@likecoin/epubcheck-ts 0.6.0 → 0.6.2

package/README.md

@@ -114,17 +114,22 @@ if (result.valid) {
 const fs = require('node:fs');
 
 async function validate() {
-  const { EpubCheck } = await import('epubcheck-ts');
-  
+  const { EpubCheck } = require('@likecoin/epubcheck-ts');
+
   const epubData = fs.readFileSync('book.epub');
   const result = await EpubCheck.validate(epubData);
-  
+
   console.log(result.valid ? 'Valid!' : 'Invalid');
 }
 
 validate();
 ```
 
+> The XML engine (`libxml2-wasm`, ESM-only with top-level await) is lazy-loaded
+> inside `EpubCheck.validate()`, so the package stays `require()`-able from
+> CommonJS and importable without forcing top-level-await support on your
+> bundler.
+
 ### Browser
 
 ```typescript

package/bin/epubcheck.js

@@ -2,8 +2,8 @@
 import { readFile, readdir, stat, writeFile } from "node:fs/promises";
 import { parseArgs } from "node:util";
 import { basename, join, relative, sep } from "node:path";
-const { EpubCheck, EPUB_VERSIONS, toJSONReport } = await import("../dist/index.js");
-const VERSION = "0.6.0";
+const { EpubCheck, EPUB_VERSIONS, MessageId, toJSONReport } = await import("../dist/index.js");
+const VERSION = "0.6.2";
 const VALID_MODES = /* @__PURE__ */ new Set([
   "exp",
   "opf",
@@ -301,6 +301,19 @@ async function main() {
     const shouldFail = result.errorCount > 0 || result.fatalCount > 0 || failOnWarnings && result.warningCount > 0;
     process.exit(shouldFail ? 1 : 0);
   } catch (error) {
+    const code = error?.code;
+    if (code === "ENOENT") {
+      console.error(`\x1B[31m\x1B[1mFATAL (${filePath}):\x1B[0m EPUB file could not be found`);
+      console.error(`  \x1B[90mID: ${MessageId.PKG_018}\x1B[0m`);
+      process.exit(1);
+    }
+    if (code === "EACCES" || code === "EISDIR" || code === "EIO") {
+      console.error(
+        `\x1B[31m\x1B[1mFATAL (${filePath}):\x1B[0m Unable to read EPUB contents: ${error instanceof Error ? error.message : String(error)}`
+      );
+      console.error(`  \x1B[90mID: ${MessageId.PKG_015}\x1B[0m`);
+      process.exit(1);
+    }
     console.error("\x1B[31mError:\x1B[0m", error instanceof Error ? error.message : String(error));
     if (error instanceof Error && error.stack && !values.quiet) {
       console.error("\x1B[90m" + error.stack + "\x1B[0m");

package/bin/epubcheck.ts

@@ -20,9 +20,9 @@ import type {
 } from '../src/types.js';
 
 // Dynamic import to support both ESM and CJS builds
-const { EpubCheck, EPUB_VERSIONS, toJSONReport } = await import('../dist/index.js');
+const { EpubCheck, EPUB_VERSIONS, MessageId, toJSONReport } = await import('../dist/index.js');
 
-const VERSION = '0.6.0';
+const VERSION = '0.6.2';
 const VALID_MODES: ReadonlySet<ValidationMode> = new Set([
   'exp',
   'opf',
@@ -399,6 +399,19 @@ async function main(): Promise<void> {
       result.errorCount > 0 || result.fatalCount > 0 || (failOnWarnings && result.warningCount > 0);
     process.exit(shouldFail ? 1 : 0);
   } catch (error) {
+    const code = (error as NodeJS.ErrnoException | undefined)?.code;
+    if (code === 'ENOENT') {
+      console.error(`\x1b[31m\x1b[1mFATAL (${filePath}):\x1b[0m EPUB file could not be found`);
+      console.error(`  \x1b[90mID: ${MessageId.PKG_018}\x1b[0m`);
+      process.exit(1);
+    }
+    if (code === 'EACCES' || code === 'EISDIR' || code === 'EIO') {
+      console.error(
+        `\x1b[31m\x1b[1mFATAL (${filePath}):\x1b[0m Unable to read EPUB contents: ${error instanceof Error ? error.message : String(error)}`,
+      );
+      console.error(`  \x1b[90mID: ${MessageId.PKG_015}\x1b[0m`);
+      process.exit(1);
+    }
     console.error('\x1b[31mError:\x1b[0m', error instanceof Error ? error.message : String(error));
     if (error instanceof Error && error.stack && !values.quiet) {
       console.error('\x1b[90m' + error.stack + '\x1b[0m');

