Compare commits
12 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2df88f4280 | ||
|
|
156a1b4aa8 | ||
|
|
962eda7860 | ||
|
|
954ce9e85c | ||
|
|
ff27ddd442 | ||
|
|
f9cc2ad70a | ||
|
|
4bcd45a795 | ||
|
|
9e7ccd6e20 | ||
|
|
631c5930e9 | ||
|
|
0ddb182642 | ||
|
|
de2f0e74c8 | ||
|
|
ad4ee6ccc9 |
@@ -11,7 +11,7 @@ const workerApi = axios.create({
|
||||
|
||||
class Reader {
|
||||
async loadBook(url, callback) {
|
||||
const refreshPause = 200;
|
||||
const refreshPause = 300;
|
||||
if (!callback) callback = () => {};
|
||||
|
||||
let response = await api.post('/load-book', {type: 'url', url});
|
||||
|
||||
@@ -226,7 +226,8 @@ class HistoryPage extends Vue {
|
||||
this.updateTableData();
|
||||
|
||||
const newRecent = bookManager.mostRecentBook();
|
||||
if (this.mostRecentBook != newRecent)
|
||||
|
||||
if (!(this.mostRecentBook && newRecent && this.mostRecentBook.key == newRecent.key))
|
||||
this.$emit('load-book', newRecent);
|
||||
|
||||
this.mostRecentBook = newRecent;
|
||||
|
||||
@@ -656,7 +656,7 @@ class Reader extends Vue {
|
||||
|
||||
// если есть в локальном кэше
|
||||
if (bookParsed) {
|
||||
await bookManager.setRecentBook(Object.assign({bookPos, bookPosSeen, bookPosPercent}, bookManager.metaOnly(bookParsed)));
|
||||
await bookManager.setRecentBook(Object.assign({bookPos, bookPosSeen, bookPosPercent}, bookParsed));
|
||||
this.mostRecentBook();
|
||||
this.addAction(bookPos);
|
||||
this.loaderActive = false;
|
||||
@@ -699,7 +699,7 @@ class Reader extends Vue {
|
||||
});
|
||||
|
||||
// добавляем в историю
|
||||
await bookManager.setRecentBook(Object.assign({bookPos, bookPosSeen, bookPosPercent}, bookManager.metaOnly(addedBook)));
|
||||
await bookManager.setRecentBook(Object.assign({bookPos, bookPosSeen, bookPosPercent}, addedBook));
|
||||
this.mostRecentBook();
|
||||
this.addAction(bookPos);
|
||||
this.updateRoute(true);
|
||||
|
||||
@@ -207,12 +207,12 @@
|
||||
<template slot="content">
|
||||
Выносить все изображения в центр экрана
|
||||
</template>
|
||||
<el-checkbox v-model="showInlineImagesInCenter" @change="needReload">Инлайн в центр</el-checkbox>
|
||||
<el-checkbox v-model="showInlineImagesInCenter" @change="needReload" :disabled="!showImages">Инлайн в центр</el-checkbox>
|
||||
</el-tooltip>
|
||||
</el-col>
|
||||
</el-form-item>
|
||||
<el-form-item label="">
|
||||
<el-checkbox v-model="imageFitWidth">Ширина не более размера экрана</el-checkbox>
|
||||
<el-checkbox v-model="imageFitWidth" :disabled="!showImages">Ширина не более размера экрана</el-checkbox>
|
||||
</el-form-item>
|
||||
<el-form-item label="">
|
||||
<el-col :span="12">
|
||||
@@ -225,7 +225,7 @@
|
||||
уменьшено с сохранением пропорций так, чтобы<br>
|
||||
помещаться в указанное количество строк.
|
||||
</template>
|
||||
<el-input-number v-model="imageHeightLines" :min="1" :max="100"></el-input-number>
|
||||
<el-input-number v-model="imageHeightLines" :min="1" :max="100" :disabled="!showImages"></el-input-number>
|
||||
</el-tooltip>
|
||||
</el-form-item>
|
||||
</el-form>
|
||||
|
||||
@@ -317,7 +317,7 @@ export default class BookParser {
|
||||
if (!text)
|
||||
return;
|
||||
|
||||
text = text.replace(/[\t\n\r]/g, ' ');
|
||||
text = text.replace(/[\t\n\r\xa0]/g, ' ');
|
||||
|
||||
switch (path) {
|
||||
case '/fictionbook/description/title-info/author/first-name':
|
||||
@@ -655,7 +655,6 @@ export default class BookParser {
|
||||
let style = {};
|
||||
let ofs = 0;//смещение от начала параграфа para.offset
|
||||
let imgW = 0;
|
||||
|
||||
// тут начинается самый замес, перенос по слогам и стилизация, а также изображения
|
||||
for (const part of parts) {
|
||||
style = part.style;
|
||||
@@ -665,7 +664,7 @@ export default class BookParser {
|
||||
parsed.visible = this.showImages;
|
||||
let bin = this.binary[part.image.id];
|
||||
if (!bin)
|
||||
bin = {h: 0, w: 0};
|
||||
bin = {h: 1, w: 1};
|
||||
|
||||
let lineCount = this.imageHeightLines;
|
||||
let c = Math.ceil(bin.h/this.lineHeight);
|
||||
|
||||
@@ -5,6 +5,10 @@ import BookParser from './BookParser';
|
||||
|
||||
const maxDataSize = 500*1024*1024;//chars, not bytes
|
||||
|
||||
const bmCacheStore = localForage.createInstance({
|
||||
name: 'bmCacheStore'
|
||||
});
|
||||
|
||||
const bmMetaStore = localForage.createInstance({
|
||||
name: 'bmMetaStore'
|
||||
});
|
||||
@@ -20,11 +24,31 @@ const bmRecentStore = localForage.createInstance({
|
||||
class BookManager {
|
||||
async init(settings) {
|
||||
this.settings = settings;
|
||||
this.books = {};
|
||||
this.recent = {};
|
||||
|
||||
//this.booksCached нужен только для ускорения загрузки читалки
|
||||
this.booksCached = await bmCacheStore.getItem('books');
|
||||
if (!this.booksCached)
|
||||
this.booksCached = {};
|
||||
this.recent = await bmCacheStore.getItem('recent');
|
||||
this.books = Object.assign({}, this.booksCached);
|
||||
|
||||
this.recentChanged1 = true;
|
||||
this.recentChanged2 = true;
|
||||
|
||||
if (!this.books || !this.recent) {
|
||||
this.books = {};
|
||||
this.recent = {};
|
||||
await this.loadMeta(true);
|
||||
} else {
|
||||
