epub2md 1.3.0 → 1.5.0

package/README.md

@@ -2,7 +2,18 @@
 
 Even though the package is primarily intended for CLI is to convert EPUB to Markdown, but it can be used programmatically.
 
-主要的目标是转换 epub 到 markdown，当然了也可以当做 epub 的解析器库使用.
+主要的目标是转换 epub 为 多个 markdown 文件，或者合并为 单个 markdown 文件，可以处理其中的远程图片资源；当然了也可以当做 epub 的解析器库使用.
+
+## Main Functions
+
+- **Convert EPUB to Markdown**: By default, convert and output numbered markdown files in sequence.
+- **Autocorrection**: Have option to Handle spaces and punctuation between Chinese and English as You Need.
+- **Merge Chapters**: Optionally merge all markdown files into a single Markdown file, Support link jumping.
+- **Image Processing**:
+  - Retain the original online image links.
+  - Download and localize online images (save remote images locally).
+- **View Information**: Easy to View the basic information, structure, and chapters of the EPUB.
+- **Extraction Function**: Dont need convert, just extract the useful contents of the EPUB file.
 
 ## Global Install for CLI
 
@@ -27,22 +38,51 @@ $ npm install @uxiew/epub2md
 ## CLI
 
 ```bash
-# show usage
+# Show usage help
 $ epub2md -h
 
 # Convert directly to markdown format
 $ epub2md ../../fixtures/zhihu.epub
-# or -m
+# or use -m
 $ epub2md -m ../../fixtures/zhihu.epub
 
-# Convert directly to markdown format with autocorrect to handle spacing between CJK and English words and Correct punctuations Only for command line use
+# Convert multiple files using wildcards
+$ epub2md "fixtures/*.epub"
+$ epub2md "books/fiction-*.epub"
+$ epub2md "library/file-[123].epub"
+
+# Convert multiple files with merge (each file gets its own merged output)
+$ epub2md "fixtures/*.epub" --merge
+
+# Note: Quotes are required around patterns with wildcards to prevent shell expansion
+
+# Convert to markdown and automatically correct spaces and punctuation between Chinese and English (CLI only)
 $ epub2md -M ../../fixtures/zhihu.epub
 
-# show other info
-$ epub2md -u ../../fixtures/zhihu.epub
-$ epub2md -i ../../fixtures/zhihu.epub
-$ epub2md -S ../../fixtures/zhihu.epub
-$ epub2md -s ../../fixtures/zhihu.epub
+# Convert and directly generate a single merged markdown file (no intermediate files)
+$ epub2md -m ../../fixtures/zhihu.epub --merge
+# You can also use the epub file path as the first parameter directly
+$ epub2md ../../fixtures/zhihu.epub --merge
+
+# Use --merge=filename.md
+$ epub2md ../../fixtures/zhihu.epub --merge="merged-book.md"
+
+# By default, DONT downloaded. Basically, the images in the epub are already included, so there is no need to download.
+# However, some epub image links are remote, You will see some warning，maybe they need to be downloaded.
+# Download and localize online images (download remote images to local) (need node > 18.0)
+$ epub2md ../../fixtures/zhihu.epub --localize
+
+# Download and localize online images, while merging all chapters into a single file
+$ epub2md ../../fixtures/zhihu.epub --merge --localize
+
+# Merge existing markdown files in a directory
+$ epub2md --merge ./path/to/markdown/dir
+
+# Show additional information
+$ epub2md -u ../../fixtures/zhihu.epub  # Extract epub
+$ epub2md -i ../../fixtures/zhihu.epub  # Show basic information
+$ epub2md -S ../../fixtures/zhihu.epub  # Show structure information
+$ epub2md -s ../../fixtures/zhihu.epub  # Show chapter information
 ```
 
 ## Usage

package/lib/bin/cli.cjs

@@ -6,59 +6,160 @@ Object.defineProperty(exports, "__esModule", {
 });
 exports.Commands = void 0;
 var _args = _interopRequireDefault(require("args"));
-var _chalk = _interopRequireDefault(require("chalk"));
 var _nodeProcess = _interopRequireDefault(require("node:process"));
+var _nodeFs = _interopRequireDefault(require("node:fs"));
 var _parseEpub = _interopRequireDefault(require("../parseEpub.cjs"));
 var _convert = require("./convert.cjs");
-var _beautyJson = require("beauty-json");
+var _merge = require("./merge.cjs");
+var _logger = _interopRequireDefault(require("../logger.cjs"));
+var _utils = require("./utils.cjs");
 function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 const name = "epub2md";
-var Commands = exports.Commands = /* @__PURE__ */(Commands2 => {
-  Commands2["markdown"] = "md";
-  Commands2["autocorrect"] = "ma";
-  Commands2["unzip"] = "unzip";
-  Commands2["info"] = "info";
-  Commands2["structure"] = "structure";
-  Commands2["sections"] = "sections";
-  return Commands2;
-})(Commands || {});
-const commands = [["md" /* markdown */, "convert the epub file to markdown format"], ["ma" /* autocorrect */, "convert the epub file to markdown format with autocorrect"], ["unzip" /* unzip */, "unzip epub file"], ["info" /* info */, "get epub file basic info"], ["structure" /* structure */, "get epub file structure"], ["sections" /* sections */, "get epub file sections"]];
-const DEFAULT_COMMAND = "md" /* markdown */;
-commands.forEach(cmd => _args.default.option(cmd[0], cmd[1]));
+const Commands = exports.Commands = {
+  convert: "convert",
+  autocorrect: "autocorrect",
+  unzip: "unzip",
+  info: "info",
+  structure: "structure",
+  sections: "sections",
+  merge: "merge",
+  localize: "localize"
+};
+const commands = [[Commands.convert, "convert the epub file to markdown format"], [Commands.autocorrect, "convert the epub file to markdown format with autocorrect"], [Commands.unzip, "unzip epub file"], [Commands.info, "get epub file basic info"], [Commands.structure, "get epub file structure"], [Commands.sections, "get epub file sections"], [Commands.merge, "merge all markdown files into a single file, can also specify output filename with --merge=filename.md"], [Commands.localize, "Retain the original online link and do not convert it to a local path", false]];
+const DEFAULT_COMMAND = Commands.convert;
+commands.forEach(cmd => _args.default.option(cmd[0], cmd[1], cmd[2]));
 const flags = _args.default.parse(_nodeProcess.default.argv, {
   name
 });
-commands.some(([cmd], i) => {
+const unprocessedArgs = _nodeProcess.default.argv.slice(2).filter(arg => !arg.startsWith("--") && !arg.startsWith("-"));
+if (unprocessedArgs.length > 0) {
+  flags[DEFAULT_COMMAND] = unprocessedArgs[0];
+}
+let hasRun = false;
+for (const cmd of [Commands.info, Commands.structure, Commands.sections]) {
   if (flags[cmd]) {
-    run(cmd);
-    return true;
-  } else {
-    if (i === commands.length - 1) {
-      if (_nodeProcess.default.argv[2]) {
-        flags[DEFAULT_COMMAND] = _nodeProcess.default.argv[2];
-        run(DEFAULT_COMMAND);
-        return true;
+    if (typeof flags[cmd] !== "string") {
+      if (unprocessedArgs.length > 0) {
+        flags[cmd] = unprocessedArgs[0];
       }
-      _args.default.showHelp();
+    }
+    if (typeof flags[cmd] === "string") {
+      run(cmd);
+      hasRun = true;
+      break;
     }
   }
-});
-function run(cmd) {
-  const epubPath = flags["md" /* markdown */] || flags["ma" /* autocorrect */] || flags["unzip" /* unzip */];
+}
+if (!hasRun && flags[Commands.unzip]) {
+  const epubPath = typeof flags[Commands.unzip] === "string" ? flags[Commands.unzip] : unprocessedArgs.length > 0 ? unprocessedArgs[0] : null;
   if (epubPath) {
-    console.log(_chalk.default.blueBright(`[${name}]: converting${cmd === "ma" /* autocorrect */ ? " with AutoCorrect" : ""}...`));
-    new _convert.Converter({
-      eubPath: epubPath,
-      cmd
-    }).run(flags["unzip" /* unzip */]).then(outDir => {
-      console.log(_chalk.default.greenBright(`[${name}]: success! output: ${outDir}`));
+    _logger.default.info("unzipping...");
+    new _convert.Converter(epubPath).run({
+      cmd: Commands.unzip,
+      // Use cmd to indicate unzip only
+      mergedFilename: void 0,
