utf8 Namespace Reference

Namespaces
	internal
	unchecked

Classes
class	exception
class	invalid_code_point
class	invalid_utf16
class	invalid_utf8
class	iterator
class	not_enough_room

Typedefs
typedef unsigned char	uint8_t
typedef unsigned short	uint16_t
typedef unsigned int	uint32_t

Functions
template<typename octet_iterator >
octet_iterator	append (uint32_t cp, octet_iterator result)
	The library API - functions intended to be called by the users. More...
template<typename octet_iterator , typename output_iterator >
output_iterator	replace_invalid (octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
template<typename octet_iterator , typename output_iterator >
output_iterator	replace_invalid (octet_iterator start, octet_iterator end, output_iterator out)
template<typename octet_iterator >
uint32_t	next (octet_iterator &it, octet_iterator end)
template<typename octet_iterator >
uint32_t	peek_next (octet_iterator it, octet_iterator end)
template<typename octet_iterator >
uint32_t	prior (octet_iterator &it, octet_iterator start)
template<typename octet_iterator >
uint32_t	previous (octet_iterator &it, octet_iterator pass_start)
	Deprecated in versions that include "prior". More...
template<typename octet_iterator , typename distance_type >
void	advance (octet_iterator &it, distance_type n, octet_iterator end)
template<typename octet_iterator >
std::iterator_traits < octet_iterator > ::difference_type	distance (octet_iterator first, octet_iterator last)
template<typename u16bit_iterator , typename octet_iterator >
octet_iterator	utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
template<typename u16bit_iterator , typename octet_iterator >
u16bit_iterator	utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
template<typename octet_iterator , typename u32bit_iterator >
octet_iterator	utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
template<typename octet_iterator , typename u32bit_iterator >
u32bit_iterator	utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
template<typename octet_iterator >
octet_iterator	find_invalid (octet_iterator start, octet_iterator end)
template<typename octet_iterator >
bool	is_valid (octet_iterator start, octet_iterator end)
template<typename octet_iterator >
bool	starts_with_bom (octet_iterator it, octet_iterator end)
template<typename octet_iterator >
bool	is_bom (octet_iterator it)

Variables
const uint8_t	bom [] = {0xef, 0xbb, 0xbf}
	The library API - functions intended to be called by the users. More...

Typedef Documentation

typedef unsigned short utf8::uint16_t

typedef unsigned int utf8::uint32_t

typedef unsigned char utf8::uint8_t

Function Documentation

template<typename octet_iterator , typename distance_type >

void utf8::advance	(	octet_iterator &	it,
		distance_type	n,
		octet_iterator	end
	)

 {
 for (distance_type i = 0; i < n; ++i)
 utf8::next(it, end);
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

octet_iterator utf8::append	(	uint32_t	cp,
		octet_iterator	result
	)

The library API - functions intended to be called by the users.

 {
 if (!utf8::internal::is_code_point_valid(cp))
 throw invalid_code_point(cp);

 if (cp < 0x80) // one octet
 *(result++) = static_cast<uint8_t>(cp);
 else if (cp < 0x800) { // two octets
 *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
 *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
 }
 else if (cp < 0x10000) { // three octets
 *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
 *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
 *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
 }
 else { // four octets
 *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
 *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80);
 *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
 *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
 }
 return result;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

std::iterator_traits<octet_iterator>::difference_type utf8::distance	(	octet_iterator	first,
		octet_iterator	last
	)

 {
 typename std::iterator_traits<octet_iterator>::difference_type dist;
 for (dist = 0; first < last; ++dist)
 utf8::next(first, last);
 return dist;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

octet_iterator utf8::find_invalid	(	octet_iterator	start,
		octet_iterator	end
	)

 {
 octet_iterator result = start;
 while (result != end) {
 utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
 if (err_code != internal::UTF8_OK)
 return result;
 }
 return result;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

bool utf8::is_bom ( octet_iterator  it )

inline

 {
 return (
 (utf8::internal::mask8(*it++)) == bom[0] &&
 (utf8::internal::mask8(*it++)) == bom[1] &&
 (utf8::internal::mask8(*it)) == bom[2]
 );
 }

Here is the call graph for this function:

template<typename octet_iterator >

bool utf8::is_valid ( octet_iterator  start, octet_iterator  end  )

inline

 {
 return (utf8::find_invalid(start, end) == end);
 }

Here is the call graph for this function:

template<typename octet_iterator >

uint32_t utf8::next	(	octet_iterator &	it,
		octet_iterator	end
	)

 {
 uint32_t cp = 0;
 internal::utf_error err_code = utf8::internal::validate_next(it, end, cp);
 switch (err_code) {
 case internal::UTF8_OK :
 break;
 case internal::NOT_ENOUGH_ROOM :
 throw not_enough_room();
 case internal::INVALID_LEAD :
 case internal::INCOMPLETE_SEQUENCE :
 case internal::OVERLONG_SEQUENCE :
 throw invalid_utf8(*it);
 case internal::INVALID_CODE_POINT :
 throw invalid_code_point(cp);
 }
 return cp;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

uint32_t utf8::peek_next	(	octet_iterator	it,
		octet_iterator	end
	)

 {
 return utf8::next(it, end);
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

uint32_t utf8::previous	(	octet_iterator &	it,
		octet_iterator	pass_start
	)

Deprecated in versions that include "prior".

 {
 octet_iterator end = it;
 while (utf8::internal::is_trail(*(--it)))
 if (it == pass_start)
 throw invalid_utf8(*it); // error - no lead byte in the sequence
 octet_iterator temp = it;
 return utf8::next(temp, end);
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator >

uint32_t utf8::prior	(	octet_iterator &	it,
		octet_iterator	start
	)

 {
 // can't do much if it == start
 if (it == start)
 throw not_enough_room();

 octet_iterator end = it;
 // Go back until we hit either a lead octet or start
 while (utf8::internal::is_trail(*(--it)))
 if (it == start)
 throw invalid_utf8(*it); // error - no lead byte in the sequence
 return utf8::peek_next(it, end);
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator , typename output_iterator >

output_iterator utf8::replace_invalid	(	octet_iterator	start,
		octet_iterator	end,
		output_iterator	out,
		uint32_t	replacement
	)

 {
 while (start != end) {
 octet_iterator sequence_start = start;
 internal::utf_error err_code = utf8::internal::validate_next(start, end);
 switch (err_code) {
 case internal::UTF8_OK :
 for (octet_iterator it = sequence_start; it != start; ++it)
 *out++ = *it;
 break;
 case internal::NOT_ENOUGH_ROOM:
 throw not_enough_room();
 case internal::INVALID_LEAD:
 out = utf8::append (replacement, out);
 ++start;
 break;
 case internal::INCOMPLETE_SEQUENCE:
 case internal::OVERLONG_SEQUENCE:
 case internal::INVALID_CODE_POINT:
 out = utf8::append (replacement, out);
 ++start;
 // just one replacement mark for the sequence
 while (start != end && utf8::internal::is_trail(*start))
 ++start;
 break;
 }
 }
 return out;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator , typename output_iterator >

output_iterator utf8::replace_invalid ( octet_iterator  start, octet_iterator  end, output_iterator  out  )

inline

 {
 static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd);
 return utf8::replace_invalid(start, end, out, replacement_marker);
 }

Here is the call graph for this function:

template<typename octet_iterator >

bool utf8::starts_with_bom ( octet_iterator  it, octet_iterator  end  )

inline

 {
 return (
 ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
 ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
 ((it != end) && (utf8::internal::mask8(*it)) == bom[2])
 );
 }

Here is the call graph for this function:

template<typename u16bit_iterator , typename octet_iterator >

octet_iterator utf8::utf16to8	(	u16bit_iterator	start,
		u16bit_iterator	end,
		octet_iterator	result
	)

 {
 while (start != end) {
 uint32_t cp = utf8::internal::mask16(*start++);
 // Take care of surrogate pairs first
 if (utf8::internal::is_lead_surrogate(cp)) {
 if (start != end) {
 uint32_t trail_surrogate = utf8::internal::mask16(*start++);
 if (utf8::internal::is_trail_surrogate(trail_surrogate))
 cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
 else
 throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
 }
 else
 throw invalid_utf16(static_cast<uint16_t>(cp));

 }
 // Lone trail surrogate
 else if (utf8::internal::is_trail_surrogate(cp))
 throw invalid_utf16(static_cast<uint16_t>(cp));

 result = utf8::append(cp, result);
 }
 return result;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator , typename u32bit_iterator >

octet_iterator utf8::utf32to8	(	u32bit_iterator	start,
		u32bit_iterator	end,
		octet_iterator	result
	)

 {
 while (start != end)
 result = utf8::append(*(start++), result);

 return result;
 }

Here is the call graph for this function:

template<typename u16bit_iterator , typename octet_iterator >

u16bit_iterator utf8::utf8to16	(	octet_iterator	start,
		octet_iterator	end,
		u16bit_iterator	result
	)

 {
 while (start != end) {
 uint32_t cp = utf8::next(start, end);
 if (cp > 0xffff) { //make a surrogate pair
 *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
 *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
 }
 else
 *result++ = static_cast<uint16_t>(cp);
 }
 return result;
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename octet_iterator , typename u32bit_iterator >

u32bit_iterator utf8::utf8to32	(	octet_iterator	start,
		octet_iterator	end,
		u32bit_iterator	result
	)

 {
 while (start != end)
 (*result++) = utf8::next(start, end);

 return result;
 }

Here is the call graph for this function:

Variable Documentation

const uint8_t utf8::bom[] = {0xef, 0xbb, 0xbf}

The library API - functions intended to be called by the users.