Избавился от easysax.js в пользу своего sax.js

client/components/Reader/share/BookParser.js

@@ -1,4 +1,4 @@
-import EasySAXParser from './easysax';
+import sax from '../../../../server/core/BookConverter/sax';
 import {sleep} from '../../../share/utils';
 
 export default class BookParser {
@@ -19,8 +19,6 @@ export default class BookParser {
             callback = () => {};
         callback(0);
 
-        this.data = data;
-
         if (data.indexOf('<FictionBook') < 0) {            
             throw new Error('Неверный формат файла');
         }
@@ -35,7 +33,6 @@ export default class BookParser {
 
         let path = '';
         let tag = '';
-        let nextPerc = 0;
         let center = false;
         let bold = false;
 
@@ -61,6 +58,7 @@ export default class BookParser {
             para[paraIndex] = p;
             paraOffset += p.length;
         };
+
         const growParagraph = (text, len) => {
             let p = para[paraIndex];
             if (p) {
@@ -84,16 +82,14 @@ export default class BookParser {
             paraOffset += p.length;
         };
 
-        const parser = new EasySAXParser();
+        const onStartNode = (elemName) => {// eslint-disable-line no-unused-vars
+            if (elemName == '?xml')
+                return;
 
-        parser.on('error', (msgError) => {// eslint-disable-line no-unused-vars
-        });
-
-        parser.on('startNode', (elemName, getAttr, isTagEnd, getStrNode) => {// eslint-disable-line no-unused-vars
             tag = elemName;
             path += '/' + elemName;
 
-            if ((tag == 'p' || tag == 'empty-line') && path.indexOf('/FictionBook/body/section') == 0) {
+            if ((tag == 'p' || tag == 'empty-line') && path.indexOf('/fictionbook/body/section') == 0) {
                 newParagraph(' ', 1);
             }
 
@@ -111,9 +107,9 @@ export default class BookParser {
                 newParagraph(' ', 1);
                 bold = true;
             }
-        });
+        };
 
-        parser.on('endNode', (elemName, isTagStart, getStrNode) => {// eslint-disable-line no-unused-vars
+        const onEndNode = (elemName) => {// eslint-disable-line no-unused-vars
             if (tag == elemName) {
                 if (tag == 'emphasis' || tag == 'strong') {
                     growParagraph(`</${tag}>`, 0);
@@ -135,9 +131,9 @@ export default class BookParser {
                     tag = path;
                 }
             }
-        });
+        };
 
-        parser.on('textNode', (text) => {
+        const onTextNode = (text) => {// eslint-disable-line no-unused-vars
             text = text.replace(/&nbsp;|[\t\n\r]/g, ' ');
 
             if (text != ' ' && text.trim() == '')
@@ -147,30 +143,30 @@ export default class BookParser {
                 return;
 
             switch (path) {
-                case '/FictionBook/description/title-info/author/first-name':
+                case '/fictionbook/description/title-info/author/first-name':
                     fb2.firstName = text;
                     break;
-                case '/FictionBook/description/title-info/author/middle-name':
+                case '/fictionbook/description/title-info/author/middle-name':
                     fb2.middleName = text;
                     break;
-                case '/FictionBook/description/title-info/author/last-name':
+                case '/fictionbook/description/title-info/author/last-name':
                     fb2.lastName = text;
                     break;
-                case '/FictionBook/description/title-info/genre':
+                case '/fictionbook/description/title-info/genre':
                     fb2.genre = text;
                     break;
-                case '/FictionBook/description/title-info/date':
+                case '/fictionbook/description/title-info/date':
                     fb2.date = text;
                     break;
-                case '/FictionBook/description/title-info/book-title':
+                case '/fictionbook/description/title-info/book-title':
                     fb2.bookTitle = text;
                     break;
-                case '/FictionBook/description/title-info/id':
+                case '/fictionbook/description/title-info/id':
                     fb2.id = text;
                     break;
             }
 
-            if (path.indexOf('/FictionBook/description/title-info/annotation') == 0) {
+            if (path.indexOf('/fictionbook/description/title-info/annotation') == 0) {
                 if (!fb2.annotation)
                     fb2.annotation = '';
                 if (tag != 'annotation')
@@ -184,11 +180,11 @@ export default class BookParser {
             let tClose = (center ? '</center>' : '');
             tClose += (bold ? '</strong>' : '');
 
-            if (path.indexOf('/FictionBook/body/title') == 0) {
+            if (path.indexOf('/fictionbook/body/title') == 0) {
                 newParagraph(`${tOpen}${text}${tClose}`, text.length, true);
             }
 
-            if (path.indexOf('/FictionBook/body/section') == 0) {
+            if (path.indexOf('/fictionbook/body/section') == 0) {
                 switch (tag) {
                     case 'p':
                         growParagraph(`${tOpen}${text}${tClose}`, text.length);
@@ -197,24 +193,17 @@ export default class BookParser {
                         growParagraph(`${tOpen}${text}${tClose}`, text.length);
                 }
             }
-        });
+        };
 
-        parser.on('cdata', (data) => {// eslint-disable-line no-unused-vars
+        const onProgress = async(prog) => {
-        });
+            await sleep(1);
+            callback(prog);
+        };
 
-        parser.on('comment', (text) => {// eslint-disable-line no-unused-vars
+        await sax.parse(data, {
+            onStartNode, onEndNode, onTextNode, onProgress
         });
 
-        parser.on('progress', async(progress) => {
-            if (progress > nextPerc) {
-                await sleep(1);
-                callback(progress);
-                nextPerc += 10;
-            }
-        });
-
-        await parser.parse(data);
-
         this.fb2 = fb2;
         this.para = para;
         this.textLength = paraOffset;
@@ -252,17 +241,16 @@ export default class BookParser {
             style: {bold: Boolean, italic: Boolean, center: Boolean},
             text: String,
         }*/
-        const parser = new EasySAXParser();
         let style = {};
 
-        parser.on('textNode', (text) => {
+        const onTextNode = async(text) => {// eslint-disable-line no-unused-vars
             result.push({
                 style: Object.assign({}, style),
                 text: text
             });
-        });
+        };
 
-        parser.on('startNode', (elemName, getAttr, isTagEnd, getStrNode) => {// eslint-disable-line no-unused-vars
+        const onStartNode = async(elemName) => {// eslint-disable-line no-unused-vars
             switch (elemName) {
                 case 'strong':
                     style.bold = true;
@@ -274,9 +262,9 @@ export default class BookParser {
                     style.center = true;
                     break;
             }
-        });
+        };
 
-        parser.on('endNode', (elemName, isTagStart, getStrNode) => {// eslint-disable-line no-unused-vars
+        const onEndNode = async(elemName) => {// eslint-disable-line no-unused-vars
             switch (elemName) {
                 case 'strong':
                     style.bold = false;
@@ -288,9 +276,11 @@ export default class BookParser {
                     style.center = false;
                     break;
             }
-        });
+        };
 
-        parser.parse(`<p>${s}</p>`);
+        sax.parseSync(s, {
+            onStartNode, onEndNode, onTextNode
+        });
 
