Examples of SuffixStringMatcher

org.apache.nutch.util.SuffixStringMatcher
A class for efficiently matching Strings against a set of suffixes. Zero-length Strings are ignored.

Examples of org.apache.nutch.util.SuffixStringMatcher

    // handle missing config file
    if (reader == null) {
      if (LOG.isWarnEnabled()) {
        LOG.warn("Missing urlfilter.suffix.file, all URLs will be rejected!");
      }
      suffixes = new SuffixStringMatcher(new String[0]);
      modeAccept = false;
      ignoreCase = false;
      return;
    }
    BufferedReader in = new BufferedReader(reader);
    List aSuffixes = new ArrayList();
    boolean allow = false;
    boolean ignore = false;
    String line;


    while ((line = in.readLine()) != null) {
      if (line.length() == 0) continue;


      char first = line.charAt(0);
      switch (first) {
        case ' ':
        case '\n':
        case '#': // skip blank & comment lines
          break;
        case '-':
          allow = false;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        case '+':
          allow = true;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        default:
          aSuffixes.add(line);
      }
    }
    if (ignore) {
      for (int i = 0; i < aSuffixes.size(); i++) {
        aSuffixes.set(i, ((String) aSuffixes.get(i)).toLowerCase());
      }
    }
    suffixes = new SuffixStringMatcher(aSuffixes);
    modeAccept = allow;
    ignoreCase = ignore;
  }

View Full Code Here

Examples of org.apache.nutch.util.SuffixStringMatcher

    // handle missing config file
    if (reader == null) {
      if (LOG.isWarnEnabled()) {
        LOG.warn("Missing urlfilter.suffix.file, all URLs will be rejected!");
      }
      suffixes = new SuffixStringMatcher(new String[0]);
      modeAccept = false;
      ignoreCase = false;
      return;
    }
    BufferedReader in = new BufferedReader(reader);
    List<String> aSuffixes = new ArrayList<String>();
    boolean allow = false;
    boolean ignore = false;
    String line;


    while ((line = in.readLine()) != null) {
      if (line.length() == 0) continue;


      char first = line.charAt(0);
      switch (first) {
        case ' ':
        case '\n':
        case '#': // skip blank & comment lines
          break;
        case '-':
          allow = false;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        case '+':
          allow = true;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        default:
          aSuffixes.add(line);
      }
    }
    if (ignore) {
      for (int i = 0; i < aSuffixes.size(); i++) {
        aSuffixes.set(i, ((String) aSuffixes.get(i)).toLowerCase());
      }
    }
    suffixes = new SuffixStringMatcher(aSuffixes);
    modeAccept = allow;
    ignoreCase = ignore;
  }

View Full Code Here

Examples of org.apache.nutch.util.SuffixStringMatcher

    // handle missing config file
    if (reader == null) {
      if (LOG.isWarnEnabled()) {
        LOG.warn("Missing urlfilter.suffix.file, all URLs will be rejected!");
      }
      suffixes = new SuffixStringMatcher(new String[0]);
      modeAccept = false;
      ignoreCase = false;
      return;
    }
    BufferedReader in = new BufferedReader(reader);
    List aSuffixes = new ArrayList();
    boolean allow = false;
    boolean ignore = false;
    String line;


    while ((line = in.readLine()) != null) {
      if (line.length() == 0) continue;


      char first = line.charAt(0);
      switch (first) {
        case ' ':
        case '\n':
        case '#': // skip blank & comment lines
          break;
        case '-':
          allow = false;
          if (line.length() > 1 && line.charAt(1) == 'I')
            ignore = true;
          break;
        case '+':
          allow = true;
          if (line.length() > 1 && line.charAt(1) == 'I')
            ignore = true;
          break;
        default:
          aSuffixes.add(line);
      }
    }
    if (ignore) {
      for (int i = 0; i < aSuffixes.size(); i++) {
        aSuffixes.set(i, ((String) aSuffixes.get(i)).toLowerCase());
      }
    }
    suffixes = new SuffixStringMatcher(aSuffixes);
    modeAccept = allow;
    ignoreCase = ignore;
  }

View Full Code Here

Examples of org.apache.nutch.util.SuffixStringMatcher

    // handle missing config file
    if (reader == null) {
      if (LOG.isWarnEnabled()) {
        LOG.warn("Missing urlfilter.suffix.file, all URLs will be rejected!");
      }
      suffixes = new SuffixStringMatcher(new String[0]);
      modeAccept = false;
      ignoreCase = false;
      return;
    }
    BufferedReader in = new BufferedReader(reader);
    List aSuffixes = new ArrayList();
    boolean allow = false;
    boolean ignore = false;
    String line;


    while ((line = in.readLine()) != null) {
      if (line.length() == 0) continue;


      char first = line.charAt(0);
      switch (first) {
        case ' ':
        case '\n':
        case '#': // skip blank & comment lines
          break;
        case '-':
          allow = false;
          if (line.length() > 1 && line.charAt(1) == 'I')
            ignore = true;
          break;
        case '+':
          allow = true;
          if (line.length() > 1 && line.charAt(1) == 'I')
            ignore = true;
          break;
        default:
          aSuffixes.add(line);
      }
    }
    if (ignore) {
      for (int i = 0; i < aSuffixes.size(); i++) {
        aSuffixes.set(i, ((String) aSuffixes.get(i)).toLowerCase());
      }
    }
    suffixes = new SuffixStringMatcher(aSuffixes);
    modeAccept = allow;
    ignoreCase = ignore;
  }

View Full Code Here

Examples of org.apache.nutch.util.SuffixStringMatcher

    // handle missing config file
    if (reader == null) {
      if (LOG.isWarnEnabled()) {
        LOG.warn("Missing urlfilter.suffix.file, all URLs will be rejected!");
      }
      suffixes = new SuffixStringMatcher(new String[0]);
      modeAccept = false;
      ignoreCase = false;
      return;
    }
    BufferedReader in = new BufferedReader(reader);
    List aSuffixes = new ArrayList();
    boolean allow = false;
    boolean ignore = false;
    String line;


    while ((line = in.readLine()) != null) {
      if (line.length() == 0) continue;


      char first = line.charAt(0);
      switch (first) {
        case ' ':
        case '\n':
        case '#': // skip blank & comment lines
          break;
        case '-':
          allow = false;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        case '+':
          allow = true;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        default:
          aSuffixes.add(line);
      }
    }
    if (ignore) {
      for (int i = 0; i < aSuffixes.size(); i++) {
        aSuffixes.set(i, ((String) aSuffixes.get(i)).toLowerCase());
      }
    }
    suffixes = new SuffixStringMatcher(aSuffixes);
    modeAccept = allow;
    ignoreCase = ignore;
  }

View Full Code Here

Examples of org.apache.nutch.util.SuffixStringMatcher

    // handle missing config file
    if (reader == null) {
      if (LOG.isWarnEnabled()) {
        LOG.warn("Missing urlfilter.suffix.file, all URLs will be rejected!");
      }
      suffixes = new SuffixStringMatcher(new String[0]);
      modeAccept = false;
      ignoreCase = false;
      return;
    }
    BufferedReader in = new BufferedReader(reader);
    List aSuffixes = new ArrayList();
    boolean allow = false;
    boolean ignore = false;
    String line;


    while ((line = in.readLine()) != null) {
      if (line.length() == 0) continue;


      char first = line.charAt(0);
      switch (first) {
        case ' ':
        case '\n':
        case '#': // skip blank & comment lines
          break;
        case '-':
          allow = false;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        case '+':
          allow = true;
          if(line.contains("P"))
            filterFromPath = true;
          if(line.contains("I"))
            ignore = true;
          break;
        default:
          aSuffixes.add(line);
      }
    }
    if (ignore) {
      for (int i = 0; i < aSuffixes.size(); i++) {
        aSuffixes.set(i, ((String) aSuffixes.get(i)).toLowerCase());
      }
    }
    suffixes = new SuffixStringMatcher(aSuffixes);
    modeAccept = allow;
    ignoreCase = ignore;
  }

View Full Code Here

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.