gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(deps): upgrade PyPDF2 to pypdf >= 3.9.0 to fix CVE-2023-36464

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-12 02:52:17 +00:00
parent 0c2e308790
commit cc98039246
10 changed files with 31 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/api/files.py
+3 -3
View File
@@ -460,7 +460,7 @@ def reprocess_with_cloud_ocr(request: Request, file_id: int, db: DbSession):
def _extract_text_from_pdf(file_path: str) -> str:
"""
Extract text from a PDF file using PyPDF2.
Extract text from a PDF file using pypdf.
Args:
file_path: Path to the PDF file
@@ -468,11 +468,11 @@ def _extract_text_from_pdf(file_path: str) -> str:
Returns:
Extracted text from all pages
"""
import PyPDF2
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
extracted_text = ""
with open(file_path, "rb") as f:
pdf_reader = PyPDF2.PdfReader(f)
pdf_reader = pypdf.PdfReader(f)
for page in pdf_reader.pages:
extracted_text += page.extract_text() + "\n"
return extracted_text
app/tasks/embed_metadata_into_pdf.py
+3 -3
View File
@@ -7,7 +7,7 @@ import shutil
import tempfile
from pathlib import Path
import PyPDF2 # Replace fitz with PyPDF2
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
# Import the shared Celery instance
from app.celery_app import celery
@@ -128,8 +128,8 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
# Open the PDF and modify metadata
with open(processed_file, "rb") as file:
pdf_reader = PyPDF2.PdfReader(file)
pdf_writer = PyPDF2.PdfWriter()
pdf_reader = pypdf.PdfReader(file)
pdf_writer = pypdf.PdfWriter()
# Copy all pages from the reader to the writer
for page in pdf_reader.pages:
app/tasks/process_document.py
+4 -4
View File
@@ -6,8 +6,8 @@ import os
import shutil
import uuid
import PyPDF2 # Replace fitz with PyPDF2
from PyPDF2.errors import PdfReadError
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
from pypdf.errors import PdfReadError
from app.celery_app import celery
from app.config import settings
@@ -343,7 +343,7 @@ def process_document(self, original_local_file: str, original_filename: str = No
)
try:
with open(new_local_path, "rb") as file:
pdf_reader = PyPDF2.PdfReader(file)
pdf_reader = pypdf.PdfReader(file)
has_text = False
for page in pdf_reader.pages:
if page.extract_text().strip():
@@ -391,7 +391,7 @@ def process_document(self, original_local_file: str, original_filename: str = No
)
extracted_text = ""
with open(new_local_path, "rb") as file:
pdf_reader = PyPDF2.PdfReader(file)
pdf_reader = pypdf.PdfReader(file)
for page in pdf_reader.pages:
extracted_text += page.extract_text() + "\n"
app/tasks/process_with_azure_document_intelligence.py
+2 -2
View File
@@ -2,7 +2,7 @@ import logging
import os
import azure.core.exceptions
import PyPDF2
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
from azure.ai.documentintelligence import DocumentIntelligenceClient
from azure.ai.documentintelligence.models import AnalyzeOutputOption, AnalyzeResult
from azure.core.credentials import AzureKeyCredential
@@ -39,7 +39,7 @@ def get_pdf_page_count(file_path):
"""Get the number of pages in a PDF file."""
try:
with open(file_path, "rb") as file:
pdf_reader = PyPDF2.PdfReader(file)
pdf_reader = pypdf.PdfReader(file)
return len(pdf_reader.pages)
except Exception as e:
logger.error(f"Error getting PDF page count: {e}")
app/tasks/rotate_pdf_pages.py
+8 -8
View File
@@ -2,7 +2,7 @@ import json
import logging
import os
import PyPDF2
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
from app.celery_app import celery
from app.config import settings
@@ -21,7 +21,7 @@ def determine_rotation_angle(detected_angle):
detected_angle: The angle detected by Azure Document Intelligence
Returns:
int: The angle to rotate the page in PyPDF2 (must be multiple of 90 degrees)
int: The angle to rotate the page in pypdf (must be multiple of 90 degrees)
"""
# Normalize angle to be between 0 and 360
normalized_angle = detected_angle % 360
@@ -35,15 +35,15 @@ def determine_rotation_angle(detected_angle):
# For angles close to 90, 180, or 270 degrees (±5°), round to nearest 90° increment
for target in [90, 180, 270]:
if abs(normalized_angle - target) < 5:
# PyPDF2 uses clockwise rotation, so we need to use the complementary angle
# pypdf uses clockwise rotation, so we need to use the complementary angle
rotation_value = (360 - target) % 360
logger.info(f"Detected angle {detected_angle}° is close to {target}°, will rotate by {rotation_value}°")