         return result;
     }

client/components/Reader/share/easysax.js

@@ -1,736 +0,0 @@
-'use strict';
-
-/*
-new function() {
-    var parser = new EasySAXParser();
-
-    parser.ns('rss', { // or false
-        'http://search.yahoo.com/mrss/': 'media',
-        'http://www.w3.org/1999/xhtml': 'xhtml',
-        'http://www.w3.org/2005/Atom': 'atom',
-        'http://purl.org/rss/1.0/': 'rss',
-    });
-
-    parser.on('error', function(msgError) {
-    });
-
-    parser.on('startNode', function(elemName, getAttr, isTagEnd, getStrNode) {
-        var attr = getAttr();
-    });
-
-    parser.on('endNode', function(elemName, isTagStart, getStrNode) {
-    });
-
-    parser.on('textNode', function(text) {
-    });
-
-    parser.on('cdata', function(data) {
-    });
-
-
-    parser.on('comment', function(text) {
-        //console.log('--'+text+'--')
-    });
-
-    //parser.on('unknownNS', function(key) {console.log('unknownNS: ' + key)});
-    //parser.on('question', function() {}); // <? ... ?>
-    //parser.on('attention', function() {}); // <!XXXXX zzzz="eeee">
-
-    console.time('easysax');
-    for(var z=1000;z--;) {
-        parser.parse(xml)
-    };
-    console.timeEnd('easysax');
-};
-
-*/
-
-// << ------------------------------------------------------------------------ >> //
-
-EasySAXParser.entityDecode = xmlEntityDecode;
-export default EasySAXParser;
-
-var stringFromCharCode = String.fromCharCode;
-var objectCreate = Object.create;
-function NULL_FUNC() {}
-
-function entity2char(x) {
-    if (x === 'amp') {
-        return '&';
-    }
-
-    switch(x.toLocaleLowerCase()) {
-        case 'quot': return '"';
-        case 'amp': return '&'
-        case 'lt': return '<'
-        case 'gt': return '>'
-
-        case 'plusmn': return '\u00B1';
-        case 'laquo': return '\u00AB';
-        case 'raquo': return '\u00BB';
-        case 'micro': return '\u00B5';
-        case 'nbsp': return '\u00A0';
-        case 'copy': return '\u00A9';
-        case 'sup2': return '\u00B2';
-        case 'sup3': return '\u00B3';
-        case 'para': return '\u00B6';
-        case 'reg': return '\u00AE';
-        case 'deg': return '\u00B0';
-        case 'apos': return '\'';
-    }
-
-    return '&' + x + ';';
-}
-
-function replaceEntities(s, d, x, z) {
-    if (z) {
-        return entity2char(z);
-    }
-
-    if (d) {
-        return stringFromCharCode(d);
-    }
-
-    return stringFromCharCode(parseInt(x, 16));
-}
-
-function xmlEntityDecode(s) {
-    s = ('' + s);
-
-    if (s.length > 3 && s.indexOf('&') !== -1) {
-        if (s.indexOf('&lt;') !== -1) {s = s.replace(/&lt;/g, '<');}
-        if (s.indexOf('&gt;') !== -1) {s = s.replace(/&gt;/g, '>');}
-        if (s.indexOf('&quot;') !== -1) {s = s.replace(/&quot;/g, '"');}
-
-        if (s.indexOf('&') !== -1) {
-            s = s.replace(/&#(\d+);|&#x([0123456789abcdef]+);|&(\w+);/ig, replaceEntities);
-        }
-    }
-
-    return s;
-}
-
-function cloneMatrixNS(nsmatrix) {
-    var nn = objectCreate(null);
-    for (var n in nsmatrix) {
-        nn[n] = nsmatrix[n];
-    }
-    return nn;
-}
-
-
-function EasySAXParser(config) {
-    if (!this) {
-        return null;
-    }
-
-    var onTextNode = NULL_FUNC, onStartNode = NULL_FUNC, onEndNode = NULL_FUNC, onCDATA = NULL_FUNC, onError = NULL_FUNC,
-        onComment, onQuestion, onAttention, onUnknownNS, onProgress;
-    var is_onComment = false, is_onQuestion = false, is_onAttention = false, is_onUnknownNS = false, is_onProgress = false;
-
-    var isAutoEntity = true; // делать "EntityDecode" всегда
-    var entityDecode = xmlEntityDecode;
-    var hasSurmiseNS = false;
-    var isNamespace = false;
-    var returnError = null;
-    var parseStop = false; // прервать парсер
-    var defaultNS;
-    var nsmatrix = null;
-    var useNS;
-    var xml = ''; // string
-
-
-    this.setup = function(op) {
-        for (var name in op) {
-            switch(name) {
-                case 'entityDecode': entityDecode = op.entityDecode || entityDecode; break;
-                case 'autoEntity': isAutoEntity = !!op.autoEntity; break;
-                case 'defaultNS': defaultNS = op.defaultNS || null; break;
-                case 'ns': isNamespace = !!(useNS = op.ns || null); break;
-                case 'on':
-                    var listeners = op.on;
-                    for (var ev in listeners) {
-                        this.on(ev, listeners[ev]);
-                    }
-                break;
-            }
-        }
-    };
-
-    this.on = function(name, cb) {
-        if (typeof cb !== 'function') {
-            if (cb !== null) {
-                throw Error('required args on(string, function||null)');
-            }
-        }
-
-        switch(name) {
-            case 'startNode': onStartNode = cb || NULL_FUNC; break;
-            case 'textNode': onTextNode = cb || NULL_FUNC; break;
-            case 'endNode': onEndNode = cb || NULL_FUNC; break;
-            case 'error': onError = cb || NULL_FUNC; break;
-            case 'cdata': onCDATA = cb || NULL_FUNC; break;
-
-            case 'unknownNS': onUnknownNS = cb; is_onUnknownNS = !!cb; break;
-            case 'attention': onAttention = cb; is_onAttention = !!cb; break; // <!XXXXX zzzz="eeee">
-            case 'question': onQuestion = cb; is_onQuestion = !!cb; break; // <? ....  ?>
-            case 'comment': onComment = cb; is_onComment = !!cb; break;
-            case 'progress': onProgress = cb; is_onProgress = !!cb; break;
-        }
-    };
-
-    this.ns = function(root, ns) {
-        if (!root) {
-            isNamespace = false;
