Merge pull request #1135 from bcgov/dev-AA-FOIMOD-3439

#FOIMOD-3439, removing sensitve info from PDF doc, Zipper services

.gitignore

@@ -100,3 +100,5 @@ bld/
 MCS.FOI.S3FileConversion/MCS.FOI.S3FileConversion/QtBinariesWindows/
 computingservices/ZippingServices/env/*
 openshift/templates/zippingservice/zipper.env
+*.locenv
+

computingservices/ZippingServices/services/zipperservice.py

@@ -14,6 +14,7 @@
 from .notificationservice import notificationservice
 import json
 import traceback
+import PyPDF2
 
 
 def processmessage(message):
@@ -110,8 +111,16 @@ def __zipfilesandupload(_message, s3credentials):
                 for fileobj in _jsonfiles:
                     filename = fileobj["filename"]
                     print("\nfilename:",filename)
+
+                    _docbytes = __getdocumentbytearray(fileobj, s3credentials)
+                    _formattedbytes = None
+
+                    try:                           
+                        _formattedbytes = __removesensitivecontent(_docbytes)                           
+                    except Exception:
+                        print(traceback.format_exc())
                     zip.writestr(
-                        filename, __getdocumentbytearray(fileobj, s3credentials)
+                        filename, _docbytes if _formattedbytes is None else _formattedbytes
                     )
 
             tp.seek(0)           
@@ -136,6 +145,22 @@ def __zipfilesandupload(_message, s3credentials):
     finally:
         zipped_bytes = None
 
+def __removesensitivecontent(documentbytes):
+    # clear metadata
+    reader2 = PyPDF2.PdfReader(BytesIO(documentbytes))
+    # Check if metadata exists.
+    if reader2.metadata is not None:
+        # Create a new PDF file without metadata.
+        writer = PyPDF2.PdfWriter()
+        # Copy pages from the original PDF to the new PDF.
+        for page_num in range(len(reader2.pages)):
+            page = reader2.pages[page_num]                
+            writer.add_page(page)        
+        #writer.remove_links() # to remove comments.
+        buffer = BytesIO()
+        writer.write(buffer)
+        return buffer.getvalue()
+
 
 def __getzipfilepath(foldername, filename):
     return (