hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-08 02:16:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: refurish python code by applying Pylint linter rules (#8322)

Browse Source
This commit is contained in:
Bowen Liang
2024-09-13 22:42:08 +08:00
committed by GitHub
parent 1ab81b4972
commit a1104ab97e
126 changed files with 253 additions and 272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
api/core/rag/extractor/extract_processor.py
View File

@@ -98,17 +98,17 @@ class ExtractProcessor:
unstructured_api_url = dify_config.UNSTRUCTURED_API_URL
unstructured_api_key = dify_config.UNSTRUCTURED_API_KEY
if etl_type == "Unstructured":
if file_extension == ".xlsx" or file_extension == ".xls":
if file_extension in {".xlsx", ".xls"}:
extractor = ExcelExtractor(file_path)
elif file_extension == ".pdf":
extractor = PdfExtractor(file_path)
elif file_extension in [".md", ".markdown"]:
elif file_extension in {".md", ".markdown"}:
extractor = (
UnstructuredMarkdownExtractor(file_path, unstructured_api_url)
if is_automatic
else MarkdownExtractor(file_path, autodetect_encoding=True)
)
elif file_extension in [".htm", ".html"]:
elif file_extension in {".htm", ".html"}:
extractor = HtmlExtractor(file_path)
elif file_extension == ".docx":
extractor = WordExtractor(file_path, upload_file.tenant_id, upload_file.created_by)
@@ -134,13 +134,13 @@ class ExtractProcessor:
else TextExtractor(file_path, autodetect_encoding=True)
)
else:
if file_extension == ".xlsx" or file_extension == ".xls":
if file_extension in {".xlsx", ".xls"}:
extractor = ExcelExtractor(file_path)
elif file_extension == ".pdf":
extractor = PdfExtractor(file_path)
elif file_extension in [".md", ".markdown"]:
elif file_extension in {".md", ".markdown"}:
extractor = MarkdownExtractor(file_path, autodetect_encoding=True)
elif file_extension in [".htm", ".html"]:
elif file_extension in {".htm", ".html"}:
extractor = HtmlExtractor(file_path)
elif file_extension == ".docx":
extractor = WordExtractor(file_path, upload_file.tenant_id, upload_file.created_by)

2
api/core/rag/extractor/firecrawl/firecrawl_app.py
View File

@@ -32,7 +32,7 @@ class FirecrawlApp:
else:
raise Exception(f'Failed to scrape URL. Error: {response["error"]}')
elif response.status_code in [402, 409, 500]:
elif response.status_code in {402, 409, 500}:
error_message = response.json().get("error", "Unknown error occurred")
raise Exception(f"Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}")
else:

4
api/core/rag/extractor/notion_extractor.py
View File

@@ -103,12 +103,12 @@ class NotionExtractor(BaseExtractor):
multi_select_list = property_value[type]
for multi_select in multi_select_list:
value.append(multi_select["name"])
elif type == "rich_text" or type == "title":
elif type in {"rich_text", "title"}:
if len(property_value[type]) > 0:
value = property_value[type][0]["plain_text"]
else:
value = ""
elif type == "select" or type == "status":
elif type in {"select", "status"}:
if property_value[type]:
value = property_value[type]["name"]
else: