From a9a31b1de5776a3b08a82101a4fa711294f0dd1d Mon Sep 17 00:00:00 2001 From: "Manuel A. Fernandez Montecelo" Date: Fri, 27 May 2016 14:28:30 +0100 Subject: Imported Upstream version 0.9.6+really0.9.3 --- doc/libunistring_14.html | 550 ++--------------------------------------------- 1 file changed, 13 insertions(+), 537 deletions(-) (limited to 'doc/libunistring_14.html') diff --git a/doc/libunistring_14.html b/doc/libunistring_14.html index 5f261d66..1a7a338f 100644 --- a/doc/libunistring_14.html +++ b/doc/libunistring_14.html @@ -1,6 +1,6 @@ - + -GNU libunistring: 14. Case mappings <unicase.h> +GNU libunistring: 14. Regular expressions <uniregex.h> - - + + @@ -43,7 +43,7 @@ ul.toc {list-style: none} - + @@ -51,545 +51,21 @@ ul.toc {list-style: none} - +
[ << ][ >> ][ >> ]         [Top] [Contents][Index][Index] [ ? ]
- + -

14. Case mappings <unicase.h>

+

14. Regular expressions <uniregex.h>

-

This include file defines functions for case mapping for Unicode strings and -case insensitive comparison of Unicode strings and C strings. +

This include file is not yet implemented.

-

These string functions fix the problems that were mentioned in -‘char *’ strings, namely, they handle the Croatian -LETTER DZ WITH CARON, the German LATIN SMALL LETTER SHARP S, the -Greek sigma and the Lithuanian i correctly. -

- -
- - -

14.1 Case mappings of characters

- -

The following functions implement case mappings on Unicode characters — -for those cases only where the result of the mapping is a again a single -Unicode character. -

-

These mappings are locale and context independent. -

-
-

WARNING! These functions are not sufficient for languages such as -German, Greek and Lithuanian. Better use the functions below that treat an -entire string at once and are language aware. -

- -
-
Function: ucs4_t uc_toupper (ucs4_t uc) - -
-

Returns the uppercase mapping of the Unicode character uc. -

- -
-
Function: ucs4_t uc_tolower (ucs4_t uc) - -
-

Returns the lowercase mapping of the Unicode character uc. -

- -
-
Function: ucs4_t uc_totitle (ucs4_t uc) - -
-

Returns the titlecase mapping of the Unicode character uc. -

-

The titlecase mapping of a character is to be used when the character should -look like upper case and the following characters are lower cased. -

-

For most characters, this is the same as the uppercase mapping. There are -only few characters where the title case variant and the uuper case variant -are different. These characters occur in the Latin writing of the Croatian, -Bosnian, and Serbian languages. -

- - - - - - -

Lower case

Title case

Upper case -

LATIN SMALL LETTER LJ -

LATIN CAPITAL LETTER L WITH SMALL LETTER J -

LATIN CAPITAL LETTER LJ -

LATIN SMALL LETTER NJ -

LATIN CAPITAL LETTER N WITH SMALL LETTER J -

LATIN CAPITAL LETTER NJ -

LATIN SMALL LETTER DZ -

LATIN CAPITAL LETTER D WITH SMALL LETTER Z -

LATIN CAPITAL LETTER DZ -

LATIN SMALL LETTER DZ WITH CARON -

LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON -

LATIN CAPITAL LETTER DZ WITH CARON -

-
- -
- - -

14.2 Case mappings of strings

- -

Case mapping should always be performed on entire strings, not on individual -characters. The functions in this sections do so. -

-

These functions allow to apply a normalization after the case mapping. The -reason is that if you want to treat ‘ä’ and ‘Ä’ the same, -you most often also want to treat the composed and decomposed forms of such -a character, U+00C4 LATIN CAPITAL LETTER A WITH DIAERESIS and -U+0041 LATIN CAPITAL LETTER A U+0308 COMBINING DIAERESIS the same. -The nf argument designates the normalization. -

