feat: Add parser tests (closes #177)

scripts/gitea_issue_parser.py

@@ -0,0 +1,131 @@
+#!/usr/bin/env python3
+"""
+Gitea Issue Body Parser — Extract structured data from markdown issue bodies.
+
+Usage:
+    cat issue_body.txt | python3 scripts/gitea_issue_parser.py --stdin --pretty
+    python3 scripts/gitea_issue_parser.py --url https://forge.../api/v1/repos/.../issues/123 --pretty
+    python3 scripts/gitea_issue_parser.py body.txt --title "Fix thing (#42)" --labels pipeline extraction
+"""
+
+import argparse
+import json
+import re
+import sys
+from typing import Dict, List, Any, Optional
+
+
+def parse_issue_body(body: str, title: str = "", labels: List[str] = None) -> Dict[str, Any]:
+    """Parse a Gitea issue markdown body into structured JSON.
+    
+    Extracted fields:
+    - title: Issue title
+    - context: Background/description section
+    - criteria[]: Acceptance criteria (checkboxes or numbered lists)
+    - labels[]: Issue labels
+    - epic_ref: Parent/epic issue reference (from "Closes #N" or title)
+    - sections{}: All ## sections as key-value pairs
+    """
+    result = {
+        "title": title,
+        "context": "",
+        "criteria": [],
+        "labels": labels or [],
+        "epic_ref": None,
+        "sections": {},
+    }
+    
+    if not body:
+        return result
+    
+    # Extract epic reference from title or body
+    epic_patterns = [
+        r"(?:closes|fixes|addresses|refs?)\s+#(\d+)",
+        r"#(\d+)",
+    ]
+    for pattern in epic_patterns:
+        match = re.search(pattern, (title + " " + body).lower())
+        if match:
+            result["epic_ref"] = int(match.group(1))
+            break
+    
+    # Parse ## sections
+    section_pattern = r"^##\s+(.+?)$\n((?:^(?!##\s).*$\n?)*)"
+    for match in re.finditer(section_pattern, body, re.MULTILINE):
+        section_name = match.group(1).strip().lower().replace(" ", "_")
+        section_content = match.group(2).strip()
+        result["sections"][section_name] = section_content
+    
+    # Extract acceptance criteria (checkboxes)
+    checkbox_pattern = r"^\s*-\s*\[([ xX])\]\s*(.+)$"
+    for match in re.finditer(checkbox_pattern, body, re.MULTILINE):
+        checked = match.group(1).lower() == "x"
+        text = match.group(2).strip()
+        result["criteria"].append({"text": text, "checked": checked})
+    
+    # If no checkboxes, try numbered lists in "Acceptance Criteria" or "Criteria" section
+    if not result["criteria"]:
+        for section_name in ["acceptance_criteria", "criteria", "acceptance criteria"]:
+            if section_name in result["sections"]:
+                numbered = r"^\s*\d+\.\s*(.+)$"
+                for match in re.finditer(numbered, result["sections"][section_name], re.MULTILINE):
+                    result["criteria"].append({"text": match.group(1).strip(), "checked": False})
+                break
+    
+    # Extract context (first section or first paragraph before any ## heading)
+    first_heading = body.find("## ")
+    if first_heading > 0:
+        context_text = body[:first_heading].strip()
+    else:
+        context_text = body.split("\n\n")[0].strip()
+    # Clean up: remove "## Context" or "## Problem" header if present
+    context_text = re.sub(r"^#+\s*\w+\s*\n?", "", context_text).strip()
+    result["context"] = context_text[:500]  # Cap at 500 chars
+    
+    return result
+
+
+def fetch_issue_from_url(url: str) -> Dict[str, Any]:
+    """Fetch an issue from a Gitea API URL and parse it."""
+    import urllib.request
+    req = urllib.request.Request(url, headers={"Accept": "application/json"})
+    with urllib.request.urlopen(req) as resp:
+        data = json.loads(resp.read())
+    
+    return parse_issue_body(
+        body=data.get("body", ""),
+        title=data.get("title", ""),
+        labels=[l["name"] for l in data.get("labels", [])]
+    )
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Parse Gitea issue markdown into structured JSON")
+    parser.add_argument("file", nargs="?", help="Issue body file (or use --stdin)")
+    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
+    parser.add_argument("--url", help="Gitea API URL to fetch issue from")
+    parser.add_argument("--title", default="", help="Issue title")
+    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()
+    
+    if args.url:
+        result = fetch_issue_from_url(args.url)
+    elif args.stdin:
+        body = sys.stdin.read()
+        result = parse_issue_body(body, args.title, args.labels)
+    elif args.file:
+        with open(args.file) 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/knowledge_staleness_check.py

