Update Doors_Schedule

Doors_Schedule

@@ -11,8 +11,8 @@ from PyPDF2.generic import TextStringObject, NameObject, ArrayObject, FloatObjec
 from PyPDF2.generic import NameObject, TextStringObject, DictionaryObject, FloatObject, ArrayObject
 from PyPDF2 import PdfReader
 from PyPDF2.generic import TextStringObject
-
-
+import numpy as np
+import cv2
 
 
 def convert2img(path):
@@ -35,7 +35,7 @@ def calculate_midpoint(x1,y1,x2,y2):
   return (xm, ym)
 
 def read_text(input_pdf_path):
-    pdf_document = fitz.open(input_pdf_path)
+    pdf_document = fitz.open('pdf',input_pdf_path)
 
     for page_num in range(pdf_document.page_count):
         page = pdf_document[page_num]
@@ -167,7 +167,7 @@ def details_in_another_table(clmn_name, clmn_idx, current_dfs, dfs):
   return new_df
 
 def extract_tables(schedule):
-  doc = fitz.open(schedule)
+  doc = fitz.open("pdf",schedule)
   for page in doc:
     tabs = page.find_tables()
   dfs = []
@@ -398,23 +398,27 @@ def modify_author_in_pypdf2(pdf_bytes, new_authors):
     #Save the modified PDF to a variable
     output_stream = io.BytesIO()
     writer.write(output_stream)
+    output_stream.seek(0)
+
+    return output_stream.read()
 
-    return output_stream.getvalue()  # Return modified PDF as bytes
+    # return output_stream.getvalue()  # Return modified PDF as bytes
 
 def process_pdf(input_pdf_path, output_pdf_path, locations, new_authors):
     #Load original PDF
-    with open(input_pdf_path, "rb") as file:
-        original_pdf_bytes = file.read()
+    # with open(input_pdf_path, "rb") as file:
+    #     original_pdf_bytes = file.read()
 
     #Add Bluebeam-compatible count annotations
-    annotated_pdf_bytes = add_bluebeam_count_annotations(original_pdf_bytes, locations)
+    annotated_pdf_bytes = add_bluebeam_count_annotations(input_pdf_path, locations)
 
     #Modify author field using PyPDF2
     final_pdf_bytes = modify_author_in_pypdf2(annotated_pdf_bytes, new_authors)
-
-    #Save the final modified PDF to disk
-    with open(output_pdf_path, "wb") as file:
-        file.write(final_pdf_bytes)
+    return final_pdf_bytes
+    # #Save the final modified PDF to disk
+    # with open(output_pdf_path, "wb") as file:
+    #     file.write(final_pdf_bytes)
+        
 def mainRun(schedule, plan):
   dfs = extract_tables(schedule)
   selected_columns = get_selected_columns(dfs)
@@ -433,5 +437,36 @@ def mainRun(schedule, plan):
   width_info_tobeprinted = get_width_info_tobeprinted(new_data)
   cleaned_width = get_cleaned_width(width_info_tobeprinted)
   widths = get_widths_bb_format(cleaned_width, kelma)
-  process_pdf(plan, "final_output_width.pdf", new_data, widths)
+  final_pdf_bytes= process_pdf(plan, "final_output_width.pdf", new_data, widths)
+  
+  
+  doc2 =fitz.open('pdf',final_pdf_bytes)
+  page=doc2[0]
+  pix = page.get_pixmap()  # render page to an image
+  pl=Image.frombytes('RGB', [pix.width,pix.height],pix.samples)
+  img=np.array(pl)
+  annotatedimg = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+
+
+  list1=pd.DataFrame(columns=['content',  'id',  'subject','color'])
+
+  # for page in doc:
+  for page in doc2:  
+    # Iterate through annotations on the page
+    for annot in page.annots():
+        # Get the color of the annotation
+        annot_color = annot.colors
+        if annot_color is not None:
+            # annot_color is a dictionary with 'stroke' and 'fill' keys
+            stroke_color = annot_color.get('stroke')  # Border color
+            fill_color = annot_color.get('fill')      # Fill color
+            if fill_color:
+              v='fill'
+              # print('fill')
+            if stroke_color:
+              v='stroke'
+            x,y,z=int(annot_color.get(v)[0]*255),int(annot_color.get(v)[1]*255),int(annot_color.get(v)[2]*255)
+            list1.loc[len(list1)] =[annot.info['content'],annot.info['id'],annot.info['subject'],[x,y,z]]
+  return annotatedimg, doc2 , list1, repeated_labels , not_found 
+