- -

These functions are locale dependent. The iso639_language argument -identifies the language (e.g. "tr" for Turkish). NULL means to use -locale independent case mappings. -

-
-
Function: const char * uc_locale_language () - -
-

Returns the ISO 639 language code of the current locale. -Returns "" if it is unknown, or in the "C" locale. -

- -
-
Function: uint8_t * u8_toupper (const uint8_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_toupper (const uint16_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_toupper (const uint32_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the uppercase mapping of a string. -

-

The nf argument identifies the normalization form to apply after the -case-mapping. It can also be NULL, for no normalization. -

- -
-
Function: uint8_t * u8_tolower (const uint8_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_tolower (const uint16_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_tolower (const uint32_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the lowercase mapping of a string. -

-

The nf argument identifies the normalization form to apply after the -case-mapping. It can also be NULL, for no normalization. -

- -
-
Function: uint8_t * u8_totitle (const uint8_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_totitle (const uint16_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_totitle (const uint32_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the titlecase mapping of a string. -

-

Mapping to title case means that, in each word, the first cased character -is being mapped to title case and the remaining characters of the word -are being mapped to lower case. -

-

The nf argument identifies the normalization form to apply after the -case-mapping. It can also be NULL, for no normalization. -

- -
- - -

14.3 Case mappings of substrings

- -

Case mapping of a substring cannot simply be performed by extracting the -substring and then applying the case mapping function to it. This does not -work because case mapping requires some information about the surrounding -characters. The following functions allow to apply case mappings to -substrings of a given string, while taking into account the characters that -precede it (the “prefix”) and the characters that follow it (the “suffix”). -

-
-
Type: casing_prefix_context_t - -
-

This data type denotes the case-mapping context that is given by a prefix -string. It is an immediate type that can be copied by simple assignment, -without involving memory allocation. It is not an array type. -

- -
-
Constant: casing_prefix_context_t unicase_empty_prefix_context - -
-

This constant is the case-mapping context that corresponds to an empty prefix -string. -

- -

The following functions return casing_prefix_context_t objects: -

-
-
Function: casing_prefix_context_t u8_casing_prefix_context (const uint8_t *s, size_t n) - -
-
Function: casing_prefix_context_t u16_casing_prefix_context (const uint16_t *s, size_t n) - -
-
Function: casing_prefix_context_t u32_casing_prefix_context (const uint32_t *s, size_t n) - -
-

Returns the case-mapping context of a given prefix string. -

- -
-
Function: casing_prefix_context_t u8_casing_prefixes_context (const uint8_t *s, size_t n, casing_prefix_context_t a_context) - -
-
Function: casing_prefix_context_t u16_casing_prefixes_context (const uint16_t *s, size_t n, casing_prefix_context_t a_context) - -
-
Function: casing_prefix_context_t u32_casing_prefixes_context (const uint32_t *s, size_t n, casing_prefix_context_t a_context) - -
-

Returns the case-mapping context of the prefix concat(a, s), -given the case-mapping context of the prefix a. -

- -
-
Type: casing_suffix_context_t - -
-

This data type denotes the case-mapping context that is given by a suffix -string. It is an immediate type that can be copied by simple assignment, -without involving memory allocation. It is not an array type. -

- -
-
Constant: casing_suffix_context_t unicase_empty_suffix_context - -
-

This constant is the case-mapping context that corresponds to an empty suffix -string. -

- -

The following functions return casing_suffix_context_t objects: -

-
-
Function: casing_suffix_context_t u8_casing_suffix_context (const uint8_t *s, size_t n) - -
-
Function: casing_suffix_context_t u16_casing_suffix_context (const uint16_t *s, size_t n) - -
-
Function: casing_suffix_context_t u32_casing_suffix_context (const uint32_t *s, size_t n) - -
-

