fix: Edit 工具增加 Tab/空格规范化匹配,修复中文和缩进文件编辑失败

Read 工具输出将 Tab 渲染为空格,用户复制后 Edit 工具无法匹配。
在 findActualString 中增加 Tab→空格规范化回退匹配,并精确映射回原始文件位置。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
claude-code-best
2026-04-27 16:52:11 +08:00
parent c6338917e5
commit 4cbef9667d
2 changed files with 179 additions and 1 deletions

View File

@@ -106,6 +106,84 @@ describe("findActualString", () => {
const result = findActualString("hello", "");
expect(result).toBe("");
});
// ── Tab/space normalization (Bug #2 reproduction) ──
test("finds match when search uses spaces but file uses tabs", () => {
// File content uses Tab indentation
const fileContent = "\tif (x) {\n\t\treturn 1;\n\t}";
// User copies from Read output which renders tabs as spaces
const searchWithSpaces = " if (x) {\n return 1;\n }";
const result = findActualString(fileContent, searchWithSpaces);
expect(result).not.toBeNull();
expect(result).toBe(fileContent);
});
test("finds match when search mixes tabs and spaces inconsistently", () => {
const fileContent = "\tconst x = 1; // comment";
const searchMixed = " const x = 1; // comment";
const result = findActualString(fileContent, searchMixed);
expect(result).not.toBeNull();
});
test("finds match for single-line tab-to-space mismatch", () => {
const fileContent = "\t\torder_price = NormalizeDouble(ask, digits);";
const searchSpaces = " order_price = NormalizeDouble(ask, digits);";
const result = findActualString(fileContent, searchSpaces);
expect(result).not.toBeNull();
});
// ── CJK / UTF-8 characters (Bug #1 reproduction) ──
test("finds match with CJK characters in content", () => {
const fileContent = "input int x = 620; // 止盈点数(点) — 32个pip=320点";
const result = findActualString(fileContent, fileContent);
expect(result).toBe(fileContent);
});
test("finds match with CJK characters when tab/space differs", () => {
const fileContent = "\t// 向上突破 → Sell Limit (逆方向做空)";
const searchSpaces = " // 向上突破 → Sell Limit (逆方向做空)";
const result = findActualString(fileContent, searchSpaces);
expect(result).not.toBeNull();
expect(result).toBe(fileContent);
});
// ── Multiline with tabs + CJK (combined Bug #1 + #2) ──
test("finds multiline match with tabs and CJK characters", () => {
const fileContent = "\tif(effective_dir == BREAKOUT_UP)\n\t\t{\n\t\t\t// 向上突破\n\t\t}";
const searchSpaces = " if(effective_dir == BREAKOUT_UP)\n {\n // 向上突破\n }";
const result = findActualString(fileContent, searchSpaces);
expect(result).not.toBeNull();
expect(result).toBe(fileContent);
});
// ── Returned string must be a valid substring of fileContent ──
test("returned string from tab match is a real substring of fileContent", () => {
const fileContent = "prefix\n\t\tindented code\nsuffix";
const searchSpaces = "prefix\n indented code\nsuffix";
const result = findActualString(fileContent, searchSpaces);
expect(result).not.toBeNull();
expect(fileContent.includes(result!)).toBe(true);
});
test("returned string from partial tab match is a real substring", () => {
const fileContent = "line1\n\tif (x) {\n\t\tdoStuff();\n\t}\nline5";
const searchSpaces = " if (x) {\n doStuff();\n }";
const result = findActualString(fileContent, searchSpaces);
expect(result).not.toBeNull();
expect(fileContent.includes(result!)).toBe(true);
});
test("tab match with mixed indentation levels", () => {
const fileContent = "class Foo {\n\t\tmethod1() {\n\t\t\treturn 42;\n\t\t}\n}";
const searchSpaces = "class Foo {\n method1() {\n return 42;\n }\n}";
const result = findActualString(fileContent, searchSpaces);
expect(result).not.toBeNull();
expect(fileContent.includes(result!)).toBe(true);
});
});
// ─── preserveQuoteStyle ─────────────────────────────────────────────────

