Unicode Manipulation

Unicode Manipulation — functions operating on Unicode characters and UTF-8 strings

Synopsis


#include <glib.h>

typedef             gunichar;
typedef             gunichar2;

gboolean            g_unichar_validate                  (gunichar ch);
gboolean            g_unichar_isalnum                   (gunichar c);
gboolean            g_unichar_isalpha                   (gunichar c);
gboolean            g_unichar_iscntrl                   (gunichar c);
gboolean            g_unichar_isdefined                 (gunichar c);
gboolean            g_unichar_isdigit                   (gunichar c);
gboolean            g_unichar_isgraph                   (gunichar c);
gboolean            g_unichar_islower                   (gunichar c);
gboolean            g_unichar_ismark                    (gunichar c);
gboolean            g_unichar_isprint                   (gunichar c);
gboolean            g_unichar_ispunct                   (gunichar c);
gboolean            g_unichar_isspace                   (gunichar c);
gboolean            g_unichar_istitle                   (gunichar c);
gboolean            g_unichar_isupper                   (gunichar c);
gboolean            g_unichar_isxdigit                  (gunichar c);
gboolean            g_unichar_iswide                    (gunichar c);
gboolean            g_unichar_iswide_cjk                (gunichar c);
gboolean            g_unichar_iszerowidth               (gunichar c);
gunichar            g_unichar_toupper                   (gunichar c);
gunichar            g_unichar_tolower                   (gunichar c);
gunichar            g_unichar_totitle                   (gunichar c);
gint                g_unichar_digit_value               (gunichar c);
gint                g_unichar_xdigit_value              (gunichar c);
enum                GUnicodeType;
GUnicodeType        g_unichar_type                      (gunichar c);
enum                GUnicodeBreakType;
GUnicodeBreakType   g_unichar_break_type                (gunichar c);
gint                g_unichar_combining_class           (gunichar uc);
void                g_unicode_canonical_ordering        (gunichar *string,
                                                         gsize len);
gunichar *          g_unicode_canonical_decomposition   (gunichar ch,
                                                         gsize *result_len);
gboolean            g_unichar_get_mirror_char           (gunichar ch,
                                                         gunichar *mirrored_ch);
enum                GUnicodeScript;
GUnicodeScript      g_unichar_get_script                (gunichar ch);

#define             g_utf8_next_char                    (p)
gunichar            g_utf8_get_char                     (const gchar *p);
gunichar            g_utf8_get_char_validated           (const gchar *p,
                                                         gssize max_len);
gchar*              g_utf8_offset_to_pointer            (const gchar *str,
                                                         glong offset);
glong               g_utf8_pointer_to_offset            (const gchar *str,
                                                         const gchar *pos);
gchar*              g_utf8_prev_char                    (const gchar *p);
gchar*              g_utf8_find_next_char               (const gchar *p,
                                                         const gchar *end);
gchar*              g_utf8_find_prev_char               (const gchar *str,
                                                         const gchar *p);
glong               g_utf8_strlen                       (const gchar *p,
                                                         gssize max);
gchar*              g_utf8_strncpy                      (gchar *dest,
                                                         const gchar *src,
                                                         gsize n);
gchar*              g_utf8_strchr                       (const gchar *p,
                                                         gssize len,
                                                         gunichar c);
gchar*              g_utf8_strrchr                      (const gchar *p,
                                                         gssize len,
                                                         gunichar c);
gchar*              g_utf8_strreverse                   (const gchar *str,
                                                         gssize len);
gboolean            g_utf8_validate                     (const gchar *str,
                                                         gssize max_len,
                                                         const gchar **end);

gchar *             g_utf8_strup                        (const gchar *str,
                                                         gssize len);
gchar *             g_utf8_strdown                      (const gchar *str,
                                                         gssize len);
gchar *             g_utf8_casefold                     (const gchar *str,
                                                         gssize len);
gchar *             g_utf8_normalize                    (const gchar *str,
                                                         gssize len,
                                                         GNormalizeMode mode);
enum                GNormalizeMode;
gint                g_utf8_collate                      (const gchar *str1,
                                                         const gchar *str2);
gchar *             g_utf8_collate_key                  (const gchar *str,
                                                         gssize len);
gchar *             g_utf8_collate_key_for_filename     (const gchar *str,
                                                         gssize len);

gunichar2 *         g_utf8_to_utf16                     (const gchar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);
gunichar *          g_utf8_to_ucs4                      (const gchar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);
gunichar *          g_utf8_to_ucs4_fast                 (const gchar *str,
                                                         glong len,
                                                         glong *items_written);
gunichar *          g_utf16_to_ucs4                     (const gunichar2 *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);
gchar*              g_utf16_to_utf8                     (const gunichar2 *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);
gunichar2 *         g_ucs4_to_utf16                     (const gunichar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);
gchar*              g_ucs4_to_utf8                      (const gunichar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);
gint                g_unichar_to_utf8                   (gunichar c,
                                                         gchar *outbuf);

Description

This section describes a number of functions for dealing with Unicode characters and strings. There are analogues of the traditional ctype.h character classification and case conversion functions, UTF-8 analogues of some string utility functions, functions to perform normalization, case conversion and collation on UTF-8 strings and finally functions to convert between the UTF-8, UTF-16 and UCS-4 encodings of Unicode.

The implementations of the Unicode functions in GLib are based on the Unicode Character Data tables, which are available from www.unicode.org. GLib 2.8 supports Unicode 4.0, GLib 2.10 supports Unicode 4.1, GLib 2.12 supports Unicode 5.0, GLib 2.16.3 supports Unicode 5.1.

Details

gunichar

typedef guint32 gunichar;

A type which can hold any UTF-32 or UCS-4 character code, also known as a Unicode code point.

To print/scan values of this type to/from text you need to convert to/from UTF-8, using g_utf32_to_utf8()/g_utf8_to_utf32().

To print/scan values of this type as integer, use G_GINT32_MODIFIER and/or G_GUINT32_FORMAT.

The notation to express a Unicode code point in running text is as a hexadecimal number with four to six digits and uppercase letters, prefixed by the string "U+". Leading zeros are omitted, unless the code point would have fewer than four hexadecimal digits. For example, "U+0041 LATIN CAPITAL LETTER A". To print a code point in the U+-notation, use the format string "U+04"G_GINT32_FORMAT"X". To scan, use the format string "U+06"G_GINT32_FORMAT"X".

gunichar c;
sscanf ("U+0041", "U+%06"G_GINT32_FORMAT"X", &c)
g_print ("Read U+%04"G_GINT32_FORMAT"X", c);


gunichar2

typedef guint16 gunichar2;

A type which can hold any UTF-16 code point[3].

To print/scan values of this type to/from text you need to convert to/from UTF-8, using g_utf16_to_utf8()/g_utf8_to_utf16().

