Botan 1.10.17
charset.cpp
Go to the documentation of this file.
1/*
2* Character Set Handling
3* (C) 1999-2007 Jack Lloyd
4*
5* Distributed under the terms of the Botan license
6*/
7
8#include <botan/charset.h>
9#include <botan/parsing.h>
10#include <botan/exceptn.h>
11#include <cctype>
12
13namespace Botan {
14
15namespace Charset {
16
17namespace {
18
19/*
20* Convert from UCS-2 to ISO 8859-1
21*/
22std::string ucs2_to_latin1(const std::string& ucs2)
23 {
24 if(ucs2.size() % 2 == 1)
25 throw Decoding_Error("UCS-2 string has an odd number of bytes");
26
27 std::string latin1;
28
29 for(size_t i = 0; i != ucs2.size(); i += 2)
30 {
31 const byte c1 = ucs2[i];
32 const byte c2 = ucs2[i+1];
33
34 if(c1 != 0)
35 throw Decoding_Error("UCS-2 has non-Latin1 characters");
36
37 latin1 += static_cast<char>(c2);
38 }
39
40 return latin1;
41 }
42
43/*
44* Convert from UTF-8 to ISO 8859-1
45*/
46std::string utf8_to_latin1(const std::string& utf8)
47 {
48 std::string iso8859;
49
50 size_t position = 0;
51 while(position != utf8.size())
52 {
53 const byte c1 = static_cast<byte>(utf8[position++]);
54
55 if(c1 <= 0x7F)
56 iso8859 += static_cast<char>(c1);
57 else if(c1 >= 0xC0 && c1 <= 0xC7)
58 {
59 if(position == utf8.size())
60 throw Decoding_Error("UTF-8: sequence truncated");
61
62 const byte c2 = static_cast<byte>(utf8[position++]);
63 const byte iso_char = ((c1 & 0x07) << 6) | (c2 & 0x3F);
64
65 if(iso_char <= 0x7F)
66 throw Decoding_Error("UTF-8: sequence longer than needed");
67
68 iso8859 += static_cast<char>(iso_char);
69 }
70 else
71 throw Decoding_Error("UTF-8: Unicode chars not in Latin1 used");
72 }
73
74 return iso8859;
75 }
76
77/*
78* Convert from ISO 8859-1 to UTF-8
79*/
80std::string latin1_to_utf8(const std::string& iso8859)
81 {
82 std::string utf8;
83 for(size_t i = 0; i != iso8859.size(); ++i)
84 {
85 const byte c = static_cast<byte>(iso8859[i]);
86
87 if(c <= 0x7F)
88 utf8 += static_cast<char>(c);
89 else
90 {
91 utf8 += static_cast<char>((0xC0 | (c >> 6)));
92 utf8 += static_cast<char>((0x80 | (c & 0x3F)));
93 }
94 }
95 return utf8;
96 }
97
98}
99
100/*
101* Perform character set transcoding
102*/
103std::string transcode(const std::string& str,
105 {
106 if(to == LOCAL_CHARSET)
107 to = LATIN1_CHARSET;
108 if(from == LOCAL_CHARSET)
109 from = LATIN1_CHARSET;
110
111 if(to == from)
112 return str;
113
114 if(from == LATIN1_CHARSET && to == UTF8_CHARSET)
115 return latin1_to_utf8(str);
116 if(from == UTF8_CHARSET && to == LATIN1_CHARSET)
117 return utf8_to_latin1(str);
118 if(from == UCS2_CHARSET && to == LATIN1_CHARSET)
119 return ucs2_to_latin1(str);
120
121 throw Invalid_Argument("Unknown transcoding operation from " +
122 to_string(from) + " to " + to_string(to));
123 }
124
125/*
126* Check if a character represents a digit
127*/
128bool is_digit(char c)
129 {
130 if(c == '0' || c == '1' || c == '2' || c == '3' || c == '4' ||
131 c == '5' || c == '6' || c == '7' || c == '8' || c == '9')
132 return true;
133 return false;
134 }
135
136/*
137* Check if a character represents whitespace
138*/
139bool is_space(char c)
140 {
141 if(c == ' ' || c == '\t' || c == '\n' || c == '\r')
142 return true;
143 return false;
144 }
145
146/*
147* Convert a character to a digit
148*/
149byte char2digit(char c)
150 {
151 switch(c)
152 {
153 case '0': return 0;
154 case '1': return 1;
155 case '2': return 2;
156 case '3': return 3;
157 case '4': return 4;
158 case '5': return 5;
159 case '6': return 6;
160 case '7': return 7;
161 case '8': return 8;
162 case '9': return 9;
163 }
164
165 throw Invalid_Argument("char2digit: Input is not a digit character");
166 }
167
168/*
169* Convert a digit to a character
170*/
171char digit2char(byte b)
172 {
173 switch(b)
174 {
175 case 0: return '0';
176 case 1: return '1';
177 case 2: return '2';
178 case 3: return '3';
179 case 4: return '4';
180 case 5: return '5';
181 case 6: return '6';
182 case 7: return '7';
183 case 8: return '8';
184 case 9: return '9';
185 }
186
187 throw Invalid_Argument("digit2char: Input is not a digit");
188 }
189
190/*
191* Case-insensitive character comparison
192*/
193bool caseless_cmp(char a, char b)
194 {
195 return (std::tolower(static_cast<unsigned char>(a)) ==
196 std::tolower(static_cast<unsigned char>(b)));
197 }
198
199}
200
201}
bool is_space(char c)
Definition charset.cpp:139
byte char2digit(char c)
Definition charset.cpp:149
std::string transcode(const std::string &str, Character_Set to, Character_Set from)
Definition charset.cpp:103
bool caseless_cmp(char a, char b)
Definition charset.cpp:193
char digit2char(byte b)
Definition charset.cpp:171
bool is_digit(char c)
Definition charset.cpp:128
Character_Set
Definition charset.h:19
@ UCS2_CHARSET
Definition charset.h:21
@ LOCAL_CHARSET
Definition charset.h:20
@ LATIN1_CHARSET
Definition charset.h:23
@ UTF8_CHARSET
Definition charset.h:22
std::string to_string(u64bit n, size_t min_len)
Definition parsing.cpp:42
std::invalid_argument Invalid_Argument
Definition exceptn.h:20
Decoding_Error(const std::string &name)
Definition exceptn.h:140