+      shouldMerge: false,
+      localize: false
+    }).then(outDir => {
+      _logger.default.info(`Unzip successful! output: ${outDir}`);
+    }).catch(error => {
+      _logger.default.error(error);
     });
+    hasRun = true;
+  } else {
+    _logger.default.error("No valid epub file path provided for unzip command");
+  }
+}
+if (!hasRun) {
+  if (flags.merge && typeof flags.merge === "string" && flags.merge !== "") {
+    if (_nodeFs.default.existsSync(flags.merge) && _nodeFs.default.statSync(flags.merge).isDirectory()) {
+      _logger.default.info("merging markdown files in directory...");
+      (0, _merge.mergeMarkdowns)(flags.merge).then(outputPath => {
+        _logger.default.info(`Merging successful! Output file: ${outputPath}`);
+      }).catch(error => {
+        _logger.default.info(`Merging failed: ${error}`);
+      });
+      hasRun = true;
+    }
+  }
+  if (!hasRun) {
+    for (const cmd of [Commands.convert, Commands.autocorrect]) {
+      if (flags[cmd]) {
+        if (typeof flags[cmd] !== "string") {
+          if (unprocessedArgs.length > 0) {
+            flags[cmd] = unprocessedArgs[0];
+          }
+        }
+        run(cmd);
+        hasRun = true;
+        break;
+      }
+    }
+    if (!hasRun && unprocessedArgs.length > 0) {
+      run(DEFAULT_COMMAND);
+    } else if (!hasRun) {
+      _args.default.showHelp();
+    }
+  }
+}
+async function run(cmd) {
+  if (cmd === Commands.convert || cmd === Commands.autocorrect) {
+    const epubPath = typeof flags[cmd] === "string" ? flags[cmd] : null;
+    if (!epubPath) {
+      _logger.default.error("No valid epub file path provided");
+      return;
+    }
+    const epubFiles = await (0, _utils.expandWildcard)(epubPath);
+    if (epubFiles.length === 0) {
+      _logger.default.error(`No files found matching pattern: ${epubPath}`);
+      return;
+    }
+    const shouldMerge = flags.merge === true || typeof flags.merge === "string" && flags.merge !== "";
+    let mergedFilename;
+    if (typeof flags.merge === "string" && flags.merge !== "") {
+      mergedFilename = flags.merge;
+    }
+    if (mergedFilename && epubFiles.length > 1) {
+      _logger.default.warn(`Warning: Using custom merge filename "${mergedFilename}" with multiple files. Each file will overwrite the previous merged output.`);
+      _logger.default.warn(`Consider using --merge (without filename) to generate separate merged files for each epub.`);
+    }
+    const localize = flags.localize === true;
+    if (epubFiles.length > 1) {
+      _logger.default.info(`Found ${epubFiles.length} files matching pattern "${epubPath}"`);
+    }
+    for (let i = 0; i < epubFiles.length; i++) {
+      const currentFile = epubFiles[i];
+      _logger.default.info(`[${i + 1}/${epubFiles.length}] Converting ${currentFile}${cmd === Commands.autocorrect ? " with autocorrect" : ""}${flags[Commands.merge] ? " and merging" : ""}...`);
+      try {
+        const outDir = await new _convert.Converter(currentFile).run({
+          cmd,
+          mergedFilename,
+          shouldMerge,
+          localize
+        });
+        if (shouldMerge) {
+          _logger.default.info(`[${i + 1}/${epubFiles.length}] Merging successful! Output file: ${outDir}`);
+        } else {
+          _logger.default.info(`[${i + 1}/${epubFiles.length}] Conversion successful! output: ${outDir}`);
+        }
+      } catch (error) {
+        _logger.default.error(`[${i + 1}/${epubFiles.length}] Failed to convert ${currentFile}:`, error);
+      }
+    }
+    if (epubFiles.length > 1) {
+      _logger.default.success(`Completed processing ${epubFiles.length} files`);
+    }
     return;
   }
-  (0, _parseEpub.default)(flags[cmd]).then(res => {
-    console.log(_chalk.default.greenBright(`[${name}]: This book ${cmd}:`));
-    _beautyJson.json.log(res[cmd]);
-  }).catch(error => {
-    console.log(_chalk.default.red(error));
-  });
+  const cmdPath = flags[cmd];
+  if (typeof cmdPath === "string") {
+    (0, _parseEpub.default)(cmdPath).then(res => {
+      _logger.default.success(`This book ${cmd}:`);
+      _logger.default.json(res[cmd]);
+    }).catch(error => {
+      _logger.default.error(error);
+    });
+  } else {
+    _logger.default.error(`Path must be a string, got ${typeof cmdPath}`);
+  }
 }