package/dist/index.cjs

@@ -1,10 +1,25 @@
 'use strict';
 
-var libxml2Wasm = require('libxml2-wasm');
 var cssTree = require('css-tree');
 var fflate = require('fflate');
 
-// src/content/validator.ts
+// src/util/xml-engine.ts
+var engine;
+async function loadXmlEngine() {
+  engine ??= await import('libxml2-wasm');
+}
+function getXmlDocument() {
+  if (!engine) {
+    throw new Error("libxml2-wasm not initialized \u2014 call loadXmlEngine() first");
+  }
+  return engine.XmlDocument;
+}
+function getXmlElement() {
+  if (!engine) {
+    throw new Error("libxml2-wasm not initialized \u2014 call loadXmlEngine() first");
+  }
+  return engine.XmlElement;
+}
 
 // src/messages/messages.ts
 var severityOverrides = /* @__PURE__ */ new Map();
@@ -2693,6 +2708,31 @@ var PROFILE_DC_TYPE = {
   dict: "dictionary",
   preview: "preview"
 };
+var TYPE_TO_PROFILE = {
+  dictionary: "dict",
+  edupub: "edupub",
+  index: "idx",
+  preview: "preview"
+};
+var RESERVED_PREFIX_URIS = {
+  dcterms: "http://purl.org/dc/terms/",
+  marc: "http://id.loc.gov/vocabulary/",
+  media: "http://www.idpf.org/epub/vocab/overlays/#",
+  onix: "http://www.editeur.org/ONIX/book/codelists/current.html#",
+  rendition: "http://www.idpf.org/vocab/rendition/#",
+  schema: "http://schema.org/",
+  xsd: "http://www.w3.org/2001/XMLSchema#",
+  a11y: "http://www.idpf.org/epub/vocab/package/a11y/#"
+};
+function isValidURI(uri) {
+  if (!uri) return false;
+  try {
+    new URL(uri);
+    return true;
+  } catch {
+    return false;
+  }
+}
 var DICTIONARY_TYPE_VALUES = /* @__PURE__ */ new Set([
   "monolingual",
   "bilingual",
@@ -2800,11 +2840,13 @@ var OPFValidator = class {
     this.validatePackageAttributes(context, opfPath);
     this.validateMetadata(context, opfPath);
     if (this.packageDoc.version !== "2.0") {
+      this.validatePrefixDeclarations(context, opfPath, opfXml);
       this.validateMetaPrefixes(context, opfPath, opfXml);
     }
     this.validateLinkElements(context, opfPath);
     this.validateManifest(context, opfPath);
     this.validateSpine(context, opfPath);
+    this.validatePageMap(context, opfPath, opfXml);
     this.validateFallbackChains(context, opfPath);
     this.validateUndeclaredResources(context, opfPath);
     if (this.packageDoc.version === "2.0") {
@@ -2835,6 +2877,7 @@ var OPFValidator = class {
     if (this.packageDoc.version.startsWith("3.")) {
       this.validateAccessibilityMetadata(context, opfPath);
       this.validateProfileDcType(context, opfPath);
+      this.validateDcTypeProfileSwitch(context, opfPath);
       this.validateEdupubMetadata(context, opfPath);
       this.validateDictionaryMetadata(context, opfPath);
       this.validatePreviewMetadata(context, opfPath);
@@ -3038,6 +3081,22 @@ var OPFValidator = class {
       });
     }
   }
+  // Mirrors Java's EPUBProfile.makeTypeCompatible flow.
+  validateDcTypeProfileSwitch(context, opfPath) {
+    if (!this.packageDoc) return;
+    for (const dc of this.packageDoc.dcElements) {
+      if (dc.name !== "type") continue;
+      const inferred = TYPE_TO_PROFILE[dc.value.trim().toLowerCase()];
+      if (inferred && inferred !== context.options.profile) {
+        pushMessage(context.messages, {
+          id: MessageId.OPF_064,
+          message: `OPF declares type "${dc.value.trim().toLowerCase()}"; consider validating using the "${inferred}" profile.`,
+          location: { path: opfPath }
+        });
+        return;
+      }
+    }
+  }
   /**
    * Build lookup maps for manifest items
    */
@@ -3054,6 +3113,13 @@ var OPFValidator = class {
    */
   validatePackageAttributes(context, opfPath) {
     if (!this.packageDoc) return;
