修复目录重构导致的引用异常

demo/download.py

@@ -2,7 +2,7 @@ import json
 import os
 from tqdm import tqdm
 
-from magic_pdf.libs import join_path
+from magic_pdf.libs.commons import join_path
 
 with open('/mnt/petrelfs/share_data/ouyanglinke/OCR/OCR_validation_dataset.json', 'r') as f:
     samples = json.load(f)

demo/draw_bbox.py

-from magic_pdf.libs import fitz  # PyMuPDF
+from magic_pdf.libs.commons import fitz  # PyMuPDF
 
 # PDF文件路径
 pdf_path = "D:\\project\\20231108code-clean\\code-clean\\tmp\\unittest\\download-pdfs\\scihub\\scihub_53700000\\libgen.scimag53724000-53724999.zip_10.1097\\00129191-200509000-00018.pdf"

demo/pdf2md.py

@@ -5,7 +5,7 @@ from pathlib import Path
 import click
 from loguru import logger
 
-from magic_pdf.libs import join_path
+from magic_pdf.libs.commons import join_path
 from magic_pdf.dict2md.mkcontent import mk_mm_markdown
 from magic_pdf.pipeline import parse_pdf_by_model
 

tests/test_commons.py

 import io
 import json
 import os
-from magic_pdf.libs import fitz
+from magic_pdf.libs.commons import fitz
 
 from app.common.s3 import get_s3_config, get_s3_client
-from magic_pdf.libs import join_path, json_dump_path, read_file, parse_bucket_key
+from magic_pdf.libs.commons import join_path, json_dump_path, read_file, parse_bucket_key
 from loguru import logger
 
 test_pdf_dir_path = "s3://llm-pdf-text/unittest/pdf/"

tests/test_metascan_classify/test_classify.py

@@ -2,10 +2,10 @@ import os
 
 import pytest
 
-from magic_pdf.filter import classify_by_area, classify_by_text_len, classify_by_avg_words, \
+from magic_pdf.filter.pdf_classify_by_type import classify_by_area, classify_by_text_len, classify_by_avg_words, \
     classify_by_img_num, classify_by_text_layout, classify_by_img_narrow_strips
 from magic_pdf.filter.pdf_meta_scan import get_pdf_page_size_pts, get_pdf_textlen_per_page, get_imgs_per_page
-from test.test_commons import get_docs_from_test_pdf, get_test_json_data
+from tests.test_commons import get_docs_from_test_pdf, get_test_json_data
 
 # 获取当前目录
 current_directory = os.path.dirname(os.path.abspath(__file__))

tests/test_metascan_classify/test_meta_scan.py

@@ -2,7 +2,7 @@ import os
 
 import pytest
 from magic_pdf.filter.pdf_meta_scan import get_pdf_page_size_pts, get_image_info, get_pdf_text_layout_per_page, get_language
-from test.test_commons import get_docs_from_test_pdf, get_test_json_data
+from tests.test_commons import get_docs_from_test_pdf, get_test_json_data
 
 # 获取当前目录
 current_directory = os.path.dirname(os.path.abspath(__file__))

tests/test_para/test_para_pipeline.py

@@ -11,21 +11,21 @@ Execute the following command to run the tests under directory code-clean:
     
 """
 
-from test.test_para.test_pdf2text_recogPara_Common import (
+from tests.test_para.test_pdf2text_recogPara_Common import (
     TestIsBboxOverlap,
     TestIsInBbox,
     TestIsBboxOverlap,
     TestIsLineLeftAlignedFromNeighbors,
     TestIsLineRightAlignedFromNeighbors,
 )
-from test.test_para.test_pdf2text_recogPara_EquationsProcessor import TestCalcOverlapPct
-from test.test_para.test_pdf2text_recogPara_BlockInnerParasProcessor import TestIsConsistentLines
-from test.test_para.test_pdf2text_recogPara_BlockContinuationProcessor import (
+from tests.test_para.test_pdf2text_recogPara_EquationsProcessor import TestCalcOverlapPct
+from tests.test_para.test_pdf2text_recogPara_BlockInnerParasProcessor import TestIsConsistentLines
+from tests.test_para.test_pdf2text_recogPara_BlockContinuationProcessor import (
     TestIsAlphabetChar,
     TestIsChineseChar,
     TestIsOtherLetterChar,
 )
-from test.test_para.test_pdf2text_recogPara_TitleProcessor import TestTitleProcessor
+from tests.test_para.test_pdf2text_recogPara_TitleProcessor import TestTitleProcessor
 
 
 # Test suite