1 // Copyright 2018 PDFium Authors. All rights reserved.
2 // Use of this source code is governed by a BSD-style license that can be
3 // found in the LICENSE file.
4
5 // Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com
6
7 #include "core/fxcrt/fx_codepage.h"
8
9 #include <algorithm>
10 #include <iterator>
11 #include <utility>
12
13 namespace {
14
15 const uint16_t g_FX_MSDOSThaiUnicodes[128] = {
16 0x20AC, 0x0000, 0x0000, 0x0000, 0x0000, 0x2026, 0x0000, 0x0000, 0x0000,
17 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2018,
18 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0000, 0x0000, 0x0000,
19 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x00A0, 0x0E01, 0x0E02, 0x0E03,
20 0x0E04, 0x0E05, 0x0E06, 0x0E07, 0x0E08, 0x0E09, 0x0E0A, 0x0E0B, 0x0E0C,
21 0x0E0D, 0x0E0E, 0x0E0F, 0x0E10, 0x0E11, 0x0E12, 0x0E13, 0x0E14, 0x0E15,
22 0x0E16, 0x0E17, 0x0E18, 0x0E19, 0x0E1A, 0x0E1B, 0x0E1C, 0x0E1D, 0x0E1E,
23 0x0E1F, 0x0E20, 0x0E21, 0x0E22, 0x0E23, 0x0E24, 0x0E25, 0x0E26, 0x0E27,
24 0x0E28, 0x0E29, 0x0E2A, 0x0E2B, 0x0E2C, 0x0E2D, 0x0E2E, 0x0E2F, 0x0E30,
25 0x0E31, 0x0E32, 0x0E33, 0x0E34, 0x0E35, 0x0E36, 0x0E37, 0x0E38, 0x0E39,
26 0x0E3A, 0x0000, 0x0000, 0x0000, 0x0000, 0x0E3F, 0x0E40, 0x0E41, 0x0E42,
27 0x0E43, 0x0E44, 0x0E45, 0x0E46, 0x0E47, 0x0E48, 0x0E49, 0x0E4A, 0x0E4B,
28 0x0E4C, 0x0E4D, 0x0E4E, 0x0E4F, 0x0E50, 0x0E51, 0x0E52, 0x0E53, 0x0E54,
29 0x0E55, 0x0E56, 0x0E57, 0x0E58, 0x0E59, 0x0E5A, 0x0E5B, 0x0000, 0x0000,
30 0x0000, 0x0000,
31 };
32
33 const uint16_t g_FX_MSWinEasternEuropeanUnicodes[128] = {
34 0x20AC, 0x0000, 0x201A, 0x0000, 0x201E, 0x2026, 0x2020, 0x2021, 0x0000,
35 0x2030, 0x0160, 0x2039, 0x015A, 0x0164, 0x017D, 0x0179, 0x0000, 0x2018,
36 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0000, 0x2122, 0x0161,
37 0x203A, 0x015B, 0x0165, 0x017E, 0x017A, 0x00A0, 0x02C7, 0x02D8, 0x0141,
38 0x00A4, 0x0104, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x015E, 0x00AB, 0x00AC,
39 0x00AD, 0x00AE, 0x017B, 0x00B0, 0x00B1, 0x02DB, 0x0142, 0x00B4, 0x00B5,
40 0x00B6, 0x00B7, 0x00B8, 0x0105, 0x015F, 0x00BB, 0x013D, 0x02DD, 0x013E,
41 0x017C, 0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7,
42 0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E, 0x0110,
43 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7, 0x0158, 0x016E,
44 0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF, 0x0155, 0x00E1, 0x00E2,
45 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7, 0x010D, 0x00E9, 0x0119, 0x00EB,
46 0x011B, 0x00ED, 0x00EE, 0x010F, 0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4,
47 0x0151, 0x00F6, 0x00F7, 0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD,
48 0x0163, 0x02D9,
49 };
50
51 const uint16_t g_FX_MSWinCyrillicUnicodes[128] = {
52 0x0402, 0x0403, 0x201A, 0x0453, 0x201E, 0x2026, 0x2020, 0x2021, 0x20AC,
53 0x2030, 0x0409, 0x2039, 0x040A, 0x040C, 0x040B, 0x040F, 0x0452, 0x2018,
54 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0000, 0x2122, 0x0459,
55 0x203A, 0x045A, 0x045C, 0x045B, 0x045F, 0x00A0, 0x040E, 0x045E, 0x0408,
56 0x00A4, 0x0490, 0x00A6, 0x00A7, 0x0401, 0x00A9, 0x0404, 0x00AB, 0x00AC,
57 0x00AD, 0x00AE, 0x0407, 0x00B0, 0x00B1, 0x0406, 0x0456, 0x0491, 0x00B5,
58 0x00B6, 0x00B7, 0x0451, 0x2116, 0x0454, 0x00BB, 0x0458, 0x0405, 0x0455,
59 0x0457, 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
60 0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F, 0x0420,
61 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429,
62 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F, 0x0430, 0x0431, 0x0432,
63 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043A, 0x043B,
64 0x043C, 0x043D, 0x043E, 0x043F, 0x0440, 0x0441, 0x0442, 0x0443, 0x0444,
65 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D,
66 0x044E, 0x044F,
67 };
68
69 const uint16_t g_FX_MSWinGreekUnicodes[128] = {
70 0x20AC, 0x0000, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x0000,
71 0x2030, 0x0000, 0x2039, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2018,
72 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0000, 0x2122, 0x0000,
73 0x203A, 0x0000, 0x0000, 0x0000, 0x0000, 0x00A0, 0x0385, 0x0386, 0x00A3,
74 0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x0000, 0x00AB, 0x00AC,
75 0x00AD, 0x00AE, 0x2015, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x0384, 0x00B5,
76 0x00B6, 0x00B7, 0x0388, 0x0389, 0x038A, 0x00BB, 0x038C, 0x00BD, 0x038E,
77 0x038F, 0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
78 0x0398, 0x0399, 0x039A, 0x039B, 0x039C, 0x039D, 0x039E, 0x039F, 0x03A0,
79 0x03A1, 0x0000, 0x03A3, 0x03A4, 0x03A5, 0x03A6, 0x03A7, 0x03A8, 0x03A9,
80 0x03AA, 0x03AB, 0x03AC, 0x03AD, 0x03AE, 0x03AF, 0x03B0, 0x03B1, 0x03B2,
81 0x03B3, 0x03B4, 0x03B5, 0x03B6, 0x03B7, 0x03B8, 0x03B9, 0x03BA, 0x03BB,
82 0x03BC, 0x03BD, 0x03BE, 0x03BF, 0x03C0, 0x03C1, 0x03C2, 0x03C3, 0x03C4,
83 0x03C5, 0x03C6, 0x03C7, 0x03C8, 0x03C9, 0x03CA, 0x03CB, 0x03CC, 0x03CD,
84 0x03CE, 0x0000,
85 };
86
87 const uint16_t g_FX_MSWinTurkishUnicodes[128] = {
88 0x20AC, 0x0000, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6,
89 0x2030, 0x0160, 0x2039, 0x0152, 0x0000, 0x0000, 0x0000, 0x0000, 0x2018,
90 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0x0161,
91 0x203A, 0x0153, 0x0000, 0x0000, 0x0178, 0x00A0, 0x00A1, 0x00A2, 0x00A3,
92 0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC,
93 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
94 0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE,
95 0x00BF, 0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
96 0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF, 0x011E,
97 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7, 0x00D8, 0x00D9,
98 0x00DA, 0x00DB, 0x00DC, 0x0130, 0x015E, 0x00DF, 0x00E0, 0x00E1, 0x00E2,
99 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7, 0x00E8, 0x00E9, 0x00EA, 0x00EB,
100 0x00EC, 0x00ED, 0x00EE, 0x00EF, 0x011F, 0x00F1, 0x00F2, 0x00F3, 0x00F4,
101 0x00F5, 0x00F6, 0x00F7, 0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0131,
102 0x015F, 0x00FF,
103 };
104
105 const uint16_t g_FX_MSWinHebrewUnicodes[128] = {
106 0x20AC, 0x0000, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6,
107 0x2030, 0x0000, 0x2039, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2018,
108 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x02DC, 0x2122, 0x0000,
109 0x203A, 0x0000, 0x0000, 0x0000, 0x0000, 0x00A0, 0x00A1, 0x00A2, 0x00A3,
110 0x20AA, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC,
111 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