+    if (this.packageDoc.isLegacyOebps12) {
+      pushMessage(context.messages, {
+        id: MessageId.OPF_047,
+        message: "OPF file is using OEBPS 1.2 syntax allowing backwards compatibility.",
+        location: { path: opfPath }
+      });
+    }
     if (this.packageDoc.versionDeclared === false) {
       pushMessage(context.messages, {
         id: MessageId.OPF_001,
@@ -3978,14 +4044,24 @@ var OPFValidator = class {
       const resolvedPath = resolvePath(opfPath, basePathNoQuery);
       const resolvedPathDecoded = basePathDecodedNoQuery !== basePathNoQuery ? resolvePath(opfPath, basePathDecodedNoQuery) : resolvedPath;
       const fileExists = context.files.has(resolvedPath) || context.files.has(resolvedPathDecoded);
-      const inManifest = this.manifestByHref.has(basePathNoQuery) || this.manifestByHref.has(basePathDecodedNoQuery);
-      if (!fileExists && !inManifest) {
+      const manifestItem = this.manifestByHref.get(basePathNoQuery) ?? this.manifestByHref.get(basePathDecodedNoQuery);
+      if (!fileExists && !manifestItem) {
         pushMessage(context.messages, {
           id: MessageId.RSC_007w,
           message: `Referenced resource "${resolvedPath}" could not be found in the EPUB`,
           location: { path: opfPath }
         });
       }
+      if (manifestItem) {
+        const inSpine = this.packageDoc.spine.some((ref) => ref.idref === manifestItem.id);
+        if (!inSpine) {
+          pushMessage(context.messages, {
+            id: MessageId.OPF_067,
+            message: `Resource "${manifestItem.href}" is referenced as a link but is also declared as a manifest item.`,
+            location: { path: opfPath }
+          });
+        }
+      }
     }
   }
   /**
@@ -4267,6 +4343,56 @@ var OPFValidator = class {
       }
     }
   }
+  // Mirrors Java's PrefixDeclarationParser + VocabUtil.parsePrefixDeclaration,
+  // but emits only the four main IDs (not Java's OPF-004a..f sub-codes).
+  validatePrefixDeclarations(context, opfPath, opfXml) {
+    const stripped = stripXmlComments(opfXml);
+    const match = /<package[^>]*\sprefix\s*=\s*["']([^"']*)["']/.exec(stripped);
+    if (!match) return;
+    const raw = match[1] ?? "";
+    if (raw !== raw.trim()) {
+      pushMessage(context.messages, {
+        id: MessageId.OPF_004,
+        message: "The value of the prefix attribute has leading or trailing whitespace.",
+        location: { path: opfPath }
+      });
+    }
+    const parts = raw.trim().split(/\s+/).filter(Boolean);
+    for (let i = 0; i < parts.length; ) {
+      const token = parts[i] ?? "";
+      if (token.endsWith(":") && token.length > 1) {
+        const prefix = token.slice(0, -1);
+        const uri = parts[i + 1];
+        if (!uri || uri.endsWith(":")) {
+          pushMessage(context.messages, {
+            id: MessageId.OPF_005,
+            message: `The prefix "${prefix}" is declared but no URI is bound to it.`,
+            location: { path: opfPath }
+          });
+          i += 1;
+          continue;
+        }
+        if (!isValidURI(uri)) {
+          pushMessage(context.messages, {
+            id: MessageId.OPF_006,
+            message: `The value "${uri}" bound to prefix "${prefix}" is not a valid URI.`,
+            location: { path: opfPath }
+          });
+        }
+        const reservedUri = RESERVED_PREFIX_URIS[prefix];
+        if (reservedUri !== void 0 && reservedUri !== uri) {
+          pushMessage(context.messages, {
+            id: MessageId.OPF_007,
+            message: `The prefix "${prefix}" is reserved and must not be re-declared.`,
+            location: { path: opfPath }
+          });
+        }
+        i += 2;
+      } else {
