pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / analyzers / common / src / test / org / apache / lucene / analysis / path / TestPathHierarchyTokenizer.java

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/path/TestPathHierarchyTokenizer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/path/TestPathHierarchyTokenizer.java
new file mode 100644 (file)
index 0000000..947479d
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/path/TestPathHierarchyTokenizer.java
@@ -0,0 +1,196 @@
+package org.apache.lucene.analysis.path;
+
+/**
+ * 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.StringReader;
+
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.CharStream;
+import org.apache.lucene.analysis.MappingCharFilter;
+import org.apache.lucene.analysis.NormalizeCharMap;
+
+public class TestPathHierarchyTokenizer extends BaseTokenStreamTestCase {
+
+  public void testBasic() throws Exception {
+    String path = "/a/b/c";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path) );
+    assertTokenStreamContents(t,
+        new String[]{"/a", "/a/b", "/a/b/c"},
+        new int[]{0, 0, 0},
+        new int[]{2, 4, 6},
+        new int[]{1, 0, 0},
+        path.length());
+  }
+
+  public void testEndOfDelimiter() throws Exception {
+    String path = "/a/b/c/";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path) );
+    assertTokenStreamContents(t,
+        new String[]{"/a", "/a/b", "/a/b/c", "/a/b/c/"},
+        new int[]{0, 0, 0, 0},
+        new int[]{2, 4, 6, 7},
+        new int[]{1, 0, 0, 0},
+        path.length());
+  }
+
+  public void testStartOfChar() throws Exception {
+    String path = "a/b/c";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path) );
+    assertTokenStreamContents(t,
+        new String[]{"a", "a/b", "a/b/c"},
+        new int[]{0, 0, 0},
+        new int[]{1, 3, 5},
+        new int[]{1, 0, 0},
+        path.length());
+  }
+
+  public void testStartOfCharEndOfDelimiter() throws Exception {
+    String path = "a/b/c/";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path) );
+    assertTokenStreamContents(t,
+        new String[]{"a", "a/b", "a/b/c", "a/b/c/"},
+        new int[]{0, 0, 0, 0},
+        new int[]{1, 3, 5, 6},
+        new int[]{1, 0, 0, 0},
+        path.length());
+  }
+
+  public void testOnlyDelimiter() throws Exception {
+    String path = "/";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path) );
+    assertTokenStreamContents(t,
+        new String[]{"/"},
+        new int[]{0},
+        new int[]{1},
+        new int[]{1},
+        path.length());
+  }
+
+  public void testOnlyDelimiters() throws Exception {
+    String path = "//";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path) );
+    assertTokenStreamContents(t,
+        new String[]{"/", "//"},
+        new int[]{0, 0},
+        new int[]{1, 2},
+        new int[]{1, 0},
+        path.length());
+  }
+
+  public void testReplace() throws Exception {
+    String path = "/a/b/c";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), '/', '\\' );
+    assertTokenStreamContents(t,
+        new String[]{"\\a", "\\a\\b", "\\a\\b\\c"},
+        new int[]{0, 0, 0},
+        new int[]{2, 4, 6},
+        new int[]{1, 0, 0},
+        path.length());
+  }
+
+  public void testWindowsPath() throws Exception {
+    String path = "c:\\a\\b\\c";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), '\\', '\\' );
+    assertTokenStreamContents(t,
+        new String[]{"c:", "c:\\a", "c:\\a\\b", "c:\\a\\b\\c"},
+        new int[]{0, 0, 0, 0},
+        new int[]{2, 4, 6, 8},
+        new int[]{1, 0, 0, 0},
+        path.length());
+  }
+
+  public void testNormalizeWinDelimToLinuxDelim() throws Exception {
+    NormalizeCharMap normMap = new NormalizeCharMap();
+    normMap.add("\\", "/");
+    String path = "c:\\a\\b\\c";
+    CharStream cs = new MappingCharFilter(normMap, new StringReader(path));
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( cs );
+    assertTokenStreamContents(t,
+        new String[]{"c:", "c:/a", "c:/a/b", "c:/a/b/c"},
+        new int[]{0, 0, 0, 0},
+        new int[]{2, 4, 6, 8},
+        new int[]{1, 0, 0, 0},
+        path.length());
+  }
+
+  public void testBasicSkip() throws Exception {
+    String path = "/a/b/c";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), 1 );
+    assertTokenStreamContents(t,
+        new String[]{"/b", "/b/c"},
+        new int[]{2, 2},
+        new int[]{4, 6},
+        new int[]{1, 0},
+        path.length());
+  }
+
+  public void testEndOfDelimiterSkip() throws Exception {
+    String path = "/a/b/c/";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), 1 );
+    assertTokenStreamContents(t,
+        new String[]{"/b", "/b/c", "/b/c/"},
+        new int[]{2, 2, 2},
+        new int[]{4, 6, 7},
+        new int[]{1, 0, 0},
+        path.length());
+  }
+
+  public void testStartOfCharSkip() throws Exception {
+    String path = "a/b/c";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), 1 );
+    assertTokenStreamContents(t,
+        new String[]{"/b", "/b/c"},
+        new int[]{1, 1},
+        new int[]{3, 5},
+        new int[]{1, 0},
+        path.length());
+  }
+
+  public void testStartOfCharEndOfDelimiterSkip() throws Exception {
+    String path = "a/b/c/";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), 1 );
+    assertTokenStreamContents(t,
+        new String[]{"/b", "/b/c", "/b/c/"},
+        new int[]{1, 1, 1},
+        new int[]{3, 5, 6},
+        new int[]{1, 0, 0},
+        path.length());
+  }
+
+  public void testOnlyDelimiterSkip() throws Exception {
+    String path = "/";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), 1 );
+    assertTokenStreamContents(t,
+        new String[]{},
+        new int[]{},
+        new int[]{},
+        new int[]{},
+        path.length());
+  }
+
+  public void testOnlyDelimitersSkip() throws Exception {
+    String path = "//";
+    PathHierarchyTokenizer t = new PathHierarchyTokenizer( new StringReader(path), 1 );
+    assertTokenStreamContents(t,
+        new String[]{"/"},
+        new int[]{1},
+        new int[]{2},
+        new int[]{1},
+        path.length());
+  }
+}