fix fitz and table_share

Dockerfile

@@ -18,6 +18,7 @@ ADD ./scripts/local_start.sh ./scripts/
 ADD ./db_versioning ./db_versioning/
 ADD ./app ./app/
 COPY --from=frontend_build /app/src ./src/
+RUN pip install --upgrade PyMuPDF==1.24.10
 
 ENV PYTHONPATH "${PYTHONPATH}:/usr/src/project/app"
 

app/main/check_packs/pack_config.py

@@ -44,7 +44,7 @@
     ["spelling_check"],
     ["max_abstract_size_check"],
     ["theme_in_report_check"],
-    # ["table_share_check"],
+    ["table_share_check"],
     ['key_words_report_check'],
     ["empty_task_page_check"],
     ["template_name"],

app/main/reports/pdf_document/pdf_document_manager.py

@@ -1,7 +1,7 @@
 # import pdfplumber
 import fitz
 
-# Version of PyMuPDF is important for find_tables() method (now it's PyMuPDF==1.23.6)
+# Version of PyMuPDF is important for find_tables() method (now it's PyMuPDF==1.24.10)
 
 from app.utils import convert_to
 
@@ -22,7 +22,7 @@ def __init__(self, path_to_file, pdf_filepath=''):
     def get_text_on_page(self):
         return {page_num + 1: page.get_text() for page_num, page in enumerate(self.pages)}
         # return {page + 1: self.pages[page].extract_text() for page in range(self.page_count)}
-    
+
     # def get_text_on_page(self):
     #     return {page + 1: self.pages[page].extract_text() for page in range(self.page_count_all)}
 
@@ -35,15 +35,18 @@ def page_table(self, page_without_pril):
             for table in tables:
                 table_coord = table.bbox
                 total_height += (table_coord[3] - table_coord[1])
-        return total_height        
+        return total_height
+
     def get_image_num(self):
         return len(self.pdf_file.get_page_images(0))
 
     def page_images(self, page_without_pril):
         total_height = 0
         for page_num in range(page_without_pril):
-            page = self.pdf_file[page_num]
-            images = self.pdf_file.get_page_images(page)
+            page = self.pages[page_num]
+            # page = self.pdf_file[page_num]
+            # images = self.pdf_file.get_page_images(page)
+            images = page.get_images()
             for image in images:
                 image_coord = page.get_image_bbox(image[7], transform=0)    # might be [1.0, 1.0, -1.0, -1.0]
                 image_height = image_coord[3] - image_coord[1]

requirements.txt

@@ -25,7 +25,6 @@ docx2python~=2.0.4
 oauthlib~=3.1.0
 pdfplumber==0.6.1
 pytest~=7.1.2
-PyMuPDF~=1.22.5
 PyPDF2~=3.0.1
 configparser~=5.3.0
 pytz~=2023.3
@@ -35,4 +34,4 @@ filetype==1.2.0
 language-tool-python==2.7.1
 markdown==3.4.4
 md2pdf==1.0.1
-# PyMuPDF==1.23.6
+PyMuPDF==1.24.10