Package org.archive.wayback

Examples of org.archive.wayback.UrlCanonicalizer

142
143
144
145
146
147
148
149
150
151
152
    }
    String path = args[0];
    String name = args[1];
    String op = args[2];
    BDBIndex index = new BDBIndex();
    UrlCanonicalizer canonicalizer = new AggressiveUrlCanonicalizer();
    try {
      index.initializeDB(path,name);
    } catch (IOException e) {
      e.printStackTrace();
      System.exit(1);
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
   * @param args
   */
  public static void main(String[] args) {
    String cdxSpec = CDXFormatIndex.CDX_HEADER_MAGIC;
    PrintWriter pw = new PrintWriter(System.out);
    UrlCanonicalizer canonicalizer = new AggressiveUrlCanonicalizer();
    boolean setFormat = false;
    boolean isIdentity = false;
    String path = null;
    if(args.length == 0) {
      USAGE();
View Full Code Here
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
    String urlkey = null;
   
    // If no canonicalizer is set, use selfRedirFilter's canonicalizer
    // Either selfRedirFilter or a canonicalizer must be set
   
    UrlCanonicalizer canon = getCanonicalizer();
   
    if (canon == null && selfRedirFilter != null) {
      canon = selfRedirFilter.getCanonicalizer();
    }
   
    if (canon == null) {
      throw new IllegalArgumentException("Unable to find canonicalizer, canonicalizer property or selfRedirFilter property must be set");
    }
   
    try {
      urlkey = canon.urlStringToKey(wbRequest.getRequestUrl());
    } catch (URIException ue) {
      throw new BadQueryException(ue.toString());
    }

    //Do local access/url validation check   
View Full Code Here
TOP

Related Classes of org.archive.wayback.UrlCanonicalizer

  • org.archive.wayback.resourceindex.bdb.BDBIndex
  • org.archive.wayback.resourceindex.cdxserver.EmbeddedCDXServerIndex
  • org.archive.wayback.resourcestore.indexer.IndexWorker
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.