Update google_sheet_Legend.py

google_sheet_Legend.py

@@ -16,7 +16,9 @@ import pandas as pd
 from google.oauth2 import service_account
 from googleapiclient.discovery import build
 import pygsheets
-import re
+import tsadropboxretrieval
+import fitz
+import numpy as np
 
 
 def authorizeLegend():
@@ -465,172 +467,114 @@ def getguessnames(gc,ws):
   return guessednamesfinal
 
 ################################################################
-
-def deletefromlegend(deletedrows,SimilarAreaDictionarycopy,section, areaPermArr=[]):
-  items=[]
-  print('dletefromlegend')
-  idx=0
-  if section.startswith('1.0'):
-    areaPermArr=ast.literal_eval(areaPermArr)
-  myDict=eval(SimilarAreaDictionarycopy)
-  SimilarAreaDictionarycopy=pd.DataFrame(myDict)
-  # deletedrows=eval(deletedrows)
-  strings=deletedrows['content']
-  areastodelete = []
-  perimstodelete=[]
-  lengthstodelete=[]
-
-  for item in strings:
-    newitem=str(item).split('\n \n')
-    input_str = " ".join(str(newitem).split())
-    # Search for the Area value
-    matchA = re.search(r"Area=(\d+\.\d+)", input_str)
-    matchL = re.search(r"Length=(\d+\.\d+)", input_str)
-    matchP = re.search(r"Perimeter=(\d+\.\d+)", input_str)
-
-    if matchA:
-      areastodelete.append(float(matchA.group(1)))
-    if matchP:
-      perimstodelete.append(float(matchP.group(1)))
-    if matchL:
-      lengthstodelete.append(float(matchL.group(1))) 
-  print('Areas to delete:', areastodelete)
-  print('Perimeters to delete:', perimstodelete)
-  print('Lengths to delete:', lengthstodelete)
-
-  for i in range(len(areastodelete)):#item in areastodelete:
-    if section.startswith('1.0'):
-      tol=0.3
-    elif section.startswith('3.2'):
-      tol=1
-    areamin=round(areastodelete[i],1)- tol
-    areamax=round(areastodelete[i],1)+ tol
-    if section.startswith('1.0'):
-      for p in range(len(areaPermArr)):  
-        if areastodelete[i] in areaPermArr[p]:
-          width= areaPermArr[p][1]
-          height= areaPermArr[p][2]
-          break
-      widthMin= width -10
-      widthMax= width +10
-      heightMin = height-10
-      heightMax=height+10
-      if len(areastodelete)>0:
-        found=SimilarAreaDictionarycopy.loc[SimilarAreaDictionarycopy.index[((SimilarAreaDictionarycopy['Rounded'] >=areamin) & (SimilarAreaDictionarycopy['Rounded']<=areamax)  ) & ( ((SimilarAreaDictionarycopy['Width']>=widthMin) & (SimilarAreaDictionarycopy['Width']<=widthMax) & (SimilarAreaDictionarycopy['Height']>=heightMin) & (SimilarAreaDictionarycopy['Height']<=heightMax) ) | ((SimilarAreaDictionarycopy['Width']>=heightMin) & (SimilarAreaDictionarycopy['Width']<=heightMax) & (SimilarAreaDictionarycopy['Height']>=widthMin) & (SimilarAreaDictionarycopy['Height']<=widthMax) )) ]]
-    elif section.startswith('3.2'):
-      found=SimilarAreaDictionarycopy.loc[SimilarAreaDictionarycopy.index[((SimilarAreaDictionarycopy['Area'] >=areamin) & (SimilarAreaDictionarycopy['Area']<=areamax)   )]]
-    if len(found.index.values) >0:
-      occ=SimilarAreaDictionarycopy.loc[found.index.values[0],'Occurences']
-      if occ== 1: #drop row
-        SimilarAreaDictionarycopy= SimilarAreaDictionarycopy.drop(found.index.values[0])
-      else: #occ minus 1 , total area - areavalue , total perim - perimvalue
-        print('occ>1')
-        if section.startswith('1.0'):
-          if len(areastodelete)>0:
-            idx=SimilarAreaDictionarycopy.index[((SimilarAreaDictionarycopy['Rounded'] >=areamin) & (SimilarAreaDictionarycopy['Rounded']<=areamax)  ) & ( ((SimilarAreaDictionarycopy['Width']>=widthMin) & (SimilarAreaDictionarycopy['Width']<=widthMax) & (SimilarAreaDictionarycopy['Height']>=heightMin) & (SimilarAreaDictionarycopy['Height']<=heightMax) ) | ((SimilarAreaDictionarycopy['Width']>=heightMin) & (SimilarAreaDictionarycopy['Width']<=heightMax) & (SimilarAreaDictionarycopy['Height']>=widthMin) & (SimilarAreaDictionarycopy['Height']<=widthMax) )) ]
