Update Doors_Schedule.py

Doors_Schedule.py

@@ -385,7 +385,7 @@ def get_selected_columns_all(dfs, user_patterns):
 # 3ayz akhaleehaa te search fel selected_columns column names nafsaha
 # 7ab2a 3ayz a3raf bardo maktooba ezay fel df el 7a2e2ya (akeed za ma el user medakhalha bezabt)
 def get_st_op_pattern(selected_columns, user_input):
-    target = 'structural opening'
+    target = 'structural_opening'
     if target in selected_columns.columns:
       name = user_input[2]
       return name
@@ -538,22 +538,29 @@ def get_cleaned_data(locations):
   return new_data
 
 
+# law 0.5 maslan tetkatab we law mesh keda yesheel el decimal point
 def get_width_info_tobeprinted(new_data):
   width_info_tobeprinted = []
   if len(new_data[0]) == 4:
     for _,_,_, w in new_data:
-      w = re.sub(r",", "", w)
-      w = int(float(w))
+      #w = re.sub(r",", "", w)
+      #w = int(float(w))
       width_info_tobeprinted.append(w)
   if len(new_data[0]) == 5:
     for _,_,_, w,h in new_data:
       w = re.sub(r",", "", w)
       h = re.sub(r",", "", h)
-      w = int(float(w))
-      h = int(float(h))
+      if float(w).is_integer():
+        w = int(float(w))
+      else:
+        w = w
+      if float(h).is_integer():
+        h = int(float(h))
+      else:
+        h = h
       width_info_tobeprinted.append(f"{w} mm wide x {h} mm high")
   return width_info_tobeprinted
-
+    
 def clean_dimensions(text):
     # Remove commas and "mm"
     text = re.sub(r'[,\s]*mm', '', text)  # Remove "mm" with optional spaces or commas before it
@@ -566,6 +573,7 @@ def get_cleaned_width(width_info_tobeprinted):
     cleaned_width.append(clean_dimensions(w))  
   return cleaned_width
 
+
 def get_widths_bb_format(cleaned_width, kelma):
   pattern = r"\bW(?:idth)?\s*[×x]\s*H(?:eight)?\b"
   match = re.search(pattern, kelma)
@@ -577,9 +585,9 @@ def get_widths_bb_format(cleaned_width, kelma):
     width_name = int(float(width_name))
     height_name = int(float(height_name))
     if match:
-      full_text = f"{width_name}mm wide x {height_name}mm high"
+      full_text = f"{width_name} mm wide x {height_name} mm high"
     else:
-      full_text = f"{height_name}mm wide x {width_name}mm high"
+      full_text = f"{height_name} mm wide x {width_name} mm high"
     widths.append(full_text)
   return widths
 
@@ -757,13 +765,14 @@ def get_width_info_tobeprinted_secondary(new_data, main_info, secondary_info):
 
   if len(main_info) == 4 and len(secondary_info) == 2:
     for coords, label, width, height, acous, fire, color in new_data:
-      #w = re.sub(r",", "", width)
-      #h = re.sub(r",", "", height)
-      #w = int(float(w))
-      #h = int(float(h))
-      width_info_tobeprinted.append(f"{width} mm wide x {height} mm high")
+      w = re.sub(r",", "", width)
+      h = re.sub(r",", "", height)
+      w = int(float(w))
+      h = int(float(h))
+      width_info_tobeprinted.append(f"{w} mm wide x {h} mm high")
       secondary_info_tobeprinted.append((acous, fire))
   return width_info_tobeprinted, secondary_info_tobeprinted
+
 def get_flattened_tuples_list_SECONDARY(col_dict):
     tuples_list = []
 
@@ -1511,30 +1520,26 @@ def mainRun(schedule, plan, searcharray):
       
     dfs = extract_tables(schedule)
 
-    all_new_data = []
-    all_widths = []
-    pdf_outputs = []
-    
-    if len(searcharray)>1:
+    pdfs = []
+    for p in plan:
+        all_new_data = []
+        all_widths = []
+        pdf_outputs = [] 
+        
         for j in range(len(searcharray)):
-          pdfs = []
           user_input = searcharray[j]
+            
           secondary_presence = False
-        
           if user_input[4] or user_input[5]:
             secondary_presence = True
-        
             main_info_, secondary_info_ = separate_main_secondary(user_input)
-        
             main_info = [item for item in main_info_ if item]
-            secondary_info = [item for item in secondary_info_ if item]
-        
+            secondary_info = [item for item in secondary_info_ if item]        
             print("feh secondary information")
             if user_input[4]:
               print("Fire rate mawgooda")
             if user_input[5]:
               print("Acoustic Rate mawgooda")
-        
           else:
             print("mafeesh secondary information")
         