Returns the case-mapping context of a given suffix string. -

- -
-
Function: casing_suffix_context_t u8_casing_suffixes_context (const uint8_t *s, size_t n, casing_suffix_context_t a_context) - -
-
Function: casing_suffix_context_t u16_casing_suffixes_context (const uint16_t *s, size_t n, casing_suffix_context_t a_context) - -
-
Function: casing_suffix_context_t u32_casing_suffixes_context (const uint32_t *s, size_t n, casing_suffix_context_t a_context) - -
-

Returns the case-mapping context of the suffix concat(s, a), -given the case-mapping context of the suffix a. -

- -

The following functions perform a case mapping, considering the -prefix context and the suffix context. -

-
-
Function: uint8_t * u8_ct_toupper (const uint8_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_ct_toupper (const uint16_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_ct_toupper (const uint32_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the uppercase mapping of a string that is surrounded by a prefix -and a suffix. -

- -
-
Function: uint8_t * u8_ct_tolower (const uint8_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_ct_tolower (const uint16_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_ct_tolower (const uint32_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the lowercase mapping of a string that is surrounded by a prefix -and a suffix. -

- -
-
Function: uint8_t * u8_ct_totitle (const uint8_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_ct_totitle (const uint16_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_ct_totitle (const uint32_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the titlecase mapping of a string that is surrounded by a prefix -and a suffix. -

- -

For example, to uppercase the UTF-8 substring between s + start_index -and s + end_index of a string that extends from s to -s + u8_strlen (s), you can use the statements -

-
 
size_t result_length;
-uint8_t result =
-  u8_ct_toupper (s + start_index, end_index - start_index,
-                 u8_casing_prefix_context (s, start_index),
-                 u8_casing_suffix_context (s + end_index,
-                                           u8_strlen (s) - end_index),
-                 iso639_language, NULL, NULL, &result_length);
-
- -
- - -

14.4 Case insensitive comparison

- -

The following functions implement comparison that ignores differences in case -and normalization. -

-
-
Function: uint8_t * u8_casefold (const uint8_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_casefold (const uint16_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_casefold (const uint32_t *s, size_t n, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the case folded string. -

-

Comparing u8_casefold (s1) and u8_casefold (s2) -with the u8_cmp2 function is equivalent to comparing s1 and -s2 with u8_casecmp. -

-

The nf argument identifies the normalization form to apply after the -case-mapping. It can also be NULL, for no normalization. -

- -
-
Function: uint8_t * u8_ct_casefold (const uint8_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint8_t *resultbuf, size_t *lengthp) - -
-
Function: uint16_t * u16_ct_casefold (const uint16_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint16_t *resultbuf, size_t *lengthp) - -
-
Function: uint32_t * u32_ct_casefold (const uint32_t *s, size_t n, casing_prefix_context_t prefix_context, casing_suffix_context_t suffix_context, const char *iso639_language, uninorm_t nf, uint32_t *resultbuf, size_t *lengthp) - -
-

Returns the case folded string. The case folding takes into account the -case mapping contexts of the prefix and suffix strings. -

- -
-
Function: int u8_casecmp (const uint8_t *s1, size_t n1, const uint8_t *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-
Function: int u16_casecmp (const uint16_t *s1, size_t n1, const uint16_t *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-
Function: int u32_casecmp (const uint32_t *s1, size_t n1, const uint32_t *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-
Function: int ulc_casecmp (const char *s1, size_t n1, const char *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-

Compares s1 and s2, ignoring differences in case and normalization. -

-

The nf argument identifies the normalization form to apply after the -case-mapping. It can also be NULL, for no normalization. -

-

If successful, sets *resultp to -1 if s1 < s2, -0 if s1 = s2, 1 if s1 > s2, and returns 0. -Upon failure, returns -1 with errno set. -

- - - - - -

The following functions additionally take into account the sorting rules of the -current locale. -

-
-
Function: char * u8_casexfrm (const uint8_t *s, size_t n, const char *iso639_language, uninorm_t nf, char *resultbuf, size_t *lengthp) - -
-
Function: char * u16_casexfrm (const uint16_t *s, size_t n, const char *iso639_language, uninorm_t nf, char *resultbuf, size_t *lengthp) - -
-
Function: char * u32_casexfrm (const uint32_t *s, size_t n, const char *iso639_language, uninorm_t nf, char *resultbuf, size_t *lengthp) - -
-
Function: char * ulc_casexfrm (const char *s, size_t n, const char *iso639_language, uninorm_t nf, char *resultbuf, size_t *lengthp) - -
-

Converts the string s of length n to a NUL-terminated byte -sequence, in such a way that comparing u8_casexfrm (s1) and -u8_casexfrm (s2) with the gnulib function memcmp2 is -equivalent to comparing s1 and s2 with u8_casecoll. -

-

nf must be either UNINORM_NFC, UNINORM_NFKC, or NULL for -no normalization. -

- -
-
Function: int u8_casecoll (const uint8_t *s1, size_t n1, const uint8_t *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-
Function: int u16_casecoll (const uint16_t *s1, size_t n1, const uint16_t *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-
Function: int u32_casecoll (const uint32_t *s1, size_t n1, const uint32_t *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-
Function: int ulc_casecoll (const char *s1, size_t n1, const char *s2, size_t n2, const char *iso639_language, uninorm_t nf, int *resultp) - -
-

Compares s1 and s2, ignoring differences in case and normalization, -using the collation rules of the current locale. -

-

The nf argument identifies the normalization form to apply after the -case-mapping. It must be either UNINORM_NFC or UNINORM_NFKC. -It can also be NULL, for no normalization. -

-

If successful, sets *resultp to -1 if s1 < s2, -0 if s1 = s2, 1 if s1 > s2, and returns 0. -Upon failure, returns -1 with errno set. -

- -
- - -

14.5 Case detection

- -

The following functions determine whether a Unicode string is entirely in -upper case. or entirely in lower case, or entirely in title case, or already -case-folded. -

-
-
Function: int u8_is_uppercase (const uint8_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u16_is_uppercase (const uint16_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u32_is_uppercase (const uint32_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-

Sets *resultp to true if mapping NFD(s) to upper case is -a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with -errno set. -

- -
-
Function: int u8_is_lowercase (const uint8_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u16_is_lowercase (const uint16_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u32_is_lowercase (const uint32_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-

Sets *resultp to true if mapping NFD(s) to lower case is -a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with -errno set. -

- -
-
Function: int u8_is_titlecase (const uint8_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u16_is_titlecase (const uint16_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u32_is_titlecase (const uint32_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-

Sets *resultp to true if mapping NFD(s) to title case is -a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with -errno set. -

- -
-
Function: int u8_is_casefolded (const uint8_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u16_is_casefolded (const uint16_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u32_is_casefolded (const uint32_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-

Sets *resultp to true if applying case folding to NFD(S) is -a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with -errno set. -

- -

The following functions determine whether case mappings have any effect on a -Unicode string. -

-
-
Function: int u8_is_cased (const uint8_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u16_is_cased (const uint16_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-
Function: int u32_is_cased (const uint32_t *s, size_t n, const char *iso639_language, bool *resultp) - -
-

Sets *resultp to true if case matters for s, that is, if -mapping NFD(s) to either upper case or lower case or title case is not -a no-op. Set *resultp to false if NFD(s) maps to itself -under the upper case mapping, under the lower case mapping, and under the title -case mapping; in other words, when NFD(s) consists entirely of caseless -characters. Upon failure, returns -1 with errno set. -

- - + + @@ -597,12 +73,12 @@ characters. Upon failure, returns -1 with errno set. - +
[ << ][ >> ]
[ << ][ >> ]         [Top] [Contents][Index][Index] [ ? ]

- This document was generated by Daiki Ueno on July, 8 2015 using texi2html 1.78a. + This document was generated by Bruno Haible on March, 30 2010 using texi2html 1.78a.
-- cgit v1.2.3