-            defaultNS = null;
-            useNS = null;
-            return this;
-        }
-
-        if (!ns || typeof root !== 'string') {
-            throw Error('required args ns(string, object)');
-        }
-
-        isNamespace = !!(useNS = ns || null);
-        defaultNS = root || null;
-
-        return this;
-    };
-
-    this.parse = async function(_xml) {
-        if (typeof _xml !== 'string') {
-            return 'required args parser(string)'; // error
-        }
-
-        returnError = null;
-        xml = _xml;
-
-        if (isNamespace) {
-            nsmatrix = objectCreate(null);
-            nsmatrix.xmlns = defaultNS;
-
-            await parse();
-
-            nsmatrix = null;
-
-        } else {
-            await parse();
-        }
-
-        parseStop = false;
-        attrRes = true;
-        xml = '';
-
-        return returnError;
-    };
-
-    this.stop = function() {
-        parseStop = true;
-    };
-
-    if (config) {
-        this.setup(config);
-    }
-
-    // -----------------------------------------------------
-
-
-    var stringNodePosStart; // number
-    var stringNodePosEnd; // number
-    var attrStartPos; // number начало позиции атрибутов в строке attrString <(div^ class="xxxx" title="sssss")/>
-    var attrString; // строка атрибутов <(div class="xxxx" title="sssss")/>
-    var attrRes; // закешированный результат разбора атрибутов , null - разбор не проводился, object - хеш атрибутов, true - нет атрибутов, false - невалидный xml
-
-    /*
-        парсит атрибуты по требованию. Важно! - функция не генерирует исключения.
-
-        если была ошибка разбора возврашается false
-        если атрибутов нет и разбор удачен то возврашается true
-        если есть атрибуты то возврашается обьект(хеш)
-    */
-
-    function getAttrs() {
-        if (attrRes !== null) {
-            return attrRes;
-        }
-
-        var xmlnsAlias;
-        var nsAttrName;
-        var attrList = isNamespace && hasSurmiseNS ? [] : null;
-        var i = attrStartPos + 1; // так как первый символ уже был проверен
-        var s = attrString;
-        var l = s.length;
-        var hasNewMatrix;
-        var newalias;
-        var value;
-        var alias;
-        var name;
-        var res = {};
-        var ok;
-        var w;
-        var j;
-
-
-        for(; i < l; i++) {
-            w = s.charCodeAt(i);
-
-            if (w === 32 || (w < 14 && w > 8) ) { // \f\n\r\t\v
-                continue
-            }
-
-            if (w < 65 || w > 122 || (w > 90 && w < 97) ) { // недопустимые первые символы
-                if (w !== 95 && w !== 58) { // char 95"_" 58":"
-                    return attrRes = false; // error. invalid first char
-                }
-            }
-
-            for(j = i + 1; j < l; j++) { // проверяем все символы имени атрибута
-                w = s.charCodeAt(j);
-
-                if ( w > 96 && w < 123 || w > 64 && w < 91 || w > 47 && w < 59 || w === 45 || w === 95) {
-                    continue;
-                }
-
-                if (w !== 61) { // "=" == 61
-                    return attrRes = false; // error. invalid char "="
-                }
-
-                break;
-            }
-
-            name = s.substring(i, j);
-            ok = true;
-
-            if (name === 'xmlns:xmlns') {
-                return attrRes = false; // error. invalid name
-            }
-
-            w = s.charCodeAt(j + 1);
-
-            if (w === 34) {  // '"'
-                j = s.indexOf('"', i = j + 2 );
-
-            } else {
-                if (w !== 39) { // "'"
-                    return attrRes = false; // error. invalid char
-                }
-
-                j = s.indexOf('\'', i = j + 2 );
-            }
-
-            if (j === -1) {
-                return attrRes = false; // error. invalid char
-            }
-
-            if (j + 1 < l) {
-                w = s.charCodeAt(j + 1);
-
-                if (w > 32 || w < 9 || (w < 32 && w > 13)) {
-                    // error. invalid char
-                    return attrRes = false;
-                }
-            }
-
-
-            value = s.substring(i, j);
-            i = j + 1; // след. семвол уже проверен потому проверять нужно следуюший
-
-            if (isAutoEntity) {
-                value = entityDecode(value);
-            }
-
-            if (!isNamespace) { //
-                res[name] = value;
-                continue;
-            }
-
-            if (hasSurmiseNS) {
-                // есть подозрение что в атрибутах присутствует xmlns
-                newalias = (name !== 'xmlns'
-                    ? name.charCodeAt(0) === 120 && name.substr(0, 6) === 'xmlns:' ? name.substr(6) : null
-                    : 'xmlns'
-                );
-
-                if (newalias !== null) {
-                    alias = useNS[entityDecode(value)];
-                    if (is_onUnknownNS && !alias) {
-                        alias = onUnknownNS(value);
-                    }
-
-                    if (alias) {
-                        if (nsmatrix[newalias] !== alias) {
-                            if (!hasNewMatrix) {
-                                nsmatrix = cloneMatrixNS(nsmatrix);
-                                hasNewMatrix = true;
-                            }
-
-                            nsmatrix[newalias] = alias;
-                        }
-                    } else {
-                        if (nsmatrix[newalias]) {
-                            if (!hasNewMatrix) {
-                                nsmatrix = cloneMatrixNS(nsmatrix);
