#include <stdlib.h>
#include <algorithm>
#include <array>
#include <bitset>
#include <cassert>
#include <cstdint>
#include <cstdio>
#include <cstring>
#include <iterator>
#include <map>
#include <vector>
#include "m_string.h"
#include "my_byteorder.h"
#include "my_compiler.h"
#include "mysql/my_loglevel.h"
#include "mysql/strings/m_ctype.h"
#include "mysys_err.h"
#include "string_with_len.h"
#include "strings/m_ctype_internals.h"
#include "strings/mb_wc.h"
#include "strings/str_uca_type.h"
#include "strings/uca900_data.h"
#include "strings/uca900_ja_data.h"
#include "strings/uca900_zh_data.h"
#include "strings/uca_data.h"
#include "template_utils.h"

Classes
class	my_uca_scanner
	Unicode Collation Algorithm: Collation element (weight) scanner, for consequent scan of collations weights from a string. More...

struct	uca_scanner_any< Mb_wc >

class	uca_scanner_900< Mb_wc, LEVELS_FOR_COMPARE >

struct	trie_node_cmp

struct	MY_COLL_LEXEM

struct	MY_COLL_RULE

struct	MY_COLL_RULES

struct	MY_COLL_RULE_PARSER

Macros
#define	HANGUL_JAMO_MAX_LENGTH 3

#define	MY_UCA_MAX_EXPANSION 6 /* Maximum expansion length */

#define	MY_CS_UTF8MB3_UCA_FLAGS (MY_CS_COMPILED \| MY_CS_STRNXFRM \| MY_CS_UNICODE)

#define	MY_CS_UTF8MB4_UCA_FLAGS (MY_CS_COMPILED \| MY_CS_STRNXFRM \| MY_CS_UNICODE \| MY_CS_UNICODE_SUPPLEMENT)

#define	MY_CS_UTF32_UCA_FLAGS

#define	MY_CS_UTF16_UCA_FLAGS (MY_CS_COMPILED \| MY_CS_STRNXFRM \| MY_CS_UNICODE \| MY_CS_NONASCII)

Typedefs
typedef enum my_coll_lexem_num_en	my_coll_lexem_num

Enumerations
enum	my_coll_lexem_num_en { MY_COLL_LEXEM_EOF = 0 , MY_COLL_LEXEM_SHIFT = 1 , MY_COLL_LEXEM_RESET = 4 , MY_COLL_LEXEM_CHAR = 5 , MY_COLL_LEXEM_ERROR = 6 , MY_COLL_LEXEM_OPTION = 7 , MY_COLL_LEXEM_EXTEND = 8 , MY_COLL_LEXEM_CONTEXT = 9 }

enum	my_coll_shift_method { my_shift_method_simple = 0 , my_shift_method_expand }

Functions
static void	my_uca_add_contraction_flag (MY_UCA_INFO::flags_type *flags, my_wc_t wc, int flag)
	Mark a code point as a contraction part. More...

static bool	my_uca_have_contractions (const MY_UCA_INFO *uca)
	Check if UCA level data has contractions. More...

static std::vector< MY_CONTRACTION >::const_iterator	find_contraction_part_in_trie (const std::vector< MY_CONTRACTION > &cont_nodes, my_wc_t ch)

static std::vector< MY_CONTRACTION >::iterator	find_contraction_part_in_trie (std::vector< MY_CONTRACTION > &cont_nodes, my_wc_t ch)

const uint16_t *	my_uca_contraction2_weight (const std::vector< MY_CONTRACTION > *cont_nodes, my_wc_t wc1, my_wc_t wc2)
	Find a contraction consisting of two code points and return its weight array. More...

static bool	my_uca_can_be_previous_context_head (const MY_UCA_INFO::flags_type *flags, my_wc_t wc)
	Check if a code point can be previous context head. More...

static bool	my_uca_can_be_previous_context_tail (const MY_UCA_INFO::flags_type *flags, my_wc_t wc)
	Check if a code point can be previous context tail. More...

static const uint16_t *	my_uca_contraction_weight (const std::vector< MY_CONTRACTION > cont_nodes, const my_wc_t wc, size_t len)
	Check if a string is a contraction of exactly the given length, and return its weight array on success. More...

static size_t	my_wstrnlen (my_wc_t *s, size_t maxlen)
	Return length of a 0-terminated wide string, analogous to strnlen(). More...

static int	my_decompose_hangul_syllable (my_wc_t syllable, my_wc_t *jamo)
	Check if a code point is Hangul syllable. More...

static uint16_t	change_zh_implicit (uint16_t weight)

static bool	is_hiragana_char (my_wc_t wc)

static bool	is_katakana_char (my_wc_t wc)

static bool	is_katakana_iteration (my_wc_t wc)

static bool	is_hiragana_iteration (my_wc_t wc)

static bool	is_ja_length_mark (my_wc_t wc)

static bool	is_tertiary_weight_upper_case (uint16_t weight)

template<class Scanner , int LEVELS_FOR_COMPARE, class Mb_wc >
static int	my_strnncoll_uca (const CHARSET_INFO cs, const Mb_wc mb_wc, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen, bool t_is_prefix)

static int	my_space_weight (const CHARSET_INFO *cs)

static uint16_t *	my_char_weight_addr (MY_UCA_INFO *uca, my_wc_t wc)
	Helper function: Find address of weights of the given code point. More...

static uint16_t *	my_char_weight_addr_900 (MY_UCA_INFO *uca, my_wc_t wc)
	Helper function: Find address of weights of the given code point, for UCA 9.0.0 format. More...

template<class Mb_wc >
static int	my_strnncollsp_uca (const CHARSET_INFO cs, Mb_wc mb_wc, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen)

template<class Mb_wc >
static void	my_hash_sort_uca (const CHARSET_INFO cs, Mb_wc mb_wc, const uint8_t s, size_t slen, uint64_t n1, uint64_t n2)

template<class Mb_wc >
static size_t	my_strnxfrm_uca (const CHARSET_INFO cs, Mb_wc mb_wc, uint8_t dst, size_t dstlen, unsigned num_codepoints, const uint8_t *src, size_t srclen, unsigned flags)

static int	my_uca_charcmp_900 (const CHARSET_INFO *cs, my_wc_t wc1, my_wc_t wc2)

static int	my_uca_charcmp (const CHARSET_INFO *cs, my_wc_t wc1, my_wc_t wc2)

static int	my_wildcmp_uca_impl (const CHARSET_INFO cs, const char str, const char str_end, const char wildstr, const char *wildend, int escape, int w_one, int w_many, int recurse_level)

static int	my_strcasecmp_uca (const CHARSET_INFO cs, const char s, const char *t)

static int	my_wildcmp_uca (const CHARSET_INFO cs, const char str, const char str_end, const char wildstr, const char *wildend, int escape, int w_one, int w_many)

static const char *	my_coll_lexem_num_to_str (my_coll_lexem_num term)
	Convert collation customization lexem to string, for nice error reporting. More...

static void	my_coll_lexem_init (MY_COLL_LEXEM lexem, const char str, const char *str_end)

static int	lex_cmp (MY_COLL_LEXEM lexem, const char pattern, size_t patternlen)
	Compare lexem to string with length. More...

static void	my_coll_lexem_print_error (MY_COLL_LEXEM lexem, char errstr, size_t errsize, const char txt, const char col_name)

static int	ch2x (int ch)

static my_coll_lexem_num	my_coll_lexem_next (MY_COLL_LEXEM *lexem)

static size_t	my_coll_rule_reset_length (MY_COLL_RULE *r)
	Return length of the "reset" string of a rule. More...

static size_t	my_coll_rule_shift_length (MY_COLL_RULE *r)
	Return length of the "shift" string of a rule. More...

static int	my_coll_rule_expand (my_wc_t *wc, size_t limit, my_wc_t code)
	Append new character to the end of a 0-terminated wide string. More...

static void	my_coll_rule_reset (MY_COLL_RULE *r)
	Initialize collation customization rule. More...

static int	my_coll_rules_realloc (MY_COLL_RULES *rules, size_t n)
	Realloc rule array to a new size. More...

static int	my_coll_rules_add (MY_COLL_RULES rules, MY_COLL_RULE rule)
	Append one new rule to a rule array. More...

static void	my_coll_rule_shift_at_level (MY_COLL_RULE *r, int level)
	Apply difference at level. More...

static MY_COLL_LEXEM *	my_coll_parser_curr (MY_COLL_RULE_PARSER *p)
	Current parser token. More...

static MY_COLL_LEXEM *	my_coll_parser_next (MY_COLL_RULE_PARSER *p)
	Next parser token, to look ahead. More...

static int	my_coll_parser_scan (MY_COLL_RULE_PARSER *p)
	Scan one token from the input stream. More...

static void	my_coll_parser_init (MY_COLL_RULE_PARSER p, MY_COLL_RULES rules, const char str, const char str_end)
	Initialize collation customization parser. More...

static int	my_coll_parser_expected_error (MY_COLL_RULE_PARSER *p, my_coll_lexem_num term)
	Display error when an unexpected token found. More...

static int	my_coll_parser_too_long_error (MY_COLL_RULE_PARSER p, const char name)
	Display error when a too long character sequence is met. More...

static int	my_coll_parser_scan_term (MY_COLL_RULE_PARSER *p, my_coll_lexem_num term)
	Scan the given lexem from input stream, or display "expected" error. More...

static int	my_coll_parser_scan_setting (MY_COLL_RULE_PARSER *p)
	Scan a collation setting in brakets, for example UCA version. More...

static int	my_coll_parser_scan_settings (MY_COLL_RULE_PARSER *p)
	Scan multiple collation settings. More...

static int	my_coll_parser_scan_reset_before (MY_COLL_RULE_PARSER *p)
	Scan [before xxx] reset option. More...

static int	my_coll_parser_scan_logical_position (MY_COLL_RULE_PARSER p, my_wc_t pwc, size_t limit)
	Scan logical position and add to the wide string. More...

static int	my_coll_parser_scan_character_list (MY_COLL_RULE_PARSER p, my_wc_t pwc, size_t limit, const char *name)
	Scan character list. More...

static int	my_coll_parser_scan_reset_sequence (MY_COLL_RULE_PARSER *p)
	Scan reset sequence. More...

static int	my_coll_parser_scan_shift_sequence (MY_COLL_RULE_PARSER *p)
	Scan shift sequence. More...

static int	my_coll_parser_scan_shift (MY_COLL_RULE_PARSER *p)
	Scan shift operator. More...

static int	my_coll_parser_scan_rule (MY_COLL_RULE_PARSER *p)
	Scan one rule: reset followed by a number of shifts. More...

static int	my_coll_parser_exec (MY_COLL_RULE_PARSER *p)
	Scan collation customization: settings followed by rules. More...

static int	my_coll_rule_parse (MY_COLL_RULES rules, const char str, const char str_end, const char col_name)

static void	spread_case_mask (uint16_t *to, size_t to_stride, size_t tailored_ce_cnt, uint16_t case_mask)

static void	change_weight_if_case_first (CHARSET_INFO cs, const MY_UCA_INFO dst, MY_COLL_RULE r, uint16_t to, size_t to_stride, size_t curr_len, size_t tailored_ce_cnt)

static size_t	my_char_weight_put_900 (MY_UCA_INFO dst, uint16_t to, size_t to_stride, size_t to_length, uint16_t to_num_ce, const MY_COLL_RULE rule, size_t base_len)

static size_t	my_char_weight_put (MY_UCA_INFO dst, uint16_t to, size_t to_stride, size_t to_length, uint16_t to_num_ce, const MY_COLL_RULE rule, size_t base_len, enum_uca_ver uca_ver)
	Helper function: Copies UCA weights for a given "unsigned" string to the given location. More...

static bool	my_uca_copy_page (CHARSET_INFO cs, MY_CHARSET_LOADER loader, const MY_UCA_INFO src, MY_UCA_INFO dst, size_t page)
	Alloc new page and copy the default UCA weights. More...

static bool	apply_primary_shift_900 (MY_COLL_RULES rules, MY_COLL_RULE r, uint16_t to, size_t to_stride, size_t nweights, uint16_t const last_weight_ptr)

static bool	apply_secondary_shift_900 (MY_COLL_RULES rules, MY_COLL_RULE r, uint16_t to, size_t to_stride, size_t nweights, uint16_t const last_weight_ptr)

static bool	apply_tertiary_shift_900 (MY_COLL_RULES rules, MY_COLL_RULE r, uint16_t to, size_t to_stride, size_t nweights, uint16_t const last_weight_ptr)

static bool	apply_shift_900 (MY_COLL_RULES rules, MY_COLL_RULE r, uint16_t *to, size_t to_stride, size_t nweights)

static bool	apply_shift (MY_COLL_RULES rules, MY_COLL_RULE r, int level, uint16_t *to, size_t to_stride, size_t nweights)

static MY_CONTRACTION *	add_contraction_to_trie (std::vector< MY_CONTRACTION > cont_nodes, MY_COLL_RULE r)

static bool	apply_one_rule (CHARSET_INFO cs, MY_COLL_RULES rules, MY_COLL_RULE r, int level, MY_UCA_INFO dst)

static int	check_rules (const MY_COLL_RULES rules, const MY_UCA_INFO dst, const MY_UCA_INFO *src)
	Check if collation rules are valid, i.e. More...

static void	synthesize_lengths_900 (uint8_t lengths, const uint16_t const *weights, unsigned npages)

static void	copy_ja_han_pages (const CHARSET_INFO cs, MY_UCA_INFO dst)

static void	copy_zh_han_pages (MY_UCA_INFO dst, MY_CHARSET_LOADER loader)

static my_wc_t	convert_implicit_to_ch (uint16_t first, uint16_t second)

static void	modify_all_zh_pages (Reorder_param reorder_param, MY_UCA_INFO dst, int npages)

static bool	init_weight_level (CHARSET_INFO cs, MY_COLL_RULES rules, int level, MY_UCA_INFO dst, const MY_UCA_INFO src)

static bool	my_comp_in_rulelist (const MY_COLL_RULES *rules, my_wc_t wc)
	Check whether the composition character is already in rule list. More...

static bool	my_compchar_is_normal_char (unsigned dec_ind)
	Check whether a composition character in the decomposition list is a normal character. More...

static bool	my_compchar_is_normal_char (const Unidata_decomp *decomp)

static Unidata_decomp *	get_decomposition (my_wc_t ch)

static Combining_mark *	my_find_combining_mark (my_wc_t code)

static bool	my_is_inheritance_of_origin (const my_wc_t origin_dec, const my_wc_t dec_codes, my_wc_t *dec_diff)
	Check if a list of combining marks contains the whole list of origin decomposed combining marks. More...

static int	my_coll_add_inherit_rules (MY_COLL_RULES rules, MY_COLL_RULE r, const Unidata_decomp decomp_rec, std::bitset< array_elements(uni_dec)> comp_added)
	Add new rules recersively if one rule's characters are in decomposition list. More...

static bool	combining_mark_in_rulelist (const my_wc_t dec_codes, const MY_COLL_RULE r_start, const MY_COLL_RULE *r_end)

static int	add_normalization_rules (const CHARSET_INFO cs, MY_COLL_RULES rules)

static int	my_coll_check_rule_and_inherit (const CHARSET_INFO cs, MY_COLL_RULES rules)
	For every rule in rule list, check and add new rules if it is in decomposition list. More...

static void	my_set_weight_rec (Reorder_wt_rec(&wt_rec)[2 *UCA_MAX_CHAR_GRP], int rec_ind, uint16_t old_begin, uint16_t old_end, uint16_t new_begin, uint16_t new_end)
	Helper function to store weight boundary values. More...

static void	my_calc_char_grp_param (const CHARSET_INFO *cs, int &rec_ind)
	Calculate the reorder parameters for the character groups. More...

static void	my_calc_char_grp_gap_param (CHARSET_INFO *cs, int &rec_ind)
	Calculate the reorder parameters for the gap between character groups. More...

static int	my_prepare_reorder (CHARSET_INFO *cs)
	Prepare reorder parameters. More...

static void	adjust_japanese_weight (CHARSET_INFO *cs, int rec_ind)

static bool	my_prepare_coll_param (CHARSET_INFO cs, MY_COLL_RULES rules)
	Prepare parametric tailoring, like reorder, etc. More...

static bool	create_tailoring (CHARSET_INFO cs, MY_CHARSET_LOADER loader, MY_CHARSET_ERRMSG *errmsg)

static void	my_coll_uninit_uca (CHARSET_INFO cs, MY_CHARSET_LOADER loader)

static bool	my_coll_init_uca (CHARSET_INFO cs, MY_CHARSET_LOADER loader, MY_CHARSET_ERRMSG *errmsg)

static int	my_strnncoll_any_uca (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen, bool t_is_prefix)

static int	my_strnncollsp_any_uca (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen)

static void	my_hash_sort_any_uca (const CHARSET_INFO cs, const uint8_t s, size_t slen, uint64_t n1, uint64_t n2)

static size_t	my_strnxfrm_any_uca (const CHARSET_INFO cs, uint8_t dst, size_t dstlen, unsigned num_codepoints, const uint8_t *src, size_t srclen, unsigned flags)

static int	my_strnncoll_uca_900 (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen, bool t_is_prefix)

static int	my_strnncollsp_uca_900 (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen)

template<class Mb_wc , int LEVELS_FOR_COMPARE>
static void	my_hash_sort_uca_900_tmpl (const CHARSET_INFO cs, const Mb_wc mb_wc, const uint8_t s, size_t slen, uint64_t *n1)

static void	my_hash_sort_uca_900 (const CHARSET_INFO cs, const uint8_t s, size_t slen, uint64_t n1, uint64_t )

