32460 upgraded pypdf2 to pypdf (bcgov#4108)

Author: vysakh-menon-aot

legal-api/.devcontainer/Dockerfile

@@ -2,9 +2,11 @@ FROM mcr.microsoft.com/devcontainers/python:3.9-bullseye
 
 
 RUN \
+    rm -f /etc/apt/sources.list.d/yarn.list && \
     apt update && apt install bash-completion postgresql-client -y && \
-    pip install pre-commit && \
-    curl -sSL https://install.python-poetry.org | POETRY_HOME=/home/vscode/.local python3 -
+    pip install --upgrade pip && \
+    pip install pre-commit poetry && \
+    poetry config virtualenvs.in-project true
 
 RUN \
     pip install ruff
@@ -19,4 +21,4 @@ RUN  \
     echo '    . /etc/bash_completion' >> /home/vscode/.bashrc && \
     echo 'fi' >> /home/vscode/.bashrc && \
     echo >> /home/vscode/.bashrc && \
-    echo '. <(poetry completions)' >> /home/vscode/.bashrc
+    echo '. <(poetry completions)' >> /home/vscode/.bashrc

legal-api/.devcontainer/devcontainer.json

@@ -9,37 +9,37 @@
 		// This saves the user a bit of time, when re-opening containers
 		"dockerfile": "Dockerfile"
 	},
-
 	"features": {
 		"ghcr.io/devcontainers/features/docker-in-docker:2": {
 			"version": "latest",
 			"dockerDashComposeVersion": "v2"
 		}
 	},
-    "runArgs": ["--add-host=host.docker.internal:host-gateway"],
+	"runArgs": [
+		"--add-host=host.docker.internal:host-gateway"
+	],
 	// this seems to be needed on OSX, at times.
 	// I have not tested it on windows, but should also work fine on Ubuntu
 	"mounts": [
-        {
-            "source": "/var/run/docker.sock",
-            "target": "/var/run/docker.sock",
-            "type": "bind"
-        }
-    ],
+		{
+			"source": "/var/run/docker.sock",
+			"target": "/var/run/docker.sock",
+			"type": "bind"
+		}
+	],
 	"containerEnv": {
-        "PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION": "python"
+		"PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION": "python"
 	},
 	"remoteEnv": {
-        "PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION": "python"
+		"PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION": "python"
 	},
-	// "forwardPorts": [5432],
-
+	"forwardPorts": [
+		8080
+	],
 	// Features to add to the dev container. More info: https://containers.dev/features.
 	// "features": {},
-
 	// Use 'forwardPorts' to make a list of ports inside the container available locally.
 	// "forwardPorts": [],
-
 	// Use 'postCreateCommand' to run commands after the container is created.
 	"postCreateCommand": ".devcontainer/commands/post-create-command.sh",
 	"customizations": {
@@ -49,10 +49,8 @@
 			]
 		}
 	}
-
 	// Configure tool-specific properties.
 	// "customizations": {},
-
 	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
 	// "remoteUser": "root"
-}
+}

legal-api/poetry.lock

@@ -40,7 +40,7 @@ dependencies = [
     "python-editor (==1.0.4)",
     "strict-rfc3339 (==0.7)",
     "minio (==7.0.2)",
-    "PyPDF2 (==1.26.0)",
+    "pypdf (==6.7.2)",
     "reportlab (==3.6.12)",
     "html-sanitizer (==2.4.1)",
     "lxml (==5.2.2)",

legal-api/pyproject.toml

@@ -19,9 +19,9 @@
 from typing import Final, Optional
 
 import pycountry
-import PyPDF2
 from flask import current_app, g, request
 from flask_babel import _
+from pypdf import PdfReader
 
 from legal_api.core.filing import Filing
 from legal_api.errors import Error
@@ -397,14 +397,14 @@ def validate_pdf(file_key: str, file_key_path: str, verify_paper_size: bool = Tr
     try:
         file = MinioService.get_file(file_key)
         open_pdf_file = io.BytesIO(file.data)
-        pdf_reader = PyPDF2.PdfFileReader(open_pdf_file)
+        pdf_reader = PdfReader(open_pdf_file)
 
         # Check that all pages in the pdf are letter size and able to be processed.
         width: Final = 612  # 8.5 inches
         height: Final = 792  # 11 inches
         if (
             verify_paper_size and
-            any(x.mediaBox.getWidth() != width or x.mediaBox.getHeight() != height for x in pdf_reader.pages)
+            any(x.mediabox.width != width or x.mediabox.height != height for x in pdf_reader.pages)
         ):
             msg.append({"error": _("Document must be set to fit onto 8.5” x 11” letter-size paper."),
                         "path": file_key_path})
@@ -414,10 +414,11 @@ def validate_pdf(file_key: str, file_key_path: str, verify_paper_size: bool = Tr
         if file_info.size > max_file_size:
             msg.append({"error": _("File exceeds maximum size."), "path": file_key_path})
 