this.loadMeta(false);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
async loadMeta(immediate) {
|
||||
if (!immediate)
|
||||
await utils.sleep(2000);
|
||||
|
||||
let len = await bmMetaStore.length();
|
||||
for (let i = 0; i < len; i++) {
|
||||
const key = await bmMetaStore.key(i);
|
||||
@@ -45,6 +69,12 @@ class BookManager {
|
||||
}
|
||||
|
||||
await this.cleanBooks();
|
||||
|
||||
this.booksCached = {};
|
||||
for (const key in this.books) {
|
||||
this.booksCached[key] = this.metaOnly(this.books[key]);
|
||||
}
|
||||
await bmCacheStore.setItem('books', this.booksCached);
|
||||
}
|
||||
|
||||
async cleanBooks() {
|
||||
@@ -80,9 +110,11 @@ class BookManager {
|
||||
const result = await this.parseBook(meta, newBook.data, callback);
|
||||
|
||||
this.books[meta.key] = result;
|
||||
this.booksCached[meta.key] = this.metaOnly(result);
|
||||
|
||||
await bmMetaStore.setItem(`bmMeta-${meta.key}`, this.metaOnly(result));
|
||||
await bmDataStore.setItem(`bmData-${meta.key}`, result.data);
|
||||
await bmCacheStore.setItem('books', this.booksCached);
|
||||
|
||||
return result;
|
||||
}
|
||||
@@ -127,11 +159,15 @@ class BookManager {
|
||||
await bmDataStore.removeItem(`bmData-${meta.key}`);
|
||||
|
||||
delete this.books[meta.key];
|
||||
delete this.booksCached[meta.key];
|
||||
|
||||
await bmCacheStore.setItem('books', this.booksCached);
|
||||
}
|
||||
|
||||
async parseBook(meta, data, callback) {
|
||||
if (!this.books)
|
||||
await this.init();
|
||||
|
||||
const parsed = new BookParser(this.settings);
|
||||
|
||||
const parsedMeta = await parsed.parse(data, callback);
|
||||
@@ -159,7 +195,7 @@ class BookManager {
|
||||
async setRecentBook(value, noTouch) {
|
||||
if (!this.recent)
|
||||
await this.init();
|
||||
const result = Object.assign({}, value);
|
||||
const result = this.metaOnly(value);
|
||||
if (!noTouch)
|
||||
Object.assign(result, {touchTime: Date.now()});
|
||||
|
||||
@@ -170,6 +206,7 @@ class BookManager {
|
||||
|
||||
await bmRecentStore.setItem(result.key, result);
|
||||
await this.cleanRecentBooks();
|
||||
await bmCacheStore.setItem('recent', this.recent);
|
||||
|
||||
this.recentChanged1 = true;
|
||||
this.recentChanged2 = true;
|
||||
@@ -188,6 +225,8 @@ class BookManager {
|
||||
|
||||
await bmRecentStore.removeItem(value.key);
|
||||
delete this.recent[value.key];
|
||||
await bmCacheStore.setItem('recent', this.recent);
|
||||
|
||||
this.recentChanged1 = true;
|
||||
this.recentChanged2 = true;
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "Liberama",
|
||||
"version": "0.4.6",
|
||||
"version": "0.4.7",
|
||||
"engines": {
|
||||
"node": ">=10.0.0"
|
||||
},
|
||||
|
||||
96
server/core/BookConverter/ConvertBase.js
Normal file
96
server/core/BookConverter/ConvertBase.js
Normal file
@@ -0,0 +1,96 @@
|
||||
const iconv = require('iconv-lite');
|
||||
const chardet = require('chardet');
|
||||
const textUtils = require('./textUtils');
|
||||
|
||||
class ConvertBase {
|
||||
constructor(config) {
|
||||
this.config = config;
|
||||
}
|
||||
|
||||
run(data, opts) {// eslint-disable-line no-unused-vars
|
||||
//override
|
||||
}
|
||||
|
||||
decode(data) {
|
||||
let selected = textUtils.getEncoding(data);
|
||||
|
||||
if (selected == 'ISO-8859-5') {
|
||||
const charsetAll = chardet.detectAll(data.slice(0, 20000));
|
||||
for (const charset of charsetAll) {
|
||||
if (charset.name.indexOf('ISO-8859') < 0) {
|
||||
selected = charset.name;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (selected.toLowerCase() != 'utf-8')
|
||||
return iconv.decode(data, selected);
|
||||
else
|
||||
return data;
|
||||
}
|
||||
|
||||
repSpaces(text) {
|
||||
return text.replace(/ |[\t\n\r]/g, ' ');
|
||||
}
|
||||
|
||||
formatFb2(fb2) {
|
||||
let out = '<?xml version="1.0" encoding="utf-8"?>';
|
||||
out += '<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:l="http://www.w3.org/1999/xlink">';
|
||||
out += this.formatFb2Node(fb2);
|
||||
out += '</FictionBook>';
|
||||
return out;
|
||||
}
|
||||
|
||||
formatFb2Node(node, name) {
|
||||
let out = '';
|
||||
|
||||
if (Array.isArray(node)) {
|
||||
for (const n of node) {
|
||||
out += this.formatFb2Node(n);
|
||||
}
|
||||
} else if (typeof node == 'string') {
|
||||
if (name)
|
||||
out += `<${name}>${this.repSpaces(node)}</${name}>`;
|
||||
else
|
||||
out += this.repSpaces(node);
|
||||
} else {
|
||||
if (node._n)
|
||||
name = node._n;
|
||||
|
||||
let attrs = '';
|
||||
if (node._attrs) {
|
||||
for (let attrName in node._attrs) {
|
||||
attrs += ` ${attrName}="${node._attrs[attrName]}"`;
|
||||
}
|
||||
}
|
||||
|
||||
let tOpen = '';
|
||||
let tBody = '';
|
||||
let tClose = '';
|
||||
if (name)
|
||||
tOpen += `<${name}${attrs}>`;
|
||||
if (node.hasOwnProperty('_t'))
|
||||
tBody += this.repSpaces(node._t);
|
||||
|
||||
for (let nodeName in node) {
|
||||
if (nodeName && nodeName[0] == '_' && nodeName != '_a')
|
||||
continue;
|
||||
|
||||
const n = node[nodeName];
|
||||
tBody += this.formatFb2Node(n, nodeName);
|
||||
}
|
||||
|
||||
if (name)
|
||||
tClose += `</${name}>`;
|
||||
|
||||
