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

scripts/diff_analyzer.py

@@ -1,216 +0,0 @@
-#!/usr/bin/env python3
-"""
-Diff Analyzer — Parse unified diffs and categorize every change.
-
-Pipeline 6.1 for Compounding Intelligence.
-"""
-
-import re
-from dataclasses import dataclass, field, asdict
-from enum import Enum
-from typing import List, Dict, Any, Optional
-
-
-class ChangeCategory(Enum):
-    ADDED = "added"
-    DELETED = "deleted"
-    MODIFIED = "modified"
-    MOVED = "moved"
-    CONTEXT = "context"
-
-
-@dataclass
-class Hunk:
-    """A single diff hunk with header, line ranges, and category."""
-    header: str
-    old_start: int
-    old_count: int
-    new_start: int
-    new_count: int
-    lines: List[str] = field(default_factory=list)
-    category: ChangeCategory = ChangeCategory.CONTEXT
-
-    def to_dict(self) -> Dict[str, Any]:
-        d = asdict(self)
-        d["category"] = self.category.value
-        return d
-
-
-@dataclass
-class FileChange:
-    """A single file's changes."""
-    path: str
-    old_path: Optional[str] = None  # For renames
-    hunks: List[Hunk] = field(default_factory=list)
-    added_lines: int = 0
-    deleted_lines: int = 0
-    is_new: bool = False
-    is_deleted: bool = False
-    is_renamed: bool = False
-    is_binary: bool = False
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "path": self.path,
-            "old_path": self.old_path,
-            "hunks": [h.to_dict() for h in self.hunks],
-            "added_lines": self.added_lines,
-            "deleted_lines": self.deleted_lines,
-            "is_new": self.is_new,
-            "is_deleted": self.is_deleted,
-            "is_renamed": self.is_renamed,
-            "is_binary": self.is_binary,
-        }
-
-
-@dataclass
-class ChangeSummary:
-    """Aggregate stats + per-file breakdown."""
-    files: List[FileChange] = field(default_factory=list)
-    total_added: int = 0
-    total_deleted: int = 0
-    total_files_changed: int = 0
-    total_hunks: int = 0
-    new_files: int = 0
-    deleted_files: int = 0
-    renamed_files: int = 0
-    binary_files: int = 0
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "total_files_changed": self.total_files_changed,
-            "total_added": self.total_added,
-            "total_deleted": self.total_deleted,
-            "total_hunks": self.total_hunks,
-            "new_files": self.new_files,
-            "deleted_files": self.deleted_files,
-            "renamed_files": self.renamed_files,
-            "binary_files": self.binary_files,
-            "files": [f.to_dict() for f in self.files],
-        }
-
-
-class DiffAnalyzer:
-    """Parses unified diff format and produces structured ChangeSummary."""
-
-    HUNK_HEADER_RE = re.compile(r"^@@\s+-(\d+)(?:,(\d+))?\s+\+(\d+)(?:,(\d+))?\s+@@(.*)$")
-    DIFF_FILE_RE = re.compile(r"^diff --git a/(.*) b/(.*)")
-    RENAME_RE = re.compile(r"^rename from (.+)$")
-    RENAME_TO_RE = re.compile(r"^rename to (.+)$")
-    NEW_FILE_RE = re.compile(r"^new file mode")
-    DELETED_FILE_RE = re.compile(r"^deleted file mode")
-    BINARY_RE = re.compile(r"^Binary files .* differ")
-
-    def analyze(self, diff_text: str) -> ChangeSummary:
-        """Parse a unified diff and return a ChangeSummary."""
-        summary = ChangeSummary()
-        if not diff_text or not diff_text.strip():
-            return summary
-
-        # Split diff into per-file sections
-        file_diffs = self._split_files(diff_text)
-
-        for file_diff in file_diffs:
-            fc = self._parse_file_diff(file_diff)
-            summary.files.append(fc)
-            summary.total_added += fc.added_lines