@@ -1,221 +0,0 @@
-#!/usr/bin/env python3
-"""
-Knowledge Store Staleness Detector
-
-Checks knowledge entries against their source files to detect staleness.
-An entry is stale when its source file has been modified since extraction.
-
-Usage:
-  python3 scripts/knowledge_staleness_check.py knowledge/index.json
-  python3 scripts/knowledge_staleness_check.py --repo /path/to/repo --index knowledge/index.json
-  python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
-
-Expected index.json format:
-{
-  "version": 1,
-  "facts": [
-    {
-      "fact": "...",
-      "category": "fact|pitfall|pattern|tool-quirk",
-      "repo": "repo-name",
-      "confidence": 0.8,
-      "source_file": "path/to/file.py",
-      "source_hash": "sha256:abcdef...",
-      "extracted_at": "2026-04-13T20:00:00Z"
-    }
-  ]
-}
-"""
-
-import argparse
-import hashlib
-import json
-import sys
-from pathlib import Path
-from typing import Optional
-
-
-def compute_file_hash(filepath: str) -> Optional[str]:
-    """Compute SHA-256 hash of a file. Returns None if file not found."""
-    path = Path(filepath)
-    if not path.exists():
-        return None
-    content = path.read_bytes()
-    return hashlib.sha256(content).hexdigest()[:16]
-
-
-def check_staleness(index_path: str, repo_root: str = None) -> dict:
-    """Check all entries in the knowledge index for staleness."""
-    index = Path(index_path)
-    if not index.exists():
-        return {"error": f"Index not found: {index_path}"}
-
-    data = json.loads(index.read_text())
-    facts = data.get("facts", [])
-
-    if not facts:
-        return {
-            "total": 0,
-            "stale": 0,
-            "fresh": 0,
-            "no_source": 0,
-            "missing_files": 0,
-            "stale_entries": [],
-        }
-
-    # Determine repo root
-    if repo_root:
-        root = Path(repo_root)
-    else:
-        root = index.parent.parent  # knowledge/index.json -> repo root
-
-    results = {
-        "total": len(facts),
-        "stale": 0,
-        "fresh": 0,
-        "no_source": 0,
-        "missing_files": 0,
-        "stale_entries": [],
-    }
-
-    for i, entry in enumerate(facts):
-        source_file = entry.get("source_file")
-        stored_hash = entry.get("source_hash")
-
-        if not source_file:
-            results["no_source"] += 1
-            continue
-
-        if not stored_hash:
-            # Entry has source file but no hash — consider stale
-            results["stale"] += 1
-            results["stale_entries"].append({
-                "index": i,
-                "fact": entry.get("fact", "")[:100],
-                "source_file": source_file,
-                "reason": "no_hash",
-            })
-            continue
-
-        # Compute current hash
-        full_path = root / source_file
-        current_hash = compute_file_hash(str(full_path))
-
-        if current_hash is None:
-            results["missing_files"] += 1
-            results["stale_entries"].append({
-                "index": i,
-                "fact": entry.get("fact", "")[:100],
-                "source_file": source_file,
-                "reason": "file_missing",
-            })
-        elif current_hash != stored_hash:
-            results["stale"] += 1
-            results["stale_entries"].append({
-                "index": i,
-                "fact": entry.get("fact", "")[:100],
-                "source_file": source_file,
-                "stored_hash": stored_hash,
-                "current_hash": current_hash,
-                "reason": "hash_mismatch",
-            })
-        else:
-            results["fresh"] += 1
-
-    return results
-
-
-def add_hashes_to_index(index_path: str, repo_root: str = None) -> dict:
-    """Add source hashes to entries that are missing them."""
-    index = Path(index_path)
-    data = json.loads(index.read_text())
-    facts = data.get("facts", [])
-
-    if repo_root:
-        root = Path(repo_root)
-    else:
-        root = index.parent.parent
-
-    updated = 0
-    skipped = 0
-
-    for entry in facts:
-        source_file = entry.get("source_file")
-        if not source_file or entry.get("source_hash"):
-            skipped += 1
-            continue
-
-        full_path = root / source_file
-        file_hash = compute_file_hash(str(full_path))
-        if file_hash:
-            entry["source_hash"] = file_hash
-            updated += 1
-
-    if updated > 0:
-        index.write_text(json.dumps(data, indent=2) + "\n")
-
-    return {"updated": updated, "skipped": skipped, "total": len(facts)}
-
-
-def report_staleness(results: dict) -> str:
-    """Format staleness check results as a report."""
-    lines = []
-    lines.append("=" * 50)
-    lines.append("KNOWLEDGE STORE STALENESS REPORT")
-    lines.append("=" * 50)
-    lines.append(f"Total entries:  {results['total']}")
-    lines.append(f"Fresh:          {results['fresh']}")
-    lines.append(f"Stale:          {results['stale']}")
-    lines.append(f"No source:      {results['no_source']}")
-    lines.append(f"Missing files:  {results['missing_files']}")
-    lines.append("")
-
-    if results["stale_entries"]:
-        lines.append("STALE ENTRIES:")
-        lines.append("-" * 50)
-        for entry in results["stale_entries"]:
-            lines.append(f"  [{entry['reason']}] {entry['source_file']}")
-            lines.append(f"    {entry['fact']}")
-            if entry.get("stored_hash") and entry.get("current_hash"):
-                lines.append(f"    stored:  {entry['stored_hash']}")
-                lines.append(f"    current: {entry['current_hash']}")
-            lines.append("")
-
-    if results["total"] > 0:
-        staleness_pct = results["stale"] / results["total"] * 100
-        lines.append(f"Staleness rate: {staleness_pct:.1f}%")
-    else:
-        lines.append("No entries to check.")
-
-    return "\n".join(lines)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Check knowledge store for stale entries")
-    parser.add_argument("--index", default="knowledge/index.json", help="Path to index.json")
-    parser.add_argument("--repo", help="Repository root (default: auto-detect from index path)")
-    parser.add_argument("--fix", action="store_true", help="Add missing hashes to index")
-    parser.add_argument("--json", action="store_true", help="Output JSON instead of report")
-    args = parser.parse_args()
-
-    if args.fix:
-        result = add_hashes_to_index(args.index, args.repo)
-        if args.json:
-            print(json.dumps(result, indent=2))
-        else:
-            print(f"Updated {result['updated']} entries with source hashes.")
-            print(f"Skipped {result['skipped']} (already had hashes or no source file).")
-    else:
-        results = check_staleness(args.index, args.repo)
-        if "error" in results:
-            print(f"Error: {results['error']}", file=sys.stderr)
-            sys.exit(1)
-
-        if args.json:
-            print(json.dumps(results, indent=2))
-        else:
-            print(report_staleness(results))
-
-
-if __name__ == "__main__":
-    main()

