wp-epub-gen 0.4.0 → 0.4.2

package/build/index.cjs

@@ -1,5 +1,5 @@
 "use strict";
-Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
+Object.defineProperties(exports, { __esModule: { value: true }, [Symbol.toStringTag]: { value: "Module" } });
 const os = require("os");
 const path = require("path");
 const url = require("url");
@@ -316,13 +316,13 @@ const ALLOWED_XHTML11_TAGS = [
 const ALLOWED_ATTRIBUTES_SET = new Set(ALLOWED_ATTRIBUTES);
 const ALLOWED_XHTML11_TAGS_SET = new Set(ALLOWED_XHTML11_TAGS);
 const SELF_CLOSING_TAGS = /* @__PURE__ */ new Set(["img", "br", "hr"]);
-function initializeChapterInfo(content, index, epubConfigs) {
+function initializeChapterInfo(content, index2, epubConfigs) {
   const chapter = { ...content };
   let { filename } = chapter;
   if (!filename) {
     let titleSlug = uslug(diacritics.remove(chapter.title || "no title"));
     titleSlug = titleSlug.replace(/[/\\]/g, "_");
-    chapter.href = `${index}_${titleSlug}.xhtml`;
+    chapter.href = `${index2}_${titleSlug}.xhtml`;
     chapter.filePath = path.join(epubConfigs.dir, "OEBPS", chapter.href);
   } else {
     filename = safeFineName(filename);
@@ -334,7 +334,7 @@ function initializeChapterInfo(content, index, epubConfigs) {
       chapter.filePath = path.join(epubConfigs.dir, "OEBPS", `${filename}.xhtml`);
     }
   }
-  chapter.id = `item_${index}`;
+  chapter.id = `item_${index2}`;
   chapter.dir = path.dirname(chapter.filePath);
   chapter.excludeFromToc = chapter.excludeFromToc || false;
   chapter.beforeToc = chapter.beforeToc || false;
@@ -363,20 +363,24 @@ function loadAndProcessHtml(data) {
   }
   try {
     let $ = cheerio__namespace.load(trimmedData, {
-      xml: {
-        lowerCaseTags: true,
-        recognizeSelfClosing: true
-      }
+      xmlMode: true,
+      // @ts-ignore
+      decodeEntities: false,
+      lowerCaseTags: true,
+      recognizeSelfClosing: true,
+      lowerCaseAttributeNames: true
     });
     const body = $("body");
     if (body.length) {
       const html = body.html();
       if (html) {
         $ = cheerio__namespace.load(html, {
-          xml: {
-            lowerCaseTags: true,
-            recognizeSelfClosing: true
-          }
+          xmlMode: true,
+          // @ts-ignore
+          decodeEntities: false,
+          lowerCaseTags: true,
+          recognizeSelfClosing: true,
+          lowerCaseAttributeNames: true
         });
       }
     }
@@ -387,7 +391,7 @@ function loadAndProcessHtml(data) {
     );
   }
 }
-function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index) {
+function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index2) {
   const allowedAttrsSet = ALLOWED_ATTRIBUTES_SET;
   const allowedTagsSet = ALLOWED_XHTML11_TAGS_SET;
   const selfClosingTags = SELF_CLOSING_TAGS;
@@ -417,7 +421,7 @@ function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfi
       if (!allowedTagsSet.has(tagName)) {
         if (epubConfigs.verbose) {
           logger.warn(
-            `Warning (content[${index}]): ${tagName} tag isn't allowed on EPUB 2/XHTML 1.1 DTD.`
+            `Warning (content[${index2}]): ${tagName} tag isn't allowed on EPUB 2/XHTML 1.1 DTD.`
           );
         }
         const child = $elem.html();
@@ -427,16 +431,16 @@ function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfi
   });
 }
 function processImages($, chapter, epubConfigs) {
-  $("img").each((index, elem) => {
+  $("img").each((index2, elem) => {
     const url2 = $(elem).attr("src") || "";
     if (!url2 || url2.trim().length === 0) {
-      logger.warn(`Image at index ${index} in chapter has empty src attribute, removing element`);
+      logger.warn(`Image at index ${index2} in chapter has empty src attribute, removing element`);
       $(elem).remove();
       return;
     }
     const trimmedUrl = url2.trim();
     try {
-      if (!trimmedUrl.match(/^(https?:\/\/|data:|\.\/|\/)/)) {
+      if (!trimmedUrl.match(/^(https?:\/\/|file:\/\/|data:|\.\/|\/)/)) {
         logger.warn(`Image URL "${trimmedUrl}" appears to be invalid, but processing anyway`);
       }
     } catch (error) {
@@ -493,90 +497,56 @@ function processImages($, chapter, epubConfigs) {
     }
   });
 }
-function extractAndCleanHtmlContent($, originalData) {
+function extractAndCleanHtmlContent($) {
   let data;
   if ($("body").length) {
     data = $("body").html() || "";
   } else {
     data = $.root().html() || "";
   }
-  if (!originalData) {
-    return data.replace(
-      /<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)><\/\1>/gi,
-      "<$1$2/>"
-    ).replace(
