change file type logic

autorag/VERSION

@@ -1 +1 @@
-0.3.11rc2
+0.3.11rc3

autorag/data/parse/run.py

@@ -53,12 +53,23 @@ def run_parser(
 		)
 		set_file_types = set([module["file_type"] for module in module_params])
 
+		# Calculate the set difference once
+		file_types_to_remove = set_file_types - file_types
+
+		# Use list comprehension to filter out unwanted elements
+		module_params = [
+			param
+			for param in module_params
+			if param["file_type"] not in file_types_to_remove
+		]
+		modules = [
+			module
+			for module, param in zip(modules, module_params)
+			if param["file_type"] not in file_types_to_remove
+		]
+
 		# create a list of only those file_types that are in file_types but not in set_file_types
 		missing_file_types = list(file_types - set_file_types)
-		if list(set_file_types - file_types):
-			raise ValueError(
-				f"File types {list(set_file_types - file_types)} are not in the data path."
-			)
 
 		if missing_file_types:
 			add_modules_list = []

tests/autorag/data/parse/test_parse_run.py

@@ -24,3 +24,25 @@ def test_run_parser():
 			"file_type": "pdf",
 		}
 		assert os.path.exists(os.path.join(temp_dir, "pdf.parquet"))
+
+
+def test_run_parser_two():
+	with tempfile.TemporaryDirectory(ignore_cleanup_errors=True) as temp_dir:
+		modules = [langchain_parse, langchain_parse]
+		module_params = [
+			{"parse_method": "pdfminer", "file_type": "pdf"},
+			{"parse_method": "csv", "file_type": "csv"},
+		]
+		data_path_glob = eng_text_glob
+		summary_df = run_parser(
+			modules, module_params, data_path_glob, temp_dir, all_files=False
+		)
+		assert os.path.exists(os.path.join(temp_dir, "summary.csv"))
+		expect_columns = {"filename", "module_name", "module_params", "execution_time"}
+		assert set(summary_df.columns) == expect_columns
+		assert len(summary_df) == 1
+		assert summary_df["module_params"][0] == {
+			"parse_method": "pdfminer",
+			"file_type": "pdf",
+		}
+		assert os.path.exists(os.path.join(temp_dir, "pdf.parquet"))