To print/scan values of this type as integer, use G_GINT16_MODIFIER and/or G_GUINT16_FORMAT.


g_unichar_validate ()

gboolean            g_unichar_validate                  (gunichar ch);

Checks whether ch is a valid Unicode character. Some possible integer values of ch will not be valid. 0 is considered a valid character, though it's normally a string terminator.

ch :

a Unicode character

Returns :

TRUE if ch is a valid Unicode character

g_unichar_isalnum ()

gboolean            g_unichar_isalnum                   (gunichar c);

Determines whether a character is alphanumeric. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is an alphanumeric character

g_unichar_isalpha ()

gboolean            g_unichar_isalpha                   (gunichar c);

Determines whether a character is alphabetic (i.e. a letter). Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is an alphabetic character

g_unichar_iscntrl ()

gboolean            g_unichar_iscntrl                   (gunichar c);

Determines whether a character is a control character. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is a control character

g_unichar_isdefined ()

gboolean            g_unichar_isdefined                 (gunichar c);

Determines if a given character is assigned in the Unicode standard.

c :

a Unicode character

Returns :

TRUE if the character has an assigned value

g_unichar_isdigit ()

gboolean            g_unichar_isdigit                   (gunichar c);

Determines whether a character is numeric (i.e. a digit). This covers ASCII 0-9 and also digits in other languages/scripts. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is a digit

g_unichar_isgraph ()

gboolean            g_unichar_isgraph                   (gunichar c);

Determines whether a character is printable and not a space (returns FALSE for control characters, format characters, and spaces). g_unichar_isprint() is similar, but returns TRUE for spaces. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is printable unless it's a space

g_unichar_islower ()

gboolean            g_unichar_islower                   (gunichar c);

Determines whether a character is a lowercase letter. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is a lowercase letter

g_unichar_ismark ()

gboolean            g_unichar_ismark                    (gunichar c);

Determines whether a character is a mark (non-spacing mark, combining mark, or enclosing mark in Unicode speak). Given some UTF-8 text, obtain a character value with g_utf8_get_char().

Note: in most cases where isalpha characters are allowed, ismark characters should be allowed to as they are essential for writing most European languages as well as many non-Latin scripts.

c :

a Unicode character

Returns :

TRUE if c is a mark character

Since 2.14


g_unichar_isprint ()

gboolean            g_unichar_isprint                   (gunichar c);

Determines whether a character is printable. Unlike g_unichar_isgraph(), returns TRUE for spaces. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is printable

g_unichar_ispunct ()

gboolean            g_unichar_ispunct                   (gunichar c);

Determines whether a character is punctuation or a symbol. Given some UTF-8 text, obtain a character value with g_utf8_get_char().

c :

a Unicode character

Returns :

TRUE if c is a punctuation or symbol character

g_unichar_isspace ()

gboolean            g_unichar_isspace                   (gunichar c);

Determines whether a character is a space, tab, or line separator (newline, carriage return, etc.). Given some UTF-8 text, obtain a character value with g_utf8_get_char().

(Note: don't use this to do word breaking; you have to use Pango or equivalent to get word breaking right, the algorithm is fairly complex.)

c :

a Unicode character

Returns :

TRUE if c is a space character

g_unichar_istitle ()

gboolean            g_unichar_istitle                   (gunichar c);

Determines if a character is titlecase. Some characters in Unicode which are composites, such as the DZ digraph have three case variants instead of just two. The titlecase form is used at the beginning of a word where only the first letter is capitalized. The titlecase form of the DZ digraph is U+01F2 LATIN CAPITAL LETTTER D WITH SMALL LETTER Z.

c :

a Unicode character

Returns :

TRUE if the character is titlecase

g_unichar_isupper ()

gboolean            g_unichar_isupper                   (gunichar c);

Determines if a character is uppercase.

c :

a Unicode character

Returns :

TRUE if c is an uppercase character

g_unichar_isxdigit ()

gboolean            g_unichar_isxdigit                  (gunichar c);

Determines if a character is a hexidecimal digit.

c :

a Unicode character.

Returns :

TRUE if the character is a hexadecimal digit

g_unichar_iswide ()

gboolean            g_unichar_iswide                    (gunichar c);

Determines if a character is typically rendered in a double-width cell.

c :

a Unicode character

Returns :

TRUE if the character is wide

g_unichar_iswide_cjk ()

gboolean            g_unichar_iswide_cjk                (gunichar c);

Determines if a character is typically rendered in a double-width cell under legacy East Asian locales. If a character is wide according to g_unichar_iswide(), then it is also reported wide with this function, but the converse is not necessarily true. See the Unicode Standard Annex #11 for details.

If a character passes the g_unichar_iswide() test then it will also pass this test, but not the other way around. Note that some characters may pas both this test and g_unichar_iszerowidth().

c :

a Unicode character

Returns :

TRUE if the character is wide in legacy East Asian locales

Since 2.12


g_unichar_iszerowidth ()

gboolean            g_unichar_iszerowidth               (gunichar c);

Determines if a given character typically takes zero width when rendered. The return value is TRUE for all non-spacing and enclosing marks (e.g., combining accents), format characters, zero-width space, but not U+00AD SOFT HYPHEN.

A typical use of this function is with one of g_unichar_iswide() or g_unichar_iswide_cjk() to determine the number of cells a string occupies when displayed on a grid display (terminals). However, note that not all terminals support zero-width rendering of zero-width marks.

c :

a Unicode character

Returns :

TRUE if the character has zero width

Since 2.14


g_unichar_toupper ()

gunichar            g_unichar_toupper                   (gunichar c);

Converts a character to uppercase.

c :

a Unicode character

Returns :

the result of converting c to uppercase. If c is not an lowercase or titlecase character, or has no upper case equivalent c is returned unchanged.

g_unichar_tolower ()

gunichar            g_unichar_tolower                   (gunichar c);

Converts a character to lower case.

c :

a Unicode character.

Returns :

the result of converting c to lower case. If c is not an upperlower or titlecase character, or has no lowercase equivalent c is returned unchanged.

g_unichar_totitle ()

gunichar            g_unichar_totitle                   (gunichar c);

Converts a character to the titlecase.

c :

a Unicode character

Returns :

the result of converting c to titlecase. If c is not an uppercase or lowercase character, c is returned unchanged.

g_unichar_digit_value ()

gint                g_unichar_digit_value               (gunichar c);

Determines the numeric value of a character as a decimal digit.

c :

a Unicode character

Returns :

If c is a decimal digit (according to g_unichar_isdigit()), its numeric value. Otherwise, -1.

g_unichar_xdigit_value ()

gint                g_unichar_xdigit_value              (gunichar c);

Determines the numeric value of a character as a hexidecimal digit.

c :

a Unicode character

Returns :

If c is a hex digit (according to g_unichar_isxdigit()), its numeric value. Otherwise, -1.

enum GUnicodeType

typedef enum
{
  G_UNICODE_CONTROL,
  G_UNICODE_FORMAT,
  G_UNICODE_UNASSIGNED,
  G_UNICODE_PRIVATE_USE,
  G_UNICODE_SURROGATE,
  G_UNICODE_LOWERCASE_LETTER,
  G_UNICODE_MODIFIER_LETTER,
  G_UNICODE_OTHER_LETTER,
  G_UNICODE_TITLECASE_LETTER,
  G_UNICODE_UPPERCASE_LETTER,
  G_UNICODE_COMBINING_MARK,
  G_UNICODE_ENCLOSING_MARK,
  G_UNICODE_NON_SPACING_MARK,
  G_UNICODE_DECIMAL_NUMBER,
  G_UNICODE_LETTER_NUMBER,
  G_UNICODE_OTHER_NUMBER,
  G_UNICODE_CONNECT_PUNCTUATION,
  G_UNICODE_DASH_PUNCTUATION,
  G_UNICODE_CLOSE_PUNCTUATION,
  G_UNICODE_FINAL_PUNCTUATION,
  G_UNICODE_INITIAL_PUNCTUATION,
  G_UNICODE_OTHER_PUNCTUATION,
  G_UNICODE_OPEN_PUNCTUATION,
  G_UNICODE_CURRENCY_SYMBOL,
  G_UNICODE_MODIFIER_SYMBOL,
  G_UNICODE_MATH_SYMBOL,
  G_UNICODE_OTHER_SYMBOL,
  G_UNICODE_LINE_SEPARATOR,
  G_UNICODE_PARAGRAPH_SEPARATOR,
  G_UNICODE_SPACE_SEPARATOR
} GUnicodeType;

These are the possible character classifications from the Unicode specification. See http://www.unicode.org/Public/UNIDATA/UnicodeData.html.

