Support for code files parse (#789)

### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
dashi6174 2024-05-15 16:34:28 +08:00 committed by GitHub
parent 12b4c5668c
commit 6ff63ee2ba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions

View File

@ -156,7 +156,7 @@ def filename_type(filename):
return FileType.PDF.value
if re.match(
r".*\.(doc|docx|ppt|pptx|yml|xml|htm|json|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md)$", filename):
r".*\.(doc|docx|ppt|pptx|yml|xml|htm|json|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt)$", filename):
return FileType.DOC.value
if re.match(

View File

@ -136,7 +136,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
excel_parser = ExcelParser()
sections = [(excel_parser.html(binary), "")]
elif re.search(r"\.(txt|md)$", filename, re.IGNORECASE):
elif re.search(r"\.(txt|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
txt = ""
if binary: