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
|
/*
* Copyright (C) 2006 The Android Open Source Project
*
* Licensed 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.
*/
#define LOG_TAG "Character"
#include "JNIHelp.h"
#include "JniConstants.h"
#include "ScopedUtfChars.h"
#include "unicode/uchar.h"
#include "unicode/uscript.h"
#include <math.h>
#include <stdio.h> // For BUFSIZ
#include <stdlib.h>
static jint Character_digitImpl(JNIEnv*, jclass, jint codePoint, jint radix) {
return u_digit(codePoint, radix);
}
static jint Character_getTypeImpl(JNIEnv*, jclass, jint codePoint) {
return u_charType(codePoint);
}
static jbyte Character_getDirectionalityImpl(JNIEnv*, jclass, jint codePoint) {
return u_charDirection(codePoint);
}
static jboolean Character_isMirroredImpl(JNIEnv*, jclass, jint codePoint) {
return u_isMirrored(codePoint);
}
static jstring Character_getNameImpl(JNIEnv* env, jclass, jint codePoint) {
// U_UNICODE_CHAR_NAME gives us the modern names for characters. For control characters,
// we need U_EXTENDED_CHAR_NAME to get "NULL" rather than "BASIC LATIN 0" and so on.
// We could just use U_EXTENDED_CHAR_NAME except that it returns strings for characters
// that aren't unassigned but that don't have names, and those strings aren't in the form
// Java specifies.
bool isControl = (codePoint <= 0x1f || (codePoint >= 0x7f && codePoint <= 0x9f));
UCharNameChoice nameType = isControl ? U_EXTENDED_CHAR_NAME : U_UNICODE_CHAR_NAME;
UErrorCode status = U_ZERO_ERROR;
char buf[BUFSIZ]; // TODO: is there a more sensible upper bound?
int32_t byteCount = u_charName(codePoint, nameType, &buf[0], sizeof(buf), &status);
return (U_FAILURE(status) || byteCount == 0) ? NULL : env->NewStringUTF(buf);
}
static jint Character_getNumericValueImpl(JNIEnv*, jclass, jint codePoint) {
double result = u_getNumericValue(codePoint);
if (result == U_NO_NUMERIC_VALUE) {
return -1;
} else if (result < 0 || floor(result + 0.5) != result) {
return -2;
}
return static_cast<jint>(result);
}
static jboolean Character_isDefinedImpl(JNIEnv*, jclass, jint codePoint) {
return u_isdefined(codePoint);
}
static jboolean Character_isDigitImpl(JNIEnv*, jclass, jint codePoint) {
return u_isdigit(codePoint);
}
static jboolean Character_isIdentifierIgnorableImpl(JNIEnv*, jclass, jint codePoint) {
return u_isIDIgnorable(codePoint);
}
static jboolean Character_isLetterImpl(JNIEnv*, jclass, jint codePoint) {
return u_isalpha(codePoint);
}
static jboolean Character_isLetterOrDigitImpl(JNIEnv*, jclass, jint codePoint) {
return u_isalnum(codePoint);
}
static jboolean Character_isSpaceCharImpl(JNIEnv*, jclass, jint codePoint) {
return u_isJavaSpaceChar(codePoint);
}
static jboolean Character_isTitleCaseImpl(JNIEnv*, jclass, jint codePoint) {
return u_istitle(codePoint);
}
static jboolean Character_isUnicodeIdentifierPartImpl(JNIEnv*, jclass, jint codePoint) {
return u_isIDPart(codePoint);
}
static jboolean Character_isUnicodeIdentifierStartImpl(JNIEnv*, jclass, jint codePoint) {
return u_isIDStart(codePoint);
}
static jboolean Character_isWhitespaceImpl(JNIEnv*, jclass, jint codePoint) {
return u_isWhitespace(codePoint);
}
static jint Character_toLowerCaseImpl(JNIEnv*, jclass, jint codePoint) {
return u_tolower(codePoint);
