From 2fa8c2dea363aa6b88cde601d11cc27b92ea3506 Mon Sep 17 00:00:00 2001
From: Alexander Payne <alex@alexanderwhitestone.com>
Date: Sun, 26 Apr 2026 05:10:14 -0400
Subject: [PATCH] scripts: add dependency_inventory script
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add dependency_inventory.py — an inventory tool that scans repos
for dependency manifests (requirements.txt, package.json,
go.mod, Cargo.toml, pyproject.toml) and produces either
JSON or markdown report.

Includes:
- Full parser suite for 5 manifest types
- --repos and --repos-dir argument support
- Incremental friendly — safe to add new features
- --output/-o file support
- Test suite in tests/test_dependency_inventory.py

Closes #107 (1/5) — first script in the Health Report toolkit.
---
 scripts/dependency_inventory.py    | 308 +++++++++++++++++++++++++++++
 tests/test_dependency_inventory.py |  52 +++++
 2 files changed, 360 insertions(+)
 create mode 100644 scripts/dependency_inventory.py
 create mode 100644 tests/test_dependency_inventory.py

diff --git a/scripts/dependency_inventory.py b/scripts/dependency_inventory.py
new file mode 100644
index 0000000..63a6505
--- /dev/null
+++ b/scripts/dependency_inventory.py
@@ -0,0 +1,308 @@
+#!/usr/bin/env python3
+"""
+Dependency Inventory — Scan repos and list third-party dependencies.
+
+Reads: package.json, requirements.txt, go.mod, Cargo.toml, pyproject.toml
+Extracts: package name, version constraint, source file/repo
+Outputs: JSON (default) or markdown table
+
+Usage:
+  python3 scripts/dependency_inventory.py --repos-dir ~/repos/
+  python3 scripts/dependency_inventory.py --repos ~/repo1,~/repo2 --format markdown
+"""
+
+import argparse
+import json
+import os
+import re
+import sys
+from pathlib import Path
+from typing import Dict, List, Any, Optional
+
+# Mapping of file pattern to canonical parser name
+MANIFEST_PATTERNS = {
+    'requirements.txt': 'requirements',
+    'package.json': 'npm',
+    'pyproject.toml': 'pyproject',
+    'go.mod': 'go',
+    'Cargo.toml': 'cargo',
+}
+
+# Parser registry
+PARSERS = {}
+
+
+def register_parser(name: str):
+    """Decorator to register a parser function."""
+    def decorator(fn):
+        PARSERS[name] = fn
+        return fn
+    return decorator
+
+
+# ─── Parsers ────────────────────────────────────────────────────────────────
+
+@register_parser('requirements')
+def parse_requirements(content: str) -> List[Dict[str, str]]:
+    """Parse requirements.txt — one requirement per line."""
+    deps = []
+    for line in content.splitlines():
+        line = line.strip()
+        if not line or line.startswith('#'):
+            continue
+        pkg_spec = re.split(r'[ ;#]', line)[0].strip()
+        if '>=' in pkg_spec:
+            name, ver = pkg_spec.split('>=', 1)
+        elif '==' in pkg_spec:
+            name, ver = pkg_spec.split('==', 1)
+        elif '<=' in pkg_spec:
+            name, ver = pkg_spec.split('<=', 1)
+        elif '~=' in pkg_spec:
+            name, ver = pkg_spec.split('~=', 1)
+        elif '>' in pkg_spec:
+            name, ver = pkg_spec.split('>', 1)
+        elif '<' in pkg_spec:
+            name, ver = pkg_spec.split('<', 1)
+        elif '=' in pkg_spec:
+            name, ver = pkg_spec.split('=', 1)
+        else:
+            name, ver = pkg_spec, ''
+        deps.append({
+            'package': name.strip(),
+            'version': ver.strip(),
+            'constraint': line[len(name):].strip()
+        })
+    return deps
+
+
+@register_parser('npm')
+def parse_package_json(content: str) -> List[Dict[str, str]]:
+    """Parse package.json dependencies."""
+    try:
+        data = json.loads(content)
+    except json.JSONDecodeError:
+        return []
+    deps = []
+    for section in ('dependencies', 'devDependencies', 'peerDependencies', 'optionalDependencies'):
+        for name, ver in data.get(section, {}).items():
+            deps.append({
+                'package': name,
+                'version': ver,
+                'constraint': ver,
+                'type': section
+            })
+    return deps
+
+
+@register_parser('pyproject')
+def parse_pyproject_toml(content: str) -> List[Dict[str, str]]:
+    """Parse pyproject.toml [project] dependencies."""
+    deps = []
+    in_deps = False
+    dep_buffer = ''
+    for line in content.splitlines():
+        stripped = line.strip()
+        if stripped.startswith('dependencies = ['):
+            in_deps = True
+            remainder = stripped.split('=', 1)[1].strip()
+            dep_buffer = remainder[1:] if remainder.startswith('[') else remainder
+            continue
+        if in_deps:
+            if stripped.startswith(']'):
+                in_deps = False
+                continue
+            dep_buffer += ' ' + line
+    dep_buffer = dep_buffer.strip().rstrip(',')
+    for match in re.finditer(r'"([^"]+)"', dep_buffer):
+        spec = match.group(1)
+        m = re.match(r'^([a-zA-Z0-9_.-]+)\s*([<>=!~]+)?\s*(.*)$', spec)
+        if m:
+            name, op, ver = m.groups()
+            deps.append({
+                'package': name,
+                'version': (ver or '').strip(),
+                'constraint': spec
+            })
+    return deps
+
+
+@register_parser('go')
+def parse_go_mod(content: str) -> List[Dict[str, str]]:
+    """Parse go.mod — require statements."""
+    deps = []
+    for line in content.splitlines():
+        line = line.strip()
+        if line.startswith('require ') and not line.startswith('require ('):
+            parts = line.split()
+            if len(parts) >= 3:
+                mod, ver = parts[1], parts[2]
+                deps.append({'package': mod, 'version': ver, 'constraint': ver})
+        elif line.startswith('\t') and '/' in line:
+            parts = line.strip().split()
+            if len(parts) >= 2:
+                mod, ver = parts[0], parts[1]
+                deps.append({'package': mod, 'version': ver, 'constraint': ver})
+    return deps
+
+
+@register_parser('cargo')
+def parse_cargo_toml(content: str) -> List[Dict[str, str]]:
+    """Parse [dependencies] section from Cargo.toml."""
+    deps = []
+    in_deps = False
+    for line in content.splitlines():
+        stripped = line.strip()
+        if stripped in ('[dependencies]', '[dependencies]'):
+            in_deps = True
+            continue
+        if stripped.startswith('['):
+            in_deps = False
+            continue
+        if in_deps and '=' in stripped:
+            name_part, ver_part = stripped.split('=', 1)
+            name = name_part.strip()
+            ver = ver_part.strip().strip('"').strip("'")
+            deps.append({'package': name, 'version': ver, 'constraint': ver})
+    return deps
+
+
+# ─── File Discovery ─────────────────────────────────────────────────────────
+
+def find_manifest_files(root: Path) -> Dict[str, List[Path]]:
+    """Find all manifest files under root."""
+    found = {k: [] for k in MANIFEST_PATTERNS}
+    for pattern in MANIFEST_PATTERNS:
+        for path in root.rglob(pattern):
+            if not any(skip in str(path) for skip in ('.git', 'node_modules', '__pycache__', '.venv', 'venv')):
+                found[pattern].append(path)
+    return found
+
+
+# ─── Main Scanner ────────────────────────────────────────────────────────────
+
+def scan_repo(repo_path: Path) -> Dict[str, Any]:
+    """Scan a single repo directory for dependency manifests."""
+    repo_name = repo_path.name
+    found = find_manifest_files(repo_path)
+    all_deps: List[Dict[str, str]] = []
+    files_scanned = 0
+
+    for pattern, paths in found.items():
+        parser_name = MANIFEST_PATTERNS[pattern]
+        # Map parser_name to function
+        if parser_name == 'requirements':
+            parser = parse_requirements
+        elif parser_name == 'npm':
+            parser = parse_package_json
+        elif parser_name == 'pyproject':
+            parser = parse_pyproject_toml
+        elif parser_name == 'go':
+            parser = parse_go_mod
+        elif parser_name == 'cargo':
+            parser = parse_cargo_toml
+        else:
+            continue
+
+        for fp in paths:
+            try:
+                content = fp.read_text(encoding='utf-8', errors='replace')
+                files_scanned += 1
+                rel = fp.relative_to(repo_path)
+                for dep in parser(content):
+                    dep['source'] = pattern
+                    dep['file'] = str(rel)
+                    dep['repo'] = repo_name
+                    all_deps.append(dep)
+            except Exception as e:
+                print(f"  [WARN] Could not parse {fp}: {e}", file=sys.stderr)
+
+    return {
+        'repo': repo_name,
+        'path': str(repo_path),
+        'files_scanned': files_scanned,
+        'dependencies': all_deps,
+        'dependency_count': len(all_deps),
+    }
+
+
+def scan_repos(repos: List[Path]) -> Dict[str, Any]:
+    """Scan multiple repos and aggregate."""