G_UNICODE_CONTROL

General category "Other, Control" (Cc)

G_UNICODE_FORMAT

General category "Other, Format" (Cf)

G_UNICODE_UNASSIGNED

General category "Other, Not Assigned" (Cn)

G_UNICODE_PRIVATE_USE

General category "Other, Private Use" (Co)

G_UNICODE_SURROGATE

General category "Other, Surrogate" (Cs)

G_UNICODE_LOWERCASE_LETTER

General category "Letter, Lowercase" (Ll)

G_UNICODE_MODIFIER_LETTER

General category "Letter, Modifier" (Lm)

G_UNICODE_OTHER_LETTER

General category "Letter, Other" (Lo)

G_UNICODE_TITLECASE_LETTER

General category "Letter, Titlecase" (Lt)

G_UNICODE_UPPERCASE_LETTER

General category "Letter, Uppercase" (Lu)

G_UNICODE_COMBINING_MARK

General category "Mark, Spacing Combining" (Mc)

G_UNICODE_ENCLOSING_MARK

General category "Mark, Enclosing" (Me)

G_UNICODE_NON_SPACING_MARK

General category "Mark, Nonspacing" (Mn)

G_UNICODE_DECIMAL_NUMBER

General category "Number, Decimal Digit" (Nd)

G_UNICODE_LETTER_NUMBER

General category "Number, Letter" (Nl)

G_UNICODE_OTHER_NUMBER

General category "Number, Other" (No)

G_UNICODE_CONNECT_PUNCTUATION

General category "Punctuation, Connector" (Pc)

G_UNICODE_DASH_PUNCTUATION

General category "Punctuation, Dash" (Pd)

G_UNICODE_CLOSE_PUNCTUATION

General category "Punctuation, Close" (Pe)

G_UNICODE_FINAL_PUNCTUATION

General category "Punctuation, Final quote" (Pf)

G_UNICODE_INITIAL_PUNCTUATION

General category "Punctuation, Initial quote" (Pi)

G_UNICODE_OTHER_PUNCTUATION

General category "Punctuation, Other" (Po)

G_UNICODE_OPEN_PUNCTUATION

General category "Punctuation, Open" (Ps)

G_UNICODE_CURRENCY_SYMBOL

General category "Symbol, Currency" (Sc)

G_UNICODE_MODIFIER_SYMBOL

General category "Symbol, Modifier" (Sk)

G_UNICODE_MATH_SYMBOL

General category "Symbol, Math" (Sm)

G_UNICODE_OTHER_SYMBOL

General category "Symbol, Other" (So)

G_UNICODE_LINE_SEPARATOR

General category "Separator, Line" (Zl)

G_UNICODE_PARAGRAPH_SEPARATOR

General category "Separator, Paragraph" (Zp)

G_UNICODE_SPACE_SEPARATOR

General category "Separator, Space" (Zs)

g_unichar_type ()

GUnicodeType        g_unichar_type                      (gunichar c);

Classifies a Unicode character by type.

c :

a Unicode character

Returns :

the type of the character.

enum GUnicodeBreakType

typedef enum
{
  G_UNICODE_BREAK_MANDATORY,
  G_UNICODE_BREAK_CARRIAGE_RETURN,
  G_UNICODE_BREAK_LINE_FEED,
  G_UNICODE_BREAK_COMBINING_MARK,
  G_UNICODE_BREAK_SURROGATE,
  G_UNICODE_BREAK_ZERO_WIDTH_SPACE,
  G_UNICODE_BREAK_INSEPARABLE,
  G_UNICODE_BREAK_NON_BREAKING_GLUE,
  G_UNICODE_BREAK_CONTINGENT,
  G_UNICODE_BREAK_SPACE,
  G_UNICODE_BREAK_AFTER,
  G_UNICODE_BREAK_BEFORE,
  G_UNICODE_BREAK_BEFORE_AND_AFTER,
  G_UNICODE_BREAK_HYPHEN,
  G_UNICODE_BREAK_NON_STARTER,
  G_UNICODE_BREAK_OPEN_PUNCTUATION,
  G_UNICODE_BREAK_CLOSE_PUNCTUATION,
  G_UNICODE_BREAK_QUOTATION,
  G_UNICODE_BREAK_EXCLAMATION,
  G_UNICODE_BREAK_IDEOGRAPHIC,
  G_UNICODE_BREAK_NUMERIC,
  G_UNICODE_BREAK_INFIX_SEPARATOR,
  G_UNICODE_BREAK_SYMBOL,
  G_UNICODE_BREAK_ALPHABETIC,
  G_UNICODE_BREAK_PREFIX,
  G_UNICODE_BREAK_POSTFIX,
  G_UNICODE_BREAK_COMPLEX_CONTEXT,
  G_UNICODE_BREAK_AMBIGUOUS,
  G_UNICODE_BREAK_UNKNOWN,
  G_UNICODE_BREAK_NEXT_LINE,
  G_UNICODE_BREAK_WORD_JOINER,
  G_UNICODE_BREAK_HANGUL_L_JAMO,
  G_UNICODE_BREAK_HANGUL_V_JAMO,
  G_UNICODE_BREAK_HANGUL_T_JAMO,
  G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,
  G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE
} GUnicodeBreakType;

These are the possible line break classifications. The five Hangul types were added in Unicode 4.1, so, has been introduced in GLib 2.10. Note that new types may be added in the future. Applications should be ready to handle unknown values. They may be regarded as G_UNICODE_BREAK_UNKNOWN. See http://www.unicode.org/unicode/reports/tr14/.

G_UNICODE_BREAK_MANDATORY

Mandatory Break (BK)

G_UNICODE_BREAK_CARRIAGE_RETURN

Carriage Return (CR)

G_UNICODE_BREAK_LINE_FEED

Line Feed (LF)

G_UNICODE_BREAK_COMBINING_MARK

Attached Characters and Combining Marks (CM)

G_UNICODE_BREAK_SURROGATE

Surrogates (SG)

G_UNICODE_BREAK_ZERO_WIDTH_SPACE

Zero Width Space (ZW)

G_UNICODE_BREAK_INSEPARABLE

Inseparable (IN)

G_UNICODE_BREAK_NON_BREAKING_GLUE

Non-breaking ("Glue") (GL)

G_UNICODE_BREAK_CONTINGENT

Contingent Break Opportunity (CB)

G_UNICODE_BREAK_SPACE

Space (SP)

G_UNICODE_BREAK_AFTER

Break Opportunity After (BA)

G_UNICODE_BREAK_BEFORE

Break Opportunity Before (BB)

G_UNICODE_BREAK_BEFORE_AND_AFTER

Break Opportunity Before and After (B2)

G_UNICODE_BREAK_HYPHEN

Hyphen (HY)

G_UNICODE_BREAK_NON_STARTER

Nonstarter (NS)

G_UNICODE_BREAK_OPEN_PUNCTUATION

Opening Punctuation (OP)

G_UNICODE_BREAK_CLOSE_PUNCTUATION

Closing Punctuation (CL)

G_UNICODE_BREAK_QUOTATION

Ambiguous Quotation (QU)

G_UNICODE_BREAK_EXCLAMATION

Exclamation/Interrogation (EX)