-        elif section.startswith('3.2'):
-          idx=SimilarAreaDictionarycopy.index[((SimilarAreaDictionarycopy['Area'] >=areamin) & (SimilarAreaDictionarycopy['Area']<=areamax) )]
-        if len(areastodelete)>0:
-          comment = SimilarAreaDictionarycopy.loc[idx, 'Comments']
-          if pd.notna(comment.iloc[0]) and 'Area' in str(comment.iloc[0]):
-            matches = re.findall(r'\b\d+\b', str(SimilarAreaDictionarycopy.loc[idx, 'Comments']))
-            area_occurrences = int(matches[1]) -1
-            perimeter_occurrences = int(matches[2])
-            print(area_occurrences, perimeter_occurrences)
-            SimilarAreaDictionarycopy.loc[idx, 'Comments'] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
-            if area_occurrences > perimeter_occurrences:
-              SimilarAreaDictionarycopy.loc[idx,'Occurences'] = area_occurrences
-            elif perimeter_occurrences> area_occurrences:
-              SimilarAreaDictionarycopy.loc[idx,'Occurences'] = perimeter_occurrences 
-            elif int(area_occurrences)==int(perimeter_occurrences):
-                SimilarAreaDictionarycopy.loc[idx,'Occurences'] = int(SimilarAreaDictionarycopy.loc[idx,'Occurences']) - 1                     
-                if section.startswith('1.0'):
-                  SimilarAreaDictionarycopy.loc[idx,'Total Length'] = SimilarAreaDictionarycopy.loc[idx,'Total Length'] - lengthstodelete[i]
-         
-          else:
-            print('not yet')
-            area_occurrences = SimilarAreaDictionarycopy.loc[idx, 'Occurences'].iloc[0] -1
-            perimeter_occurrences = SimilarAreaDictionarycopy.loc[idx, 'Occurences'].iloc[0]
-            print(area_occurrences,perimeter_occurrences)
-            SimilarAreaDictionarycopy.loc[idx, 'Comments'] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
-          SimilarAreaDictionarycopy.loc[idx,'Total Area'] = SimilarAreaDictionarycopy.loc[idx,'Total Area'] - areastodelete[i]
- 
-
-  for i in range(len(perimstodelete)):#item in areastodelete:
-    if section.startswith('1.0'):
-      tol=0.3
-    elif section.startswith('3.2'):
-      tol=10
+def is_color_within_tolerance(color1, color2, tolerance):
+    # Ensure both colors are tuples of integers
+    color1 = tuple(map(int, color1))
+    color2 = tuple(map(int, color2))
     
-    if len(perimstodelete)>0:
-        print(perimstodelete[i])
-        perimmin=round(perimstodelete[i],1)- 0.3
-        perimmax=round(perimstodelete[i],1)+ 0.3
-        print('perimmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm')
-    if section.startswith('1.0'):
-      for p in range(len(areaPermArr)):  
-        if areastodelete[i] in areaPermArr[p]:
-          print('AAA',areaPermArr[p])
-          area= areaPermArr[p][0]
-          width= areaPermArr[p][1]
-          height= areaPermArr[p][2]
-          break
-      widthMin= width -10
-      widthMax= width +10
-      heightMin = height-10
-      heightMax=height+10
-      found=SimilarAreaDictionarycopy.loc[SimilarAreaDictionarycopy.index[( (SimilarAreaDictionarycopy['Perimeter'] >=perimmin) & (SimilarAreaDictionarycopy['Perimeter']<=perimmax)   ) & ( ((SimilarAreaDictionarycopy['Width']>=widthMin) & (SimilarAreaDictionarycopy['Width']<=widthMax) & (SimilarAreaDictionarycopy['Height']>=heightMin) & (SimilarAreaDictionarycopy['Height']<=heightMax) ) | ((SimilarAreaDictionarycopy['Width']>=heightMin) & (SimilarAreaDictionarycopy['Width']<=heightMax) & (SimilarAreaDictionarycopy['Height']>=widthMin) & (SimilarAreaDictionarycopy['Height']<=widthMax) )) ]]
-    elif section.startswith('3.2'):
-      found=SimilarAreaDictionarycopy.loc[SimilarAreaDictionarycopy.index[( (SimilarAreaDictionarycopy['Perimeter'] >=perimmin) & (SimilarAreaDictionarycopy['Perimeter']<=perimmax)    )]]
-    
-    if len(found.index.values) >0:
-      occ=SimilarAreaDictionarycopy.loc[found.index.values[0],'Occurences']