View File

@@ -63,9 +63,26 @@ export function stripTrailingWhitespace(str: string): string {
return result
}
/**
* Normalizes whitespace for fuzzy matching by converting tabs to spaces
* and collapsing leading whitespace on each line to a canonical form.
* This handles the case where Read tool output renders tabs as spaces,
* so users copy spaces from the output but the file actually has tabs.
*/
function normalizeWhitespace(str: string): string {
return str.replace(/\t/g, ' ')
}
/**
* Finds the actual string in the file content that matches the search string,
* accounting for quote normalization
* accounting for quote normalization and tab/space differences.
*
* Matching cascade:
* 1. Exact match
* 2. Quote normalization (curly → straight quotes)
* 3. Tab/space normalization (tabs ↔ spaces in leading whitespace)
* 4. Quote + tab/space normalization combined
*
* @param fileContent The file content to search in
* @param searchString The string to search for
* @returns The actual string found in the file, or null if not found
@@ -89,9 +106,92 @@ export function findActualString(
return fileContent.substring(searchIndex, searchIndex + searchString.length)
}
// Try with tab/space normalization — handles the case where Read output
// renders tabs as spaces and the user copies the rendered version
const wsNormalizedFile = normalizeWhitespace(fileContent)
const wsNormalizedSearch = normalizeWhitespace(searchString)
const wsSearchIndex = wsNormalizedFile.indexOf(wsNormalizedSearch)
if (wsSearchIndex !== -1) {
// Map the match position back to the original file content.
// We need to find the corresponding range in the original string.
return mapNormalizedMatchBackToFile(fileContent, wsNormalizedFile, wsSearchIndex, wsNormalizedSearch.length)
}
// Try combined: quote normalization + tab/space normalization
const combinedFile = normalizeWhitespace(normalizedFile)
const combinedSearch = normalizeWhitespace(normalizedSearch)
const combinedIndex = combinedFile.indexOf(combinedSearch)
if (combinedIndex !== -1) {
return mapNormalizedMatchBackToFile(fileContent, combinedFile, combinedIndex, combinedSearch.length)
}
return null
}
/**
* Given a match found in a normalized version of fileContent, map the match
* position back to the original fileContent and extract the corresponding
* substring.
*
* Strategy: walk through both strings character by character, building a
* mapping from normalized offset to original offset. When a tab is expanded
* to 4 spaces in the normalized version, the normalized offset advances by 4
* while the original offset advances by 1.
*/
function mapNormalizedMatchBackToFile(
fileContent: string,
normalizedFile: string,
normalizedStart: number,
normalizedLength: number,
): string {
// Build a sparse mapping from normalized position → original position.
// We only need to map the range [normalizedStart, normalizedStart + normalizedLength].
let normPos = 0
let origPos = 0
let origStart = -1
let origEnd = -1
while (origPos < fileContent.length && normPos <= normalizedStart + normalizedLength) {
if (normPos === normalizedStart) {
origStart = origPos
}
if (normPos === normalizedStart + normalizedLength) {
origEnd = origPos
break
}
const origChar = fileContent[origPos]!
if (origChar === '\t') {
// Tab expands to 4 spaces in normalized version
const nextNormPos = normPos + 4
// If normalizedStart falls within this expanded tab, snap to origPos
if (normPos < normalizedStart && nextNormPos > normalizedStart && origStart === -1) {
origStart = origPos
}
if (normPos < normalizedStart + normalizedLength && nextNormPos > normalizedStart + normalizedLength && origEnd === -1) {
origEnd = origPos + 1
}
normPos = nextNormPos
origPos++
} else {
normPos++
origPos++
}
}
// Fallback: if we couldn't map precisely, use character-count heuristic
if (origStart === -1) origStart = 0
if (origEnd === -1) {
// Approximate: use the ratio of original to normalized length
const ratio = fileContent.length / normalizedFile.length
origEnd = Math.round(origStart + normalizedLength * ratio)
}
return fileContent.substring(origStart, origEnd)
}
/**
* When old_string matched via quote normalization (curly quotes in file,
* straight quotes from model), apply the same curly quote style to new_string