+        i += 1;
+      }
+    }
+  }
   /**
    * RSC-005: all id attributes on elements in the OPF document must be unique.
    * Mirrors Java's id-unique.sch / opf.sch opf_idAttrUnique pattern, which
@@ -4275,16 +4401,7 @@ var OPFValidator = class {
    */
   validateMetaPrefixes(context, opfPath, opfXml) {
     if (!this.packageDoc) return;
-    const RESERVED = /* @__PURE__ */ new Set([
-      "dcterms",
-      "marc",
-      "onix",
-      "schema",
-      "xsd",
-      "a11y",
-      "media",
-      "rendition"
-    ]);
+    const RESERVED = new Set(Object.keys(RESERVED_PREFIX_URIS));
     const declared = new Set(Object.keys(this.packageDoc.prefixes ?? {}));
     const reported = /* @__PURE__ */ new Set();
     const reportIfUndeclared = (prefix) => {
@@ -4491,6 +4608,26 @@ var OPFValidator = class {
       }
     }
   }
+  validatePageMap(context, opfPath, opfXml) {
+    if (!this.packageDoc) return;
+    const stripped = stripXmlComments(opfXml);
+    const m = /<spine\b[^>]*\spage-map\s*=\s*["']([^"']*)["']/.exec(stripped);
+    if (!m) return;
+    const pageMapId = (m[1] ?? "").trim();
+    pushMessage(context.messages, {
+      id: MessageId.OPF_062,
+      message: `Found Adobe page-map attribute on spine element (page-map="${pageMapId}")`,
+      location: { path: opfPath }
+    });
+    if (!pageMapId) return;
+    if (!this.manifestById.has(pageMapId)) {
+      pushMessage(context.messages, {
+        id: MessageId.OPF_063,
+        message: `The Adobe page-map item "${pageMapId}" was not found in the manifest`,
+        location: { path: opfPath }
+      });
+    }
+  }
   /**
    * Validate fallback chains
    */
@@ -4962,7 +5099,7 @@ var SKMValidator = class {
     const content = typeof data === "string" ? data : new TextDecoder().decode(data);
     let doc = null;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(content);
+      doc = getXmlDocument().fromString(content);
     } catch {
       pushMessage(context.messages, {
         id: MessageId.RSC_016,
@@ -5199,7 +5336,7 @@ var SMILValidator = class {
     const content = typeof data === "string" ? data : new TextDecoder().decode(data);
     let doc = null;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(content);
+      doc = getXmlDocument().fromString(content);
     } catch {
       pushMessage(context.messages, {
         id: MessageId.RSC_016,
@@ -6109,7 +6246,7 @@ var ContentValidator = class {
     const svgContent = new TextDecoder().decode(svgData);
     let doc;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(svgContent);
+      doc = getXmlDocument().fromString(svgContent);
       this.extractAndRegisterIDs(path, doc.root, registry);
     } catch (e) {
       pushMessage(context.messages, {
@@ -6127,7 +6264,7 @@ var ContentValidator = class {
     const svgContent = new TextDecoder().decode(svgData);
     let doc;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(svgContent);
+      doc = getXmlDocument().fromString(svgContent);
     } catch {
       return;
     }
@@ -6173,7 +6310,7 @@ var ContentValidator = class {
     const svgContent = new TextDecoder().decode(svgData);
     let doc;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(svgContent);
+      doc = getXmlDocument().fromString(svgContent);
     } catch {
       return;
     }
@@ -6523,7 +6660,7 @@ var ContentValidator = class {
     }
     let doc = null;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(content);
+      doc = getXmlDocument().fromString(content);
     } catch (error) {
       if (error instanceof Error) {
         const { message, line, column } = this.parseLibxmlError(error.message);
@@ -7214,6 +7351,9 @@ var ContentValidator = class {
