From 1d9ca172e3b70271ad4f021d76a044d435f3b1f4 Mon Sep 17 00:00:00 2001
From: hy89 <31279043+hy89@users.noreply.github.com>
Date: Thu, 20 Mar 2025 16:00:17 +0800
Subject: [PATCH] Fix(api): correct document parsing progress check logic
 (#6318)

- Fix incorrect progress check condition that prevented re-parsing of
completed documents
- Allow parsing for documents with progress 0.0 (not started) or 1.0
(completed)
- Only block parsing for documents currently in progress (0.0 < progress
< 1.0)

Close #6312

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
---
 api/apps/sdk/doc.py                                           | 4 ++--
 .../test_parse_documents.py                                   | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/api/apps/sdk/doc.py b/api/apps/sdk/doc.py
index 25c78d520..65271dba4 100644
--- a/api/apps/sdk/doc.py
+++ b/api/apps/sdk/doc.py
@@ -688,9 +688,9 @@ def parse(tenant_id, dataset_id):
             continue
         if not doc:
             return get_error_data_result(message=f"You don't own the document {id}.")
-        if doc[0].progress != 0.0:
+        if 0.0 < doc[0].progress < 1.0:
             return get_error_data_result(
-                "Can't stop parsing document with progress at 0 or 100"
+                "Can't parse document that is currently being processed"
             )
         info = {"run": "1", "progress": 0, "progress_msg": "", "chunk_num": 0, "token_num": 0}
         DocumentService.update_by_id(id, info)
diff --git a/sdk/python/test/test_http_api/test_file_management_within_dataset/test_parse_documents.py b/sdk/python/test/test_http_api/test_file_management_within_dataset/test_parse_documents.py
index d4a5ff0a7..f96a06613 100644
--- a/sdk/python/test/test_http_api/test_file_management_within_dataset/test_parse_documents.py
+++ b/sdk/python/test/test_http_api/test_file_management_within_dataset/test_parse_documents.py
@@ -205,8 +205,7 @@ class TestDocumentsParse:
         res = parse_documnet(
             get_http_api_auth, dataset_id, {"document_ids": document_ids}
         )
-        assert res["code"] == 102
-        assert res["message"] == "Can't stop parsing document with progress at 0 or 100"
+        assert res["code"] == 0
 
     @pytest.mark.skip(reason="issues/6234")
     def test_duplicate_parse(self, get_http_api_auth, tmp_path):