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

@@ -1,131 +0,0 @@
-#!/usr/bin/env python3
-"""
-Knowledge Store Staleness Detector — Detect stale knowledge entries by comparing source file hashes.
-
-Usage:
-    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json
-    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --json
-    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
-"""
-
-import argparse
-import hashlib
-import json
-import os
-import sys
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Dict, List, Any, Optional
-
-
-def compute_file_hash(filepath: str) -> Optional[str]:
-    """Compute SHA-256 hash of a file. Returns None if file doesn't exist."""
-    try:
-        with open(filepath, "rb") as f:
-            return "sha256:" + hashlib.sha256(f.read()).hexdigest()
-    except (FileNotFoundError, IsADirectoryError, PermissionError):
-        return None
-
-
-def check_staleness(index_path: str, repo_root: str = ".") -> List[Dict[str, Any]]:
-    """Check all entries in knowledge index for staleness.
-    
-    Returns list of entries with staleness info:
-    - status: "fresh" | "stale" | "missing_source" | "no_hash"
-    - current_hash: computed hash (if source exists)
-    - stored_hash: hash from index
-    """
-    with open(index_path) as f:
-        data = json.load(f)
-
-    facts = data.get("facts", [])
-    results = []
-
-    for entry in facts:
-        source_file = entry.get("source_file")
-        stored_hash = entry.get("source_hash")
-
-        if not source_file:
-            results.append({**entry, "status": "no_source", "current_hash": None})
-            continue
-
-        full_path = os.path.join(repo_root, source_file)
-        current_hash = compute_file_hash(full_path)
-
-        if current_hash is None:
-            results.append({**entry, "status": "missing_source", "current_hash": None})
-        elif not stored_hash:
-            results.append({**entry, "status": "no_hash", "current_hash": current_hash})
-        elif current_hash != stored_hash:
-            results.append({**entry, "status": "stale", "current_hash": current_hash})
-        else:
-            results.append({**entry, "status": "fresh", "current_hash": current_hash})
-
-    return results
-
-
-def fix_hashes(index_path: str, repo_root: str = ".") -> int:
-    """Add hashes to entries missing them. Returns count of fixed entries."""
-    with open(index_path) as f:
-        data = json.load(f)
-
-    fixed = 0
-    for entry in data.get("facts", []):
-        if entry.get("source_hash"):
-            continue
-        source_file = entry.get("source_file")
-        if not source_file:
-            continue
-        full_path = os.path.join(repo_root, source_file)
-        h = compute_file_hash(full_path)
-        if h:
-            entry["source_hash"] = h
-            fixed += 1
-
-    with open(index_path, "w") as f:
-        json.dump(data, f, indent=2)
-
-    return fixed
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Check knowledge store staleness")
-    parser.add_argument("--index", required=True, help="Path to knowledge/index.json")
-    parser.add_argument("--repo", default=".", help="Repo root for source file resolution")
-    parser.add_argument("--json", action="store_true", help="Output as JSON")
-    parser.add_argument("--fix", action="store_true", help="Add hashes to entries missing them")
-
-    args = parser.parse_args()
-
-    if args.fix:
-        fixed = fix_hashes(args.index, args.repo)
-        print(f"Fixed {fixed} entries with missing hashes.")
-        return
-
-    results = check_staleness(args.index, args.repo)
-
-    if args.json:
-        print(json.dumps(results, indent=2))
-    else:
-        stale = [r for r in results if r["status"] != "fresh"]
-        fresh = [r for r in results if r["status"] == "fresh"]
-
-        print(f"Knowledge Store Staleness Check")
-        print(f"  Total entries: {len(results)}")
-        print(f"  Fresh: {len(fresh)}")
-        print(f"  Stale/Issues: {len(stale)}")
-        print()
-
-        if stale:
-            print("Issues found:")
-            for r in stale:
-                status = r["status"]
-                fact = r.get("fact", "?")[:60]
-                source = r.get("source_file", "?")
-                print(f"  [{status}] {source}: {fact}")
-        else:
-            print("All entries are fresh!")
-
-
-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()

scripts/test_knowledge_staleness.py

@@ -1,129 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/knowledge_staleness_check.py — 8 tests."""
-
-import json
-import os
-import sys
-import tempfile
-
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-import importlib.util
-spec = importlib.util.spec_from_file_location("ks", os.path.join(os.path.dirname(__file__) or ".", "knowledge_staleness_check.py"))
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-check_staleness = mod.check_staleness
-fix_hashes = mod.fix_hashes
-compute_file_hash = mod.compute_file_hash
-
-
-def test_fresh_entry():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("print('hello')")
-        h = compute_file_hash(src)
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "hello", "source_file": "source.py", "source_hash": h}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "fresh"
-        print("PASS: test_fresh_entry")
-
-
-def test_stale_entry():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("original content")
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "old", "source_file": "source.py", "source_hash": "sha256:wrong"}]}, f)
-        # Now change the source
-        with open(src, "w") as f:
-            f.write("modified content")
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "stale"
-        print("PASS: test_stale_entry")
-
-
-def test_missing_source():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "gone", "source_file": "nonexistent.py", "source_hash": "sha256:abc"}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "missing_source"
-        print("PASS: test_missing_source")
-
-
-def test_no_hash():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("content")
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "no hash", "source_file": "source.py"}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "no_hash"
-        assert results[0]["current_hash"].startswith("sha256:")
-        print("PASS: test_no_hash")
-
-
-def test_no_source_field():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "orphan"}]}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results[0]["status"] == "no_source"
-        print("PASS: test_no_source_field")
-
-
-def test_fix_hashes():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        src = os.path.join(tmpdir, "source.py")
-        with open(src, "w") as f:
-            f.write("content for hashing")
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": [{"fact": "needs hash", "source_file": "source.py"}]}, f)
-        fixed = fix_hashes(idx, tmpdir)
-        assert fixed == 1
-        # Verify hash was added
-        with open(idx) as f:
-            data = json.load(f)
-        assert data["facts"][0]["source_hash"].startswith("sha256:")
-        print("PASS: test_fix_hashes")
-
-
-def test_empty_index():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        idx = os.path.join(tmpdir, "index.json")
-        with open(idx, "w") as f:
-            json.dump({"facts": []}, f)
-        results = check_staleness(idx, tmpdir)
-        assert results == []
-        print("PASS: test_empty_index")
-
-
-def test_compute_hash_nonexistent():
-    h = compute_file_hash("/nonexistent/path/file.py")
-    assert h is None
-    print("PASS: test_compute_hash_nonexistent")
-
-
-def run_all():
-    test_fresh_entry()
-    test_stale_entry()
-    test_missing_source()
-    test_no_hash()
-    test_no_source_field()
-    test_fix_hashes()
-    test_empty_index()
-    test_compute_hash_nonexistent()
-    print("\nAll 8 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()