目录重构

demo/download.py

@@ -2,7 +2,7 @@ import json
 import os
 from tqdm import tqdm
 
-from pdf_tools.libs import join_path
+from magic_pdf.libs 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 pdf_tools.libs import fitz  # PyMuPDF
+from magic_pdf.libs 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

@@ -5,9 +5,9 @@ from pathlib import Path
 import click
 from loguru import logger
 
-from pdf_tools.libs import join_path
-from pdf_tools.dict2md.mkcontent import mk_mm_markdown
-from pdf_tools.pipeline import parse_pdf_by_model
+from magic_pdf.libs import join_path
+from magic_pdf.dict2md.mkcontent import mk_mm_markdown
+from magic_pdf.pipeline import parse_pdf_by_model
 
 
 

pdf_tools/dict2md/mkcontent.py → magic_pdf/dict2md/mkcontent.py

 import math
 from loguru import logger
 
-from pdf_tools.libs.boxbase import find_bottom_nearest_text_bbox, find_top_nearest_text_bbox
+from magic_pdf.libs.boxbase import find_bottom_nearest_text_bbox, find_top_nearest_text_bbox
 
 
 def mk_nlp_markdown(para_dict: dict):

pdf_tools/filter/pdf_classify_by_type.py → magic_pdf/filter/pdf_classify_by_type.py

@@ -16,8 +16,8 @@ from collections import Counter
 import click
 import numpy as np
 
-from pdf_tools.libs.commons import mymax, get_top_percent_list
-from pdf_tools.filter.pdf_meta_scan import scan_max_page, junk_limit_min
+from magic_pdf.libs.commons import mymax, get_top_percent_list
+from magic_pdf.filter.pdf_meta_scan import scan_max_page, junk_limit_min
 
 TEXT_LEN_THRESHOLD = 100
 AVG_TEXT_LEN_THRESHOLD = 200

pdf_tools/filter/pdf_meta_scan.py → magic_pdf/filter/pdf_meta_scan.py

@@ -5,13 +5,13 @@
 import sys
 import click
 
-from pdf_tools.libs.commons import read_file, mymax, get_top_percent_list
-from pdf_tools.libs.commons import fitz
+from magic_pdf.libs.commons import read_file, mymax, get_top_percent_list
+from magic_pdf.libs.commons import fitz
 from loguru import logger
 from collections import Counter
 
-from pdf_tools.libs.drop_reason import DropReason
-from pdf_tools.libs.language import detect_lang
+from magic_pdf.libs.drop_reason import DropReason
+from magic_pdf.libs.language import detect_lang
 
 scan_max_page = 50
 junk_limit_min = 10

pdf_tools/layout/bbox_sort.py → magic_pdf/layout/bbox_sort.py

@@ -3,9 +3,9 @@
 
 
 
-from pdf_tools.layout.layout_spiler_recog import get_spilter_of_page
-from pdf_tools.libs.boxbase import _is_in, _is_in_or_part_overlap, _is_vertical_full_overlap
-from pdf_tools.libs.commons import mymax
+from magic_pdf.layout.layout_spiler_recog import get_spilter_of_page
+from magic_pdf.libs.boxbase import _is_in, _is_in_or_part_overlap, _is_vertical_full_overlap
+from magic_pdf.libs.commons import mymax
 
 X0_IDX = 0
 Y0_IDX = 1

pdf_tools/layout/layout_det_utils.py → magic_pdf/layout/layout_det_utils.py

-from pdf_tools.layout.bbox_sort import X0_EXT_IDX, X0_IDX, X1_EXT_IDX, X1_IDX, Y0_IDX, Y1_EXT_IDX, Y1_IDX
-from pdf_tools.libs.boxbase import _is_bottom_full_overlap, _left_intersect, _right_intersect
+from magic_pdf.layout.bbox_sort import X0_EXT_IDX, X0_IDX, X1_EXT_IDX, X1_IDX, Y0_IDX, Y1_EXT_IDX, Y1_IDX
+from magic_pdf.libs.boxbase import _is_bottom_full_overlap, _left_intersect, _right_intersect
 
 
 def find_all_left_bbox_direct(this_bbox, all_bboxes) -> list:

pdf_tools/layout/layout_sort.py → magic_pdf/layout/layout_sort.py

@@ -3,9 +3,9 @@
 """
 
 from loguru import logger
-from pdf_tools.layout.bbox_sort import CONTENT_IDX, CONTENT_TYPE_IDX, X0_EXT_IDX, X0_IDX, X1_EXT_IDX, X1_IDX, Y0_EXT_IDX, Y0_IDX, Y1_EXT_IDX, Y1_IDX, paper_bbox_sort
-from pdf_tools.layout.layout_det_utils import find_all_left_bbox_direct, find_all_right_bbox_direct, find_bottom_bbox_direct_from_left_edge, find_bottom_bbox_direct_from_right_edge, find_top_bbox_direct_from_left_edge, find_top_bbox_direct_from_right_edge, find_all_top_bbox_direct, find_all_bottom_bbox_direct, get_left_edge_bboxes, get_right_edge_bboxes
-from pdf_tools.libs.boxbase import get_bbox_in_boundry
+from magic_pdf.layout.bbox_sort import CONTENT_IDX, CONTENT_TYPE_IDX, X0_EXT_IDX, X0_IDX, X1_EXT_IDX, X1_IDX, Y0_EXT_IDX, Y0_IDX, Y1_EXT_IDX, Y1_IDX, paper_bbox_sort
+from magic_pdf.layout.layout_det_utils import find_all_left_bbox_direct, find_all_right_bbox_direct, find_bottom_bbox_direct_from_left_edge, find_bottom_bbox_direct_from_right_edge, find_top_bbox_direct_from_left_edge, find_top_bbox_direct_from_right_edge, find_all_top_bbox_direct, find_all_bottom_bbox_direct, get_left_edge_bboxes, get_right_edge_bboxes
+from magic_pdf.libs.boxbase import get_bbox_in_boundry
 
 
 LAYOUT_V = "V"

pdf_tools/layout/layout_spiler_recog.py → magic_pdf/layout/layout_spiler_recog.py

@@ -3,8 +3,8 @@
 """
 
 import os
-from pdf_tools.libs.commons import fitz
-from pdf_tools.libs.boxbase import _is_in_or_part_overlap
+from magic_pdf.libs.commons import fitz
+from magic_pdf.libs.boxbase import _is_in_or_part_overlap
 
 
 def __rect_filter_by_width(rect, page_w, page_h):

pdf_tools/layout/mcol_sort.py → magic_pdf/layout/mcol_sort.py

@@ -50,7 +50,7 @@ Usage
   ----------------------------------------------------------------------------------
 """
 import sys
-from pdf_tools.libs.commons import fitz
+from magic_pdf.libs.commons import fitz
 
 
 def column_boxes(page, footer_margin=50, header_margin=50, no_image_text=True):