@ngocsangairvds/vsaf 3.2.13 → 3.2.15

package/tools/vds-scripts/pdf_orchestrator/pyproject.toml

@@ -1,87 +0,0 @@
-[project]
-name = "vds-pdf-orchestrator"
-version = "0.1.0"
-description = "PDF manipulation orchestrator for VDS platform with security-first approach"
-readme = "README.md"
-requires-python = ">=3.13"
-# Pruned 2026-04-25: only the 8 deps that are actually imported in src/ are
-# kept. Removed 33 phantom deps (presidio + spaCy stack, pymupdf, weasyprint
-# extras, etc.) — see git log for the full diff. The largest impact: drops
-# stpyv8 (V8 bindings, no arm64 wheels for cp313/cp314) which had blocked
-# the pdf and audit container builds on Apple Silicon.
-dependencies = [
-    "vds-cli-common",
-    "markdown>=3.10",          # markdown_to_html in cli
-    "pydantic>=2.12.5",        # config models
-    "pydantic-settings>=2.12.0", # BaseSettings for config
-    "pypdf>=6.4.0",            # PdfReader/PdfWriter (PyPDF2 successor)
-    "reportlab>=4.4.5",        # canvas + pdfmetrics + pagesizes
-    "rich>=14.3.3",            # Console + Table for CLI output
-    "typer>=0.24.1",           # CLI framework
-    "weasyprint>=66.0",        # HTML→PDF conversion
-]
-
-[project.optional-dependencies]
-# Re-add deps here when actually importing them. Examples:
-#   pii = ["presidio-analyzer", "presidio-anonymizer", "spacy", "en-core-web-lg"]
-#   ocr = ["pdf2image", "pillow"]
-#   advanced-extraction = ["pdfplumber", "pymupdf", "pymupdf4llm"]
-dev = [
-    "pytest>=9.0.2",
-    "pytest-asyncio>=1.3.0",
-    "pytest-cov>=7.0.0",
-    "ruff>=0.14.11",
-    "mypy>=1.18.2",
-]
-
-[project.scripts]
-vds-pdf = "vds_pdf_orchestrator.cli:app"
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-[tool.hatch.build.targets.wheel]
-packages = ["src/vds_pdf_orchestrator"]
-
-[tool.hatch.metadata]
-allow-direct-references = true
-
-[tool.pytest.ini_options]
-testpaths = ["tests"]
-python_files = ["test_*.py"]
-python_classes = ["Test*"]
-python_functions = ["test_*"]
-addopts = "-v --tb=short --strict-markers"
-markers = [
-    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
-    "integration: marks tests as integration tests",
-    "security: marks tests as security-focused tests",
-]
-
-[tool.coverage.run]
-source = ["src"]
-omit = ["*/tests/*", "*/test_*"]
-
-[tool.coverage.report]
-exclude_lines = [
-    "pragma: no cover",
-    "def __repr__",
-    "raise AssertionError",
-    "raise NotImplementedError",
-]
-
-[dependency-groups]
-dev = [
-    "pytest>=9.0.2",
-    "pytest-asyncio>=1.3.0",
-    "pytest-cov>=7.0.0",
-    "pytest-html>=4.1.1",
-    "ruff>=0.14.11",
-    "yamllint>=1.37.1",
-    "black>=26.1.0",
-    "mypy>=1.19.1",
-]
-
-[tool.uv.sources]
-vds-cli-common = { workspace = true }

