Updated test suite to deal with missing file issues

.github/scripts/setup_test_data.py

@@ -5,6 +5,7 @@ Creates dummy test files when example data is not available.
 """
 
 import os
+import sys
 
 import pandas as pd
 
@@ -19,7 +20,7 @@ def create_directories():
 
 
 def create_dummy_pdf():
-    """Create a dummy PDF for testing."""
+    """Create dummy PDFs for testing."""
 
     # Install reportlab if not available
     try:
@@ -33,9 +34,12 @@ def create_dummy_pdf():
         from reportlab.pdfgen import canvas
 
     try:
+        # Create the main test PDF
         pdf_path = (
             "example_data/example_of_emails_sent_to_a_professor_before_applying.pdf"
         )
+        print(f"Creating PDF: {pdf_path}")
+        print(f"Directory exists: {os.path.exists('example_data')}")
 
         c = canvas.Canvas(pdf_path, pagesize=letter)
         c.drawString(100, 750, "This is a test document for redaction testing.")
@@ -53,15 +57,69 @@ def create_dummy_pdf():
 
         print(f"Created dummy PDF: {pdf_path}")
 
+        # Create Partnership Agreement Toolkit PDF
+        partnership_pdf_path = "example_data/Partnership-Agreement-Toolkit_0_0.pdf"
+        print(f"Creating PDF: {partnership_pdf_path}")
+        c = canvas.Canvas(partnership_pdf_path, pagesize=letter)
+        c.drawString(100, 750, "Partnership Agreement Toolkit")
+        c.drawString(100, 700, "This is a test partnership agreement document.")
+        c.drawString(100, 650, "Contact: partnership@example.com")
+        c.drawString(100, 600, "Phone: (555) 123-4567")
+        c.drawString(100, 550, "Address: 123 Partnership Street, City, State 12345")
+        c.showPage()
+
+        # Add second page
+        c.drawString(100, 750, "Page 2 - Partnership Details")
+        c.drawString(100, 700, "More partnership information here.")
+        c.drawString(100, 650, "Contact: info@partnership.org")
+        c.showPage()
+
+        # Add third page
+        c.drawString(100, 750, "Page 3 - Terms and Conditions")
+        c.drawString(100, 700, "Terms and conditions content.")
+        c.drawString(100, 650, "Legal contact: legal@partnership.org")
+        c.save()
+
+        print(f"Created dummy PDF: {partnership_pdf_path}")
+
+        # Create Graduate Job Cover Letter PDF
+        cover_letter_pdf_path = "example_data/graduate-job-example-cover-letter.pdf"
+        print(f"Creating PDF: {cover_letter_pdf_path}")
+        c = canvas.Canvas(cover_letter_pdf_path, pagesize=letter)
+        c.drawString(100, 750, "Cover Letter Example")
+        c.drawString(100, 700, "Dear Hiring Manager,")
+        c.drawString(100, 650, "I am writing to apply for the position.")
+        c.drawString(100, 600, "Contact: applicant@example.com")
+        c.drawString(100, 550, "Phone: (555) 987-6543")
+        c.drawString(100, 500, "Address: 456 Job Street, Employment City, EC 54321")
+        c.drawString(100, 450, "Sincerely,")
+        c.drawString(100, 400, "John Applicant")
+        c.save()
+
+        print(f"Created dummy PDF: {cover_letter_pdf_path}")
+
     except ImportError:
         print("ReportLab not available, skipping PDF creation")
-        # Create a simple text file instead
+        # Create simple text files instead
         with open(
             "example_data/example_of_emails_sent_to_a_professor_before_applying.pdf",
             "w",
         ) as f:
             f.write("This is a dummy PDF file for testing")
-        print("Created dummy text file instead of PDF")
+
+        with open(
+            "example_data/Partnership-Agreement-Toolkit_0_0.pdf",
+            "w",
+        ) as f:
+            f.write("This is a dummy Partnership Agreement PDF file for testing")
+
+        with open(
+            "example_data/graduate-job-example-cover-letter.pdf",
+            "w",
+        ) as f:
+            f.write("This is a dummy cover letter PDF file for testing")
+
+        print("Created dummy text files instead of PDFs")
 
 
 def create_dummy_csv():
@@ -209,6 +267,8 @@ def create_dummy_image():
 def main():
     """Main setup function."""
     print("Setting up test data for GitHub Actions...")
+    print(f"Current working directory: {os.getcwd()}")
+    print(f"Python version: {sys.version}")
 
     create_directories()
     create_dummy_pdf()
@@ -222,7 +282,29 @@ def main():
     print("Created files:")
     for root, dirs, files in os.walk("example_data"):
         for file in files:
-            print(f"  {os.path.join(root, file)}")
+            file_path = os.path.join(root, file)
+            print(f"  {file_path}")
+            # Verify the file exists and has content
+            if os.path.exists(file_path):
+                file_size = os.path.getsize(file_path)
+                print(f"    Size: {file_size} bytes")
+            else:
+                print("    WARNING: File does not exist!")
+
+    # Verify critical files exist
+    critical_files = [
+        "example_data/Partnership-Agreement-Toolkit_0_0.pdf",
+        "example_data/graduate-job-example-cover-letter.pdf",
+        "example_data/example_of_emails_sent_to_a_professor_before_applying.pdf",
+    ]
+
+    print("\nVerifying critical test files:")
+    for file_path in critical_files:
+        if os.path.exists(file_path):
+            file_size = os.path.getsize(file_path)
+            print(f"✅ {file_path} exists ({file_size} bytes)")
+        else:
+            print(f"❌ {file_path} MISSING!")
 
