|
|
在“JS、CSS的合并、壓縮、緩存管理”一文中說到自己寫過的1個自動合并、壓縮JS,CSS,并添加版本號的組件。這次把壓縮html的功能也加入到該組件中，流程很簡單，就是在程序啟動(contextInitialized or Application_Start)的時候掃描所有html,jsp(ASPx)進行壓縮。
壓縮的注意事項：
實現的方式主要是用正則表達式去查找，替換。在html壓縮的時候，主要要注意下面幾點：
1. pre,textarea 標簽里面的內容格式需要保留，不能壓縮。
2. 去掉html注釋的時候，有些注釋是不能去掉的，比如：<!--[if IE 6]> ..... <![endif]-->
3. 壓縮嵌入式js中的注釋要注意，因為可能注釋符號會出現在字符串中，比如： var url = "http://www.cnblogs.com"; // 前面的//不是注釋
去掉JS換行符的時候，不能直接跟一下行動內容，需要有空格，考慮下面的代碼：
else
return;
如果不帶空格，則變成elsereturn。
4. jsp(ASPx) 中很有可能會使用<% %>嵌入一些服務器代碼，這個時候也需要單獨處理，里面注釋的處理方法跟js的一樣。
源代碼：
下面是Java實現的源代碼，也可以 猛擊此處 下載該代碼，相信大家都看的懂，也很容易改成NET代碼：
復制代碼 代碼如下:
import Java.io.StringReader;
import Java.io.StringWriter;
import Java.util.*;
import Java.util.regex.*;
/*******************************************
* 壓縮jsp,html中的代碼，去掉所有空白符、換行符
* @author bearrui(ak-47)
* @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&&&";
private static Pattern commentPattern = Pattern.compile("<!--//s*[^//[].*?-->", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
private static Pattern itsPattern = Pattern.compile(">//s+?<", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
private static Pattern prePattern = Pattern.compile("<pre[^>]*?>.*?</pre>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
private static Pattern taPattern = Pattern.compile("<textarea[^>]*?>.*?</textarea>", Pattern.DOTALL | Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
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);
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("http://.*");
// 字符串匹配
private static Pattern stringPattern = Pattern.compile("(/"[^/"http://n]*?/"|'[^'//n]*?')");
// trim去空格和換行符
private static Pattern trimPattern = Pattern.compile("http://n//s*",Pattern.MULTILINE);
private static Pattern trimPattern2 = Pattern.compile("http://s*//r",Pattern.MULTILINE);
// 多行注釋
private static Pattern multiCommentPattern = Pattern.compile("http:///*.*?//*/", 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("http://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("http://") != -1 || tmpStr.indexOf("/*") != -1 || tmpStr.indexOf("*/") != -1){
String blockStr = tmpStr.replaceAll("http://", tempSingleCommentBlock).replaceAll("http:///*", tempMulitCommentBlock1)
.replaceAll("http://*/", 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, "http://").replaceAll(tempMulitCommentBlock1, "/*")
.replaceAll(tempMulitCommentBlock2, "*/");
return result;
}
}
使用注意事項：
使用了上面方法后，再運行程序，是不是發現每個頁面查看源代碼的時候都變成1行啦，還不錯吧，但是在使用的時候還是要注意一些問題：
1. 嵌入js本來想調用yuicompressor來壓縮，yuicompressor壓縮JS前，會先編譯js是否合法，因我們嵌入的js中可能很多會用到一些服務器端代碼，比如 var now = <%=DateTime.now %> ，這樣的代碼會編譯不通過，所以無法使用yuicompressor。
最后只能自己寫壓縮JS代碼，自己寫的比較粗燥，所以有個問題還解決，就是如果開發人員在一句js代碼后面沒有加分號的話，壓縮成1行就很有可能出問題。所以使用這個需要保證每條語句結束后都必須帶分號。
2. 因為是在程序啟動的時候壓縮所有jsp(ASPx)，所以如果是用戶請求的時候動態產生的html就無法壓縮。
JavaScript技術：WEB高性能開發之瘋狂的HTML壓縮，轉載需保留來源！
鄭重聲明：本文版權歸原作者所有，轉載文章僅為傳播更多信息之目的，如作者信息標記有誤，請第一時間聯系我們修改或刪除，多謝。
