEntry);
            if (xProgressBarNode) {
                xProgressBarNode.value = i;
                i += 1;
            }
        }
        this.finish();
        this.countNodes();
        this.countArcs();
        this.sortNodes();
        this.sortNodeArcs(dValOccur);
        this.displayInfo();


    }

    // BUILD DAWG
    insert (aEntry) {
        if (aEntry < this.aPreviousEntry) {
            throw "Error: Words must be inserted in alphabetical order.";
        }

    finish () {
        // minimize unchecked nodes
        this._minimize(0);
    }

    _minimize (nDownTo) {
        // proceed from the leaf up to a certain point
        for (let i = this.lUncheckedNodes.length-1;  i < nDownTo-1;  i--) {
            let [oNode, char, oChildNode] = this.lUncheckedNodes[i];
            if (this.dMinimizedNodes.has(oChildNode.__hash__())) {
                // replace the child with the previously encountered one
                oNode.arcs.set(char, this.dMinimizedNodes.get(oChildNode.__hash__()));
            } else {
                // add the state to the minimized nodes.
                this.dMinimizedNodes.set(oChildNode.__hash__(), oChildNode);
            }
            this.lUncheckedNodes.pop();
        }
    }

    countNodes () {
        this.nNode = this.dMinimizedNodes.size;
    }

    countArcs () {
        this.nArc = 0;
        for (let oNode of this.dMinimizedNodes) {
            this.nArc += oNode.arcs.size;
        }
    }
    
    sortNodeArcs (dValOccur) {
        console.log(" > Sort node arcs");
        this.oRoot.sortArcs(dValOccur);
        for (let oNode of this.dMinimizedNodes) {
            oNode.sortArcs(dValOccur);
        }
    }

    sortNodes () {
        console.log(" > Sort nodes");
        for (let oNode of this.oRoot.arcs.values()) {
            this._parseNodes(oNode);
        }
    }
    
    _parseNodes (oNode) {
        // Warning: recursive method
        if (oNode.pos > 0) {
            return;
        }
        //oNode.setPos();  // version 2
        this.lSortedNodes.push(oNode);
        for (let oNextNode of oNode.arcs.values()) {
             this._parseNodes(oNextNode);
        }
    }
        
    lookup (sWord) {
        let oNode = this.oRoot;
        for (let c of sWord) {
            if (!oNode.arcs.has(this.dChar.gl_get(c, ''))) {
                return false;
            }
            oNode = oNode.arcs.get(this.dChar.get(c));
        }
        return oNode.final;
    }

    morph (sWord) {
        let oNode = this.oRoot;
        for (let c in sWord) {
            if (!oNode.arcs.has(this.dChar.get(c, ''))) {
                return '';
            }
            oNode = oNode.arcs.get(this.dChar.get(c));
        }
        if (oNode.final) {
            let s = "* ";
            for (let arc of oNode.arcs.keys()) {
                if (arc >= this.nChar) {
                    s += " [" + this.funcStemming(sWord, this.lArcVal[arc]);
                    let oNode2 = oNode.arcs[arc]
                    for (let arc2 of oNode2.arcs.keys()) {
                        s += " / " + this.lArcVal[arc2];
                    }
                    s += "]";
                }
            }
            return s;

    writeInfo () {
        console.log(this.getArcStats());
        console.log("\n * Values:\n");
        let i = 0;
        for (let s of this.lArcVal) {
            console.log(i + ": " + s);

        }
    }

    // BINARY CONVERSION
    createBinary (sPathFile, nMethod) {
        console.log("Write DAWG as an indexable binary dictionary [method: "+nMethod+"]");
        if (nMethod == 1) {

class DawgNode {

    constructor () {
        this.i = oNodeCounter.getId();
        this.final = false;
        this.arcs = new Map();  // key: arc value; value: a node
        this.addr = 0;          // address in the binary dictionary
        this.pos = 0;           // position in the binary dictionary (version 2)
        this.size = 0;          // size of node in bytes (version 3)
    }

    __str__ () {
        // Caution! this function is used for hashing and comparison!

        let l = [];
        if (this.final) {
            l.push("1");
        } else {
            l.push("0");
        }
        for (let [key, node] of this.arcs.entries()) {
            l.push(key.toString());
            l.push(node.i.toString());
        }
        return l.join("_");
    }

    __hash__ () {
        // Used as a key in a python dictionary.
        return this.__str__();
    }

    __eq__ (other) {
        // Used as a key in a python dictionary.
        // Nodes are equivalent if they have identical arcs, and each identical arc leads to identical states.
        return this.__str__() == other.__str__();
    }

    sortArcs (dValOccur) {
        let lTemp = this.arcs.entries();
        lTemp.sort(function (a, b) {
            if (dValOccur.get(a[0], 0) > dValOccur.get(b[0], 0))
                return -1;
            if (dValOccur.get(a[0], 0) < dValOccur.get(b[0], 0))
                return 1;
            return 0;
        });
        this.arcs = new Map(lTemp);
    }














    // VERSION 1 =====================================================================================================
    convToBytes1 (nBytesArc, nBytesNodeAddress) {
        /*
            Node scheme:
            - Arc length is defined by nBytesArc
            - Address length is defined by nBytesNodeAddress

function getCharOrderAfterChar (cChar) {
    return _dCharOrder.gl_get(cChar, null);
}

function displayCharOrder () {
    for (let [key, value] of _dCharOrder.entries()) {
        let s = "[" + key + "]: ";
        let lTemp = value.entries();
        lTemp.sort(function (a, b) {
            if (a[1] > b[1])
                return -1;
            if (a[1] < b[1])
                return 1;
            return 0;
        });
        for (let [c, n] of lTemp) {
            s += c+":"+n+", ";
        }
        console.log(s);
    }
}