112 0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE,
113 0x00BF, 0x05B0, 0x05B1, 0x05B2, 0x05B3, 0x05B4, 0x05B5, 0x05B6, 0x05B7,
114 0x05B8, 0x05B9, 0x0000, 0x05BB, 0x05BC, 0x05BD, 0x05BE, 0x05BF, 0x05C0,
115 0x05C1, 0x05C2, 0x05C3, 0x05F0, 0x05F1, 0x05F2, 0x05F3, 0x05F4, 0x0000,
116 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x05D0, 0x05D1, 0x05D2,
117 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7, 0x05D8, 0x05D9, 0x05DA, 0x05DB,
118 0x05DC, 0x05DD, 0x05DE, 0x05DF, 0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4,
119 0x05E5, 0x05E6, 0x05E7, 0x05E8, 0x05E9, 0x05EA, 0x0000, 0x0000, 0x200E,
120 0x200F, 0x0000,
121 };
122
123 const uint16_t g_FX_MSWinArabicUnicodes[128] = {
124 0x20AC, 0x067E, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021, 0x02C6,
125 0x2030, 0x0679, 0x2039, 0x0152, 0x0686, 0x0698, 0x0688, 0x06AF, 0x2018,
126 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x06A9, 0x2122, 0x0691,
127 0x203A, 0x0153, 0x200C, 0x200D, 0x06BA, 0x00A0, 0x060C, 0x00A2, 0x00A3,
128 0x00A4, 0x00A5, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x06BE, 0x00AB, 0x00AC,
129 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
130 0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x061B, 0x00BB, 0x00BC, 0x00BD, 0x00BE,
131 0x061F, 0x06C1, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627,
132 0x0628, 0x0629, 0x062A, 0x062B, 0x062C, 0x062D, 0x062E, 0x062F, 0x0630,
133 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x00D7, 0x0637, 0x0638,
134 0x0639, 0x063A, 0x0640, 0x0641, 0x0642, 0x0643, 0x00E0, 0x0644, 0x00E2,
135 0x0645, 0x0646, 0x0647, 0x0648, 0x00E7, 0x00E8, 0x00E9, 0x00EA, 0x00EB,
136 0x0649, 0x064A, 0x00EE, 0x00EF, 0x064B, 0x064C, 0x064D, 0x064E, 0x00F4,
137 0x064F, 0x0650, 0x00F7, 0x0651, 0x00F9, 0x0652, 0x00FB, 0x00FC, 0x200E,
138 0x200F, 0x06D2,
139 };
140
141 const uint16_t g_FX_MSWinBalticUnicodes[128] = {
142 0x20AC, 0x0000, 0x201A, 0x0000, 0x201E, 0x2026, 0x2020, 0x2021, 0x0000,
143 0x2030, 0x0000, 0x2039, 0x0000, 0x00A8, 0x02C7, 0x00B8, 0x0000, 0x2018,
144 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014, 0x0000, 0x2122, 0x0000,
145 0x203A, 0x0000, 0x00AF, 0x02DB, 0x0000, 0x00A0, 0x0000, 0x00A2, 0x00A3,
146 0x00A4, 0x0000, 0x00A6, 0x00A7, 0x00D8, 0x00A9, 0x0156, 0x00AB, 0x00AC,
147 0x00AD, 0x00AE, 0x00C6, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5,
148 0x00B6, 0x00B7, 0x00F8, 0x00B9, 0x0157, 0x00BB, 0x00BC, 0x00BD, 0x00BE,
149 0x00E6, 0x0104, 0x012E, 0x0100, 0x0106, 0x00C4, 0x00C5, 0x0118, 0x0112,
150 0x010C, 0x00C9, 0x0179, 0x0116, 0x0122, 0x0136, 0x012A, 0x013B, 0x0160,
151 0x0143, 0x0145, 0x00D3, 0x014C, 0x00D5, 0x00D6, 0x00D7, 0x0172, 0x0141,
152 0x015A, 0x016A, 0x00DC, 0x017B, 0x017D, 0x00DF, 0x0105, 0x012F, 0x0101,
153 0x0107, 0x00E4, 0x00E5, 0x0119, 0x0113, 0x010D, 0x00E9, 0x017A, 0x0117,
154 0x0123, 0x0137, 0x012B, 0x013C, 0x0161, 0x0144, 0x0146, 0x00F3, 0x014D,
155 0x00F5, 0x00F6, 0x00F7, 0x0173, 0x0142, 0x015B, 0x016B, 0x00FC, 0x017C,
156 0x017E, 0x02D9,
157 };
158
159 struct FX_CHARSET_MAP {
160 uint16_t charset;
161 uint16_t codepage;
162 };
163
164 const FX_CHARSET_MAP g_FXCharset2CodePageTable[] = {
165 {FX_CHARSET_ANSI, FX_CODEPAGE_MSWin_WesternEuropean},
166 {FX_CHARSET_Default, FX_CODEPAGE_DefANSI},
