Update Code_2_7.py

Code_2_7.py

@@ -846,7 +846,9 @@ def get_hatched_areas(datadoc,filename,FinalRatio,rotationangle,SearchArray):
                             if not duplicate_found:
                                 # rgb_color = get_hatch_color(entity)  # Assuming this function exists
                                 unique_shapes.append((normalized_vertices, area1))
-                                hatched_areas.append([vertices, area1, length, rgb_color])
+
+                                if length > 0.6:
+                                    hatched_areas.append([vertices, area1, length, rgb_color])
 
                 elif str(path.type) == 'BoundaryPathType.EDGE' or path.type == 2:
                 # elif path.type == 2:  # Edge path
@@ -894,7 +896,9 @@ def get_hatched_areas(datadoc,filename,FinalRatio,rotationangle,SearchArray):
                         if not duplicate_found:
                             # rgb_color = get_hatch_color(entity)  # Assuming this function exists
                             unique_shapes.append((normalized_vertices, area1))
-                            hatched_areas.append([vert, area1, length, rgb_color])
+
+                            if length > 0.6:
+                                hatched_areas.append([vert, area1, length, rgb_color])
 
                 else:
                     print(f"Encountered path type: {path.type}")
@@ -1193,19 +1197,6 @@ def adjustannotations(OutputPdfStage1,text_with_positions):
   metadata = reader.metadata
   writer.add_metadata(metadata)
 
-#   x=input_pdf_path
-
-#   # Load the input PDF
-#   reader = PdfReader(input_pdf_path)
-#   writer = PdfWriter()
-
-#   # Append all pages to the writer
-#   writer.append_pages_from_reader(reader)
-
-#   # Add metadata (optional)
-#   metadata = reader.metadata
-#   writer.add_metadata(metadata)
-
   for page_index, page in enumerate(writer.pages):
       if "/Annots" in page:
           annotations = page["/Annots"]
@@ -1265,12 +1256,74 @@ def adjustannotations(OutputPdfStage1,text_with_positions):
 
   print(f"Annotations updated and saved to {output_pdf_path}")
   return output_pdf_io.read()
-#   # Save the modified PDF
-#   with open(output_pdf_path, "wb") as fp:
-#       writer.write(fp)
 
-#   print(f"Annotations updated and saved to {output_pdf_path}")
-#   return output_pdf_path
+def distance(rect1, rect2):
+    """Calculate the Euclidean distance between two annotation centers."""
+    x1, y1 = (float(rect1[0]) + float(rect1[2])) / 2, (float(rect1[1]) + float(rect1[3])) / 2
+    x2, y2 = (float(rect2[0]) + float(rect2[2])) / 2, (float(rect2[1]) + float(rect2[3])) / 2
+    return math.sqrt((x2 - x1) ** 2 + (y2 - y1) ** 2)
+
+def remove_duplicate_annotations(pdf_path, threshold):
+    """Remove one of the duplicate annotations if they are close and have the same color."""
+
+    input_pdf_path = pdf_path
+    output_pdf_path = "Filtered-Walls.pdf"
+
+    # Load the input PDF
+    pdf_bytes_io = BytesIO(pdf_path)
+
+    reader = PdfReader(pdf_bytes_io)
+    writer = PdfWriter()
+
+    # Append all pages to the writer
+    # writer.append_pages_from_reader(reader)
+
+    # Add metadata (optional)
+    metadata = reader.metadata
+    writer.add_metadata(metadata)
+
+    for page_index in range(len(reader.pages)):
+        page = reader.pages[page_index]
+
+        if "/Annots" in page:
+            annotations = page["/Annots"]
+            annots_data = []
+            to_delete = set()
+
+            # Extract annotation positions and colors
+            for annot_index, annot_ref in enumerate(annotations):
+                annot = annot_ref.get_object()
+
+                if "/Rect" in annot and "/C" in annot:
+                    rect = annot["/Rect"]
+                    if isinstance(rect, ArrayObject):  # Ensure rect is a list
+                        rect = list(rect)
+
+                    color = normalize_color(annot["/C"])
+                    annots_data.append((annot_index, rect, color))
+
+            # Compare distances and mark duplicates
+            for i, (idx1, rect1, color1) in enumerate(annots_data):
+                if idx1 in to_delete:
+                    continue
+                for j, (idx2, rect2, color2) in enumerate(annots_data[i+1:], start=i+1):
+                    if idx2 in to_delete:
+                        continue
+                    if color1 == color2 and distance(rect1, rect2) < threshold:
+                        to_delete.add(idx2)  # Mark second annotation for deletion
+
+            # Remove duplicates
+            new_annotations = [annotations[i] for i in range(len(annotations)) if i not in to_delete]
+            page[NameObject("/Annots")] = ArrayObject(new_annotations)
+
+        writer.add_page(page)
+
+    output_pdf_io = BytesIO()
+    writer.write(output_pdf_io)
+    output_pdf_io.seek(0)
+
+    return output_pdf_io.read()
+
 
 
 
@@ -1281,7 +1334,7 @@ def calculate_distance(p1, p2):
 
 
 
-def mainFunctionDrawImgPdf(datadoc,dxfpath, dxfratio,SearchArray,pdfpath=0,pdfname=0):
+def mainFunctionDrawImgPdf(datadoc,dxfpath, dxfratio,SearchArray,Thickness,pdfpath=0,pdfname=0):
   OutputPdfStage1='BB Trial.pdf'
   FinalRatio= RetriveRatio(datadoc,dxfpath)
 
@@ -1586,15 +1639,14 @@ def mainFunctionDrawImgPdf(datadoc,dxfpath, dxfratio,SearchArray,pdfpath=0,pdfna
 #   OutputPdfStage2=adjustannotations(OutputPdfStage1,text_with_positions)
   modified_pdf_data = doc.tobytes()
   OutputPdfStage2=adjustannotations(modified_pdf_data,text_with_positions)
-  latestimg,pix=pdftoimg(OutputPdfStage2)
-  doc2 =fitz.open('pdf',OutputPdfStage2)
-    
+  
+  threshold = math.ceil(float(Thickness) * float(dxfratio) )
+  print(threshold)
+  OutputPdfStage3 = remove_duplicate_annotations(OutputPdfStage2,threshold)
+
+  latestimg,pix=pdftoimg(OutputPdfStage3)
+  doc2 =fitz.open('pdf',OutputPdfStage3)
   gc,spreadsheet_service,spreadsheetId, spreadsheet_url , namepathArr=google_sheet_Legend.legendGoogleSheets(grouped_df , pdfname,pdfpath)
-  # dbxTeam=tsadropboxretrieval.ADR_Access_DropboxTeam('user')
-  # md, res =dbxTeam.files_download(path= pdfpath+pdfname)
-  # data = res.content
-  # doc=fitz.open("pdf", data)
-  # list1=pd.DataFrame(columns=['content', 'creationDate', 'id', 'modDate', 'name', 'subject', 'title'])
   list1=pd.DataFrame(columns=['content',  'id',  'subject','color'])
 
   # for page in doc: