mirror of
https://git.openldap.org/openldap/openldap.git
synced 2024-12-15 03:01:09 +08:00
344 lines
9.4 KiB
Plaintext
344 lines
9.4 KiB
Plaintext
#
|
|
# $Id: api.txt,v 1.2 1999/11/19 15:24:29 mleisher Exp $
|
|
#
|
|
|
|
The MUTT UCData API
|
|
-------------------
|
|
|
|
|
|
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
Macros that combine to select data tables for ucdata_load(), ucdata_unload(),
|
|
and ucdata_reload().
|
|
|
|
#define UCDATA_CASE 0x01
|
|
#define UCDATA_CTYPE 0x02
|
|
#define UCDATA_DECOMP 0x04
|
|
#define UCDATA_CMBCL 0x08
|
|
#define UCDATA_NUM 0x10
|
|
#define UCATA_ALL (UCDATA_CASE|UCDATA_CTYPE|UCDATA_DECOMP|\
|
|
UCDATA_CMBCL|UCDATA_NUM)
|
|
-----------------------------------------------------------------------------
|
|
|
|
void ucdata_load(char *paths, int masks)
|
|
|
|
This function initializes the UCData library by locating the data files in
|
|
one of the colon-separated directories in the `paths' parameter. The data
|
|
files to be loaded are specified in the `masks' parameter as a bitwise
|
|
combination of the macros listed above.
|
|
|
|
This should be called before using any of the other functions.
|
|
|
|
NOTE: the ucdata_setup(char *paths) function is now a macro that expands
|
|
into this function at compile time.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
void ucdata_unload(int masks)
|
|
|
|
This function unloads the data tables specified in the `masks' parameter.
|
|
|
|
This function should be called when the application is done using the UCData
|
|
package.
|
|
|
|
NOTE: the ucdata_cleanup() function is now a macro that expands into this
|
|
function at compile time.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
void ucdata_reload(char *paths, int masks)
|
|
|
|
This function reloads the data files from one of the colon-separated
|
|
directories in the `paths' parameter. The data files to be reloaded are
|
|
specified in the `masks' parameter as a bitwise combination of the macros
|
|
listed above.
|
|
|
|
If the data files have already been loaded, they are unloaded before the
|
|
data files are loaded again.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
int ucdecomp(unsigned long code, unsigned long *num, unsigned long **decomp)
|
|
|
|
This function determines if a character has a decomposition and returns the
|
|
decomposition information if it exists.
|
|
|
|
If a zero is returned, there is no decomposition. If a non-zero is
|
|
returned, then the `num' and `decomp' variables are filled in with the
|
|
appropriate values.
|
|
|
|
Example call:
|
|
|
|
unsigned long i, num, *decomp;
|
|
|
|
if (ucdecomp(0x1d5, &num, &decomp) != 0) {
|
|
for (i = 0; i < num; i++)
|
|
printf("0x%08lX,", decomp[i]);
|
|
putchar('\n');
|
|
}
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
int ucdecomp_hangul(unsigned long code, unsigned long *num,
|
|
unsigned long decomp[])
|
|
|
|
This function determines if a Hangul syllable has a decomposition and
|
|
returns the decomposition information.
|
|
|
|
An array of at least size 3 should be passed to the function for the
|
|
decomposition of the syllable.
|
|
|
|
If a zero is returned, the character is not a Hangul syllable. If a
|
|
non-zero is returned, the `num' field will be 2 or 3 and the syllable will
|
|
be decomposed into the `decomp' array arithmetically.
|
|
|
|
Example call:
|
|
|
|
unsigned long i, num, decomp[3];
|
|
|
|
if (ucdecomp_hangul(0xb1ba, &num, &decomp) != 0) {
|
|
for (i = 0; i < num; i++)
|
|
printf("0x%08lX,", decomp[i]);
|
|
putchar('\n');
|
|
}
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
struct ucnumber {
|
|
int numerator;
|
|
int denominator;
|
|
};
|
|
|
|
int ucnumber_lookup(unsigned long code, struct ucnumber *num)
|
|
|
|
This function determines if the code is a number and fills in the `num'
|
|
field with the numerator and denominator. If the code happens to be a
|
|
single digit, the numerator and denominator fields will be the same.
|
|
|
|
If the function returns 0, the code is not a number. Any other return
|
|
value means the code is a number.
|
|
|
|
int ucdigit_lookup(unsigned long code, int *digit)
|
|
|
|
This function determines if the code is a digit and fills in the `digit'
|
|
field with the digit value.
|
|
|
|
If the function returns 0, the code is not a number. Any other return
|
|
value means the code is a number.
|
|
|
|
struct ucnumber ucgetnumber(unsigned long code)
|
|
|
|
This is a compatibility function with John Cowan's "uctype" package. It
|
|
uses ucnumber_lookup().
|
|
|
|
int ucgetdigit(unsigned long code)
|
|
|
|
This is a compatibility function with John Cowan's "uctype" package. It
|
|
uses ucdigit_lookup().
