mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
Feat: parse email (#10181)
### What problem does this PR solve? - Dataflow support email. - Fix old email parser. - Add new depends to parse msg file. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [x] Other (please describe): add new depends.
This commit is contained in:
@ -155,7 +155,7 @@ def filename_type(filename):
|
||||
if re.match(r".*\.pdf$", filename):
|
||||
return FileType.PDF.value
|
||||
|
||||
if re.match(r".*\.(eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
|
||||
if re.match(r".*\.(msg|eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
|
||||
return FileType.DOC.value
|
||||
|
||||
if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
|
||||
|
||||
Reference in New Issue
Block a user