壓縮jsp,html中的代碼，去掉所有空白符、換行符
package zj.compress.util;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/*******************************************
* 壓縮jsp,html中的代碼，去掉所有空白符、換行符
*
* @author 張軍
* @version 0.1
* @date 2010-5-13
*******************************************/
public class HtmlCompressor {
private static String tempPreBlock = "%%%HTMLCOMPRESS~PRE&&&";
private static String tempTextAreaBlock = "%%%HTMLCOMPRESS~TEXTAREA&&&";
private static String tempScriptBlock = "%%%HTMLCOMPRESS~SCRIPT&&&";
private static String tempStyleBlock = "%%%HTMLCOMPRESS~STYLE&&&";
private static String tempJspBlock = "%%%HTMLCOMPRESS~JSP&&&";
/**
*
*
* @see flag的取值范圍如下：
* @see Pattern.CANON_EQ 當且僅當兩個字符的"正規分解(canonical decomposition)"都完全相同的情況下，才認定匹配。比如用了這個標志之后，表達式"a\u030A"會匹配"?"。默認情況下，不考慮"規 范相等性(canonical equivalence)"。
* @see Pattern.CASE_INSENSITIVE(?i) 默認情況下，大小寫不明感的匹配只適用于US-ASCII字符集。這個標志能讓表達式忽略大小寫進行匹配。要想對Unicode字符進行大小不明感的匹 配，只要將UNICODE_CASE與這個標志合起來就行了。
* @see Pattern.COMMENTS(?x) 在這種模式下，匹配時會忽略(正則表達式里的)空格字符(譯者注：不是指表達式里的"\\s"，而是指表達式里的空格，tab，回車之類)。注釋從#開始，一直到這行結束。可以通過嵌入式的標志來啟用Unix行模式。
* @see Pattern.DOTALL(?s) 在這種模式下，表達式'.'可以匹配任意字符，包括表示一行的結束符。默認情況下，表達式'.'不匹配行的結束符。
* @see Pattern.MULTILINE (?m) 在這種模式下，'^'和'$'分別匹配一行的開始和結束。此外，'^'仍然匹配字符串的開始，'$'也匹配字符串的結束。默認情況下，這兩個表達式僅僅匹配字符串的開始和結束。
* @see Pattern.UNICODE_CASE (?u) 在這個模式下，如果你還啟用了CASE_INSENSITIVE標志，那么它會對Unicode字符進行大小寫不明感的匹配。默認情況下，大小寫不敏感的匹配只適用于US-ASCII字符集。
* @see Pattern.UNIX_LINES(?d) 在這個模式下，只有'\n'才被認作一行的中止，并且與'.'，'^'，以及'$'進行匹配。
*/
// 注釋
private static Pattern commentPattern = Pattern.compile("<!--\\s*[^\\[].*?-->", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// 換行
private static Pattern itsPattern = Pattern.compile(">\\s+?<", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// pre標簽
private static Pattern prePattern = Pattern.compile("<pre[^>]*?>.*?</pre>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// textarea標簽
private static Pattern taPattern = Pattern.compile("<textarea[^>]*?>.*?</textarea>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// jsp標簽
private static Pattern jspPattern = Pattern.compile("<%([^-@][\\w\\W]*?)%>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// <script></script>
private static Pattern scriptPattern = Pattern.compile("(?:<script\\s*>|<script type=['\"]text/javascript['\"]\\s*>)(.*?)</script>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// style標簽
private static Pattern stylePattern = Pattern.compile("<style[^>()]*?>(.+)</style>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
// 單行注釋，
private static Pattern signleCommentPattern = Pattern.compile("//.*");
// 字符串匹配
private static Pattern stringPattern = Pattern.compile("(\"[^\"\\n]*?\"|'[^'\\n]*?')");
// trim去空格和換行符
private static Pattern trimPattern = Pattern.compile("\\n\\s*", Pattern.MULTILINE);
private static Pattern trimPattern2 = Pattern.compile("\\s*\\r", Pattern.MULTILINE);
// 多行注釋
private static Pattern multiCommentPattern = Pattern.compile("/\\*.*?\\*/", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
private static String tempSingleCommentBlock = "%%%HTMLCOMPRESS~SINGLECOMMENT&&&"; // //占位符
private static String tempMulitCommentBlock1 = "%%%HTMLCOMPRESS~MULITCOMMENT1&&&"; // /*占位符
private static String tempMulitCommentBlock2 = "%%%HTMLCOMPRESS~MULITCOMMENT2&&&"; // */占位符
