X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java

diff --git a/lucene-java-3.5.0/lucene/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java b/lucene-java-3.5.0/lucene/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java
new file mode 100644
index 0000000..ce19ecd
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java
@@ -0,0 +1,136 @@
+package org.apache.lucene.benchmark.byTask.feeds;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.File;
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.Locale;
+import java.util.Map;
+
+/** 
+ * Parser for trec doc content, invoked on doc text excluding <DOC> and <DOCNO>
+ * which are handled in TrecContentSource. Required to be stateless and hence thread safe. 
+ */
+public abstract class TrecDocParser {
+
+  /** Types of trec parse paths, */
+  public enum ParsePathType { GOV2, FBIS, FT, FR94, LATIMES }
+  
+  /** trec parser type used for unknown extensions */
+  public static final ParsePathType DEFAULT_PATH_TYPE  = ParsePathType.GOV2;
+
+  static final Map<ParsePathType,TrecDocParser> pathType2parser = new HashMap<ParsePathType,TrecDocParser>();
+  static {
+    pathType2parser.put(ParsePathType.GOV2, new TrecGov2Parser());
+    pathType2parser.put(ParsePathType.FBIS, new TrecFBISParser());
+    pathType2parser.put(ParsePathType.FR94, new TrecFR94Parser());
+    pathType2parser.put(ParsePathType.FT, new TrecFTParser());
+    pathType2parser.put(ParsePathType.LATIMES, new TrecLATimesParser());
+  }
+
+  static final Map<String,ParsePathType> pathName2Type = new HashMap<String,ParsePathType>();
+  static {
+    for (ParsePathType ppt : ParsePathType.values()) {
+      pathName2Type.put(ppt.name().toUpperCase(Locale.ENGLISH),ppt);
+    }
+  }
+  
+  /** max length of walk up from file to its ancestors when looking for a known path type */ 
+  private static final int MAX_PATH_LENGTH = 10;
+  
+  /**
+   * Compute the path type of a file by inspecting name of file and its parents
+   */
+  public static ParsePathType pathType(File f) {
+    int pathLength = 0;
+    while (f != null && ++pathLength < MAX_PATH_LENGTH) {
+      ParsePathType ppt = pathName2Type.get(f.getName().toUpperCase(Locale.ENGLISH));
+      if (ppt!=null) {
+        return ppt;
+      }
+      f = f.getParentFile();
+    }
+    return DEFAULT_PATH_TYPE;
+  }
+  
+  /** 
+   * parse the text prepared in docBuf into a result DocData, 
+   * no synchronization is required.
+   * @param docData reusable result
+   * @param name name that should be set to the result
+   * @param trecSrc calling trec content source  
+   * @param docBuf text to parse  
+   * @param pathType type of parsed file, or null if unknown - may be used by 
+   * parsers to alter their behavior according to the file path type. 
+   */  
+  public abstract DocData parse(DocData docData, String name, TrecContentSource trecSrc, 
+      StringBuilder docBuf, ParsePathType pathType) throws IOException, InterruptedException;
+  
+  /** 
+   * strip tags from <code>buf</code>: each tag is replaced by a single blank.
+   * @return text obtained when stripping all tags from <code>buf</code> (Input StringBuilder is unmodified).
+   */
+  public static String stripTags(StringBuilder buf, int start) {
+    return stripTags(buf.substring(start),0);
+  }
+
+  /** 
+   * strip tags from input.
+   * @see #stripTags(StringBuilder, int)
+   */
+  public static String stripTags(String buf, int start) {
+    if (start>0) {
+      buf = buf.substring(0);
+    }
+    return buf.replaceAll("<[^>]*>", " ");
+  }
+  
+  /**
+   * Extract from <code>buf</code> the text of interest within specified tags
+   * @param buf entire input text
+   * @param startTag tag marking start of text of interest 
+   * @param endTag tag marking end of text of interest
+   * @param maxPos if &ge; 0 sets a limit on start of text of interest
+   * @return text of interest or null if not found
+   */
+  public static String extract(StringBuilder buf, String startTag, String endTag, int maxPos, String noisePrefixes[]) {
+    int k1 = buf.indexOf(startTag);
+    if (k1>=0 && (maxPos<0 || k1<maxPos)) {
+      k1 += startTag.length();
+      int k2 = buf.indexOf(endTag,k1);
+      if (k2>=0 && (maxPos<0 || k2<maxPos)) { // found end tag with allowed range
+        if (noisePrefixes != null) {
+          for (String noise : noisePrefixes) {
+            int k1a = buf.indexOf(noise,k1);
+            if (k1a>=0 && k1a<k2) {
+              k1 = k1a + noise.length();
+            }
+          }          
+        }
+        return buf.substring(k1,k2).trim();
+      }
+    }
+    return null;
+  }
+
+  //public static void main(String[] args) {
+  //  System.out.println(stripTags("is it true that<space>2<<second space>><almost last space>1<one more space>?",0));
+  //}
+
+}