package/tools/vds-scripts/pdf_orchestrator/pytest.ini

@@ -1,71 +0,0 @@
-[tool:pytest]
-testpaths = tests
-python_files = test_*.py
-python_classes = Test*
-python_functions = test_*
-addopts =
-    -v
-    --tb=short
-    --strict-markers
-    --strict-config
-    --disable-warnings
-    --color=yes
-    --durations=10
-    --max-fail=10
-    --cov=vds_pdf_orchestrator
-    --cov-report=html
-    --cov-report=xml
-    --cov-report=term-missing
-    --cov-fail-under=80
-    --junitxml=test-reports/junit.xml
-    --html=test-reports/report.html
-    --self-contained-html
-
-markers =
-    unit: marks tests as unit tests
-    integration: marks tests as integration tests
-    e2e: marks tests as end-to-end tests
-    container: marks tests as container tests
-    slow: marks tests as slow running (timeout > 30s)
-    security: marks tests as security-focused
-    performance: marks tests as performance tests
-    requires_docker: marks tests that require Docker
-    requires_redis: marks tests that require Redis
-    requires_internet: marks tests that require internet
-    requires_pdf_processing: marks tests that require PDF processing tools
-
-filterwarnings =
-    ignore::UserWarning
-    ignore::DeprecationWarning
-    ignore::PendingDeprecationWarning
-
-minversion = 6.0
-required_plugins =
-    pytest-cov
-    pytest-html
-    pytest-mock
-
-[tool:coverage:run]
-source = src
-omit =
-    */tests/*
-    */test_*
-    */__pycache__/*
-    */migrations/*
-    */venv/*
-    */env/*
-    */node_modules/*
-
-branch = true
-omit_covered_lines =
-    pragma: no cover
-    def __repr__
-    raise AssertionError
-    raise NotImplementedError
-
-fail_under = 80
-show_missing = true
-skip_covered = false
-
-[tool:coverage:html]
-directory = htmlcov

package/tools/vds-scripts/pdf_orchestrator/ruff.toml

@@ -1,6 +0,0 @@
-line-length = 88
-target-version = "py313"
-
-[lint]
-select = ["E", "F", "W", "I", "N", "B", "C90", "UP"]
-ignore = ["E501", "B008"]

package/tools/vds-scripts/pdf_orchestrator/scripts/debug_security_report.py

@@ -1,59 +0,0 @@
-#!/usr/bin/env python3
-"""Debug script for security report generation."""
-
-import logging
-from datetime import UTC, datetime, timedelta
-
-from vds_pdf_orchestrator.compliance.security_operations import (
-    SecurityEventType,
-    SecurityOperationsCenter,
-    SecuritySeverity,
-    ThreatType,
-)
-
-# Configure logging
-logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
-)
-logger = logging.getLogger(__name__)
-
-# Create SOC
-soc = SecurityOperationsCenter()
-
-# Create test data
-start_time = datetime.now(UTC) - timedelta(hours=2)
-end_time = datetime.now(UTC)
-
-logger.info(f"Time range: {start_time} to {end_time}")
-
-# Create events and incidents
-for i in range(5):
-    logger.info(f"Creating event {i}...")
-    event = soc.log_security_event(
-        event_type=SecurityEventType.AUTHENTICATION_FAILURE,
-        severity=SecuritySeverity.HIGH,
-        event_description=f"Failed login attempt {i}",
-        threat_type=ThreatType.BRUTE_FORCE,
-        source_ip=f"192.168.1.{100 + i}",  # Add source IP
-    )
-    logger(f"  Event timestamp: {event.timestamp}")
-    logger(f"  Event in range: {start_time <= event.timestamp <= end_time}")
-    logger(f"  Source IP: {event.source_ip}")
-
-# Check events in SOC
-logger(f"\nTotal events in SOC: {len(soc._events)}")
-logger(f"Events by ID: {list(soc._events.keys())}")
-
-# Filter events manually
-filtered_events = []
-for event in soc._events.values():
-    if start_time <= event.timestamp <= end_time:
-        filtered_events.append(event)
-        logger(f"Event {event.event_id} is in range: {event.timestamp}")
-
-logger(f"\nFiltered events: {len(filtered_events)}")
-
-# Test report generation
-logger("\nGenerating report...")
-report = soc.generate_security_report(start_time, end_time)
-logger(f"Report total_events: {report['summary']['total_events']}")

