From 3f2792dff4d76b072d8b04a9bc5e6612f6857ae3 Mon Sep 17 00:00:00 2001
From: cc <12849@>
Date: Thu, 15 Jan 2026 17:46:20 +0800
Subject: [PATCH] fix(parser): provide explicit file_extension for markitdown
 to resolve #544

---
 docreader/parser/markitdown_parser.py | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/docreader/parser/markitdown_parser.py b/docreader/parser/markitdown_parser.py
index c067cd74..bf4b1213 100644
--- a/docreader/parser/markitdown_parser.py
+++ b/docreader/parser/markitdown_parser.py
@@ -22,9 +22,24 @@ class StdMarkitdownParser(BaseParser):
     def __init__(self, *args, **kwargs):
         self.markitdown = MarkItDown()
 
-    def parse_into_text(self, content: bytes) -> Document:
-        result = self.markitdown.convert(io.BytesIO(content), keep_data_uris=True)
-        return Document(content=result.text_content)
+    def parse_into_text(self, content: bytes, file_extension: str = None) -> Document:
+        """
+        Modified to support explicit file_extension to fix Issue #544.
+        If file_extension is not provided, we try to infer it or default to None.
+        """
+        try:
+            # 核心修复点：传入 file_extension 参数
+            # 如果调用方没传，markitdown 可能会报错，这里我们至少保证它有尝试的机会
+            result = self.markitdown.convert(
+                io.BytesIO(content),
+                file_extension=file_extension,
+                keep_data_uris=True
+            )
+            return Document(content=result.text_content)
+        except Exception as e:
+            logger.warning(f"Markitdown conversion failed: {e}. Fallback might be triggered.")
+            # 必须抛出异常，这样外部的 FirstParser 才会切换到 DocxParser 这种备选方案
+            raise e
 
 
 class MarkitdownParser(PipelineParser):