change from pypdf2 to pypdf (#2666)

# Description

addition to #2636

## Checklist

- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [x] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [x] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)

cucumber/exampleFiles/example.html

@@ -8,4 +8,3 @@
 
 </body>
 </html>
-

cucumber/features/environment.py

@@ -18,4 +18,4 @@ def after_scenario(context, scenario):
     # Remove any temporary files
     for temp_file in os.listdir('.'):
         if temp_file.startswith('genericNonCustomisableName') or temp_file.startswith('temp_image_'):
-            os.remove(temp_file)
+            os.remove(temp_file)

cucumber/features/steps/step_definitions.py

@@ -1,7 +1,8 @@
 import os
 import requests
 from behave import given, when, then
-from PyPDF2 import PdfWriter, PdfReader
+from pypdf import PdfWriter, PdfReader
+from pypdf.errors import PdfReadError
 import io
 import random
 import string
@@ -42,7 +43,7 @@ def step_use_example_file(context, filePath, fileInput):
     context.file_name = filePath.split('/')[-1]
     if not hasattr(context, 'files'):
         context.files = {}
-    
+
     # Ensure the file exists before opening
     try:
         example_file = open(filePath, 'rb')
@@ -165,17 +166,17 @@ def step_pdf_contains_pages_with_random_text(context, page_count):
     buffer = io.BytesIO()
     c = canvas.Canvas(buffer, pagesize=letter)
     width, height = letter
-    
+
     for _ in range(page_count):
         text = ''.join(random.choices(string.ascii_letters + string.digits, k=100))
         c.drawString(100, height - 100, text)
         c.showPage()
-        
+
     c.save()
-    
+
     with open(context.file_name, 'wb') as f:
         f.write(buffer.getvalue())
-        
+
     context.files[context.param_name].close()
     context.files[context.param_name] = open(context.file_name, 'rb')
 
@@ -184,16 +185,16 @@ def step_pdf_pages_contain_text(context, text):
     buffer = io.BytesIO()
     c = canvas.Canvas(buffer, pagesize=letter)
     width, height = letter
-    
+
     for _ in range(len(PdfReader(context.file_name).pages)):
         c.drawString(100, height - 100, text)
         c.showPage()
-        
+
     c.save()
-    
+
     with open(context.file_name, 'wb') as f:
         f.write(buffer.getvalue())
-        
+
     context.files[context.param_name].close()
     context.files[context.param_name] = open(context.file_name, 'rb')
 
@@ -345,7 +346,7 @@ def step_check_response_pdf_page_count(context, page_count):
 def step_check_response_zip_file_count(context, file_count):
     response_file = io.BytesIO(context.response.content)
     with zipfile.ZipFile(io.BytesIO(response_file.getvalue())) as zip_file:
-      actual_file_count = len(zip_file.namelist())
+        actual_file_count = len(zip_file.namelist())
     assert actual_file_count == file_count, f"Expected {file_count} files but got {actual_file_count} files"
 
 @then('the response ZIP file should contain {doc_count:d} documents each having {pages_per_doc:d} pages')
@@ -354,7 +355,7 @@ def step_check_response_zip_doc_page_count(context, doc_count, pages_per_doc):
     with zipfile.ZipFile(io.BytesIO(response_file.getvalue())) as zip_file:
         actual_doc_count = len(zip_file.namelist())
         assert actual_doc_count == doc_count, f"Expected {doc_count} documents but got {actual_doc_count} documents"
-        
+
         for file_name in zip_file.namelist():
             with zip_file.open(file_name) as pdf_file:
                 reader = PdfReader(pdf_file)

cucumber/requirements.in

@@ -1,5 +1,5 @@
 behave
 requests
-PyPDF2
+pypdf
 reportlab
 PyCryptodome

cucumber/requirements.txt

@@ -231,9 +231,9 @@ pycryptodome==3.21.0 \
     --hash=sha256:f7787e0d469bdae763b876174cf2e6c0f7be79808af26b1da96f1a64bcf47297 \
     --hash=sha256:ff99f952db3db2fbe98a0b355175f93ec334ba3d01bbde25ad3a5a33abc02b58
     # via -r cucumber\requirements.in
-pypdf2==3.0.1 \
+pypdf==5.1.0 \
-    --hash=sha256:a74408f69ba6271f71b9352ef4ed03dc53a31aa404d29b5d31f53bfecfee1440 \
+    --hash=sha256:3bd4f503f4ebc58bae40d81e81a9176c400cbbac2ba2d877367595fb524dfdfc \
-    --hash=sha256:d16e4205cfee272fbdc0568b68d82be796540b1537508cef59388f839c191928
+    --hash=sha256:425a129abb1614183fd1aca6982f650b47f8026867c0ce7c4b9f281c443d2740
     # via -r cucumber\requirements.in
 reportlab==4.2.5 \
     --hash=sha256:5cf35b8fd609b68080ac7bbb0ae1e376104f7d5f7b2d3914c7adc63f2593941f \
@@ -249,6 +249,10 @@ six==1.17.0 \
     # via
     #   behave
     #   parse-type
+typing-extensions==4.12.2 \
+    --hash=sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d \
+    --hash=sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8
+    # via pypdf
 urllib3==2.3.0 \
     --hash=sha256:1cee9ad369867bfdbbb48b7dd50374c0967a0bb7710050facf0dd6911440e3df \
     --hash=sha256:f8c5449b3cf0861679ce7e0503c7b44b5ec981bec0d1d3795a07f1ba96f0204d