-      if occ== 1: #drop row
-        print('occ=1')
-        print(found)
-        SimilarAreaDictionarycopy= SimilarAreaDictionarycopy.drop(found.index.values[0])
-
-      else: #occ minus 1 , total area - areavalue , total perim - perimvalue
-        print('occ>1')
-        if section.startswith('1.0'):
-          if len(perimstodelete)>0:
-            idx=SimilarAreaDictionarycopy.index[((SimilarAreaDictionarycopy['Perimeter'] >=perimmin) & (SimilarAreaDictionarycopy['Perimeter']<=perimmax)   ) & ( ((SimilarAreaDictionarycopy['Width']>=widthMin) & (SimilarAreaDictionarycopy['Width']<=widthMax) & (SimilarAreaDictionarycopy['Height']>=heightMin) & (SimilarAreaDictionarycopy['Height']<=heightMax) ) | ((SimilarAreaDictionarycopy['Width']>=heightMin) & (SimilarAreaDictionarycopy['Width']<=heightMax) & (SimilarAreaDictionarycopy['Height']>=widthMin) & (SimilarAreaDictionarycopy['Height']<=widthMax) )) ]
-        elif section.startswith('3.2'):
-          if len(perimstodelete)>0:
-            perimmin=round(perimstodelete[i],1)- 1
-            perimmax=round(perimstodelete[i],1)+ 1
-            idx=SimilarAreaDictionarycopy.index[((SimilarAreaDictionarycopy['Perimeter'] >=perimmin) & (SimilarAreaDictionarycopy['Perimeter']<=perimmax)    )]
+    return all(abs(c1 - c2) <= tolerance for c1, c2 in zip(color1, color2))
+
+def deletefromlegend(deletedrows, SimilarAreaDictionarycopy, section, areaPermArr=[]):
+    items = []
+    print('deletefromlegend',deletedrows)
+    idx = 0
+    if section.startswith('1.0') or section.startswith('3.2'):
+        areaPermArr = ast.literal_eval(areaPermArr)
+    myDict = eval(SimilarAreaDictionarycopy)
+    SimilarAreaDictionarycopy = pd.DataFrame(myDict)
+    strings = deletedrows['content']
+    colors = deletedrows['color']
+    indicies_toDelete=[]
+    print(colors)
+    # Define your tolerance value
+    tolerance = 2 # Allowable tolerance for RGB differences
+    print(SimilarAreaDictionarycopy)
+    color_list = list(SimilarAreaDictionarycopy['Color'])  # Convert Index/Series to list
+    if section.startswith('1.0'):       
+       color_list = [ast.literal_eval(color) for color in color_list]
         
-          
-        if len(perimstodelete)>0:
-          comment = SimilarAreaDictionarycopy.loc[idx, 'Comments']
-          if pd.notna(comment.iloc[0]) and 'Area' in str(comment.iloc[0]):
-            matches = re.findall(r'\b\d+\b', str(SimilarAreaDictionarycopy.loc[idx, 'Comments']))
-            area_occurrences = int(matches[1]) 
-            perimeter_occurrences = int(matches[2])-1
-            print(area_occurrences, perimeter_occurrences)
-            SimilarAreaDictionarycopy.loc[idx, 'Comments'] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
-            if area_occurrences > perimeter_occurrences:
-              SimilarAreaDictionarycopy.loc[idx,'Occurences'] = area_occurrences
-            elif perimeter_occurrences> area_occurrences:
-              SimilarAreaDictionarycopy.loc[idx,'Occurences'] = perimeter_occurrences 
-            elif int(area_occurrences)==int(perimeter_occurrences):
-                SimilarAreaDictionarycopy.loc[idx,'Occurences'] = int(SimilarAreaDictionarycopy.loc[idx,'Occurences']) - 1                     
-                if section.startswith('1.0'):
-                  SimilarAreaDictionarycopy.loc[idx,'Total Length'] = SimilarAreaDictionarycopy.loc[idx,'Total Length'] - lengthstodelete[i]
-         
-          else:
-            print('not yet')
-            area_occurrences = SimilarAreaDictionarycopy.loc[idx, 'Occurences'].iloc[0] 
-            perimeter_occurrences = SimilarAreaDictionarycopy.loc[idx, 'Occurences'].iloc[0] -1
-           
-            SimilarAreaDictionarycopy.loc[idx, 'Comments'] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
-            area_occurrences = SimilarAreaDictionarycopy.loc[idx, 'Occurences'].iloc[0] -1
