libglibmm-2.4-dev 2.39.93-0ubuntu1 / usr / include / glibmm-2.4 / glibmm / unicode.h

// -*- c++ -*-
// Generated by gmmproc 2.39.93 -- DO NOT MODIFY!
#ifndef _GLIBMM_UNICODE_H
#define _GLIBMM_UNICODE_H


/* Copyright (C) 2002 The gtkmm Development Team
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free
 * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */


#include <glib.h>

// Not used, but we want to get rid of possible <ctype.h> macros.
#include <cctype>

#undef isalnum
#undef isalpha
#undef iscntrl
#undef isdigit
#undef isgraph
#undef islower
#undef isprint
#undef ispunct
#undef isspace
#undef isupper
#undef isxdigit
#undef istitle
#undef isdefined
#undef iswide
#undef toupper
#undef tolower
#undef totitle


namespace Glib
{

/** @addtogroup glibmmEnums glibmm Enums and Flags */

/** 
 *  @var UnicodeType UNICODE_CONTROL
 *  General category "Other, Control" (Cc).
 * 
 *  @var UnicodeType UNICODE_FORMAT
 *  General category "Other, Format" (Cf).
 * 
 *  @var UnicodeType UNICODE_UNASSIGNED
 *  General category "Other, Not Assigned" (Cn).
 * 
 *  @var UnicodeType UNICODE_PRIVATE_USE
 *  General category "Other, Private Use" (Co).
 * 
 *  @var UnicodeType UNICODE_SURROGATE
 *  General category "Other, Surrogate" (Cs).
 * 
 *  @var UnicodeType UNICODE_LOWERCASE_LETTER
 *  General category "Letter, Lowercase" (Ll).
 * 
 *  @var UnicodeType UNICODE_MODIFIER_LETTER
 *  General category "Letter, Modifier" (Lm).
 * 
 *  @var UnicodeType UNICODE_OTHER_LETTER
 *  General category "Letter, Other" (Lo).
 * 
 *  @var UnicodeType UNICODE_TITLECASE_LETTER
 *  General category "Letter, Titlecase" (Lt).
 * 
 *  @var UnicodeType UNICODE_UPPERCASE_LETTER
 *  General category "Letter, Uppercase" (Lu).
 * 
 *  @var UnicodeType UNICODE_SPACING_MARK
 *  General category "Mark, Spacing" (Mc).
 * 
 *  @var UnicodeType UNICODE_ENCLOSING_MARK
 *  General category "Mark, Enclosing" (Me).
 * 
 *  @var UnicodeType UNICODE_NON_SPACING_MARK
 *  General category "Mark, Nonspacing" (Mn).
 * 
 *  @var UnicodeType UNICODE_DECIMAL_NUMBER
 *  General category "Number, Decimal Digit" (Nd).
 * 
 *  @var UnicodeType UNICODE_LETTER_NUMBER
 *  General category "Number, Letter" (Nl).
 * 
 *  @var UnicodeType UNICODE_OTHER_NUMBER
 *  General category "Number, Other" (No).
 * 
 *  @var UnicodeType UNICODE_CONNECT_PUNCTUATION
 *  General category "Punctuation, Connector" (Pc).
 * 
 *  @var UnicodeType UNICODE_DASH_PUNCTUATION
 *  General category "Punctuation, Dash" (Pd).
 * 
 *  @var UnicodeType UNICODE_CLOSE_PUNCTUATION
 *  General category "Punctuation, Close" (Pe).
 * 
 *  @var UnicodeType UNICODE_FINAL_PUNCTUATION
 *  General category "Punctuation, Final quote" (Pf).
 * 
 *  @var UnicodeType UNICODE_INITIAL_PUNCTUATION
 *  General category "Punctuation, Initial quote" (Pi).
 * 
 *  @var UnicodeType UNICODE_OTHER_PUNCTUATION
 *  General category "Punctuation, Other" (Po).
 * 
 *  @var UnicodeType UNICODE_OPEN_PUNCTUATION
 *  General category "Punctuation, Open" (Ps).
 * 
 *  @var UnicodeType UNICODE_CURRENCY_SYMBOL
 *  General category "Symbol, Currency" (Sc).
 * 
 *  @var UnicodeType UNICODE_MODIFIER_SYMBOL
 *  General category "Symbol, Modifier" (Sk).
 * 
 *  @var UnicodeType UNICODE_MATH_SYMBOL
 *  General category "Symbol, Math" (Sm).
 * 
 *  @var UnicodeType UNICODE_OTHER_SYMBOL
 *  General category "Symbol, Other" (So).
 * 
 *  @var UnicodeType UNICODE_LINE_SEPARATOR
 *  General category "Separator, Line" (Zl).
 * 
 *  @var UnicodeType UNICODE_PARAGRAPH_SEPARATOR
 *  General category "Separator, Paragraph" (Zp).
 * 
 *  @var UnicodeType UNICODE_SPACE_SEPARATOR
 *  General category "Separator, Space" (Zs).
 * 
 *  @enum UnicodeType
 * 
 * These are the possible character classifications from the
 * Unicode specification.
 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html.
 * @ingroup glibmmEnums
 */
enum UnicodeType
{
  UNICODE_CONTROL,
  UNICODE_FORMAT,
  UNICODE_UNASSIGNED,
  UNICODE_PRIVATE_USE,
  UNICODE_SURROGATE,
  UNICODE_LOWERCASE_LETTER,
  UNICODE_MODIFIER_LETTER,
  UNICODE_OTHER_LETTER,
  UNICODE_TITLECASE_LETTER,
  UNICODE_UPPERCASE_LETTER,
  UNICODE_SPACING_MARK,
  UNICODE_ENCLOSING_MARK,
  UNICODE_NON_SPACING_MARK,
  UNICODE_DECIMAL_NUMBER,
  UNICODE_LETTER_NUMBER,
  UNICODE_OTHER_NUMBER,
  UNICODE_CONNECT_PUNCTUATION,
  UNICODE_DASH_PUNCTUATION,
  UNICODE_CLOSE_PUNCTUATION,
  UNICODE_FINAL_PUNCTUATION,
  UNICODE_INITIAL_PUNCTUATION,
  UNICODE_OTHER_PUNCTUATION,
  UNICODE_OPEN_PUNCTUATION,
  UNICODE_CURRENCY_SYMBOL,
  UNICODE_MODIFIER_SYMBOL,
  UNICODE_MATH_SYMBOL,
  UNICODE_OTHER_SYMBOL,
  UNICODE_LINE_SEPARATOR,
  UNICODE_PARAGRAPH_SEPARATOR,
  UNICODE_SPACE_SEPARATOR
};


