src/c%2B%2B11/codecvt.cc

102     read_bom(range<const char>& from, const unsigned char (&bom)[N])
104       if (from.size() >= N && !memcmp(from.next, bom, N))
106 	  from.next += N;
112   // If consume_header is set in mode update from.next to after any BOM.
114   read_utf8_bom(range<const char>& from, codecvt_mode mode)
117       read_bom(from, utf8_bom);
120   // If consume_header is set in mode update from.next to after any BOM.
123   read_utf16_bom(range<const char16_t>& from, codecvt_mode mode)
125     if (mode & consume_header && from.size())
127 	if (*from.next == 0xFEFF)
128 	  ++from.next;
129 	else if (*from.next == 0xFFFE)
131 	    ++from.next;
138   // Read a codepoint from a UTF-8 multibyte sequence.
139   // Updates from.next if the codepoint is not greater than maxcode.
142   read_utf8_code_point(range<const char>& from, unsigned long maxcode)
144     const size_t avail = from.size();
147     unsigned char c1 = from.next[0];
151       ++from.next;
160       unsigned char c2 = from.next[1];
165 	from.next += 2;
172       unsigned char c2 = from.next[1];
177       unsigned char c3 = from.next[2];
182 	from.next += 3;
189       unsigned char c2 = from.next[1];
196       unsigned char c3 = from.next[2];
199       unsigned char c4 = from.next[3];
204 	from.next += 4;
279   // Read a codepoint from a UTF-16 multibyte sequence.
281   // Updates from.next if the codepoint is not greater than maxcode.
284   read_utf16_code_point(range<const char16_t>& from, unsigned long maxcode,
287     const size_t avail = from.size();
291     char32_t c = adjust_byte_order(from.next[0], mode);
296 	const char16_t c2 = adjust_byte_order(from.next[1], mode);
308       from.next += inc;
329 	// Algorithm from http://www.unicode.org/faq/utf_bom.html#utf16-4
343   ucs4_in(range<const char>& from, range<char32_t>& to,
346     read_utf8_bom(from, mode);
347     while (from.size() && to.size())
349 	const char32_t codepoint = read_utf8_code_point(from, maxcode);
356     return from.size() ? codecvt_base::partial : codecvt_base::ok;
361   ucs4_out(range<const char32_t>& from, range<char>& to,
366     while (from.size())
368 	const char32_t c = from.next[0];
373 	++from.next;
380   ucs4_in(range<const char16_t>& from, range<char32_t>& to,
383     if (read_utf16_bom(from, mode) == little_endian)
385     while (from.size() && to.size())
387 	const char32_t codepoint = read_utf16_code_point(from, maxcode, mode);
394     return from.size() ? codecvt_base::partial : codecvt_base::ok;
399   ucs4_out(range<const char32_t>& from, range<char16_t>& to,
404     while (from.size())
406 	const char32_t c = from.next[0];
411 	++from.next;
419   utf16_in(range<const char>& from, range<C>& to,
422     read_utf8_bom(from, mode);
423     while (from.size() && to.size())
425 	const char* const first = from.next;
426 	const char32_t codepoint = read_utf8_code_point(from, maxcode);
433 	    from.next = first;
443   utf16_out(range<const C>& from, range<char>& to,
448     while (from.size())
450 	char32_t c = from.next[0];
454 	    if (from.size() < 2)
457 	    const char32_t c2 = from.next[1];
472 	from.next += inc;
482     range<const char> from{ begin, end };
483     read_utf8_bom(from, mode);
487 	char32_t c = read_utf8_code_point(from, maxcode);
489 	  return from.next;
495       read_utf8_code_point(from, std::max(max_single_utf16_unit, maxcode));
496     return from.next;
501   ucs2_in(range<const char>& from, range<char16_t>& to,
504     return utf16_in(from, to, std::max(max_single_utf16_unit, maxcode), mode);
509   ucs2_out(range<const char16_t>& from, range<char>& to,
512     return utf16_out(from, to, std::max(max_single_utf16_unit, maxcode), mode);
517   ucs2_out(range<const char16_t>& from, range<char16_t>& to,
522     while (from.size() && to.size())
524 	char16_t c = from.next[0];
530 	++from.next;
532     return from.size() == 0 ? codecvt_base::ok : codecvt_base::partial;
537   ucs2_in(range<const char16_t>& from, range<char16_t>& to,
540     if (read_utf16_bom(from, mode) == little_endian)
543     while (from.size() && to.size())
545 	const char32_t c = read_utf16_code_point(from, maxcode, mode);
552     return from.size() == 0 ? codecvt_base::ok : codecvt_base::partial;
559     range<const char16_t> from{ begin, end };
560     if (read_utf16_bom(from, mode) == little_endian)
565       c = read_utf16_code_point(from, maxcode, mode);
566     return from.next;
573     range<const char> from{ begin, end };
574     read_utf8_bom(from, mode);
578       c = read_utf8_code_point(from, maxcode);
579     return from.next;
587     range<const char> from{ begin, end };
588     read_utf8_bom(from, mode);
591       c = read_utf8_code_point(from, maxcode);
592     return from.next;
600     range<const char16_t> from{ begin, end };
601     if (read_utf16_bom(from, mode) == little_endian)
605       c = read_utf16_code_point(from, maxcode, mode);
606     return from.next;
611 // Converts from UTF-8 to UTF-16.
