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
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
|
/*
* Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/**
* @test
* @summary Test behavior of isJavaIdentifierXX, isJavaLetter, and
* isJavaLetterOrDigit methods for all code points.
* @bug 8218915
*/
public class TestIsJavaIdentifierMethods {
// Japanese Era Square character code point not present in Unicode 10.0
private static final int JAPANESE_ERA_CODEPOINT = 0x32FF;
public static void main(String[] args) {
testIsJavaIdentifierPart_int();
testIsJavaIdentifierPart_char();
testIsJavaIdentifierStart_int();
testIsJavaIdentifierStart_char();
testIsJavaLetter();
testIsJavaLetterOrDigit();
}
/**
* Assertion testing for public static boolean isJavaIdentifierPart(int
* codePoint), A character may be part of a Java identifier if any of the
* following are true:
* <ul>
* <li>it is a letter</li>
* <li>it is a currency symbol (such as <code>'$'</code>)</li>
* <li>it is a connecting punctuation character (such as <code>'_'</code>)
* </li>
* <li>it is a digit</li>
* <li>it is a numeric letter (such as a Roman numeral character)</li>
* <li>it is a combining mark</li>
* <li>it is a non-spacing mark</li>
* <li><code>isIdentifierIgnorable</code> returns <code>true</code> for the
* character</li>
* </ul>
* All code points from (0x0000..0x10FFFF) are tested.
*/
public static void testIsJavaIdentifierPart_int() {
for (int cp = 0; cp <= Character.MAX_CODE_POINT; cp++) {
boolean expected = false;
// Since Character.isJavaIdentifierPart(int) strictly conforms to
// character information from version 10.0 of the Unicode Standard,
// check if code point is "Japanese Era Square character code
// point". If the code point is "Japanese Era Square character code
// point", value of variable "expected" is considered false.
if (cp != JAPANESE_ERA_CODEPOINT) {
byte type = (byte) Character.getType(cp);
expected = Character.isLetter(cp)
|| type == Character.CURRENCY_SYMBOL
|| type == Character.CONNECTOR_PUNCTUATION
|| Character.isDigit(cp)
|| type == Character.LETTER_NUMBER
|| type == Character.COMBINING_SPACING_MARK
|| type == Character.NON_SPACING_MARK
|| Character.isIdentifierIgnorable(cp);
}
if (Character.isJavaIdentifierPart(cp) != expected) {
throw new RuntimeException(
"Character.isJavaIdentifierPart(int) failed for codepoint "
+ Integer.toHexString(cp));
}
}
}
/**
* Assertion testing for public static boolean isJavaIdentifierPart(char
* ch), A character may be part of a Java identifier if any of the
* following are true:
* <ul>
* <li>it is a letter;
* <li>it is a currency symbol (such as "$");
* <li>it is a connecting punctuation character (such as "_");
* <li>it is a digit;
* <li>it is a numeric letter (such as a Roman numeral character);
* <li>it is a combining mark;
* <li>it is a non-spacing mark;
* <li>isIdentifierIgnorable returns true for the character.
* </ul>
* All Unicode code points in the BMP (0x0000..0xFFFF) are tested.
*/
public static void testIsJavaIdentifierPart_char() {
for (int i = 0; i <= Character.MAX_VALUE; ++i) {
char ch = (char) i;
boolean expected = false;
// Since Character.isJavaIdentifierPart(char) strictly conforms to
// character information from version 10.0 of the Unicode Standard,
// check if code point is "Japanese Era Square character code
// point". If the code point is "Japanese Era Square character code
// point", value of variable "expected" is considered false.
if (i != JAPANESE_ERA_CODEPOINT) {
byte type = (byte) Character.getType(ch);
expected = Character.isLetter(ch)
|| type == Character.CURRENCY_SYMBOL
|| type == Character.CONNECTOR_PUNCTUATION
|| Character.isDigit(ch)
|| type == Character.LETTER_NUMBER
|| type == Character.COMBINING_SPACING_MARK
|| type == Character.NON_SPACING_MARK
|| Character.isIdentifierIgnorable(ch);
}
if (Character.isJavaIdentifierPart((char) i) != expected) {
throw new RuntimeException(
"Character.isJavaIdentifierPart(char) failed for codepoint "
+ Integer.toHexString(i));
}
}
}
/**
* Assertion testing for public static boolean isJavaIdentifierStart(int
* codePoint), A character may start a Java identifier if and only if it is
* one of the following:
* <ul>
* <li>it is a letter;</li>
* <li>getType(ch) returns LETTER_NUMBER;</li>
* <li>it is a currency symbol (such as "$");</li>
* <li>it is a connecting punctuation character (such as "_");</li>
* </ul>
* All Code points from (0x0000..0x10FFFF) are tested.
