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

scripts/dead_code_detector.py

@@ -1,282 +0,0 @@
-#!/usr/bin/env python3
-"""
-Dead Code Detector for Python Codebases
-
-AST-based analysis to find defined but never-called functions and classes.
-Excludes entry points, plugin hooks, __init__ exports.
-
-Usage:
-  python3 scripts/dead_code_detector.py /path/to/repo/
-  python3 scripts/dead_code_detector.py hermes-agent/ --format json
-  python3 scripts/dead_code_detector.py . --exclude tests/,venv/
-
-Output: file:line, function/class name, last git author (if available)
-"""
-
-import argparse
-import ast
-import json
-import os
-import subprocess
-import sys
-from collections import defaultdict
-from pathlib import Path
-from typing import Optional
-
-
-# Names that are expected to be unused (entry points, protocol methods, etc.)
-SAFE_UNUSED_PATTERNS = {
-    # Python dunders
-    "__init__", "__str__", "__repr__", "__eq__", "__hash__", "__len__",
-    "__getitem__", "__setitem__", "__contains__", "__iter__", "__next__",
-    "__enter__", "__exit__", "__call__", "__bool__", "__del__",
-    "__post_init__", "__class_getitem__",
-    # Common entry points
-    "main", "app", "handler", "setup", "teardown", "fixture",
-    # pytest
-    "conftest", "test_", "pytest_",  # prefix patterns
-    # Protocols / abstract
-    "abstractmethod", "abc_",
-}
-
-
-def is_safe_unused(name: str, filepath: str) -> bool:
-    """Check if an unused name is expected to be unused."""
-    # Test files are exempt
-    if "test" in filepath.lower():
-        return True
-
-    # Known patterns
-    for pattern in SAFE_UNUSED_PATTERNS:
-        if name.startswith(pattern) or name == pattern:
-            return True
-
-    # __init__.py exports are often unused internally
-    if filepath.endswith("__init__.py"):
-        return True
-
-    return False
-
-
-def get_git_blame(filepath: str, lineno: int) -> Optional[str]:
-    """Get last author of a line via git blame."""
-    try:
-        result = subprocess.run(
-            ["git", "blame", "-L", f"{lineno},{lineno}", "--porcelain", filepath],
-            capture_output=True, text=True, timeout=5
-        )
-        for line in result.stdout.split("\n"):
-            if line.startswith("author "):
-                return line[7:]
-    except:
-        pass
-    return None
-
-
-class DefinitionCollector(ast.NodeVisitor):
-    """Collect all function and class definitions."""
-
-    def __init__(self):
-        self.definitions = []  # (name, type, lineno, filepath)
-
-    def visit_FunctionDef(self, node):
-        self.definitions.append((node.name, "function", node.lineno))
-        self.generic_visit(node)
-
-    def visit_AsyncFunctionDef(self, node):
-        self.definitions.append((node.name, "async_function", node.lineno))
-        self.generic_visit(node)
-
-    def visit_ClassDef(self, node):
-        self.definitions.append((node.name, "class", node.lineno))
-        self.generic_visit(node)
-
-
-class NameUsageCollector(ast.NodeVisitor):
-    """Collect all name references (calls, imports, attribute access)."""
-
-    def __init__(self):
-        self.names = set()
-        self.calls = set()
-        self.imports = set()
-
-    def visit_Name(self, node):
-        self.names.add(node.id)
-        self.generic_visit(node)
-
-    def visit_Attribute(self, node):
-        if isinstance(node.value, ast.Name):
-            self.names.add(node.value.id)
-        self.generic_visit(node)
-
-    def visit_Call(self, node):
-        if isinstance(node.func, ast.Name):
-            self.calls.add(node.func.id)
-        elif isinstance(node.func, ast.Attribute):
-            if isinstance(node.func.value, ast.Name):
-                self.names.add(node.func.value.id)
-            self.calls.add(node.func.attr)
-        self.generic_visit(node)
-
-    def visit_Import(self, node):
-        for alias in node.names:
-            self.imports.add(alias.asname or alias.name)
-        self.generic_visit(node)
-
-    def visit_ImportFrom(self, node):
-        for alias in node.names:
-            self.imports.add(alias.asname or alias.name)
-        self.generic_visit(node)
-
-
-def analyze_file(filepath: str) -> dict:
-    """Analyze a single Python file for dead code."""
