1// Created on: 2013-01-28
2// Created by: Kirill GAVRILOV
3// Copyright (c) 2013-2014 OPEN CASCADE SAS
4//
5// This file is part of Open CASCADE Technology software library.
6//
7// This library is free software; you can redistribute it and/or modify it under
8// the terms of the GNU Lesser General Public License version 2.1 as published
9// by the Free Software Foundation, with special exception defined in the file
10// OCCT_LGPL_EXCEPTION.txt. Consult the file LICENSE_LGPL_21.txt included in OCCT
11// distribution for complete text of the license and disclaimer of any warranty.
12//
13// Alternatively, this file may be used under the terms of Open CASCADE
14// commercial license or contractual agreement.
15
16// Portions of code are copyrighted by Unicode, Inc.
17//
18// Copyright (c) 2001-2004 Unicode, Inc.
19//
20// Disclaimer
21//
22// This source code is provided as is by Unicode, Inc. No claims are
23// made as to fitness for any particular purpose. No warranties of any
24// kind are expressed or implied. The recipient agrees to determine
25// applicability of information provided. If this file has been
26// purchased on magnetic or optical media from Unicode, Inc., the
27// sole remedy for any claim will be exchange of defective media
28// within 90 days of receipt.
29//
30// Limitations on Rights to Redistribute This Code
31//
32// Unicode, Inc. hereby grants the right to freely use the information
33// supplied in this file in the creation of products supporting the
34// Unicode Standard, and to make copies of this file in any form
35// for internal or external distribution as long as this notice
36// remains attached.
37
38//! The first character in a UTF-8 sequence indicates how many bytes
39//! to read (among other things).
40template<typename Type>
41const unsigned char NCollection_UtfIterator<Type>::UTF8_BYTES_MINUS_ONE[256] =
42{
43  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
44  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
45  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
46  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
47  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
48  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
49  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
50  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
51};
52
53//! Magic values subtracted from a buffer value during UTF-8 conversion.
54//! This table contains as many values as there might be trailing bytes
55//! in a UTF-8 sequence.
56template<typename Type>
57const unsigned long NCollection_UtfIterator<Type>::offsetsFromUTF8[6] =
58{
59  0x00000000UL, 0x00003080UL, 0x000E2080UL,
60  0x03C82080UL, 0xFA082080UL, 0x82082080UL
61};
62
63//! The first character in a UTF-8 sequence indicates how many bytes to read.
64template<typename Type>
65const unsigned char NCollection_UtfIterator<Type>::UTF8_FIRST_BYTE_MARK[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
66
67// =======================================================================
68// function : readUTF8
69// purpose  : Get a UTF-8 character; leave the tracking pointer at the start of the next character.
70//            Not protected against invalid UTF-8.
71// =======================================================================
72template<typename Type>
73inline void NCollection_UtfIterator<Type>::readUTF8()
74{
75  // unsigned arithmetic used
76  Standard_Utf8UChar* aPos = (Standard_Utf8UChar* )myPosNext;
77  const unsigned char aBytesToRead = UTF8_BYTES_MINUS_ONE[*aPos];
78  myCharUtf32 = 0;
79  switch (aBytesToRead)
80  {
81    case 5: myCharUtf32 += *aPos++; myCharUtf32 <<= 6; // remember, illegal UTF-8
82      Standard_FALLTHROUGH
83    case 4: myCharUtf32 += *aPos++; myCharUtf32 <<= 6; // remember, illegal UTF-8
84      Standard_FALLTHROUGH
85    case 3: myCharUtf32 += *aPos++; myCharUtf32 <<= 6;
86      Standard_FALLTHROUGH
87    case 2: myCharUtf32 += *aPos++; myCharUtf32 <<= 6;
88      Standard_FALLTHROUGH
89    case 1: myCharUtf32 += *aPos++; myCharUtf32 <<= 6;
90      Standard_FALLTHROUGH
91    case 0: myCharUtf32 += *aPos++;
92  }
93  myCharUtf32 -= offsetsFromUTF8[aBytesToRead];
94  myPosNext = (Type* )aPos;