*/
public static void testIsJavaIdentifierStart_int() {
for (int cp = 0; cp <= Character.MAX_CODE_POINT; cp++) {
boolean expected = false;
// Since Character.isJavaIdentifierStart(int) strictly conforms to
// character information from version 10.0 of the Unicode Standard,
// check if code point is "Japanese Era Square character code
// point". If the code point is "Japanese Era Square character code
// point", value of variable "expected" is considered false.
if (cp != JAPANESE_ERA_CODEPOINT) {
byte type = (byte) Character.getType(cp);
expected = Character.isLetter(cp)
|| type == Character.LETTER_NUMBER
|| type == Character.CURRENCY_SYMBOL
|| type == Character.CONNECTOR_PUNCTUATION;
}
if (Character.isJavaIdentifierStart(cp) != expected) {
throw new RuntimeException(
"Character.isJavaIdentifierStart(int) failed for codepoint "
+ Integer.toHexString(cp));
}
}
}
/**
* Assertion testing for public static boolean isJavaIdentifierStart(char),
* A character may start a Java identifier if and only if it is
* one of the following:
* <ul>
* <li>it is a letter;</li>
* <li>getType(ch) returns LETTER_NUMBER;</li>
* <li>it is a currency symbol (such as "$");</li>
* <li>it is a connecting punctuation character (such as "_");</li>
* </ul>
* All Unicode code points in the BMP (0x0000..0xFFFF) are tested.
*/
public static void testIsJavaIdentifierStart_char() {
for (int i = 0; i <= Character.MAX_VALUE; i++) {
char ch = (char) i;
boolean expected = false;
// Since Character.isJavaIdentifierStart(char) strictly conforms to
// character information from version 10.0 of the Unicode Standard,
// check if code point is "Japanese Era Square character code
// point". If the code point is "Japanese Era Square character code
// point", value of variable "expected" is considered false.
if (i != JAPANESE_ERA_CODEPOINT) {
byte type = (byte) Character.getType(ch);
expected = Character.isLetter(ch)
|| type == Character.LETTER_NUMBER
|| type == Character.CURRENCY_SYMBOL
|| type == Character.CONNECTOR_PUNCTUATION;
}
if (Character.isJavaIdentifierStart(ch) != expected) {
throw new RuntimeException(
"Character.isJavaIdentifierStart(char) failed for codepoint "
+ Integer.toHexString(i));
}
}
}
/**
* Assertion testing for public static boolean isJavaLetter(char ch), A
* character may start a Java identifier if and only if one of the following
* is true:
* <ul>
* <li>isLetter(ch) returns true
* <li>getType(ch) returns LETTER_NUMBER
* <li>ch is a currency symbol (such as "$")
* <li>ch is a connecting punctuation character (such as "_").
* </ul>
* All Unicode code points in the BMP (0x0000..0xFFFF) are tested.
*/
public static void testIsJavaLetter() {
for (int i = 0; i <= Character.MAX_VALUE; ++i) {
char ch = (char) i;
boolean expected = false;
// Since Character.isJavaLetter(char) strictly conforms to
// character information from version 10.0 of the Unicode Standard,
// check if code point is "Japanese Era Square character code
// point". If the code point is "Japanese Era Square character code
// point", value of variable "expected" is considered false.
if (i != JAPANESE_ERA_CODEPOINT) {
byte type = (byte) Character.getType(ch);
expected = Character.isLetter(ch)
|| type == Character.LETTER_NUMBER
|| type == Character.CURRENCY_SYMBOL
|| type == Character.CONNECTOR_PUNCTUATION;
}
if (Character.isJavaLetter(ch) != expected) {
throw new RuntimeException(
"Character.isJavaLetter(ch) failed for codepoint "
+ Integer.toHexString(i));
}
}
}
/**
* Assertion testing for public static boolean isJavaLetterOrDigit(char ch),
* A character may be part of a Java identifier if and only if any of the
* following are true:
* <ul>
* <li>it is a letter
* <li>it is a currency symbol (such as '$')
* <li>it is a connecting punctuation character (such as '_')
* <li>it is a digit
* <li>it is a numeric letter (such as a Roman numeral character)
* <li>it is a combining mark
* <li>it is a non-spacing mark
* <li>isIdentifierIgnorable returns true for the character.
* </ul>
* All Unicode code points in the BMP (0x0000..0xFFFF) are tested.
*/
public static void testIsJavaLetterOrDigit() {
for (int i = 0; i <= Character.MAX_VALUE; ++i) {
char ch = (char) i;
boolean expected = false;
// Since Character.isJavaLetterOrDigit(char) strictly conforms to
// character information from version 10.0 of the Unicode Standard,
// check if code point is "Japanese Era Square character code
// point". If the code point is "Japanese Era Square character code
// point", value of variable "expected" is considered false.
if (i != JAPANESE_ERA_CODEPOINT) {
byte type = (byte) Character.getType(ch);
expected = Character.isLetter(ch)
|| type == Character.CURRENCY_SYMBOL
|| type == Character.CONNECTOR_PUNCTUATION
|| Character.isDigit(ch)
|| type == Character.LETTER_NUMBER
|| type == Character.COMBINING_SPACING_MARK
|| type == Character.NON_SPACING_MARK
|| Character.isIdentifierIgnorable(ch);
}
if (Character.isJavaLetterOrDigit(ch) != expected) {
throw new RuntimeException(
"Character.isJavaLetterOrDigit(ch) failed for codepoint "
+ Integer.toHexString(i));
}
}
}
}
|