     const docDir = path.includes("/") ? path.substring(0, path.lastIndexOf("/")) : "";
     const opfDir = context.opfPath?.includes("/") ? context.opfPath.substring(0, context.opfPath.lastIndexOf("/")) : "";
     const tocAnchors = tocNav.find(".//html:a[@href]", HTML_NS);
+    if (context.contentFeatures) {
+      context.contentFeatures.tocLinkCount = (context.contentFeatures.tocLinkCount ?? 0) + tocAnchors.length;
+    }
     const tocLinks = [];
     for (const anchor of tocAnchors) {
       const href = this.getAttribute(anchor, "href")?.trim();
@@ -8336,6 +8476,10 @@ var ContentValidator = class {
     if (!features.hasRDFa && root.get(".//*[@property]")) {
       features.hasRDFa = true;
     }
+    if (context.options.profile === "edupub") {
+      const sections = root.find(".//html:body//html:section", XHTML_NS);
+      features.sectionCount = (features.sectionCount ?? 0) + sections.length;
+    }
   }
   validateImages(context, path, root) {
     const packageDoc = context.packageDocument;
@@ -8601,11 +8745,12 @@ var ContentValidator = class {
       }
       return Number.parseInt(el.name.substring(1), 10);
     };
+    const XmlElement = getXmlElement();
     const directElementChildren = (parent) => {
       const out = [];
       let n = parent.firstChild;
       while (n) {
-        if (n instanceof libxml2Wasm.XmlElement) out.push(n);
+        if (n instanceof XmlElement) out.push(n);
         n = n.next;
       }
       return out;
@@ -8759,7 +8904,7 @@ var ContentValidator = class {
       let prev = p.prev;
       let hasHeadingBefore = false;
       while (prev) {
-        if (prev instanceof libxml2Wasm.XmlElement && /^h[1-6]$/.test(prev.name)) {
+        if (prev instanceof XmlElement && /^h[1-6]$/.test(prev.name)) {
           hasHeadingBefore = true;
           break;
         }
@@ -10209,11 +10354,13 @@ function toJSONReport(result) {
     2
   );
 }
+
+// src/ncx/validator.ts
 var NCXValidator = class {
   validate(context, ncxContent, ncxPath, registry) {
     let doc = null;
     try {
-      doc = libxml2Wasm.XmlDocument.fromString(ncxContent);
+      doc = getXmlDocument().fromString(ncxContent);
     } catch (error) {
       if (error instanceof Error) {
         pushMessage(context.messages, {
@@ -10271,6 +10418,13 @@ var NCXValidator = class {
       });
       return;
     }
+    if (uidContent !== uidContent.trim()) {
+      pushMessage(context.messages, {
+        id: MessageId.NCX_004,
+        message: "NCX dtb:uid meta content has leading or trailing whitespace.",
+        location: { path, line: uidElement.line }
+      });
+    }
     context.ncxUid = uidContent.trim();
   }
   checkNavMap(context, root, path) {
@@ -10900,8 +11054,8 @@ var OCFValidator = class {
       zip = ZipReader.open(context.data);
     } catch (error) {
       pushMessage(context.messages, {
-        id: MessageId.PKG_001,
-        message: `Failed to open EPUB file: ${error instanceof Error ? error.message : "Unknown error"}`
+        id: MessageId.PKG_004,
+        message: `Failed to open EPUB ZIP: ${error instanceof Error ? error.message : "Unknown error"}`
       });
       return;
     }
@@ -10935,8 +11089,8 @@ var OCFValidator = class {
     const compressionInfo = zip.getMimetypeCompressionInfo();
     if (compressionInfo === null) {
       pushMessage(messages, {
-        id: MessageId.PKG_006,
-        message: "Could not read ZIP header",
+        id: MessageId.PKG_003,
+        message: "Unable to read EPUB file header, likely corrupted",
         location: { path: "mimetype" }
       });
       return;
@@ -11963,11 +12117,11 @@ var RelaxNGValidator = class extends BaseSchemaValidator {
     try {
