pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: support json file (#1217)

Browse Source 
### What problem does this PR solve?

feat: support json file.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: KevinHuSh <kevinhu.sh@gmail.com>
This commit is contained in:
Wang Baoling
2024-06-21 10:42:29 +08:00
committed by GitHub
parent f7cdb2678c
commit 18f4a6b35c
4 changed files with 126 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
rag/app/naive.py
View File

@ -17,7 +17,7 @@ from timeit import default_timer as timer
import re
from deepdoc.parser.pdf_parser import PlainParser
from rag.nlp import rag_tokenizer, naive_merge, tokenize_table, tokenize_chunks, find_codec
from deepdoc.parser import PdfParser, ExcelParser, DocxParser, HtmlParser
from deepdoc.parser import PdfParser, ExcelParser, DocxParser, HtmlParser, JsonParser
from rag.settings import cron_logger
from rag.utils import num_tokens_from_string
@ -167,6 +167,12 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
sections = [(l, "") for l in sections if l]
callback(0.8, "Finish parsing.")
elif re.search(r"\.json$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
sections = JsonParser(parser_config.get("chunk_token_num", 128))(binary)
sections = [(l, "") for l in sections if l]
callback(0.8, "Finish parsing.")
elif re.search(r"\.doc$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
binary = BytesIO(binary)