youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-03 08:58:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/end-user-oauth

Browse Source
This commit is contained in:
zhsama
2025-12-08 16:49:57 +08:00
parent ff3e3338cb 71497954b8
commit 2ea8e11882
204 changed files with 7347 additions and 5943 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
api/core/workflow/nodes/document_extractor/node.py
View File

@ -7,7 +7,7 @@ import tempfile
from collections.abc import Mapping, Sequence
from typing import Any
import chardet
import charset_normalizer
import docx
import pandas as pd
import pypandoc
@ -228,9 +228,12 @@ def _extract_text_by_file_extension(*, file_content: bytes, file_extension: str)
def _extract_text_from_plain_text(file_content: bytes) -> str:
try:
# Detect encoding using chardet
result = chardet.detect(file_content)
encoding = result["encoding"]
# Detect encoding using charset_normalizer
result = charset_normalizer.from_bytes(file_content, cp_isolation=["utf_8", "latin_1", "cp1252"]).best()
if result:
encoding = result.encoding
else:
encoding = "utf-8"
# Fallback to utf-8 if detection fails
if not encoding:
@ -247,9 +250,12 @@ def _extract_text_from_plain_text(file_content: bytes) -> str:
def _extract_text_from_json(file_content: bytes) -> str:
try:
# Detect encoding using chardet
result = chardet.detect(file_content)
encoding = result["encoding"]
# Detect encoding using charset_normalizer
result = charset_normalizer.from_bytes(file_content).best()
if result:
encoding = result.encoding
else:
encoding = "utf-8"
# Fallback to utf-8 if detection fails
if not encoding:
@ -269,9 +275,12 @@ def _extract_text_from_json(file_content: bytes) -> str:
def _extract_text_from_yaml(file_content: bytes) -> str:
"""Extract the content from yaml file"""
try:
# Detect encoding using chardet
result = chardet.detect(file_content)
encoding = result["encoding"]
# Detect encoding using charset_normalizer
result = charset_normalizer.from_bytes(file_content).best()
if result:
encoding = result.encoding
else:
encoding = "utf-8"
# Fallback to utf-8 if detection fails
if not encoding:
@ -424,9 +433,12 @@ def _extract_text_from_file(file: File):
def _extract_text_from_csv(file_content: bytes) -> str:
try:
# Detect encoding using chardet
result = chardet.detect(file_content)
encoding = result["encoding"]
# Detect encoding using charset_normalizer
result = charset_normalizer.from_bytes(file_content).best()
if result:
encoding = result.encoding
else:
encoding = "utf-8"
# Fallback to utf-8 if detection fails
if not encoding:

5
api/core/workflow/nodes/node_factory.py
View File

@ -64,7 +64,10 @@ class DifyNodeFactory(NodeFactory):
if not node_mapping:
raise ValueError(f"No class mapping found for node type: {node_type}")
node_class = node_mapping.get(LATEST_VERSION)
latest_node_class = node_mapping.get(LATEST_VERSION)
node_version = str(node_data.get("version", "1"))
matched_node_class = node_mapping.get(node_version)
node_class = matched_node_class or latest_node_class
if not node_class:
raise ValueError(f"No latest version class found for node type: {node_type}")