if (attrs == '' && name == 'p' && tBody.trim() == '')
|
||||
out += '<empty-line/>'
|
||||
else
|
||||
out += `${tOpen}${tBody}${tClose}`;
|
||||
}
|
||||
return out;
|
||||
}
|
||||
}
|
||||
|
||||
module.exports = ConvertBase;
|
||||
41
server/core/BookConverter/ConvertFb2.js
Normal file
41
server/core/BookConverter/ConvertFb2.js
Normal file
@@ -0,0 +1,41 @@
|
||||
const ConvertBase = require('./ConvertBase');
|
||||
const iconv = require('iconv-lite');
|
||||
|
||||
class ConvertFb2 extends ConvertBase {
|
||||
check(data, opts) {
|
||||
const {fileType} = opts;
|
||||
|
||||
return (fileType && fileType.ext == 'xml' && data.toString().indexOf('<FictionBook') >= 0);
|
||||
}
|
||||
|
||||
run(data, opts) {
|
||||
if (!this.check(data, opts))
|
||||
return false;
|
||||
|
||||
return this.checkEncoding(data);
|
||||
}
|
||||
|
||||
checkEncoding(data) {
|
||||
let result = data;
|
||||
|
||||
const left = data.indexOf('<?xml version="1.0"');
|
||||
if (left >= 0) {
|
||||
const right = data.indexOf('?>', left);
|
||||
if (right >= 0) {
|
||||
const head = data.slice(left, right + 2).toString();
|
||||
const m = head.match(/encoding="(.*)"/);
|
||||
if (m) {
|
||||
let encoding = m[1].toLowerCase();
|
||||
if (encoding != 'utf-8') {
|
||||
result = iconv.decode(data, encoding);
|
||||
result = Buffer.from(result.toString().replace(m[0], 'encoding="utf-8"'));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
}
|
||||
|
||||
module.exports = ConvertFb2;
|
||||
162
server/core/BookConverter/ConvertHtml.js
Normal file
162
server/core/BookConverter/ConvertHtml.js
Normal file
@@ -0,0 +1,162 @@
|
||||
const ConvertBase = require('./ConvertBase');
|
||||
const sax = require('./sax');
|
||||
const textUtils = require('./textUtils');
|
||||
|
||||
class ConvertHtml extends ConvertBase {
|
||||
check(data, opts) {
|
||||
const {fileType} = opts;
|
||||
|
||||
if (fileType && (fileType.ext == 'html' || fileType.ext == 'xml'))
|
||||
return {isText: false};
|
||||
|
||||
//может это чистый текст?
|
||||
if (textUtils.checkIfText(data)) {
|
||||
return {isText: true};
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
run(data, opts) {
|
||||
const checkResult = this.check(data, opts);
|
||||
if (!checkResult)
|
||||
return false;
|
||||
|
||||
let {isText} = checkResult;
|
||||
let titleInfo = {};
|
||||
let desc = {_n: 'description', 'title-info': titleInfo};
|
||||
let pars = [];
|
||||
let body = {_n: 'body', section: {_a: []}};
|
||||
let fb2 = [desc, body];
|
||||
|
||||
let title = '';
|
||||
let inTitle = false;
|
||||
|
||||
let spaceCounter = [];
|
||||
|
||||
const repCrLfTab = (text) => text.replace(/[\n\r]/g, '').replace(/\t/g, ' ');
|
||||
|
||||
const newParagraph = () => {
|
||||
pars.push({_n: 'p', _t: ''});
|
||||
};
|
||||
|
||||
const growParagraph = (text) => {
|
||||
if (!pars.length)
|
||||
newParagraph();
|
||||
|
||||
const l = pars.length;
|
||||
if (pars[l - 1]._t == '')
|
||||
text = text.trimLeft();
|
||||
pars[l - 1]._t += text;
|
||||
|
||||
//посчитаем отступы у текста, чтобы выделить потом параграфы
|
||||
const lines = text.split('\n');
|
||||
for (let line of lines) {
|
||||
line = repCrLfTab(line)
|
||||
|
||||
let l = 0;
|
||||
while (l < line.length && line[l] == ' ') {
|
||||
l++;
|
||||
}
|
||||
if (!spaceCounter[l])
|
||||
spaceCounter[l] = 0;
|
||||
spaceCounter[l]++;
|
||||
}
|
||||
};
|
||||
|
||||
const newPara = new Set(['tr', 'br', 'br/', 'dd', 'p', 'title', '/title', 'h1', 'h2', 'h3', '/h1', '/h2', '/h3']);
|
||||
|
||||
const onTextNode = (text, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (!cutCounter) {
|
||||
growParagraph(text);
|
||||
}
|
||||
|
||||
if (inTitle && !title)
|
||||
title = text;
|
||||
};
|
||||
|
||||
const onStartNode = (tag, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (!cutCounter) {
|
||||
if (newPara.has(tag))
|
||||
newParagraph();
|
||||
}
|
||||
|
||||
if (tag == 'title')
|
||||
inTitle = true;
|
||||
};
|
||||
|
||||
const onEndNode = (tag, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (tag == 'title')
|
||||
inTitle = false;
|
||||
};
|
||||
|
||||
let buf = this.decode(data).toString();
|
||||
|
||||
sax.parseSync(buf, {
|
||||
onStartNode, onEndNode, onTextNode,
|
||||
innerCut: new Set(['head', 'script', 'style', 'binary'])
|
||||
});
|
||||
|
||||
titleInfo['book-title'] = title;
|
||||
|
||||
//подозрение на чистый текст, надо разбить на параграфы
|
||||
if (isText || pars.length < buf.length/2000) {
|
||||
let total = 0;
|
||||
for (let i = 0; i < spaceCounter.length; i++) {
|
||||
total += (spaceCounter[i] ? spaceCounter[i] : 0);
|
||||
}
|
||||
total /= 10;
|
||||
let i = spaceCounter.length - 1;
|
||||
while (i > 0 && (!spaceCounter[i] || spaceCounter[i] < total)) i--;
|
||||
|
||||
const parIndent = (i > 0 ? i : 0);
|
||||
|
||||
let newPars = [];
|
||||
const newPar = () => {
|
||||
newPars.push({_n: 'p', _t: ''});
|
||||
};
|
||||
|
||||
const growPar = (text) => {
|
||||
if (!newPars.length)
|
||||
newPar();
|
||||
|
||||
const l = newPars.length;
|
||||
newPars[l - 1]._t += text;
|
||||
}
|
||||
|
||||
i = 0;
|
||||
for (const par of pars) {
|
||||
if (i > 0)
|
||||
newPar();
|
||||
i++;
|
||||
|
||||
const lines = par._t.split('\n');
|
||||
for (let line of lines) {
|
||||
line = repCrLfTab(line);
|
||||
|
||||
let l = 0;
|
||||
while (l < line.length && line[l] == ' ') {
|
||||
l++;
|
||||
}
|
||||
|
||||
if (l >= parIndent)
|
||||
newPar();
|
||||
growPar(line.trim() + ' ');
|
||||
}
|
||||
}
|
||||
|
||||
body.section._a[0] = newPars;
|
||||
} else {
|
||||
body.section._a[0] = pars;
|
||||
}
|
||||
|
||||
//убираем лишнее
|
||||
for (let i = 0; i < pars.length; i++)
|
||||
pars[i]._t = this.repSpaces(pars[i]._t).trim();
|
||||
|
||||
return this.formatFb2(fb2);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
module.exports = ConvertHtml;
|
||||
275
server/core/BookConverter/ConvertSamlib.js
Normal file
275
server/core/BookConverter/ConvertSamlib.js
Normal file
@@ -0,0 +1,275 @@
|
||||
const _ = require('lodash');
|
||||
const URL = require('url').URL;
|
||||
|
||||
const sax = require('./sax');
|
||||
const ConvertBase = require('./ConvertBase');
|
||||
|
||||
class ConvertSamlib extends ConvertBase {
|
||||
check(data, opts) {
|
||||
const {url} = opts;
|
||||
|
||||
const parsedUrl = new URL(url);
|
||||
if (parsedUrl.hostname == 'samlib.ru' ||
|
||||
parsedUrl.hostname == 'budclub.ru' ||
|
||||
parsedUrl.hostname == 'zhurnal.lib.ru') {
|
||||
return {hostname: parsedUrl.hostname};
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
run(data, opts) {
|
||||
const checkResult = this.check(data, opts);
|
||||
if (!checkResult)
|
||||
return false;
|
||||
|
||||
const {hostname} = checkResult;
|
||||
let titleInfo = {};
|
||||
let desc = {_n: 'description', 'title-info': titleInfo};
|
||||
let pars = [];
|
||||
let body = {_n: 'body', section: {_a: pars}};
|
||||
let fb2 = [desc, body];
|
||||
|
||||
let inSubtitle = false;
|
||||
let inJustify = true;
|
||||
let inImage = false;
|
||||
let isFirstPara = false;
|
||||
let path = '';
|
||||
let tag = '';// eslint-disable-line no-unused-vars
|
||||
|
||||
let inText = false;
|
||||
let textFound = false;
|
||||
let node = {_a: pars};
|
||||
|
||||
let inPara = false;
|
||||
let italic = false;
|
||||
let bold = false;
|
||||
|
||||
const openTag = (name, attrs) => {
|
||||
if (name == 'p')
|
||||
inPara = true;
|
||||
let n = {_n: name, _attrs: attrs, _a: [], _p: node};
|
||||
node._a.push(n);
|
||||
node = n;
|
||||
};
|
||||
|
||||
const closeTag = (name) => {
|
||||
if (name == 'p')
|
||||
inPara = false;
|
||||
if (node._p) {
|
||||
const exact = (node._n == name);
|
||||
node = node._p;
|
||||
if (!exact)
|
||||
closeTag(name);
|
||||
}
|
||||
};
|
||||
|
||||
const growParagraph = (text) => {
|
||||
if (!node._p) {
|
||||
if (text.trim() != '')
|
||||
openTag('p');
|
||||
else
|
||||
return;
|
||||
}
|
||||
if (node._n == 'p' && node._a.length == 0)
|
||||
text = text.trimLeft();
|
||||
node._a.push({_t: text});
|
||||
};
|
||||
|
||||
const onStartNode = (elemName, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (elemName == '')
|
||||
return;
|
||||
if (!inText) {
|
||||
path += '/' + elemName;
|
||||
tag = elemName;
|
||||
} else {
|
||||
switch (elemName) {
|
||||
case 'li':
|
||||
case 'p':
|
||||
case 'dd':
|
||||
case 'br':
|
||||
if (!(inSubtitle && isFirstPara)) {
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
openTag('p');
|
||||
}
|
||||
isFirstPara = false;
|
||||
break;
|
||||
case 'h1':
|
||||
case 'h2':
|
||||
case 'h3':
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
openTag('p');
|
||||
bold = true;
|
||||
break;
|
||||
case 'i':
|
||||
case 'em':
|
||||
italic = true;
|
||||
break;
|
||||
case 'b':
|
||||
case 'strong':
|
||||
bold = true;
|
||||
break;
|
||||
case 'div':
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
if (tail.indexOf('align="center"') >= 0) {
|
||||
openTag('subtitle');
|
||||
inSubtitle = true;
|
||||
isFirstPara = true;
|
||||
}
|
||||
|
||||
if (tail.indexOf('align="justify"') >= 0) {
|
||||
openTag('p');
|
||||
inJustify = true;
|
||||
}
|
||||
|
||||
break;
|
||||
case 'img': {
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
const attrs = sax.getAttrsSync(tail);
|
||||
if (attrs.src && attrs.src.value) {
|
||||
let href = attrs.src.value;
|
||||
if (href[0] == '/')
|
||||
href = `http://${hostname}${href}`;
|
||||
openTag('image', {href});
|
||||
inImage = true;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const onEndNode = (elemName, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (!inText) {
|
||||
const oldPath = path;
|
||||
let t = '';
|
||||
do {
|
||||
let i = path.lastIndexOf('/');
|
||||
t = path.substr(i + 1);
|
||||
path = path.substr(0, i);
|
||||
} while (t != elemName && path);
|
||||
|
||||
if (t != elemName) {
|
||||
path = oldPath;
|
||||
}
|
||||
|
||||
let i = path.lastIndexOf('/');
|
||||
tag = path.substr(i + 1);
|
||||
} else {
|
||||
switch (elemName) {
|
||||
case 'li':
|
||||
case 'p':
|
||||
case 'dd':
|
||||
closeTag('p');
|
||||
break;
|
||||
case 'h1':
|
||||
case 'h2':
|
||||
case 'h3':
|
||||
closeTag('p');
|
||||
bold = false;
|
||||
break;
|
||||
case 'i':
|
||||
case 'em':
|
||||
