fix: param skip_infer_table_types should be first item from m_skip_infer_table_types (#200)

forgot `m_skip_infer_table_types` is a list of str

Author: yuming-long

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.0.39-dev0
+
+* Fix wrong handleing on param skip_infer_table_types
+
 ## 0.0.38
 
 * Fix page break has None page number bug

pipeline-notebooks/pipeline-general.ipynb

@@ -824,7 +824,7 @@
     "    else:\n",
     "        pdf_infer_table_structure = False\n",
     "        \n",
-    "    skip_infer_table_types = m_skip_infer_table_types if len(m_skip_infer_table_types) else [\"pdf\", \"jpg\", \"png\"]\n",
+    "    skip_infer_table_types = m_skip_infer_table_types[0] if len(m_skip_infer_table_types) else [\"pdf\", \"jpg\", \"png\"]\n",
     "    \n",
     "    try:\n",
     "        logger.debug(\"partition input data: {}\".format(\n",

prepline_general/api/general.py

@@ -294,7 +294,7 @@ def pipeline_api(
         pdf_infer_table_structure = False
 
     skip_infer_table_types = (
-        m_skip_infer_table_types if len(m_skip_infer_table_types) else ["pdf", "jpg", "png"]
+        m_skip_infer_table_types[0] if len(m_skip_infer_table_types) else ["pdf", "jpg", "png"]
     )
 
     try:
@@ -485,7 +485,7 @@ def return_content_type(filename):
 
 
 @router.post("/general/v0/general")
-@router.post("/general/v0.0.38/general")
+@router.post("/general/v0.0.39/general")
 def pipeline_1(
     request: Request,
     gz_uncompressed_content_type: Optional[str] = Form(default=None),

preprocessing-pipeline-family.yaml

@@ -1,2 +1,2 @@
 name: general
-version: 0.0.38
+version: 0.0.39

test_general/api/test_app.py

@@ -166,7 +166,7 @@ def test_skip_infer_table_types_param():
     response = client.post(
         MAIN_API_ROUTE,
         files=[("files", (str(test_file), open(test_file, "rb")))],
-        data={"skip_infer_table_types": ["pdf"]},
+        data={"skip_infer_table_types": "['pdf']"},
     )
 
     assert response.status_code == 200