-            perimeter_occurrences = SimilarAreaDictionarycopy.loc[idx, 'Occurences'].iloc[0]
-          
-            
-          SimilarAreaDictionarycopy.loc[idx,'Total Perimeter'] = SimilarAreaDictionarycopy.loc[idx,'Total Perimeter'] - perimstodelete[i]
-  return SimilarAreaDictionarycopy
+    for j in range(len(colors)):
+        # newitem=str(colors[j]).split('\n \n')
+        # input_str = " ".join(str(newitem).split())
+        color = tuple(colors[j])  # Ensure 'color' is in tuple format
+        found = False
+
+        for idx, existing_color in enumerate(color_list):
+            existing_color = tuple(existing_color)  # Ensure it's a tuple for comparison
+
+               
+            print('eee',existing_color,color)
+            if is_color_within_tolerance(existing_color, color, tolerance):
+                print(f'Color {color} found close to {existing_color} at index {idx}')
+                found = True
+                print(strings[j])
+                matchA = re.search(r"Area=(\d+\.\d+)", strings[j])
+                matchP = re.search(r"Perimeter=(\d+\.\d+)", strings[j])
+                matchL = re.search(r"Length=(\d+\.\d+)", strings[j])
+                comment = SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Comments')]
+                occ = SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')]
+
+                # Only subtract area if the area value is found
+                if matchA:
+                    SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Area')] =SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Area')] - float(matchA.group(1))
+                    # Update area occurrences
+                    if pd.notna(comment) and 'Area' in str(comment):
+                        matches = re.findall(r'\b\d+\b', str(comment))
+                        area_occurrences = int(matches[0]) - 1
+                        perimeter_occurrences = int(matches[1])
+                    else:
+                        area_occurrences = int(SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')]) - 1
+                        perimeter_occurrences = SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')]
+
+                    SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Comments')] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
+                if matchP:
+
+                    SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Perimeter')] =SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Perimeter')]  - float(matchP.group(1))# Replace 'Area' with the actual column name
+                    if pd.notna(comment) and 'Perimeter' in str(comment):
+                      matches = re.findall(r'\b\d+\b', str(comment))
+                      area_occurrences = int(matches[0])
+                      perimeter_occurrences = int(matches[1]) -1
+                    else:       
+                      area_occurrences = int(SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')]) 
+                      perimeter_occurrences = SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')]-1
+                      # print(area_occurrences,perimeter_occurrences)
+                      SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Comments')] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
+                  
+
+
+
+                # Handle occurrences and row deletion
+                if area_occurrences==0 and perimeter_occurrences==0:
+                    # if area_occurrences ==0 and perimeter_occurrences==0:
+                      if str(idx) not in indicies_toDelete:
+                        indicies_toDelete.append(str(idx))
+                    # print(SimilarAreaDictionarycopy.index[idx],idx)
+                    
+
+                else:
+                    SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Comments')] = f'Area occurrences: {area_occurrences}, Perimeter occurrences: {perimeter_occurrences}'
