test: add tests for issue body parser (#90)

scripts/dependency_graph.py

@@ -1,249 +0,0 @@
-#!/usr/bin/env python3
-"""
-Cross-Repo Dependency Graph Builder
-
-Scans repos for import/require/reference patterns and builds a directed
-dependency graph. Detects circular dependencies. Outputs DOT and Mermaid.
-
-Usage:
-  python3 scripts/dependency_graph.py /path/to/repos/
-  python3 scripts/dependency_graph.py --repos repo1,repo2,repo3 --format mermaid
-  python3 scripts/dependency_graph.py --repos-dir /path/to/ --format dot --output deps.dot
-
-Patterns detected:
-  - Python: import X, from X import Y
-  - JavaScript: require("X"), import ... from "X"
-  - Go: import "X"
-  - Ansible: include_role, import_role
-  - Docker/Compose: image: X, depends_on
-  - Config references: repo-name in YAML/TOML/JSON
-"""
-
-import argparse
-import json
-import os
-import re
-import sys
-from collections import defaultdict
-from pathlib import Path
-
-
-# Known repo names for matching
-KNOWN_REPOS = [
-    "hermes-agent", "timmy-config", "timmy-home", "the-nexus", "the-door",
-    "the-beacon", "fleet-ops", "burn-fleet", "timmy-dispatch", "turboquant",
-    "compounding-intelligence", "the-playground", "second-son-of-timmy",
-    "ai-safety-review", "the-echo-pattern", "timmy-academy", "wolf",
-    "the-testament",
-]
-
-
-def normalize_repo_name(name: str) -> str:
-    """Normalize a repo name for comparison."""
-    return name.lower().replace("_", "-").replace(".git", "").strip()
-
-
-def scan_file_for_deps(filepath: str, content: str, own_repo: str) -> set:
-    """Scan a file's content for references to other repos."""
-    deps = set()
-    own_norm = normalize_repo_name(own_repo)
-
-    for repo in KNOWN_REPOS:
-        repo_norm = normalize_repo_name(repo)
-        if repo_norm == own_norm:
-            continue
-
-        # Direct name references
-        patterns = [
-            repo,  # exact name
-            repo.replace("-", "_"),  # underscore variant
-            repo.replace("-", ""),  # no separator
-            f"/{repo}/",  # path reference
-            f'"{repo}"',  # quoted
-            f"'{repo}'",  # single quoted
-            f"Timmy_Foundation/{repo}",  # full Gitea path
-            f"Timmy_Foundation.{repo}",  # Python module path
-        ]
-
-        for pattern in patterns:
-            if pattern in content:
-                deps.add(repo)
-                break
-
-    return deps
-
-
-def scan_repo(repo_path: str, repo_name: str = None) -> dict:
-    """Scan a repo directory for dependencies."""
-    path = Path(repo_path)
-    if not path.is_dir():
-        return {"error": f"Not a directory: {repo_path}"}
-
-    if not repo_name:
-        repo_name = path.name
-
-    deps = set()
-    files_scanned = 0
-    exts = {".py", ".js", ".ts", ".go", ".yaml", ".yml", ".toml", ".json",
-            ".md", ".sh", ".bash", ".Dockerfile", ".tf", ".hcl"}
-
-    for fpath in path.rglob("*"):
-        if not fpath.is_file():
-            continue
-        if fpath.suffix not in exts:
-            continue
-        # Skip common non-source dirs
-        parts = fpath.parts
-        if any(p in (".git", "node_modules", "__pycache__", ".venv", "venv",
-                      "vendor", "dist", "build", ".tox") for p in parts):
-            continue
-
-        try:
-            content = fpath.read_text(errors="ignore")
-        except:
-            continue
-
-        file_deps = scan_file_for_deps(str(fpath), content, repo_name)
-        deps.update(file_deps)
-        files_scanned += 1
-
-    return {
-        "repo": repo_name,
-        "dependencies": sorted(deps),
-        "files_scanned": files_scanned,
-    }
-
-
-def detect_cycles(graph: dict) -> list:
-    """Detect circular dependencies using DFS."""
-    cycles = []
-    visited = set()
-    rec_stack = set()
-
-    def dfs(node, path):
-        visited.add(node)
-        rec_stack.add(node)
-
-        for neighbor in graph.get(node, {}).get("dependencies", []):
-            if neighbor not in visited:
-                result = dfs(neighbor, path + [neighbor])
-                if result:
-                    return result
-            elif neighbor in rec_stack:
-                cycle_start = path.index(neighbor)
-                return path[cycle_start:] + [neighbor]
-
-        rec_stack.remove(node)
-        return None
-
-    for node in graph:
-        if node not in visited:
-            cycle = dfs(node, [node])
-            if cycle:
-                cycles.append(cycle)
-
-    return cycles
-
-
-def to_dot(graph: dict) -> str:
-    """Generate DOT format output."""
-    lines = ["digraph dependencies {"]
-    lines.append("  rankdir=LR;")
-    lines.append("  node [shape=box, style=filled, fillcolor="#1a1a2e", fontcolor="#e6edf3"];")
-    lines.append("  edge [color="#4a4a6a"];")
-    lines.append("")
-
-    for repo, data in sorted(graph.items()):
-        dep_count = len(data.get("dependencies", []))
-        fill = "#2d1b69" if dep_count > 2 else "#16213e"
-        lines.append(f'  "{repo}" [fillcolor="{fill}"];')
-        for dep in data.get("dependencies", []):
-            lines.append(f'  "{repo}" -> "{dep}";')
-
-    lines.append("}")
-    return "\n".join(lines)
-
-
-def to_mermaid(graph: dict) -> str:
-    """Generate Mermaid format output."""
-    lines = ["graph LR"]
-
-    for repo, data in sorted(graph.items()):
-        for dep in data.get("dependencies", []):
-            lines.append(f"    {repo.replace('-','_')} --> {dep.replace('-','_')}")
-
-    # Add node labels
-    lines.append("")
-    for repo in sorted(graph.keys()):
-        lines.append(f"    {repo.replace('-','_')}[{repo}]")
-
-    return "\n".join(lines)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Build cross-repo dependency graph")
-    parser.add_argument("repos_dir", nargs="?", help="Directory containing repos")
-    parser.add_argument("--repos", help="Comma-separated list of repo paths")
-    parser.add_argument("--format", choices=["dot", "mermaid", "json"], default="json")
-    parser.add_argument("--output", "-o", help="Output file (default: stdout)")
-    parser.add_argument("--cycles-only", action="store_true", help="Only report cycles")
-    args = parser.parse_args()
-
-    results = {}
-    repo_paths = []
-
-    if args.repos:
-        repo_paths = [p.strip() for p in args.repos.split(",")]
-    elif args.repos_dir:
-        base = Path(args.repos_dir)
-        repo_paths = [str(p) for p in base.iterdir() if p.is_dir() and not p.name.startswith(".")]
-    else:
-        parser.print_help()
-        sys.exit(1)
-
-    for rpath in repo_paths:
-        name = Path(rpath).name
-        print(f"Scanning {name}...", file=sys.stderr)
-        result = scan_repo(rpath, name)
-        if "error" not in result:
-            results[name] = result
-
-    # Detect cycles
-    cycles = detect_cycles(results)
-
-    if args.cycles_only:
-        if cycles:
-            print("CIRCULAR DEPENDENCIES DETECTED:")
-            for cycle in cycles:
-                print(f"  {' -> '.join(cycle)}")
-            sys.exit(1)
-        else:
-            print("No circular dependencies found.")
-            sys.exit(0)
-
-    # Output
-    output = {}
-    if args.format == "dot":
-        output = to_dot(results)
-    elif args.format == "mermaid":
-        output = to_mermaid(results)
-    else:
-        output = json.dumps({
-            "repos": results,
-            "cycles": cycles,
-            "summary": {
-                "total_repos": len(results),
-                "total_deps": sum(len(r["dependencies"]) for r in results.values()),
-                "cycles_found": len(cycles),
-            }
-        }, indent=2)
-
-    if args.output:
-        Path(args.output).write_text(output)
-        print(f"Written to {args.output}", file=sys.stderr)
-    else:
-        print(output)
-
-
-if __name__ == "__main__":
-    main()

scripts/gitea_issue_parser.py

@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+"""
+Gitea Issue Body Parser
+
+Extracts structured data from Gitea issue markdown bodies:
+- Title
+- Context section
+- Acceptance criteria (checkboxes)
+- Labels
+- Epic/parent references
+
+Usage:
+  python3 scripts/gitea_issue_parser.py <issue_body.txt
+  python3 scripts/gitea_issue_parser.py --url https://forge.../api/v1/repos/.../issues/123
+  echo "issue body" | python3 scripts/gitea_issue_parser.py --stdin
+
+Output: JSON with {title, context, criteria[], labels[], epic_ref}
+"""
+
+import argparse
+import json
+import re
+import sys
+from typing import Optional
+
+
+def parse_issue_body(body: str, title: str = "", labels: list = None) -> dict:
+    """Parse a Gitea issue body into structured JSON."""
+    result = {
+        "title": title,
+        "context": "",
+        "criteria": [],
+        "labels": labels or [],
+        "epic_ref": None,
+        "sections": {},
+    }
+
+    if not body:
+        return result
+
+    # Extract epic/parent reference from title or body
+    epic_pattern = r"#(\d+)"
+    title_refs = re.findall(epic_pattern, title)
+    body_refs = re.findall(epic_pattern, body[:200])  # Check early body refs
+
+    # Look for "Closes #N" or "Part of #N" or "Epic: #N"
+    close_match = re.search(r"(?:Closes?|Fixes?|Resolves?)\s+#(\d+)", body, re.IGNORECASE)
+    part_match = re.search(r"(?:Part of|Epic|Parent|Blocks?)\s+#(\d+)", body, re.IGNORECASE)
+
+    if close_match:
+        result["epic_ref"] = f"#{close_match.group(1)}"
+    elif part_match:
+        result["epic_ref"] = f"#{part_match.group(1)}"
+    elif title_refs:
+        result["epic_ref"] = f"#{title_refs[0]}"
+    elif body_refs:
+        result["epic_ref"] = f"#{body_refs[0]}"
+
+    # Split into sections by ## headers
+    section_pattern = r"^##\s+(.+)$"
+    lines = body.split("\n")
+    current_section = None
+    current_content = []
+
+    for line in lines:
+        header_match = re.match(section_pattern, line)
+        if header_match:
+            # Save previous section
+            if current_section:
+                result["sections"][current_section] = "\n".join(current_content).strip()
+            current_section = header_match.group(1).strip().lower()
+            current_content = []
+        else:
+            current_content.append(line)
+
+    # Save last section
+    if current_section:
+        result["sections"][current_section] = "\n".join(current_content).strip()
+
+    # Extract context
+    for key in ["context", "background", "description", "problem"]:
+        if key in result["sections"]:
+            result["context"] = result["sections"][key]
+            break
+
+    # Extract acceptance criteria (checkboxes)
+    criteria_section = None
+    for key in ["acceptance criteria", "acceptance_criteria", "criteria", "requirements", "definition of done"]:
+        if key in result["sections"]:
+            criteria_section = result["sections"][key]
+            break
+
+    if criteria_section:
+        checkbox_pattern = r"-\s*\[[ xX]?\]\s*(.+)"
+        for match in re.finditer(checkbox_pattern, criteria_section):
+            result["criteria"].append(match.group(1).strip())
+
+        # Also try plain numbered/bulleted lists if no checkboxes found
+        if not result["criteria"]:
+            list_pattern = r"^\s*(?:\d+\.|-|\*)\s+(.+)"
+            for match in re.finditer(list_pattern, criteria_section, re.MULTILINE):
+                result["criteria"].append(match.group(1).strip())
+
+    # If no sectioned criteria found, scan whole body for checkboxes
+    if not result["criteria"]:
+        for match in re.finditer(r"-\s*\[[ xX]?\]\s*(.+)", body):
+            result["criteria"].append(match.group(1).strip())
+
+    return result
+
+
+def parse_from_url(api_url: str, token: str = None) -> dict:
+    """Parse an issue from a Gitea API URL."""