/** 
 *  @var UnicodeBreakType UNICODE_BREAK_MANDATORY
 *  Mandatory Break (BK).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_CARRIAGE_RETURN
 *  Carriage Return (CR).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_LINE_FEED
 *  Line Feed (LF).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_COMBINING_MARK
 *  Attached Characters and Combining Marks (CM).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_SURROGATE
 *  Surrogates (SG).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_ZERO_WIDTH_SPACE
 *  Zero Width Space (ZW).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_INSEPARABLE
 *  Inseparable (IN).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_NON_BREAKING_GLUE
 *  Non-breaking ("Glue") (GL).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_CONTINGENT
 *  Contingent Break Opportunity (CB).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_SPACE
 *  Space (SP).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_AFTER
 *  Break Opportunity After (BA).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_BEFORE
 *  Break Opportunity Before (BB).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_BEFORE_AND_AFTER
 *  Break Opportunity Before and After (B2).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HYPHEN
 *  Hyphen (HY).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_NON_STARTER
 *  Nonstarter (NS).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_OPEN_PUNCTUATION
 *  Opening Punctuation (OP).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_CLOSE_PUNCTUATION
 *  Closing Punctuation (CL).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_QUOTATION
 *  Ambiguous Quotation (QU).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_EXCLAMATION
 *  Exclamation/Interrogation (EX).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_IDEOGRAPHIC
 *  Ideographic (ID).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_NUMERIC
 *  Numeric (NU).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_INFIX_SEPARATOR
 *  Infix Separator (Numeric) (IS).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_SYMBOL
 *  Symbols Allowing Break After (SY).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_ALPHABETIC
 *  Ordinary Alphabetic and Symbol Characters (AL).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_PREFIX
 *  Prefix (Numeric) (PR).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_POSTFIX
 *  Postfix (Numeric) (PO).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_COMPLEX_CONTEXT
 *  Complex Content Dependent (South East Asian) (SA).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_AMBIGUOUS
 *  Ambiguous (Alphabetic or Ideographic) (AI).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_UNKNOWN
 *  Unknown (XX).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_NEXT_LINE
 *  Next Line (NL).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_WORD_JOINER
 *  Word Joiner (WJ).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HANGUL_L_JAMO
 *  Hangul L Jamo (JL).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HANGUL_V_JAMO
 *  Hangul V Jamo (JV).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HANGUL_T_JAMO
 *  Hangul T Jamo (JT).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HANGUL_LV_SYLLABLE
 *  Hangul LV Syllable (H2).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HANGUL_LVT_SYLLABLE
 *  Hangul LVT Syllable (H3).
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_CLOSE_PARANTHESIS
 *  Closing Parenthesis (CP). Since 2.28.
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER
 *  Conditional Japanese Starter (CJ). @newin{2,32}
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_HEBREW_LETTER
 *  Hebrew Letter (HL). @newin{2,32}
 * 
 *  @var UnicodeBreakType UNICODE_BREAK_REGIONAL_INDICATOR
 *  Regional Indicator (RI). @newin{2,36}
 * 
 *  @enum UnicodeBreakType
 * 
 * These are the possible line break classifications.
 * 
 * Since new unicode versions may add new types here, applications should be ready 
 * to handle unknown values. They may be regarded as UNICODE_BREAK_UNKNOWN.
 * 
 * See http://www.unicode.org/unicode/reports/tr14/.
 * @ingroup glibmmEnums
 */
enum UnicodeBreakType
{
  UNICODE_BREAK_MANDATORY,
  UNICODE_BREAK_CARRIAGE_RETURN,
  UNICODE_BREAK_LINE_FEED,
  UNICODE_BREAK_COMBINING_MARK,
  UNICODE_BREAK_SURROGATE,
  UNICODE_BREAK_ZERO_WIDTH_SPACE,
  UNICODE_BREAK_INSEPARABLE,
  UNICODE_BREAK_NON_BREAKING_GLUE,
  UNICODE_BREAK_CONTINGENT,
  UNICODE_BREAK_SPACE,
  UNICODE_BREAK_AFTER,
  UNICODE_BREAK_BEFORE,
  UNICODE_BREAK_BEFORE_AND_AFTER,
  UNICODE_BREAK_HYPHEN,
  UNICODE_BREAK_NON_STARTER,
  UNICODE_BREAK_OPEN_PUNCTUATION,
  UNICODE_BREAK_CLOSE_PUNCTUATION,
  UNICODE_BREAK_QUOTATION,
  UNICODE_BREAK_EXCLAMATION,
  UNICODE_BREAK_IDEOGRAPHIC,
  UNICODE_BREAK_NUMERIC,
  UNICODE_BREAK_INFIX_SEPARATOR,
  UNICODE_BREAK_SYMBOL,
  UNICODE_BREAK_ALPHABETIC,
  UNICODE_BREAK_PREFIX,
  UNICODE_BREAK_POSTFIX,
  UNICODE_BREAK_COMPLEX_CONTEXT,
  UNICODE_BREAK_AMBIGUOUS,
  UNICODE_BREAK_UNKNOWN,
  UNICODE_BREAK_NEXT_LINE,
  UNICODE_BREAK_WORD_JOINER,
  UNICODE_BREAK_HANGUL_L_JAMO,
  UNICODE_BREAK_HANGUL_V_JAMO,
  UNICODE_BREAK_HANGUL_T_JAMO,
  UNICODE_BREAK_HANGUL_LV_SYLLABLE,
  UNICODE_BREAK_HANGUL_LVT_SYLLABLE,
  UNICODE_BREAK_CLOSE_PARANTHESIS,
  UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER,
  UNICODE_BREAK_HEBREW_LETTER,
  UNICODE_BREAK_REGIONAL_INDICATOR
};


