1 // Copyright 2014 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 "../../include/fxcrt/fx_basic.h"
Clear()8 void CFX_UTF8Decoder::Clear()
9 {
10 m_Buffer.Clear();
11 m_PendingBytes = 0;
12 }
AppendChar(FX_DWORD ch)13 void CFX_UTF8Decoder::AppendChar(FX_DWORD ch)
14 {
15 m_Buffer.AppendChar((FX_WCHAR)ch);
16 }
Input(FX_BYTE byte)17 void CFX_UTF8Decoder::Input(FX_BYTE byte)
18 {
19 if (byte < 0x80) {
20 m_PendingBytes = 0;
21 m_Buffer.AppendChar(byte);
22 } else if (byte < 0xc0) {
23 if (m_PendingBytes == 0) {
24 return;
25 }
26 m_PendingBytes --;
27 m_PendingChar |= (byte & 0x3f) << (m_PendingBytes * 6);
28 if (m_PendingBytes == 0) {
29 AppendChar(m_PendingChar);
30 }
31 } else if (byte < 0xe0) {
32 m_PendingBytes = 1;
33 m_PendingChar = (byte & 0x1f) << 6;
34 } else if (byte < 0xf0) {
35 m_PendingBytes = 2;
36 m_PendingChar = (byte & 0x0f) << 12;
37 } else if (byte < 0xf8) {
38 m_PendingBytes = 3;
39 m_PendingChar = (byte & 0x07) << 18;
40 } else if (byte < 0xfc) {
41 m_PendingBytes = 4;
42 m_PendingChar = (byte & 0x03) << 24;
43 } else if (byte < 0xfe) {
44 m_PendingBytes = 5;
45 m_PendingChar = (byte & 0x01) << 30;
46 }
47 }
Input(FX_WCHAR unicode)48 void CFX_UTF8Encoder::Input(FX_WCHAR unicode)
49 {
50 if ((FX_DWORD)unicode < 0x80) {
51 m_Buffer.AppendChar(unicode);
52 } else {
53 if ((FX_DWORD)unicode >= 0x80000000) {
54 return;
55 }
56 int nbytes = 0;
57 if ((FX_DWORD)unicode < 0x800) {
58 nbytes = 2;
59 } else if ((FX_DWORD)unicode < 0x10000) {
60 nbytes = 3;
61 } else if ((FX_DWORD)unicode < 0x200000) {
62 nbytes = 4;
63 } else if ((FX_DWORD)unicode < 0x4000000) {
64 nbytes = 5;
65 } else {
66 nbytes = 6;
67 }
68 static FX_BYTE prefix[] = {0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
69 int order = 1 << ((nbytes - 1) * 6);
70 int code = unicode;
71 m_Buffer.AppendChar(prefix[nbytes - 2] | (code / order));
72 for (int i = 0; i < nbytes - 1; i ++) {
73 code = code % order;
74 order >>= 6;
75 m_Buffer.AppendChar(0x80 | (code / order));
76 }
77 }
78 }
FX_UTF8Encode(FX_LPCWSTR pwsStr,FX_STRSIZE len)79 CFX_ByteString FX_UTF8Encode(FX_LPCWSTR pwsStr, FX_STRSIZE len)
80 {
81 FXSYS_assert(pwsStr != NULL);
82 if (len < 0) {
83 len = (FX_STRSIZE)FXSYS_wcslen(pwsStr);
84 }
85 CFX_UTF8Encoder encoder;
86 while (len -- > 0) {
87 encoder.Input(*pwsStr ++);
88 }
89 return encoder.GetResult();
90 }
FX_UTF8Encode(FX_LPCWSTR pwsStr,FX_STRSIZE len,CFX_ByteStringL & utf8Str,IFX_Allocator * pAllocator)91 void FX_UTF8Encode(FX_LPCWSTR pwsStr, FX_STRSIZE len, CFX_ByteStringL &utf8Str, IFX_Allocator* pAllocator)
92 {
93 FXSYS_assert(pwsStr != NULL);
94 if (len < 0) {
95 len = (FX_STRSIZE)FXSYS_wcslen(pwsStr);
96 }
97 CFX_UTF8Encoder encoder(pAllocator);
98 while (len -- > 0) {
99 encoder.Input(*pwsStr ++);
100 }
101 encoder.GetResult(utf8Str);
102 }
103