bool	my_propagate_uca_900 (const CHARSET_INFO cs, const uint8_t str, size_t length)

template<class Mb_wc , int LEVELS_FOR_COMPARE>
static size_t	my_strnxfrm_uca_900_tmpl (const CHARSET_INFO cs, const Mb_wc mb_wc, uint8_t dst, size_t dstlen, const uint8_t *src, size_t srclen, unsigned flags)

static size_t	my_strnxfrm_uca_900 (const CHARSET_INFO cs, uint8_t dst, size_t dstlen, unsigned num_codepoints, const uint8_t *src, size_t srclen, unsigned flags)

static size_t	my_strnxfrmlen_uca_900 (const CHARSET_INFO *cs, size_t len)

static int	my_strnncoll_ucs2_uca (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen, bool t_is_prefix)

static int	my_strnncollsp_ucs2_uca (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen)

static void	my_hash_sort_ucs2_uca (const CHARSET_INFO cs, const uint8_t s, size_t slen, uint64_t n1, uint64_t n2)

static size_t	my_strnxfrm_ucs2_uca (const CHARSET_INFO cs, uint8_t dst, size_t dstlen, unsigned num_codepoints, const uint8_t *src, size_t srclen, unsigned flags)

static size_t	my_strnxfrm_utf8mb4_0900_bin (const CHARSET_INFO cs, uint8_t dst, size_t dstlen, unsigned nweights, const uint8_t *src, size_t srclen, unsigned flags)

static int	my_strnncollsp_utf8mb4_0900_bin (const CHARSET_INFO cs, const uint8_t s, size_t slen, const uint8_t *t, size_t tlen)

Variables
MY_UCA_INFO	my_uca_v400

MY_UCA_INFO	my_uca_v520

static const char	german2 []

static const char	icelandic []

static const char	latvian []

static const char	romanian []

static const char	slovenian []

static const char	polish []

static const char	estonian []

static const char	spanish [] = "& N < \\u00F1 <<< \\u00D1 "

static const char	swedish []

static const char	turkish []

static const char	czech []

static const char	danish []

static const char	lithuanian []

static const char	slovak []

static const char	spanish2 []

static const char	roman []

static const char	persian []

static const char	esperanto []

static const char	hungarian []

static const char	croatian []

static const char	sinhala []

static const char	vietnamese []

static const char	de_pb_cldr_30 []

static const char	is_cldr_30 []

static const char	lv_cldr_30 []

static const char	ro_cldr_30 []

static const char	sl_cldr_30 []

static const char	pl_cldr_30 []

static const char	et_cldr_30 []

static const char	sv_cldr_30 []

static const char	tr_cldr_30 []

static const char	cs_cldr_30 []

static const char	da_cldr_30 []

static Coll_param	da_coll_param = {nullptr, false, CASE_FIRST_UPPER}

static Coll_param	no_coll_param = {nullptr, false, CASE_FIRST_OFF}

static const char	lt_cldr_30 []

static const char	sk_cldr_30 []

static const char	es_trad_cldr_30 []

static const char	hu_cldr_30 []

static const char	hr_cldr_30 []

static Reorder_param	hr_reorder_param

static Coll_param	hr_coll_param = {&hr_reorder_param, false, CASE_FIRST_OFF}

static const char	vi_cldr_30 []

static Coll_param	vi_coll_param = {nullptr, true, CASE_FIRST_OFF}

static Reorder_param	ja_reorder_param

static Coll_param	ja_coll_param

static Reorder_param	zh_reorder_param

static Coll_param	zh_coll_param = {&zh_reorder_param, false, CASE_FIRST_OFF}

static Reorder_param	ru_reorder_param

static Coll_param	ru_coll_param

static constexpr uint16_t	nochar [] = {0, 0}

MY_COLLATION_HANDLER	my_collation_ucs2_uca_handler

CHARSET_INFO	my_charset_ucs2_unicode_ci

CHARSET_INFO	my_charset_ucs2_icelandic_uca_ci

CHARSET_INFO	my_charset_ucs2_latvian_uca_ci

CHARSET_INFO	my_charset_ucs2_romanian_uca_ci

CHARSET_INFO	my_charset_ucs2_slovenian_uca_ci

CHARSET_INFO	my_charset_ucs2_polish_uca_ci

CHARSET_INFO	my_charset_ucs2_estonian_uca_ci

CHARSET_INFO	my_charset_ucs2_spanish_uca_ci

CHARSET_INFO	my_charset_ucs2_swedish_uca_ci

CHARSET_INFO	my_charset_ucs2_turkish_uca_ci

CHARSET_INFO	my_charset_ucs2_czech_uca_ci

CHARSET_INFO	my_charset_ucs2_danish_uca_ci

CHARSET_INFO	my_charset_ucs2_lithuanian_uca_ci

CHARSET_INFO	my_charset_ucs2_slovak_uca_ci

CHARSET_INFO	my_charset_ucs2_spanish2_uca_ci

CHARSET_INFO	my_charset_ucs2_roman_uca_ci

CHARSET_INFO	my_charset_ucs2_persian_uca_ci

CHARSET_INFO	my_charset_ucs2_esperanto_uca_ci

CHARSET_INFO	my_charset_ucs2_hungarian_uca_ci

CHARSET_INFO	my_charset_ucs2_sinhala_uca_ci

CHARSET_INFO	my_charset_ucs2_german2_uca_ci

CHARSET_INFO	my_charset_ucs2_croatian_uca_ci

CHARSET_INFO	my_charset_ucs2_unicode_520_ci

CHARSET_INFO	my_charset_ucs2_vietnamese_ci

MY_COLLATION_HANDLER	my_collation_any_uca_handler

MY_COLLATION_HANDLER	my_collation_uca_900_handler

static const uint8_t	ctype_utf8 []

MY_CHARSET_HANDLER	my_charset_utf8mb3_handler

CHARSET_INFO	my_charset_utf8mb3_unicode_ci

CHARSET_INFO	my_charset_utf8mb3_icelandic_uca_ci

CHARSET_INFO	my_charset_utf8mb3_latvian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_romanian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_slovenian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_polish_uca_ci

CHARSET_INFO	my_charset_utf8mb3_estonian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_spanish_uca_ci

CHARSET_INFO	my_charset_utf8mb3_swedish_uca_ci

CHARSET_INFO	my_charset_utf8mb3_turkish_uca_ci

CHARSET_INFO	my_charset_utf8mb3_czech_uca_ci

CHARSET_INFO	my_charset_utf8mb3_danish_uca_ci

CHARSET_INFO	my_charset_utf8mb3_lithuanian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_slovak_uca_ci

CHARSET_INFO	my_charset_utf8mb3_spanish2_uca_ci

CHARSET_INFO	my_charset_utf8mb3_roman_uca_ci

CHARSET_INFO	my_charset_utf8mb3_persian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_esperanto_uca_ci

CHARSET_INFO	my_charset_utf8mb3_hungarian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_sinhala_uca_ci

CHARSET_INFO	my_charset_utf8mb3_german2_uca_ci

CHARSET_INFO	my_charset_utf8mb3_croatian_uca_ci

CHARSET_INFO	my_charset_utf8mb3_unicode_520_ci

CHARSET_INFO	my_charset_utf8mb3_vietnamese_ci

MY_CHARSET_HANDLER	my_charset_utf8mb4_handler

CHARSET_INFO	my_charset_utf8mb4_unicode_ci

CHARSET_INFO	my_charset_utf8mb4_icelandic_uca_ci

CHARSET_INFO	my_charset_utf8mb4_latvian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_romanian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_slovenian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_polish_uca_ci

CHARSET_INFO	my_charset_utf8mb4_estonian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_spanish_uca_ci

CHARSET_INFO	my_charset_utf8mb4_swedish_uca_ci

CHARSET_INFO	my_charset_utf8mb4_turkish_uca_ci

CHARSET_INFO	my_charset_utf8mb4_czech_uca_ci

CHARSET_INFO	my_charset_utf8mb4_danish_uca_ci

CHARSET_INFO	my_charset_utf8mb4_lithuanian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_slovak_uca_ci

CHARSET_INFO	my_charset_utf8mb4_spanish2_uca_ci

CHARSET_INFO	my_charset_utf8mb4_roman_uca_ci

CHARSET_INFO	my_charset_utf8mb4_persian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_esperanto_uca_ci

CHARSET_INFO	my_charset_utf8mb4_hungarian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_sinhala_uca_ci