-      new RegExp("<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)(?<!\\/)>", "gi"),
-      "<$1$2/>"
-    );
-  }
-  const entityMap = /* @__PURE__ */ new Map();
-  const entityRegex = /&[a-zA-Z][a-zA-Z0-9]*;|&#[0-9]+;|&#x[0-9a-fA-F]+;/g;
-  const matches = Array.from(originalData.matchAll(entityRegex));
-  let processedOriginal = originalData;
-  const timestamp = Date.now();
-  const randomId = Math.random().toString(36).substring(2, 8);
-  const placeholderPrefix = `__ENTITY_${timestamp}_${randomId}_`;
-  for (let i = matches.length - 1; i >= 0; i--) {
-    const match = matches[i];
-    const placeholder = `${placeholderPrefix}${i}__`;
-    entityMap.set(placeholder, match[0]);
-    processedOriginal = processedOriginal.substring(0, match.index) + placeholder + processedOriginal.substring(match.index + match[0].length);
-  }
-  const $temp = cheerio__namespace.load(processedOriginal, {
-    xmlMode: false
-  });
-  let tempData;
-  if ($temp("body").length) {
-    tempData = $temp("body").html() || "";
-  } else {
-    tempData = $temp.root().html() || "";
-  }
-  for (const [placeholder, entity] of entityMap) {
-    tempData = tempData.replace(new RegExp(placeholder, "g"), entity);
-  }
-  return tempData.replace(
+  return data.replace(
     /<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)><\/\1>/gi,
     "<$1$2/>"
   ).replace(
     new RegExp("<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)(?<!\\/)>", "gi"),
     "<$1$2/>"
-  );
+  ).replace(/<\/img\s*>/gi, "");
 }
-function processChildrenChapters(chapter, index, epubConfigs) {
+function processChildrenChapters(chapter, index2, epubConfigs) {
   if (Array.isArray(chapter.children)) {
     chapter.children = chapter.children.map(
-      (content, idx) => parseContent(content, `${index}_${idx}`, epubConfigs)
+      (content, idx) => parseContent(content, `${index2}_${idx}`, epubConfigs)
     );
   }
 }
-function parseContent(content, index, epubConfigs) {
+function parseContent(content, index2, epubConfigs) {
   if (!content) {
     throw new Error("Content cannot be null or undefined");
   }
   if (!content.data) {
-    logger.warn(`Chapter at index ${index} has no data, using empty string`);
+    logger.warn(`Chapter at index ${index2} has no data, using empty string`);
     content.data = "";
   }
-  const chapter = initializeChapterInfo(content, index, epubConfigs);
+  const chapter = initializeChapterInfo(content, index2, epubConfigs);
   normalizeAuthorInfo(chapter);
   const allowedAttributes = getAllowedAttributes();
   const allowedXhtml11Tags = getAllowedXhtml11Tags();
   if (!chapter.data || chapter.data.trim().length === 0) {
-    logger.warn(`Chapter at index ${index} has empty data, setting empty content`);
+    logger.warn(`Chapter at index ${index2} has empty data, setting empty content`);
     chapter.data = "";
   } else {
     let $;
     try {
       $ = loadAndProcessHtml(chapter.data);
     } catch (error) {
-      logger.error(`Failed to process HTML for chapter ${index}: ${error}`);
+      logger.error(`Failed to process HTML for chapter ${index2}: ${error}`);
       $ = cheerio__namespace.load(`<div>${chapter.data}</div>`);
     }
-    processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index);
+    processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index2);
     processImages($, chapter, epubConfigs);
-    chapter.data = extractAndCleanHtmlContent($, content.data);
+    chapter.data = extractAndCleanHtmlContent($);
   }
-  processChildrenChapters(chapter, index, epubConfigs);
+  processChildrenChapters(chapter, index2, epubConfigs);
   return chapter;
 }
 util.promisify(fs.readFile);
@@ -1234,7 +1204,7 @@ function parseOptions(options) {
   if (typeof data.author === "string") {
     data.author = [data.author];
   }
-  data.content = options.content.map((content, index) => parseContent(content, index, data));
+  data.content = options.content.map((content, index2) => parseContent(content, index2, data));
   if (data.cover) {
     data._coverMediaType = mime.getType(data.cover) || "";
     data._coverExtension = mime.getExtension(data._coverMediaType) || "";
@@ -1245,6 +1215,7 @@ async function epubGen(options, configs) {
   if (configs?.logger) {
     logger.setLogger(configs.logger);
   }
+  logger.info("EpubGen started 101...");
   options = { ...options };
   const o = check(options);
   const verbose = options.verbose !== false;
@@ -1274,6 +1245,12 @@ async function epubGen(options, configs) {
   }
 }
 const gen = epubGen;
+const index = {
+  epubGen,
+  gen,
+  errors
+};
+exports.default = index;
 exports.epubGen = epubGen;
 exports.errors = errors;
 exports.gen = gen;