scripts/test_gitea_issue_parser.py

@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+"""Tests for scripts/gitea_issue_parser.py"""
+
+import sys
+import os
+sys.path.insert(0, os.path.dirname(__file__) or ".")
+
+# Import from sibling
+import importlib.util
+spec = importlib.util.spec_from_file_location("parser", os.path.join(os.path.dirname(__file__) or ".", "gitea_issue_parser.py"))
+mod = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(mod)
+parse_issue_body = mod.parse_issue_body
+
+
+def test_basic_parsing():
+    body = """## Context
+
+This is the background info.
+
+## Acceptance Criteria
+
+- [ ] First criterion
+- [x] Second criterion (done)
+
+## What to build
+
+Some description.
+"""
+    result = parse_issue_body(body, title="Test (#42)", labels=["bug"])
+    assert result["title"] == "Test (#42)"
+    assert result["labels"] == ["bug"]
+    assert result["epic_ref"] == 42
+    assert len(result["criteria"]) == 2
+    assert result["criteria"][0]["text"] == "First criterion"
+    assert result["criteria"][0]["checked"] == False
+    assert result["criteria"][1]["checked"] == True
+    assert "context" in result["sections"]
+    print("PASS: test_basic_parsing")
+
+
+def test_numbered_criteria():
+    body = """## Acceptance Criteria
+
+1. First item
+2. Second item
+3. Third item
+"""
+    result = parse_issue_body(body)
+    assert len(result["criteria"]) == 3
+    assert result["criteria"][0]["text"] == "First item"
+    print("PASS: test_numbered_criteria")
+
+
+def test_epic_ref_from_body():
+    body = "Closes #123\n\nSome description."
+    result = parse_issue_body(body)
+    assert result["epic_ref"] == 123
+    print("PASS: test_epic_ref_from_body")
+
+
+def test_empty_body():
+    result = parse_issue_body("")
+    assert result["criteria"] == []
+    assert result["context"] == ""
+    assert result["sections"] == {}
+    print("PASS: test_empty_body")
+
+
+def test_no_sections():
+    body = "Just a plain issue body with no headings."
+    result = parse_issue_body(body)
+    assert result["context"] == "Just a plain issue body with no headings."
+    print("PASS: test_no_sections")
+
+
+def test_multiple_sections():
+    body = """## Problem
+
+Something is broken.
+
+## Fix
+
+Do this instead.
+
+## Notes
+
+Additional info.
+"""
+    result = parse_issue_body(body)
+    assert "problem" in result["sections"]
+    assert "fix" in result["sections"]
+    assert "notes" in result["sections"]
+    assert "Something is broken" in result["sections"]["problem"]
+    print("PASS: test_multiple_sections")
+
+
+def run_all():
+    test_basic_parsing()
+    test_numbered_criteria()
+    test_epic_ref_from_body()
+    test_empty_body()
+    test_no_sections()
+    test_multiple_sections()
+    print("\nAll 6 tests passed!")
+
+
+if __name__ == "__main__":
+    run_all()