G_UNICODE_BREAK_IDEOGRAPHIC

Ideographic (ID)

G_UNICODE_BREAK_NUMERIC

Numeric (NU)

G_UNICODE_BREAK_INFIX_SEPARATOR

Infix Separator (Numeric) (IS)

G_UNICODE_BREAK_SYMBOL

Symbols Allowing Break After (SY)

G_UNICODE_BREAK_ALPHABETIC

Ordinary Alphabetic and Symbol Characters (AL)

G_UNICODE_BREAK_PREFIX

Prefix (Numeric) (PR)

G_UNICODE_BREAK_POSTFIX

Postfix (Numeric) (PO)

G_UNICODE_BREAK_COMPLEX_CONTEXT

Complex Content Dependent (South East Asian) (SA)

G_UNICODE_BREAK_AMBIGUOUS

Ambiguous (Alphabetic or Ideographic) (AI)

G_UNICODE_BREAK_UNKNOWN

Unknown (XX)

G_UNICODE_BREAK_NEXT_LINE

Next Line (NL)

G_UNICODE_BREAK_WORD_JOINER

Word Joiner (WJ)

G_UNICODE_BREAK_HANGUL_L_JAMO

Hangul L Jamo (JL)

G_UNICODE_BREAK_HANGUL_V_JAMO

Hangul V Jamo (JV)

G_UNICODE_BREAK_HANGUL_T_JAMO

Hangul T Jamo (JT)

G_UNICODE_BREAK_HANGUL_LV_SYLLABLE

Hangul LV Syllable (H2)

G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE

Hangul LVT Syllable (H3)

g_unichar_break_type ()

GUnicodeBreakType   g_unichar_break_type                (gunichar c);

Determines the break type of c. c should be a Unicode character (to derive a character from UTF-8 encoded text, use g_utf8_get_char()). The break type is used to find word and line breaks ("text boundaries"), Pango implements the Unicode boundary resolution algorithms and normally you would use a function such as pango_break() instead of caring about break types yourself.

c :

a Unicode character

Returns :

the break type of c

g_unichar_combining_class ()

gint                g_unichar_combining_class           (gunichar uc);

Determines the canonical combining class of a Unicode character.

uc :

a Unicode character

Returns :

the combining class of the character

Since 2.14


g_unicode_canonical_ordering ()

void                g_unicode_canonical_ordering        (gunichar *string,
                                                         gsize len);

Computes the canonical ordering of a string in-place. This rearranges decomposed characters in the string according to their combining classes. See the Unicode manual for more information.

string :

a UCS-4 encoded string.

len :

the maximum length of string to use.

g_unicode_canonical_decomposition ()

gunichar *          g_unicode_canonical_decomposition   (gunichar ch,
                                                         gsize *result_len);

Computes the canonical decomposition of a Unicode character.

ch :

a Unicode character.

result_len :

location to store the length of the return value.

Returns :

a newly allocated string of Unicode characters. result_len is set to the resulting length of the string.

g_unichar_get_mirror_char ()

gboolean            g_unichar_get_mirror_char           (gunichar ch,
                                                         gunichar *mirrored_ch);

In Unicode, some characters are mirrored. This means that their images are mirrored horizontally in text that is laid out from right to left. For instance, "(" would become its mirror image, ")", in right-to-left text.

If ch has the Unicode mirrored property and there is another unicode character that typically has a glyph that is the mirror image of ch's glyph and mirrored_ch is set, it puts that character in the address pointed to by mirrored_ch. Otherwise the original character is put.

ch :

a Unicode character

mirrored_ch :

location to store the mirrored character

Returns :

TRUE if ch has a mirrored character, FALSE otherwise

Since 2.4


enum GUnicodeScript

typedef enum 
{                         /* ISO 15924 code */
  G_UNICODE_SCRIPT_INVALID_CODE = -1,
  G_UNICODE_SCRIPT_COMMON       = 0,   /* Zyyy */
  G_UNICODE_SCRIPT_INHERITED,          /* Qaai */
  G_UNICODE_SCRIPT_ARABIC,             /* Arab */
  G_UNICODE_SCRIPT_ARMENIAN,           /* Armn */
  G_UNICODE_SCRIPT_BENGALI,            /* Beng */
  G_UNICODE_SCRIPT_BOPOMOFO,           /* Bopo */
  G_UNICODE_SCRIPT_CHEROKEE,           /* Cher */
  G_UNICODE_SCRIPT_COPTIC,             /* Qaac */
  G_UNICODE_SCRIPT_CYRILLIC,           /* Cyrl (Cyrs) */
  G_UNICODE_SCRIPT_DESERET,            /* Dsrt */
  G_UNICODE_SCRIPT_DEVANAGARI,         /* Deva */
  G_UNICODE_SCRIPT_ETHIOPIC,           /* Ethi */
  G_UNICODE_SCRIPT_GEORGIAN,           /* Geor (Geon, Geoa) */
  G_UNICODE_SCRIPT_GOTHIC,             /* Goth */
  G_UNICODE_SCRIPT_GREEK,              /* Grek */
  G_UNICODE_SCRIPT_GUJARATI,           /* Gujr */
  G_UNICODE_SCRIPT_GURMUKHI,           /* Guru */
  G_UNICODE_SCRIPT_HAN,                /* Hani */
  G_UNICODE_SCRIPT_HANGUL,             /* Hang */
  G_UNICODE_SCRIPT_HEBREW,             /* Hebr */
  G_UNICODE_SCRIPT_HIRAGANA,           /* Hira */
  G_UNICODE_SCRIPT_KANNADA,            /* Knda */
  G_UNICODE_SCRIPT_KATAKANA,           /* Kana */
  G_UNICODE_SCRIPT_KHMER,              /* Khmr */
  G_UNICODE_SCRIPT_LAO,                /* Laoo */
  G_UNICODE_SCRIPT_LATIN,              /* Latn (Latf, Latg) */
  G_UNICODE_SCRIPT_MALAYALAM,          /* Mlym */
  G_UNICODE_SCRIPT_MONGOLIAN,          /* Mong */
  G_UNICODE_SCRIPT_MYANMAR,            /* Mymr */
  G_UNICODE_SCRIPT_OGHAM,              /* Ogam */
  G_UNICODE_SCRIPT_OLD_ITALIC,         /* Ital */
  G_UNICODE_SCRIPT_ORIYA,              /* Orya */
  G_UNICODE_SCRIPT_RUNIC,              /* Runr */
  G_UNICODE_SCRIPT_SINHALA,            /* Sinh */
  G_UNICODE_SCRIPT_SYRIAC,             /* Syrc (Syrj, Syrn, Syre) */
  G_UNICODE_SCRIPT_TAMIL,              /* Taml */
  G_UNICODE_SCRIPT_TELUGU,             /* Telu */
  G_UNICODE_SCRIPT_THAANA,             /* Thaa */
  G_UNICODE_SCRIPT_THAI,               /* Thai */
  G_UNICODE_SCRIPT_TIBETAN,            /* Tibt */
  G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, /* Cans */
  G_UNICODE_SCRIPT_YI,                 /* Yiii */
  G_UNICODE_SCRIPT_TAGALOG,            /* Tglg */
  G_UNICODE_SCRIPT_HANUNOO,            /* Hano */
  G_UNICODE_SCRIPT_BUHID,              /* Buhd */
  G_UNICODE_SCRIPT_TAGBANWA,           /* Tagb */

