mirror of
https://github.com/php/php-src.git
synced 2024-10-05 08:46:11 +00:00
280 lines
7.4 KiB
Plaintext
280 lines
7.4 KiB
Plaintext
Oniguruma API 2003/07/04
|
|
|
|
declared in regex.h.
|
|
|
|
|
|
# int regex_init(void)
|
|
|
|
Initialize library.
|
|
|
|
You don't have to call it explicitly, because it is called in regex_new().
|
|
|
|
|
|
# int regex_error_code_to_str(UChar* err_buf, int err_code, ...)
|
|
|
|
Return error message string length.
|
|
|
|
arguments
|
|
1 err_buf: error message buffer.
|
|
(required size: REG_MAX_ERROR_MESSAGE_LEN)
|
|
2 err_code: error code returned from other API functions.
|
|
3 err_info (optional): error info returned from regex_new()
|
|
and regex_recompile().
|
|
|
|
|
|
# int regex_new(regex_t** reg, UChar* pattern, UChar* pattern_end,
|
|
RegOptionType option, RegCharEncoding code, RegSyntaxType* syntax,
|
|
RegErrorInfo* err_info)
|
|
|
|
Create new regex object(regex_t).
|
|
|
|
normal return: REG_NORMAL
|
|
|
|
arguments
|
|
1 reg: return regex object's address.
|
|
2 pattern: regex pattern string.
|
|
3 pattern_end: terminate address of pattern. (pattern + pattern length)
|
|
4 option: compile time options.
|
|
|
|
REG_OPTION_NONE no option
|
|
REG_OPTION_SINGLELINE '^' -> '\A', '$' -> '\z', '\Z' -> '\z'
|
|
REG_OPTION_MULTILINE '.' match with newline
|
|
REG_OPTION_IGNORECASE ignore case (case-insensitive)
|
|
REG_OPTION_EXTEND extended pattern form
|
|
REG_OPTION_FIND_LONGEST find longest match
|
|
REG_OPTION_FIND_NOT_EMPTY ignore empty match
|
|
REG_OPTION_NEGATE_SINGLELINE
|
|
clear REG_OPTION_SINGLELINE which is default on
|
|
in REG_SYNTAX_POSIX_XXX, REG_SYNTAX_PERL and REG_SYNTAX_JAVA.
|
|
REG_OPTION_CAPTURE_ONLY_NAMED_GROUP named group only captured.
|
|
|
|
5 code: character encoding.
|
|
|
|
REGCODE_ASCII ASCII
|
|
REGCODE_UTF8 UTF-8
|
|
REGCODE_EUCJP EUC-JP
|
|
REGCODE_SJIS Shift_JIS
|
|
REGCODE_DEFAULT ASCII
|
|
|
|
6 syntax: pointer to pattern syntax definition.
|
|
|
|
REG_SYNTAX_POSIX_BASIC POSIX Basic RE
|
|
REG_SYNTAX_POSIX_EXTENDED POSIX Extended RE
|
|
REG_SYNTAX_EMACS Emacs
|
|
REG_SYNTAX_GREP grep
|
|
REG_SYNTAX_GNU_REGEX GNU regex
|
|
REG_SYNTAX_JAVA Java (Sun java.util.regex)
|
|
REG_SYNTAX_PERL Perl
|
|
REG_SYNTAX_RUBY Ruby
|
|
REG_SYNTAX_DEFAULT default (== Ruby)
|
|
regex_set_default_syntax()
|
|
|
|
or any RegSyntaxType data pointer defined by user.
|
|
|
|
7 err_info: address for return optional error info.
|
|
use this value as 3rd argument of regex_error_code_to_str().
|
|
|
|
|
|
# void regex_free(regex_t* reg)
|
|
|
|
Free memory used by regex object.
|
|
|
|
arguments
|
|
1 reg: regex object.
|
|
|
|
|
|
# int regex_recompile(regex_t* reg, UChar* pattern, UChar* pattern_end,
|
|
RegOptionType option, RegCharEncoding code, RegSyntaxType* syntax,
|
|
RegErrorInfo* err_info)
|
|
|
|
Recompile regex object.
|
|
|
|
normal return: REG_NORMAL
|
|
|
|
arguments
|
|
1 reg: regex object.
|
|
|
|
Another arguments are same with regex_new().
|
|
|
|
|
|
# int regex_search(regex_t* reg, UChar* str, UChar* end, UChar* start,
|
|
UChar* range, RegRegion* region, RegOptionType option)
|
|
|
|
Search string and return search result and matching region.
|
|
|
|
normal return: match position offset (i.e. p - str >= 0)
|
|
not found: REG_MISMATCH (< 0)
|
|
|
|
arguments
|
|
1 reg: regex object
|
|
2 str: target string
|
|
3 end: terminate address of target string
|
|
4 start: search start address of target string
|
|
5 range: search terminate address of target string
|
|
6 region: address for return group match range info (NULL is allowed)
|
|
7 option: search time option
|
|
|
|
REG_OPTION_NOTBOL string head(str) isn't considered as begin of line
|
|
REG_OPTION_NOTEOL string end (end) isn't considered as end of line
|
|
REG_OPTION_POSIX_REGION region argument is regmatch_t[] of POSIX API.