package/build/index.d.ts

@@ -2,4 +2,14 @@ import { IEpubGenOptions, IGenConfigs, IOut } from './types';
 export declare function epubGen(options: IEpubGenOptions, configs?: IGenConfigs): Promise<IOut>;
 export declare const gen: typeof epubGen;
 export { errors } from './errors';
+declare const _default: {
+    epubGen: typeof epubGen;
+    gen: typeof epubGen;
+    errors: {
+        no_output_path: string;
+        no_title: string;
+        no_content: string;
+    };
+};
+export default _default;
 export type { IChapter, IChapterData, IEpubData, IEpubGenOptions, IEpubImage, IOut } from './types';

package/build/index.js

@@ -295,13 +295,13 @@ const ALLOWED_XHTML11_TAGS = [
 const ALLOWED_ATTRIBUTES_SET = new Set(ALLOWED_ATTRIBUTES);
 const ALLOWED_XHTML11_TAGS_SET = new Set(ALLOWED_XHTML11_TAGS);
 const SELF_CLOSING_TAGS = /* @__PURE__ */ new Set(["img", "br", "hr"]);
-function initializeChapterInfo(content, index, epubConfigs) {
+function initializeChapterInfo(content, index2, epubConfigs) {
   const chapter = { ...content };
   let { filename } = chapter;
   if (!filename) {
     let titleSlug = uslug(remove(chapter.title || "no title"));
     titleSlug = titleSlug.replace(/[/\\]/g, "_");
-    chapter.href = `${index}_${titleSlug}.xhtml`;
+    chapter.href = `${index2}_${titleSlug}.xhtml`;
     chapter.filePath = path.join(epubConfigs.dir, "OEBPS", chapter.href);
   } else {
     filename = safeFineName(filename);
@@ -313,7 +313,7 @@ function initializeChapterInfo(content, index, epubConfigs) {
       chapter.filePath = path.join(epubConfigs.dir, "OEBPS", `${filename}.xhtml`);
     }
   }
-  chapter.id = `item_${index}`;
+  chapter.id = `item_${index2}`;
   chapter.dir = path.dirname(chapter.filePath);
   chapter.excludeFromToc = chapter.excludeFromToc || false;
   chapter.beforeToc = chapter.beforeToc || false;
@@ -342,20 +342,24 @@ function loadAndProcessHtml(data) {
   }
   try {
     let $ = cheerio.load(trimmedData, {
-      xml: {
-        lowerCaseTags: true,
-        recognizeSelfClosing: true
-      }
+      xmlMode: true,
+      // @ts-ignore
+      decodeEntities: false,
+      lowerCaseTags: true,
+      recognizeSelfClosing: true,
+      lowerCaseAttributeNames: true
     });
     const body = $("body");
     if (body.length) {
       const html = body.html();
       if (html) {
         $ = cheerio.load(html, {
-          xml: {
-            lowerCaseTags: true,
-            recognizeSelfClosing: true
-          }
+          xmlMode: true,
+          // @ts-ignore
+          decodeEntities: false,
+          lowerCaseTags: true,
+          recognizeSelfClosing: true,
+          lowerCaseAttributeNames: true
         });
       }
     }
@@ -366,7 +370,7 @@ function loadAndProcessHtml(data) {
     );
   }
 }
-function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index) {
+function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index2) {
   const allowedAttrsSet = ALLOWED_ATTRIBUTES_SET;
   const allowedTagsSet = ALLOWED_XHTML11_TAGS_SET;
   const selfClosingTags = SELF_CLOSING_TAGS;
@@ -396,7 +400,7 @@ function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfi
       if (!allowedTagsSet.has(tagName)) {
         if (epubConfigs.verbose) {
           logger.warn(
-            `Warning (content[${index}]): ${tagName} tag isn't allowed on EPUB 2/XHTML 1.1 DTD.`
+            `Warning (content[${index2}]): ${tagName} tag isn't allowed on EPUB 2/XHTML 1.1 DTD.`
           );
         }
         const child = $elem.html();
@@ -406,16 +410,16 @@ function processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfi
   });
 }
 function processImages($, chapter, epubConfigs) {
-  $("img").each((index, elem) => {
+  $("img").each((index2, elem) => {
     const url = $(elem).attr("src") || "";
     if (!url || url.trim().length === 0) {
-      logger.warn(`Image at index ${index} in chapter has empty src attribute, removing element`);
+      logger.warn(`Image at index ${index2} in chapter has empty src attribute, removing element`);
       $(elem).remove();
       return;
     }
     const trimmedUrl = url.trim();
     try {
-      if (!trimmedUrl.match(/^(https?:\/\/|data:|\.\/|\/)/)) {
+      if (!trimmedUrl.match(/^(https?:\/\/|file:\/\/|data:|\.\/|\/)/)) {
         logger.warn(`Image URL "${trimmedUrl}" appears to be invalid, but processing anyway`);
       }
     } catch (error) {
@@ -472,90 +476,56 @@ function processImages($, chapter, epubConfigs) {
     }
   });
 }
-function extractAndCleanHtmlContent($, originalData) {
+function extractAndCleanHtmlContent($) {
   let data;
   if ($("body").length) {
     data = $("body").html() || "";
   } else {
     data = $.root().html() || "";
   }
-  if (!originalData) {
-    return data.replace(
