android 获取文件编码格式，读出文件内容

最新推荐文章于 2023-02-15 14:05:48 发布

if-you

最新推荐文章于 2023-02-15 14:05:48 发布

阅读量1k

点赞数

分类专栏： Android 文章标签： android java

本文链接：https://blog.csdn.net/supermess/article/details/126183183

版权

Android 专栏收录该内容

10 篇文章 0 订阅

订阅专栏

/**
 * 根据文件路径获取文件的编码格式
 * @param filePath
 * @return
 */
private static String getTextFileCharset(String filePath) {
    String[] charsets = {"US-ASCII", "UTF-8", "GB2312", "BIG5", "GBK", "GB18030", "UTF-16BE", "UTF-16LE", "UTF-16", "UNICODE"};
    String charset = Charset.defaultCharset().displayName();
    CharsetDecoder decoder;
    BufferedReader br = null;
    String s = null;
    for (int i = 0; i < charsets.length; i++) {
        decoder = Charset.forName(charsets[i]).newDecoder();
        try {
            br = new BufferedReader(new InputStreamReader(new FileInputStream(filePath), decoder));
            do {
                s = br.readLine();
            } while (s != null);
            charset = charsets[i];
            break;
        } catch (FileNotFoundException e) {
            e.printStackTrace();
            break;
        } catch (MalformedInputException e) { //如果编码不能解码此文本就会抛出这个异常
            continue;
        } catch (IOException e) {
            e.printStackTrace();
            break;
        }
    }
    return charset;
}

/**
 * Metodo responsavel por fazer parse de um arquivos de legenda. <br>
 * Obs. O texto n�o vai conter quebra de linhas e pode ser usado Node
 *
 * @param path
 * @return
 */
public static ArrayList<Subtitle> getSubtitlesFromFile(String path, boolean twm, boolean usingNodes) {
    String codeFormat = getTextFileCharset(path);
    ArrayList<Subtitle> subtitles = null;
    Subtitle sub = null;
    StringBuilder srt = null;

    try {
        FileInputStream fileInputStream = new FileInputStream(new File(path));
        BufferedReader br = new BufferedReader(new InputStreamReader(fileInputStream, Charset.forName(codeFormat)));
        subtitles = new ArrayList<>();
        sub = new Subtitle();
        srt = new StringBuilder();

        while (br.ready()) {

            String line = br.readLine();

            Matcher matcher = PATTERN_NUMBERS.matcher(line);

            if (matcher.find()) {
                sub.id = Integer.parseInt(matcher.group(1)); // index
                line = br.readLine();
            }

            matcher = PATTERN_TIME.matcher(line);

            if (matcher.find()) {
                sub.startTime = matcher.group(1); // start time
                sub.timeIn = SRTUtils.textTimeToMillis(sub.startTime);
                sub.endTime = matcher.group(2); // end time
                sub.timeOut = SRTUtils.textTimeToMillis(sub.endTime);
            }

            String aux;
            while ((aux = br.readLine()) != null && !aux.isEmpty()) {
                srt.append(aux);
                if (twm)
                    srt.append("\n");
                else {
                    if (!line.endsWith(" ")) // for new lines '\n' removed from BufferedReader
                        srt.append(" ");
                }
            }

            srt.delete(srt.length() > 0 ? srt.length() - 1 : 0, srt.length()); // remove '\n' or space from end string

            line = srt.toString();
            srt.setLength(0);

            if (line != null && !line.isEmpty())
                line = line.replaceAll("<[^>]*>", ""); // clear all tags

            sub.text = line;
            subtitles.add(sub);
            if (usingNodes) {
                sub.nextSubtitle = new Subtitle();
                sub = sub.nextSubtitle;
            } else {
                sub = new Subtitle();
            }
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
    return subtitles;
}