-            summary.total_deleted += fc.deleted_lines
-            summary.total_hunks += len(fc.hunks)
-            if fc.is_new:
-                summary.new_files += 1
-            if fc.is_deleted:
-                summary.deleted_files += 1
-            if fc.is_renamed:
-                summary.renamed_files += 1
-            if fc.is_binary:
-                summary.binary_files += 1
-
-        summary.total_files_changed = len(summary.files)
-        return summary
-
-    def _split_files(self, diff_text: str) -> List[str]:
-        """Split a multi-file diff into individual file diffs."""
-        lines = diff_text.split("\n")
-        chunks = []
-        current = []
-        for line in lines:
-            if line.startswith("diff --git ") and current:
-                chunks.append("\n".join(current))
-                current = [line]
-            else:
-                current.append(line)
-        if current:
-            chunks.append("\n".join(current))
-        return chunks
-
-    def _parse_file_diff(self, diff_text: str) -> FileChange:
-        """Parse a single file's diff section."""
-        lines = diff_text.split("\n")
-        fc = FileChange(path="")
-
-        # Extract file paths
-        for line in lines:
-            m = self.DIFF_FILE_RE.match(line)
-            if m:
-                fc.path = m.group(2)
-                break
-
-        # Check for special states
-        for line in lines:
-            if self.NEW_FILE_RE.match(line):
-                fc.is_new = True
-            elif self.DELETED_FILE_RE.match(line):
-                fc.is_deleted = True
-            elif self.RENAME_RE.match(line):
-                fc.old_path = m.group(1) if (m := self.RENAME_RE.match(line)) else None
-                fc.is_renamed = True
-            elif self.BINARY_RE.match(line):
-                fc.is_binary = True
-                return fc  # No hunks for binary
-
-        # Rename TO
-        for line in lines:
-            m = self.RENAME_TO_RE.match(line)
-            if m and fc.is_renamed:
-                fc.path = m.group(1)
-
-        # Parse hunks
-        current_hunk = None
-        for line in lines:
-            m = self.HUNK_HEADER_RE.match(line)
-            if m:
-                if current_hunk:
-                    self._classify_hunk(current_hunk, fc)
-                    fc.hunks.append(current_hunk)
-                current_hunk = Hunk(
-                    header=m.group(5).strip(),
-                    old_start=int(m.group(1)),
-                    old_count=int(m.group(2) or 1),
-                    new_start=int(m.group(3)),
-                    new_count=int(m.group(4) or 1),
-                )
-            elif current_hunk and (line.startswith("+") or line.startswith("-") or line.startswith(" ")):
-                current_hunk.lines.append(line)
-
-        if current_hunk:
-            self._classify_hunk(current_hunk, fc)
-            fc.hunks.append(current_hunk)
-
-        return fc
-
-    def _classify_hunk(self, hunk: Hunk, fc: FileChange):
-        """Classify a hunk and count lines."""
-        added = sum(1 for l in hunk.lines if l.startswith("+"))
-        deleted = sum(1 for l in hunk.lines if l.startswith("-"))
-
-        fc.added_lines += added
-        fc.deleted_lines += deleted
-
-        if added > 0 and deleted == 0:
-            hunk.category = ChangeCategory.ADDED
-        elif deleted > 0 and added == 0:
-            hunk.category = ChangeCategory.DELETED
-        elif added > 0 and deleted > 0:
-            hunk.category = ChangeCategory.MODIFIED
-        else:
-            hunk.category = ChangeCategory.CONTEXT