-        if pdf_reader.isEncrypted:
+        if pdf_reader.is_encrypted:
             msg.append({"error": _("File must be unencrypted."), "path": file_key_path})
 
-    except Exception:
+    except Exception as ex:
+        current_app.logger.debug(f"Error validating PDF: {ex}")
         msg.append({"error": _("Invalid file."), "path": file_key_path})
 
     if msg:

legal-api/src/legal_api/services/filings/validations/common_validations.py

@@ -15,8 +15,8 @@
 import io
 from typing import Final
 
-import PyPDF2
 from flask import current_app
+from pypdf import PdfWriter
 
 from legal_api.models import Furnishing, db
 from legal_api.reports.report_v2 import ReportTypes, ReportV2
@@ -79,15 +79,15 @@ def _get_batch_cover(self, files: list) -> bytes:
     @staticmethod
     def _merge_documents(files: dict) -> bytes:
         try:
-            merger = PyPDF2.PdfFileMerger()
+            writer = PdfWriter()
             if files["cover"]:
-                merger.append(io.BytesIO(files["cover"]))
+                writer.append(io.BytesIO(files["cover"]))
             contents = files["contents"]
             for _, pdf in enumerate(contents):
-                merger.append(io.BytesIO(pdf))
+                writer.append(io.BytesIO(pdf))
             writer_buffer = io.BytesIO()
-            merger.write(writer_buffer)
-            merger.close()
+            writer.write(writer_buffer)
+            writer.close()
             return writer_buffer.getvalue()
         except Exception as e:
             current_app.logger.error(f"Error merging PDF:{e}")

legal-api/src/legal_api/services/furnishing_documents_service.py

@@ -18,8 +18,8 @@
 from datetime import datetime
 from typing import Optional
 
-import PyPDF2
 from flask import current_app
+from pypdf import PdfReader, PdfWriter
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfbase import pdfmetrics
 from reportlab.pdfbase.ttfonts import TTFont
@@ -51,19 +51,19 @@ def __init__(self):
     @staticmethod
     def stamp_pdf(input_pdf, watermark, only_first_page=True):
         """Merge two PDFs."""
-        watermark_obj = PyPDF2.PdfFileReader(watermark)
-        watermark_page = watermark_obj.getPage(0)
+        watermark_obj = PdfReader(watermark)
+        watermark_page = watermark_obj.get_page(0)
 
-        pdf_reader = PyPDF2.PdfFileReader(input_pdf)
-        pdf_writer = PyPDF2.PdfFileWriter()
+        pdf_reader = PdfReader(input_pdf)
+        pdf_writer = PdfWriter()
 
-        for page_num in range(pdf_reader.getNumPages()):
-            page = pdf_reader.getPage(page_num)
+        for page_num in range(pdf_reader.get_num_pages()):
+            page = pdf_reader.get_page(page_num)
 
             if (only_first_page and page_num == 0) or not only_first_page:
-                page.mergePage(watermark_page)
+                page.merge_page(watermark_page)
 
-            pdf_writer.addPage(page)
+            pdf_writer.add_page(page)
 
         output = io.BytesIO()
         pdf_writer.write(output)

legal-api/src/legal_api/services/pdf_service.py

@@ -16,7 +16,7 @@
 """
 import io
 
-import PyPDF2
+from pypdf import PdfReader
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
 
@@ -36,15 +36,15 @@ def test_stamp(app):  # pylint:disable=unused-argument
         registrars_stamp = pdf_service.create_registrars_stamp(registrar_stamp_data)
 
         certified_copy = pdf_service.stamp_pdf(pdf_input, registrars_stamp, only_first_page=True)
-        certified_copy_obj = PyPDF2.PdfFileReader(certified_copy)
+        certified_copy_obj = PdfReader(certified_copy)
 
-        certified_copy_page = certified_copy_obj.getPage(0)
-        text = certified_copy_page.extractText()
+        certified_copy_page = certified_copy_obj.get_page(0)
+        text = certified_copy_page.extract_text()
         assert 'Filed on' in text
         assert 'File Name: rules.pdf' in text
 
-        certified_copy_page = certified_copy_obj.getPage(1)
-        text = certified_copy_page.extractText()
+        certified_copy_page = certified_copy_obj.get_page(1)
+        text = certified_copy_page.extract_text()
         assert 'Filed on' not in text
 
         # Uncomment to generate the file: