zhywpt-sp/utils/util/fileData.js

import {
	TextDecoder
} from "../node-model/text-decoding";

export function IntegerToHexString(num, nLen) {
	if (num == null) {
		let str = "";
		for (let i = 0; i < nLen; i++) {
			str += "0";
		}
		return str;
	}
	return HighAddZero(num.toString(16), nLen);
}
export function HighAddZero(str, nLen) {
	let length = str.length;
	let nAddLen = nLen - length;
	if (length > nLen) {
		str = str.substring(0, nLen);
	} else {
		for (let i = 0; i < nAddLen; i++) {
			str = "0" + str;
		}
	}
	return str;
}

const DIGITS_UPPER = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D',
	'E', 'F'
];
export function HexToString(inHex) {
	let i;
	let strResult = "";
	for (i = 0; i < inHex.length; i++) {
		strResult += DIGITS_UPPER[(0xF0 & inHex[i]) >>> 4];
		strResult += DIGITS_UPPER[inHex[i] & 0x0F];
	}
	return strResult;
}

/**
 * 十六进制转汉字
 *
 * @param {string} data
 * @returns {string}
 */
export function HexToStrig(data, charType = 1) {

	let str = data.substring(data.length - 2);
	while (str === "00") {
		data = data.substring(0, data.length - 2);
		if (data.length === 0) {
			return "";
		}
		str = data.substring(data.length - 2);
	}
	const asd = hexStringToByteArray(data);
	try {
		str = new TextDecoder("GBK").decode(asd);

	} catch (e) {
		console.error(e);
	}
	return str;
}

/**
 * 十六进制字符串转字节数组
 *
 * @param {string} str
 * @returns {Uint8Array}
 */
export function hexStringToByteArray(str) {
	if (!str) {
		return new Uint8Array();
	}
	const result = new Uint8Array(str.length / 2);
	for (let i = 0; i < str.length; i += 2) {
		result[i / 2] = parseInt(str.substr(i, 2), 16);
	}
	return result;
}

/**
 * 十六进制转十进制
 *
 * @param {string} data
 * @returns {string}
 */
export function HexToInt(data) {
	let num = -1;
	try {
		num = parseInt(data, 16);
	} catch (e) {
		console.error(e);
	}
	return num.toString();
}


function guessEncoding(bytes) {
	// 检查字节序列是否以 BOM（字节顺序标记）开头
	if (bytes[0] === 0xEF && bytes[1] === 0xBB && bytes[2] === 0xBF) {
		return 'UTF-8';
	} else if (bytes[0] === 0xFE && bytes[1] === 0xFF) {
		return 'UTF-16BE';
	} else if (bytes[0] === 0xFF && bytes[1] === 0xFE) {
		return 'UTF-16LE';
	} else {
		// 统计每个字节的频率
		let freq = {};
		for (let i = 0; i < bytes.length; i++) {
			let b = bytes[i];
			freq[b] = freq[b] ? freq[b] + 1 : 1;
		}

		// 检查是否存在 GBK 的特定字节序列
		if (freq[0x81] && freq[0x81] > 0 && freq[0x40] && freq[0x40] > 0) {
			return 'GBK';
		}

		// 如果没有特定的 GBK 字节序列，则假设为 UTF-8
		return 'UTF-8';
	}
}