-      /<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)><\/\1>/gi,
-      "<$1$2/>"
-    ).replace(
-      new RegExp("<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)(?<!\\/)>", "gi"),
-      "<$1$2/>"
-    );
-  }
-  const entityMap = /* @__PURE__ */ new Map();
-  const entityRegex = /&[a-zA-Z][a-zA-Z0-9]*;|&#[0-9]+;|&#x[0-9a-fA-F]+;/g;
-  const matches = Array.from(originalData.matchAll(entityRegex));
-  let processedOriginal = originalData;
-  const timestamp = Date.now();
-  const randomId = Math.random().toString(36).substring(2, 8);
-  const placeholderPrefix = `__ENTITY_${timestamp}_${randomId}_`;
-  for (let i = matches.length - 1; i >= 0; i--) {
-    const match = matches[i];
-    const placeholder = `${placeholderPrefix}${i}__`;
-    entityMap.set(placeholder, match[0]);
-    processedOriginal = processedOriginal.substring(0, match.index) + placeholder + processedOriginal.substring(match.index + match[0].length);
-  }
-  const $temp = cheerio.load(processedOriginal, {
-    xmlMode: false
-  });
-  let tempData;
-  if ($temp("body").length) {
-    tempData = $temp("body").html() || "";
-  } else {
-    tempData = $temp.root().html() || "";
-  }
-  for (const [placeholder, entity] of entityMap) {
-    tempData = tempData.replace(new RegExp(placeholder, "g"), entity);
-  }
-  return tempData.replace(
+  return data.replace(
     /<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)><\/\1>/gi,
     "<$1$2/>"
   ).replace(
     new RegExp("<(br|hr|img|input|meta|area|base|col|embed|link|source|track|wbr)([^>]*?)(?<!\\/)>", "gi"),
     "<$1$2/>"
-  );
+  ).replace(/<\/img\s*>/gi, "");
 }
-function processChildrenChapters(chapter, index, epubConfigs) {
+function processChildrenChapters(chapter, index2, epubConfigs) {
   if (Array.isArray(chapter.children)) {
     chapter.children = chapter.children.map(
-      (content, idx) => parseContent(content, `${index}_${idx}`, epubConfigs)
+      (content, idx) => parseContent(content, `${index2}_${idx}`, epubConfigs)
     );
   }
 }
-function parseContent(content, index, epubConfigs) {
+function parseContent(content, index2, epubConfigs) {
   if (!content) {
     throw new Error("Content cannot be null or undefined");
   }
   if (!content.data) {
-    logger.warn(`Chapter at index ${index} has no data, using empty string`);
+    logger.warn(`Chapter at index ${index2} has no data, using empty string`);
     content.data = "";
   }
-  const chapter = initializeChapterInfo(content, index, epubConfigs);
+  const chapter = initializeChapterInfo(content, index2, epubConfigs);
   normalizeAuthorInfo(chapter);
   const allowedAttributes = getAllowedAttributes();
   const allowedXhtml11Tags = getAllowedXhtml11Tags();
   if (!chapter.data || chapter.data.trim().length === 0) {
-    logger.warn(`Chapter at index ${index} has empty data, setting empty content`);
+    logger.warn(`Chapter at index ${index2} has empty data, setting empty content`);
     chapter.data = "";
   } else {
     let $;
     try {
       $ = loadAndProcessHtml(chapter.data);
     } catch (error) {
-      logger.error(`Failed to process HTML for chapter ${index}: ${error}`);
+      logger.error(`Failed to process HTML for chapter ${index2}: ${error}`);
       $ = cheerio.load(`<div>${chapter.data}</div>`);
     }
-    processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index);
+    processHtmlElements($, allowedAttributes, allowedXhtml11Tags, epubConfigs, index2);
     processImages($, chapter, epubConfigs);
-    chapter.data = extractAndCleanHtmlContent($, content.data);
+    chapter.data = extractAndCleanHtmlContent($);
   }
-  processChildrenChapters(chapter, index, epubConfigs);
+  processChildrenChapters(chapter, index2, epubConfigs);
   return chapter;
 }
 promisify(fs.readFile);
@@ -1213,7 +1183,7 @@ function parseOptions(options) {
   if (typeof data.author === "string") {
     data.author = [data.author];
   }
-  data.content = options.content.map((content, index) => parseContent(content, index, data));
+  data.content = options.content.map((content, index2) => parseContent(content, index2, data));
   if (data.cover) {
     data._coverMediaType = mime.getType(data.cover) || "";
     data._coverExtension = mime.getExtension(data._coverMediaType) || "";
@@ -1224,6 +1194,7 @@ async function epubGen(options, configs) {
   if (configs?.logger) {
     logger.setLogger(configs.logger);
   }
+  logger.info("EpubGen started 101...");
   options = { ...options };
   const o = check(options);
   const verbose = options.verbose !== false;
@@ -1253,7 +1224,13 @@ async function epubGen(options, configs) {
   }
 }
 const gen = epubGen;
+const index = {
+  epubGen,
+  gen,
+  errors
+};
 export {
+  index as default,
   epubGen,
   errors,
   gen