  /* Unicode-4.0 additions */
  G_UNICODE_SCRIPT_BRAILLE,            /* Brai */
  G_UNICODE_SCRIPT_CYPRIOT,            /* Cprt */
  G_UNICODE_SCRIPT_LIMBU,              /* Limb */
  G_UNICODE_SCRIPT_OSMANYA,            /* Osma */
  G_UNICODE_SCRIPT_SHAVIAN,            /* Shaw */
  G_UNICODE_SCRIPT_LINEAR_B,           /* Linb */
  G_UNICODE_SCRIPT_TAI_LE,             /* Tale */
  G_UNICODE_SCRIPT_UGARITIC,           /* Ugar */
      
  /* Unicode-4.1 additions */
  G_UNICODE_SCRIPT_NEW_TAI_LUE,        /* Talu */
  G_UNICODE_SCRIPT_BUGINESE,           /* Bugi */
  G_UNICODE_SCRIPT_GLAGOLITIC,         /* Glag */
  G_UNICODE_SCRIPT_TIFINAGH,           /* Tfng */
  G_UNICODE_SCRIPT_SYLOTI_NAGRI,       /* Sylo */
  G_UNICODE_SCRIPT_OLD_PERSIAN,        /* Xpeo */
  G_UNICODE_SCRIPT_KHAROSHTHI,         /* Khar */

  /* Unicode-5.0 additions */
  G_UNICODE_SCRIPT_UNKNOWN,            /* Zzzz */
  G_UNICODE_SCRIPT_BALINESE,           /* Bali */
  G_UNICODE_SCRIPT_CUNEIFORM,          /* Xsux */
  G_UNICODE_SCRIPT_PHOENICIAN,         /* Phnx */
  G_UNICODE_SCRIPT_PHAGS_PA,           /* Phag */
  G_UNICODE_SCRIPT_NKO,                /* Nkoo */

  /* Unicode-5.1 additions */
  G_UNICODE_SCRIPT_KAYAH_LI,           /* Kali */
  G_UNICODE_SCRIPT_LEPCHA,             /* Lepc */
  G_UNICODE_SCRIPT_REJANG,             /* Rjng */
  G_UNICODE_SCRIPT_SUNDANESE,          /* Sund */
  G_UNICODE_SCRIPT_SAURASHTRA,         /* Saur */
  G_UNICODE_SCRIPT_CHAM,               /* Cham */
  G_UNICODE_SCRIPT_OL_CHIKI,           /* Olck */
  G_UNICODE_SCRIPT_VAI,                /* Vaii */
  G_UNICODE_SCRIPT_CARIAN,             /* Cari */
  G_UNICODE_SCRIPT_LYCIAN,             /* Lyci */
  G_UNICODE_SCRIPT_LYDIAN              /* Lydi */
} GUnicodeScript;

The GUnicodeScript enumeration identifies different writing systems. The values correspond to the names as defined in the Unicode standard. The enumeration has been added in GLib 2.14, and is interchangeable with PangoScript. Note that new types may be added in the future. Applications should be ready to handle unknown values. See Unicode Standard Annex #24: Script names.

G_UNICODE_SCRIPT_INVALID_CODE

a value never returned from g_unichar_get_script()

G_UNICODE_SCRIPT_COMMON

a character used by multiple different scripts

G_UNICODE_SCRIPT_INHERITED

a mark glyph that takes its script from the base glyph to which it is attached

G_UNICODE_SCRIPT_ARABIC

Arabic

G_UNICODE_SCRIPT_ARMENIAN

Armenian

G_UNICODE_SCRIPT_BENGALI

Bengali

G_UNICODE_SCRIPT_BOPOMOFO

Bopomofo

G_UNICODE_SCRIPT_CHEROKEE

Cherokee

G_UNICODE_SCRIPT_COPTIC

Coptic

G_UNICODE_SCRIPT_CYRILLIC

Cyrillic

G_UNICODE_SCRIPT_DESERET

Deseret

G_UNICODE_SCRIPT_DEVANAGARI

Devanagari

G_UNICODE_SCRIPT_ETHIOPIC

Ethiopic

G_UNICODE_SCRIPT_GEORGIAN

Georgian

G_UNICODE_SCRIPT_GOTHIC

Gothic

G_UNICODE_SCRIPT_GREEK

Greek

G_UNICODE_SCRIPT_GUJARATI

Gujarati

G_UNICODE_SCRIPT_GURMUKHI

Gurmukhi

G_UNICODE_SCRIPT_HAN

Han

G_UNICODE_SCRIPT_HANGUL

Hangul

G_UNICODE_SCRIPT_HEBREW

Hebrew

G_UNICODE_SCRIPT_HIRAGANA

Hiragana

G_UNICODE_SCRIPT_KANNADA

Kannada

G_UNICODE_SCRIPT_KATAKANA

Katakana

G_UNICODE_SCRIPT_KHMER

Khmer

G_UNICODE_SCRIPT_LAO

Lao

G_UNICODE_SCRIPT_LATIN

Latin

G_UNICODE_SCRIPT_MALAYALAM

Malayalam

G_UNICODE_SCRIPT_MONGOLIAN

Mongolian

G_UNICODE_SCRIPT_MYANMAR

Myanmar

G_UNICODE_SCRIPT_OGHAM

Ogham

G_UNICODE_SCRIPT_OLD_ITALIC

Old Italic

G_UNICODE_SCRIPT_ORIYA

Oriya

G_UNICODE_SCRIPT_RUNIC

Runic

G_UNICODE_SCRIPT_SINHALA

Sinhala

G_UNICODE_SCRIPT_SYRIAC

Syriac

G_UNICODE_SCRIPT_TAMIL

Tamil

G_UNICODE_SCRIPT_TELUGU

Telugu

G_UNICODE_SCRIPT_THAANA

Thaana

G_UNICODE_SCRIPT_THAI

Thai

G_UNICODE_SCRIPT_TIBETAN

Tibetan

G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL

Canadian Aboriginal

G_UNICODE_SCRIPT_YI

Yi

G_UNICODE_SCRIPT_TAGALOG

Tagalog

G_UNICODE_SCRIPT_HANUNOO

Hanunoo

G_UNICODE_SCRIPT_BUHID

Buhid

G_UNICODE_SCRIPT_TAGBANWA

Tagbanwa

G_UNICODE_SCRIPT_BRAILLE

Braille

G_UNICODE_SCRIPT_CYPRIOT

Cypriot

G_UNICODE_SCRIPT_LIMBU

Limbu

G_UNICODE_SCRIPT_OSMANYA

Osmanya

G_UNICODE_SCRIPT_SHAVIAN

Shavian

G_UNICODE_SCRIPT_LINEAR_B

Linear B

G_UNICODE_SCRIPT_TAI_LE

Tai Le

G_UNICODE_SCRIPT_UGARITIC

Ugaritic

G_UNICODE_SCRIPT_NEW_TAI_LUE

New Tai Lue

G_UNICODE_SCRIPT_BUGINESE

Buginese

G_UNICODE_SCRIPT_GLAGOLITIC

Glagolitic

G_UNICODE_SCRIPT_TIFINAGH

Tifinagh

G_UNICODE_SCRIPT_SYLOTI_NAGRI

Syloti Nagri

G_UNICODE_SCRIPT_OLD_PERSIAN

Old Persian

G_UNICODE_SCRIPT_KHAROSHTHI

Kharoshthi

G_UNICODE_SCRIPT_UNKNOWN

an unassigned code point

G_UNICODE_SCRIPT_BALINESE

Balinese

G_UNICODE_SCRIPT_CUNEIFORM

Cuneiform

G_UNICODE_SCRIPT_PHOENICIAN

Phoenician

G_UNICODE_SCRIPT_PHAGS_PA

Phags-pa

G_UNICODE_SCRIPT_NKO

N'Ko

G_UNICODE_SCRIPT_KAYAH_LI

Kayah Li. Since 2.16.3

G_UNICODE_SCRIPT_LEPCHA

Lepcha. Since 2.16.3

G_UNICODE_SCRIPT_REJANG

Rejang. Since 2.16.3

G_UNICODE_SCRIPT_SUNDANESE

Sundanese. Since 2.16.3

G_UNICODE_SCRIPT_SAURASHTRA

Saurashtra. Since 2.16.3

G_UNICODE_SCRIPT_CHAM

Cham. Since 2.16.3

G_UNICODE_SCRIPT_OL_CHIKI

Ol Chiki. Since 2.16.3

G_UNICODE_SCRIPT_VAI

Vai. Since 2.16.3

G_UNICODE_SCRIPT_CARIAN

Carian. Since 2.16.3

G_UNICODE_SCRIPT_LYCIAN

Lycian. Since 2.16.3

G_UNICODE_SCRIPT_LYDIAN

Lydian. Since 2.16.3

g_unichar_get_script ()

GUnicodeScript      g_unichar_get_script                (gunichar ch);

Looks up the GUnicodeScript for a particular character (as defined by Unicode Standard Annex 24). No check is made for ch being a valid Unicode character; if you pass in invalid character, the result is undefined.

This function is equivalent to pango_script_for_unichar() and the two are interchangeable.

ch :

a Unicode character

Returns :

the GUnicodeScript for the character.

Since 2.14


g_utf8_next_char()

#define             g_utf8_next_char(p)

Skips to the next character in a UTF-8 string. The string must be valid; this macro is as fast as possible, and has no error-checking. You would use this macro to iterate over a string character by character. The macro returns the start of the next UTF-8 character. Before using this macro, use g_utf8_validate() to validate strings that may contain invalid UTF-8.

p :

Pointer to the start of a valid UTF-8 character.

g_utf8_get_char ()

gunichar            g_utf8_get_char                     (const gchar *p);

Converts a sequence of bytes encoded as UTF-8 to a Unicode character. If p does not point to a valid UTF-8 encoded character, results are undefined. If you are not sure that the bytes are complete valid Unicode characters, you should use g_utf8_get_char_validated() instead.

p :

a pointer to Unicode character encoded as UTF-8

Returns :

the resulting character

g_utf8_get_char_validated ()

gunichar            g_utf8_get_char_validated           (const gchar *p,
                                                         gssize max_len);

Convert a sequence of bytes encoded as UTF-8 to a Unicode character. This function checks for incomplete characters, for invalid characters such as characters that are out of the range of Unicode, and for overlong encodings of valid characters.

p :

a pointer to Unicode character encoded as UTF-8

max_len :

the maximum number of bytes to read, or -1, for no maximum or if p is nul-terminated

Returns :

the resulting character. If p points to a partial sequence at the end of a string that could begin a valid character (or if max_len is zero), returns (gunichar)-2; otherwise, if p does not point to a valid UTF-8 encoded Unicode character, returns (gunichar)-1.

g_utf8_offset_to_pointer ()

gchar*              g_utf8_offset_to_pointer            (const gchar *str,
                                                         glong offset);

Converts from an integer character offset to a pointer to a position within the string.

Since 2.10, this function allows to pass a negative offset to step backwards. It is usually worth stepping backwards from the end instead of forwards if offset is in the last fourth of the string, since moving forward is about 3 times faster than moving backward.

Note

This function doesn't abort when reaching the end of str. Therefore you should be sure that offset is within string boundaries before calling that function. Call g_utf8_strlen() when unsure.

This limitation exists as this function is called frequently during text rendering and therefore has to be as fast as possible.

str :

a UTF-8 encoded string

offset :

a character offset within str

Returns :

the resulting pointer

g_utf8_pointer_to_offset ()

glong               g_utf8_pointer_to_offset            (const gchar *str,
                                                         const gchar *pos);

Converts from a pointer to position within a string to a integer character offset.

Since 2.10, this function allows pos to be before str, and returns a negative offset in this case.

str :

a UTF-8 encoded string

pos :

a pointer to a position within str

Returns :

the resulting character offset

g_utf8_prev_char ()

gchar*              g_utf8_prev_char                    (const gchar *p);

Finds the previous UTF-8 character in the string before p.

p does not have to be at the beginning of a UTF-8 character. No check is made to see if the character found is actually valid other than it starts with an appropriate byte. If p might be the first character of the string, you must use g_utf8_find_prev_char() instead.

p :

a pointer to a position within a UTF-8 encoded string

Returns :

a pointer to the found character.

g_utf8_find_next_char ()

gchar*              g_utf8_find_next_char               (const gchar *p,
                                                         const gchar *end);

Finds the start of the next UTF-8 character in the string after p.

p does not have to be at the beginning of a UTF-8 character. No check is made to see if the character found is actually valid other than it starts with an appropriate byte.

p :

a pointer to a position within a UTF-8 encoded string

end :

a pointer to the byte following the end of the string, or NULL to indicate that the string is nul-terminated.

Returns :

a pointer to the found character or NULL

g_utf8_find_prev_char ()

gchar*              g_utf8_find_prev_char               (const gchar *str,
                                                         const gchar *p);

Given a position p with a UTF-8 encoded string str, find the start of the previous UTF-8 character starting before p. Returns NULL if no UTF-8 characters are present in str before p.

p does not have to be at the beginning of a UTF-8 character. No check is made to see if the character found is actually valid other than it starts with an appropriate byte.

str :

pointer to the beginning of a UTF-8 encoded string

p :

pointer to some position within str

Returns :

a pointer to the found character or NULL.

g_utf8_strlen ()

glong               g_utf8_strlen                       (const gchar *p,
                                                         gssize max);

Returns the length of the string in characters.

p :

pointer to the start of a UTF-8 encoded string.

max :

the maximum number of bytes to examine. If max is less than 0, then the string is assumed to be nul-terminated. If max is 0, p will not be examined and may be NULL.

Returns :

the length of the string in characters

g_utf8_strncpy ()

gchar*              g_utf8_strncpy                      (gchar *dest,
                                                         const gchar *src,
                                                         gsize n);

Like the standard C strncpy() function, but copies a given number of characters instead of a given number of bytes. The src string must be valid UTF-8 encoded text. (Use g_utf8_validate() on all text before trying to use UTF-8 utility functions with it.)

dest :

buffer to fill with characters from src

src :

UTF-8 encoded string

n :

character count

Returns :

dest

g_utf8_strchr ()

gchar*              g_utf8_strchr                       (const gchar *p,
                                                         gssize len,
                                                         gunichar c);

Finds the leftmost occurrence of the given Unicode character in a UTF-8 encoded string, while limiting the search to len bytes. If len is -1, allow unbounded search.

p :

a nul-terminated UTF-8 encoded string

len :

the maximum length of p

c :

a Unicode character

Returns :

NULL if the string does not contain the character, otherwise, a pointer to the start of the leftmost occurrence of the character in the string.

g_utf8_strrchr ()

gchar*              g_utf8_strrchr                      (const gchar *p,
                                                         gssize len,
                                                         gunichar c);

Find the rightmost occurrence of the given Unicode character in a UTF-8 encoded string, while limiting the search to len bytes. If len is -1, allow unbounded search.

p :

a nul-terminated UTF-8 encoded string

len :

the maximum length of p

c :

a Unicode character

Returns :

NULL if the string does not contain the character, otherwise, a pointer to the start of the rightmost occurrence of the character in the string.

g_utf8_strreverse ()

gchar*              g_utf8_strreverse                   (const gchar *str,
                                                         gssize len);

Reverses a UTF-8 string. str must be valid UTF-8 encoded text. (Use g_utf8_validate() on all text before trying to use UTF-8 utility functions with it.)