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_diff_analyzer.py

@@ -1,189 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for scripts/diff_analyzer.py — 10 tests."""
-
-import sys
-import os
-sys.path.insert(0, os.path.dirname(__file__) or ".")
-
-import importlib.util
-spec = importlib.util.spec_from_file_location("da", os.path.join(os.path.dirname(__file__) or ".", "diff_analyzer.py"))
-mod = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(mod)
-DiffAnalyzer = mod.DiffAnalyzer
-ChangeCategory = mod.ChangeCategory
-
-
-SAMPLE_ADD = """diff --git a/new.py b/new.py
-new file mode 100644
---- /dev/null
-+++ b/new.py
-@@ -0,0 +1,3 @@
-+def hello():
-+    print("world")
-+    return True
-"""
-
-SAMPLE_DELETE = """diff --git a/old.py b/old.py
-deleted file mode 100644
---- a/old.py
-+++ /dev/null
-@@ -1,2 +0,0 @@
--def goodbye():
--    pass
-"""
-
-SAMPLE_MODIFY = """diff --git a/app.py b/app.py
---- a/app.py
-+++ b/app.py
-@@ -1,3 +1,4 @@
- def main():
--    print("old")
-+    print("new")
-+    print("extra")
-     return 0
-"""
-
-SAMPLE_RENAME = """diff --git a/old_name.py b/new_name.py
-rename from old_name.py
-rename to new_name.py
---- a/old_name.py
-+++ b/new_name.py
-@@ -1,1 +1,1 @@
--old content
-+new content
-"""
-
-SAMPLE_MULTI = """diff --git a/a.py b/a.py
---- a/a.py
-+++ b/a.py
-@@ -1,1 +1,2 @@
- existing
-+added line
-diff --git b/b.py b/b.py
-new file mode 100644
---- /dev/null
-+++ b/b.py
-@@ -0,0 +1,1 @@
-+new file
-"""
-
-SAMPLE_BINARY = """diff --git a/img.png b/img.png
-Binary files a/img.png and b/img.png differ
-"""
-
-
-def test_empty():
-    a = DiffAnalyzer()
-    s = a.analyze("")
-    assert s.total_files_changed == 0
-    print("PASS: test_empty")
-
-def test_addition():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_ADD)
-    assert s.total_files_changed == 1
-    assert s.total_added == 3
-    assert s.total_deleted == 0
-    assert s.new_files == 1
-    assert s.files[0].hunks[0].category == ChangeCategory.ADDED
-    print("PASS: test_addition")
-
-def test_deletion():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_DELETE)
-    assert s.total_deleted == 2
-    assert s.deleted_files == 1
-    assert s.files[0].hunks[0].category == ChangeCategory.DELETED
-    print("PASS: test_deletion")
-
-def test_modification():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_MODIFY)
-    assert s.total_added == 2
-    assert s.total_deleted == 1
-    assert s.files[0].hunks[0].category == ChangeCategory.MODIFIED
-    print("PASS: test_modification")
-
-def test_rename():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_RENAME)
-    assert s.renamed_files == 1
-    assert s.files[0].old_path == "old_name.py"
-    assert s.files[0].path == "new_name.py"
-    assert s.files[0].is_renamed == True
-    print("PASS: test_rename")
-
-def test_multiple_files():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_MULTI)
-    assert s.total_files_changed == 2
-    assert s.new_files == 1
-    print("PASS: test_multiple_files")
-
-def test_binary():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_BINARY)
-    assert s.binary_files == 1
-    assert s.files[0].is_binary == True
-    assert len(s.files[0].hunks) == 0
-    print("PASS: test_binary")
-
-def test_to_dict():
-    a = DiffAnalyzer()
-    s = a.analyze(SAMPLE_MODIFY)
-    d = s.to_dict()
-    assert "total_files_changed" in d
-    assert "files" in d
-    assert isinstance(d["files"], list)
-    print("PASS: test_to_dict")
-
-def test_context_only():
-    diff = """diff --git a/f.py b/f.py
---- a/f.py
-+++ b/f.py
-@@ -1,3 +1,3 @@
- line1
--old
-+new
- line3
-"""
-    a = DiffAnalyzer()
-    s = a.analyze(diff)
-    # Has both added and deleted = MODIFIED
-    assert s.files[0].hunks[0].category == ChangeCategory.MODIFIED
-    print("PASS: test_context_only")
-
-def test_multi_hunk():
-    diff = """diff --git a/f.py b/f.py
---- a/f.py
-+++ b/f.py
-@@ -1,1 +1,2 @@
- existing
-+first addition
-@@ -10,1 +11,2 @@
- more
-+second addition
-"""
-    a = DiffAnalyzer()
-    s = a.analyze(diff)
-    assert s.total_hunks == 2
-    assert s.total_added == 2
-    print("PASS: test_multi_hunk")
-
-
-def run_all():
-    test_empty()
-    test_addition()
-    test_deletion()
-    test_modification()
-    test_rename()
-    test_multiple_files()
-    test_binary()
-    test_to_dict()
-    test_context_only()
-    test_multi_hunk()
-    print("\nAll 10 tests passed!")
-
-
-if __name__ == "__main__":
-    run_all()

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.")