167 {FX_CHARSET_Symbol, FX_CODEPAGE_Symbol},
168 {FX_CHARSET_MAC_Roman, FX_CODEPAGE_MAC_Roman},
169 {FX_CHARSET_MAC_ShiftJIS, FX_CODEPAGE_MAC_ShiftJIS},
170 {FX_CHARSET_MAC_Korean, FX_CODEPAGE_MAC_Korean},
171 {FX_CHARSET_MAC_ChineseSimplified, FX_CODEPAGE_MAC_ChineseSimplified},
172 {FX_CHARSET_MAC_ChineseTraditional, FX_CODEPAGE_MAC_ChineseTraditional},
173 {FX_CHARSET_MAC_Hebrew, FX_CODEPAGE_MAC_Hebrew},
174 {FX_CHARSET_MAC_Arabic, FX_CODEPAGE_MAC_Arabic},
175 {FX_CHARSET_MAC_Greek, FX_CODEPAGE_MAC_Greek},
176 {FX_CHARSET_MAC_Turkish, FX_CODEPAGE_MAC_Turkish},
177 {FX_CHARSET_MAC_Thai, FX_CODEPAGE_MAC_Thai},
178 {FX_CHARSET_MAC_EasternEuropean, FX_CODEPAGE_MAC_EasternEuropean},
179 {FX_CHARSET_MAC_Cyrillic, FX_CODEPAGE_MAC_Cyrillic},
180 {FX_CHARSET_ShiftJIS, FX_CODEPAGE_ShiftJIS},
181 {FX_CHARSET_Hangul, FX_CODEPAGE_Hangul},
182 {FX_CHARSET_Johab, FX_CODEPAGE_Johab},
183 {FX_CHARSET_ChineseSimplified, FX_CODEPAGE_ChineseSimplified},
184 {FX_CHARSET_ChineseTraditional, FX_CODEPAGE_ChineseTraditional},
185 {FX_CHARSET_MSWin_Greek, FX_CODEPAGE_MSWin_Greek},
186 {FX_CHARSET_MSWin_Turkish, FX_CODEPAGE_MSWin_Turkish},
187 {FX_CHARSET_MSWin_Vietnamese, FX_CODEPAGE_MSWin_Vietnamese},
188 {FX_CHARSET_MSWin_Hebrew, FX_CODEPAGE_MSWin_Hebrew},
189 {FX_CHARSET_MSWin_Arabic, FX_CODEPAGE_MSWin_Arabic},
190 {FX_CHARSET_MSWin_Baltic, FX_CODEPAGE_MSWin_Baltic},
191 {FX_CHARSET_MSWin_Cyrillic, FX_CODEPAGE_MSWin_Cyrillic},
192 {FX_CHARSET_Thai, FX_CODEPAGE_MSDOS_Thai},
193 {FX_CHARSET_MSWin_EasternEuropean, FX_CODEPAGE_MSWin_EasternEuropean},
194 {FX_CHARSET_US, FX_CODEPAGE_MSDOS_US},
195 {FX_CHARSET_OEM, FX_CODEPAGE_MSDOS_WesternEuropean},
196 };
197
198 } // namespace
199
200 const FX_CharsetUnicodes g_FX_CharsetUnicodes[8] = {
201 {FX_CHARSET_Thai, g_FX_MSDOSThaiUnicodes},
202 {FX_CHARSET_MSWin_EasternEuropean, g_FX_MSWinEasternEuropeanUnicodes},
203 {FX_CHARSET_MSWin_Cyrillic, g_FX_MSWinCyrillicUnicodes},
204 {FX_CHARSET_MSWin_Greek, g_FX_MSWinGreekUnicodes},
205 {FX_CHARSET_MSWin_Turkish, g_FX_MSWinTurkishUnicodes},
206 {FX_CHARSET_MSWin_Hebrew, g_FX_MSWinHebrewUnicodes},
207 {FX_CHARSET_MSWin_Arabic, g_FX_MSWinArabicUnicodes},
208 {FX_CHARSET_MSWin_Baltic, g_FX_MSWinBalticUnicodes},
209 };
210
FX_GetCodePageFromCharset(uint8_t charset)211 uint16_t FX_GetCodePageFromCharset(uint8_t charset) {
212 auto* result =
213 std::lower_bound(std::begin(g_FXCharset2CodePageTable),
214 std::end(g_FXCharset2CodePageTable), charset,
215 [](const FX_CHARSET_MAP& iter, const uint16_t& charset) {
216 return iter.charset < charset;
217 });
218 if (result != std::end(g_FXCharset2CodePageTable) &&
219 result->charset == charset) {
220 return result->codepage;
221 }
222 return 0xFFFF;
223 }
224
FX_GetCharsetFromCodePage(uint16_t codepage)225 uint8_t FX_GetCharsetFromCodePage(uint16_t codepage) {
226 for (const auto& it : g_FXCharset2CodePageTable) {
227 if (it.codepage == codepage)
228 return it.charset;
229 }
230 return FX_CHARSET_ANSI;
231 }
232
FX_CharSetIsCJK(uint8_t uCharset)233 bool FX_CharSetIsCJK(uint8_t uCharset) {
234 return (uCharset == FX_CHARSET_ChineseSimplified) ||
235 (uCharset == FX_CHARSET_ChineseTraditional) ||
236 (uCharset == FX_CHARSET_Hangul) || (uCharset == FX_CHARSET_ShiftJIS);
237 }
238