重构目录结构

test/test_commons.py → tests/test_commons.py

 import io
 import json
 import os
-from libs.commons import fitz
+from pdf_tools.libs import fitz
 
 from app.common.s3 import get_s3_config, get_s3_client
-from libs.commons import join_path, json_dump_path, read_file, parse_bucket_key
+from pdf_tools.libs 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/"

test/test_metascan_classify/test_classify.py → tests/test_metascan_classify/test_classify.py

@@ -2,9 +2,9 @@ import os
 
 import pytest
 
-from filter.pdf_classify_by_type import classify_by_area, classify_by_text_len, classify_by_avg_words, \
+from pdf_tools.filter 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 filter.pdf_meta_scan import get_pdf_page_size_pts, get_pdf_textlen_per_page, get_imgs_per_page
+from pdf_tools.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
 
 # 获取当前目录

test/test_metascan_classify/test_meta_scan.py → tests/test_metascan_classify/test_meta_scan.py

 import os
 
 import pytest
-from filter.pdf_meta_scan import get_pdf_page_size_pts, get_image_info, get_pdf_text_layout_per_page, get_language
+from pdf_tools.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
 
 # 获取当前目录

test/test_para/test_para_pipeline.py → tests/test_para/test_para_pipeline.py

 import unittest
 
 """
-Execute the following command to run the test under directory code-clean:
+Execute the following command to run the tests under directory code-clean:
 
-    python -m test.test_para.test_para_pipeline
+    python -m tests.test_para.test_para_pipeline
     
     or
     
-    pytest -v -s app/pdf_toolbox/test/test_para/test_para_pipeline.py
+    pytest -v -s app/pdf_toolbox/tests/test_para/test_para_pipeline.py
     
 """
 

test/test_para/test_pdf2text_recogPara_BlockContinuationProcessor.py → tests/test_para/test_pdf2text_recogPara_BlockContinuationProcessor.py

 import unittest
 
-from post_proc.detect_para import BlockContinuationProcessor
+from pdf_tools.post_proc.detect_para import BlockContinuationProcessor
 
 # from ... pdf2text_recogPara import BlockContinuationProcessor # another way to import
 
 """
 Execute the following command to run the test under directory code-clean:
 
-    python -m test.test_para.test_pdf2text_recogPara_ClassName
+    python -m tests.test_para.test_pdf2text_recogPara_ClassName
     
     or
     
-    pytest -v -s app/pdf_toolbox/test/test_para/test_pdf2text_recogPara_BlockContinuationProcessor.py
+    pytest -v -s app/pdf_toolbox/tests/test_para/test_pdf2text_recogPara_BlockContinuationProcessor.py
     
 """
 

test/test_para/test_pdf2text_recogPara_BlockInnerParasProcessor.py → tests/test_para/test_pdf2text_recogPara_BlockInnerParasProcessor.py

 import unittest
 
-from post_proc.detect_para import BlockTerminationProcessor
+from pdf_tools.post_proc.detect_para import BlockTerminationProcessor
 
 # from ... pdf2text_recogPara import BlockInnerParasProcessor # another way to import
 
 """
 Execute the following command to run the test under directory code-clean:
 
-    python -m test.test_para.test_pdf2text_recogPara_ClassName
+    python -m tests.test_para.test_pdf2text_recogPara_ClassName
     
     or
     
-    pytest -v -s app/pdf_toolbox/test/test_para/test_pdf2text_recogPara_BlockInnerParasProcessor.py
+    pytest -v -s app/pdf_toolbox/tests/test_para/test_pdf2text_recogPara_BlockInnerParasProcessor.py
     
 """
 

test/test_para/test_pdf2text_recogPara_Common.py → tests/test_para/test_pdf2text_recogPara_Common.py

 import unittest
 
-from post_proc.detect_para import (
+from pdf_tools.post_proc.detect_para import (
     is_bbox_overlap,
     is_in_bbox,
     is_line_right_aligned_from_neighbors,
@@ -12,11 +12,11 @@ from post_proc.detect_para import (
 """
 Execute the following command to run the test under directory code-clean:
 
-    python -m test.test_para.test_pdf2text_recogPara_Common
+    python -m tests.test_para.test_pdf2text_recogPara_Common
     
     or 
     
-    pytest -v -s app/pdf_toolbox/test/test_para/test_pdf2text_recogPara_Common.py
+    pytest -v -s app/pdf_toolbox/tests/test_para/test_pdf2text_recogPara_Common.py
     
 """
 

test/test_para/test_pdf2text_recogPara_TitleProcessor.py → tests/test_para/test_pdf2text_recogPara_TitleProcessor.py

@@ -2,18 +2,18 @@ import json
 import unittest
 
 from utils_for_test_para import UtilsForTestPara
-from post_proc.detect_para import TitleProcessor
+from pdf_tools.post_proc.detect_para import TitleProcessor
 
 # from ... pdf2text_recogPara import * # another way to import
 
 """
 Execute the following command to run the test under directory code-clean:
 
-    python -m test.test_para.test_pdf2text_recogPara_ClassName
+    python -m tests.test_para.test_pdf2text_recogPara_ClassName
     
     or 
     
-    pytest -v -s app/pdf_toolbox/test/test_para/test_pdf2text_recogPara_TitleProcessor.py
+    pytest -v -s app/pdf_toolbox/tests/test_para/test_pdf2text_recogPara_TitleProcessor.py
     
 """