625   range<const char16_t> from{ __from, __from_end };
627   auto res = utf16_out(from, to);
628   __from_next = from.next;
649   range<const char> from{ __from, __from_end };
656   auto res = utf16_in(from, to, max_code_point, mode);
657   __from_next = from.next;
688 // Converts from UTF-8 to UTF-32 (aka UCS-4).
701   range<const char32_t> from{ __from, __from_end };
703   auto res = ucs4_out(from, to);
704   __from_next = from.next;
725   range<const char> from{ __from, __from_end };
727   auto res = ucs4_in(from, to);
728   __from_next = from.next;
755 // Converts from UTF-8 to UCS-2.
766   range<const char16_t> from{ __from, __from_end };
768   auto res = ucs2_out(from, to, _M_maxcode, _M_mode);
769   __from_next = from.next;
790   range<const char> from{ __from, __from_end };
796   auto res = ucs2_in(from, to, _M_maxcode, mode);
797   __from_next = from.next;
824 // Converts from UTF-8 to UTF-32 (aka UCS-4).
835   range<const char32_t> from{ __from, __from_end };
837   auto res = ucs4_out(from, to, _M_maxcode, _M_mode);
838   __from_next = from.next;
859   range<const char> from{ __from, __from_end };
861   auto res = ucs4_in(from, to, _M_maxcode, _M_mode);
862   __from_next = from.next;
890 // Converts from UTF-8 to UCS-2 or UCS-4 depending on sizeof(wchar_t).
903   range<const char16_t> from{
907   auto res = ucs2_out(from, to, _M_maxcode, _M_mode);
909   range<const char32_t> from{
913   auto res = ucs4_out(from, to, _M_maxcode, _M_mode);
917   __from_next = reinterpret_cast<const wchar_t*>(from.next);
938   range<const char> from{ __from, __from_end };
944   auto res = ucs2_in(from, to, _M_maxcode, _M_mode);
950   auto res = ucs4_in(from, to, _M_maxcode, _M_mode);
954   __from_next = from.next;
988 // Converts from UTF-16 to UCS-2.
999   range<const char16_t> from{ __from, __from_end };
1004   auto res = ucs2_out(from, to, _M_maxcode, _M_mode);
1005   __from_next = from.next;
1026   range<const char16_t> from{
1031   auto res = ucs2_in(from, to, _M_maxcode, _M_mode);
1032   __from_next = reinterpret_cast<const char*>(from.next);
1061 // Converts from UTF-16 to UTF-32 (aka UCS-4).
1072   range<const char32_t> from{ __from, __from_end };
1077   auto res = ucs4_out(from, to, _M_maxcode, _M_mode);
1078   __from_next = from.next;
1099   range<const char16_t> from{
1104   auto res = ucs4_in(from, to, _M_maxcode, _M_mode);
1105   __from_next = reinterpret_cast<const char*>(from.next);
1135 // Converts from UTF-8 to UCS-2 or UCS-4 depending on sizeof(wchar_t).
1148   range<const char16_t> from{
1152   auto res = ucs2_out(from, to, _M_maxcode, _M_mode);
1154   range<const char32_t> from{
1158   auto res = ucs4_out(from, to, _M_maxcode, _M_mode);
1162   __from_next = reinterpret_cast<const wchar_t*>(from.next);
1183   range<const char> from{ __from, __from_end };
1189   auto res = ucs2_in(from, to, _M_maxcode, _M_mode);
1195   auto res = ucs4_in(from, to, _M_maxcode, _M_mode);
1199   __from_next = from.next;
1234 // Converts from UTF-8 to UTF-16.
1245   range<const char16_t> from{ __from, __from_end };
1247   auto res = utf16_out(from, to, _M_maxcode, _M_mode);
1248   __from_next = from.next;
1269   range<const char> from{ __from, __from_end };
1275   auto res = utf16_in(from, to, _M_maxcode, mode);
1276   __from_next = from.next;
1307 // Converts from UTF-8 to UTF-16.
1318   range<const char32_t> from{ __from, __from_end };
1320   auto res = utf16_out(from, to, _M_maxcode, _M_mode);
1321   __from_next = from.next;
1342   range<const char> from{ __from, __from_end };
1344   auto res = utf16_in(from, to, _M_maxcode, _M_mode);
1345   __from_next = from.next;
1377 // Converts from UTF-8 to UTF-16.
1388   range<const wchar_t> from{ __from, __from_end };
1390   auto res = utf16_out(from, to, _M_maxcode, _M_mode);
1391   __from_next = from.next;
1412   range<const char> from{ __from, __from_end };
1414   auto res = utf16_in(from, to, _M_maxcode, _M_mode);
1415   __from_next = from.next;