From 9ba877fae487038d9d7449f25227e8b9b015df75 Mon Sep 17 00:00:00 2001
From: Aaron Liang <76561968+AaronL725@users.noreply.github.com>
Date: Wed, 15 Jul 2026 01:43:12 +0800
Subject: [PATCH] fix: repair AST source span extraction

---
 tools/fix_modularization_ast_spans.py | 35 +++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 tools/fix_modularization_ast_spans.py

diff --git a/tools/fix_modularization_ast_spans.py b/tools/fix_modularization_ast_spans.py
new file mode 100644
index 0000000..b4dbd23
--- /dev/null
+++ b/tools/fix_modularization_ast_spans.py
@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+from pathlib import Path
+
+path = Path(__file__).resolve().parent / "apply_full_safe_modularization.py"
+text = path.read_text(encoding="utf-8")
+old = '''def node_span(text: str, node: ast.AST) -> tuple[int, int]:
+    lines = text.splitlines(keepends=True)
+    offsets = [0]
+    for line in lines:
+        offsets.append(offsets[-1] + len(line))
+    start = offsets[node.lineno - 1] + getattr(node, "col_offset", 0)
+    end_line = getattr(node, "end_lineno", node.lineno)
+    end_col = getattr(node, "end_col_offset", len(lines[end_line - 1]))
+    end = offsets[end_line - 1] + end_col
+    while end < len(text) and text[end] in "\\r\\n":
+        end += 1
+    return start, end
+'''
+new = '''def node_span(text: str, node: ast.AST) -> tuple[int, int]:
+    # AST column offsets are UTF-8 byte offsets, not Python character offsets.
+    # Every node moved by this script is top-level, so complete source lines are
+    # the safest exact boundary and preserve non-ASCII strings without truncation.
+    lines = text.splitlines(keepends=True)
+    offsets = [0]
+    for line in lines:
+        offsets.append(offsets[-1] + len(line))
+    start = offsets[node.lineno - 1]
+    end_line = getattr(node, "end_lineno", node.lineno)
+    end = offsets[end_line]
+    return start, end
+'''
+if text.count(old) != 1:
+    raise RuntimeError(f"node_span patch expected one match, got {text.count(old)}")
+path.write_text(text.replace(old, new, 1), encoding="utf-8")
+print("fixed AST source spans")