95}
96
97// magic numbers
98template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF8_BYTE_MASK = 0xBF;
99template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF8_BYTE_MARK = 0x80;
100template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_HIGH_START = 0xD800;
101template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_HIGH_END   = 0xDBFF;
102template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_LOW_START  = 0xDC00;
103template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_LOW_END    = 0xDFFF;
104template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_HIGH_SHIFT = 10;
105template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_LOW_BASE   = 0x0010000UL;
106template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF16_SURROGATE_LOW_MASK   = 0x3FFUL;
107template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF32_MAX_BMP   = 0x0000FFFFUL;
108template<typename Type> const unsigned long NCollection_UtfIterator<Type>::UTF32_MAX_LEGAL = 0x0010FFFFUL;
109
110// =======================================================================
111// function : readUTF16
112// purpose  :
113// =======================================================================
114template<typename Type> inline
115void NCollection_UtfIterator<Type>::readUTF16()
116{
117  Standard_Utf32Char aChar = *myPosNext++;
118  // if we have the first half of the surrogate pair
119  if (aChar >= UTF16_SURROGATE_HIGH_START
120   && aChar <= UTF16_SURROGATE_HIGH_END)
121  {
122    const Standard_Utf32Char aChar2 = *myPosNext;
123    // complete the surrogate pair
124    if (aChar2 >= UTF16_SURROGATE_LOW_START
125     && aChar2 <= UTF16_SURROGATE_LOW_END)
126    {
127      aChar = ((aChar - UTF16_SURROGATE_HIGH_START) << UTF16_SURROGATE_HIGH_SHIFT)
128            + (aChar2 - UTF16_SURROGATE_LOW_START)   + UTF16_SURROGATE_LOW_BASE;
129      ++myPosNext;
130    }
131  }
132  myCharUtf32 = aChar;
133}
134
135// =======================================================================
136// function : AdvanceBytesUtf8
137// purpose  :
138// =======================================================================
139template<typename Type> inline
140Standard_Integer NCollection_UtfIterator<Type>::AdvanceBytesUtf8() const
141{
142  if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START
143   && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
144   {
145    // UTF-16 surrogate values are illegal in UTF-32
146    return 0;
147  }
148  else if (myCharUtf32 < Standard_Utf32Char(0x80))
149  {
150    return 1;
151  }
152  else if (myCharUtf32 < Standard_Utf32Char(0x800))
153  {
154    return 2;
155  }
156  else if (myCharUtf32 < Standard_Utf32Char(0x10000))
157  {
158    return 3;
159  }
160  else if (myCharUtf32 <= UTF32_MAX_LEGAL)
161  {
162    return 4;
163  }
164  else
165  {
166    // illegal
167    return 0;
168  }
169}
170
171// =======================================================================
172// function : GetUtf8
173// purpose  :
174// =======================================================================
175template<typename Type> inline
176Standard_Utf8Char* NCollection_UtfIterator<Type>::GetUtf8 (Standard_Utf8Char* theBuffer) const
177{
178  // unsigned arithmetic used
179  return (Standard_Utf8Char* )GetUtf8 ((Standard_Utf8UChar* )theBuffer);
180}
181
182// =======================================================================
183// function : GetUtf8
184// purpose  :
185// =======================================================================
186template<typename Type> inline
187Standard_Utf8UChar* NCollection_UtfIterator<Type>::GetUtf8 (Standard_Utf8UChar* theBuffer) const
188{
189  Standard_Utf32Char aChar = myCharUtf32;
190  if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START
191   && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
192  {
193    // UTF-16 surrogate values are illegal in UTF-32
194    return theBuffer;
195  }
196  else if (myCharUtf32 < Standard_Utf32Char(0x80))
197  {
198    *theBuffer++ = Standard_Utf8UChar (aChar | UTF8_FIRST_BYTE_MARK[1]);
199    return theBuffer;
200  }
201  else if (myCharUtf32 < Standard_Utf32Char(0x800))
202  {
203    *++theBuffer = Standard_Utf8UChar((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK); aChar >>= 6;
204    *--theBuffer = Standard_Utf8UChar (aChar | UTF8_FIRST_BYTE_MARK[2]);
205    return theBuffer + 2;
206  }
207  else if (myCharUtf32 < Standard_Utf32Char(0x10000))
208  {
209    theBuffer += 3;
210    *--theBuffer = Standard_Utf8UChar((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK); aChar >>= 6;
211    *--theBuffer = Standard_Utf8UChar((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK); aChar >>= 6;
212    *--theBuffer = Standard_Utf8UChar (aChar | UTF8_FIRST_BYTE_MARK[3]);
213    return theBuffer + 3;
214  }
215  else if (myCharUtf32 <= UTF32_MAX_LEGAL)
216  {
217    theBuffer += 4;
218    *--theBuffer = Standard_Utf8UChar((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK); aChar >>= 6;
219    *--theBuffer = Standard_Utf8UChar((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK); aChar >>= 6;
220    *--theBuffer = Standard_Utf8UChar((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK); aChar >>= 6;
221    *--theBuffer = Standard_Utf8UChar (aChar | UTF8_FIRST_BYTE_MARK[4]);
222    return theBuffer + 4;
223  }
224  else
225  {
226    // illegal
227    return theBuffer;
228  }
229}
230
231// =======================================================================
232// function : AdvanceBytesUtf16
233// purpose  :
234// =======================================================================
235template<typename Type> inline
236Standard_Integer NCollection_UtfIterator<Type>::AdvanceBytesUtf16() const
237{
238  return AdvanceCodeUnitsUtf16() * sizeof(Standard_Utf16Char);
239}
240
241// =======================================================================
242// function : AdvanceCodeUnitsUtf16
243// purpose  :
244// =======================================================================
245template<typename Type> inline
246Standard_Integer NCollection_UtfIterator<Type>::AdvanceCodeUnitsUtf16() const
247{
248  if (myCharUtf32 <= UTF32_MAX_BMP) // target is a character <= 0xFFFF
249  {
250    // UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values
251    if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START
252     && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
253    {
254      return 0;
255    }
256    else
257    {
258      return 1;
259    }
260  }
261  else if (myCharUtf32 > UTF32_MAX_LEGAL)
262  {
263    // illegal
264    return 0;
265  }
266  else
267  {
268    // target is a character in range 0xFFFF - 0x10FFFF
269    // surrogate pair
270    return 2;
271  }
272}
273
274// =======================================================================
275// function : GetUtf16
276// purpose  :
277// =======================================================================
278template<typename Type> inline
279Standard_Utf16Char* NCollection_UtfIterator<Type>::GetUtf16 (Standard_Utf16Char* theBuffer) const
280{
281  if (myCharUtf32 <= UTF32_MAX_BMP) // target is a character <= 0xFFFF
282  {
283    // UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values
284    if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START
285     && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
286    {
287      return theBuffer;
288    }
289    else
290    {
291      *theBuffer++ = Standard_Utf16Char(myCharUtf32);
292      return theBuffer;
293    }
294  }
295  else if (myCharUtf32 > UTF32_MAX_LEGAL)
296  {
297    // illegal
298    return theBuffer;
299  }
300  else
301  {
302    // surrogate pair
303    Standard_Utf32Char aChar = myCharUtf32 - UTF16_SURROGATE_LOW_BASE;
304    *theBuffer++ = Standard_Utf16Char((aChar >> UTF16_SURROGATE_HIGH_SHIFT) + UTF16_SURROGATE_HIGH_START);
305    *theBuffer++ = Standard_Utf16Char((aChar &  UTF16_SURROGATE_LOW_MASK)   + UTF16_SURROGATE_LOW_START);
306    return theBuffer;
307  }
308}
309
310// =======================================================================
311// function : GetUtf32
312// purpose  :
313// =======================================================================
314template<typename Type> inline
315Standard_Utf32Char* NCollection_UtfIterator<Type>::GetUtf32 (Standard_Utf32Char* theBuffer) const
316{
317  *theBuffer++ = myCharUtf32;
318  return theBuffer;
319}
320