java对文本字符串的压缩与解压

为什么80%的码农都做不了架构师？>>>   

public class GzipUtil {
    /**
     * @param str
     * @return 压缩
     */
    public static String compress(String str) {
        if (str == null || str.length() == 0) {
            return str;
        }
        ByteArrayOutputStream out = null;
        GZIPOutputStream gzip = null;
        String compress = "";
        try {
            out = new ByteArrayOutputStream();
            gzip = new GZIPOutputStream(out);
            gzip.write(str.getBytes());
            gzip.close();
            compress = out.toString("ISO-8859-1");
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (null != out) {
                try {
                    out.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return compress;
    }
 
    /**
     * @param str
     * @return 解压缩
     */
    public static String uncompress(String str) {
        if (str == null || str.length() == 0) {
            return str;
        }
        ByteArrayOutputStream out = null;
        ByteArrayInputStream in = null;
        GZIPInputStream gzip = null;
        String uncompress = "";
        try {
            out = new ByteArrayOutputStream();
            in = new ByteArrayInputStream(str.getBytes("ISO-8859-1"));
            gzip = new GZIPInputStream(in);
            byte[] buffer = new byte[1024];
            int offset = -1;
            while ((offset = gzip.read(buffer)) != -1) {
                out.write(buffer, 0, offset);
            }
            uncompress = out.toString();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (null != gzip) {
                try {
                    gzip.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (null != in) {
                try {
                    in.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (null != out) {
                try {
                    out.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return uncompress;
    }
 
    public static void main(String[] args) throws IOException {
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 10; i++) {
            sb.append("代码笔记：www.note52.com");
        }
        String str = sb.toString();
        System.out.println("原长度：" + str.length());
 
        System.out.println("压缩后长度：" + GzipUtil.compress(str).length());
        String compress = GzipUtil.compress(str);
        System.out.println("压缩后内容：" + compress);
        System.out.println("解压后内容：" + GzipUtil.uncompress(compress));
    }
}

这段代码的压缩效率还是比较高的，对于大段文本，能压缩到原文本的10%左右。但是有个问题时，这个压缩会出现特殊字符，如果用web service调用或者其他封装成xml格式数据时候，会报异常。那么，我们可以，将压缩后的文本通过base64进行编码，解压缩之前先进行base64解码，这样就可以避免特殊字符问题了。如下面代码

public class GzipUtil {
    /**
     * @param str
     * @return 压缩
     */
    public static String compress(String str) {
        if (str == null || str.length() == 0) {
            return str;
        }
        ByteArrayOutputStream out = null;
        GZIPOutputStream gzip = null;
        String compress = "";
        try {
            out = new ByteArrayOutputStream();
            gzip = new GZIPOutputStream(out);
            gzip.write(str.getBytes());
            gzip.close();
            // 这里增加base64编码
            byte[] compressed = out.toByteArray();
            compress = new sun.misc.BASE64Encoder().encodeBuffer(compressed);
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (null != out) {
                try {
                    out.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return compress;
    }
 
    /**
     * @param str
     * @return 解压缩
     */
    public static String uncompress(String str) {
        if (str == null || str.length() == 0) {
            return str;
        }
        ByteArrayOutputStream out = null;
        ByteArrayInputStream in = null;
        GZIPInputStream gzip = null;
        String uncompress = "";
        try {
            out = new ByteArrayOutputStream();
            // 这里增加base64解码
            byte[] compressed = new sun.misc.BASE64Decoder().decodeBuffer(str);
            in = new ByteArrayInputStream(compressed);
            gzip = new GZIPInputStream(in);
            byte[] buffer = new byte[1024];
            int offset = -1;
            while ((offset = gzip.read(buffer)) != -1) {
                out.write(buffer, 0, offset);
            }
            uncompress = out.toString();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (null != gzip) {
                try {
                    gzip.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (null != in) {
                try {
                    in.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
            if (null != out) {
                try {
                    out.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
        return uncompress;
    }
 
    public static void main(String[] args) throws IOException {
        StringBuilder sb = new StringBuilder();
        for (int i = 0; i < 10; i++) {
            sb.append("代码笔记：www.note52.com");
        }
        String str = sb.toString();
        System.out.println("原长度：" + str.length());
 
        System.out.println("压缩后长度：" + GzipUtil.compress(str).length());
        String compress = GzipUtil.compress(str);
        System.out.println("压缩后内容：" + compress);
        System.out.println("解压后内容：" + GzipUtil.uncompress(compress));
    }
}

base64编码后，就不会出现特殊字符了，完美解决xml传输问题。

转载于:https://my.oschina.net/jywm/blog/784593