italic = false;
|
||||
break;
|
||||
case 'b':
|
||||
case 'strong':
|
||||
bold = false;
|
||||
break;
|
||||
case 'div':
|
||||
if (inSubtitle) {
|
||||
closeTag('subtitle');
|
||||
inSubtitle = false;
|
||||
isFirstPara = false;
|
||||
}
|
||||
|
||||
if (inJustify) {
|
||||
closeTag('p');
|
||||
inJustify = false;
|
||||
}
|
||||
break;
|
||||
case 'img':
|
||||
if (inImage)
|
||||
closeTag('image');
|
||||
inImage = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const onComment = (text) => {// eslint-disable-line no-unused-vars
|
||||
if (text == '--------- Собственно произведение -------------') {
|
||||
inText = true;
|
||||
textFound = true;
|
||||
}
|
||||
if (text == '-----------------------------------------------')
|
||||
inText = false;
|
||||
};
|
||||
|
||||
const onTextNode = (text) => {// eslint-disable-line no-unused-vars
|
||||
if (text && text.trim() == '')
|
||||
text = (text.indexOf(' ') >= 0 ? ' ' : '');
|
||||
|
||||
if (!text)
|
||||
return;
|
||||
|
||||
switch (path) {
|
||||
case '/html/body/center/h2':
|
||||
titleInfo['book-title'] = text;
|
||||
return;
|
||||
case '/html/body/div/h3':
|
||||
if (!titleInfo.author)
|
||||
titleInfo.author = {};
|
||||
text = text.replace(':', '').trim().split(' ');
|
||||
if (text[0])
|
||||
titleInfo.author['last-name'] = text[0];
|
||||
if (text[1])
|
||||
titleInfo.author['first-name'] = text[1];
|
||||
if (text[2])
|
||||
titleInfo.author['middle-name'] = text[2];
|
||||
return;
|
||||
}
|
||||
|
||||
let tOpen = (bold ? '<strong>' : '');
|
||||
tOpen += (italic ? '<emphasis>' : '');
|
||||
let tClose = (italic ? '</emphasis>' : '');
|
||||
tClose += (bold ? '</strong>' : '');
|
||||
|
||||
if (inText)
|
||||
growParagraph(`${tOpen}${text}${tClose}`);
|
||||
};
|
||||
|
||||
sax.parseSync(this.decode(data).toString().replace(/ /g, ' '), {
|
||||
onStartNode, onEndNode, onTextNode, onComment,
|
||||
innerCut: new Set(['head', 'script', 'style'])
|
||||
});
|
||||
|
||||
//текст не найден на странице, обработать корректно не получилось
|
||||
if (!textFound)
|
||||
return false;
|
||||
|
||||
const title = (titleInfo['book-title'] ? titleInfo['book-title'] : '');
|
||||
let author = '';
|
||||
if (titleInfo.author) {
|
||||
author = _.compact([
|
||||
(titleInfo.author['last-name'] ? titleInfo.author['last-name'] : ''),
|
||||
(titleInfo.author['first-name'] ? titleInfo.author['first-name'] : ''),
|
||||
(titleInfo.author['middle-name'] ? titleInfo.author['middle-name'] : ''),
|
||||
]).join(' ');
|
||||
}
|
||||
|
||||
pars.unshift({_n: 'title', _a: [
|
||||
{_n: 'p', _t: author}, {_n: 'p', _t: ''},
|
||||
{_n: 'p', _t: title}, {_n: 'p', _t: ''},
|
||||
]})
|
||||
|
||||
return this.formatFb2(fb2);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
module.exports = ConvertSamlib;
|
||||
@@ -1,536 +1,45 @@
|
||||
const fs = require('fs-extra');
|
||||
const URL = require('url').URL;
|
||||
const iconv = require('iconv-lite');
|
||||
const chardet = require('chardet');
|
||||
const _ = require('lodash');
|
||||
const sax = require('./sax');
|
||||
const textUtils = require('./textUtils');
|
||||
|
||||
const FileDetector = require('../FileDetector');
|
||||
|
||||
const repSpaces = (text) => text.replace(/ |[\t\n\r]/g, ' ');
|
||||
const repSpaces2 = (text) => text.replace(/[\n\r]/g, '');
|
||||
const repSpaces3 = (text) => text.replace(/ /g, ' ');
|
||||
//порядок важен
|
||||
const convertClassFactory = [
|
||||
require('./ConvertFb2'),
|
||||
require('./ConvertSamlib'),
|
||||
require('./ConvertHtml'),
|
||||
];
|
||||
|
||||
class BookConverter {
|
||||
constructor() {
|
||||
constructor(config) {
|
||||
this.detector = new FileDetector();
|
||||
|
||||
this.convertFactory = [];
|
||||
for (const convertClass of convertClassFactory) {
|
||||
this.convertFactory.push(new convertClass(config));
|
||||
}
|
||||
}
|
||||
|
||||
async convertToFb2(inputFile, outputFile, url, callback) {
|
||||
const fileType = await this.detector.detectFile(inputFile);
|
||||
|
||||
const data = await fs.readFile(inputFile);
|
||||
callback(100);
|
||||
|
||||
if (fileType && (fileType.ext == 'html' || fileType.ext == 'xml')) {
|
||||
if (data.toString().indexOf('<FictionBook') >= 0) {
|
||||
await fs.writeFile(outputFile, this.checkEncoding(data));
|
||||
return;
|
||||
let result = false;
|
||||
for (const convert of this.convertFactory) {
|
||||
result = convert.run(data, {inputFile, url, callback, fileType});
|
||||
if (result) {
|
||||
await fs.writeFile(outputFile, result);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
const parsedUrl = new URL(url);
|
||||
if (parsedUrl.hostname == 'samlib.ru' ||
|
||||
parsedUrl.hostname == 'budclub.ru' ||
|
||||
parsedUrl.hostname == 'zhurnal.lib.ru') {
|
||||
await fs.writeFile(outputFile, this.convertSamlib(data, parsedUrl.hostname));
|
||||
return;
|
||||
}
|
||||
|
||||
await fs.writeFile(outputFile, this.convertHtml(data));
|
||||
return;
|
||||
} else {
|
||||
if (!result) {
|
||||
if (fileType)
|
||||
throw new Error(`Этот формат файла не поддерживается: ${fileType.mime}`);
|
||||
else {
|
||||
//может это чистый текст?
