Improve EPUB restoration, book terminology and Calibre QA workflow

2026-10-08 07:25:27 +08:00
parent 40491e6386
commit caf9d8f4bb
35 changed files with 1439 additions and 959 deletions
@@ -0,0 +1,79 @@
+"""Patch the original container to preserve OPF, navigation, heads and assets."""
+import posixpath
+import zipfile
+from pathlib import Path
+from urllib.parse import unquote
+from lxml import etree
+from src.common.html import parse_html
+
+OPF = 'http://www.idpf.org/2007/opf'
+DC = 'http://purl.org/dc/elements/1.1/'
+
+
+def package_path(zf):
+    container = etree.fromstring(zf.read('META-INF/container.xml'))
+    return container.xpath('//*[local-name()="rootfile"]/@full-path')[0]
+
+
+def write_preserving_package(original, structure, output):
+    output = Path(output)
+    if output.resolve() == Path(original).resolve():
+        raise ValueError('Output must not overwrite the source EPUB')
+    replacements = {}
+    with zipfile.ZipFile(original) as source:
+        opf_path = package_path(source)
+        base = posixpath.dirname(opf_path)
+        opf = etree.fromstring(source.read(opf_path))
+        manifest = opf.find(f'{{{OPF}}}manifest')
+        items = {x.get('id'): x for x in manifest}
+        # A collision-free stylesheet path and ID, independent of book layout.
+        css_href = 'Styles/bilingual_style.css'
+        css_id = 'bilingual_style_css'
+        while posixpath.join(base, css_href) in source.namelist():
+            css_href = 'Styles/' + Path(css_href).stem + '-new.css'
+        while css_id in items:
+            css_id += '_new'
+        css_archive_path = posixpath.normpath(posixpath.join(base, css_href))
+        etree.SubElement(manifest, f'{{{OPF}}}item', id=css_id, href=css_href, **{'media-type': 'text/css'})
+        replacements[css_archive_path] = (Path(__file__).parent/'bilingual_style.css').read_bytes()
+        for item_id, resource in structure.resources.items():
+            if resource.media_type != 'application/xhtml+xml' or not resource.content:
+                continue
+            if 'nav' in (items.get(item_id).get('properties', '') if item_id in items else '').split() and 'translation-for' not in resource.content and 'class="translation"' not in resource.content:
+                continue
+            if item_id not in items:
+                raise ValueError(f'Unknown package item: {item_id}')
+            archive_path = posixpath.normpath(posixpath.join(base, unquote(items[item_id].get('href'))))
+            if archive_path not in source.namelist():
+                raise ValueError(f'Missing source resource: {archive_path}')
+            soup = parse_html(resource.content)
+            soup.html['xmlns'] = 'http://www.w3.org/1999/xhtml'
+            soup.html['xmlns:epub'] = 'http://www.idpf.org/2007/ops'
+            soup.html['lang'] = structure.metadata.language
+            soup.html['xml:lang'] = structure.metadata.language
+            if soup.find(class_='translation'):
+                link = soup.new_tag('link', rel='stylesheet', type='text/css')
+                link['href'] = posixpath.relpath(css_archive_path, posixpath.dirname(archive_path))
+                soup.head.append(link)
+            data = str(soup).encode('utf-8')
+            # Never silently let an EPUB contain invalid XHTML.
+            etree.fromstring(data, etree.XMLParser(resolve_entities=False, no_network=True))
+            replacements[archive_path] = data
+        for language in opf.findall(f'.//{{{DC}}}language'):
+            language.text = structure.metadata.language
+        replacements[opf_path] = etree.tostring(opf, encoding='utf-8', xml_declaration=True)
+        temp = output.with_suffix(output.suffix + '.tmp')
+        output.parent.mkdir(parents=True, exist_ok=True)
+        try:
+            with zipfile.ZipFile(temp, 'w', compression=zipfile.ZIP_DEFLATED) as target:
+                target.writestr('mimetype', b'application/epub+zip', compress_type=zipfile.ZIP_STORED)
+                for info in source.infolist():
+                    if info.filename == 'mimetype':
+                        continue
+                    target.writestr(info, replacements.pop(info.filename, source.read(info.filename)))
+                for name, data in replacements.items():
+                    target.writestr(name, data)
+            temp.replace(output)
+        finally:
+            temp.unlink(missing_ok=True)
+    return output