TextEncoder

Inheritance:

Methods of TextEncoder:

Constants in TextEncoder:

TextEncoder
TextEncoder::TextEncoder(void);

Description:

appendText
void TextEncoder::append_text(string const &text);

Description: Appends the indicates string to the end of the stored text.

appendUnicodeChar
void TextEncoder::append_unicode_char(int character);

Description: Appends a single character to the end of the stored text. This may be a wide character, up to 16 bits in Unicode.

appendWtext
void TextEncoder::append_wtext(basic_string< wchar_t > const &text);

Description: Appends the indicates string to the end of the stored wide-character text.

clearText
void TextEncoder::clear_text(void);

Description: Removes the text from the TextEncoder.

decodeText
basic_string< wchar_t > TextEncoder::decode_text(string const &text) const;

Description: Returns the given wstring decoded to a single-byte string, via the current encoding system.
Description: Returns the given wstring decoded to a single-byte string, via the given encoding system.

encodeWchar
static string TextEncoder::encode_wchar(wchar_t ch, TextEncoder::Encoding encoding);

Description: Encodes a single wide char into a one-, two-, or three-byte string, according to the given encoding system.

encodeWtext
string TextEncoder::encode_wtext(basic_string< wchar_t > const &wtext) const;

Description: Encodes a wide-text string into a single-char string, according to the current encoding.
Description: Encodes a wide-text string into a single-char string, according to the given encoding.

getClassType
static TypeHandle TextEncoder::get_class_type(void);

Undocumented function.

getDefaultEncoding
static TextEncoder::Encoding TextEncoder::get_default_encoding(void);

Description: Specifies the default encoding to be used for all subsequently created TextEncoder objects. See set_encoding().

getEncodedChar
string TextEncoder::get_encoded_char(int index) const;

Description: Returns the nth char of the stored text, as a one-, two-, or three-byte encoded string.

getEncoding
TextEncoder::Encoding TextEncoder::get_encoding(void) const;

Description: Returns the encoding by which the string set via set_text() is to be interpreted. See set_encoding().

getNumChars
int TextEncoder::get_num_chars(void) const;

Description: Returns the number of characters in the stored text. This is a count of wide characters, after the string has been decoded according to set_encoding().

getText
string TextEncoder::get_text(void) const;

Description: Returns the current text, as encoded via the current encoding system.
Description: Returns the current text, as encoded via the indicated encoding system.

getTextAsAscii
string TextEncoder::get_text_as_ascii(void) const;

Description: Returns the text associated with the node, converted as nearly as possible to a fully-ASCII representation. This means replacing accented letters with their unaccented ASCII equivalents.
It is possible that some characters in the string cannot be converted to ASCII. (The string may involve symbols like the copyright symbol, for instance, or it might involve letters in some other alphabet such as Greek or Cyrillic, or even Latin letters like thorn or eth that are not part of the ASCII character set.) In this case, as much of the string as possible will be converted to ASCII, and the nonconvertible characters will remain encoded in the encoding specified by set_encoding().

getUnicodeChar
int TextEncoder::get_unicode_char(int index) const;

Description: Returns the Unicode value of the nth character in the stored text. This may be a wide character (greater than 255), after the string has been decoded according to set_encoding().

getWtext
basic_string< wchar_t > const &TextEncoder::get_wtext(void) const;

Direct support for wide-character strings. Now publishable with the new wstring support in interrogate.
Description: Returns the text associated with the TextEncoder, as a wide-character string.

getWtextAsAscii
basic_string< wchar_t > TextEncoder::get_wtext_as_ascii(void) const;

Description: Returns the text associated with the node, converted as nearly as possible to a fully-ASCII representation. This means replacing accented letters with their unaccented ASCII equivalents.
It is possible that some characters in the string cannot be converted to ASCII. (The string may involve symbols like the copyright symbol, for instance, or it might involve letters in some other alphabet such as Greek or Cyrillic, or even Latin letters like thorn or eth that are not part of the ASCII character set.) In this case, as much of the string as possible will be converted to ASCII, and the nonconvertible characters will remain in their original form.

hasText
bool TextEncoder::has_text(void) const;

Description:

isWtext
bool TextEncoder::is_wtext(void) const;

Description: Returns true if any of the characters in the string returned by get_wtext() are out of the range of an ASCII character (and, therefore, get_wtext() should be called in preference to get_text()).