public static String compress(String html) throws Exception {
if (html == null || html.length() == 0) {
return html;
}
List<String> preBlocks = new ArrayList<String>();
List<String> taBlocks = new ArrayList<String>();
List<String> scriptBlocks = new ArrayList<String>();
List<String> styleBlocks = new ArrayList<String>();
List<String> jspBlocks = new ArrayList<String>();
String result = html;
// preserve inline java code
Matcher jspMatcher = jspPattern.matcher(result);
while (jspMatcher.find()) {
jspBlocks.add(jspMatcher.group(0));
}
result = jspMatcher.replaceAll(tempJspBlock);
// preserve PRE tags
Matcher preMatcher = prePattern.matcher(result);
while (preMatcher.find()) {
preBlocks.add(preMatcher.group(0));
}
result = preMatcher.replaceAll(tempPreBlock);
// preserve TEXTAREA tags
Matcher taMatcher = taPattern.matcher(result);
while (taMatcher.find()) {
taBlocks.add(taMatcher.group(0));
}
result = taMatcher.replaceAll(tempTextAreaBlock);
// preserve SCRIPT tags
Matcher scriptMatcher = scriptPattern.matcher(result);
while (scriptMatcher.find()) {
scriptBlocks.add(scriptMatcher.group(0));
}
result = scriptMatcher.replaceAll(tempScriptBlock);
// don't process inline css
Matcher styleMatcher = stylePattern.matcher(result);
while (styleMatcher.find()) {
styleBlocks.add(styleMatcher.group(0));
}
result = styleMatcher.replaceAll(tempStyleBlock);
// process pure html
result = processHtml(result);
// process preserved blocks
result = processPreBlocks(result, preBlocks);
result = processTextareaBlocks(result, taBlocks);
result = processScriptBlocks(result, scriptBlocks);
result = processStyleBlocks(result, styleBlocks);
result = processJspBlocks(result, jspBlocks);
preBlocks = taBlocks = scriptBlocks = styleBlocks = jspBlocks = null;
return result.trim();
}
private static String processHtml(String html) {
String result = html;
// remove comments
// if(removeComments) {
result = commentPattern.matcher(result).replaceAll("");
// }
// remove inter-tag spaces
// if(removeIntertagSpaces) {
result = itsPattern.matcher(result).replaceAll("><");
// }
// remove multi whitespace characters
// if(removeMultiSpaces) {
result = result.replaceAll("\\s{2,}", " ");
// }
return result;
}
private static String processJspBlocks(String html, List<String> blocks) {
String result = html;
for (int i = 0; i < blocks.size(); i++) {
blocks.set(i, compressJsp(blocks.get(i)));
}
// put preserved blocks back
while (result.contains(tempJspBlock)) {
result = result.replaceFirst(tempJspBlock, Matcher.quoteReplacement(blocks.remove(0)));
}
return result;
}
private static String processPreBlocks(String html, List<String> blocks) throws Exception {
String result = html;
// put preserved blocks back
while (result.contains(tempPreBlock)) {
result = result.replaceFirst(tempPreBlock, Matcher.quoteReplacement(blocks.remove(0)));
}
return result;
}
private static String processTextareaBlocks(String html, List<String> blocks) throws Exception {
String result = html;
// put preserved blocks back
while (result.contains(tempTextAreaBlock)) {
result = result.replaceFirst(tempTextAreaBlock, Matcher.quoteReplacement(blocks.remove(0)));
}
return result;
}
private static String processScriptBlocks(String html, List<String> blocks) throws Exception {
String result = html;
// if(compressJavaScript) {