+    import urllib.request
+
+    headers = {}
+    if token:
+        headers["Authorization"] = f"token {token}"
+
+    req = urllib.request.Request(api_url, headers=headers)
+    resp = json.loads(urllib.request.urlopen(req, timeout=30).read())
+
+    title = resp.get("title", "")
+    body = resp.get("body", "")
+    labels = [l["name"] for l in resp.get("labels", [])]
+
+    return parse_issue_body(body, title, labels)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Parse Gitea issue body into structured JSON")
+    parser.add_argument("input", nargs="?", help="Issue body file (or - for stdin)")
+    parser.add_argument("--url", help="Gitea API URL for the issue")
+    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
+    parser.add_argument("--token", help="Gitea API token (or set GITEA_TOKEN env var)")
+    parser.add_argument("--title", default="", help="Issue title (for epic ref extraction)")
+    parser.add_argument("--labels", nargs="*", default=[], help="Issue labels")
+    parser.add_argument("--pretty", action="store_true", help="Pretty-print JSON output")
+    args = parser.parse_args()
+
+    import os
+    token = args.token or os.environ.get("GITEA_TOKEN")
+
+    if args.url:
+        result = parse_from_url(args.url, token)
+    elif args.stdin or (args.input and args.input == "-"):
+        body = sys.stdin.read()
+        result = parse_issue_body(body, args.title, args.labels)
+    elif args.input:
+        with open(args.input) as f:
+            body = f.read()
+        result = parse_issue_body(body, args.title, args.labels)
+    else:
+        parser.print_help()
+        sys.exit(1)
+
+    indent = 2 if args.pretty else None
+    print(json.dumps(result, indent=indent))
+
+
+if __name__ == "__main__":
+    main()

scripts/test_gitea_issue_parser.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+"""Tests for gitea_issue_parser."""
+
+import json
+import sys
+import os
+
+sys.path.insert(0, os.path.dirname(__file__))
+from gitea_issue_parser import parse_issue_body
+
+
+def test_basic_structure():
+    body = """## Context
+This is the background.
+
+## Acceptance Criteria
+- [ ] First criterion
+- [x] Second criterion (already done)
+- [ ] Third criterion
+
+## Labels
+`pipeline`, `extraction`
+"""
+    result = parse_issue_body(body, "Test Issue", ["pipeline", "extraction"])
+    assert result["title"] == "Test Issue"
+    assert "background" in result["context"].lower()
+    assert len(result["criteria"]) == 3
+    assert "First criterion" in result["criteria"]
+    assert result["labels"] == ["pipeline", "extraction"]
+    print("PASS: test_basic_structure")
+
+
+def test_epic_ref():
+    body = "Closes #645\n\nSome description."
+    result = parse_issue_body(body, "feat: thing (#688)")
+    assert result["epic_ref"] == "#645"
+    print("PASS: test_epic_ref")
+
+
+def test_epic_ref_from_title():
+    body = "Some description without close ref."
+    result = parse_issue_body(body, "feat: scene descriptions (#645)")
+    assert result["epic_ref"] == "#645"
+    print("PASS: test_epic_ref_from_title")
+
+
+def test_no_checkboxes():
+    body = """## Requirements
+1. First thing
+2. Second thing
+3. Third thing
+"""
+    result = parse_issue_body(body)
+    assert len(result["criteria"]) == 3
+    print("PASS: test_no_checkboxes")
+
+
+def test_empty_body():
+    result = parse_issue_body("", "Empty Issue")
+    assert result["title"] == "Empty Issue"
+    assert result["criteria"] == []
+    assert result["context"] == ""
+    print("PASS: test_empty_body")
+
+
+def test_real_issue_format():
+    body = """Closes #681
+
+## Changes
+
+Add `#!/usr/bin/env python3` shebang to 6 Python scripts.
+
+## Verification
+
+All 6 files confirmed missing shebangs before fix.
+
+## Impact
+
+Scripts can now be executed directly.
+"""
+    result = parse_issue_body(body, "fix: add python3 shebangs (#685)")
+    assert result["epic_ref"] == "#681"
+    assert "shebang" in result["context"].lower()
+    print("PASS: test_real_issue_format")
+
+
+def test_all_sections_captured():
+    body = """## Context
+Background info.
+
+## Acceptance Criteria
+- [ ] Do thing
+
+## Labels
+`test`
+"""
+    result = parse_issue_body(body)
+    assert "context" in result["sections"]
+    assert "acceptance criteria" in result["sections"]
+    print("PASS: test_all_sections_captured")
+
+
+if __name__ == "__main__":
+    test_basic_structure()
+    test_epic_ref()
+    test_epic_ref_from_title()
+    test_no_checkboxes()
+    test_empty_body()
+    test_real_issue_format()
+    test_all_sections_captured()
+    print("\nAll tests passed.")