-                                hasNewMatrix = true;
-                            }
-
-                            nsmatrix[newalias] = false;
-                        }
-                    }
-
-                    res[name] = value;
-                    continue;
-                }
-
-                attrList.push(name, value);
-                continue;
-            }
-
-            w = name.indexOf(':');
-            if (w === -1) {
-                res[name] = value;
-                continue;
-            }
-
-            nsAttrName = nsmatrix[name.substring(0, w)];
-            if (nsAttrName) {
-                nsAttrName = nsmatrix['xmlns'] === nsAttrName ? name.substr(w + 1) : nsAttrName + name.substr(w);
-                res[nsAttrName + name.substr(w)] = value;
-            }
-        }
-
-
-        if (!ok) {
-            return attrRes = true;  // атрибутов нет, ошибок тоже нет
-        }
-
-        if (hasSurmiseNS)  {
-            xmlnsAlias = nsmatrix['xmlns'];
-
-            for (i = 0, l = attrList.length; i < l; i++) {
-                name = attrList[i++];
-
-                w = name.indexOf(':');
-                if (w !== -1) {
-                    nsAttrName = nsmatrix[name.substring(0, w)];
-                    if (nsAttrName) {
-                        nsAttrName = xmlnsAlias === nsAttrName ? name.substr(w + 1) : nsAttrName + name.substr(w);
-                        res[nsAttrName] = attrList[i];
-                    }
-                    continue;
-                }
-                res[name] = attrList[i];
-            }
-        }
-
-        return attrRes = res;
-    }
-
-    function getStringNode() {
-        return xml.substring(stringNodePosStart, stringNodePosEnd + 1);
-    }
-
-
-    async function parse() {
-        var stacknsmatrix = [];
-        var nodestack = [];
-        var stopIndex = 0;
-        var _nsmatrix;
-        var isTagStart = false;
-        var isTagEnd = false;
-        var x, y, q, w;
-        var j = 0;
-        var i = 0;
-        var xmlns;
-        var elem;
-        var stop; // используется при разборе "namespace" . если встретился неизвестное пространство то события не генерируются
-        var xmlLength = xml.length;
-        var progStep = xmlLength/100;
-        var progCur = 0;
-
-        while(j !== -1) {
-            stop = stopIndex > 0;
-
-            if (xml.charCodeAt(j) === 60) { // "<"
-                i = j;
-            } else {
-                i = xml.indexOf('<', j);
-            }
-
-            if (i === -1) { // конец разбора
-                if (nodestack.length) {
-                    onError(returnError = 'unexpected end parse');
-                    return;
-                }
-
-                if (j === 0) {
-                    onError(returnError = 'missing first tag');
-                    return;
-                }
-
-                return;
-            }
-
-            if (j !== i && !stop) {
-                onTextNode(isAutoEntity ? entityDecode(xml.substring(j, i)) : xml.substring(j, i));
-                if (parseStop) {
-                    return;
-                }
-            }
-
-            w = xml.charCodeAt(i+1);
-
-            if (w === 33) { // "!"
-                w = xml.charCodeAt(i+2);
-                if (w === 91 && xml.substr(i + 3, 6) === 'CDATA[') { // 91 == "["
-                    j = xml.indexOf(']]>', i);
-                    if (j === -1) {
-                        onError(returnError = 'cdata');
-                        return;
-                    }
-
-                    if (!stop) {
-                        onCDATA(xml.substring(i + 9, j));
-                        if (parseStop) {
-                            return;
-                        }
-                    }
-
-                    j += 3;
-                    continue;
-                }
-
-
-                if (w === 45 && xml.charCodeAt(i + 3) === 45) { // 45 == "-"
-                    j = xml.indexOf('-->', i);
-                    if (j === -1) {
-                        onError(returnError = 'expected -->');
-                        return;
-                    }
-
-
-                    if (is_onComment && !stop) {
-                        onComment(isAutoEntity ? entityDecode(xml.substring(i + 4, j)) : xml.substring(i + 4, j));
-                        if (parseStop) {
-                            return;
-                        }
-                    }
-
-                    j += 3;
-                    continue;
-                }
-
-                j = xml.indexOf('>', i + 1);
-                if (j === -1) {
-                    onError(returnError = 'expected ">"');
-                    return;
-                }
-
-                if (is_onAttention && !stop) {
-                    onAttention(xml.substring(i, j + 1));
-                    if (parseStop) {
-                        return;
-                    }
-                }
-
-                j += 1;
-                continue;
-            }
-
-            if (w === 63) { // "?"
-                j = xml.indexOf('?>', i);
-                if (j === -1) { // error
-                    onError(returnError = '...?>');
-                    return;
-                }
-
-                if (is_onQuestion) {
-                    onQuestion(xml.substring(i, j + 2));
-                    if (parseStop) {
-                        return;
-                    }
-                }
-
-                j += 2;
-                continue;
-            }
-
-            j = xml.indexOf('>', i + 1);
-
-            if (j == -1) { // error
-                onError(returnError = 'unclosed tag'); // ...>
