Function decodePdfDocEncoding

src/helpers/encoding.ts:134–169

(bytes: Uint8Array)

 * Decode PDFDocEncoding bytes to string.
 */
export function decodePdfDocEncoding(bytes: Uint8Array): string {
  const chars: string[] = [];

  for (const byte of bytes) {
    if (byte < 0x18) {
      // Control chars - preserve tab, newline, carriage return
      if (byte === 0x09 || byte === 0x0a || byte === 0x0d) {
        chars.push(String.fromCharCode(byte));
      }
      // Skip other control chars
    } else if (byte <= 0x1f) {
      // Special low bytes (accents)
      const code = PDF_DOC_LOW[byte];

      if (code) {
        chars.push(String.fromCharCode(code));
      }
    } else if (byte < 0x80) {
      // ASCII range - direct mapping
      chars.push(String.fromCharCode(byte));
    } else if (byte <= 0xa0) {
      // High bytes with special mapping
      const code = PDF_DOC_HIGH[byte];

      if (code) {
        chars.push(String.fromCharCode(code));
      }
      // 0x9F is undefined, skip
    } else if (byte !== 0xad) {
      // 0xA1-0xFF map to Unicode (same as Latin-1), except 0xAD (undefined)
      chars.push(String.fromCharCode(byte));
    }
  }

  return chars.join("");
}

/**
 * Decode PDF text string bytes (auto-detects encoding).