1 /*
2 * Copyright (c) 2021-2022 Huawei Device Co., Ltd.
3 * Licensed under the Apache License, Version 2.0 (the "License");
4 * you may not use this file except in compliance with the License.
5 * You may obtain a copy of the License at
6 *
7 * http://www.apache.org/licenses/LICENSE-2.0
8 *
9 * Unless required by applicable law or agreed to in writing, software
10 * distributed under the License is distributed on an "AS IS" BASIS,
11 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 * See the License for the specific language governing permissions and
13 * limitations under the License.
14 */
15 #include "character.h"
16
17 #include <sys/types.h>
18 #include <set>
19 #include <string>
20
21 #include "cctype"
22 #include "map"
23 #include "string"
24 #include "unicode/uchar.h"
25 #include "unicode/umachine.h"
26 #include "unicode/unistr.h"
27 #include "unicode/urename.h"
28
29 namespace OHOS {
30 namespace Global {
31 namespace I18n {
32 static std::set<UCharDirection> RTLDirectionSet = {
33 U_RIGHT_TO_LEFT,
34 U_RIGHT_TO_LEFT_ARABIC,
35 U_RIGHT_TO_LEFT_EMBEDDING,
36 U_RIGHT_TO_LEFT_OVERRIDE,
37 U_RIGHT_TO_LEFT_ISOLATE
38 };
39
IsDigit(const std::string & character)40 bool IsDigit(const std::string &character)
41 {
42 icu::UnicodeString unicodeString(character.c_str());
43 UChar32 char32 = unicodeString.char32At(0);
44 return u_isdigit(char32);
45 }
46
IsSpaceChar(const std::string & character)47 bool IsSpaceChar(const std::string &character)
48 {
49 icu::UnicodeString unicodeString(character.c_str());
50 UChar32 char32 = unicodeString.char32At(0);
51 return u_isJavaSpaceChar(char32);
52 }
53
IsWhiteSpace(const std::string & character)54 bool IsWhiteSpace(const std::string &character)
55 {
56 icu::UnicodeString unicodeString(character.c_str());
57 UChar32 char32 = unicodeString.char32At(0);
58 return u_isWhitespace(char32);
59 }
60
IsRTLCharacter(const std::string & character)61 bool IsRTLCharacter(const std::string &character)
62 {
63 icu::UnicodeString unicodeString(character.c_str());
64 UChar32 char32 = unicodeString.char32At(0);
65 UCharDirection direction = u_charDirection(char32);
66 if (RTLDirectionSet.find(direction) != RTLDirectionSet.end()) {
67 return true;
68 }
69 return false;
70 }
71
IsIdeoGraphic(const std::string & character)72 bool IsIdeoGraphic(const std::string &character)
73 {
74 icu::UnicodeString unicodeString(character.c_str());
75 UChar32 char32 = unicodeString.char32At(0);
76 return u_hasBinaryProperty(char32, UCHAR_IDEOGRAPHIC);
77 }
78
IsLetter(const std::string & character)79 bool IsLetter(const std::string &character)
80 {
81 icu::UnicodeString unicodeString(character.c_str());
82 UChar32 char32 = unicodeString.char32At(0);
83 return isalpha(char32);
84 }
85
IsLowerCase(const std::string & character)86 bool IsLowerCase(const std::string &character)
87 {
88 icu::UnicodeString unicodeString(character.c_str());
89 UChar32 char32 = unicodeString.char32At(0);
90 return u_islower(char32);
91 }
92
IsUpperCase(const std::string & character)93 bool IsUpperCase(const std::string &character)
94 {
95 icu::UnicodeString unicodeString(character.c_str());
96 UChar32 char32 = unicodeString.char32At(0);
97 return u_isupper(char32);
98 }
99
100 std::map<UCharCategory, std::string> categoryMap = {
101 { U_UNASSIGNED, "U_UNASSIGNED" },
102 { U_GENERAL_OTHER_TYPES, "U_GENERAL_OTHER_TYPES" },
103 { U_UPPERCASE_LETTER, "U_UPPERCASE_LETTER" },
104 { U_LOWERCASE_LETTER, "U_LOWERCASE_LETTER" },
105 { U_TITLECASE_LETTER, "U_TITLECASE_LETTER" },
106 { U_MODIFIER_LETTER, "U_MODIFIER_LETTER" },
107 { U_OTHER_LETTER, "U_OTHER_LETTER" },
108 { U_NON_SPACING_MARK, "U_NON_SPACING_MARK" },
109 { U_ENCLOSING_MARK, "U_ENCLOSING_MARK" },
110 { U_COMBINING_SPACING_MARK, "U_COMBINING_SPACING_MARK" },
111 { U_DECIMAL_DIGIT_NUMBER, "U_DECIMAL_DIGIT_NUMBER" },
112 { U_LETTER_NUMBER, "U_LETTER_NUMBER" },
113 { U_OTHER_NUMBER, "U_OTHER_NUMBER" },
114 { U_SPACE_SEPARATOR, "U_SPACE_SEPARATOR" },
115 { U_LINE_SEPARATOR, "U_LINE_SEPARATOR" },
116 { U_PARAGRAPH_SEPARATOR, "U_PARAGRAPH_SEPARATOR" },
117 { U_CONTROL_CHAR, "U_CONTROL_CHAR" },
118 { U_FORMAT_CHAR, "U_FORMAT_CHAR" },
119 { U_PRIVATE_USE_CHAR, "U_PRIVATE_USE_CHAR" },
120 { U_SURROGATE, "U_SURROGATE" },
121 { U_DASH_PUNCTUATION, "U_DASH_PUNCTUATION" },
122 { U_START_PUNCTUATION, "U_START_PUNCTUATION" },
123 { U_END_PUNCTUATION, "U_END_PUNCTUATION" },
124 { U_CONNECTOR_PUNCTUATION, "U_CONNECTOR_PUNCTUATION" },
125 { U_OTHER_PUNCTUATION, "U_OTHER_PUNCTUATION" },
126 { U_MATH_SYMBOL, "U_MATH_SYMBOL" },
127 { U_CURRENCY_SYMBOL, "U_CURRENCY_SYMBOL" },
128 { U_MODIFIER_SYMBOL, "U_MODIFIER_SYMBOL" },
129 { U_OTHER_SYMBOL, "U_OTHER_SYMBOL" },
130 { U_INITIAL_PUNCTUATION, "U_INITIAL_PUNCTUATION" },
131 { U_FINAL_PUNCTUATION, "U_FINAL_PUNCTUATION" },
132 { U_CHAR_CATEGORY_COUNT, "U_CHAR_CATEGORY_COUNT" },
133 };
134
GetType(const std::string & character)135 std::string GetType(const std::string &character)
136 {
137 icu::UnicodeString unicodeString(character.c_str());
138 UChar32 char32 = unicodeString.char32At(0);
139 int8_t category = u_charType(char32);
140 return categoryMap[UCharCategory(category)];
141 }
142 } // namespace I18n
143 } // namespace Global
144 } // namespace OHOS