{"id":268,"date":"2007-10-08T00:00:00","date_gmt":"2007-10-08T00:00:00","guid":{"rendered":"http:\/\/www.strongd.net\/?p=268"},"modified":"2007-10-08T00:00:00","modified_gmt":"2007-10-08T00:00:00","slug":"TestRegex regexp","status":"publish","type":"post","link":"https:\/\/www.strongd.net\/?p=268","title":{"rendered":"TestRegex regexp"},"content":{"rendered":"

 
\n

package<\/B><\/FONT> net.strong.util;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.MatchResult;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.Pattern;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.PatternCompiler;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.PatternMatcher;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.PatternMatcherInput;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.Perl5Compiler;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.Perl5Matcher;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.Perl5Substitution;<\/FONT><\/FONT><\/FONT><\/P>
\n

import<\/B><\/FONT> org.apache.oro.text.regex.Util;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

public<\/B><\/FONT> <\/FONT>class<\/B><\/FONT> TestRegex {<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>public<\/B><\/FONT> TestRegex() {}<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>public<\/B><\/FONT> <\/FONT>void<\/B><\/FONT> parseLog() <\/FONT>throws<\/B><\/FONT> Exception {<\/FONT><\/FONT><\/FONT><\/P>
\n

String log1=<\/FONT>“172.26.155.241 – – [26\/Feb\/2001:10:56:03 -0500] \\”GET \/IsAlive.htm HTTP\/1.0\\” 200 15 “<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

String regexp=<\/FONT>“(\\\\d{1,3}\\\\.\\\\d{1,3}\\\\.\\\\d{1,3}\\\\.\\\\d{1,3})\\\\s-\\\\s-\\\\s\\\\[([^\\\\]]+)\\\\]”<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternCompiler compiler=<\/FONT>new<\/B><\/FONT> Perl5Compiler();<\/FONT><\/FONT><\/FONT><\/P>
\n

Pattern pattern=compiler.compile(regexp);<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternMatcher matcher=<\/FONT>new<\/B><\/FONT> Perl5Matcher();<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>if<\/B><\/FONT> (matcher.contains(log1,pattern)) {<\/FONT><\/FONT><\/FONT><\/P>
\n

MatchResult result=matcher.getMatch();<\/FONT><\/FONT><\/FONT><\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(<\/FONT>“IP: “<\/FONT>+result.group(1));<\/FONT><\/FONT><\/FONT><\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(<\/FONT>“Timestamp: “<\/FONT>+result.group(2));<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>public<\/B><\/FONT> <\/FONT>void<\/B><\/FONT> parseHTML() <\/FONT>throws<\/B><\/FONT> Exception {<\/FONT><\/FONT><\/FONT><\/P>
\n

String html=<\/FONT>“<font face=\\”Arial, Serif\\” size=\\”+1\\”color=\\”red\\”>”<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

String regexpForFontTag=<\/FONT>“<\\\\s*font\\\\s+([^>]*)\\\\s*>”<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n

String regexpForFontAttrib=<\/FONT>“([a-z]+)\\\\s*=\\\\s*\\”([^\\”]+)\\””<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternCompiler compiler=<\/FONT>new<\/B><\/FONT> Perl5Compiler();<\/FONT><\/FONT><\/FONT><\/P>
\n

Pattern patternForFontTag=compiler.compile(regexpForFontTag,Perl5Compiler.<\/FONT>CASE_INSENSITIVE_MASK<\/I><\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n

Pattern patternForFontAttrib=compiler.compile(regexpForFontAttrib,Perl5Compiler.<\/FONT>CASE_INSENSITIVE_MASK<\/I><\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternMatcher matcher=<\/FONT>new<\/B><\/FONT> Perl5Matcher();<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>if<\/B><\/FONT> (matcher.contains(html,patternForFontTag)) {<\/FONT><\/FONT><\/FONT><\/P>
\n

MatchResult result=matcher.getMatch();<\/FONT><\/FONT><\/FONT><\/P>
\n

String attrib=result.group(1);<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternMatcherInput input=<\/FONT>new<\/B><\/FONT> PatternMatcherInput(attrib);<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>while<\/B><\/FONT> (matcher.contains(input,patternForFontAttrib)) {<\/FONT><\/FONT><\/FONT><\/P>
\n

result=matcher.getMatch();<\/FONT><\/FONT><\/FONT><\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(result.group(1)+<\/FONT>“: “<\/FONT>+result.group(2));<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>public<\/B><\/FONT> <\/FONT>void<\/B><\/FONT> substitutelink() <\/FONT>throws<\/B><\/FONT> Exception {<\/FONT><\/FONT><\/FONT><\/P>
\n

String link=<\/FONT>“<a href=\\”http:\/\/widgets.acme.com\/interface.html#How_To_Trade\\”>”<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n

String regexpForLink=<\/FONT>“<\\\\s*a\\\\s+href\\\\s*=\\\\s*\\”http:\/\/widgets.acme.com\/interface.html#([^\\”]+)\\”>”<\/FONT>;<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternCompiler compiler=<\/FONT>new<\/B><\/FONT> Perl5Compiler();<\/FONT><\/FONT><\/FONT><\/P>
\n

Pattern patternForLink=compiler.compile(regexpForLink,Perl5Compiler.<\/FONT>CASE_INSENSITIVE_MASK<\/I><\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

PatternMatcher matcher=<\/FONT>new<\/B><\/FONT> Perl5Matcher();<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

String result=Util.substitute<\/I>(matcher,<\/FONT><\/FONT><\/FONT><\/P>
\n

patternForLink,<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>new<\/B><\/FONT> Perl5Substitution(<\/FONT>“<a href=\\”http:\/\/newserver.acme.com\/interface.html#$1\\”>”<\/FONT>),<\/FONT><\/FONT><\/FONT><\/P>
\n

link,<\/FONT><\/FONT><\/FONT><\/P>
\n

Util.<\/FONT>SUBSTITUTE_ALL<\/I><\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(result);<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

<\/FONT>public<\/B><\/FONT> <\/FONT>static<\/B><\/FONT> <\/FONT>void<\/B><\/FONT> main(String[] args) <\/FONT>throws<\/B><\/FONT> Exception {<\/FONT><\/FONT><\/FONT><\/P>
\n

TestRegex test=<\/FONT>new<\/B><\/FONT> TestRegex();<\/FONT><\/FONT><\/FONT><\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(<\/FONT>“\\n\\nLog Parsing Example”<\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n

test.parseLog();<\/FONT><\/FONT><\/FONT><\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(<\/FONT>“\\n\\nHtml Example 1”<\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n

test.parseHTML();<\/FONT><\/FONT><\/FONT><\/P>
\n

System.<\/FONT>out<\/I><\/FONT>.println(<\/FONT>“\\n\\nHtml Example 2”<\/FONT>);<\/FONT><\/FONT><\/FONT><\/P>
\n

test.substitutelink();<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n

}<\/FONT><\/FONT><\/FONT><\/P>
\n


<\/P>
\n


<\/P>
\n

<\/DIV><\/p>\n","protected":false},"excerpt":{"rendered":"

  package net.strong.util; import org.apache.oro.text.regex.MatchResult; import org.apache.oro.text.regex.Pattern; import org.apache.oro.text.regex.PatternCompiler; import org.apache.oro.text.regex.PatternMatcher; import org.apache.oro.text.regex.PatternMatcherInput; import org.apache.oro.text.regex.Perl5Compiler; import org.apache.oro.text.regex.Perl5Matcher; import org.apache.oro.text.regex.Perl5Substitution; import org.apache.oro.text.regex.Util; public class TestRegex { public TestRegex() {} public void parseLog() throws Exception { String log1=“172.26.155.241 – – [26\/Feb\/2001:10:56:03 -0500] \\”GET \/IsAlive.htm HTTP\/1.0\\” 200 15 “; String regexp=“(\\\\d{1,3}\\\\.\\\\d{1,3}\\\\.\\\\d{1,3}\\\\.\\\\d{1,3})\\\\s-\\\\s-\\\\s\\\\[([^\\\\]]+)\\\\]”; PatternCompiler compiler=new Perl5Compiler(); Pattern pattern=compiler.compile(regexp); PatternMatcher matcher=new … Continue reading TestRegex regexp<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-268","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/www.strongd.net\/index.php?rest_route=\/wp\/v2\/posts\/268","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.strongd.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.strongd.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.strongd.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.strongd.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=268"}],"version-history":[{"count":0,"href":"https:\/\/www.strongd.net\/index.php?rest_route=\/wp\/v2\/posts\/268\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.strongd.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=268"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.strongd.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=268"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.strongd.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=268"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}