+                    if area_occurrences > perimeter_occurrences:
+                        SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')] = area_occurrences
+                    elif perimeter_occurrences > area_occurrences:
+                        SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')] = perimeter_occurrences
+                    else:
+                        SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Occurences')] = area_occurrences
+                    if area_occurrences==1:
+                       SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Area')]= SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Area')] 
+                    if perimeter_occurrences==1:
+                       SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Perimeter')]= SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Perimeter')] 
+                    if area_occurrences==perimeter_occurrences:
+                       if section.startswith('1.0'):
+                          SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Length')] =SimilarAreaDictionarycopy.iloc[int(idx), SimilarAreaDictionarycopy.columns.get_loc('Total Length')]  - float(matchL.group(1))# Replace 'Area' with the actual column name
+                break
+
+        if not found:
+            print(f'Color {color} not found within tolerance')
+    print('indicies_toDelete',indicies_toDelete)
+    SimilarAreaDictionarycopy.drop(index=indicies_toDelete, axis=0, inplace=True)
+    print('SimilarAreaDictionarycopy',SimilarAreaDictionarycopy)
+    return SimilarAreaDictionarycopy
+
 
 
 def DoorsLegend(Dictionary,spreadsheetId,worksheet):
@@ -762,4 +706,58 @@ def delete3_2(deletedrows,dictionary):
   df_doors = df_doors[['Type', 'Quantity']]
   return df_doors
 
-######################
+######################
+
+
+def deletemarkups(list1, dbPath, path):
+    '''list1 : original markup pdf
+       list2 : deleted markup pdf
+       deletedrows : deleted markups - difference between both dfs
+    '''
+
+    myDict1 = eval(list1)
+    list1 = pd.DataFrame(myDict1)
+
+    dbxTeam = tsadropboxretrieval.ADR_Access_DropboxTeam('user')
+    md, res = dbxTeam.files_download(path=dbPath + path)
+    data = res.content
+    doc = fitz.open("pdf", data)
+    
+    # Prepare a DataFrame for the annotations in the new PDF
+    list2 = pd.DataFrame(columns=['content', 'id', 'subject', 'color'])
+
+    for page in doc:
+        # 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:
+                # Check for fill or stroke color
+                stroke_color = annot_color.get('stroke')
+                fill_color = annot_color.get('fill')
+
+                v = 'stroke' if stroke_color else 'fill'
+                color = annot_color.get(v)
+                if color:
+                    # Convert color to tuple and multiply by 255 to get RGB values
+                    color_tuple = (int(color[0] * 255), int(color[1] * 255), int(color[2] * 255))
+                    # Append annotation data to list2
+                    list2.loc[len(list2)] = [annot.info['content'], annot.info['id'], annot.info['subject'], color_tuple]
+
+    # Ensure that colors are stored as tuples (which are hashable)
+    list1['color'] = list1['color'].apply(lambda x: tuple(x) if isinstance(x, list) else x)
+    
+    # Find the deleted rows by checking the difference between original and current annotations
+    deletedrows = pd.concat([list1, list2]).drop_duplicates(keep=False)
+
+    print(deletedrows, len(deletedrows))
+    flag = 0
+    if len(deletedrows) != 0:
+        flag = 1
+        deletedrows = deletedrows[['content', 'id', 'subject', 'color']]
+        # Drop rows where 'content' starts with 'Scale'
+        deletedrows = deletedrows.drop(deletedrows.index[deletedrows['content'].str.startswith('Scale')])
+    else:
+        flag = 0
+    
+    return deletedrows