package/tools/vds-scripts/pdf_orchestrator/scripts/demo_library_selector.py

@@ -1,109 +0,0 @@
-#!/usr/bin/env python3
-"""
-Demo script for the dynamic library selector implementation.
-
-This script demonstrates the library selector's capabilities including:
-- Dynamic library selection based on operation type
-- Performance recommendations
-- Library information and benchmarking
-- AI workflow detection
-"""
-
-import sys
-from pathlib import Path
-
-# Add src to path for demo
-sys.path.insert(0, str(Path(__file__).parent / "src"))
-
-from vds_pdf_orchestrator.performance.library_selector import (
-    OperationType,
-    create_library_selector,
-    select_library_for_ai_workflow,
-    select_library_for_text_extraction,
-)
-
-from vds_pdf_orchestrator.config import load_settings
-
-
-def demo_library_selection() -> None:
-    """Demonstrate library selection capabilities."""
-
-    # Load settings
-    settings = load_settings()
-    selector = create_library_selector(settings)
-
-    # Demo different operation types
-    operations = [
-        (OperationType.TEXT_EXTRACTION, "Standard text extraction"),
-        (OperationType.AI_WORKFLOW, "AI-powered document processing"),
-        (OperationType.HIGH_VOLUME, "High-volume batch processing"),
-        (OperationType.TABLE_EXTRACTION, "Table extraction"),
-        (OperationType.METADATA_EXTRACTION, "Metadata extraction"),
-    ]
-
-    for operation, _description in operations:
-        library = selector.select_optimal_library(operation)
-        selector.get_performance_recommendations(operation)
-
-    # Demo AI workflow hints
-
-    selector.select_optimal_library(
-        OperationType.TEXT_EXTRACTION, ai_workflow_hint=True
-    )
-
-    selector.select_optimal_library(OperationType.TEXT_EXTRACTION)
-
-    # Demo library information
-
-    for library in ["pymupdf", "pypdfium2", "pymupdf4llm"]:
-        if library in selector._get_available_libraries():
-            selector.get_library_info(library)
-
-
-def demo_convenience_functions() -> None:
-    """Demonstrate convenience functions."""
-
-    settings = load_settings()
-
-    # Text extraction
-    select_library_for_text_extraction(settings)
-
-    # AI workflow text extraction
-    select_library_for_text_extraction(settings, ai_workflow=True)
-
-    # AI workflow
-    select_library_for_ai_workflow(settings)
-
-
-def demo_performance_benchmarks() -> None:
-    """Demonstrate performance benchmarking."""
-
-    benchmarks = {
-        "pypdfium2": {"speed": 0.003, "accuracy": 0.85, "memory_efficiency": 0.95},
-        "pymupdf4llm": {"speed": 0.12, "accuracy": 0.95, "memory_efficiency": 0.80},
-        "pymupdf": {"speed": 0.15, "accuracy": 0.92, "memory_efficiency": 0.85},
-        "pypdf": {"speed": 1.11, "accuracy": 0.88, "memory_efficiency": 0.70},
-    }
-
-    for _library, _metrics in benchmarks.items():
-        pass
-
-
-def main() -> int:
-    """Run the demo."""
-    try:
-        demo_library_selection()
-        demo_convenience_functions()
-        demo_performance_benchmarks()
-
-    except Exception:
-        import traceback
-
-        traceback.print_exc()
-        return 1
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

package/tools/vds-scripts/pdf_orchestrator/scripts/generate_project_stats.py

@@ -1,52 +0,0 @@
-"""
-Generate basic project metrics for documentation accuracy.
-
-Outputs:
-- src Python LOC (non-blank, non-comment)
-- number of test files and test functions
-"""
-
-from __future__ import annotations
-
-import json
-from pathlib import Path
-
-SRC_DIR = Path(__file__).resolve().parent.parent / "src"
-TESTS_DIR = Path(__file__).resolve().parent.parent / "tests"
-
-
-def count_loc(py_path: Path) -> int:
-    lines = 0
-    for line in py_path.read_text(encoding="utf-8").splitlines():
-        stripped = line.strip()
-        if stripped and not stripped.startswith("#"):
-            lines += 1
-    return lines
-
-
-def collect_stats() -> dict[str, int]:
-    src_files = list(SRC_DIR.rglob("*.py"))
-    test_files = list(TESTS_DIR.rglob("*.py"))
-
-    loc = sum(count_loc(p) for p in src_files)
-    test_functions = 0
-    for f in test_files:
-        for line in f.read_text(encoding="utf-8").splitlines():
-            if line.lstrip().startswith("def test_"):
-                test_functions += 1
-
-    return {
-        "src_files": len(src_files),
-        "tests_files": len(test_files),
-        "loc": loc,
-        "test_functions": test_functions,
-    }
-
-
-def main() -> None:
-    stats = collect_stats()
-    print(json.dumps(stats, indent=2))
-
-
-if __name__ == "__main__":
-    main()

package/tools/vds-scripts/pdf_orchestrator/scripts/generate_styled_pdf.py

@@ -1,95 +0,0 @@
-import markdown
-from weasyprint import CSS, HTML
-
-
-def create_styled_pdf(markdown_file, output_pdf):
-    """
-    Reads a Markdown file, converts it to styled HTML, and generates a PDF.
-    """
-    # --- 1. Read Markdown Content ---
-    try:
-        with open(markdown_file, encoding="utf-8") as f:
-            md_content = f.read()
-    except FileNotFoundError:
-        print(f"Error: Markdown file not found at {markdown_file}")
-        return
-
-    # --- 2. Convert Markdown to HTML ---
-    # Using extensions for better compatibility, e.g., for tables
-    html_content = markdown.markdown(md_content, extensions=["tables", "fenced_code"])
-
-    # --- 3. Apply Professional CSS Styling ---
-    # This CSS is designed for professional reports, with better fonts and spacing.
-    # It uses common system fonts that are likely to support a wide range of characters.
-    css_styles = """
-    @page {
-        size: A4;
-        margin: 2cm;
-    }
-    body {
-        font-family: 'Helvetica Neue', Arial, sans-serif;
-        line-height: 1.5;
-        color: #333;
-    }
-    h1, h2, h3, h4, h5, h6 {
-        font-family: 'Georgia', serif;
-        color: #2c3e50;
-        margin-top: 1.5em;
-        margin-bottom: 0.5em;
-    }
-    h1 { border-bottom: 2px solid #ddd; padding-bottom: 5px; }
-    h2 { border-bottom: 1px solid #eee; padding-bottom: 5px; }
-    p {
-        margin-bottom: 1em;
-    }
-    code {
-        font-family: 'Menlo', 'Monaco', 'Courier New', monospace;
-        background-color: #f8f8f8;
-        padding: 2px 4px;
-        border-radius: 3px;
-        font-size: 0.9em;
-    }
-    pre {
-        background-color: #f8f8f8;
-        border: 1px solid #ddd;
-        border-radius: 4px;
-        padding: 1em;
-        overflow-x: auto;
-    }
-    pre code {
-        background-color: transparent;
-        padding: 0;
-        border-radius: 0;
-        font-size: 0.9em;
-    }
-    table {
-        width: 100%;
-        border-collapse: collapse;
-        margin: 1em 0;
-    }
-    th, td {
-        border: 1px solid #ddd;
-        padding: 8px;
-        text-align: left;
-    }
-    th {
-        background-color: #f2f2f2;
-        font-weight: bold;
-    }
-    tr:nth-child(even) {
-        background-color: #f9f9f9;
-    }
-    """
-
-    # --- 4. Generate PDF with WeasyPrint ---
-    try:
-        html = HTML(string=html_content)
-        css = CSS(string=css_styles)
-        html.write_pdf(output_pdf, stylesheets=[css])
-        print(f"Successfully generated PDF: {output_pdf}")
-    except Exception as e:
-        print(f"Error during PDF generation with WeasyPrint: {e}")
-
-
-if __name__ == "__main__":
-    create_styled_pdf("AGENTS.md", "AGENTS_styled.pdf")