/** 
 * 
 * @ingroup glibmmEnums
 * @par Bitwise operators:
 * <tt>%AsciiType operator|(AsciiType, AsciiType)</tt><br>
 * <tt>%AsciiType operator&(AsciiType, AsciiType)</tt><br>
 * <tt>%AsciiType operator^(AsciiType, AsciiType)</tt><br>
 * <tt>%AsciiType operator~(AsciiType)</tt><br>
 * <tt>%AsciiType& operator|=(AsciiType&, AsciiType)</tt><br>
 * <tt>%AsciiType& operator&=(AsciiType&, AsciiType)</tt><br>
 * <tt>%AsciiType& operator^=(AsciiType&, AsciiType)</tt><br>
 */
enum AsciiType
{
  ASCII_ALNUM = 1 << 0,
  ASCII_ALPHA = 1 << 1,
  ASCII_CNTRL = 1 << 2,
  ASCII_DIGIT = 1 << 3,
  ASCII_GRAPH = 1 << 4,
  ASCII_LOWER = 1 << 5,
  ASCII_PRINT = 1 << 6,
  ASCII_PUNCT = 1 << 7,
  ASCII_SPACE = 1 << 8,
  ASCII_UPPER = 1 << 9,
  ASCII_XDIGIT = 1 << 10
};