       const libxml2 = await import('libxml2-wasm');
       const LibRelaxNGValidator = libxml2.RelaxNGValidator;
-      const { XmlDocument: XmlDocument5 } = libxml2;
-      const doc = XmlDocument5.fromString(xml);
+      const { XmlDocument } = libxml2;
+      const doc = XmlDocument.fromString(xml);
       try {
         const schemaContent = await loadSchema(schemaPath);
-        const schemaDoc = XmlDocument5.fromString(schemaContent);
+        const schemaDoc = XmlDocument.fromString(schemaContent);
         try {
           const validator = LibRelaxNGValidator.fromDoc(schemaDoc);
           try {
@@ -12177,6 +12331,7 @@ var EpubCheck = class _EpubCheck {
    */
   async check(data, filename) {
     const startTime = performance.now();
+    await loadXmlEngine();
     const context = {
       data,
       options: this.options,
@@ -12201,7 +12356,7 @@ var EpubCheck = class _EpubCheck {
       await this.runPipeline(context);
     } catch (error) {
       pushMessage(context.messages, {
-        id: MessageId.PKG_025,
+        id: MessageId.PKG_008,
         message: error instanceof Error ? error.message : "Unknown validation error"
       });
     } finally {
@@ -12218,6 +12373,7 @@ var EpubCheck = class _EpubCheck {
    */
   async checkExpanded(files) {
     const startTime = performance.now();
+    await loadXmlEngine();
     const context = {
       data: new Uint8Array(0),
       options: this.options,
@@ -12243,7 +12399,7 @@ var EpubCheck = class _EpubCheck {
       await this.runPipeline(context);
     } catch (error) {
       pushMessage(context.messages, {
-        id: MessageId.PKG_025,
+        id: MessageId.PKG_008,
         message: error instanceof Error ? error.message : "Unknown validation error"
       });
     } finally {
@@ -12262,6 +12418,7 @@ var EpubCheck = class _EpubCheck {
   async checkSingleFile(data, filename) {
     const startTime = performance.now();
     const mode = this.options.mode;
+    await loadXmlEngine();
     const context = {
       data: new Uint8Array(0),
       options: this.options,
@@ -12310,7 +12467,7 @@ var EpubCheck = class _EpubCheck {
       }
     } catch (error) {
       pushMessage(context.messages, {
-        id: MessageId.PKG_025,
+        id: MessageId.PKG_008,
         message: error instanceof Error ? error.message : "Unknown validation error"
       });
     } finally {
@@ -12360,6 +12517,15 @@ var EpubCheck = class _EpubCheck {
     const profile = context.options.profile;
     const opfPath = context.opfPath ?? "";
     if (profile === "edupub") {
+      const sectionCount = features.sectionCount ?? 0;
+      const tocLinkCount = features.tocLinkCount ?? 0;
+      if (sectionCount > 0 && sectionCount !== tocLinkCount) {
+        pushMessage(context.messages, {
+          id: MessageId.NAV_004,
+          message: "The Navigation Document should contain the full hierarchy of headings in the document for EDUPUB.",
+          location: { path: opfPath }
+        });
+      }
       if (features.hasPageBreak && !features.hasPageList) {
         pushMessage(context.messages, {
           id: MessageId.NAV_003,
@@ -12700,7 +12866,14 @@ var EpubCheck = class _EpubCheck {
         message: "For maximum compatibility, use only lowercase characters for the EPUB file extension.",
         location: { path: filename }
       });
+      return;
     }
+    const isEpub2 = context.version.startsWith("2");
+    pushMessage(context.messages, {
+      id: isEpub2 ? MessageId.PKG_017 : MessageId.PKG_024,
+      message: `EPUB file has an uncommon extension "${extension}".`,
+      location: { path: filename }
+    });
   }
   /**
    * Build a filtered report from validation context