Man page - unicode::utf_8(3)

Packages contains this manual

Package:  libcourier-unicode-dev
apt-get install libcourier-unicode-dev

Manuals in package:
• unicode_lb_end(3)
• unicode_derived_changes_when_casemapped_lookup(3)
• unicode_bidi_cleaned_size(3)
• unicode_locale_chset(3)
• unicode_emoji_extended_pictographic(3)
• unicode_convert_tou_tobuf(3)
• courier-unicode(7)
• unicode_derived_case_ignorable_lookup(3)
• unicode::ucs_2(3)
• unicode_convert_tobuf(3)
• unicode_tc(3)
• unicode_convert_tocbuf_init(3)
• unicode_default_chset(3)
• unicode::linebreakc_iter(3)
• unicode_emoji_lookup(3)
• unicode::iconvert::fromu(3)
• unicode_lb_next_cnt(3)
• unicode_convert(3)
• unicode_derived_xid_start_lookup(3)
• unicode_composition_deinit(3)
• unicode_emoji_modifier_base(3)
• unicode_bidi_calc_levels(3)
• unicode_canonical(3)
• unicode::ucs_4(3)
• unicode::bidi_logical_order(3)
• unicode::bidi_embed_paragraph_level(3)
• unicode::bidi_get_direction(3)
• unicode_isalnum(3)
• unicode_lb_set_opts(3)
• unicode_isspace(3)
• unicode_grapheme_break_init(3)
• unicode_lbc_end(3)
• unicode_general_category_lookup(3)
• unicode::iconvert::convert(3)
• unicode_script(3)
• unicode::bidi(3)
• unicode_derived_incb_lookup(3)
• unicode_ispunct(3)
• unicode_convert_fromutf8(3)
• unicode::bidi_reorder(3)
• unicode_decomposition_init(3)
• unicode_bidi_reorder(3)
• unicode_wbscan_init(3)
• unicode_convert_tocbuf_toutf8_init(3)
• unicode_wb_next(3)
• unicode_bidi_setbnl(3)
• unicode_bidi_direction(3)
• unicode::decompose_default_reallocate(3)
• unicode_html40ent_lookup(3)
• unicode_derived_changes_when_casefolded_lookup(3)
• unicode_emoji_modifier(3)
• unicode_convert_init(3)
• unicode_grapheme_break(3)
• unicode_bidi_logical_order(3)
• unicode_emoji_presentation(3)
• unicode_bidi_mirror(3)
• unicode::canonical(3)
• unicode::bidi_override(3)
• unicode_wb_next_cnt(3)
• unicode::linebreak_callback_save_buf(3)
• unicode_derived_cased_lookup(3)
• unicode::compose(3)
• unicode::wordbreak_callback_base(3)
• unicode::iso_8859_1(3)
• unicode_grapheme_break_deinit(3)
• unicode_derived_grapheme_base_lookup(3)
• unicode_derived_default_ignorable_code_point_lookup(3)
• unicode_derived_changes_when_titlecased_lookup(3)
• unicode_derived_lowercase_lookup(3)
• unicode_convert_deinit(3)
• unicode_bidi_combinings(3)
• unicode_derived_grapheme_extend_lookup(3)
• unicode::bidi_embed(3)
• unicode_uc(3)
• unicode_composition_apply(3)
• unicode_bidi_type(3)
• unicode_derived_uppercase_lookup(3)
• unicode_derived_id_start_lookup(3)
• unicode::tolower(3)
• unicode_derived_changes_when_lowercased_lookup(3)
• unicode::linebreak_callback_base(3)
• unicode_compose(3)
• unicode_grapheme_break_next(3)
• unicode_isupper(3)
• unicode_lbc_next_cnt(3)
• unicode::linebreak_iter(3)
• unicode_bidi(3)
• unicode_decompose_reallocate_size(3)
• unicode::toupper(3)
• unicode::linebreakc_callback_base(3)
• unicode::bidi_cleanup(3)
• unicode::iconvert::convert_tocase(3)
• unicode_composition_init(3)
• unicode_lbc_next(3)
• unicode_bidi_bracket_type(3)
• unicode_convert_fromu_init(3)
• unicode_category_lookup(3)
• unicode_ccc(3)
• unicode_emoji(3)
• unicode::iconvert::tou(3)
• unicode_bidi_needs_embed(3)
• unicode_derived_id_continue_lookup(3)
• unicode_convert_uc(3)
• unicode_emoji_component(3)
• unicode_u_ucs2_native(3)
• unicode::wordbreak(3)
• unicode_wbscan_end(3)
• unicode::compose_default_callback(3)
• unicode_bidi_calc(3)
• unicode_isalpha(3)
• unicode::decompose(3)
• unicode_convert_toutf8(3)
• unicode_line_break(3)
• unicode_derived_math_lookup(3)
• unicode_derived_core_properties(3)
• unicode_bidi_cleanup(3)
• unicode_derived_xid_continue_lookup(3)
• unicode_wbscan_next(3)
• unicode_islower(3)
• unicode_convert_tocase(3)
• unicode_word_break(3)
• unicode_convert_tou_init(3)
• unicode_derived_grapheme_link_lookup(3)
• unicode_bidi_embed_paragraph_level(3)
• unicode_bidi_calc_types(3)
• unicode_lc(3)
• unicode_wb_end(3)
• unicode_isdigit(3)
• unicode_isblank(3)
• unicode_derived_changes_when_uppercased_lookup(3)
• unicode::bidi_calc(3)
• unicode_decomposition_deinit(3)
• unicode::utf_8(3)
• unicode_decompose(3)
• unicode_bidi_embed(3)
• unicode_lb_next(3)
• unicode_u_ucs4_native(3)
• unicode::bidi_calc_types(3)
• unicode_isgraph(3)
• unicode_wb_init(3)
• unicode_convert_tocbuf_fromutf8_init(3)
• unicode::bidi_combinings(3)
• unicode_lbc_set_opts(3)
• unicode_lbc_init(3)
• unicode::bidi_needs_embed(3)
• unicode_convert_fromu_tobuf(3)
• unicode_lb_init(3)
Documentations in package:
• libcourier-unicode-dev