|
|
|
|
|
|
# int regex_match(regex_t* reg, UChar* str, UChar* end, UChar* at,
|
|
RegRegion* region, RegOptionType option)
|
|
|
|
Match string and return result and matching region.
|
|
|
|
normal return: match length (i.e. p - at >= 0)
|
|
not match: REG_MISMATCH (< 0)
|
|
|
|
arguments
|
|
1 reg: regex object
|
|
2 str: target string
|
|
3 end: terminate address of target string
|
|
4 at: match address of target string
|
|
5 region: address for return group match range info (NULL is allowed)
|
|
6 option: search time option
|
|
|
|
REG_OPTION_NOTBOL string head(str) isn't considered as begin of line
|
|
REG_OPTION_NOTEOL string end (end) isn't considered as end of line
|
|
REG_OPTION_POSIX_REGION region argument is regmatch_t[] of POSIX API.
|
|
|
|
|
|
# RegRegion* regex_region_new(void)
|
|
|
|
Create a region.
|
|
|
|
|
|
# void regex_region_free(RegRegion* region, int free_self)
|
|
|
|
Free memory used by region.
|
|
|
|
arguments
|
|
1 region: target region
|
|
2 free_self: [1: free all, 0: free memory used in region but not self]
|
|
|
|
|
|
# void regex_region_copy(RegRegion* to, RegRegion* from)
|
|
|
|
Copy contents of region.
|
|
|
|
arguments
|
|
1 to: target region
|
|
2 from: source region
|
|
|
|
|
|
# void regex_region_clear(RegRegion* region)
|
|
|
|
Clear contents of region.
|
|
|
|
arguments
|
|
1 region: target region
|
|
|
|
|
|
# int regex_region_resize(RegRegion* region, int n)
|
|
|
|
Resize group range area of region.
|
|
|
|
normal return: REG_NORMAL
|
|
|
|
arguments
|
|
1 region: target region
|
|
2 n: new size
|
|
|
|
|
|
# int regex_name_to_group_numbers(regex_t* reg, UChar* name, UChar* name_end,
|
|
int** num_list)
|
|
|
|
Return group number list of name.
|
|
Named subexp is defined by (?<name>....).
|
|
|
|
normal return: number of groups for the name.
|
|
(ex. /(?<x>..)...(?<x>..)/ ==> 2)
|
|
name not found: -1
|
|
|
|
arguments
|
|
1 reg: regex object.
|
|
2 name: subexp-name.
|
|
3 name_end: terminate address of subexp-name.
|
|
4 num_list: return list of group number.
|
|
|
|
|
|
# int regex_foreach_names(regex_t* reg, int (*func)(UChar*,int,int*,void*),
|
|
void* arg)
|
|
|
|
Iterate function call for all names.
|
|
|
|
normal return: 0
|
|
error: func's return value.
|
|
|
|
arguments
|
|
1 reg: regex object.
|
|
2 func: called function.
|
|
func(name, <number of groups>, <group number's list>, arg);
|
|
if func return non 0 value, iteration is stopped.
|
|
3 arg: argument for func.
|
|
|
|
|
|
# UChar* regex_get_prev_char_head(RegCharEncoding code, UChar* start, UChar* s)
|
|
|
|
Return previous character head address.
|
|
|
|
arguments
|
|
1 code: character encoding
|
|
2 start: string address
|
|
3 s: target address of string
|
|
|
|
|
|
# UChar* regex_get_left_adjust_char_head(RegCharEncoding code,
|
|
UChar* start, UChar* s)
|
|
|
|
Return left-adjusted head address of a character.
|
|
|
|
arguments
|
|
1 code: character encoding
|
|
2 start: string address
|
|
3 s: target address of string
|
|
|
|
|
|
# UChar* regex_get_right_adjust_char_head(RegCharEncoding code,
|
|
UChar* start, UChar* s)
|
|
|
|
Return right-adjusted head address of a character.
|
|
|
|
arguments
|
|
1 code: character encoding
|
|
2 start: string address
|
|
3 s: target address of string
|
|
|
|
|
|
# int regex_set_default_syntax(RegSyntaxType* syntax)
|
|
|
|
Set default syntax.
|
|
|
|
arguments
|
|
1 syntax: pointer to pattern syntax definition.
|
|
|
|
|
|
# void regex_set_default_trans_table(UChar* table)
|
|
|
|
Set default case transformation table.
|
|
|
|
arguments
|
|
1 table: case transformation table
|
|
|
|
(* this function will be obsoleted in future version)
|
|
|
|
|
|
# int regex_end(void)
|
|
|
|
The use of this library is finished.
|
|
|
|
normal return: REG_NORMAL
|
|
|
|
|
|
# const char* regex_version(void)
|
|
|
|
Return version string. (ex. "1.8.6")
|
|
|
|
// END
|