 
 if __name__ == "__main__":

.github/workflows/ci.yml

@@ -89,6 +89,17 @@ jobs:
     - name: Setup test data
       run: |
         python .github/scripts/setup_test_data.py
+        echo "Setup script completed. Checking results:"
+        ls -la example_data/ || echo "example_data directory not found"
+    
+    - name: Verify test data files
+      run: |
+        echo "Checking if critical test files exist:"
+        ls -la example_data/
+        echo "Checking for specific PDF files:"
+        ls -la example_data/*.pdf || echo "No PDF files found"
+        echo "Checking file sizes:"
+        find example_data -name "*.pdf" -exec ls -lh {} \;
     
     - name: Clean up problematic config files
       run: |
@@ -161,6 +172,17 @@ jobs:
     - name: Setup test data
       run: |
         python .github/scripts/setup_test_data.py
+        echo "Setup script completed. Checking results:"
+        ls -la example_data/ || echo "example_data directory not found"
+    
+    - name: Verify test data files
+      run: |
+        echo "Checking if critical test files exist:"
+        ls -la example_data/
+        echo "Checking for specific PDF files:"
+        ls -la example_data/*.pdf || echo "No PDF files found"
+        echo "Checking file sizes:"
+        find example_data -name "*.pdf" -exec ls -lh {} \;
     
     - name: Run integration tests
       run: |

.github/workflows/simple-test.yml

@@ -45,6 +45,17 @@ jobs:
     - name: Setup test data
       run: |
         python .github/scripts/setup_test_data.py
+        echo "Setup script completed. Checking results:"
+        ls -la example_data/ || echo "example_data directory not found"
+    
+    - name: Verify test data files
+      run: |
+        echo "Checking if critical test files exist:"
+        ls -la example_data/
+        echo "Checking for specific PDF files:"
+        ls -la example_data/*.pdf || echo "No PDF files found"
+        echo "Checking file sizes:"
+        find example_data -name "*.pdf" -exec ls -lh {} \;
     
     - name: Run CLI tests
       run: |

cli_redact.py

@@ -636,6 +636,21 @@ python cli_redact.py --task textract --textract_action list
             if isinstance(args.input_file, str):
                 args.input_file = [args.input_file]
 
+            # Debug: Print file path information
+            input_file_path = args.input_file[0]
+            print(f"Debug: Input file path: {input_file_path}")
+            print(f"Debug: File exists: {os.path.exists(input_file_path)}")
+            print(f"Debug: Absolute path: {os.path.abspath(input_file_path)}")
+            if os.path.exists(input_file_path):
+                print(f"Debug: File size: {os.path.getsize(input_file_path)} bytes")
+            else:
+                print(
+                    f"Debug: File not found! Current working directory: {os.getcwd()}"
+                )
+                print(
+                    f"Debug: Directory contents: {os.listdir(os.path.dirname(input_file_path) if os.path.dirname(input_file_path) else '.')}"
+                )
+
             _, file_extension = os.path.splitext(args.input_file[0])
             file_extension = file_extension.lower()
         else:

test/test.py

@@ -500,6 +500,18 @@ class TestCLIRedactExamples(unittest.TestCase):
         print(f"Example data directory: {cls.example_data_dir}")
         print(f"Temp output directory: {cls.temp_output_dir}")
 
+        # Debug: Check if example data directory exists and list contents
+        if os.path.exists(cls.example_data_dir):
+            print("Example data directory exists. Contents:")
+            for item in os.listdir(cls.example_data_dir):
+                item_path = os.path.join(cls.example_data_dir, item)
+                if os.path.isfile(item_path):
+                    print(f"  File: {item} ({os.path.getsize(item_path)} bytes)")
+                else:
+                    print(f"  Directory: {item}")
+        else:
+            print(f"Example data directory does not exist: {cls.example_data_dir}")
+
     @classmethod
     def tearDownClass(cls):
         """Clean up test environment after running tests."""

tools/file_redaction.py

@@ -3954,6 +3954,21 @@ def redact_text_pdf(
         )
         nlp_analyser.registry.add_recognizer(new_custom_fuzzy_recogniser)
 
+    # Debug: Print file path information before opening
+    print(f"Debug: Attempting to open PDF file: {file_path}")
+    print(f"Debug: File exists: {os.path.exists(file_path)}")
+    print(f"Debug: Absolute path: {os.path.abspath(file_path)}")
+    if os.path.exists(file_path):
+        print(f"Debug: File size: {os.path.getsize(file_path)} bytes")
+    else:
+        print(f"Debug: File not found! Current working directory: {os.getcwd()}")
+        print(
+            f"Debug: Directory contents: {os.listdir(os.path.dirname(file_path) if os.path.dirname(file_path) else '.')}"
+        )
+        raise FileNotFoundError(
+            f"Failed to open file '{file_path}'. File does not exist."
+        )
+
     # Open with Pikepdf to get text lines
     pikepdf_pdf = Pdf.open(file_path)
     number_of_pages = len(pikepdf_pdf.pages)