CCharsetDetection Class Reference

#include <CharsetDetection.h>

Static Public Member Functions
static std::string	GetBomEncoding (const char *const content, const size_t contentLength)
static std::string	GetBomEncoding (const std::string &content)
static bool	DetectXmlEncoding (const std::string &xmlContent, std::string &detectedEncoding)
static bool	DetectXmlEncoding (const char *const xmlContent, const size_t contentLength, std::string &detectedEncoding)
static bool	ConvertHtmlToUtf8 (const std::string &htmlContent, std::string &converted, const std::string &serverReportedCharset="")
static bool	ConvertHtmlToUtf8 (const std::string &htmlContent, std::string &converted, const std::string &serverReportedCharset, std::string &usedHtmlCharset)
static bool	ConvertPlainTextToUtf8 (const std::string &textContent, std::string &converted, const std::string &serverReportedCharset, std::string &usedCharset)

Member Function Documentation

ConvertHtmlToUtf8() [1/2]

bool CCharsetDetection::ConvertHtmlToUtf8 ( const std::string &  htmlContent, std::string &  converted, const std::string &  serverReportedCharset, std::string &  usedHtmlCharset  )

static

Detect HTML charset and HTML convert to UTF-8

Parameters

htmlContent	content of HTML file
converted	receive result of conversion
serverReportedCharset	charset from HTTP header or from other out-of-band source, empty if unknown or unset
usedHtmlCharset	receive charset used for conversion

Returns

true if charset is properly detected and HTML is correctly converted, false if charset is only guessed

ConvertHtmlToUtf8() [2/2]

static bool CCharsetDetection::ConvertHtmlToUtf8 ( const std::string &  htmlContent, std::string &  converted, const std::string &  serverReportedCharset = ""  )

inlinestatic

Detect HTML charset and HTML convert to UTF-8

Parameters

htmlContent	content of HTML file
converted	receive result of conversion
serverReportedCharset	charset from HTTP header or from other out-of-band source, empty if unknown or unset

Returns

true if charset is properly detected and HTML is correctly converted, false if charset is only guessed

ConvertPlainTextToUtf8()

bool CCharsetDetection::ConvertPlainTextToUtf8 ( const std::string &  textContent, std::string &  converted, const std::string &  serverReportedCharset, std::string &  usedCharset  )

static

Try to convert plain text to UTF-8 using best suitable charset

Parameters

textContent	text to convert
converted	receive result of conversion
serverReportedCharset	charset from HTTP header or from other out-of-band source, empty if unknown or unset
usedCharset	receive charset used for conversion

Returns

true if converted without errors, false otherwise

DetectXmlEncoding() [1/2]

bool CCharsetDetection::DetectXmlEncoding ( const char *const  xmlContent, const size_t  contentLength, std::string &  detectedEncoding  )

static

DetectXmlEncoding() [2/2]

static bool CCharsetDetection::DetectXmlEncoding ( const std::string &  xmlContent, std::string &  detectedEncoding  )

inlinestatic

GetBomEncoding() [1/2]

std::string CCharsetDetection::GetBomEncoding ( const char *const  content, const size_t  contentLength  )

static

Detect text encoding by Byte Order Mark Multibyte encodings (UTF-16/32) always ends with explicit endianness (LE/BE)

Parameters

content	pointer to text to analyze
contentLength	length of text

Returns

detected encoding or empty string if BOM not detected

GetBomEncoding() [2/2]

static std::string CCharsetDetection::GetBomEncoding ( const std::string &  content )

inlinestatic

Detect text encoding by Byte Order Mark Multibyte encodings (UTF-16/32) always ends with explicit endianness (LE/BE)

Parameters

content

the text to analyze

Returns

detected encoding or empty string if BOM not detected

---

The documentation for this class was generated from the following files:

• CharsetDetection.h
• CharsetDetection.cpp