for (int i = 0; i < blocks.size(); i++) {
blocks.set(i, compressJavaScript(blocks.get(i)));
}
// }
// put preserved blocks back
while (result.contains(tempScriptBlock)) {
result = result.replaceFirst(tempScriptBlock, Matcher.quoteReplacement(blocks.remove(0)));
}
return result;
}
private static String processStyleBlocks(String html, List<String> blocks) throws Exception {
String result = html;
// if(compressCss) {
for (int i = 0; i < blocks.size(); i++) {
blocks.set(i, compressCssStyles(blocks.get(i)));
}
// }
// put preserved blocks back
while (result.contains(tempStyleBlock)) {
result = result.replaceFirst(tempStyleBlock, Matcher.quoteReplacement(blocks.remove(0)));
}
return result;
}
private static String compressJsp(String source) {
// check if block is not empty
Matcher jspMatcher = jspPattern.matcher(source);
if (jspMatcher.find()) {
String result = compressJspJs(jspMatcher.group(1));
return (new StringBuilder(source.substring(0, jspMatcher.start(1))).append(result).append(source.substring(jspMatcher.end(1)))).toString();
} else {
return source;
}
}
private static String compressJavaScript(String source) {
// check if block is not empty
Matcher scriptMatcher = scriptPattern.matcher(source);
if (scriptMatcher.find()) {
String result = compressJspJs(scriptMatcher.group(1));
return (new StringBuilder(source.substring(0, scriptMatcher.start(1))).append(result).append(source.substring(scriptMatcher.end(1)))).toString();
} else {
return source;
}
}
private static String compressCssStyles(String source) {
// check if block is not empty
Matcher styleMatcher = stylePattern.matcher(source);
if (styleMatcher.find()) {
// 去掉注釋，換行
String result = multiCommentPattern.matcher(styleMatcher.group(1)).replaceAll("");
result = trimPattern.matcher(result).replaceAll("");
result = trimPattern2.matcher(result).replaceAll("");
return (new StringBuilder(source.substring(0, styleMatcher.start(1))).append(result).append(source.substring(styleMatcher.end(1)))).toString();
} else {
return source;
}
}
private static String compressJspJs(String source) {
String result = source;
// 因注釋符合有可能出現在字符串中，所以要先把字符串中的特殊符好去掉
Matcher stringMatcher = stringPattern.matcher(result);
while (stringMatcher.find()) {
String tmpStr = stringMatcher.group(0);
if (tmpStr.indexOf("//") != -1 || tmpStr.indexOf("/*") != -1 || tmpStr.indexOf("*/") != -1) {
String blockStr = tmpStr.replaceAll("//", tempSingleCommentBlock).replaceAll("/\\*", tempMulitCommentBlock1).replaceAll("\\*/", tempMulitCommentBlock2);
result = result.replace(tmpStr, blockStr);
}
}
// 去掉注釋
result = signleCommentPattern.matcher(result).replaceAll("");
result = multiCommentPattern.matcher(result).replaceAll("");
result = trimPattern2.matcher(result).replaceAll("");
result = trimPattern.matcher(result).replaceAll(" ");
// 恢復替換掉的字符串
result = result.replaceAll(tempSingleCommentBlock, "//").replaceAll(tempMulitCommentBlock1, "/*").replaceAll(tempMulitCommentBlock2, "*/");
return result;
}
}
本文為張軍原創文章,轉載無需和我聯系,但請注明來自張軍的軍軍小站,個人博客http://www.dlhighland.cn
更多文章、技術交流、商務合作、聯系博主
微信掃碼或搜索：z360901061
微信掃一掃加我為好友
QQ號聯系： 360901061
您的支持是博主寫作最大的動力，如果您喜歡我的文章，感覺我的文章對您有幫助，請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧，狠狠點擊下面給點支持吧，站長非常感激您！手機微信長按不能支付解決辦法：請將微信支付二維碼保存到相冊，切換到微信，然后點擊微信右上角掃一掃功能，選擇支付二維碼完成支付。
【本文對您有幫助就好】元