|
||||
if (textUtils.checkIfText(data)) {
|
||||
await fs.writeFile(outputFile, this.convertHtml(data, true));
|
||||
return;
|
||||
}
|
||||
|
||||
throw new Error(`Не удалось определить формат файла: ${url}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
decode(data) {
|
||||
let selected = textUtils.getEncoding(data);
|
||||
|
||||
if (selected == 'ISO-8859-5') {
|
||||
const charsetAll = chardet.detectAll(data.slice(0, 20000));
|
||||
for (const charset of charsetAll) {
|
||||
if (charset.name.indexOf('ISO-8859') < 0) {
|
||||
selected = charset.name;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (selected.toLowerCase() != 'utf-8')
|
||||
return iconv.decode(data, selected);
|
||||
else
|
||||
return data;
|
||||
}
|
||||
|
||||
checkEncoding(data) {
|
||||
let result = data;
|
||||
|
||||
const left = data.indexOf('<?xml version="1.0"');
|
||||
if (left >= 0) {
|
||||
const right = data.indexOf('?>', left);
|
||||
if (right >= 0) {
|
||||
const head = data.slice(left, right + 2).toString();
|
||||
const m = head.match(/encoding="(.*)"/);
|
||||
if (m) {
|
||||
let encoding = m[1].toLowerCase();
|
||||
if (encoding != 'utf-8') {
|
||||
result = iconv.decode(data, encoding);
|
||||
result = Buffer.from(result.toString().replace(m[0], 'encoding="utf-8"'));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
convertHtml(data, isText) {
|
||||
let titleInfo = {};
|
||||
let desc = {_n: 'description', 'title-info': titleInfo};
|
||||
let pars = [];
|
||||
let body = {_n: 'body', section: {_a: []}};
|
||||
let fb2 = [desc, body];
|
||||
|
||||
let title = '';
|
||||
let inTitle = false;
|
||||
|
||||
let spaceCounter = [];
|
||||
|
||||
const newParagraph = () => {
|
||||
pars.push({_n: 'p', _t: ''});
|
||||
};
|
||||
|
||||
const growParagraph = (text) => {
|
||||
if (!pars.length)
|
||||
newParagraph();
|
||||
|
||||
const l = pars.length;
|
||||
if (pars[l - 1]._t == '')
|
||||
text = text.trimLeft();
|
||||
pars[l - 1]._t += text;
|
||||
|
||||
//посчитаем отступы у текста, чтобы выделить потом параграфы
|
||||
const lines = text.split('\n');
|
||||
for (let line of lines) {
|
||||
line = repSpaces2(line).replace(/\t/g, ' ');
|
||||
|
||||
let l = 0;
|
||||
while (l < line.length && line[l] == ' ') {
|
||||
l++;
|
||||
}
|
||||
if (!spaceCounter[l])
|
||||
spaceCounter[l] = 0;
|
||||
spaceCounter[l]++;
|
||||
}
|
||||
};
|
||||
|
||||
const newPara = new Set(['tr', 'br', 'br/', 'dd', 'p', 'title', '/title', 'h1', 'h2', 'h3', '/h1', '/h2', '/h3']);
|
||||
|
||||
const onTextNode = (text, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (!cutCounter) {
|
||||
growParagraph(text);
|
||||
}
|
||||
|
||||
if (inTitle && !title)
|
||||
title = text;
|
||||
};
|
||||
|
||||
const onStartNode = (tag, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (!cutCounter) {
|
||||
if (newPara.has(tag))
|
||||
newParagraph();
|
||||
}
|
||||
|
||||
if (tag == 'title')
|
||||
inTitle = true;
|
||||
};
|
||||
|
||||
const onEndNode = (tag, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (tag == 'title')
|
||||
inTitle = false;
|
||||
};
|
||||
|
||||
let buf = this.decode(data).toString();
|
||||
|
||||
sax.parseSync(buf, {
|
||||
onStartNode, onEndNode, onTextNode,
|
||||
innerCut: new Set(['head', 'script', 'style'])
|
||||
});
|
||||
|
||||
titleInfo['book-title'] = title;
|
||||
|
||||
//подозрение на чистый текст, надо разбить на параграфы
|
||||
if (isText || pars.length < buf.length/2000) {
|
||||
let total = 0;
|
||||
for (let i = 0; i < spaceCounter.length; i++) {
|
||||
total += (spaceCounter[i] ? spaceCounter[i] : 0);
|
||||
}
|
||||
total /= 10;
|
||||
let i = spaceCounter.length - 1;
|
||||
while (i > 0 && (!spaceCounter[i] || spaceCounter[i] < total)) i--;
|
||||
|
||||
const parIndent = (i > 0 ? i : 0);
|
||||
|
||||
let newPars = [];
|
||||
const newPar = () => {
|
||||
newPars.push({_n: 'p', _t: ''});
|
||||
};
|
||||
|
||||
const growPar = (text) => {
|
||||
if (!newPars.length)
|
||||
newPar();
|
||||
|
||||
const l = newPars.length;
|
||||
newPars[l - 1]._t += text;
|
||||
}
|
||||
|
||||
i = 0;
|
||||
for (const par of pars) {
|
||||
if (i > 0)
|
||||
newPar();
|
||||
i++;
|
||||
|
||||
const lines = par._t.split('\n');
|
||||
for (let line of lines) {
|
||||
line = repSpaces2(line).replace(/\t/g, ' ');
|
||||
|
||||
let l = 0;
|
||||
while (l < line.length && line[l] == ' ') {
|
||||
l++;
|
||||
}
|
||||
|
||||
if (l >= parIndent)
|
||||
newPar();
|
||||
growPar(line.trim() + ' ');
|
||||
}
|
||||
}
|
||||
|
||||
body.section._a[0] = newPars;
|
||||
} else {
|
||||
body.section._a[0] = pars;
|
||||
}
|
||||
|
||||
//убираем лишнее
|
||||
for (let i = 0; i < pars.length; i++)
|
||||
pars[i]._t = repSpaces(pars[i]._t).trim();
|
||||
|
||||
return this.formatFb2(fb2);
|
||||
}
|
||||
|
||||
convertSamlib(data, hostname) {
|
||||
let titleInfo = {};
|
||||
let desc = {_n: 'description', 'title-info': titleInfo};
|
||||
let pars = [];
|
||||
let body = {_n: 'body', section: {_a: pars}};
|
||||
let fb2 = [desc, body];
|
||||
|
||||
let inSubtitle = false;
|
||||
let inJustify = true;
|
||||
let inImage = false;
|
||||
let isFirstPara = false;
|
||||
let path = '';
|
||||
let tag = '';// eslint-disable-line no-unused-vars
|
||||
|
||||
let inText = false;
|
||||
let textFound = false;
|
||||
let node = {_a: pars};
|
||||
|
||||
let inPara = false;
|
||||
let italic = false;
|
||||
let bold = false;
