This project has retired. For details please refer to its Attic page.
Filter xref
View Javadoc

1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one
3    * or more contributor license agreements.  See the NOTICE file
4    * distributed with this work for additional information
5    * regarding copyright ownership.  The ASF licenses this file
6    * to you under the Apache License, Version 2.0 (the
7    * "License"); you may not use this file except in compliance
8    * with the License.  You may obtain a copy of the License at
9    *
10   *     http://www.apache.org/licenses/LICENSE-2.0
11   *
12   * Unless required by applicable law or agreed to in writing, software
13   * distributed under the License is distributed on an "AS IS" BASIS,
14   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15   * See the License for the specific language governing permissions and
16   * limitations under the License.
17   */
18  package org.apache.hadoop.chukwa.util;
19  
20  import java.util.ArrayList;
21  import java.util.List;
22  import java.util.regex.Pattern;
23  import java.util.regex.PatternSyntaxException;
24  import org.apache.commons.lang.ArrayUtils;
25  import org.apache.hadoop.chukwa.Chunk;
26  import org.apache.hadoop.chukwa.extraction.engine.RecordUtil;
27  import org.apache.hadoop.chukwa.util.RegexUtil.CheckedPatternSyntaxException;
28  import org.apache.log4j.Logger;
29  
30  
31  public class Filter {
32  
33    static Logger log = Logger.getLogger(Filter.class);
34  
35    private static final String[] SEARCH_TARGS = 
36    {"datatype", "name", "host", "cluster", "content"};
37    static final String SEPARATOR="&";
38    
39    private static class SearchRule {
40      Pattern p;
41      String targ;
42      
43      SearchRule(Pattern p, String t) {
44        this.p = p;
45        this.targ = t;
46      }
47      
48      boolean matches(Chunk chunk) {
49        if(targ.equals("datatype")) {
50          return p.matcher(chunk.getDataType()).matches();
51        } else if(targ.equals("name")) {
52          return p.matcher(chunk.getStreamName()).matches();
53        } else if(targ.equals("host")) {
54          return p.matcher(chunk.getSource()).matches();
55        } else if(targ.equals("cluster")) {
56          String cluster = RecordUtil.getClusterName(chunk);
57          return p.matcher(cluster).matches();
58        } else if(targ.equals("content")) {
59          String content = new String(chunk.getData());
60          return p.matcher(content).matches();
61        } else if(targ.startsWith("tags.")) {
62          String tagName = targ.substring("tags.".length());
63          if (!RegexUtil.isRegex(tagName)) {
64            log.warn("Error parsing 'tagName' as a regex: "
65                + RegexUtil.regexError(tagName));
66            return false;
67          }
68          String tagVal = chunk.getTag(tagName);
69          if(tagVal == null)
70            return false;
71          return p.matcher(tagVal).matches();
72        } else { 
73          assert false: "unknown target: " +targ;
74          return false;
75        }
76      }
77      
78      public String toString() {
79        return targ + "=" +p.toString();
80      } 
81    }
82  
83    List<SearchRule> compiledPatterns;
84      
85    public Filter(String listOfPatterns) throws CheckedPatternSyntaxException {
86      compiledPatterns = new ArrayList<SearchRule>();
87      //FIXME: could escape these
88      String[] patterns = listOfPatterns.split(SEPARATOR);
89      for(String p: patterns) {
90        int equalsPos = p.indexOf('=');
91        
92        if(equalsPos < 0 || equalsPos > (p.length() -2)) {
93          throw new CheckedPatternSyntaxException(
94              "pattern must be of form targ=pattern", p, -1);
95        }
96        
97        String targ = p.substring(0, equalsPos);
98        if(!targ.startsWith("tags.") && !ArrayUtils.contains(SEARCH_TARGS, targ)) {
99          throw new CheckedPatternSyntaxException(
100             "pattern doesn't start with recognized search target", p, -1);
101       }
102       
103       String regex = p.substring(equalsPos+1);
104       if (!RegexUtil.isRegex(regex)) {
105           throw new CheckedPatternSyntaxException(RegexUtil.regexException(regex));
106       }
107 
108       Pattern pat = Pattern.compile(regex, Pattern.DOTALL);
109       compiledPatterns.add(new SearchRule(pat, targ));
110     }
111   }
112 
113   public boolean matches(Chunk chunk) {
114     for(SearchRule r: compiledPatterns) {
115       if(!r.matches(chunk))
116         return false;
117     }
118     return true;
119   }
120   
121   int size() {
122     return compiledPatterns.size();
123   }
124   
125   public String toString() {
126     StringBuilder sb = new StringBuilder();
127     sb.append(compiledPatterns.get(0));
128     for(int i=1; i < compiledPatterns.size(); ++i) {
129       sb.append(" & ");
130       sb.append(compiledPatterns.get(i));
131     }
132     return sb.toString();
133   }
134   
135   private static final class MatchAll extends Filter {
136     public MatchAll() throws CheckedPatternSyntaxException {
137       super("datatype=.*");
138     }
139     
140     public boolean matches(Chunk c) {
141       return true;
142     }
143     
144     public String toString() {
145       return "ALL";
146     }
147   } 
148 
149   public static final Filter ALL = newMatchAll();
150   private static Filter newMatchAll() {
151     try {
152       return new MatchAll();
153     } catch (CheckedPatternSyntaxException e) {
154       throw new RuntimeException("Illegal MatchAll regular expression.", e);
155     }
156   }
157   
158 }//end class