From 6fd237986ece44915918d7f6fa50edb1a93fa922 Mon Sep 17 00:00:00 2001
From: BukeLy <bukely0119@foxmail.com>
Date: Tue, 28 Apr 2026 15:23:34 +0800
Subject: [PATCH 1/2] Recognize whole-line bold as level-1 heading in markdown
 parser
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

extract_nodes_from_markdown now matches `**Title**` lines as level-1
headings (alongside ATX `#` headings) and attaches the heading level
on the producer side. extract_node_text_content reads the level from
the node instead of re-running a `^#{1,6}` regex on the source line,
which was silently dropping bold-heading nodes from OCR / MinerU output.

Bold maps to level 1 even when mixed with `#` / `##` / `###` — bold-as-
heading is a courtesy heuristic for non-ATX markdown sources, and
CommonMark has no concept of bold heading depth.
---
 pageindex/page_index_md.py | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/pageindex/page_index_md.py b/pageindex/page_index_md.py
index 5a59716..7785f81 100644
--- a/pageindex/page_index_md.py
+++ b/pageindex/page_index_md.py
@@ -31,6 +31,7 @@ async def generate_summaries_for_structure_md(structure, summary_token_threshold
 
 def extract_nodes_from_markdown(markdown_content):
     header_pattern = r'^(#{1,6})\s+(.+)$'
+    bold_heading_pattern = r'^\*\*(.+?)\*\*\s*$'
     code_block_pattern = r'^```'
     node_list = []
     
@@ -54,7 +55,14 @@ def extract_nodes_from_markdown(markdown_content):
             match = re.match(header_pattern, stripped_line)
             if match:
                 title = match.group(2).strip()
-                node_list.append({'node_title': title, 'line_num': line_num})
+                level = len(match.group(1))
+                node_list.append({'node_title': title, 'line_num': line_num, 'level': level})
+                continue
+
+            bold_match = re.match(bold_heading_pattern, stripped_line)
+            if bold_match:
+                title = bold_match.group(1).strip()
+                node_list.append({'node_title': title, 'line_num': line_num, 'level': 1})
 
     return node_list, lines
 
@@ -62,17 +70,10 @@ def extract_nodes_from_markdown(markdown_content):
 def extract_node_text_content(node_list, markdown_lines):    
     all_nodes = []
     for node in node_list:
-        line_content = markdown_lines[node['line_num'] - 1]
-        header_match = re.match(r'^(#{1,6})', line_content)
-        
-        if header_match is None:
-            print(f"Warning: Line {node['line_num']} does not contain a valid header: '{line_content}'")
-            continue
-            
         processed_node = {
             'title': node['node_title'],
             'line_num': node['line_num'],
-            'level': len(header_match.group(1))
+            'level': node['level']
         }
         all_nodes.append(processed_node)
     

From 01dbcbf47f50030d1df0aa1adec3d417c6328977 Mon Sep 17 00:00:00 2001
From: BukeLy <bukely0119@foxmail.com>
Date: Thu, 16 Jul 2026 19:36:52 +0800
Subject: [PATCH 2/2] fix(markdown): skip empty bold headings

---
 pageindex/page_index_md.py  |  5 +++--
 tests/test_page_index_md.py | 23 +++++++++++++++++++++++
 2 files changed, 26 insertions(+), 2 deletions(-)
 create mode 100644 tests/test_page_index_md.py

diff --git a/pageindex/page_index_md.py b/pageindex/page_index_md.py
index 7785f81..7c5e958 100644
--- a/pageindex/page_index_md.py
+++ b/pageindex/page_index_md.py
@@ -62,7 +62,8 @@ def extract_nodes_from_markdown(markdown_content):
             bold_match = re.match(bold_heading_pattern, stripped_line)
             if bold_match:
                 title = bold_match.group(1).strip()
-                node_list.append({'node_title': title, 'line_num': line_num, 'level': 1})
+                if title:
+                    node_list.append({'node_title': title, 'line_num': line_num, 'level': 1})
 
     return node_list, lines
 
@@ -340,4 +341,4 @@ if __name__ == "__main__":
     with open(output_path, 'w', encoding='utf-8') as f:
         json.dump(tree_structure, f, indent=2, ensure_ascii=False)
     
-    print(f"\nTree structure saved to: {output_path}")
\ No newline at end of file
+    print(f"\nTree structure saved to: {output_path}")
diff --git a/tests/test_page_index_md.py b/tests/test_page_index_md.py
new file mode 100644
index 0000000..12aa908
--- /dev/null
+++ b/tests/test_page_index_md.py
@@ -0,0 +1,23 @@
+import unittest
+
+from pageindex.page_index_md import extract_nodes_from_markdown
+
+
+class ExtractNodesFromMarkdownTest(unittest.TestCase):
+    def test_skips_bold_heading_with_only_whitespace(self):
+        nodes, _ = extract_nodes_from_markdown("**   **\n**Valid heading**")
+
+        self.assertEqual(
+            nodes,
+            [
+                {
+                    "node_title": "Valid heading",
+                    "line_num": 2,
+                    "level": 1,
+                }
+            ],
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()