|
||||
|
||||
const openTag = (name, attrs) => {
|
||||
if (name == 'p')
|
||||
inPara = true;
|
||||
let n = {_n: name, _attrs: attrs, _a: [], _p: node};
|
||||
node._a.push(n);
|
||||
node = n;
|
||||
};
|
||||
|
||||
const closeTag = (name) => {
|
||||
if (name == 'p')
|
||||
inPara = false;
|
||||
if (node._p) {
|
||||
const exact = (node._n == name);
|
||||
node = node._p;
|
||||
if (!exact)
|
||||
closeTag(name);
|
||||
}
|
||||
};
|
||||
|
||||
const growParagraph = (text) => {
|
||||
if (!node._p) {
|
||||
if (text.trim() != '')
|
||||
openTag('p');
|
||||
else
|
||||
return;
|
||||
}
|
||||
if (node._n == 'p' && node._a.length == 0)
|
||||
text = text.trimLeft();
|
||||
node._a.push({_t: text});
|
||||
};
|
||||
|
||||
const onStartNode = (elemName, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (elemName == '')
|
||||
return;
|
||||
if (!inText) {
|
||||
path += '/' + elemName;
|
||||
tag = elemName;
|
||||
} else {
|
||||
switch (elemName) {
|
||||
case 'li':
|
||||
case 'p':
|
||||
case 'dd':
|
||||
case 'br':
|
||||
if (!(inSubtitle && isFirstPara)) {
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
openTag('p');
|
||||
}
|
||||
isFirstPara = false;
|
||||
break;
|
||||
case 'h1':
|
||||
case 'h2':
|
||||
case 'h3':
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
openTag('p');
|
||||
bold = true;
|
||||
break;
|
||||
case 'i':
|
||||
case 'em':
|
||||
italic = true;
|
||||
break;
|
||||
case 'b':
|
||||
case 'strong':
|
||||
bold = true;
|
||||
break;
|
||||
case 'div':
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
if (tail.indexOf('align="center"') >= 0) {
|
||||
openTag('subtitle');
|
||||
inSubtitle = true;
|
||||
isFirstPara = true;
|
||||
}
|
||||
|
||||
if (tail.indexOf('align="justify"') >= 0) {
|
||||
openTag('p');
|
||||
inJustify = true;
|
||||
}
|
||||
|
||||
break;
|
||||
case 'img': {
|
||||
if (inPara)
|
||||
closeTag('p');
|
||||
const attrs = sax.getAttrsSync(tail);
|
||||
if (attrs.src && attrs.src.value) {
|
||||
let href = attrs.src.value;
|
||||
if (href[0] == '/')
|
||||
href = `http://${hostname}${href}`;
|
||||
openTag('image', {href});
|
||||
inImage = true;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const onEndNode = (elemName, tail, singleTag, cutCounter, cutTag) => {// eslint-disable-line no-unused-vars
|
||||
if (!inText) {
|
||||
const oldPath = path;
|
||||
let t = '';
|
||||
do {
|
||||
let i = path.lastIndexOf('/');
|
||||
t = path.substr(i + 1);
|
||||
path = path.substr(0, i);
|
||||
} while (t != elemName && path);
|
||||
|
||||
if (t != elemName) {
|
||||
path = oldPath;
|
||||
}
|
||||
|
||||
let i = path.lastIndexOf('/');
|
||||
tag = path.substr(i + 1);
|
||||
} else {
|
||||
switch (elemName) {
|
||||
case 'li':
|
||||
case 'p':
|
||||
case 'dd':
|
||||
closeTag('p');
|
||||
break;
|
||||
case 'h1':
|
||||
case 'h2':
|
||||
case 'h3':
|
||||
closeTag('p');
|
||||
bold = false;
|
||||
break;
|
||||
case 'i':
|
||||
case 'em':
|
||||
italic = false;
|
||||
break;
|
||||
case 'b':
|
||||
case 'strong':
|
||||
bold = false;
|
||||
break;
|
||||
case 'div':
|
||||
if (inSubtitle) {
|
||||
closeTag('subtitle');
|
||||
inSubtitle = false;
|
||||
isFirstPara = false;
|
||||
}
|
||||
|
||||
if (inJustify) {
|
||||
closeTag('p');
|
||||
inJustify = false;
|
||||
}
|
||||
break;
|
||||
case 'img':
|
||||
if (inImage)
|
||||
closeTag('image');
|
||||
inImage = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const onComment = (text) => {// eslint-disable-line no-unused-vars
|
||||
if (text == '--------- Собственно произведение -------------') {
|
||||
inText = true;
|
||||
textFound = true;
|
||||
}
|
||||
if (text == '-----------------------------------------------')
|
||||
inText = false;
|
||||
};
|
||||
|
||||
const onTextNode = (text) => {// eslint-disable-line no-unused-vars
|
||||
if (text && text.trim() == '')
|
||||
text = (text.indexOf(' ') >= 0 ? ' ' : '');
|
||||
|
||||
if (!text)
|
||||
return;
|
||||
|
||||
switch (path) {
|
||||
case '/html/body/center/h2':
|
||||
titleInfo['book-title'] = text;
|
||||
return;
|
||||
case '/html/body/div/h3':
|
||||
if (!titleInfo.author)
|
||||
titleInfo.author = {};
|
||||
text = text.replace(':', '').trim().split(' ');
|
||||
if (text[0])
|
||||
titleInfo.author['last-name'] = text[0];
|
||||
if (text[1])
|
||||
titleInfo.author['first-name'] = text[1];
|
||||
if (text[2])
|
||||
titleInfo.author['middle-name'] = text[2];
|
||||
return;
|
||||
}
|
||||
|
||||
let tOpen = (bold ? '<strong>' : '');
|
||||
tOpen += (italic ? '<emphasis>' : '');
|
||||
let tClose = (italic ? '</emphasis>' : '');
|
||||
tClose += (bold ? '</strong>' : '');
|
||||
|
||||
if (inText)
|
||||
growParagraph(`${tOpen}${text}${tClose}`);
|
||||
};
|
||||
|
||||
sax.parseSync(repSpaces3(this.decode(data).toString()), {
|
||||
onStartNode, onEndNode, onTextNode, onComment,
|
||||
innerCut: new Set(['head', 'script', 'style'])
|
||||
});
|
||||
|
||||
//текст не найден на странице, обрабатываем как html
|
||||
if (!textFound)
|
||||
return this.convertHtml(data);
|
||||
|
||||
const title = (titleInfo['book-title'] ? titleInfo['book-title'] : '');
|
||||
let author = '';
|
||||
if (titleInfo.author) {
|
||||
author = _.compact([
|
||||
(titleInfo.author['last-name'] ? titleInfo.author['last-name'] : ''),
|
||||
(titleInfo.author['first-name'] ? titleInfo.author['first-name'] : ''),
|
||||
