Add support for HTML file (#973)

### What problem does this PR solve?

Add support for HTML file

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Zhedong Cen
2024-05-30 09:12:55 +08:00
committed by GitHub
parent dded365b8d
commit 8dd45459be
10 changed files with 66 additions and 6 deletions

View File

@ -15,7 +15,7 @@ from io import BytesIO
import re
from rag.app import laws
from rag.nlp import rag_tokenizer, tokenize, find_codec
from deepdoc.parser import PdfParser, ExcelParser, PlainParser
from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser
class Pdf(PdfParser):
@ -97,6 +97,12 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
sections = [s for s in sections if s]
callback(0.8, "Finish parsing.")
elif re.search(r"\.(htm|html)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
sections = HtmlParser()(filename, binary)
sections = [s for s in sections if s]
callback(0.8, "Finish parsing.")
elif re.search(r"\.doc$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
binary = BytesIO(binary)