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
unsigned long uctoupper(unsigned long code)
|
|
|
|
This function returns the code unchanged if it is already upper case or has
|
|
no upper case equivalent. Otherwise the upper case equivalent is returned.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
unsigned long uctolower(unsigned long code)
|
|
|
|
This function returns the code unchanged if it is already lower case or has
|
|
no lower case equivalent. Otherwise the lower case equivalent is returned.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
unsigned long uctotitle(unsigned long code)
|
|
|
|
This function returns the code unchanged if it is already title case or has
|
|
no title case equivalent. Otherwise the title case equivalent is returned.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
int ucisalpha(unsigned long code)
|
|
int ucisalnum(unsigned long code)
|
|
int ucisdigit(unsigned long code)
|
|
int uciscntrl(unsigned long code)
|
|
int ucisspace(unsigned long code)
|
|
int ucisblank(unsigned long code)
|
|
int ucispunct(unsigned long code)
|
|
int ucisgraph(unsigned long code)
|
|
int ucisprint(unsigned long code)
|
|
int ucisxdigit(unsigned long code)
|
|
|
|
int ucisupper(unsigned long code)
|
|
int ucislower(unsigned long code)
|
|
int ucistitle(unsigned long code)
|
|
|
|
These functions (actually macros) determine if a character has these
|
|
properties. These behave in a fashion very similar to the venerable ctype
|
|
package.
|
|
|
|
-----------------------------------------------------------------------------
|
|
|
|
int ucisisocntrl(unsigned long code)
|
|
|
|
Is the character a C0 control character (< 32) ?
|
|
|
|
int ucisfmtcntrl(unsigned long code)
|
|
|
|
Is the character a format control character?
|
|
|
|
int ucissymbol(unsigned long code)
|
|
|
|
Is the character a symbol?
|
|
|
|
int ucisnumber(unsigned long code)
|
|
|
|
Is the character a number or digit?
|
|
|
|
int ucisnonspacing(unsigned long code)
|
|
|
|
Is the character non-spacing?
|
|
|
|
int ucisopenpunct(unsigned long code)
|
|
|
|
Is the character an open/left punctuation (i.e. '[')
|
|
|
|
int ucisclosepunct(unsigned long code)
|
|
|
|
Is the character an close/right punctuation (i.e. ']')
|
|
|
|
int ucisinitialpunct(unsigned long code)
|
|
|
|
Is the character an initial punctuation (i.e. U+2018 LEFT SINGLE QUOTATION
|
|
MARK)
|
|
|
|
int ucisfinalpunct(unsigned long code)
|
|
|
|
Is the character a final punctuation (i.e. U+2019 RIGHT SINGLE QUOTATION
|
|
MARK)
|
|
|
|
int uciscomposite(unsigned long code)
|
|
|
|
Can the character be decomposed into a set of other characters?
|
|
|
|
int ucisquote(unsigned long code)
|
|
|
|
Is the character one of the many quotation marks?
|
|
|
|
int ucissymmetric(unsigned long code)
|
|
|
|
Is the character one that has an opposite form (i.e. <>)
|
|
|
|
int ucismirroring(unsigned long code)
|
|
|
|
Is the character mirroring (superset of symmetric)?
|
|
|
|
int ucisnonbreaking(unsigned long code)
|
|
|
|
Is the character non-breaking (i.e. non-breaking space)?
|
|
|
|
int ucisrtl(unsigned long code)
|
|
|
|
Does the character have strong right-to-left directionality (i.e. Arabic
|
|
letters)?
|
|
|
|
int ucisltr(unsigned long code)
|
|
|
|
Does the character have strong left-to-right directionality (i.e. Latin
|
|
letters)?
|
|
|
|
int ucisstrong(unsigned long code)
|
|
|
|
Does the character have strong directionality?
|
|
|
|
int ucisweak(unsigned long code)
|
|
|
|
Does the character have weak directionality (i.e. numbers)?
|
|
|
|
int ucisneutral(unsigned long code)
|
|
|
|
Does the character have neutral directionality (i.e. whitespace)?
|
|
|
|
int ucisseparator(unsigned long code)
|
|
|
|
Is the character a block or segment separator?
|
|
|
|
int ucislsep(unsigned long code)
|
|
|
|
Is the character a line separator?
|
|
|
|
int ucispsep(unsigned long code)
|
|
|
|
Is the character a paragraph separator?
|
|
|
|
int ucismark(unsigned long code)
|
|
|
|
Is the character a mark of some kind?
|
|
|
|
int ucisnsmark(unsigned long code)
|
|
|
|
Is the character a non-spacing mark?
|
|
|
|
int ucisspmark(unsigned long code)
|
|
|
|
Is the character a spacing mark?
|
|
|
|
int ucismodif(unsigned long code)
|
|
|
|
Is the character a modifier letter?
|
|
|
|
int ucismodifsymbol(unsigned long code)
|
|
|
|
Is the character a modifier symbol?
|
|
|
|
int ucisletnum(unsigned long code)
|
|
|
|
Is the character a number represented by a letter?
|
|
|
|
int ucisconnect(unsigned long code)
|
|
|
|
Is the character connecting punctuation?
|
|
|
|
int ucisdash(unsigned long code)
|
|
|
|
Is the character dash punctuation?
|
|
|
|
int ucismath(unsigned long code)
|
|
|
|
Is the character a math character?
|
|
|
|
int uciscurrency(unsigned long code)
|
|
|
|
Is the character a currency character?
|
|
|
|
int ucisenclosing(unsigned long code)
|
|
|
|
Is the character enclosing (i.e. enclosing box)?
|
|
|
|
int ucisprivate(unsigned long code)
|
|
|
|
Is the character from the Private Use Area?
|
|
|
|
int ucissurrogate(unsigned long code)
|
|
|
|
Is the character one of the surrogate codes?
|
|
|
|
int ucisdefined(unsigned long code)
|
|
|
|
Is the character defined (appeared in one of the data files)?
|
|
|
|
int ucisundefined(unsigned long code)
|
|
|
|
Is the character not defined (non-Unicode)?
|
|
|
|
int ucishan(unsigned long code)
|
|
|
|
Is the character a Han ideograph?
|
|
|
|
int ucishangul(unsigned long code)
|
|
|
|
Is the character a pre-composed Hangul syllable?
|