Function parseQuotedFileName

src/patch/parse.ts:354–410

* Parses a C-style quoted filename as used by Git or GNU `diff -u`. * Returns the unescaped filename and the raw length consumed (including quotes).

(s: string)

   * Returns the unescaped filename and the raw length consumed (including quotes).
   */
  function parseQuotedFileName(s: string): { fileName: string, rawLength: number } | null {
    if (!s.startsWith('"')) { return null; }
    let result = '';
    let j = 1; // skip opening quote
    while (j < s.length) {
      if (s[j] === '"') {
        return { fileName: result, rawLength: j + 1 };
      }
      if (s[j] === '\\' && j + 1 < s.length) {
        j++;
        switch (s[j]) {
          case 'a': result += '\x07'; break;
          case 'b': result += '\b'; break;
          case 'f': result += '\f'; break;
          case 'n': result += '\n'; break;
          case 'r': result += '\r'; break;
          case 't': result += '\t'; break;
          case 'v': result += '\v'; break;
          case '\\': result += '\\'; break;
          case '"': result += '"'; break;
          case '0': case '1': case '2': case '3':
          case '4': case '5': case '6': case '7': {
            // C-style octal escapes represent raw bytes. Collect
            // consecutive octal-escaped bytes and decode as UTF-8.
            // Validate that we have a full 3-digit octal escape
            if (j + 2 >= s.length || s[j + 1] < '0' || s[j + 1] > '7' || s[j + 2] < '0' || s[j + 2] > '7') {
              return null;
            }
            const bytes = [parseInt(s.substring(j, j + 3), 8)];
            j += 3;
            while (s[j] === '\\' && s[j + 1] >= '0' && s[j + 1] <= '7') {
              if (j + 3 >= s.length || s[j + 2] < '0' || s[j + 2] > '7' || s[j + 3] < '0' || s[j + 3] > '7') {
                return null;
              }
              bytes.push(parseInt(s.substring(j + 1, j + 4), 8));
              j += 4;
            }
            result += new TextDecoder('utf-8').decode(new Uint8Array(bytes));
            continue; // j already points at the next character
          }
          // Note that in C, there are also three kinds of hex escape sequences:
          // - \xhh
          // - \uhhhh
          // - \Uhhhhhhhh
          // We do not bother to parse them here because, so far as we know,
          // they are never emitted by any tools that generate unified diff
          // format diffs, and so for now jsdiff does not consider them legal.
          default: return null;
        }
      } else {
        result += s[j];
      }
      j++;
    }
    // Unterminated quote
    return null;
  }