test/fixtures/generate_fixtures.py

"""
Generate test fixtures for file parser tests
Author: @mangubee
"""

from pathlib import Path

# ============================================================================
# CONFIG
# ============================================================================
FIXTURES_DIR = Path(__file__).parent

# ============================================================================
# Generate PDF
# ============================================================================
def generate_pdf():
    """Generate sample PDF file using fpdf"""
    try:
        from fpdf import FPDF
    except ImportError:
        print("Skipping PDF generation (fpdf not installed)")
        return

    pdf = FPDF()
    pdf.add_page()
    pdf.set_font("Arial", size=12)
    pdf.cell(200, 10, txt="Test PDF Document", ln=True)
    pdf.cell(200, 10, txt="This is page 1 content.", ln=True)
    pdf.add_page()
    pdf.cell(200, 10, txt="Page 2", ln=True)
    pdf.cell(200, 10, txt="This is page 2 content.", ln=True)

    pdf_path = FIXTURES_DIR / "sample.pdf"
    pdf.output(str(pdf_path))

    print(f"Created: {pdf_path}")


# ============================================================================
# Generate Excel
# ============================================================================
def generate_excel():
    """Generate sample Excel file"""
    from openpyxl import Workbook

    wb = Workbook()

    # Sheet 1
    ws1 = wb.active
    ws1.title = "Data"
    ws1.append(["Product", "Price", "Quantity"])
    ws1.append(["Apple", 1.50, 100])
    ws1.append(["Banana", 0.75, 150])
    ws1.append(["Orange", 2.00, 80])

    # Sheet 2
    ws2 = wb.create_sheet("Summary")
    ws2.append(["Total Products", 3])
    ws2.append(["Total Quantity", 330])

    excel_path = FIXTURES_DIR / "sample.xlsx"
    wb.save(excel_path)

    print(f"Created: {excel_path}")


# ============================================================================
# Generate Word
# ============================================================================
def generate_word():
    """Generate sample Word document"""
    from docx import Document

    doc = Document()
    doc.add_heading("Test Word Document", 0)
    doc.add_paragraph("This is the first paragraph.")
    doc.add_paragraph("This is the second paragraph with some content.")
    doc.add_heading("Section 2", level=1)
    doc.add_paragraph("Content in section 2.")

    word_path = FIXTURES_DIR / "sample.docx"
    doc.save(word_path)

    print(f"Created: {word_path}")


# ============================================================================
# Main
# ============================================================================
if __name__ == "__main__":
    print("Generating test fixtures...")
    generate_pdf()
    generate_excel()
    generate_word()
    print("All fixtures generated successfully!")