}
static jint Character_toTitleCaseImpl(JNIEnv*, jclass, jint codePoint) {
return u_totitle(codePoint);
}
static jint Character_toUpperCaseImpl(JNIEnv*, jclass, jint codePoint) {
return u_toupper(codePoint);
}
static jboolean Character_isUpperCaseImpl(JNIEnv*, jclass, jint codePoint) {
return u_isupper(codePoint);
}
static jboolean Character_isLowerCaseImpl(JNIEnv*, jclass, jint codePoint) {
return u_islower(codePoint);
}
static int Character_unicodeBlockForName(JNIEnv* env, jclass, jstring javaBlockName) {
ScopedUtfChars blockName(env, javaBlockName);
if (blockName.c_str() == NULL) {
return 0;
}
return u_getPropertyValueEnum(UCHAR_BLOCK, blockName.c_str());
}
static int Character_unicodeBlockForCodePoint(JNIEnv*, jclass, jint codePoint) {
return ublock_getCode(codePoint);
}
static int Character_unicodeScriptForName(JNIEnv* env, jclass, jstring javaScriptName) {
ScopedUtfChars scriptName(env, javaScriptName);
if (scriptName.c_str() == NULL) {
return -1;
}
return u_getPropertyValueEnum(UCHAR_SCRIPT, scriptName.c_str());
}
static int Character_unicodeScriptForCodePoint(JNIEnv*, jclass, jint codePoint) {
UErrorCode status = U_ZERO_ERROR;
const UScriptCode script = uscript_getScript(codePoint, &status);
if (status != U_ZERO_ERROR) {
return -1;
}
return script;
}
static jboolean Character_isAlphabetic(JNIEnv*, jclass, jint codePoint) {
return u_hasBinaryProperty(codePoint, UCHAR_ALPHABETIC);
}
static jboolean Character_isIdeographic(JNIEnv*, jclass, jint codePoint) {
return u_hasBinaryProperty(codePoint, UCHAR_IDEOGRAPHIC);
}
static JNINativeMethod gMethods[] = {
NATIVE_METHOD(Character, digitImpl, "!(II)I"),
NATIVE_METHOD(Character, getDirectionalityImpl, "!(I)B"),
NATIVE_METHOD(Character, getNameImpl, "(I)Ljava/lang/String;"),
NATIVE_METHOD(Character, getNumericValueImpl, "!(I)I"),
NATIVE_METHOD(Character, getTypeImpl, "!(I)I"),
NATIVE_METHOD(Character, isAlphabetic, "!(I)Z"),
NATIVE_METHOD(Character, isDefinedImpl, "!(I)Z"),
NATIVE_METHOD(Character, isDigitImpl, "!(I)Z"),
NATIVE_METHOD(Character, isIdentifierIgnorableImpl, "!(I)Z"),
NATIVE_METHOD(Character, isIdeographic, "!(I)Z"),
NATIVE_METHOD(Character, isLetterImpl, "!(I)Z"),
NATIVE_METHOD(Character, isLetterOrDigitImpl, "!(I)Z"),
NATIVE_METHOD(Character, isLowerCaseImpl, "!(I)Z"),
NATIVE_METHOD(Character, isMirroredImpl, "!(I)Z"),
NATIVE_METHOD(Character, isSpaceCharImpl, "!(I)Z"),
NATIVE_METHOD(Character, isTitleCaseImpl, "!(I)Z"),
NATIVE_METHOD(Character, isUnicodeIdentifierPartImpl, "!(I)Z"),
NATIVE_METHOD(Character, isUnicodeIdentifierStartImpl, "!(I)Z"),
NATIVE_METHOD(Character, isUpperCaseImpl, "!(I)Z"),
NATIVE_METHOD(Character, isWhitespaceImpl, "!(I)Z"),
NATIVE_METHOD(Character, toLowerCaseImpl, "!(I)I"),
NATIVE_METHOD(Character, toTitleCaseImpl, "!(I)I"),
NATIVE_METHOD(Character, toUpperCaseImpl, "!(I)I"),
NATIVE_METHOD(Character, unicodeBlockForName, "(Ljava/lang/String;)I"),
NATIVE_METHOD(Character, unicodeBlockForCodePoint, "!(I)I"),
NATIVE_METHOD(Character, unicodeScriptForName, "(Ljava/lang/String;)I"),
NATIVE_METHOD(Character, unicodeScriptForCodePoint, "!(I)I"),
};
void register_java_lang_Character(JNIEnv* env) {
jniRegisterNativeMethods(env, "java/lang/Character", gMethods, NELEM(gMethods));
}
|