This function is intended for programmatic uses of reversed strings. It pays no attention to decomposed characters, combining marks, byte order marks, directional indicators (LRM, LRO, etc) and similar characters which might need special handling when reversing a string for display purposes.

Note that unlike g_strreverse(), this function returns newly-allocated memory, which should be freed with g_free() when no longer needed.

str :

a UTF-8 encoded string

len :

the maximum length of str to use, in bytes. If len < 0, then the string is nul-terminated.

Returns :

a newly-allocated string which is the reverse of str.

Since 2.2


g_utf8_validate ()

gboolean            g_utf8_validate                     (const gchar *str,
                                                         gssize max_len,
                                                         const gchar **end);

Validates UTF-8 encoded text. str is the text to validate; if str is nul-terminated, then max_len can be -1, otherwise max_len should be the number of bytes to validate. If end is non-NULL, then the end of the valid range will be stored there (i.e. the start of the first invalid character if some bytes were invalid, or the end of the text being validated otherwise).

Note that g_utf8_validate() returns FALSE if max_len is positive and NUL is met before max_len bytes have been read.

Returns TRUE if all of str was valid. Many GLib and GTK+ routines require valid UTF-8 as input; so data read from a file or the network should be checked with g_utf8_validate() before doing anything else with it.

str :

a pointer to character data

max_len :

max bytes to validate, or -1 to go until NUL

end :

return location for end of valid data

Returns :

TRUE if the text was valid UTF-8

g_utf8_strup ()

gchar *             g_utf8_strup                        (const gchar *str,
                                                         gssize len);

Converts all Unicode characters in the string that have a case to uppercase. The exact manner that this is done depends on the current locale, and may result in the number of characters in the string increasing. (For instance, the German ess-zet will be changed to SS.)

str :

a UTF-8 encoded string

len :

length of str, in bytes, or -1 if str is nul-terminated.

Returns :

a newly allocated string, with all characters converted to uppercase.

g_utf8_strdown ()

gchar *             g_utf8_strdown                      (const gchar *str,
                                                         gssize len);

Converts all Unicode characters in the string that have a case to lowercase. The exact manner that this is done depends on the current locale, and may result in the number of characters in the string changing.

str :

a UTF-8 encoded string

len :

length of str, in bytes, or -1 if str is nul-terminated.

Returns :

a newly allocated string, with all characters converted to lowercase.

g_utf8_casefold ()

gchar *             g_utf8_casefold                     (const gchar *str,
                                                         gssize len);

Converts a string into a form that is independent of case. The result will not correspond to any particular case, but can be compared for equality or ordered with the results of calling g_utf8_casefold() on other strings.

Note that calling g_utf8_casefold() followed by g_utf8_collate() is only an approximation to the correct linguistic case insensitive ordering, though it is a fairly good one. Getting this exactly right would require a more sophisticated collation function that takes case sensitivity into account. GLib does not currently provide such a function.

str :

a UTF-8 encoded string

len :

length of str, in bytes, or -1 if str is nul-terminated.

Returns :

a newly allocated string, that is a case independent form of str.

g_utf8_normalize ()

gchar *             g_utf8_normalize                    (const gchar *str,
                                                         gssize len,
                                                         GNormalizeMode mode);

Converts a string into 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. The string has to be valid UTF-8, otherwise NULL is returned. You should generally call g_utf8_normalize() before comparing two Unicode strings.

The normalization mode G_NORMALIZE_DEFAULT only standardizes differences that do not affect the text content, such as the above-mentioned accent representation. G_NORMALIZE_ALL also standardizes the "compatibility" characters in Unicode, such as SUPERSCRIPT THREE to the standard forms (in this case DIGIT THREE). Formatting information may be lost but for most text operations such characters should be considered the same.

G_NORMALIZE_DEFAULT_COMPOSE and G_NORMALIZE_ALL_COMPOSE are like G_NORMALIZE_DEFAULT and G_NORMALIZE_ALL, but returned a result with composed forms rather than a maximally decomposed form. This is often useful if you intend to convert the string to a legacy encoding or pass it to a system with less capable Unicode handling.

str :

a UTF-8 encoded string.

len :

length of str, in bytes, or -1 if str is nul-terminated.

mode :

the type of normalization to perform.

Returns :

a newly allocated string, that is the normalized form of str, or NULL if str is not valid UTF-8.

enum GNormalizeMode

typedef enum {
  G_NORMALIZE_DEFAULT,
  G_NORMALIZE_NFD = G_NORMALIZE_DEFAULT,
  G_NORMALIZE_DEFAULT_COMPOSE,
  G_NORMALIZE_NFC = G_NORMALIZE_DEFAULT_COMPOSE,
  G_NORMALIZE_ALL,
  G_NORMALIZE_NFKD = G_NORMALIZE_ALL,
  G_NORMALIZE_ALL_COMPOSE,
  G_NORMALIZE_NFKC = G_NORMALIZE_ALL_COMPOSE
} GNormalizeMode;

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.

G_NORMALIZE_DEFAULT

standardize differences that do not affect the text content, such as the above-mentioned accent representation.

G_NORMALIZE_NFD

another name for G_NORMALIZE_DEFAULT.

G_NORMALIZE_DEFAULT_COMPOSE

like G_NORMALIZE_DEFAULT, but with composed forms rather than a maximally decomposed form.

G_NORMALIZE_NFC

another name for G_NORMALIZE_DEFAULT_COMPOSE.

G_NORMALIZE_ALL

beyond G_NORMALIZE_DEFAULT also standardize the "compatibility" characters in Unicode, such as SUPERSCRIPT THREE to the standard forms (in this case DIGIT THREE). Formatting information may be lost but for most text operations such characters should be considered the same.

G_NORMALIZE_NFKD

another name for G_NORMALIZE_ALL.

G_NORMALIZE_ALL_COMPOSE

like G_NORMALIZE_ALL, but with composed forms rather than a maximally decomposed form.

G_NORMALIZE_NFKC

another name for G_NORMALIZE_ALL_COMPOSE.

g_utf8_collate ()

gint                g_utf8_collate                      (const gchar *str1,
                                                         const gchar *str2);

Compares two strings for ordering using the linguistically correct rules for the current locale. When sorting a large number of strings, it will be significantly faster to obtain collation keys with g_utf8_collate_key() and compare the keys with strcmp() when sorting instead of sorting the original strings.

str1 :

a UTF-8 encoded string

str2 :

a UTF-8 encoded string

Returns :

< 0 if str1 compares before str2, 0 if they compare equal, > 0 if str1 compares after str2.

g_utf8_collate_key ()

gchar *             g_utf8_collate_key                  (const gchar *str,
                                                         gssize len);

Converts a string into a collation key that can be compared with other collation keys produced by the same function using strcmp().

The results of comparing the collation keys of two strings with strcmp() will always be the same as comparing the two original keys with g_utf8_collate().

Note that this function depends on the current locale.

str :

a UTF-8 encoded string.

len :

length of str, in bytes, or -1 if str is nul-terminated.

Returns :

a newly allocated string. This string should be freed with g_free() when you are done with it.

g_utf8_collate_key_for_filename ()

gchar *             g_utf8_collate_key_for_filename     (const gchar *str,
                                                         gssize len);

Converts a string into a collation key that can be compared with other collation keys produced by the same function using strcmp().

