#include "squid.h"
#include "auth/toUtf.h"
#include "sbuf/SBuf.h"
#include <limits>

Include dependency graph for toUtf.cc:

Functions
SBuf	Latin1ToUtf8 (const char *in)
	converts ISO-LATIN-1 to UTF-8

SBuf	Cp1251ToUtf8 (const char *in)
	converts CP1251 to UTF-8

static size_t	utf8CodePointLength (const char b0)

static bool	isValidUtf8CodePoint (const unsigned char *source, const size_t length)

bool	isValidUtf8String (const char source, const char sourceEnd)
	returns whether the given input is a valid (or empty) sequence of UTF-8 code points

Function Documentation

◆ Cp1251ToUtf8()

SBuf Cp1251ToUtf8 ( const char * in )

Definition at line 37 of file toUtf.cc.

References SBuf::append().

◆ isValidUtf8CodePoint()

static bool isValidUtf8CodePoint	(	const unsigned char *	source,
		const size_t	length
	)

static

Utility routine to tell whether a sequence of bytes is valid UTF-8. This must be called with the length pre-determined by the first byte. If presented with a length > 4, this returns false. The Unicode definition of UTF-8 goes up to 4-byte code points.

Definition at line 123 of file toUtf.cc.

Referenced by isValidUtf8String().

◆ isValidUtf8String()

bool isValidUtf8String	(	const char *	source,
		const char *	sourceEnd
	)

Returns: whether the given input is a valid (or empty) sequence of UTF-8 code points

Definition at line 172 of file toUtf.cc.

References isValidUtf8CodePoint(), and utf8CodePointLength().

◆ Latin1ToUtf8()

SBuf Latin1ToUtf8 ( const char * in )

Definition at line 16 of file toUtf.cc.

References SBuf::append().

◆ utf8CodePointLength()

static size_t utf8CodePointLength ( const char b0 )

inlinestatic

Returns: the length of a UTF-8 code point that starts at the given byte

Return values

0	indicates an invalid code point

Parameters

b0	the first byte of a UTF-8 code point

Definition at line 101 of file toUtf.cc.