1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
|
// Copyright Yahoo. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
package com.yahoo.document;
import com.yahoo.document.idstring.IdIdString;
import com.yahoo.document.idstring.IdString;
import com.yahoo.vespa.objects.BufferSerializer;
import org.junit.Before;
import org.junit.Test;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.util.regex.Pattern;
import java.util.Arrays;
import static org.junit.Assert.assertArrayEquals;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertNotEquals;
import static org.junit.Assert.assertTrue;
import static org.junit.Assert.fail;
public class DocumentIdTestCase {
DocumentTypeManager manager = new DocumentTypeManager();
@Before
public void setUp() {
DocumentType testDocType = new DocumentType("testdoc");
testDocType.addField("intattr", DataType.INT);
testDocType.addField("rawattr", DataType.RAW);
testDocType.addField("floatattr", DataType.FLOAT);
testDocType.addField("stringattr", DataType.STRING);
testDocType.addField("Minattr", DataType.INT);
manager.registerDocumentType(testDocType);
}
@Test
public void testCompareTo() {
DocumentId docId1 = new Document(manager.getDocumentType("testdoc"), new DocumentId("id:ns:testdoc::http://www.uio.no/")).getId();
DocumentId docId2 = new Document(manager.getDocumentType("testdoc"), new DocumentId("id:ns:testdoc::http://www.uio.no/")).getId();
DocumentId docId3 = new Document(manager.getDocumentType("testdoc"), new DocumentId("id:ns:testdoc::http://www.ntnu.no/")).getId();
assertTrue(docId1.equals(docId2));
assertTrue(!docId1.equals(docId3));
assertTrue(docId1.compareTo(docId3) > 0);
assertTrue(docId3.compareTo(docId1) < 0);
assertEquals(docId1.hashCode(), docId2.hashCode());
}
private void checkInvalidUri(String uri) {
try {
//invalid URI
new DocumentId(uri);
fail();
} catch (IllegalArgumentException iae) {
}
}
@Test
public void testValidInvalidUriSchemes() {
try {
//valid URIs
new DocumentId("id:namespace:type:n=42:whatever");
new DocumentId("id:namespace:type::whatever");
} catch (IllegalArgumentException iae) {
fail(iae.getMessage());
}
checkInvalidUri("foobar:");
checkInvalidUri("ballooo:blabla/something/");
checkInvalidUri("id:namespace:type");
checkInvalidUri("id:namespace:type:key-values");
checkInvalidUri("id:namespace:type:n=0,n=1:foo");
checkInvalidUri("id:namespace:type:g=foo,g=bar:foo");
checkInvalidUri("id:namespace:type:n=0,g=foo:foo");
}
@Test
public void empty_user_location_value_throws_exception() {
try {
new DocumentId("id:namespace:type:n=:foo");
fail();
} catch (IllegalArgumentException e) {
assertEquals("ID location value for 'n=' key is empty", e.getMessage());
}
}
@Test
public void empty_group_location_value_throws_exception() {
try {
new DocumentId("id:namespace:type:g=:foo");
fail();
} catch (IllegalArgumentException e) {
assertEquals("ID location value for 'g=' key is empty", e.getMessage());
}
}
//Compares globalId with C++ implementation located in
// ~document-HEAD/document/src/tests/cpp-globalidbucketids.txt
@Test
public void testCalculateGlobalId() throws IOException {
String file = "src/tests/cpp-globalidbucketids.txt";
BufferedReader fr = new BufferedReader(new FileReader(file));
String line;
String[] split_line;
String[] split_gid;
byte[] b;
// reads from file
while ((line = fr.readLine()) != null) {
split_line = line.split(" - ");
DocumentId mydoc = new DocumentId(split_line[0]);
b = mydoc.getGlobalId();
split_gid = Pattern.compile("\\(|\\)").split(split_line[1]);
compareStringByte(split_gid[1],b);
}
fr.close();
}
private void compareStringByte(String s, byte[] b){
/*
System.out.println("-- "+s+" --");
System.out.print("++ 0x");
for (int i=0; i<b.length; ++i) {
int nr = b[i] & 0xFF;
System.out.print(Integer.toHexString(nr / 16) + Integer.toHexString(nr % 16));
}
System.out.println(" ++");
*/
s = s.substring(2);
assertEquals(s.length()/2, b.length);
for(int i=0; i<b.length;i++){
String ss = s.substring(2*i,2*i+2);
assertEquals(Integer.valueOf(ss, 16).intValue(),(((int)b[i])+256)%256);
}
}
//Compares bucketId with C++ implementation located in
// ~document-HEAD/document/src/tests/cpp-globalidbucketids.txt
@Test
public void testGetBucketId() throws IOException{
