diff options
Diffstat (limited to 'doc/unigbrk.texi')
-rw-r--r-- | doc/unigbrk.texi | 126 |
1 files changed, 126 insertions, 0 deletions
diff --git a/doc/unigbrk.texi b/doc/unigbrk.texi new file mode 100644 index 0000000..196bd9f --- /dev/null +++ b/doc/unigbrk.texi @@ -0,0 +1,126 @@ +@node unigbrk.h +@chapter Grapheme cluster breaks in strings @code{<unigbrk.h>} + +@cindex grapheme cluster breaks +@cindex grapheme cluster boundaries +@cindex breaks, grapheme cluster +@cindex boundaries, between grapheme clusters +This include file declares functions for determining where in a string +``grapheme clusters'' start and end. A ``grapheme cluster'' is an +approximation to a user-perceived character, which sometimes +corresponds to multiple Unicode characters. Editing operations such as +mouse selection, cursor movement, and backspacing often operate on +grapheme clusters as units, not on individual characters. + +Some grapheme clusters are built from a base character and a combining +character. The letter @samp{@'e}, +for example, is most commonly represented in Unicode as a single +character U+00E8 @sc{LATIN SMALL LETTER E WITH ACUTE}. It is, +however, equally valid to use the pair of characters U+0065 @sc{LATIN +SMALL LETTER E} followed by U+0301 @sc{COMBINING ACUTE ACCENT}. Since +the user would perceive this pair of characters as a single character, +they would be grouped into a single grapheme cluster. + +But there are also grapheme clusters that consist of several base characters. +For example, a Devanagari letter and a Devanagari vowel sign that follows it +may form a grapheme cluster. Similarly, some pairs of Thai characters and +Hangul syllables (formed by two or three Hangul characters) are grapheme +clusters. + +@menu +* Grapheme cluster breaks in a string:: +* Grapheme cluster break property:: +@end menu + +@node Grapheme cluster breaks in a string +@section Grapheme cluster breaks in a string + +The following functions find a single boundary between grapheme +clusters in a string. + +@deftypefun void u8_grapheme_next (const uint8_t *@var{s}, const uint8_t *@var{end}) +@deftypefunx void u16_grapheme_next (const uint16_t *@var{s}, const uint16_t *@var{end}) +@deftypefunx void u32_grapheme_next (const uint32_t *@var{s}, const uint32_t *@var{end}) +Returns the start of the next grapheme cluster following @var{s}, +or @var{end} if no grapheme cluster break is encountered before it. +Returns NULL if and only if @code{@var{s} == @var{end}}. +@end deftypefun + +@deftypefun void u8_grapheme_prev (const uint8_t *@var{s}, const uint8_t *@var{start}) +@deftypefunx void u16_grapheme_prev (const uint16_t *@var{s}, const uint16_t *@var{start}) +@deftypefunx void u32_grapheme_prev (const uint32_t *@var{s}, const uint32_t *@var{start}) +Returns the start of the grapheme cluster preceding @var{s}, or +@var{start} if no grapheme cluster break is encountered before it. +Returns NULL if and only if @code{@var{s} == @var{start}}. +@end deftypefun + +The following functions determine all of the grapheme cluster +boundaries in a string. + +@deftypefun void u8_grapheme_breaks (const uint8_t *@var{s}, size_t @var{n}, char *@var{p}) +@deftypefunx void u16_grapheme_breaks (const uint16_t *@var{s}, size_t @var{n}, char *@var{p}) +@deftypefunx void u32_grapheme_breaks (const uint32_t *@var{s}, size_t @var{n}, char *@var{p}) +@deftypefunx void ulc_grapheme_breaks (const char *@var{s}, size_t @var{n}, char *@var{p}) +Determines the grapheme cluster break points in @var{s}, an array of +@var{n} units, and stores the result at @code{@var{p}[0..@var{n}-1]}. +@table @asis +@item @code{@var{p}[i] = 1} +means that there is a grapheme cluster boundary between +@code{@var{s}[i-1]} and @code{@var{s}[i]}. +@item @code{@var{p}[i] = 0} +means that @code{@var{s}[i-1]} and @code{@var{s}[i]} are part of the +same grapheme cluster. +@end table +@code{@var{p}[0]} is always set to 1, because there is always a +grapheme cluster break at start of text. +@end deftypefun + +@node Grapheme cluster break property +@section Grapheme cluster break property + +This is a more low-level API. The grapheme cluster break property is a +property defined in Unicode Standard Annex #29, section ``Grapheme Cluster +Boundaries'', see +@url{http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries}.@texnl{} +It is used for determining the grapheme cluster breaks in a string. + +The following are the possible values of the grapheme cluster break +property. More values may be added in the future. + +@deftypevr Constant int GBP_OTHER +@deftypevrx Constant int GBP_CR +@deftypevrx Constant int GBP_LF +@deftypevrx Constant int GBP_CONTROL +@deftypevrx Constant int GBP_EXTEND +@deftypevrx Constant int GBP_PREPEND +@deftypevrx Constant int GBP_SPACINGMARK +@deftypevrx Constant int GBP_L +@deftypevrx Constant int GBP_V +@deftypevrx Constant int GBP_T +@deftypevrx Constant int GBP_LV +@deftypevrx Constant int GBP_LVT +@end deftypevr + +The following function looks up the grapheme cluster break property of a +character. + +@deftypefun int uc_graphemeclusterbreak_property (ucs4_t @var{uc}) +Returns the Grapheme_Cluster_Break property of a Unicode character. +@end deftypefun + +The following function determines whether there is a grapheme cluster +break between two Unicode characters. It is the primitive upon which +the higher-level functions in the previous section are directly based. + +@deftypefun bool uc_is_grapheme_break (ucs4_t @var{a}, ucs4_t @var{b}) +Returns true if there is an grapheme cluster boundary between Unicode +characters @var{a} and @var{b}. + +There is always a grapheme cluster break at the start or end of text. +You can specify zero for @var{a} or @var{b} to indicate start of text or end +of text, respectively. + +This implements the extended (not legacy) grapheme cluster rules +described in the Unicode standard, because the standard says that they +are preferred. +@end deftypefun |