/** @ingroup glibmmEnums */
inline AsciiType operator|(AsciiType lhs, AsciiType rhs)
  { return static_cast<AsciiType>(static_cast<unsigned>(lhs) | static_cast<unsigned>(rhs)); }

/** @ingroup glibmmEnums */
inline AsciiType operator&(AsciiType lhs, AsciiType rhs)
  { return static_cast<AsciiType>(static_cast<unsigned>(lhs) & static_cast<unsigned>(rhs)); }

/** @ingroup glibmmEnums */
inline AsciiType operator^(AsciiType lhs, AsciiType rhs)
  { return static_cast<AsciiType>(static_cast<unsigned>(lhs) ^ static_cast<unsigned>(rhs)); }

/** @ingroup glibmmEnums */
inline AsciiType operator~(AsciiType flags)
  { return static_cast<AsciiType>(~static_cast<unsigned>(flags)); }

/** @ingroup glibmmEnums */
inline AsciiType& operator|=(AsciiType& lhs, AsciiType rhs)
  { return (lhs = static_cast<AsciiType>(static_cast<unsigned>(lhs) | static_cast<unsigned>(rhs))); }

/** @ingroup glibmmEnums */
inline AsciiType& operator&=(AsciiType& lhs, AsciiType rhs)
  { return (lhs = static_cast<AsciiType>(static_cast<unsigned>(lhs) & static_cast<unsigned>(rhs))); }

/** @ingroup glibmmEnums */
inline AsciiType& operator^=(AsciiType& lhs, AsciiType rhs)
  { return (lhs = static_cast<AsciiType>(static_cast<unsigned>(lhs) ^ static_cast<unsigned>(rhs))); }


/** 
 *  @var NormalizeMode NORMALIZE_DEFAULT
 *  standardize differences that do not affect thetext content, such as the above-mentioned accent representation.
 * 
 *  @var NormalizeMode NORMALIZE_NFD
 *  another name for Normalize::DEFAULT.
 * 
 *  @var NormalizeMode NORMALIZE_DEFAULT_COMPOSE
 *  like Normalize::DEFAULT, but withcomposed forms rather than a maximally decomposed form.
 * 
 *  @var NormalizeMode NORMALIZE_NFC
 *  another name for Normalize::DEFAULT_COMPOSE.
 * 
 *  @var NormalizeMode NORMALIZE_ALL
 *  beyond Normalize::DEFAULT also standardize the"compatibility" characters in Unicode, such as SUPERSCRIPT THREEto the standard forms (in this case DIGIT THREE). Formattinginformation may be lost but for most text operations suchcharacters should be considered the same.
 * 
 *  @var NormalizeMode NORMALIZE_NFKD
 *  another name for Normalize::ALL.
 * 
 *  @var NormalizeMode NORMALIZE_ALL_COMPOSE
 *  like Normalize::ALL, but with composedforms rather than a maximally decomposed form.
 * 
 *  @var NormalizeMode NORMALIZE_NFKC
 *  another name for Normalize::ALL_COMPOSE.
 * 
 *  @enum NormalizeMode
 * 
 * Defines how a Unicode string is transformed in a canonical
 * form, standardizing such issues as whether a character with
 * an accent is represented as a base character and combining
 * accent or as a single precomposed character. Unicode strings
 * should generally be normalized before comparing them.
 * @ingroup glibmmEnums
 */
enum NormalizeMode
{
  NORMALIZE_DEFAULT,
  NORMALIZE_NFD = NORMALIZE_DEFAULT,
  NORMALIZE_DEFAULT_COMPOSE,
  NORMALIZE_NFC = NORMALIZE_DEFAULT_COMPOSE,
  NORMALIZE_ALL,
  NORMALIZE_NFKD = NORMALIZE_ALL,
  NORMALIZE_ALL_COMPOSE,
  NORMALIZE_NFKC = NORMALIZE_ALL_COMPOSE
};