package/package.json

@@ -1,11 +1,18 @@
 {
   "name": "wp-epub-gen",
-  "version": "0.4.0",
+  "version": "0.4.2",
   "description": "Epub generator.",
   "type": "module",
-  "main": "build/index.js",
-  "module": "build/index.mjs",
+  "main": "build/index.cjs",
+  "module": "build/index.js",
   "types": "build/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./build/index.d.ts",
+      "import": "./build/index.js",
+      "require": "./build/index.cjs"
+    }
+  },
   "scripts": {
     "tsc": "tsc",
     "test": "vitest --watch=false run",

package/vite.config.ts

@@ -1,8 +1,8 @@
+import { existsSync, readdirSync, readFileSync, statSync, writeFileSync } from 'fs'
 import * as path from 'path'
 import { defineConfig } from 'vite'
 import dts from 'vite-plugin-dts'
 import tsconfigPaths from 'vite-tsconfig-paths'
-import { readFileSync, writeFileSync, existsSync, readdirSync, statSync } from 'fs'
 
 /**
  * 生成模板文件的 TypeScript 代码
@@ -76,15 +76,19 @@ export default defineConfig({
   base: './',
   build: {
     rollupOptions: {
-      input: {
-        index: path.join(__dirname, 'src', 'index.ts'),
+      output: {
+        exports: 'named',
       },
     },
     lib: {
       entry: path.join(__dirname, 'src', 'index.ts'),
       name: 'index',
       formats: ['cjs', 'es'],
-      fileName: (format) => `index.${format === 'es' ? 'mjs' : 'js'}`,
+      // fileName: (format) => {
+      //   if (format === 'es') return 'index.mjs'
+      //   if (format === 'cjs') return 'index.js'
+      //   return `index.${format}`
+      // },
     },
     outDir: path.join(__dirname, 'build'),
     minify: false,