From c6e3a2e713c1aae9f4f051e370a6cc396c0e6e61 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=88=98=E5=BA=B7=E4=BC=9F?=
 <71975350+lksr1201@users.noreply.github.com>
Date: Tue, 19 May 2026 12:28:31 +0800
Subject: [PATCH] Fix: MinerU vlm-http-client backend output file detection
 (#14240)

## Problem
When using MinerU with `vlm-http-client` backend, the parser fails to
find the output files because they are located in a `vlm/` subdirectory,
but the `_read_output`
  method doesn't check this location.

  ## Error Message
  [ERROR]MinerU not found.
  [MinerU] Missing output file, tried: ...

  ## Root Cause
The MinerU API with `vlm-http-client` backend returns output files in
the following structure:
  output_dir/
    vlm/
      filename_content_list.json
      filename.md
      images/

  However, the `_read_output` method in `mineru_parser.py` only checks:
  1. `output_dir/filename_content_list.json`
  2. `output_dir/sanitized_filename_content_list.json`
3. `output_dir/sanitized_filename/sanitized_filename_content_list.json`

  It doesn't check the `vlm/` subdirectory.

  ## Solution
  Added two additional fallback paths to check the `vlm/` subdirectory:
  - `output_dir/vlm/filename_content_list.json`
  - `output_dir/vlm/sanitized_filename_content_list.json`

  ## Testing
Tested with MinerU API using `vlm-http-client` backend. The parser now
successfully finds and processes the output files.

  ## Related
  This issue occurs specifically when using:
  - MinerU backend: `vlm-http-client`
  - MinerU server URL configured for remote vLLM inference
---
 deepdoc/parser/mineru_parser.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/deepdoc/parser/mineru_parser.py b/deepdoc/parser/mineru_parser.py
index 90c33573ce..b369f9122a 100644
--- a/deepdoc/parser/mineru_parser.py
+++ b/deepdoc/parser/mineru_parser.py
@@ -539,6 +539,21 @@ class MinerUParser(RAGFlowPdfParser):
                 if nested_alt.exists():
                     subdir = nested_alt.parent
                     json_file = nested_alt
+                else:
+                    # Try vlm subdirectory (for vlm-http-client backend)
+                    vlm_path = output_dir / "vlm" / f"{file_stem}_content_list.json"
+                    self.logger.info(f"[MinerU] Trying vlm subdirectory: {vlm_path}")
+                    attempted.append(vlm_path)
+                    if vlm_path.exists():
+                        subdir = vlm_path.parent
+                        json_file = vlm_path
+                    else:
+                        vlm_safe = output_dir / "vlm" / f"{safe_stem}_content_list.json"
+                        self.logger.info(f"[MinerU] Trying vlm subdirectory with sanitized name: {vlm_safe}")
+                        attempted.append(vlm_safe)
+                        if vlm_safe.exists():
+                            subdir = vlm_safe.parent
+                            json_file = vlm_safe
 
         if not json_file:
             parse_subdir = None