Function extractWithRegex

src/codegraph/extractor.ts:207–247

(lang: string, source: string)

};

function extractWithRegex(lang: string, source: string): ExtractedSymbol[] {
  const patterns = REGEX_PATTERNS[lang];
  if (!patterns) return [];

  const lines = source.split('\n');
  const lineOffsets: number[] = [0];
  for (let i = 0; i < lines.length; i++) {
    lineOffsets.push(lineOffsets[i]! + lines[i]!.length + 1);
  }
  const positionToLine = (pos: number): { line: number; col: number } => {
    // Binary search
    let lo = 0, hi = lineOffsets.length - 1;
    while (lo < hi) {
      const mid = (lo + hi + 1) >>> 1;
      if (lineOffsets[mid]! <= pos) lo = mid;
      else hi = mid - 1;
    }
    return { line: lo + 1, col: pos - lineOffsets[lo]! };
  };

  const symbols: ExtractedSymbol[] = [];
  for (const { pattern, kind } of patterns) {
    const re = new RegExp(pattern.source, pattern.flags);
    let m: RegExpExecArray | null;
    while ((m = re.exec(source)) !== null) {
      const name = m[1];
      if (!name) continue;
      const { line, col } = positionToLine(m.index);
      const lineText = (lines[line - 1] ?? '').slice(0, 200);
      symbols.push({
        name,
        kind,
        startLine: line,
        endLine: line, // regex doesn't know body bounds
        startColumn: col,
        signature: lineText,
      });
    }
  }
  return symbols;
}