String file = "src/tests/cpp-globalidbucketids.txt";
BufferedReader fr = new BufferedReader(new FileReader(file));
String line;
String[] split_line;
BucketId bid;
// reads from file
while ((line = fr.readLine()) != null) {
split_line = line.split(" - ");
DocumentId mydoc = new DocumentId(split_line[0]);
BucketIdFactory factory = new BucketIdFactory(32, 26, 6);
bid = new BucketId(factory.getBucketId(mydoc).getId());
assertEquals(split_line[2], bid.toString());
}
fr.close();
}
@Test
public void testIdStrings() {
DocumentId docId = new DocumentId(new IdIdString("namespace", "type", "g=group", "foobar"));
assertEquals("id:namespace:type:g=group:foobar", docId.toString());
assertTrue(docId.hasDocType());
assertEquals("type", docId.getDocType());
}
@Test
public void testIdStringFeatures() {
DocumentId none = new DocumentId("id:ns:type::foo");
assertFalse(none.getScheme().hasGroup());
assertFalse(none.getScheme().hasNumber());
DocumentId user = new DocumentId("id:ns:type:n=42:foo");
assertFalse(user.getScheme().hasGroup());
assertTrue(user.getScheme().hasNumber());
assertEquals(42, user.getScheme().getNumber());
DocumentId group = new DocumentId("id:ns:type:g=mygroup:foo");
assertTrue(group.getScheme().hasGroup());
assertFalse(group.getScheme().hasNumber());
assertEquals("mygroup", group.getScheme().getGroup());
group = new DocumentId("id:ns:type:g=mygroup:foo");
assertTrue(group.getScheme().hasGroup());
assertFalse(group.getScheme().hasNumber());
assertEquals("mygroup", group.getScheme().getGroup());
}
@Test
public void testHashCodeOfGids() {
DocumentId docId0 = new DocumentId("id:blabla:type::0");
byte[] docId0Gid = docId0.getGlobalId();
DocumentId docId0Copy = new DocumentId("id:blabla:type::0");
byte[] docId0CopyGid = docId0Copy.getGlobalId();
assertArrayEquals(docId0Gid, docId0CopyGid);
//straight hashCode() of byte arrays won't be the same
assertNotEquals(docId0Gid.hashCode(), docId0CopyGid.hashCode());
//Arrays.hashCode() works better...
assertEquals(Arrays.hashCode(docId0Gid), Arrays.hashCode(docId0CopyGid));
}
@Test
public void testDocumentIdCanOnlyContainTextCharacters() throws UnsupportedEncodingException {
assertExceptionWhenConstructing(new byte[]{105, 100, 58, 97, 58, 98, 58, 58, 0, 99}, // "id:a:b::0x0c"
"illegal code point 0x0");
assertExceptionWhenConstructing(new byte[]{105, 100, 58, 97, 58, 98, 58, 58, 7, 99}, // "id:a:b::0x7c"
"illegal code point 0x7");
}
private void assertExceptionWhenConstructing(byte[] rawId,
String exceptionMsg) throws UnsupportedEncodingException {
String strId = new String(rawId, "UTF-8");
try {
new DocumentId(strId);
fail("Expected an IllegalArgumentException to be thrown");
} catch (IllegalArgumentException ex) {
assertTrue(ex.getMessage().contains(exceptionMsg));
}
}
@Test
public void testSerializedDocumentIdCanContainNonTextCharacter() {
String strId = new String(new byte[]{105, 100, 58, 97, 58, 98, 58, 58, 7, 99}); // "id:a:b::0x7c"
DocumentId docId = DocumentId.createFromSerialized(strId);
{
assertEquals(strId, docId.toString());
}
{
BufferSerializer buf = new BufferSerializer();
docId.serialize(buf);
buf.flip();
DocumentId deserializedId = new DocumentId(buf);
assertEquals(strId, deserializedId.toString());
}
}
@Test
public void testSerializedDocumentIdCannotContainZeroByte() {
String strId = new String(new byte[]{105, 100, 58, 97, 58, 98, 58, 58, 0, 99}); // "id:a:b::0x0c"
try {
DocumentId.createFromSerialized(strId);
fail("Expected an IllegalArgumentException to be thrown");
} catch (IllegalArgumentException ex) {
assertTrue(ex.getMessage().contains("illegal zero byte code point"));
}
}
@Test
public void testTooLongDocId() {
StringBuilder sb = new StringBuilder("id:ns:type::");
for(int i=0; i < 0x10000; i++) {
sb.append('x');
}
try {
new DocumentId(sb.toString());
fail("Expected an IllegalArgumentException to be thrown");
} catch (IllegalArgumentException ex) {
assertTrue(ex.getMessage().contains("However if you have already fed a document earlier on and want to remove it, " +
"you can do so by calling new DocumentId(IdString.createIdStringLessStrict()) that will bypass this restriction."));
}
assertEquals(65548, new DocumentId(IdString.createIdStringLessStrict(sb.toString())).toString().length());
}
}
|