-                return;
-            }
-
-            attrRes = true; // атрибутов нет
-
-            //if (xml.charCodeAt(i+1) === 47) { // </...
-            if (w === 47) { // </...
-                isTagStart = false;
-                isTagEnd = true;
-
-                // проверяем что должен быть закрыт тотже тег что и открывался
-                if (!nodestack.length) {
-                    onError(returnError = 'close tag, requires open tag');
-                    return;
-                }
-
-                x = elem = nodestack.pop();
-                q = i + 2 + elem.length;
-
-                if (elem !== xml.substring(i + 2, q)) {
-                    onError(returnError = 'close tag, not equal to the open tag');
-                    return;
-                }
-
-                // проверим что в закрываюшем теге нет лишнего
-                for(; q < j; q++) {
-                    w = xml.charCodeAt(q);
-
-                    if (w === 32 || (w > 8 && w < 14)) {  // \f\n\r\t\v пробел
-                        continue;
-                    }
-
-                    onError(returnError = 'close tag');
-                    return;
-                }
-
-            } else {
-                if (xml.charCodeAt(j - 1) ===  47) { // .../>
-                    x = elem = xml.substring(i + 1, j - 1);
-
-                    isTagStart = true;
-                    isTagEnd = true;
-
-                } else {
-                    x = elem = xml.substring(i + 1, j);
-
-                    isTagStart = true;
-                    isTagEnd = false;
-                }
-
-                if (!(w > 96  && w < 123 || w > 64 && w < 91 || w === 95 || w === 58)) { // char 95"_" 58":"
-                    onError(returnError = 'first char nodeName');
-                    return;
-                }
-
-                for (q = 1, y = x.length; q < y; q++) {
-                    w = x.charCodeAt(q);
-
-                    if (w > 96 && w < 123 || w > 64 && w < 91 || w > 47 && w < 59 || w === 45 || w === 95) {
-                        continue;
-                    }
-
-                    if (w === 32 || (w < 14 && w > 8)) { // \f\n\r\t\v пробел
-                        attrRes = null; // возможно есть атирибуты
-                        elem = x.substring(0, q)
-                        break;
-                    }
-
-                    onError(returnError = 'invalid nodeName');
-                    return;
-                }
-
-                if (!isTagEnd) {
-                    nodestack.push(elem);
-                }
-            }
-
-
-            if (isNamespace) {
-                if (stop) { // потомки неизвестного пространства имен
-                    if (isTagEnd) {
-                        if (!isTagStart) {
-                            if (--stopIndex === 0) {
-                                nsmatrix = stacknsmatrix.pop();
-                            }
-                        }
-
-                    } else {
-                        stopIndex += 1;
-                    }
-
-                    j += 1;
-                    continue;
-                }
-
-                // добавляем в stacknsmatrix только если !isTagEnd, иначе сохраняем контекст пространств в переменной
-                _nsmatrix = nsmatrix;
-                if (!isTagEnd) {
-                    stacknsmatrix.push(nsmatrix);
-                }
-
-                if (isTagStart && (attrRes === null)) {
-                    hasSurmiseNS = x.indexOf('xmlns', q) !== -1;
-                    if (hasSurmiseNS) { // есть подозрение на xmlns
-                        attrStartPos = q;
-                        attrString = x;
-
-                        getAttrs();
-
-                        hasSurmiseNS = false;
-                    }
-                }
-
-                w = elem.indexOf(':');
-                if (w !== -1) {
-                    xmlns = nsmatrix[elem.substring(0, w)];
-                    elem = elem.substr(w + 1);
-
-                } else {
-                    xmlns = nsmatrix.xmlns;
-                }
-
-
-                if (!xmlns) {
-                    // элемент неизвестного пространства имен
-                    if (isTagEnd) {
-                        nsmatrix = _nsmatrix; // так как тут всегда isTagStart
-                    } else {
-                        stopIndex = 1; // первый элемент для которого не определено пространство имен
-                    }
-
-                    j += 1;
-                    continue;
-                }
-
-                elem = xmlns + ':' + elem;
-            }
-
-            stringNodePosStart = i;
-            stringNodePosEnd = j;
-
-            if (isTagStart) {
-                attrStartPos = q;
-                attrString = x;
-
-                onStartNode(elem, getAttrs, isTagEnd, getStringNode);
-                if (parseStop) {
-                    return;
-                }
-            }
-
-            if (isTagEnd) {
-                onEndNode(elem, isTagStart, getStringNode);
-                if (parseStop) {
-                    return;
-                }
-
-                if (isNamespace) {
-                    if (isTagStart) {
-                        nsmatrix = _nsmatrix;
-                    } else {
-                        nsmatrix = stacknsmatrix.pop();
-                    }
-                }
-            }
-
-            j += 1;
-            
-            if (j > progCur) {
-                if (is_onProgress)
-                    await onProgress(Math.round(j*100/xmlLength));
-                progCur += progStep;
-            }
-        }
-    }
-}

