Fix nested chapter anchors and Chinese ordinal navigation

src/preprocessing/navigation.py

@@ -98,6 +98,12 @@ def _headings(soup, target, label):
     anchor = soup.find(id=fragment) if fragment else None
     if fragment and anchor is None:
         return [], 'missing anchor'
+    # Publisher TOCs often target an <a>/<span> inside a heading. The
+    # enclosing heading owns the text; subsequent prose is not the target.
+    if anchor and anchor.name not in HEADINGS:
+        enclosing = anchor.find_parent(HEADINGS)
+        if enclosing is not None:
+            anchor = enclosing
     identity = title_identity(label)
     # Only inspect the opening leaf blocks or blocks at the explicit anchor.
     # An exact match across adjacent blocks also recognizes Calibre-converted
@@ -108,7 +114,7 @@ def _headings(soup, target, label):
         nearby = [anchor] + anchor.find_all_next(HEADINGS + ['p','div'], limit=16)
         block_ids = {id(t) for t in blocks}
         blocks = [t for t in nearby if id(t) in block_ids]
-    blocks = [t for t in blocks if plain(t.get_text())][:12]
+    blocks = [t for t in blocks if any(c.isalnum() for c in plain(t.get_text()))][:12]
     matches = []
     for start in range(min(len(blocks), 6)):
         for end in range(start+1, min(start+4, len(blocks))+1):
@@ -220,7 +226,10 @@ def normalize_heading_html(record, html):
     prefix=ordinal(record)
     if not prefix: return html
     soup=parse_html('<div>'+html+'</div>');root=soup.body.div
-    nodes=[n for n in root.find_all(string=True) if plain(str(n))]
+    hidden = [n for n in root.find_all(string=True) if plain(str(n)) and
+              n.find_parent(class_=re.compile(r'^(?:sr-only|visually-hidden|screen-reader-only)$'))]
+    hidden_ids = {id(n) for n in hidden}
+    nodes=[n for n in root.find_all(string=True) if plain(str(n)) and id(n) not in hidden_ids]
     if not nodes: return html
     node=nodes[0];text=plain(str(node));compact=re.sub(r'\s+', '', text).strip('：:')
     # Some publishers put the digit in its own styled span: 第<span>1</span>部.
@@ -228,11 +237,18 @@ def normalize_heading_html(record, html):
             and re.fullmatch(r'[章部篇][：:]?',plain(str(nodes[2])))):
         nodes[1].replace_with(chinese_number(record['number']))
         nodes[2].replace_with('章' if record['role']=='chapter' else '部')
-    elif re.fullmatch(r'(?:\d+|[IVXLCDM]+|第[零一二三四五六七八九十百千万\d]+(?:章|部分?|篇))',compact,re.I):
+    elif re.fullmatch(r'(?:\d+|[IVXLCDM]+|[零一二三四五六七八九十百千万]+(?:章|部分?|篇)?|第[零一二三四五六七八九十百千万\d]+(?:章|部分?|篇))',compact,re.I):
         node.replace_with(prefix)
         if len(nodes)>1 and plain(str(nodes[1])) in {':','：'}: nodes[1].replace_with('')
+        elif len(nodes)>1 and plain(str(nodes[1])) in {'章','部','部分','篇'}: nodes[1].replace_with('')
     elif re.match(r'^第[零一二三四五六七八九十百千万\d]+[章部篇]',compact):
         node.replace_with(re.sub(r'^第[零一二三四五六七八九十百千万\d]+(?:章|部分?|篇)',prefix,compact))
+    visible_now = [n for n in root.find_all(string=True) if plain(str(n)) and id(n) not in hidden_ids]
+    if visible_now and plain(str(visible_now[0])).startswith(prefix):
+        # The visible ordinal now includes "chapter/part"; the hidden prefix
+        # would otherwise announce it a second time to assistive readers.
+        for text_node in hidden:
+            text_node.parent['aria-hidden'] = 'true'
     return root.decode_contents()
 
 
@@ -242,7 +258,13 @@ def navigation_labels(structure, entries):
         units=[by_id.get(key) for key in record.get('entry_ids',[record['entry_id']])]
         if any(not e or not e.translated_html or e.validation_errors for e in units): continue
         units[0].translated_html=normalize_heading_html(record,units[0].translated_html)
-        label=plain(' '.join(parse_html(e.translated_html).get_text(' ',strip=True) for e in units))
+        visible = []
+        for entry in units:
+            soup = parse_html(entry.translated_html)
+            for hidden in soup.select('[aria-hidden="true"], .sr-only, .visually-hidden, .screen-reader-only'):
+                hidden.decompose()
+            visible.append(soup.get_text(' ', strip=True))
+        label=plain(' '.join(visible))
         prefix=ordinal(record)
         # Standardize punctuation only for the navigation label; the rich
         # heading can keep its number and subtitle on separate lines.