CHARSET_INFO	my_charset_utf8mb4_german2_uca_ci

CHARSET_INFO	my_charset_utf8mb4_croatian_uca_ci

CHARSET_INFO	my_charset_utf8mb4_unicode_520_ci

CHARSET_INFO	my_charset_utf8mb4_vietnamese_ci

MY_COLLATION_HANDLER	my_collation_utf32_uca_handler

MY_CHARSET_HANDLER	my_charset_utf32_handler

CHARSET_INFO	my_charset_utf32_unicode_ci

CHARSET_INFO	my_charset_utf32_icelandic_uca_ci

CHARSET_INFO	my_charset_utf32_latvian_uca_ci

CHARSET_INFO	my_charset_utf32_romanian_uca_ci

CHARSET_INFO	my_charset_utf32_slovenian_uca_ci

CHARSET_INFO	my_charset_utf32_polish_uca_ci

CHARSET_INFO	my_charset_utf32_estonian_uca_ci

CHARSET_INFO	my_charset_utf32_spanish_uca_ci

CHARSET_INFO	my_charset_utf32_swedish_uca_ci

CHARSET_INFO	my_charset_utf32_turkish_uca_ci

CHARSET_INFO	my_charset_utf32_czech_uca_ci

CHARSET_INFO	my_charset_utf32_danish_uca_ci

CHARSET_INFO	my_charset_utf32_lithuanian_uca_ci

CHARSET_INFO	my_charset_utf32_slovak_uca_ci

CHARSET_INFO	my_charset_utf32_spanish2_uca_ci

CHARSET_INFO	my_charset_utf32_roman_uca_ci

CHARSET_INFO	my_charset_utf32_persian_uca_ci

CHARSET_INFO	my_charset_utf32_esperanto_uca_ci

CHARSET_INFO	my_charset_utf32_hungarian_uca_ci

CHARSET_INFO	my_charset_utf32_sinhala_uca_ci

CHARSET_INFO	my_charset_utf32_german2_uca_ci

CHARSET_INFO	my_charset_utf32_croatian_uca_ci

CHARSET_INFO	my_charset_utf32_unicode_520_ci

CHARSET_INFO	my_charset_utf32_vietnamese_ci

MY_COLLATION_HANDLER	my_collation_utf16_uca_handler

MY_CHARSET_HANDLER	my_charset_utf16_handler

CHARSET_INFO	my_charset_utf16_unicode_ci

CHARSET_INFO	my_charset_utf16_icelandic_uca_ci

CHARSET_INFO	my_charset_utf16_latvian_uca_ci

CHARSET_INFO	my_charset_utf16_romanian_uca_ci

CHARSET_INFO	my_charset_utf16_slovenian_uca_ci

CHARSET_INFO	my_charset_utf16_polish_uca_ci

CHARSET_INFO	my_charset_utf16_estonian_uca_ci

CHARSET_INFO	my_charset_utf16_spanish_uca_ci

CHARSET_INFO	my_charset_utf16_swedish_uca_ci

CHARSET_INFO	my_charset_utf16_turkish_uca_ci

CHARSET_INFO	my_charset_utf16_czech_uca_ci

CHARSET_INFO	my_charset_utf16_danish_uca_ci

CHARSET_INFO	my_charset_utf16_lithuanian_uca_ci

CHARSET_INFO	my_charset_utf16_slovak_uca_ci

CHARSET_INFO	my_charset_utf16_spanish2_uca_ci

CHARSET_INFO	my_charset_utf16_roman_uca_ci

CHARSET_INFO	my_charset_utf16_persian_uca_ci

CHARSET_INFO	my_charset_utf16_esperanto_uca_ci

CHARSET_INFO	my_charset_utf16_hungarian_uca_ci

CHARSET_INFO	my_charset_utf16_sinhala_uca_ci

CHARSET_INFO	my_charset_utf16_german2_uca_ci

CHARSET_INFO	my_charset_utf16_croatian_uca_ci

CHARSET_INFO	my_charset_utf16_unicode_520_ci

CHARSET_INFO	my_charset_utf16_vietnamese_ci

MY_COLLATION_HANDLER	my_collation_gb18030_uca_handler

static const uint8_t	ctype_gb18030 [257]
	The array used for "type of characters" bit mask for each character. More...

MY_CHARSET_HANDLER	my_charset_gb18030_uca_handler

CHARSET_INFO	my_charset_gb18030_unicode_520_ci

CHARSET_INFO	my_charset_utf8mb4_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_de_pb_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_is_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_lv_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_ro_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_sl_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_pl_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_et_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_es_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_sv_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_tr_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_cs_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_da_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_lt_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_sk_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_es_trad_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_la_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_eo_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_hu_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_hr_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_vi_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_de_pb_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_is_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_lv_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_ro_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_sl_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_pl_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_et_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_es_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_sv_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_tr_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_cs_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_da_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_lt_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_sk_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_es_trad_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_la_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_eo_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_hu_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_hr_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_vi_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_ja_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_ja_0900_as_cs_ks

CHARSET_INFO	my_charset_utf8mb4_0900_as_ci

CHARSET_INFO	my_charset_utf8mb4_ru_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_ru_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_zh_0900_as_cs

static MY_COLLATION_HANDLER	my_collation_utf8mb4_0900_bin_handler

CHARSET_INFO	my_charset_utf8mb4_0900_bin

CHARSET_INFO	my_charset_utf8mb4_nb_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_nb_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_nn_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_nn_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_sr_latn_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_sr_latn_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_bs_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_bs_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_bg_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_bg_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_gl_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_gl_0900_as_cs

CHARSET_INFO	my_charset_utf8mb4_mn_cyrl_0900_ai_ci

CHARSET_INFO	my_charset_utf8mb4_mn_cyrl_0900_as_cs

Macro Definition Documentation

◆ HANGUL_JAMO_MAX_LENGTH

#define HANGUL_JAMO_MAX_LENGTH 3

◆ MY_CS_UTF16_UCA_FLAGS

#define MY_CS_UTF16_UCA_FLAGS (MY_CS_COMPILED | MY_CS_STRNXFRM | MY_CS_UNICODE | MY_CS_NONASCII)

◆ MY_CS_UTF32_UCA_FLAGS

#define MY_CS_UTF32_UCA_FLAGS

Value:

(MY_CS_COMPILED | MY_CS_STRNXFRM | MY_CS_UNICODE | \

MY_CS_UNICODE_SUPPLEMENT | MY_CS_NONASCII)

MY_CS_NONASCII

static constexpr uint32_t MY_CS_NONASCII

Definition: m_ctype.h:142

MY_CS_STRNXFRM

static constexpr uint32_t MY_CS_STRNXFRM

Definition: m_ctype.h:124

MY_CS_UNICODE

static constexpr uint32_t MY_CS_UNICODE

Definition: m_ctype.h:130

MY_CS_COMPILED

static constexpr uint32_t MY_CS_COMPILED

Definition: m_ctype.h:112

◆ MY_CS_UTF8MB3_UCA_FLAGS

#define MY_CS_UTF8MB3_UCA_FLAGS (MY_CS_COMPILED | MY_CS_STRNXFRM | MY_CS_UNICODE)

◆ MY_CS_UTF8MB4_UCA_FLAGS

#define MY_CS_UTF8MB4_UCA_FLAGS (MY_CS_COMPILED | MY_CS_STRNXFRM | MY_CS_UNICODE | MY_CS_UNICODE_SUPPLEMENT)

◆ MY_UCA_MAX_EXPANSION

#define MY_UCA_MAX_EXPANSION 6 /* Maximum expansion length */

Typedef Documentation

◆ my_coll_lexem_num

typedef enum my_coll_lexem_num_en my_coll_lexem_num

Enumeration Type Documentation

◆ my_coll_lexem_num_en

enum my_coll_lexem_num_en

Enumerator
MY_COLL_LEXEM_EOF
MY_COLL_LEXEM_SHIFT
MY_COLL_LEXEM_RESET
MY_COLL_LEXEM_CHAR
MY_COLL_LEXEM_ERROR
MY_COLL_LEXEM_OPTION
MY_COLL_LEXEM_EXTEND
MY_COLL_LEXEM_CONTEXT

◆ my_coll_shift_method

enum my_coll_shift_method

Enumerator
my_shift_method_simple
my_shift_method_expand

Function Documentation

◆ add_contraction_to_trie()

static MY_CONTRACTION * add_contraction_to_trie	(	std::vector< MY_CONTRACTION > *	cont_nodes,
		MY_COLL_RULE *	r
	)

static

◆ add_normalization_rules()

static int add_normalization_rules	(	const CHARSET_INFO *	cs,
		MY_COLL_RULES *	rules
	)

static

◆ adjust_japanese_weight()

static void adjust_japanese_weight	(	CHARSET_INFO *	cs,
		int	rec_ind
	)

static

◆ apply_one_rule()

static bool apply_one_rule	(	CHARSET_INFO *	cs,
		MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		int	level,
		MY_UCA_INFO *	dst
	)

static

◆ apply_primary_shift_900()

static bool apply_primary_shift_900	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		uint16_t *	to,
		size_t	to_stride,
		size_t	nweights,
		uint16_t *const	last_weight_ptr
	)

static

◆ apply_secondary_shift_900()

static bool apply_secondary_shift_900	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		uint16_t *	to,
		size_t	to_stride,
		size_t	nweights,
		uint16_t *const	last_weight_ptr
	)

static

◆ apply_shift()

static bool apply_shift	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		int	level,
		uint16_t *	to,
		size_t	to_stride,
		size_t	nweights
	)

static

◆ apply_shift_900()

static bool apply_shift_900	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		uint16_t *	to,
		size_t	to_stride,
		size_t	nweights
	)

static

◆ apply_tertiary_shift_900()

static bool apply_tertiary_shift_900	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		uint16_t *	to,
		size_t	to_stride,
		size_t	nweights,
		uint16_t *const	last_weight_ptr
	)

static

◆ ch2x()

static int ch2x ( int ch )

static

◆ change_weight_if_case_first()

static void change_weight_if_case_first	(	CHARSET_INFO *	cs,
		const MY_UCA_INFO *	dst,
		MY_COLL_RULE *	r,
		uint16_t *	to,
		size_t	to_stride,
		size_t	curr_len,
		size_t	tailored_ce_cnt
	)

static

◆ change_zh_implicit()

static uint16_t change_zh_implicit ( uint16_t weight )

static

◆ check_rules()

static int check_rules	(	const MY_COLL_RULES *	rules,
		const MY_UCA_INFO *	dst,
		const MY_UCA_INFO *	src
	)

static

Check if collation rules are valid, i.e.

characters are not outside of the collation supported range.

◆ combining_mark_in_rulelist()

static bool combining_mark_in_rulelist	(	const my_wc_t *	dec_codes,
		const MY_COLL_RULE *	r_start,
		const MY_COLL_RULE *	r_end
	)

static

◆ convert_implicit_to_ch()

static my_wc_t convert_implicit_to_ch	(	uint16_t	first,
		uint16_t	second
	)

inlinestatic

◆ copy_ja_han_pages()

static void copy_ja_han_pages	(	const CHARSET_INFO *	cs,
		MY_UCA_INFO *	dst
	)

static

◆ copy_zh_han_pages()

static void copy_zh_han_pages	(	MY_UCA_INFO *	dst,
		MY_CHARSET_LOADER *	loader
	)

static

◆ create_tailoring()

static bool create_tailoring	(	CHARSET_INFO *	cs,
		MY_CHARSET_LOADER *	loader,
		MY_CHARSET_ERRMSG *	errmsg
	)

static

◆ find_contraction_part_in_trie() [1/2]

static std::vector< MY_CONTRACTION >::const_iterator find_contraction_part_in_trie	(	const std::vector< MY_CONTRACTION > &	cont_nodes,
		my_wc_t	ch
	)

static

◆ find_contraction_part_in_trie() [2/2]

static std::vector< MY_CONTRACTION >::iterator find_contraction_part_in_trie	(	std::vector< MY_CONTRACTION > &	cont_nodes,
		my_wc_t	ch
	)

static

◆ get_decomposition()

static Unidata_decomp * get_decomposition ( my_wc_t ch )

static

◆ init_weight_level()

static bool init_weight_level	(	CHARSET_INFO *	cs,
		MY_COLL_RULES *	rules,
		int	level,
		MY_UCA_INFO *	dst,
		const MY_UCA_INFO *	src
	)

static

◆ is_hiragana_char()

static bool is_hiragana_char ( my_wc_t wc )

inlinestatic

◆ is_hiragana_iteration()

static bool is_hiragana_iteration ( my_wc_t wc )

inlinestatic

◆ is_ja_length_mark()

static bool is_ja_length_mark ( my_wc_t wc )

inlinestatic

◆ is_katakana_char()

static bool is_katakana_char ( my_wc_t wc )

inlinestatic

◆ is_katakana_iteration()

static bool is_katakana_iteration ( my_wc_t wc )

inlinestatic

◆ is_tertiary_weight_upper_case()

static bool is_tertiary_weight_upper_case ( uint16_t weight )

static

◆ lex_cmp()

static int lex_cmp	(	MY_COLL_LEXEM *	lexem,
		const char *	pattern,
		size_t	patternlen
	)

static

Compare lexem to string with length.

Parameters

lexem	lexem
pattern	string
patternlen	string length

Return values

0	if lexem is equal to string, non-0 otherwise.

◆ modify_all_zh_pages()

static void modify_all_zh_pages	(	Reorder_param *	reorder_param,
		MY_UCA_INFO *	dst,
		int	npages
	)

static

◆ my_calc_char_grp_gap_param()

static void my_calc_char_grp_gap_param	(	CHARSET_INFO *	cs,
		int &	rec_ind
	)

static

Calculate the reorder parameters for the gap between character groups.

Parameters

cs	Character set info
rec_ind	The position from where to store weight boundary

◆ my_calc_char_grp_param()

static void my_calc_char_grp_param	(	const CHARSET_INFO *	cs,
		int &	rec_ind
	)

static

Calculate the reorder parameters for the character groups.

Parameters

	cs	Character set info
[out]	rec_ind	The position from where to store weight boundary

◆ my_char_weight_addr()

static uint16_t * my_char_weight_addr	(	MY_UCA_INFO *	uca,
		my_wc_t	wc
	)

inlinestatic

Helper function: Find address of weights of the given code point.

Parameters

uca	Pointer to UCA data
wc	character Unicode code point

Returns: Weight array

Return values

pointer to weight array for the given code point, or nullptr if this page does not have implicit weights.

◆ my_char_weight_addr_900()

static uint16_t * my_char_weight_addr_900	(	MY_UCA_INFO *	uca,
		my_wc_t	wc
	)

inlinestatic

Helper function: Find address of weights of the given code point, for UCA 9.0.0 format.

Parameters

uca	Pointer to UCA data
wc	character Unicode code point

Returns: Weight array

Return values

pointer to weight array for the given code point, or nullptr if this page does not have implicit weights.

◆ my_char_weight_put()

static size_t my_char_weight_put	(	MY_UCA_INFO *	dst,
		uint16_t *	to,
		size_t	to_stride,
		size_t	to_length,
		uint16_t *	to_num_ce,
		const MY_COLL_RULE *	rule,
		size_t	base_len,
		enum_uca_ver	uca_ver
	)

static

Helper function: Copies UCA weights for a given "unsigned" string to the given location.

Parameters

dst	destination UCA weight data
to	destination address
to_stride	number of bytes between each successive weight in "to"
to_length	size of destination
to_num_ce	where to put the number of CEs generated
rule	The rule that contains the characters whose weight are to copied
base_len	The length of base character list
uca_ver	UCA version

Returns: number of weights put

◆ my_char_weight_put_900()

static size_t my_char_weight_put_900	(	MY_UCA_INFO *	dst,
		uint16_t *	to,
		size_t	to_stride,
		size_t	to_length,
		uint16_t *	to_num_ce,
		const MY_COLL_RULE *	rule,
		size_t	base_len
	)

static

◆ my_coll_add_inherit_rules()

static int my_coll_add_inherit_rules	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	r,
		const Unidata_decomp *	decomp_rec,
		std::bitset< array_elements(uni_dec)> *	comp_added
	)

static

Add new rules recersively if one rule's characters are in decomposition list.

Parameters

rules	The rule list
r	The rule to check
decomp_rec	The decomposition of the character in rule.
comp_added	Bitset which marks whether the comp character has been added to rule list.

Returns: 1 Error adding new rules 0 Add rules successfully

◆ my_coll_check_rule_and_inherit()

static int my_coll_check_rule_and_inherit	(	const CHARSET_INFO *	cs,
		MY_COLL_RULES *	rules
	)

static

For every rule in rule list, check and add new rules if it is in decomposition list.

Parameters

cs	Character set info
rules	The rule list

Returns: 1 Error happens when adding new rule 0 Add rules successfully

◆ my_coll_init_uca()

static bool my_coll_init_uca	(	CHARSET_INFO *	cs,
		MY_CHARSET_LOADER *	loader,
		MY_CHARSET_ERRMSG *	errmsg
	)

static

◆ my_coll_lexem_init()

static void my_coll_lexem_init	(	MY_COLL_LEXEM *	lexem,
		const char *	str,
		const char *	str_end
	)

static

◆ my_coll_lexem_next()

static my_coll_lexem_num my_coll_lexem_next ( MY_COLL_LEXEM * lexem )

static

◆ my_coll_lexem_num_to_str()

static const char * my_coll_lexem_num_to_str ( my_coll_lexem_num term )

static

Convert collation customization lexem to string, for nice error reporting.

Parameters

term	lexem code

Returns: lexem name

◆ my_coll_lexem_print_error()

static void my_coll_lexem_print_error	(	MY_COLL_LEXEM *	lexem,
		char *	errstr,
		size_t	errsize,
		const char *	txt,
		const char *	col_name
	)

static

◆ my_coll_parser_curr()

static MY_COLL_LEXEM * my_coll_parser_curr ( MY_COLL_RULE_PARSER * p )

static

Current parser token.

Parameters

p	Collation customization parser

Returns: Pointer to the current token

◆ my_coll_parser_exec()

static int my_coll_parser_exec ( MY_COLL_RULE_PARSER * p )

static

Scan collation customization: settings followed by rules.

<collation customization> ::= [ <setting> ... ] [ <rule>... ]

Parameters

p	Collation customization parser

Return values

0	if collation customization expression was not scanned.
1	if collation customization expression was scanned.

◆ my_coll_parser_expected_error()

static int my_coll_parser_expected_error	(	MY_COLL_RULE_PARSER *	p,
		my_coll_lexem_num	term
	)

static

Display error when an unexpected token found.

Parameters

p	Collation customization parser
term	Which lexem was expected

Returns: 0, to use in "return" and boolean expressions.

◆ my_coll_parser_init()

static void my_coll_parser_init	(	MY_COLL_RULE_PARSER *	p,
		MY_COLL_RULES *	rules,
		const char *	str,
		const char *	str_end
	)

static

Initialize collation customization parser.

Parameters

p	Collation customization parser
rules	Where to store rules
str	Beginning of a collation customization string
str_end	End of the collation customizations string

◆ my_coll_parser_next()

static MY_COLL_LEXEM * my_coll_parser_next ( MY_COLL_RULE_PARSER * p )

static

Next parser token, to look ahead.

Parameters

p	Collation customization parser

Returns: Pointer to the next token

◆ my_coll_parser_scan()

static int my_coll_parser_scan ( MY_COLL_RULE_PARSER * p )

static

Scan one token from the input stream.

Parameters

p	Collation customization parser

Returns: 1, for convenience, to use in logical expressions easier.

◆ my_coll_parser_scan_character_list()

static int my_coll_parser_scan_character_list	(	MY_COLL_RULE_PARSER *	p,
		my_wc_t *	pwc,
		size_t	limit,
		const char *	name
	)

static

Scan character list.

<character list> ::= CHAR [ CHAR... ]

Parameters

p	Collation customization parser
pwc	Character string to add code to
limit	The result string cannot be longer than 'limit' characters
name	E.g. "contraction", "expansion"

Return values

0	if character sequence was not scanned.
1	if character sequence was scanned.

◆ my_coll_parser_scan_logical_position()

static int my_coll_parser_scan_logical_position	(	MY_COLL_RULE_PARSER *	p,
		my_wc_t *	pwc,
		size_t	limit
	)

static

Scan logical position and add to the wide string.

Parameters

p	Collation customization parser
pwc	Wide string to add code to
limit	The result string cannot be longer than 'limit' characters

Return values

0	if logical position was not scanned.
1	if logical position was scanned.

◆ my_coll_parser_scan_reset_before()

static int my_coll_parser_scan_reset_before ( MY_COLL_RULE_PARSER * p )

static

Scan [before xxx] reset option.

Parameters

p	Collation customization parser

Return values

0	if reset option was not scanned.
1	if reset option was scanned.

◆ my_coll_parser_scan_reset_sequence()

static int my_coll_parser_scan_reset_sequence ( MY_COLL_RULE_PARSER * p )

static

Scan reset sequence.

Parameters

p	Collation customization parser

Return values

0	if reset sequence was not scanned.
1	if reset sequence was scanned.

◆ my_coll_parser_scan_rule()

static int my_coll_parser_scan_rule ( MY_COLL_RULE_PARSER * p )

static

Scan one rule: reset followed by a number of shifts.

<rule> ::= & <reset sequence> <shift> <shift sequence> [ { <shift> <shift sequence> }... ]

Parameters

p	Collation customization parser

Return values

0	if rule was not scanned.
1	if rule was scanned.

◆ my_coll_parser_scan_setting()

static int my_coll_parser_scan_setting ( MY_COLL_RULE_PARSER * p )

static

Scan a collation setting in brakets, for example UCA version.

Parameters

p	Collation customization parser

Return values

0	if setting was scanned.
1	if setting was not scanned.

◆ my_coll_parser_scan_settings()

static int my_coll_parser_scan_settings ( MY_COLL_RULE_PARSER * p )

static

Scan multiple collation settings.

Parameters

p	Collation customization parser

Return values

0	if no settings were scanned.
1	if one or more settings were scanned.

◆ my_coll_parser_scan_shift()

static int my_coll_parser_scan_shift ( MY_COLL_RULE_PARSER * p )

static

Scan shift operator.

<shift> ::= < | << | <<< | <<<< | =

Parameters

p	Collation customization parser

Return values

0	if shift operator was not scanned.
1	if shift operator was scanned.

◆ my_coll_parser_scan_shift_sequence()

static int my_coll_parser_scan_shift_sequence ( MY_COLL_RULE_PARSER * p )

static

Scan shift sequence.

<shift sequence> ::= <character list> [ / <character list> ] | <character list> [ | <character list> ]

Parameters

p	Collation customization parser

Return values

0	if shift sequence was not scanned.
1	if shift sequence was scanned.

◆ my_coll_parser_scan_term()

static int my_coll_parser_scan_term	(	MY_COLL_RULE_PARSER *	p,
		my_coll_lexem_num	term
	)

static

Scan the given lexem from input stream, or display "expected" error.

Parameters

p	Collation customization parser
term	Which lexem is expected.

Return values

0	if the required term was not found.
1	if the required term was found.

◆ my_coll_parser_too_long_error()

static int my_coll_parser_too_long_error	(	MY_COLL_RULE_PARSER *	p,
		const char *	name
	)

static

Display error when a too long character sequence is met.

Parameters

p	Collation customization parser
name	Which kind of sequence: contraction, expansion, etc.

Returns: 0, to use in "return" and boolean expressions.

◆ my_coll_rule_expand()

static int my_coll_rule_expand	(	my_wc_t *	wc,
		size_t	limit,
		my_wc_t	code
	)

static

Append new character to the end of a 0-terminated wide string.

Parameters

wc	Wide string
limit	Maximum possible result length
code	Character to add

Returns: 1 if character was added, 0 if string was too long

◆ my_coll_rule_parse()

static int my_coll_rule_parse	(	MY_COLL_RULES *	rules,
		const char *	str,
		const char *	str_end,
		const char *	col_name
	)

static

◆ my_coll_rule_reset()

static void my_coll_rule_reset ( MY_COLL_RULE * r )

static

Initialize collation customization rule.

Parameters

r Rule

◆ my_coll_rule_reset_length()

static size_t my_coll_rule_reset_length ( MY_COLL_RULE * r )

inlinestatic

Return length of the "reset" string of a rule.

Parameters

r	Collation customization rule

Returns: Length of r->base

◆ my_coll_rule_shift_at_level()

static void my_coll_rule_shift_at_level	(	MY_COLL_RULE *	r,
		int	level
	)

static

Apply difference at level.

Parameters

r	Rule
level	Level (0,1,2,3,4)

◆ my_coll_rule_shift_length()

static size_t my_coll_rule_shift_length ( MY_COLL_RULE * r )

inlinestatic

Return length of the "shift" string of a rule.

Parameters

r	Collation customization rule

Returns: Length of r->base

◆ my_coll_rules_add()

static int my_coll_rules_add	(	MY_COLL_RULES *	rules,
		MY_COLL_RULE *	rule
	)

static

Append one new rule to a rule array.

Parameters

rules	Rule container
rule	New rule to add

Returns: 0 on success, -1 on error.

◆ my_coll_rules_realloc()

static int my_coll_rules_realloc	(	MY_COLL_RULES *	rules,
		size_t	n
	)

static

Realloc rule array to a new size.

Reallocate memory for 128 additional rules at once, to reduce the number of reallocs, which is important for long tailorings (e.g. for East Asian collations).

Parameters

rules	Rule container
n	new number of rules

Returns: 0 on success, -1 on error.

◆ my_coll_uninit_uca()

static void my_coll_uninit_uca	(	CHARSET_INFO *	cs,
		MY_CHARSET_LOADER *	loader
	)

static

◆ my_comp_in_rulelist()

static bool my_comp_in_rulelist	(	const MY_COLL_RULES *	rules,
		my_wc_t	wc
	)

static

Check whether the composition character is already in rule list.

Parameters

rules	The rule list
wc	The composition character

Returns: true The composition character is already in list false The composition character is not in list

◆ my_compchar_is_normal_char() [1/2]

static bool my_compchar_is_normal_char ( const Unidata_decomp * decomp )

inlinestatic

◆ my_compchar_is_normal_char() [2/2]

static bool my_compchar_is_normal_char ( unsigned dec_ind )

inlinestatic

Check whether a composition character in the decomposition list is a normal character.

Parameters

dec_ind The index of composition character in list

Returns: Whether it is a normal character

◆ my_decompose_hangul_syllable()

static int my_decompose_hangul_syllable	(	my_wc_t	syllable,
		my_wc_t *	jamo
	)

static

Check if a code point is Hangul syllable.

Decompose it to jamos if it is, and return tailored weights.