-    path = Path(filepath)
-    try:
-        content = path.read_text()
-        tree = ast.parse(content, filename=str(filepath))
-    except (SyntaxError, UnicodeDecodeError):
-        return {"error": f"Could not parse {filepath}"}
-
-    # Collect definitions
-    def_collector = DefinitionCollector()
-    def_collector.visit(tree)
-    definitions = def_collector.definitions
-
-    # Collect usage
-    usage_collector = NameUsageCollector()
-    usage_collector.visit(tree)
-    used_names = usage_collector.names | usage_collector.calls | usage_collector.imports
-
-    # Also scan the entire repo for references to this file's definitions
-    # (this is done at the repo level, not file level)
-
-    dead = []
-    for name, def_type, lineno in definitions:
-        if name.startswith("_") and not name.startswith("__"):
-            # Private functions — might be used externally, less likely dead
-            pass
-
-        if name not in used_names:
-            if not is_safe_unused(name, filepath):
-                dead.append({
-                    "name": name,
-                    "type": def_type,
-                    "file": filepath,
-                    "line": lineno,
-                })
-
-    return {"definitions": len(definitions), "dead": dead}
-
-
-def scan_repo(repo_path: str, exclude_patterns: list = None) -> dict:
-    """Scan an entire repo for dead code."""
-    path = Path(repo_path)
-    exclude = exclude_patterns or ["venv", ".venv", "node_modules", "__pycache__",
-                                    ".git", "dist", "build", ".tox", "vendor"]
-
-    all_definitions = {}  # name -> [{file, line, type}]
-    all_files = []
-    dead_code = []
-
-    # First pass: collect all definitions across repo
-    for fpath in path.rglob("*.py"):
-        parts = fpath.parts
-        if any(ex in parts for ex in exclude):
-            continue
-        if fpath.name.startswith("."):
-            continue
-
-        try:
-            content = fpath.read_text(errors="ignore")
-            tree = ast.parse(content, filename=str(fpath))
-        except:
-            continue
-
-        all_files.append(str(fpath))
-        collector = DefinitionCollector()
-        collector.visit(tree)
-
-        for name, def_type, lineno in collector.definitions:
-            rel_path = str(fpath.relative_to(path))
-            if name not in all_definitions:
-                all_definitions[name] = []
-            all_definitions[name].append({
-                "file": rel_path,
-                "line": lineno,
-                "type": def_type,
-            })
-
-    # Second pass: check each name for usage across entire repo
-    all_used_names = set()
-    for fpath_str in all_files:
-        try:
-            content = Path(fpath_str).read_text(errors="ignore")
-            tree = ast.parse(content)
-        except:
-            continue
-        usage = NameUsageCollector()
-        usage.visit(tree)
-        all_used_names.update(usage.names)
-        all_used_names.update(usage.calls)
-        all_used_names.update(usage.imports)
-
-    # Find dead code
-    for name, locations in all_definitions.items():
-        if name not in all_used_names:
-            for loc in locations:
-                if not is_safe_unused(name, loc["file"]):
-                    dead_code.append({
-                        "name": name,
-                        "type": loc["type"],
-                        "file": loc["file"],
-                        "line": loc["line"],
-                    })
-
-    return {
-        "repo": path.name,
-        "files_scanned": len(all_files),
-        "total_definitions": sum(len(v) for v in all_definitions.values()),
-        "dead_code_count": len(dead_code),
-        "dead_code": sorted(dead_code, key=lambda x: (x["file"], x["line"])),
-    }
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Find dead code in Python codebases")
-    parser.add_argument("repo", help="Repository path to scan")
-    parser.add_argument("--format", choices=["text", "json"], default="text")
-    parser.add_argument("--exclude", help="Comma-separated patterns to exclude")
-    parser.add_argument("--git-blame", action="store_true", help="Include git blame info")
-    args = parser.parse_args()
-
-    exclude = args.exclude.split(",") if args.exclude else None
-    result = scan_repo(args.repo, exclude)
-
-    if args.format == "json":
-        print(json.dumps(result, indent=2))
-    else:
-        print(f"Dead Code Report: {result['repo']}")
-        print(f"Files scanned: {result['files_scanned']}")
-        print(f"Total definitions: {result['total_definitions']}")
-        print(f"Dead code found: {result['dead_code_count']}")
-        print()
-
-        if result["dead_code"]:
-            print(f"{'File':<45} {'Line':>4} {'Type':<10} {'Name'}")
-            print("-" * 85)
-            for item in result["dead_code"]:
-                author = ""
-                if args.git_blame:
-                    author = get_git_blame(
-                        os.path.join(args.repo, item["file"]),
-                        item["line"]
-                    ) or ""
-                    author = f" ({author})" if author else ""
-                print(f"{item['file']:<45} {item['line']:>4} {item['type']:<10} {item['name']}{author}")
-        else:
-            print("No dead code detected!")
-
-
-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.")