File: CharacterSet.h

package info (click to toggle)
codequery 1.0.1%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 17,860 kB
  • sloc: cpp: 151,420; xml: 16,576; python: 5,602; ansic: 5,487; makefile: 559; perl: 496; ruby: 209; sql: 194; sh: 106; php: 53; vhdl: 51; erlang: 47; objc: 22; lisp: 18; cobol: 18; modula3: 17; asm: 14; fortran: 12; ml: 11; tcl: 6
file content (195 lines) | stat: -rw-r--r-- 5,294 bytes parent folder | download | duplicates (4)
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
// Scintilla source code edit control
/** @file CharacterSet.h
 ** Encapsulates a set of characters. Used to test if a character is within a set.
 **/
// Copyright 2007 by Neil Hodgson <neilh@scintilla.org>
// The License.txt file describes the conditions under which this software may be distributed.

#ifndef CHARACTERSET_H
#define CHARACTERSET_H

namespace Lexilla {

template<int N>
class CharacterSetArray {
	unsigned char bset[(N-1)/8 + 1] = {};
	bool valueAfter = false;
public:
	enum setBase {
		setNone=0,
		setLower=1,
		setUpper=2,
		setDigits=4,
		setAlpha=setLower|setUpper,
		setAlphaNum=setAlpha|setDigits
	};
	CharacterSetArray(setBase base=setNone, const char *initialSet="", bool valueAfter_=false) noexcept {
		valueAfter = valueAfter_;
		AddString(initialSet);
		if (base & setLower)
			AddString("abcdefghijklmnopqrstuvwxyz");
		if (base & setUpper)
			AddString("ABCDEFGHIJKLMNOPQRSTUVWXYZ");
		if (base & setDigits)
			AddString("0123456789");
	}
	CharacterSetArray(const char *initialSet, bool valueAfter_=false) noexcept :
		CharacterSetArray(setNone, initialSet, valueAfter_) {
	}
	// For compatibility with previous version but should not be used in new code.
	CharacterSetArray(setBase base, const char *initialSet, [[maybe_unused]]int size_, bool valueAfter_=false) noexcept :
		CharacterSetArray(base, initialSet, valueAfter_) {
		assert(size_ == N);
	}
	void Add(int val) noexcept {
		assert(val >= 0);
		assert(val < N);
		bset[val >> 3] |= 1 << (val & 7);
	}
	void AddString(const char *setToAdd) noexcept {
		for (const char *cp=setToAdd; *cp; cp++) {
			const unsigned char uch = *cp;
			assert(uch < N);
			Add(uch);
		}
	}
	bool Contains(int val) const noexcept {
		assert(val >= 0);
		if (val < 0) return false;
		if (val >= N) return valueAfter;
		return bset[val >> 3] & (1 << (val & 7));
	}
	bool Contains(char ch) const noexcept {
		// Overload char as char may be signed
		const unsigned char uch = ch;
		return Contains(uch);
	}
};

using CharacterSet = CharacterSetArray<0x80>;

// Functions for classifying characters

template <typename T, typename... Args>
constexpr bool AnyOf(T t, Args... args) noexcept {
#if defined(__clang__)
	static_assert(__is_integral(T) || __is_enum(T));
#endif
	return ((t == args) || ...);
}

// prevent pointer without <type_traits>
template <typename T, typename... Args>
constexpr void AnyOf([[maybe_unused]] T *t, [[maybe_unused]] Args... args) noexcept {}
template <typename T, typename... Args>
constexpr void AnyOf([[maybe_unused]] const T *t, [[maybe_unused]] Args... args) noexcept {}

constexpr bool IsASpace(int ch) noexcept {
    return (ch == ' ') || ((ch >= 0x09) && (ch <= 0x0d));
}

constexpr bool IsASpaceOrTab(int ch) noexcept {
	return (ch == ' ') || (ch == '\t');
}

constexpr bool IsADigit(int ch) noexcept {
	return (ch >= '0') && (ch <= '9');
}

constexpr bool IsAHeXDigit(int ch) noexcept {
	return (ch >= '0' && ch <= '9')
		|| (ch >= 'A' && ch <= 'F')
		|| (ch >= 'a' && ch <= 'f');
}

constexpr bool IsAnOctalDigit(int ch) noexcept {
	return ch >= '0' && ch <= '7';
}

constexpr bool IsADigit(int ch, int base) noexcept {
	if (base <= 10) {
		return (ch >= '0') && (ch < '0' + base);
	} else {
		return ((ch >= '0') && (ch <= '9')) ||
		       ((ch >= 'A') && (ch < 'A' + base - 10)) ||
		       ((ch >= 'a') && (ch < 'a' + base - 10));
	}
}

constexpr bool IsASCII(int ch) noexcept {
	return (ch >= 0) && (ch < 0x80);
}

constexpr bool IsLowerCase(int ch) noexcept {
	return (ch >= 'a') && (ch <= 'z');
}

constexpr bool IsUpperCase(int ch) noexcept {
	return (ch >= 'A') && (ch <= 'Z');
}

constexpr bool IsUpperOrLowerCase(int ch) noexcept {
	return IsUpperCase(ch) || IsLowerCase(ch);
}

constexpr bool IsAlphaNumeric(int ch) noexcept {
	return
		((ch >= '0') && (ch <= '9')) ||
		((ch >= 'a') && (ch <= 'z')) ||
		((ch >= 'A') && (ch <= 'Z'));
}

/**
 * Check if a character is a space.
 * This is ASCII specific but is safe with chars >= 0x80.
 */
constexpr bool isspacechar(int ch) noexcept {
    return (ch == ' ') || ((ch >= 0x09) && (ch <= 0x0d));
}

constexpr bool iswordchar(int ch) noexcept {
	return IsAlphaNumeric(ch) || ch == '.' || ch == '_';
}

constexpr bool iswordstart(int ch) noexcept {
	return IsAlphaNumeric(ch) || ch == '_';
}

constexpr bool isoperator(int ch) noexcept {
	if (IsAlphaNumeric(ch))
		return false;
	if (ch == '%' || ch == '^' || ch == '&' || ch == '*' ||
	        ch == '(' || ch == ')' || ch == '-' || ch == '+' ||
	        ch == '=' || ch == '|' || ch == '{' || ch == '}' ||
	        ch == '[' || ch == ']' || ch == ':' || ch == ';' ||
	        ch == '<' || ch == '>' || ch == ',' || ch == '/' ||
	        ch == '?' || ch == '!' || ch == '.' || ch == '~')
		return true;
	return false;
}

// Simple case functions for ASCII supersets.

template <typename T>
constexpr T MakeUpperCase(T ch) noexcept {
	if (ch < 'a' || ch > 'z')
		return ch;
	else
		return ch - 'a' + 'A';
}

template <typename T>
constexpr T MakeLowerCase(T ch) noexcept {
	if (ch < 'A' || ch > 'Z')
		return ch;
	else
		return ch - 'A' + 'a';
}

int CompareCaseInsensitive(const char *a, const char *b) noexcept;
bool EqualCaseInsensitive(std::string_view a, std::string_view b) noexcept;
int CompareNCaseInsensitive(const char *a, const char *b, size_t len) noexcept;

}

#endif