Merge remote-tracking branch 'origin/main' into codex/pr32-final

# Conflicts:
#	.github/workflows/ci.yml

scripts/build-icons.py

@@ -314,6 +314,10 @@ def normalize_url(raw: str) -> str:
 def normalize_devicon(raw: str) -> str:
     """Devicon SVGs have colored fills and a 128x128 or 32x32 viewBox.
     Strip fills/classes and rewrite to 24x24 currentColor."""
+    viewbox_match = re.search(
+        r'\bviewBox\s*=\s*(["\'])(.*?)\1', raw, flags=re.IGNORECASE
+    )
+    viewbox = viewbox_match.group(2).strip() if viewbox_match else "0 0 128 128"
     inner = re.search(r"<svg\b[^>]*>(.*?)</svg>", raw, flags=re.DOTALL | re.IGNORECASE)
     if not inner:
         raise ValueError("no <svg> in Devicon payload")
@@ -325,7 +329,7 @@ def normalize_devicon(raw: str) -> str:
     body = re.sub(r'\bclass="[^"]*"', 'fill="currentColor"', body)
     body = re.sub(r"\s+", " ", body).strip()
     return (
-        '<svg aria-hidden="true" width="24" height="24" viewBox="0 0 128 128" '
+        f'<svg aria-hidden="true" width="24" height="24" viewBox="{viewbox}" '
         f'fill="currentColor">{body}</svg>'
     )
 

scripts/fix-mojibake.py

@@ -17,8 +17,10 @@ PAIRS = [
     ('…', '…'),  # horizontal ellipsis
     ('•', '•'),  # bullet
     ('→', '→'),  # right arrow
-    ('↑', '←'),  # left arrow
-    ('↑', '↑'),  # up arrow (same prefix collision - rare)
+    # CP1252 leaves byte 0x90 undefined, so spell the left-arrow corruption
+    # with a Unicode escape instead of embedding an invisible control character.
+    ('\u00e2\u2020\u0090', '←'),  # left arrow
+    ('↑', '↑'),  # up arrow
     ('↓', '↓'),  # down arrow
     ('≤', '≤'),  # less-than-or-equal
     ('≥', '≥'),  # greater-than-or-equal

scripts/test-build-icons-devicon.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+"""Regression tests for Devicon viewBox preservation."""
+
+from __future__ import annotations
+
+import importlib.util
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parent.parent
+BUILD = ROOT / "scripts" / "build-icons.py"
+
+
+def load_build_module():
+    sys.dont_write_bytecode = True
+    spec = importlib.util.spec_from_file_location("diagram_design_build_icons", BUILD)
+    if spec is None or spec.loader is None:
+        raise AssertionError("could not load build-icons.py")
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def main() -> int:
+    build_icons = load_build_module()
+    svg = '<svg viewBox="0 0 32 32"><path fill="#123456" d="M0 0h32v32H0z"/></svg>'
+    normalized = build_icons.normalize_devicon(svg)
+    if 'viewBox="0 0 32 32"' not in normalized:
+        raise AssertionError(f"source viewBox was not preserved: {normalized}")
+    if 'fill="#123456"' in normalized:
+        raise AssertionError("source fill escaped currentColor normalization")
+    if 'fill="currentColor"' not in normalized:
+        raise AssertionError("normalized icon does not inherit currentColor")
+    print("PASS: Devicon normalization preserves non-128 source viewBoxes")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

scripts/test-fix-mojibake.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+"""Regression tests for the mojibake repair utility."""
+
+from __future__ import annotations
+
+import subprocess
+import sys
+import tempfile
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parent.parent
+SCRIPT = ROOT / "scripts" / "fix-mojibake.py"
+
+
+def main() -> int:
+    # These are the strings produced when UTF-8 arrow bytes are decoded as
+    # Windows-1252. Byte 0x90 is undefined in CP1252, hence the explicit escape.
+    source = "right →, left \u00e2\u2020\u0090, up ↑, down ↓\n"
+    expected = "right →, left ←, up ↑, down ↓\n"
+    with tempfile.TemporaryDirectory(prefix="diagram-design-mojibake-") as directory:
+        path = Path(directory) / "fixture.md"
+        path.write_text(source, encoding="utf-8")
+        result = subprocess.run(
+            [sys.executable, str(SCRIPT), str(path)],
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        if result.returncode != 0:
+            raise AssertionError(f"repair failed: {result.stdout}{result.stderr}")
+        actual = path.read_text(encoding="utf-8")
+        if actual != expected:
+            raise AssertionError(f"expected {expected!r}, got {actual!r}")
+    print("PASS: mojibake arrow sequences repair to the intended directions")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())