lower
static string TextEncoder::lower(string const &source);

Description: Converts the string to lowercase, assuming the string is encoded in the default encoding.
Description: Converts the string to lowercase, assuming the string is encoded in the indicated encoding.

makeLower
void TextEncoder::make_lower(void);

Description: Adjusts the text stored within the encoder to all lowercase letters (preserving accent marks correctly).

makeUpper
void TextEncoder::make_upper(void);

Description: Adjusts the text stored within the encoder to all uppercase letters (preserving accent marks correctly).

reencodeText
static string TextEncoder::reencode_text(string const &text, TextEncoder::Encoding from, TextEncoder::Encoding to);

Description: Given the indicated text string, which is assumed to be encoded via the encoding "from", decodes it and then reencodes it into the encoding "to", and returns the newly encoded string. This does not change or affect any properties on the TextEncoder itself.

setDefaultEncoding
static void TextEncoder::set_default_encoding(TextEncoder::Encoding encoding);

Description: Specifies the default encoding to be used for all subsequently created TextEncoder objects. See set_encoding().

setEncoding
void TextEncoder::set_encoding(TextEncoder::Encoding encoding);

Description: Specifies how the string set via set_text() is to be interpreted. The default, E_iso8859, means a standard string with one-byte characters (i.e. ASCII). Other encodings are possible to take advantage of character sets with more than 256 characters.
This affects only future calls to set_text(); it does not change text that was set previously.

setText
void TextEncoder::set_text(string const &text);

Description: Changes the text that is stored in the encoder. The text should be encoded according to the method indicated by set_encoding(). Subsequent calls to get_text() will return this same string, while get_wtext() will return the decoded version of the string.
Description: The two-parameter version of set_text() accepts an explicit encoding; the text is immediately decoded and stored as a wide-character string. Subsequent calls to get_text() will return the same text re-encoded using whichever encoding is specified by set_encoding().

setUnicodeChar
void TextEncoder::set_unicode_char(int index, int character);

Description: Sets the Unicode value of the nth character in the stored text. This may be a wide character (greater than 255), after the string has been decoded according to set_encoding().

setWtext
void TextEncoder::set_wtext(basic_string< wchar_t > const &wtext);

Direct support for wide-character strings. Now publishable with the new wstring support in interrogate.
Description: Changes the text that is stored in the encoder. Subsequent calls to get_wtext() will return this same string, while get_text() will return the encoded version of the string.

unicodeIsalpha
static bool TextEncoder::unicode_isalpha(int character);

Description: Returns true if the indicated character is an alphabetic letter, false otherwise. This is akin to ctype's isalpha(), extended to Unicode.

unicodeIsdigit
static bool TextEncoder::unicode_isdigit(int character);

Description: Returns true if the indicated character is a numeric digit, false otherwise. This is akin to ctype's isdigit(), extended to Unicode.

unicodeIslower
static bool TextEncoder::unicode_islower(int character);

Description: Returns true if the indicated character is a lowercase letter, false otherwise. This is akin to ctype's islower(), extended to Unicode.

unicodeIspunct
static bool TextEncoder::unicode_ispunct(int character);

Description: Returns true if the indicated character is a punctuation mark, false otherwise. This is akin to ctype's ispunct(), extended to Unicode.

unicodeIsspace
static bool TextEncoder::unicode_isspace(int character);

Description: Returns true if the indicated character is a whitespace letter, false otherwise. This is akin to ctype's isspace(), extended to Unicode.

unicodeIsupper
static bool TextEncoder::unicode_isupper(int character);

Description: Returns true if the indicated character is an uppercase letter, false otherwise. This is akin to ctype's isupper(), extended to Unicode.

unicodeTolower
static int TextEncoder::unicode_tolower(int character);

Description: Returns the uppercase equivalent of the given Unicode character. This is akin to ctype's tolower(), extended to Unicode.

unicodeToupper
static int TextEncoder::unicode_toupper(int character);

Description: Returns the uppercase equivalent of the given Unicode character. This is akin to ctype's toupper(), extended to Unicode.

upper
static string TextEncoder::upper(string const &source);

Description: Converts the string to uppercase, assuming the string is encoded in the default encoding.
Description: Converts the string to uppercase, assuming the string is encoded in the indicated encoding.