centersl/MinerU
1
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-03-27 02:58:54 +07:00
Code Issues Packages Projects Releases Wiki Activity

修复init错误

Browse Source
This commit is contained in:
赵小蒙
2024-03-29 17:29:44 +08:00
parent 4b8dbd7cfb
commit 016cde3ece
7 changed files with 6 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -34,4 +34,4 @@ tmp
ocr_demo
/app/common/__init__.py
/magic_pdf/spark/__init__.py
/magic_pdf/config/__init__.py

1
demo/ocr_demo.py
View File

@@ -12,7 +12,6 @@ from magic_pdf.dict2md.ocr_mkcontent import (
make_standard_format_with_para
)
from magic_pdf.libs.commons import join_path, read_file
from magic_pdf.pdf_parse_by_ocr import parse_pdf_by_ocr
def save_markdown(markdown_text, input_filepath):

4
magic_pdf/pipeline.py
View File

@@ -19,9 +19,9 @@ from magic_pdf.filter.pdf_meta_scan import pdf_meta_scan
from loguru import logger
from magic_pdf.pdf_parse_for_train import parse_pdf_for_train
from magic_pdf.spark.base import exception_handler, get_data_source, get_bookname, get_pdf_bytes
from magic_pdf.spark import exception_handler, get_data_source
from magic_pdf.train_utils.convert_to_train_format import convert_to_train_format
from magic_pdf.spark.s3 import get_s3_config, get_s3_client
from magic_pdf.spark import get_s3_config, get_s3_client

2
magic_pdf/pipeline_txt.py
View File

@@ -8,7 +8,7 @@ from loguru import logger
from magic_pdf.dict2md.mkcontent import mk_mm_markdown, mk_universal_format
from magic_pdf.libs.commons import join_path
from magic_pdf.libs.json_compressor import JsonCompressor
from magic_pdf.spark.base import exception_handler, get_data_source
from magic_pdf.spark import exception_handler, get_data_source
def txt_pdf_to_standard_format(jso: dict, debug_mode=False) -> dict:

0
magic_pdf/spark/__init__.py Normal file
View File

2
magic_pdf/spark/s3.py
View File

@@ -8,7 +8,7 @@ from typing import List, Union
try:
from app.config import s3_buckets, s3_clusters, get_cluster_name, s3_users
except ImportError:
from magic_pdf.spark import s3_buckets, s3_clusters, get_cluster_name, s3_users
from magic_pdf.config import s3_buckets, s3_clusters, get_cluster_name, s3_users
__re_s3_path = re.compile("^s3a?://([^/]+)(?:/(.*))?$")
def get_s3_config(path: Union[str, List[str]], outside=False):

2
tests/test_commons.py
View File

@@ -3,7 +3,7 @@ import json
import os
from magic_pdf.libs.commons import fitz
from magic_pdf.spark.s3 import get_s3_config, get_s3_client
from magic_pdf.spark import get_s3_config, get_s3_client
from magic_pdf.libs.commons import join_path, json_dump_path, read_file, parse_bucket_key
from loguru import logger