+    results = {}
+    total_deps = 0
+    total_files = 0
+    for repo in repos:
+        if not repo.is_dir():
+            print(f"[WARN] Skipping {repo}: not a directory", file=sys.stderr)
+            continue
+        print(f"Scanning {repo.name}...", file=sys.stderr)
+        result = scan_repo(repo)
+        results[repo.name] = result
+        total_deps += result['dependency_count']
+        total_files += result['files_scanned']
+    return {
+        'repos': results,
+        'summary': {
+            'total_repos': len(results),
+            'total_files_scanned': total_files,
+            'total_dependencies': total_deps,
+        }
+    }
+
+
+# ─── Output ─────────────────────────────────────────────────────────────────
+
+def output_json(data: Dict[str, Any], out_path: Optional[Path] = None) -> None:
+    text = json.dumps(data, indent=2)
+    if out_path:
+        out_path.write_text(text)
+        print(f"Written: {out_path}", file=sys.stderr)
+    else:
+        print(text)
+
+
+def output_markdown(data: Dict[str, Any], out_path: Optional[Path] = None) -> None:
+    lines = []
+    lines.append("# Dependency Inventory")
+    lines.append("\nGenerated: *(TODO: add timestamp)*")
+    lines.append(f"\n**Summary:** {data['summary']['total_dependencies']} dependencies across {data['summary']['total_repos']} repos")
+    lines.append("")
+    lines.append("| Repo | File | Package | Version |")
+    lines.append("|------|------|---------|---------|")
+    for repo_name, rdata in sorted(data['repos'].items()):
+        for dep in sorted(rdata['dependencies'], key=lambda d: d['package']):
+            lines.append(f"| {repo_name} | {dep['file']} | {dep['package']} | {dep['version']} |")
+    text = '\n'.join(lines) + '\n'
+    if out_path:
+        out_path.write_text(text)
+        print(f"Written: {out_path}", file=sys.stderr)
+    else:
+        print(text)
+
+
+# ─── CLI Entry ────────────────────────────────────────────────────────────────
+
+def main():
+    parser = argparse.ArgumentParser(description="Generate org-wide dependency inventory")
+    parser.add_argument('--repos-dir', help='Directory containing multiple repos')
+    parser.add_argument('--repos', help='Comma-separated list of repo paths')
+    parser.add_argument('--output', '-o', help='Output file (default: stdout)')
+    parser.add_argument('--format', choices=['json', 'markdown'], default='json',
+                       help='Output format (default: json)')
+    args = parser.parse_args()
+    if args.repos:
+        repo_paths = [Path(p.strip()).expanduser() for p in args.repos.split(',')]
+    elif args.repos_dir:
+        base = Path(args.repos_dir).expanduser()
+        repo_paths = [p for p in base.iterdir() if p.is_dir() and not p.name.startswith('.')]
+    else:
+        repo_paths = [Path(__file__).resolve().parent.parent]
+    out_path = Path(args.output).expanduser() if args.output else None
+    data = scan_repos(repo_paths)
+    if args.format == 'json':
+        output_json(data, out_path)
+    else:
+        output_markdown(data, out_path)
+
+
+if __name__ == '__main__':
+    main()
diff --git a/tests/test_dependency_inventory.py b/tests/test_dependency_inventory.py
new file mode 100644
index 0000000..69ceb8d
--- /dev/null
+++ b/tests/test_dependency_inventory.py
@@ -0,0 +1,52 @@
+"""
+Tests for scripts/dependency_inventory.py
+"""
+
+import unittest
+import json
+from pathlib import Path
+import sys
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from scripts.dependency_inventory import (
+    parse_requirements,
+    parse_package_json,
+    parse_pyproject_toml,
+    scan_repo,
+)
+
+
+class TestParseRequirements(unittest.TestCase):
+    def test_parses_simple_requirement(self):
+        result = parse_requirements("requests>=2.33.0")
+        self.assertEqual(len(result), 1)
+        self.assertEqual(result[0]["package"], "requests")
+
+    def test_parses_version_range(self):
+        result = parse_requirements("pytest>=8,<9")
+        self.assertEqual(result[0]["package"], "pytest")
+
+
+class TestParsePackageJson(unittest.TestCase):
+    def test_parses_dependencies(self):
+        content = json.dumps({"name": "test", "dependencies": {"react": "^18.2.0"}})
+        result = parse_package_json(content)
+        self.assertTrue(any(d["package"] == "react" for d in result))
+
+
+class TestParsePyprojectToml(unittest.TestCase):
+    def test_parses_project_dependencies(self):
+        content = "\n[project]\nname = \"test\"\ndependencies = [\n  \"openai>=2.21.0,<3\",\n]"
+        result = parse_pyproject_toml(content)
+        self.assertEqual(len(result), 1)
+
+
+class TestScanRepo(unittest.TestCase):
+    def test_scans_local_repo(self):
+        result = scan_repo(Path(__file__).resolve().parents[1])
+        self.assertGreater(result["dependency_count"], 0)
+
+
+if __name__ == "__main__":
+    unittest.main()
\ No newline at end of file
-- 
2.43.0