feat: Add diff analyzer tests (closes #176)

scripts/diff_analyzer.py

@@ -0,0 +1,216 @@
+#!/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

@@ -1,131 +0,0 @@
-#!/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/test_diff_analyzer.py

@@ -0,0 +1,189 @@
+#!/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

@@ -1,109 +0,0 @@
-#!/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()