From e2e1c86dd4b0a5a7307a62aebc1b4e6abf1c37cd Mon Sep 17 00:00:00 2001
From: "m.dabbagh" <mostafadabbagh76@gmail.com>
Date: Mon, 19 Jan 2026 14:00:17 +0330
Subject: [PATCH] fix sorting and merging in zip extractor

---
 .../outgoing/extractors/zip_extractor.py      | 25 ++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/src/adapters/outgoing/extractors/zip_extractor.py b/src/adapters/outgoing/extractors/zip_extractor.py
index 13e4253..c7c4048 100644
--- a/src/adapters/outgoing/extractors/zip_extractor.py
+++ b/src/adapters/outgoing/extractors/zip_extractor.py
@@ -5,6 +5,7 @@ This adapter implements the IExtractor port for ZIP files containing
 Markdown documents. It merges all .md files into a single document.
 """
 import logging
+import re
 import zipfile
 from pathlib import Path
 from typing import List
@@ -184,7 +185,7 @@ class ZipExtractor(IExtractor):
                 )
 
                 # Join all parts with proper spacing
-                return "".join(merged_parts).strip()
+                return "\n".join(merged_parts).strip()
 
         except EmptyContentError:
             raise
@@ -234,11 +235,29 @@ class ZipExtractor(IExtractor):
             if filename.lower().endswith('.md'):
                 md_files.append(filename)
 
-        # Sort alphabetically for deterministic order
-        md_files.sort()
+        # Sort using natural/numeric order (page_1, page_2, ..., page_10)
+        md_files.sort(key=self._natural_sort_key)
 
         return md_files
 
+    def _natural_sort_key(self, filename: str):
+        """
+        Generate a natural sort key for proper numeric ordering.
+
+        Converts numeric parts to integers for correct sorting:
+        - 'page_1.md' < 'page_2.md' < 'page_10.md'
+
+        Args:
+            filename: Filename to generate sort key for
+
+        Returns:
+            List of alternating strings and integers for natural sorting
+        """
+        def convert(text):
+            return int(text) if text.isdigit() else text.lower()
+
+        return [convert(c) for c in re.split(r'(\d+)', filename)]
+
     def _extract_file_content(
         self,
         zip_file: zipfile.ZipFile,