@daisy/epub-utils - npm Package Compare versions

Comparing version 1.2.0-beta.6 to 1.2.0-beta.7

lib/epub-parse.js

@@ -14,4 +14,4 @@ // input: unzipped book directory
 const fileUrl = require('file-url');
-const DOMParser = require('xmldom-alpha').DOMParser;
-const XMLSerializer = require('xmldom-alpha').XMLSerializer;
+const DOMParser = require('xmldom').DOMParser;
+const XMLSerializer = require('xmldom').XMLSerializer;
 const fs = require('fs');
@@ -45,3 +45,6 @@ const path = require('path');
   const content = fs.readFileSync(fullpath).toString();
-  //FIXME hack to workaround xmldom-alpha regex test
+  // not application/xhtml+xml because:
+  // https://github.com/jindw/xmldom/pull/208
+  // https://github.com/jindw/xmldom/pull/242
+  // https://github.com/xmldom/xmldom/blob/3db6ccf3f7ecbde73608490d71f96c727abdd69a/lib/dom-parser.js#L12
   const doc = new DOMParser({ errorHandler }).parseFromString(content, 'application/xhtml');
@@ -85,7 +88,18 @@
   const result = {};
-  select('//dc:*', doc).forEach(dcElem => {
+  select('/opf:package/opf:metadata/dc:*', doc).forEach(dcElem => {
     addMeta(`dc:${dcElem.localName}`, dcElem.textContent, result);
   });
-  select('//opf:meta[not(@refines)]', doc).forEach(meta => {
-    addMeta(meta.getAttribute('property'), meta.textContent, result);
+  select('/opf:package/opf:metadata/opf:meta[not(@refines)]', doc).forEach(meta => {
+    const prop = meta.getAttribute('property');
+    if (prop) {
+      if (meta.textContent) {
+        addMeta(prop, meta.textContent, result);
+      }
+    } else {
+      const name = meta.getAttribute('name');
+      const content = meta.getAttribute('content');
+      if (name && content) {
+        addMeta(name, content, result);
+      }
+    }
   });
@@ -106,4 +120,4 @@ return result;
   const result = {};
-  select('//opf:link[not(@refines)]', doc).forEach(link => {
-    addLink(link.getAttribute('rel'), decodeURI(link.getAttribute('href')), result);
+  select('/opf:package/opf:metadata/opf:link[not(@refines)]', doc).forEach(link => {
+    addLink(link.getAttribute('rel') || link.getAttribute('property'), decodeURI(link.getAttribute('href')), result);
   });
@@ -145,5 +159,5 @@ return result;
 
-  const spineItemIdrefs = select('//opf:itemref/@idref', doc);
+  const spineItemIdrefs = select('/opf:package/opf:spine/opf:itemref/@idref', doc);
   spineItemIdrefs.forEach(idref => {
-    const manifestItem = select(`//opf:item[@id='${idref.nodeValue}']`, doc);
+    const manifestItem = select(`/opf:package/opf:manifest/opf:item[@id='${idref.nodeValue}']`, doc);
     if (manifestItem.length > 0) {
@@ -169,3 +183,3 @@ const contentType = (manifestItem[0].getAttribute('media-type') || '').trim();
 
-  const navDocRef = select('//opf:item' + '[contains(concat(" ", normalize-space(@properties), " ")," nav ")]' + '/@href', doc);
+  const navDocRef = select('/opf:package/opf:manifest/opf:item' + '[contains(concat(" ", normalize-space(@properties), " ")," nav ")]' + '/@href', doc);
   if (navDocRef.length > 0) {
@@ -177,4 +191,5 @@ const navDocPath = decodeURI(navDocRef[0].nodeValue);
 
-  this.hasBindings = select('//opf:bindings', doc).length > 0;
-  this.hasManifestFallbacks = select('//opf:item[@fallback]', doc).length > 0;
+  this.hasGuide = select('/opf:package/opf:guide', doc).length > 0;
+  this.hasBindings = select('/opf:package/opf:bindings', doc).length > 0;
+  this.hasManifestFallbacks = select('/opf:package/opf:manifest/opf:item[@fallback]', doc).length > 0;
 };
@@ -184,6 +199,9 @@
   const content = fs.readFileSync(filepath).toString();
-  //FIXME hack to workaround xmldom-alpha regex test
+  // not application/xhtml+xml because:
+  // https://github.com/jindw/xmldom/pull/208
+  // https://github.com/jindw/xmldom/pull/242
+  // https://github.com/xmldom/xmldom/blob/3db6ccf3f7ecbde73608490d71f96c727abdd69a/lib/dom-parser.js#L12
   const doc = new DOMParser({ errorHandler }).parseFromString(content, 'application/xhtml');
   const select = xpath.useNamespaces({ html: "http://www.w3.org/1999/xhtml", epub: "http://www.idpf.org/2007/ops" });
-  const title = select('//html:title/text()', doc);
+  const title = select('/html:html/html:head/html:title/text()', doc);
   if (title.length > 0) {
@@ -201,3 +219,3 @@ return title[0].nodeValue;
   const select = xpath.useNamespaces({ ocf: 'urn:oasis:names:tc:opendocument:xmlns:container' });
-  const rootfiles = select('//ocf:rootfile[@media-type="application/oebps-package+xml"]/@full-path', doc);
+  const rootfiles = select('/ocf:container/ocf:rootfiles/ocf:rootfile[@media-type="application/oebps-package+xml"]/@full-path', doc);
   // just grab the first one as we're not handling the case of multiple renditions
@@ -204,0 +222,0 @@ if (rootfiles.length > 0) {

lib/epub.js

@@ -15,4 +15,4 @@ 'use strict';
 