Manual

UNICODE::ICONVERT::C

NAME
SYNOPSIS
DESCRIPTION
SEE ALSO
AUTHOR

---

NAME

unicode::iconvert::convert, unicode::ucs_4, unicode::ucs_2, unicode::utf_8, unicode::iso_8859_1 - unicode character set conversion

SYNOPSIS

#include <courier-unicode.h>

extern const char unicode::ucs_4[];
extern const char unicode::ucs_2[];
extern const char unicode::utf_8[];
extern const char unicode::iso_8859_1[];

	std::string unicode::iconvert::convert(const std::string & text , const std::string & srccharset , const std::string & dstcharset );
	std::string unicode::iconvert::convert(const std::string & text , const std::string & srccharset , const std::string & dstcharset , bool & errflag );
	std::string unicode::iconvert::convert( const std::vector<char32_t> & text , const std::string & dstcharset );
	std::string unicode::iconvert::convert( const std::vector<char32_t> & text , const std::string & dstcharset , bool & errflag );
	bool unicode::iconvert::convert(const std::string & text , const std::string & charset , std::vector<char32_t> & text );

DESCRIPTION

The overloaded unicode::convert::convert () functions convert:

• A text string between two different character sets, returning the new string.

• A vector of unicode characters (not null-terminated) to a character string in a supported character set.

• Initialize a vector of unicode characters, passed by reference, by converting a text string in a given character set to unicode.

These functions use iconv (3), and can use any character set that's supported by iconv (3). Use unicode::ucs_2 and unicode::ucs_4 to specify the 16 and the 32 bit unicode octet in native byte order. Use unicode::utf_8 and unicode::iso_8859_1 to specify these two standard character sets. The overloaded versions that pass a reference to a bool set the flag to true if some characters could not be converted. The overloaded version that initializes a unicode vector returns the bool flag, instead.

SEE ALSO

courier-unicode (7), unicode::convert::convert_tocase (3), unicode_convert (3), iconv (3).

AUTHOR

Sam Varshavchik

Author

---