Merge pull request #136 from department-of-veterans-affairs/117-pypdf…

…2-deprecation

#117 PyPDF2 deprecation

notifications_utils/field.py

@@ -1,7 +1,7 @@
 import re
 
 from orderedset import OrderedSet
-from flask import Markup
+from markupsafe import Markup
 
 from notifications_utils.columns import Columns
 from notifications_utils.formatters import (

notifications_utils/formatters.py

@@ -5,7 +5,7 @@
 import mistune
 import bleach
 from itertools import count
-from flask import Markup
+from markupsafe import Markup
 from . import email_with_smart_quotes_regex
 from notifications_utils.sanitise_text import SanitiseSMS
 import smartypants

notifications_utils/pdf.py

@@ -1,17 +1,16 @@
-import PyPDF2
-from PyPDF2 import PdfWriter
-from PyPDF2.errors import PdfReadError
+from pypdf import PdfWriter, PdfReader
+from pypdf.errors import PdfReadError
 import io
 
 
 def pdf_page_count(src_pdf):
     """
     Returns number of pages in a pdf file
 
-    :param PyPDF2.PdfReader src_pdf: A File object or an object that supports the standard read and seek methods
+    :param PdfReader src_pdf: A File object or an object that supports the standard read and seek methods
     """
     try:
-        pdf = PyPDF2.PdfReader(src_pdf)
+        pdf = PdfReader(src_pdf)
     except AttributeError as e:
         raise PdfReadError("Could not open PDF file, stream is null", e)
 
@@ -25,7 +24,7 @@ def extract_page_from_pdf(src_pdf, page_number):
     :param src_pdf: File object or an object that supports the standard read and seek methods similar to a File object.
     :param page_number: The page number to retrieve (pages begin at zero)
     """
-    pdf = PyPDF2.PdfReader(src_pdf)
+    pdf = PdfReader(src_pdf)
 
     if len(pdf.pages) < page_number:
         raise PdfReadError("Page number requested: {} of {} does not exist in document".format(

notifications_utils/template.py

@@ -4,7 +4,7 @@
 from datetime import datetime
 
 from jinja2 import Environment, FileSystemLoader
-from flask import Markup
+from markupsafe import Markup
 from html import unescape
 
 from notifications_utils import SMS_CHAR_COUNT_LIMIT

setup.py

@@ -32,16 +32,17 @@
         'Flask>=1.1.1',
         'Flask-Redis>=0.4.0',
         'Jinja2>=2.11.3',
+        'MarkupSafe>=2.1.3',
         'mistune==0.8.4',
         'monotonic>=1.6',
         'orderedset>=2.0.3',
         'phonenumbers~=8.12.12',
-        'pypdf2 ~= 3.0.1',
+        'pypdf >= 3.15.0',
         'python-json-logger~=2.0.7',
         'pytz>=2021.3',
         'pyyaml==5.4.1',
         'requests>=2.26.0',
         'smartypants>=2.0.1',
-        'statsd>=3.3.0',
+        'statsd>=3.3.0'
     ]
 )

tests/test_formatters.py

@@ -1,5 +1,5 @@
 import pytest
-from flask import Markup
+from markupsafe import Markup
 
 from notifications_utils.formatters import (
     unlink_govuk_escaped,

tests/test_pdf.py

@@ -1,9 +1,9 @@
 import base64
 from io import BytesIO
 
-import PyPDF2
 import pytest
-from PyPDF2.errors import PdfReadError
+from pypdf import PdfReader
+from pypdf.errors import PdfReadError
 
 from notifications_utils.pdf import pdf_page_count, extract_page_from_pdf
 from tests.pdf_consts import one_page_pdf, multi_page_pdf, not_pdf
@@ -36,9 +36,9 @@ def test_extract_page_from_pdf_one_page_pdf():
     file_data = base64.b64decode(one_page_pdf)
     pdf_page = extract_page_from_pdf(BytesIO(file_data), 0)
 
-    pdf_original = PyPDF2.PdfReader(BytesIO(file_data))
+    pdf_original = PdfReader(BytesIO(file_data))
 
-    pdf_new = PyPDF2.PdfReader(BytesIO(pdf_page))
+    pdf_new = PdfReader(BytesIO(pdf_page))
 
     assert pdf_original.pages[0].extract_text() == pdf_new.pages[0].extract_text()
 
@@ -47,9 +47,9 @@ def test_extract_page_from_pdf_multi_page_pdf():
     file_data = base64.b64decode(multi_page_pdf)
     pdf_page = extract_page_from_pdf(BytesIO(file_data), 4)
 
-    pdf_original = PyPDF2.PdfReader(BytesIO(file_data))
+    pdf_original = PdfReader(BytesIO(file_data))
 
-    pdf_new = PyPDF2.PdfReader(BytesIO(pdf_page))
+    pdf_new = PdfReader(BytesIO(pdf_page))
 
     assert pdf_original.pages[4].extract_text() == pdf_new.pages[0].extract_text()
     assert pdf_original.pages[3].extract_text() != pdf_new.pages[0].extract_text()

tests/test_template_types.py

@@ -2,10 +2,9 @@
 from time import process_time
 import os
 import pytest
-
 from functools import partial
 from unittest import mock
-from flask import Markup
+from markupsafe import Markup
 from freezegun import freeze_time
 
 from notifications_utils.formatters import unlink_govuk_escaped