/** @defgroup Unicode Unicode Manipulation
 * Functions operating on Unicode characters and UTF-8 strings.
 * @{
 */

namespace Unicode
{

inline bool validate(gunichar uc)
  { return (g_unichar_validate(uc) != 0); }
inline bool isalnum(gunichar uc)
  { return (g_unichar_isalnum(uc) != 0); }
inline bool isalpha(gunichar uc)
  { return (g_unichar_isalpha(uc) != 0); }
inline bool iscntrl(gunichar uc)
  { return (g_unichar_iscntrl(uc) != 0); }
inline bool isdigit(gunichar uc)
  { return (g_unichar_isdigit(uc) != 0); }
inline bool isgraph(gunichar uc)
  { return (g_unichar_isgraph(uc) != 0); }
inline bool islower(gunichar uc)
  { return (g_unichar_islower(uc) != 0); }
inline bool isprint(gunichar uc)
  { return (g_unichar_isprint(uc) != 0); }
inline bool ispunct(gunichar uc)
  { return (g_unichar_ispunct(uc) != 0); }
inline bool isspace(gunichar uc)
  { return (g_unichar_isspace(uc) != 0); }
inline bool isupper(gunichar uc)
  { return (g_unichar_isupper(uc) != 0); }
inline bool isxdigit(gunichar uc)
  { return (g_unichar_isxdigit(uc) != 0); }
inline bool istitle(gunichar uc)
  { return (g_unichar_istitle(uc) != 0); }
inline bool isdefined(gunichar uc)
  { return (g_unichar_isdefined(uc) != 0); }
inline bool iswide(gunichar uc)
  { return (g_unichar_iswide(uc) != 0); }

inline gunichar toupper(gunichar uc)
  { return g_unichar_toupper(uc); }
inline gunichar tolower(gunichar uc)
  { return g_unichar_tolower(uc); }
inline gunichar totitle(gunichar uc)
  { return g_unichar_totitle(uc); }

inline int digit_value(gunichar uc)
  { return g_unichar_digit_value(uc); }
inline int xdigit_value(gunichar uc)
  { return g_unichar_xdigit_value(uc); }

inline Glib::UnicodeType type(gunichar uc)
  { return static_cast<Glib::UnicodeType>(static_cast<int>(g_unichar_type(uc))); }

inline Glib::UnicodeBreakType break_type(gunichar uc)
  { return static_cast<Glib::UnicodeBreakType>(static_cast<int>(g_unichar_break_type(uc))); }

} // namespace Unicode


namespace Ascii
{

inline bool isalnum(char c)
  { return g_ascii_isalnum(c); }
inline bool isalpha(char c)
  { return g_ascii_isalpha(c); }
inline bool iscntrl(char c)
  { return g_ascii_iscntrl(c); }
inline bool isdigit(char c)
  { return g_ascii_isdigit(c); }
inline bool isgraph(char c)
  { return g_ascii_isgraph(c); }
inline bool islower(char c)
  { return g_ascii_islower(c); }
inline bool isprint(char c)
  { return g_ascii_isprint(c); }
inline bool ispunct(char c)
  { return g_ascii_ispunct(c); }
inline bool isspace(char c)
  { return g_ascii_isspace(c); }
inline bool isupper(char c)
  { return g_ascii_isupper(c); }
inline bool isxdigit(char c)
  { return g_ascii_isxdigit(c); }

inline char tolower(char c)
  { return g_ascii_tolower(c); }
inline char toupper(char c)
  { return g_ascii_toupper(c); }

inline int digit_value(char c)
  { return g_ascii_digit_value(c); }
inline int xdigit_value(char c)
  { return g_ascii_xdigit_value(c); }

} // namespace Ascii


/** @} group Unicode */

} // namespace Glib


#endif /* _GLIBMM_UNICODE_H */