Class TextEncodingHandler

src/handlers/textEncoding.ts:106–189

];

export default class TextEncodingHandler implements FormatHandler {
  name = "TextEncoding";
  supportedFormats = formats;
  ready = true;
  init = async () => { this.ready = true };

  async doConvert(inputFiles: FileData[], inputFormat: FileFormat, outputFormat: FileFormat) {
    const results: FileData[] = [];
    for (const file of inputFiles) {
      const inBytes = file.bytes;
      let text = "";

      // Determine input encoding: prefer inputFormat.internal when present
      const inf = inputFormat.internal;
      if (inf === "txt" || inf === "utf8NB") {
        text = decodeUsingTextDecoder(inBytes, "utf-8");
      } else if (inf === "utf8WB") {
        text = decodeUsingTextDecoder(inBytes.subarray(3), "utf-8");
      } else if (inf === "utf16le") {
        text = decodeUTF16(inBytes, true);
      } else if (inf === "utf16be") {
        text = decodeUTF16(inBytes, false);
      } else if (inf === "utf32le") {
        text = decodeUTF32(inBytes, true);
      } else if (inf === "utf32be") {
        text = decodeUTF32(inBytes, false);
      } else {
        // Try BOM detection
        if (hasPrefix(inBytes, [0xEF, 0xBB, 0xBF])) {
          text = decodeUsingTextDecoder(inBytes.subarray(3), "utf-8");
        } else if (hasPrefix(inBytes, [0xFF, 0xFE, 0x00, 0x00])) {
          text = decodeUTF32(inBytes.subarray(4), true);
        } else if (hasPrefix(inBytes, [0x00, 0x00, 0xFE, 0xFF])) {
          text = decodeUTF32(inBytes.subarray(4), false);
        } else if (hasPrefix(inBytes, [0xFF, 0xFE])) {
          text = decodeUTF16(inBytes.subarray(2), true);
        } else if (hasPrefix(inBytes, [0xFE, 0xFF])) {
          text = decodeUTF16(inBytes.subarray(2), false);
        } else {
          // default to utf-8
          text = decodeUsingTextDecoder(inBytes, "utf-8");
        }
      }

      // Now encode to output format
      const outf = (outputFormat && outputFormat.internal) || "utf8NB";
      let outBytes: Uint8Array;
      if (outf === "utf8NB") {
        const utf8Bytes = new TextEncoder().encode(text);
        if (utf8Bytes.length >= 3 && hasPrefix(utf8Bytes, [0xEF, 0xBB, 0xBF])) {
          // has BOM, remove it
          outBytes = utf8Bytes.subarray(3);
        } else {
          // Already without BOM, just use it as is
          outBytes = utf8Bytes;
        }
      } else if (outf === "utf8WB") {
        const utf8Bytes = new TextEncoder().encode(text);