return rotation_value
# For other significant angles, round to nearest 90° increment
# (PyPDF2 only supports rotations in 90-degree increments)
# (pypdf only supports rotations in 90-degree increments)
closest_90_multiple = round(normalized_angle / 90) * 90
# Convert to PyPDF2 rotation value (clockwise)
# Convert to pypdf rotation value (clockwise)
rotation_value = (360 - closest_90_multiple) % 360
logger.info(f"Detected angle {detected_angle}° rounded to {closest_90_multiple}°, will rotate by {rotation_value}°")
return rotation_value
@@ -110,8 +110,8 @@ def rotate_pdf_pages(self, filename: str, extracted_text: str, rotation_data=Non
# Load the PDF
with open(pdf_path, "rb") as file:
pdf_reader = PyPDF2.PdfReader(file)
pdf_writer = PyPDF2.PdfWriter()
pdf_reader = pypdf.PdfReader(file)
pdf_writer = pypdf.PdfWriter()
# Process each page
for page_idx in range(len(pdf_reader.pages)):
@@ -123,7 +123,7 @@ def rotate_pdf_pages(self, filename: str, extracted_text: str, rotation_data=Non
rotation_angle = determine_rotation_angle(detected_angle)
if rotation_angle > 0:
# PyPDF2 uses clockwise rotation in 90-degree increments
# pypdf uses clockwise rotation in 90-degree increments
page.rotate(rotation_angle)
logger.info(
f"[{task_id}] Page {page_idx+1} rotated by {rotation_angle}° "
app/utils/file_splitting.py
+1 -1
View File
@@ -10,7 +10,7 @@ import logging
import os
from typing import List, Optional
from PyPDF2 import PdfReader, PdfWriter
from pypdf import PdfReader, PdfWriter # Upgraded from PyPDF2 to fix CVE-2023-36464
logger = logging.getLogger(__name__)
app/views/files.py
+4 -4
View File
@@ -492,8 +492,8 @@ def get_original_text(request: Request, file_id: int, db: Session = Depends(get_
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Original file not found on disk")
try:
# Extract text from PDF using PyPDF2
from PyPDF2 import PdfReader
# Extract text from PDF using pypdf
from pypdf import PdfReader # Upgraded from PyPDF2 to fix CVE-2023-36464
reader = PdfReader(file_record.original_file_path)
text = ""
@@ -532,8 +532,8 @@ def get_processed_text(request: Request, file_id: int, db: Session = Depends(get
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Processed file not found on disk")
try:
# Extract text from PDF using PyPDF2
from PyPDF2 import PdfReader
# Extract text from PDF using pypdf
from pypdf import PdfReader # Upgraded from PyPDF2 to fix CVE-2023-36464
reader = PdfReader(file_record.processed_file_path)
text = ""
requirements.txt
+1 -1
View File
@@ -6,7 +6,7 @@ sqlalchemy # Database ORM
pydantic # Data validation
cryptography>=41.0.0 # Encryption for sensitive settings in database
openai # GPT integration for metadata extraction
PyPDF2>=3.0.0 # PDF processing for text extraction, metadata editing and rotation (replaces PyMuPDF)
pypdf>=3.9.0 # PDF processing for text extraction, metadata editing and rotation (upgraded from PyPDF2 to fix CVE-2023-36464)
requests # HTTP client
puremagic>=1.25,<2.0 # File type detection (pure Python)
filetype>=1.2.0,<2.0 # File type detection fallback (pure Python)
tests/test_external_integrations.py
+4 -4
View File
@@ -778,7 +778,7 @@ class TestPdfGenerator:
@staticmethod
def test_generate_default_pdf() -> None:
"""Test that generate_test_pdf creates a valid PDF with embedded text."""
import PyPDF2
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
path = generate_test_pdf()
try:
@@ -786,7 +786,7 @@ class TestPdfGenerator:
assert os.path.getsize(path) > 100
with open(path, "rb") as f:
reader = PyPDF2.PdfReader(f)
reader = pypdf.PdfReader(f)
assert len(reader.pages) >= 1
text = reader.pages[0].extract_text()
assert "Invoice" in text
@@ -797,13 +797,13 @@ class TestPdfGenerator:
@staticmethod
def test_generate_custom_content_pdf() -> None:
"""Test that generate_test_pdf accepts custom content."""
import PyPDF2
import pypdf # Upgraded from PyPDF2 to fix CVE-2023-36464
custom = "Custom test content for verification"
path = generate_test_pdf(content=custom)
try:
with open(path, "rb") as f:
reader = PyPDF2.PdfReader(f)
reader = pypdf.PdfReader(f)
text = reader.pages[0].extract_text()
assert "Custom test content" in text
finally:
tests/test_file_splitting.py
+1 -1
View File
@@ -12,7 +12,7 @@ import os
import tempfile
import pytest
from PyPDF2 import PdfReader, PdfWriter
from pypdf import PdfReader, PdfWriter # Upgraded from PyPDF2 to fix CVE-2023-36464
from app.utils.file_splitting import should_split_file, split_pdf_by_size