@@ -1542,9 +1547,9 @@ def mainRun(schedule, plan, searcharray):
           kelma = get_st_op_pattern(selected_columns_combined, user_input)
           col_dict = get_similar_colors_all(selected_columns_combined)
           flattened_list = get_flattened_tuples_list_all(col_dict)
-        
+          plan_texts = read_text(p)
+
           if secondary_presence:
-              for p in plan:
                   plan_texts = read_text(p)
                   locations, not_found = get_word_locations_plan_secondary(flattened_list,plan_texts, main_info, secondary_info)
                   new_data3 = get_cleaned_data_secondary(locations,main_info,secondary_info)
@@ -1558,153 +1563,61 @@ def mainRun(schedule, plan, searcharray):
                       width_info_tobeprinted, secondary_tobeprinted = get_width_info_tobeprinted_secondary(new_data3, main_info, secondary_info)
                       cleaned_width = get_cleaned_width(width_info_tobeprinted)
                       widths = get_widths_bb_format(cleaned_width, kelma)
+                  #Handling schedules without dimensions (width and height)
+                  if selected_columns_combined.shape[1] == 2:
+                    widths = []
+                  
                   secondary_printed_clean =  get_secondary_tobeprinted_clean(selected_columns_combined, secondary_tobeprinted, secondary_info)
                   all_print =  mix_width_secondary(widths, secondary_printed_clean)
-        
+
                   #Single page annotation
                   all_widths.append(all_print)
         
-                  flat_list_new_data = [item for sublist in all_new_data for item in sublist]
-                  flat_list_widths = [item for sublist in all_widths for item in sublist]
+                  #flat_list_new_data = [item for sublist in all_new_data for item in sublist]
+                  #flat_list_widths = [item for sublist in all_widths for item in sublist]
         
                   if pdf_outputs:
-                    final_pdf_bytes = process_pdf_secondary(pdf_outputs[j-1], "final_output_multiple_input_new2.pdf", flat_list_new_data, flat_list_widths, main_info, secondary_info)
+                    final_pdf_bytes = process_pdf_secondary(pdf_outputs[j-1], "final_output_multiple_input_new2.pdf", all_new_data[j], all_widths[j], main_info, secondary_info)
                     pdf_outputs.append(final_pdf_bytes)
                   else:
-                    final_pdf_bytes = process_pdf_secondary(p, "final_output_multiple_input_new2.pdf", flat_list_new_data, flat_list_widths, main_info, secondary_info)
+                    final_pdf_bytes = process_pdf_secondary(p, "final_output_multiple_input_new2.pdf", all_new_data[j], all_widths[j], main_info, secondary_info)
                     pdf_outputs.append(final_pdf_bytes)
-                    
-                  pdfs.append(final_pdf_bytes)
-        
-        
-          else:
-              for p in plan:
-                  print(f" p in plan is {type(p)}")
-                  print(p)
-                  plan_texts = read_text(p)
-                  locations, not_found = get_word_locations_plan(flattened_list,plan_texts)
-                  new_data = get_cleaned_data(locations)
-                  #Single page annotation
-                  all_new_data.append(new_data)
-                  repeated_labels = get_repeated_labels(locations)
-                  if kelma == None:
-                    widths = get_width_info_tobeprinted(new_data)
-                  else:
-                    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)
-                  #Single page annotation
-                  all_widths.append(widths)
-        
-                  flat_list_new_data = [item for sublist in all_new_data for item in sublist]
-                  flat_list_widths = [item for sublist in all_widths for item in sublist]
-        
-                  if pdf_outputs:
-                    final_pdf_bytes = process_pdf(pdf_outputs[j-1], "final_output_width_trial.pdf", flat_list_new_data, flat_list_widths)
-                    #final_pdf_bytes = process_pdf(p, "final_output_width.pdf", new_data, widths)         
-                    pdfs.append(final_pdf_bytes)
-                  else:
-                    final_pdf_bytes = process_pdf(p, "final_output_width_trial.pdf", flat_list_new_data, flat_list_widths)
-                    #final_pdf_bytes = process_pdf(p, "final_output_width.pdf", new_data, widths)         
-                    pdfs.append(final_pdf_bytes)  
-          
-          #Handling schedules without dimensions (width and height)  
-          if selected_columns_combined.shape[1] == 2:
-              widths = []
-        
-          merged_pdf = merge_pdf_bytes_list(pdfs)
-          print(f"number of pges of merged_pdf is {len(merged_pdf)} and its type is {type(merged_pdf)}")
-    
-    else:
-        for j in range(len(searcharray)):
-          pdfs = []
-          user_input = searcharray[j]
-          secondary_presence = False
-        
-          if user_input[4] or user_input[5]:
-            secondary_presence = True
-        
-            main_info_, secondary_info_ = separate_main_secondary(user_input)
-        
-            main_info = [item for item in main_info_ if item]
-            secondary_info = [item for item in secondary_info_ if item]
-        
-            print("feh secondary information")
-            if user_input[4]:
-              print("Fire rate mawgooda")
-            if user_input[5]:
-              print("Acoustic Rate mawgooda")
-        
+                                    
           else:
-            print("mafeesh secondary information")
-        
-          selected_columns_combined = get_selected_columns_all(dfs, user_input)
-          kelma = get_st_op_pattern(selected_columns_combined, user_input)
-          col_dict = get_similar_colors_all(selected_columns_combined)
-          flattened_list = get_flattened_tuples_list_all(col_dict)
-        
-          if secondary_presence:
-              for p in plan:
-                  plan_texts = read_text(p)
-                  locations, not_found = get_word_locations_plan_secondary(flattened_list,plan_texts, main_info, secondary_info)
-                  new_data3 = get_cleaned_data_secondary(locations,main_info,secondary_info)
-                  
-                  #Single page annotation
-                  all_new_data.append(new_data3)
-                  repeated_labels = get_repeated_labels(locations)
-                  if kelma == None:
-                      widths, secondary_tobeprinted = get_width_info_tobeprinted_secondary(new_data3, main_info, secondary_info)
-                  else:
-                      width_info_tobeprinted, secondary_tobeprinted = get_width_info_tobeprinted_secondary(new_data3, main_info, secondary_info)
-                      cleaned_width = get_cleaned_width(width_info_tobeprinted)
-                      widths = get_widths_bb_format(cleaned_width, kelma)
-                  secondary_printed_clean =  get_secondary_tobeprinted_clean(selected_columns_combined, secondary_tobeprinted, secondary_info)
-                  all_print =  mix_width_secondary(widths, secondary_printed_clean)
-        
-                  #Single page annotation
-                  all_widths.append(all_print)
-        
-                  flat_list_new_data = [item for sublist in all_new_data for item in sublist]
-                  flat_list_widths = [item for sublist in all_widths for item in sublist]
-        
-                  
-                  final_pdf_bytes = process_pdf_secondary(p, "final_output_multiple_input_new2.pdf", flat_list_new_data, flat_list_widths, main_info, secondary_info)
-                  pdfs.append(final_pdf_bytes)
+              locations, not_found = get_word_locations_plan(flattened_list,plan_texts)
+              new_data = get_cleaned_data(locations)
+              #Single page annotation
+              all_new_data.append(new_data)
+              repeated_labels = get_repeated_labels(locations)
+              if kelma == None:
+                  widths = get_width_info_tobeprinted(new_data)
+              else:
+                  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)
+
+              #Handling schedules without dimensions (width and height)  
+              if selected_columns_combined.shape[1] == 2:
+                  widths = []
+              
+              #Single page annotation
+              all_widths.append(widths)
         
+              flat_list_new_data = [item for sublist in all_new_data for item in sublist]
+              flat_list_widths = [item for sublist in all_widths for item in sublist]
         
-          else:
-              for p in plan:
-                  print(f" p in plan is {type(p)}")
-                  print(p)
-                  plan_texts = read_text(p)
-                  locations, not_found = get_word_locations_plan(flattened_list,plan_texts)
-                  new_data = get_cleaned_data(locations)
-                  #Single page annotation
-                  all_new_data.append(new_data)
-                  repeated_labels = get_repeated_labels(locations)
-                  if kelma == None:
-                    widths = get_width_info_tobeprinted(new_data)
-                  else:
-                    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)
-                  #Single page annotation
-                  all_widths.append(widths)
-        
-                  flat_list_new_data = [item for sublist in all_new_data for item in sublist]
-                  flat_list_widths = [item for sublist in all_widths for item in sublist]
-
-                  final_pdf_bytes = process_pdf(p, "final_output_width_trial.pdf", flat_list_new_data, flat_list_widths)
-                  #final_pdf_bytes = process_pdf(p, "final_output_width.pdf", new_data, widths)         
-                  pdfs.append(final_pdf_bytes)  
+              if pdf_outputs:
+                  final_pdf_bytes = process_pdf(pdf_outputs[j-1], "final_output_width_trial.pdf", all_new_data[j], all_widths[j])
+                  pdf_outputs.append(final_pdf_bytes)
+              else:
+                  final_pdf_bytes = process_pdf(p, "final_output_width_trial.pdf", all_new_data[j], all_widths[j])
+                  pdf_outputs.append(final_pdf_bytes)  
           
-          #Handling schedules without dimensions (width and height)  
-          if selected_columns_combined.shape[1] == 2:
-              widths = []
-        
-          merged_pdf = merge_pdf_bytes_list(pdfs)
-          print(f"number of pges of merged_pdf is {len(merged_pdf)} and its type is {type(merged_pdf)}")
 
+        pdfs.append(final_pdf_bytes)
+        merged_pdf = merge_pdf_bytes_list(pdfs)
+        print(f"number of pges of merged_pdf is {len(merged_pdf)} and its type is {type(merged_pdf)}")
+    
     not_found = []
     doc2 =fitz.open('pdf',merged_pdf)
     len_doc2 = len(doc2)
@@ -1735,6 +1648,4 @@ def mainRun(schedule, plan, searcharray):
                   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 
-
-  
+    return annotatedimg, doc2 , list1, repeated_labels , not_found