Fix clickable parent Part navigation in Calibre

src/common/html.py

@@ -14,14 +14,30 @@ def parse_html(content):
     return BeautifulSoup(re.sub(r'^\s*<\?xml[^>]*\?>', '', content), 'html5lib')
 
 
+def normalize_navigation_markup(soup):
+    """Remove only our generated wrappers around nested NAV labels.
+
+    Reader TOC parsers expect li > a + ol. A generated li > span > a
+    retains a valid href but is interpreted as an unlinked section by Calibre.
+    This also upgrades source structures cached by earlier versions.
+    """
+    for wrapper in list(soup.find_all('span', attrs={'data-translation-unit': 'true'})):
+        parent = wrapper.parent
+        if (parent and parent.name == 'li' and wrapper.find_parent('nav')
+                and parent.find('ol', recursive=False)
+                and wrapper.find('a', href=True, recursive=False)):
+            wrapper.unwrap()
+
+
 def translation_targets(soup):
     """Choose disjoint leaf blocks; wrap mixed direct text without renaming containers.
 
     A li containing p must never be extracted twice. Text before a nested list or
     inside an otherwise bare body still needs its own unit.
     """
+    normalize_navigation_markup(soup)
     for container in list(soup.find_all(list(TARGET_TAGS | {'body'}))):
-        if container.find_parent(list(SKIP_TAGS)):
+        if container.find_parent(list(SKIP_TAGS)) or container.find_parent('nav'):
             continue
         has_blocks = container.find(list(BLOCK_TAGS)) is not None
         if container.name != 'body' and not has_blocks:

src/preprocessing/navigation.py

@@ -10,7 +10,7 @@ import zipfile
 from urllib.parse import unquote, urlsplit
 from bs4 import NavigableString
 from lxml import etree
-from src.common.html import parse_html
+from src.common.html import parse_html, normalize_navigation_markup
 from src.common.data_model import ManifestEntry
 from src.preprocessing.format_extractor import FormatExtractor
 from src.assembly.package_writer import package_path
@@ -134,6 +134,8 @@ def prepare_navigation(original, structure, entries):
     """Enrich the manifest with canonical heading entries, never translate TOC duplicates."""
     soups={r.href:parse_html(r.content) for r in structure.resources.values()
            if r.media_type=='application/xhtml+xml' and r.content}
+    for soup in soups.values():
+        normalize_navigation_markup(soup)
     resources={posixpath.normpath(unquote(r.href)):r for r in structure.resources.values()}
     labels={}
     def collect(document, href, label):