infrastructure-validation

Validation Module

Quality assurance and content validation tools for research outputs. Covers PDFs, markdown, links, output integrity, and comprehensive audits.

PDF Validation (content/pdf_validator.py)

from infrastructure.validation import validate_pdf_rendering, extract_text_from_pdf, scan_for_issues

# Validate a rendered PDF
results = validate_pdf_rendering(pdf_path)

# Extract text for analysis
text = extract_text_from_pdf(pdf_path)

# Scan for rendering issues
issues = scan_for_issues(text)

CLI:

uv run python -m infrastructure.validation.cli pdf --project {project} --repo-root .

Markdown Validation (markdown_validator.py)

from pathlib import Path

from infrastructure.validation.content.discovery import discover_markdown_files
from infrastructure.validation.content.markdown_validator import (
    collect_symbols,
    validate_images,
    validate_markdown,
    validate_math,
    validate_refs,
)

repo_root = Path(".")
manuscript_dir = repo_root / "projects" / "project" / "manuscript"
md_files = [str(path) for path in discover_markdown_files(manuscript_dir, scope="tree")]
labels, anchors = collect_symbols(md_files)

# Validate all markdown in a directory
problems, exit_code = validate_markdown(manuscript_dir, repo_root)

# Individual checks
image_issues = validate_images(md_files, repo_root)
ref_issues = validate_refs(md_files, repo_root, labels, anchors)
math_issues = validate_math(md_files, repo_root)

CLI:

uv run python -m infrastructure.validation.cli markdown projects/{name}/manuscript/

Output Integrity (integrity/checks.py)

from infrastructure.validation import (
    verify_output_integrity, verify_file_integrity,
    verify_cross_references, verify_data_consistency,
    verify_academic_standards, generate_integrity_report,
)

# Full integrity check
report = verify_output_integrity(output_dir)

# Individual checks
verify_file_integrity(file_path)
verify_cross_references(manuscript_dir)
verify_data_consistency(data_dir)
verify_academic_standards(manuscript_dir)