-async function unzip(path, useLegacyZipLib) {
-  const tmpdir = tmp.dirSync({ unsafeCleanup: true, keep: LOG_DEBUG_URLS }).name;
+async function unzip(unzipDir, path, useLegacyZipLib) {
+  const tmpdir = unzipDir || tmp.dirSync({ unsafeCleanup: true, keep: LOG_DEBUG_URLS }).name;
   if (LOG_DEBUG_URLS) {
@@ -25,11 +25,9 @@ console.log(">>>>>> LOG_DEBUG_URLS");
     if (useLegacyZipLib) {
-      extractZip(path, { dir: tmpdir }, err => {
-        if (err) {
-          if (LOG_DEBUG_URLS) {
-            console.log(err);
-          }
-          reject(err);
-        } else {
-          resolve(tmpdir);
+      extractZip(path, { dir: tmpdir }).then(() => {
+        resolve(tmpdir);
+      }).catch(err => {
+        if (LOG_DEBUG_URLS) {
+          console.log(err);
         }
+        reject(err);
       });
@@ -75,3 +73,3 @@ } else {
 
-async function retryUnzip(epub, error) {
+async function retryUnzip(unzipDir, epub, error) {
   if (error.message === undefined) throw error;
@@ -102,3 +100,3 @@ winston.info('Trying to repair the archive and unzip again...');
       fs.truncateSync(tmpEPUB, truncatedSize);
-      const res = await unzip(tmpEPUB, true);
+      const res = await unzip(unzipDir, unzipDirtmpEPUB, true);
       if (needsDelete) {
@@ -134,3 +132,3 @@ process.nextTick(() => {
 
-  async extract() {
+  async extract(unzipDir) {
     if (this.basedir !== undefined) {
@@ -146,3 +144,3 @@ return this;
       try {
-        unzippedDir = await unzip(this.path);
+        unzippedDir = await unzip(unzipDir, this.path);
       } catch (error) {
@@ -152,3 +150,3 @@ winston.error('Failed to unzip EPUB (the ZIP archive may be corrupt). TRYING LEGACY ZIP LIB ...');
         try {
-          unzippedDir = await unzip(this.path, true);
+          unzippedDir = await unzip(unzipDir, this.path, true);
         } catch (error) {
@@ -158,3 +156,3 @@ winston.error('Failed to unzip EPUB again (the ZIP archive may be corrupt). TRYING ZIP PATCH ...');
           try {
-            unzippedDir = await retryUnzip(this, error);
+            unzippedDir = await retryUnzip(unzipDir, this, error);
           } catch (error) {
@@ -161,0 +159,0 @@ throw error;

package.json

 {
   "name": "@daisy/epub-utils",
-  "version": "1.2.0-beta.6",
+  "version": "1.2.0-beta.7",
   "description": "EPUB parser and model, used by Ace",
@@ -21,10 +21,10 @@ "author": {
   "dependencies": {
-    "extract-zip": "^1.6.7",
+    "extract-zip": "^2.0.0",
     "file-url": "^3.0.0",
-    "fs-extra": "^8.1.0",
-    "node-stream-zip": "^1.8.2",
+    "fs-extra": "^9.0.0",
+    "node-stream-zip": "^1.9.1",
     "tmp": "^0.1.0",
     "winston": "^3.2.1",
-    "xmldom-alpha": "^0.1.28",
-    "xpath": "0.0.24"
+    "xmldom": "^0.3.0",
+    "xpath": "^0.0.27"
   },
@@ -31,0 +31,0 @@ "publishConfig": {

No alert changes

Improved metrics

Total package byte prevSize

14464

increased by7.51%

Lines of code

362

increased by4.62%

Dependency changes

• + Addedxmldom@^0.3.0

• + Added@types/node@22.13.1(transitive)

• + Added@types/yauzl@2.10.3(transitive)

• + Addedat-least-node@1.0.0(transitive)

• + Addeddebug@4.4.0(transitive)

• + Addedend-of-stream@1.4.4(transitive)

• + Addedextract-zip@2.0.1(transitive)

• + Addedfs-extra@9.1.0(transitive)

• + Addedget-stream@5.2.0(transitive)

• + Addedjsonfile@6.1.0(transitive)

• + Addedpump@3.0.2(transitive)

• + Addedsafe-buffer@5.2.1(transitive)

• + Addedstring_decoder@1.3.0(transitive)

• + Addedundici-types@6.20.0(transitive)

• + Addeduniversalify@2.0.1(transitive)

• + Addedxmldom@0.3.0(transitive)

• + Addedxpath@0.0.27(transitive)

• - Removedxmldom-alpha@^0.1.28

• - Removedbuffer-from@1.1.2(transitive)

• - Removedconcat-stream@1.6.2(transitive)

• - Removedcore-util-is@1.0.3(transitive)

• - Removeddebug@2.6.9(transitive)

• - Removedextract-zip@1.7.0(transitive)

• - Removedfs-extra@8.1.0(transitive)

• - Removedisarray@1.0.0(transitive)

• - Removedjsonfile@4.0.0(transitive)

• - Removedminimist@1.2.8(transitive)

• - Removedmkdirp@0.5.6(transitive)

• - Removedms@2.0.0(transitive)

• - Removedprocess-nextick-args@2.0.1(transitive)

• - Removedreadable-stream@2.3.8(transitive)

• - Removedsafe-buffer@5.1.2(transitive)

• - Removedstring_decoder@1.1.1(transitive)

• - Removedtypedarray@0.0.6(transitive)

• - Removeduniversalify@0.1.2(transitive)

• - Removedxmldom-alpha@0.1.28(transitive)

• - Removedxpath@0.0.24(transitive)

• Updatedextract-zip@^2.0.0

• Updatedfs-extra@^9.0.0

• Updatednode-stream-zip@^1.9.1

• Updatedxpath@^0.0.27