server/core/BookConverter/index.js

@@ -56,7 +56,7 @@ class BookConverter {
         return iconv.decode(data, selected);
     }
 
-    convertHtml(data, isText) {
+    async convertHtml(data, isText) {
         let titleInfo = {};
         let desc = {_n: 'description', 'title-info': titleInfo};
         let pars = [];
@@ -123,7 +123,7 @@ class BookConverter {
 
         let buf = this.decode(data).toString();
 
-        sax.parse(buf, {
+        await sax.parse(buf, {
             onStartNode, onEndNode, onTextNode,
             innerCut: new Set(['head', 'script', 'style'])
         });
@@ -321,7 +321,7 @@ class BookConverter {
                 growParagraph(text);
         };
 
-        sax.parse(repSpaces(this.decode(data).toString()), {
+        await sax.parse(repSpaces(this.decode(data).toString()), {
             onStartNode, onEndNode, onTextNode, onComment,
             innerCut: new Set(['head', 'script', 'style'])
         });

server/core/BookConverter/sax.js

@@ -1,5 +1,5 @@
-function parse(xstr, options) {
+function parseSync(xstr, options) {
-    let {onStartNode, onEndNode, onTextNode, onCdata, onComment, innerCut} = options;
+    let {onStartNode, onEndNode, onTextNode, onCdata, onComment, onProgress, innerCut} = options;
 
     if (!onStartNode)
         onStartNode = () => {};
@@ -11,12 +11,17 @@ function parse(xstr, options) {
         onCdata = () => {};
     if (!onComment)
         onComment = () => {};
+    if (!onProgress)
+        onProgress = () => {};
 
     if (!innerCut)
         innerCut = new Set();
 
     let i = 0;
     const len = xstr.length;
+    const progStep = len/10;
+    let nextProg = 0;
+
     let cutCounter = 0;
     let cutTag = '';
     let inCdata;
@@ -110,6 +115,11 @@ function parse(xstr, options) {
             }
         }
 
+        if (right >= nextProg) {
+            const prog = Math.round(right/(len + 1)*100);
+            onProgress((prog >= 100 ? 99 : prog));
+            nextProg += progStep;
+        }
         i = right + 1;
     }
 