In order to sort filenames correctly, this function treats the dot '.' as a special case. Most dictionary orderings seem to consider it insignificant, thus producing the ordering "event.c" "eventgenerator.c" "event.h" instead of "event.c" "event.h" "eventgenerator.c". Also, we would like to treat numbers intelligently so that "file1" "file10" "file5" is sorted as "file1" "file5" "file10".

Note that this function depends on the current locale.

str :

a UTF-8 encoded string.

len :

length of str, in bytes, or -1 if str is nul-terminated.

Returns :

a newly allocated string. This string should be freed with g_free() when you are done with it.

Since 2.8


g_utf8_to_utf16 ()

gunichar2 *         g_utf8_to_utf16                     (const gchar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);

Convert a string from UTF-8 to UTF-16. A 0 character will be added to the result after the converted text.

str :

a UTF-8 encoded string

len :

the maximum length (number of characters) of str to use. If len < 0, then the string is nul-terminated.

items_read :

location to store number of bytes read, or NULL. If NULL, then G_CONVERT_ERROR_PARTIAL_INPUT will be returned in case str contains a trailing partial character. If an error occurs then the index of the invalid input is stored here.

items_written :

location to store number of gunichar2 written, or NULL. The value stored here does not include the trailing 0.

error :

location to store the error occuring, or NULL to ignore errors. Any of the errors in GConvertError other than G_CONVERT_ERROR_NO_CONVERSION may occur.

Returns :

a pointer to a newly allocated UTF-16 string. This value must be freed with g_free(). If an error occurs, NULL will be returned and error set.

g_utf8_to_ucs4 ()

gunichar *          g_utf8_to_ucs4                      (const gchar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);

Convert a string from UTF-8 to a 32-bit fixed width representation as UCS-4. A trailing 0 will be added to the string after the converted text.

str :

a UTF-8 encoded string

len :

the maximum length of str to use, in bytes. If len < 0, then the string is nul-terminated.

items_read :

location to store number of bytes read, or NULL. If NULL, then G_CONVERT_ERROR_PARTIAL_INPUT will be returned in case str contains a trailing partial character. If an error occurs then the index of the invalid input is stored here.

items_written :

location to store number of characters written or NULL. The value here stored does not include the trailing 0 character.

error :

location to store the error occuring, or NULL to ignore errors. Any of the errors in GConvertError other than G_CONVERT_ERROR_NO_CONVERSION may occur.

Returns :

a pointer to a newly allocated UCS-4 string. This value must be freed with g_free(). If an error occurs, NULL will be returned and error set.

g_utf8_to_ucs4_fast ()

gunichar *          g_utf8_to_ucs4_fast                 (const gchar *str,
                                                         glong len,
                                                         glong *items_written);

Convert a string from UTF-8 to a 32-bit fixed width representation as UCS-4, assuming valid UTF-8 input. This function is roughly twice as fast as g_utf8_to_ucs4() but does no error checking on the input.

str :

a UTF-8 encoded string

len :

the maximum length of str to use, in bytes. If len < 0, then the string is nul-terminated.

items_written :

location to store the number of characters in the result, or NULL.

Returns :

a pointer to a newly allocated UCS-4 string. This value must be freed with g_free().

g_utf16_to_ucs4 ()

gunichar *          g_utf16_to_ucs4                     (const gunichar2 *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);

Convert a string from UTF-16 to UCS-4. The result will be nul-terminated.

str :

a UTF-16 encoded string

len :

the maximum length (number of gunichar2) of str to use. If len < 0, then the string is nul-terminated.

items_read :

location to store number of words read, or NULL. If NULL, then G_CONVERT_ERROR_PARTIAL_INPUT will be returned in case str contains a trailing partial character. If an error occurs then the index of the invalid input is stored here.

items_written :

location to store number of characters written, or NULL. The value stored here does not include the trailing 0 character.

error :

location to store the error occuring, or NULL to ignore errors. Any of the errors in GConvertError other than G_CONVERT_ERROR_NO_CONVERSION may occur.

Returns :

a pointer to a newly allocated UCS-4 string. This value must be freed with g_free(). If an error occurs, NULL will be returned and error set.

g_utf16_to_utf8 ()

gchar*              g_utf16_to_utf8                     (const gunichar2 *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);

Convert a string from UTF-16 to UTF-8. The result will be terminated with a 0 byte.

Note that the input is expected to be already in native endianness, an initial byte-order-mark character is not handled specially. g_convert() can be used to convert a byte buffer of UTF-16 data of ambiguous endianess.

str :

a UTF-16 encoded string

len :

the maximum length (number of gunichar2) of str to use. If len < 0, then the string is nul-terminated.

items_read :

location to store number of words read, or NULL. If NULL, then G_CONVERT_ERROR_PARTIAL_INPUT will be returned in case str contains a trailing partial character. If an error occurs then the index of the invalid input is stored here.

items_written :

location to store number of bytes written, or NULL. The value stored here does not include the trailing 0 byte.

error :

location to store the error occuring, or NULL to ignore errors. Any of the errors in GConvertError other than G_CONVERT_ERROR_NO_CONVERSION may occur.

Returns :

a pointer to a newly allocated UTF-8 string. This value must be freed with g_free(). If an error occurs, NULL will be returned and error set.

g_ucs4_to_utf16 ()

gunichar2 *         g_ucs4_to_utf16                     (const gunichar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);

Convert a string from UCS-4 to UTF-16. A 0 character will be added to the result after the converted text.

str :

a UCS-4 encoded string

len :

the maximum length (number of characters) of str to use. If len < 0, then the string is nul-terminated.

items_read :

location to store number of bytes read, or NULL. If an error occurs then the index of the invalid input is stored here.

items_written :

location to store number of gunichar2 written, or NULL. The value stored here does not include the trailing 0.

error :

location to store the error occuring, or NULL to ignore errors. Any of the errors in GConvertError other than G_CONVERT_ERROR_NO_CONVERSION may occur.

Returns :

a pointer to a newly allocated UTF-16 string. This value must be freed with g_free(). If an error occurs, NULL will be returned and error set.

g_ucs4_to_utf8 ()

gchar*              g_ucs4_to_utf8                      (const gunichar *str,
                                                         glong len,
                                                         glong *items_read,
                                                         glong *items_written,
                                                         GError **error);

Convert a string from a 32-bit fixed width representation as UCS-4. to UTF-8. The result will be terminated with a 0 byte.

str :

a UCS-4 encoded string

len :

the maximum length (number of characters) of str to use. If len < 0, then the string is nul-terminated.

items_read :

location to store number of characters read, or NULL.

items_written :

location to store number of bytes written or NULL. The value here stored does not include the trailing 0 byte.

error :

location to store the error occuring, or NULL to ignore errors. Any of the errors in GConvertError other than G_CONVERT_ERROR_NO_CONVERSION may occur.

Returns :

a pointer to a newly allocated UTF-8 string. This value must be freed with g_free(). If an error occurs, NULL will be returned and error set. In that case, items_read will be set to the position of the first invalid input character.

g_unichar_to_utf8 ()

gint                g_unichar_to_utf8                   (gunichar c,
                                                         gchar *outbuf);

Converts a single character to UTF-8.

c :

a Unicode character code

outbuf :

output buffer, must have at least 6 bytes of space. If NULL, the length will be computed and returned and nothing will be written to outbuf.

Returns :

number of bytes written

See Also

g_locale_to_utf8(), g_locale_from_utf8()

Convenience functions for converting between UTF-8 and the locale encoding.



[3] surrogate pairs