feat: Gitea issue body parser for structured task extraction (#90)

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()