基于Java和Kotlin的MyBookshelf项目设计源码与前端技术整合实践

package com.kunfei.bookshelf.utils; import androidx.annotation.NonNull; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.nodes.Element; import org.jsoup.select.Elements; import java.io.File; import java.io.FileInputStream; import java.io.InputStream; import java.net.URL; import static android.text.TextUtils.isEmpty; /** * <Detect encoding .> Copyright (C) <2009> <Fluck,ACC http://androidos.cc/dev> * <p> * This program is free software: you can redistribute it and/or modify it under * the terms of the GNU General Public License as published by the Free Software * Foundation, either version 3 of the License, or (at your option) any later * version. * <p> * This program is distributed in the hope that it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS * FOR A PARTICULAR PURPOSE. See the GNU General Public License for more * details. * <p> * EncodingDetect.java<br> * 自动获取文件的编码 * * @author Billows.Van * @version 1.0 * @since Create on 2010-01-27 11:19:00 */ public class EncodingDetect { public static String getEncodeInHtml(@NonNull byte[] bytes) { try { String charsetStr = "UTF-8"; Document doc = Jsoup.parse(new String(bytes, charsetStr)); int a = doc.childNode(0).toString().indexOf("encoding"); if (a > 0) { String e = doc.childNode(0).toString().substring(a); int b = e.indexOf('"'); int c = e.indexOf('"', b + 1); return e.substring(b + 1, c); } Elements metaTags = doc.getElementsByTag("meta"); for (Element metaTag : metaTags) { String content = metaTag.attr("content"); String http_equiv = metaTag.attr("http-equiv"); charsetStr = metaTag.attr("charset"); if (!charsetStr.isEmpty()) { if (!isEmpty(charsetStr)) { return charsetStr; } } if (http_equiv.toLowerCase().equals("content-type")) { if (content.toLowerCase().contains("charset")) { charsetStr = content.substring(content.toLowerCase().indexOf("charset") + "charset=".length()); } else { charsetStr = content.substring(content.toLowerCase().indexOf(";") + 1); } if (!isEmpty(charsetStr)) { return charsetStr; } } } } catch (Exception ignored) { } return getJavaEncode(bytes); } public static String getJavaEncode(@NonNull byte[] bytes) { int len = bytes.length > 2000 ? 2000 : bytes.length; byte[] cBytes = new byte[len]; System.arraycopy(bytes, 0, cBytes, 0, len); BytesEncodingDetect bytesEncodingDetect = new BytesEncodingDetect(); String code = BytesEncodingDetect.javaname[bytesEncodingDetect.detectEncoding(cBytes)]; // UTF-16LE 特殊处理 if ("Unicode".equals(code)) { if (cBytes[0] == -1) { code = "UTF-16LE"; } } return code; } /** * 得到文件的编码 */ public static String getJavaEncode(@NonNull String filePath) { BytesEncodingDetect s = new BytesEncodingDetect(); String fileCode = BytesEncodingDetect.javaname[s .detectEncoding(new File(filePath))]; // UTF-16LE 特殊处理 if ("Unicode".equals(fileCode)) { byte[] tempByte = BytesEncodingDetect.getFileBytes(new File( filePath)); if (tempByte[0] == -1) { fileCode = "UTF-16LE"; } } return fileCode; } /** * 得到文件的编码 */ public static String getJavaEncode(@NonNull File file) { BytesEncodingDetect s = new BytesEncodingDetect(); String fileCode = BytesEncodingDetect.javaname[s.detectEncoding(file)]; // UTF-16LE 特殊处理 if ("Unicode".equals(fileCode)) { byte[] tempByte = BytesEncodingDetect.getFileBytes(file); if (tempByte[0] == -1) { fileCode = "UTF-16LE"; } } return fileCode; } } class BytesEncodingDetect extends Encoding { // Frequency tables to hold the GB, Big5, and EUC-TW character // frequencies private int[][] GBFreq; private int[][] GBKFreq; private int[][] Big5Freq; private int[][] Big5PFreq; private int[][] EUC_TWFreq; private int[][] KRFreq; private int[][] JPFreq; // int UnicodeFreq[94][128]; // public static String[] nicename; // public static String[] codings; public boolean debug; public BytesEncodingDetect() { super(); debug = false; GBFreq = new int[94][94]; GBKFreq = new int[126][191]; Big5Freq = new int[94][158]; Big5PFreq = new int[126][191]; EUC_TWFreq = new int[94][94]; KRFreq = new int[94][94]; JPFreq = new int[94][94]; // Initialize the Frequency Table for GB, GBK, Big5, EUC-TW, KR, JP initialize_frequencies(); } /** * Function : detectEncoding Aruguments: URL Returns : One of the encodings * from the Encoding enumeration (GB2312, HZ, BIG5, EUC_TW, ASCII, or OTHER) * Description: This function looks at the URL contents and assigns it a * probability score for each encoding type. The encoding type with the * highest probability is returned. */ public int detectEncoding(URL testurl) { byte[] rawtext = new byte[10000]; int bytesread = 0, byteoffset = 0; int guess = OTHER; InputStream chinesestream; try { chinesestream = testurl.openStream(); while ((bytesread = chinesestream.read(rawtext, byteoffset, rawtext.length - byteoffset)) > 0) { byteoffset += bytesread; } ; chinesestream.close(); guess = detectEncoding(rawtext); } catch (Exception e) { System.err.println("Error loading or using URL " + e.toString()); guess = -1; } return guess; } /** * Function : detectEncoding Aruguments: File Returns : One of the encodings * from the Encoding enumeration (GB2312, HZ, BIG5, EUC_TW, ASCII, or OTHER) * Description: This function looks at the file and assigns it a probability * score for each encoding type. The encoding type with the highest * probability is returned. */ public int detectEncoding(File testfile) { byte[] rawtext = getFileBytes(testfile); return detectEncoding(rawtext); } public static byte[] getFileBytes(File testfile) { FileInputStream chinesefile; byte[] rawtext; rawtext = new byte[2000]; try { chinesefile = new FileInputStream(testfile); chinesefile.read(rawtext); chinesefile.close(); } catch (Exception e) { System.err.println("Error: " + e); } return rawtext; } /** * Function : detectEncoding Aruguments: byte array Returns : One of the * encodings from the Encoding enumeration (GB2312, HZ, BIG5, EUC_TW, ASCII, * or OTHER) Description: This function looks at the byte array and assigns * it a probability score for each encoding type. The encoding type with the * highest probability is returned. */ public int detectEncoding(byte[] rawtext) { int[] scores; int index, maxscore = 0; int encoding_guess = OTHER; scores = new int[TOTALTYPES]; // Assign Scores scores[GB2312] = gb2312_probability(rawtext); sco