@@ -122,9 +132,150 @@ function parse(xstr, options) {
             onTextNode(xstr.substr(i, len - i), len - 1, cutCounter, cutTag);
         }
     }
+
+    onProgress(100);
 }
 
+//асинхронная копия parseSync
+async function parse(xstr, options) {
+    let {onStartNode, onEndNode, onTextNode, onCdata, onComment, onProgress, innerCut} = options;
+
+    if (!onStartNode)
+        onStartNode = () => {};
+    if (!onEndNode)
+        onEndNode = () => {};
+    if (!onTextNode)
+        onTextNode = () => {};
+    if (!onCdata)
+        onCdata = () => {};
+    if (!onComment)
+        onComment = () => {};
+    if (!onProgress)
+        onProgress = () => {};
+
+    if (!innerCut)
+        innerCut = new Set();
+
+    let i = 0;
+    const len = xstr.length;
+    const progStep = len/10;
+    let nextProg = 0;
+
+    let cutCounter = 0;
+    let cutTag = '';
+    let inCdata;
+    let inComment;
+    while (i < len) {
+        inCdata = false;
+        inComment = false;
+
+        let left = xstr.indexOf('<', i);
+        if (left < 0)
+            break;
+        let leftData = left;
+
+        if (left < len - 2 && xstr[left + 1] == '!') {
+            if (xstr[left + 2] == '-') {
+                const leftComment = xstr.indexOf('<!--', left);
+                if (leftComment == left) {
+                    inComment = true;
+                    leftData = left + 3;
+                }
+            }
+
+            if (!inComment && xstr[left + 2] == '[') {
+                const leftCdata = xstr.indexOf('<![CDATA[', left);
+                if (leftCdata == left) {
+                    inCdata = true;
+                    leftData = left + 8;
+                }
+            }
+        }
+
+        let right = null;
+        let rightData = null;
+        if (inCdata) {
+            rightData = xstr.indexOf(']]>', leftData + 1);
+            if (rightData < 0)
+                break;
+            right = rightData + 2;
+        } else if (inComment) {
+            rightData = xstr.indexOf('-->', leftData + 1);
+            if (rightData < 0)
+                break;
+            right = rightData + 2;
+        } else {
+            rightData = xstr.indexOf('>', leftData + 1);
+            if (rightData < 0)
+                break;
+            right = rightData;
+        }
+
+        let tagData = xstr.substr(leftData + 1, rightData - leftData - 1);
+
+        if (inCdata) {
+            await onCdata(tagData, left, cutCounter, cutTag);
+        } else if (inComment) {
+            await onComment(tagData, left, cutCounter, cutTag);
+        } else {
+            let tag = '';
+            let tail = '';
+            const firstSpace = tagData.indexOf(' ');
+            if (firstSpace >= 0) {
+                tail = tagData.substr(firstSpace);
+                tag = tagData.substr(0, firstSpace);
+            } else {
+                tag = tagData;
+            }
+            tag = tag.toLowerCase();
+
+            const text = xstr.substr(i, left - i);
+
+            await onTextNode(text, left, cutCounter, cutTag);
+
+            let endTag = '';
+            if (tag === '' || tag[0] !== '/') {
+                await onStartNode(tag, tail, left, cutCounter, cutTag);
+            } else {
+                endTag = tag.substr(1);
+                await onEndNode(endTag, tail, left, cutCounter, cutTag);
+            }
+
+            if (innerCut.has(tag) && (!cutCounter || cutTag === tag)) {
+                if (!cutCounter)
+                    cutTag = tag;
+                cutCounter++;
+            }
+
+            if (cutTag === endTag) {
+                cutCounter = (cutCounter > 0 ? cutCounter - 1 : 0);
+                if (!cutCounter)
+                    cutTag = '';
+            }
+        }
+
+        if (right >= nextProg) {
+            const prog = Math.round(right/(len + 1)*100);
+            await onProgress((prog >= 100 ? 99 : prog));
+            nextProg += progStep;
+        }
+        i = right + 1;
+    }
+
+    if (i < len) {
+        if (inCdata) {
+            await onCdata(xstr.substr(i, len - i), len - 1, cutCounter, cutTag);
+        } else if (inComment) {
+            await onComment(xstr.substr(i, len - i), len - 1, cutCounter, cutTag);
+        } else {
+            await onTextNode(xstr.substr(i, len - i), len - 1, cutCounter, cutTag);
+        }
+    }
+
+    await onProgress(100);
+}
 
 module.exports = {
+    parseSync,
     parse
 }