Parameters

	syllable	Hangul syllable to be decomposed
[out]	jamo	Corresponding jamos

Returns: 0 The code point is not Hangul syllable or cannot be decomposed others The number of jamos returned

◆ my_find_combining_mark()

static Combining_mark * my_find_combining_mark ( my_wc_t code )

static

◆ my_hash_sort_any_uca()

static void my_hash_sort_any_uca	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		uint64_t *	n1,
		uint64_t *	n2
	)

static

◆ my_hash_sort_uca()

template<class Mb_wc >

static void my_hash_sort_uca	(	const CHARSET_INFO *	cs,
		Mb_wc	mb_wc,
		const uint8_t *	s,
		size_t	slen,
		uint64_t *	n1,
		uint64_t *	n2
	)

static

◆ my_hash_sort_uca_900()

static void my_hash_sort_uca_900	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		uint64_t *	n1,
		uint64_t *
	)

static

◆ my_hash_sort_uca_900_tmpl()

template<class Mb_wc , int LEVELS_FOR_COMPARE>

static void my_hash_sort_uca_900_tmpl	(	const CHARSET_INFO *	cs,
		const Mb_wc	mb_wc,
		const uint8_t *	s,
		size_t	slen,
		uint64_t *	n1
	)

static

◆ my_hash_sort_ucs2_uca()

static void my_hash_sort_ucs2_uca	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		uint64_t *	n1,
		uint64_t *	n2
	)

static

◆ my_is_inheritance_of_origin()

static bool my_is_inheritance_of_origin	(	const my_wc_t *	origin_dec,
		const my_wc_t *	dec_codes,
		my_wc_t *	dec_diff
	)

static

Check if a list of combining marks contains the whole list of origin decomposed combining marks.

Parameters

origin_dec	The origin list of combining marks decomposed from character in tailoring rule.
dec_codes	The list of combining marks decomposed from character in decomposition list.
dec_diff	The combining marks exist in dec_codes but not in origin_dec.

Returns: Whether the list of combining marks contains the whole list of origin combining marks.

◆ my_prepare_coll_param()

static bool my_prepare_coll_param	(	CHARSET_INFO *	cs,
		MY_COLL_RULES *	rules
	)

static

Prepare parametric tailoring, like reorder, etc.

Parameters

cs	Character set info
rules	Collation rule list to add to.

Returns: false Collation parameters applied successfully. true Error happened.

◆ my_prepare_reorder()

static int my_prepare_reorder ( CHARSET_INFO * cs )

static

Prepare reorder parameters.

Parameters

cs	Character set info

◆ my_propagate_uca_900()

bool my_propagate_uca_900	(	const CHARSET_INFO *	cs,
		const uint8_t *	str,
		size_t	length
	)

◆ my_set_weight_rec()

static void my_set_weight_rec	(	Reorder_wt_rec(&)	wt_rec[2 *UCA_MAX_CHAR_GRP],
		int	rec_ind,
		uint16_t	old_begin,
		uint16_t	old_end,
		uint16_t	new_begin,
		uint16_t	new_end
	)

inlinestatic

Helper function to store weight boundary values.

Parameters

[out]	wt_rec	Weight boundary for each character group and gap between groups
	rec_ind	The position from where to store weight boundary
	old_begin	Beginning weight of character group before reorder
	old_end	End weight of character group before reorder
	new_begin	Beginning weight of character group after reorder
	new_end	End weight of character group after reorder

◆ my_space_weight()

static int my_space_weight ( const CHARSET_INFO * cs )

inlinestatic

◆ my_strcasecmp_uca()

static int my_strcasecmp_uca	(	const CHARSET_INFO *	cs,
		const char *	s,
		const char *	t
	)

static

◆ my_strnncoll_any_uca()

static int my_strnncoll_any_uca	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen,
		bool	t_is_prefix
	)

static

◆ my_strnncoll_uca()

template<class Scanner , int LEVELS_FOR_COMPARE, class Mb_wc >

static int my_strnncoll_uca	(	const CHARSET_INFO *	cs,
		const Mb_wc	mb_wc,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen,
		bool	t_is_prefix
	)

static

◆ my_strnncoll_uca_900()

static int my_strnncoll_uca_900	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen,
		bool	t_is_prefix
	)

static

◆ my_strnncoll_ucs2_uca()

static int my_strnncoll_ucs2_uca	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen,
		bool	t_is_prefix
	)

static

◆ my_strnncollsp_any_uca()

static int my_strnncollsp_any_uca	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen
	)

static

◆ my_strnncollsp_uca()

template<class Mb_wc >

static int my_strnncollsp_uca	(	const CHARSET_INFO *	cs,
		Mb_wc	mb_wc,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen
	)

static

◆ my_strnncollsp_uca_900()

static int my_strnncollsp_uca_900	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen
	)

static

◆ my_strnncollsp_ucs2_uca()

static int my_strnncollsp_ucs2_uca	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen
	)

static

◆ my_strnncollsp_utf8mb4_0900_bin()

static int my_strnncollsp_utf8mb4_0900_bin	(	const CHARSET_INFO *	cs,
		const uint8_t *	s,
		size_t	slen,
		const uint8_t *	t,
		size_t	tlen
	)

static

◆ my_strnxfrm_any_uca()

static size_t my_strnxfrm_any_uca	(	const CHARSET_INFO *	cs,
		uint8_t *	dst,
		size_t	dstlen,
		unsigned	num_codepoints,
		const uint8_t *	src,
		size_t	srclen,
		unsigned	flags
	)

static

◆ my_strnxfrm_uca()

template<class Mb_wc >

static size_t my_strnxfrm_uca	(	const CHARSET_INFO *	cs,
		Mb_wc	mb_wc,
		uint8_t *	dst,
		size_t	dstlen,
		unsigned	num_codepoints,
		const uint8_t *	src,
		size_t	srclen,
		unsigned	flags
	)

static

◆ my_strnxfrm_uca_900()

static size_t my_strnxfrm_uca_900	(	const CHARSET_INFO *	cs,
		uint8_t *	dst,
		size_t	dstlen,
		unsigned	num_codepoints,
		const uint8_t *	src,
		size_t	srclen,
		unsigned	flags
	)

static

◆ my_strnxfrm_uca_900_tmpl()

template<class Mb_wc , int LEVELS_FOR_COMPARE>

static size_t my_strnxfrm_uca_900_tmpl	(	const CHARSET_INFO *	cs,
		const Mb_wc	mb_wc,
		uint8_t *	dst,
		size_t	dstlen,
		const uint8_t *	src,
		size_t	srclen,
		unsigned	flags
	)

static

◆ my_strnxfrm_ucs2_uca()

static size_t my_strnxfrm_ucs2_uca	(	const CHARSET_INFO *	cs,
		uint8_t *	dst,
		size_t	dstlen,
		unsigned	num_codepoints,
		const uint8_t *	src,
		size_t	srclen,
		unsigned	flags
	)

static

◆ my_strnxfrm_utf8mb4_0900_bin()

static size_t my_strnxfrm_utf8mb4_0900_bin	(	const CHARSET_INFO *	cs,
		uint8_t *	dst,
		size_t	dstlen,
		unsigned	nweights,
		const uint8_t *	src,
		size_t	srclen,
		unsigned	flags
	)

static

◆ my_strnxfrmlen_uca_900()

static size_t my_strnxfrmlen_uca_900	(	const CHARSET_INFO *	cs,
		size_t	len
	)

static

◆ my_uca_add_contraction_flag()

static void my_uca_add_contraction_flag	(	MY_UCA_INFO::flags_type *	flags,
		my_wc_t	wc,
		int	flag
	)

inlinestatic

Mark a code point as a contraction part.

Parameters

flags	Pointer to UCA contraction flag data
wc	Unicode code point
flag	flag: "is contraction head", "is contraction tail"

◆ my_uca_can_be_previous_context_head()

static bool my_uca_can_be_previous_context_head	(	const MY_UCA_INFO::flags_type *	flags,
		my_wc_t	wc
	)

inlinestatic

Check if a code point can be previous context head.

Parameters

flags	Pointer to UCA contraction flag data
wc	Code point

Return values

false	- cannot be previous context head
true	- can be previous context head

◆ my_uca_can_be_previous_context_tail()

static bool my_uca_can_be_previous_context_tail	(	const MY_UCA_INFO::flags_type *	flags,
		my_wc_t	wc
	)

inlinestatic

Check if a code point can be previous context tail.

Parameters

flags	Pointer to UCA contraction flag data
wc	Code point

Return values

false	- cannot be contraction tail
true	- can be contraction tail

◆ my_uca_charcmp()

static int my_uca_charcmp	(	const CHARSET_INFO *	cs,
		my_wc_t	wc1,
		my_wc_t	wc2
	)

static

◆ my_uca_charcmp_900()

static int my_uca_charcmp_900	(	const CHARSET_INFO *	cs,
		my_wc_t	wc1,
		my_wc_t	wc2
	)

static

◆ my_uca_contraction2_weight()

const uint16_t * my_uca_contraction2_weight	(	const std::vector< MY_CONTRACTION > *	cont_nodes,
		my_wc_t	wc1,
		my_wc_t	wc2
	)

Find a contraction consisting of two code points and return its weight array.