(titleInfo.author['middle-name'] ? titleInfo.author['middle-name'] : ''),
|
||||
]).join(' ');
|
||||
}
|
||||
|
||||
pars.unshift({_n: 'title', _a: [
|
||||
{_n: 'p', _t: author}, {_n: 'p', _t: ''},
|
||||
{_n: 'p', _t: title}, {_n: 'p', _t: ''},
|
||||
]})
|
||||
|
||||
return this.formatFb2(fb2);
|
||||
}
|
||||
|
||||
formatFb2(fb2) {
|
||||
let out = '<?xml version="1.0" encoding="utf-8"?>';
|
||||
out += '<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:l="http://www.w3.org/1999/xlink">';
|
||||
out += this.formatFb2Node(fb2);
|
||||
out += '</FictionBook>';
|
||||
return out;
|
||||
}
|
||||
|
||||
formatFb2Node(node, name) {
|
||||
let out = '';
|
||||
|
||||
if (Array.isArray(node)) {
|
||||
for (const n of node) {
|
||||
out += this.formatFb2Node(n);
|
||||
}
|
||||
} else if (typeof node == 'string') {
|
||||
if (name)
|
||||
out += `<${name}>${repSpaces(node)}</${name}>`;
|
||||
else
|
||||
out += repSpaces(node);
|
||||
} else {
|
||||
if (node._n)
|
||||
name = node._n;
|
||||
|
||||
let attrs = '';
|
||||
if (node._attrs) {
|
||||
for (let attrName in node._attrs) {
|
||||
attrs += ` ${attrName}="${node._attrs[attrName]}"`;
|
||||
}
|
||||
}
|
||||
|
||||
let tOpen = '';
|
||||
let tBody = '';
|
||||
let tClose = '';
|
||||
if (name)
|
||||
tOpen += `<${name}${attrs}>`;
|
||||
if (node.hasOwnProperty('_t'))
|
||||
tBody += repSpaces(node._t);
|
||||
|
||||
for (let nodeName in node) {
|
||||
if (nodeName && nodeName[0] == '_' && nodeName != '_a')
|
||||
continue;
|
||||
|
||||
const n = node[nodeName];
|
||||
tBody += this.formatFb2Node(n, nodeName);
|
||||
}
|
||||
|
||||
if (name)
|
||||
tClose += `</${name}>`;
|
||||
|
||||
if (attrs == '' && name == 'p' && tBody.trim() == '')
|
||||
out += '<empty-line/>'
|
||||
else
|
||||
out += `${tOpen}${tBody}${tClose}`;
|
||||
}
|
||||
return out;
|
||||
callback(100);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -9,18 +9,18 @@ detect.addSignature(
|
||||
"rules": [
|
||||
{ "type": "or", "rules":
|
||||
[
|
||||
{ "type": "contains", "bytes": "3c68746d6c" },
|
||||
{ "type": "contains", "bytes": "3c00680074006d006c00" },
|
||||
{ "type": "equal", "end": 5, "bytes": "3c68746d6c" },
|
||||
{ "type": "equal", "end": 10, "bytes": "3c00680074006d006c00" },
|
||||
|
||||
{ "type": "contains", "bytes": "3c21646f6374797065" },
|
||||
{ "type": "contains", "bytes": "3c626f6479" },
|
||||
{ "type": "contains", "bytes": "3c68656164" },
|
||||
{ "type": "contains", "bytes": "3c696672616d65" },
|
||||
{ "type": "contains", "bytes": "3c696d67" },
|
||||
{ "type": "contains", "bytes": "3c6f626a656374" },
|
||||
{ "type": "contains", "bytes": "3c736372697074" },
|
||||
{ "type": "contains", "bytes": "3c7461626c65" },
|
||||
{ "type": "contains", "bytes": "3c7469746c65" },
|
||||
{ "type": "equal", "end": 9, "bytes": "3c21646f6374797065" },
|
||||
{ "type": "equal", "end": 5, "bytes": "3c626f6479" },
|
||||
{ "type": "equal", "end": 5, "bytes": "3c68656164" },
|
||||
{ "type": "equal", "end": 7, "bytes": "3c696672616d65" },
|
||||
{ "type": "equal", "end": 4, "bytes": "3c696d67" },
|
||||
{ "type": "equal", "end": 7, "bytes": "3c6f626a656374" },
|
||||
{ "type": "equal", "end": 7, "bytes": "3c736372697074" },
|
||||
{ "type": "equal", "end": 6, "bytes": "3c7461626c65" },
|
||||
{ "type": "equal", "end": 6, "bytes": "3c7469746c65" },
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -36,7 +36,7 @@ detect.addSignature(
|
||||
"rules": [
|
||||
{ "type": "or", "rules":
|
||||
[
|
||||
{ "type": "contains", "bytes": "3c3f786d6c2076657273696f6e3d22312e3022" },
|
||||
{ "type": "equal", "end": 19, "bytes": "3c3f786d6c2076657273696f6e3d22312e3022" },
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
@@ -22,7 +22,7 @@ class ReaderWorker {
|
||||
|
||||
this.down = new FileDownloader();
|
||||
this.decomp = new FileDecompressor();
|
||||
this.bookConverter = new BookConverter();
|
||||
this.bookConverter = new BookConverter(this.config);
|
||||
|
||||
if (!singleCleanExecute) {
|
||||
this.periodicCleanDir(this.config.tempPublicDir, this.config.maxTempPublicDirSize, 60*60*1000);//1 раз в час
|
||||
@@ -66,14 +66,14 @@ class ReaderWorker {
|
||||
const decompFilename = await this.decomp.decompressFile(downloadedFilename, decompDir);
|
||||
wState.set({progress: 100});
|
||||
|
||||
//parse book
|
||||
//конвертирование в fb2
|
||||
wState.set({state: 'convert', step: 3, progress: 0});
|
||||
convertFilename = `${this.config.tempDownloadDir}/${tempFilename2}`;
|
||||
await this.bookConverter.convertToFb2(decompFilename, convertFilename, url, progress => {
|
||||
wState.set({progress});
|
||||
});
|
||||
|
||||
//compress file to tmp dir, if not exists with the same hashname
|
||||
//сжимаем файл в tmp, если там уже нет с тем же именем-sha256
|
||||
const compFilename = await this.decomp.gzipFileIfNotExists(convertFilename, `${this.config.tempPublicDir}`);
|
||||
|
||||
wState.set({progress: 100});
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
const config = require('./config');
|
||||
const {initLogger, getLog} = require('./core/getLogger');
|
||||
initLogger(config);
|
||||
const log = getLog();
|
||||
const logger = require('./core/getLogger');
|
||||
logger.initLogger(config);
|
||||
const log = logger.getLog();
|
||||
|
||||
const configSaver = require('./config/configSaver');
|
||||
const argv = require('minimist')(process.argv.slice(2));
|
||||
|
||||
Reference in New Issue
Block a user