Parameters

cont_nodes	Vector that contains contraction nodes
wc1	First code point
wc2	Second code point

Returns: Weight array

Return values

NULL	- no contraction found
ptr	- contraction weight array

◆ my_uca_contraction_weight()

static const uint16_t * my_uca_contraction_weight	(	const std::vector< MY_CONTRACTION > *	cont_nodes,
		const my_wc_t *	wc,
		size_t	len
	)

inlinestatic

Check if a string is a contraction of exactly the given length, and return its weight array on success.

Parameters

cont_nodes	Vector that contains contraction nodes
wc	Pointer to wide string
len	String length

Returns: Weight array

Return values

NULL	- Input string is not a known contraction
ptr	- contraction weight array

◆ my_uca_copy_page()

static bool my_uca_copy_page	(	CHARSET_INFO *	cs,
		MY_CHARSET_LOADER *	loader,
		const MY_UCA_INFO *	src,
		MY_UCA_INFO *	dst,
		size_t	page
	)

static

Alloc new page and copy the default UCA weights.

Parameters

cs	Character set
loader	Character set loader
src	Default UCA data to copy from
dst	UCA data to copy weights to
page	page number

Return values

false	on success
true	on error

◆ my_uca_have_contractions()

static bool my_uca_have_contractions ( const MY_UCA_INFO * uca )

inlinestatic

Check if UCA level data has contractions.

Parameters

uca	Pointer to UCA data

Returns: Flags indicating if UCA with contractions

Return values

0	- no contractions
1	- there are some contractions

◆ my_wildcmp_uca()

static int my_wildcmp_uca	(	const CHARSET_INFO *	cs,
		const char *	str,
		const char *	str_end,
		const char *	wildstr,
		const char *	wildend,
		int	escape,
		int	w_one,
		int	w_many
	)

static

◆ my_wildcmp_uca_impl()

static int my_wildcmp_uca_impl	(	const CHARSET_INFO *	cs,
		const char *	str,
		const char *	str_end,
		const char *	wildstr,
		const char *	wildend,
		int	escape,
		int	w_one,
		int	w_many,
		int	recurse_level
	)

static

◆ my_wstrnlen()

static size_t my_wstrnlen	(	my_wc_t *	s,
		size_t	maxlen
	)

static

Return length of a 0-terminated wide string, analogous to strnlen().

Parameters

s	Pointer to wide string
maxlen	Mamixum string length

Returns: string length, or maxlen if no '\0' is met.

◆ spread_case_mask()

static void spread_case_mask	(	uint16_t *	to,
		size_t	to_stride,
		size_t	tailored_ce_cnt,
		uint16_t	case_mask
	)

static

◆ synthesize_lengths_900()

static void synthesize_lengths_900	(	uint8_t *	lengths,
		const uint16_t const	weights,
		unsigned	npages
	)

static

Variable Documentation

◆ croatian

const char croatian[]

static

Initial value:

=
    "&C < \\u010D <<< \\u010C < \\u0107 <<< \\u0106"
    "&D < d\\u017E = \\u01C6 <<< d\\u017D <<< D\\u017E = \\u01C5 <<< D\\u017D "
    "= \\u01C4"
    "   < \\u0111 <<< \\u0110"
    "&L < lj = \\u01C9  <<< lJ <<< Lj = \\u01C8 <<< LJ = \\u01C7"
    "&N < nj = \\u01CC  <<< nJ <<< Nj = \\u01CB <<< NJ = \\u01CA"
    "&S < \\u0161 <<< \\u0160"
    "&Z < \\u017E <<< \\u017D"

◆ cs_cldr_30

const char cs_cldr_30[]

static

Initial value:

=
    "&C < \\u010D <<< \\u010C "
    "&H < ch      <<< cH       <<< Ch <<< CH "
    "&R < \\u0159 <<< \\u0158"
    "&S < \\u0161 <<< \\u0160"
    "&Z < \\u017E <<< \\u017D"

◆ ctype_gb18030

const uint8_t ctype_gb18030[257]

static

Initial value:

= {
    0, 
    32,  32,  32,  32,  32,  32,  32,  32,  32,  40,  40, 40, 40, 40, 32, 32,
    32,  32,  32,  32,  32,  32,  32,  32,  32,  32,  32, 32, 32, 32, 32, 32,
    72,  16,  16,  16,  16,  16,  16,  16,  16,  16,  16, 16, 16, 16, 16, 16,
    132, 132, 132, 132, 132, 132, 132, 132, 132, 132, 16, 16, 16, 16, 16, 16,
    16,  129, 129, 129, 129, 129, 129, 1,   1,   1,   1,  1,  1,  1,  1,  1,
    1,   1,   1,   1,   1,   1,   1,   1,   1,   1,   1,  16, 16, 16, 16, 16,
    16,  130, 130, 130, 130, 130, 130, 2,   2,   2,   2,  2,  2,  2,  2,  2,
    2,   2,   2,   2,   2,   2,   2,   2,   2,   2,   2,  16, 16, 16, 16, 32,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  3,
    3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,  0}

The array used for "type of characters" bit mask for each character.

The ctype[0] is reserved for EOF(-1), so we use ctype[(char)+1]. Also refer to strings/CHARSET_INFO.txt

◆ ctype_utf8

const uint8_t ctype_utf8[]

static

Initial value:

= {
    0,  32,  32,  32,  32,  32,  32,  32,  32,  32,  40,  40, 40, 40, 40, 32,
    32, 32,  32,  32,  32,  32,  32,  32,  32,  32,  32,  32, 32, 32, 32, 32,
    32, 72,  16,  16,  16,  16,  16,  16,  16,  16,  16,  16, 16, 16, 16, 16,
    16, 132, 132, 132, 132, 132, 132, 132, 132, 132, 132, 16, 16, 16, 16, 16,
    16, 16,  129, 129, 129, 129, 129, 129, 1,   1,   1,   1,  1,  1,  1,  1,
    1,  1,   1,   1,   1,   1,   1,   1,   1,   1,   1,   1,  16, 16, 16, 16,
    16, 16,  130, 130, 130, 130, 130, 130, 2,   2,   2,   2,  2,  2,  2,  2,
    2,  2,   2,   2,   2,   2,   2,   2,   2,   2,   2,   2,  16, 16, 16, 16,
    32, 3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    3,  3,   3,   3,   3,   3,   3,   3,   3,   3,   3,   3,  3,  3,  3,  3,
    0}

◆ czech

const char czech[]

static

Initial value:

=
    "& C < \\u010D <<< \\u010C "
    "& H <      ch <<<      Ch <<< CH"
    "& R < \\u0159 <<< \\u0158"
    "& S < \\u0161 <<< \\u0160"
    "& Z < \\u017E <<< \\u017D"

◆ da_cldr_30

const char da_cldr_30[]

static

Initial value:

=
    "&          D       <<  \\u0111   <<< \\u0110 <<  \\u00F0 <<< \\u00D0 "
    "&          t       <<< \\u00FE/h "
    "&          T       <<< \\u00DE/H "
    "&          Y       <<  \\u00FC   <<< \\u00DC <<  \\u0171 <<< \\u0170 "
    "&[before 1]\\u01C0 <   \\u00E6   <<< \\u00C6 <<  \\u00E4 <<< \\u00C4 "
    "<   \\u00F8   <<< \\u00D8 <<  \\u00F6 <<< \\u00D6 "
    "<<  \\u0151   <<< \\u0150 <<  \\u0153 <<< \\u0152 "
    "<   \\u00E5   <<< \\u00C5 <<< aa      <<< Aa "
    "<<< AA"

◆ da_coll_param

Coll_param da_coll_param = {nullptr, false, CASE_FIRST_UPPER}

static

◆ danish

const char danish[]

static

Initial value:

= 
    "& Y << \\u00FC <<< \\u00DC << \\u0171 <<< \\u0170"
    "& Z  < \\u00E6 <<< \\u00C6 << \\u00E4 <<< \\u00C4"
    " < \\u00F8 <<< \\u00D8 << \\u00F6 <<< \\u00D6 << \\u0151 <<< \\u0150"
    " < \\u00E5 <<< \\u00C5 << aa <<<  Aa <<< AA"

◆ de_pb_cldr_30

const char de_pb_cldr_30[]

static

Initial value:

=
    "&AE << \\u00E4 <<< \\u00C4 "
    "&OE << \\u00F6 <<< \\u00D6 "
    "&UE << \\u00FC <<< \\u00DC "

◆ es_trad_cldr_30

const char es_trad_cldr_30[]

static

Initial value:

=
    "&N <  \\u00F1 <<< \\u00D1 "
    "&C <  ch      <<< Ch      <<< CH "
    "&l <  ll      <<< Ll      <<< LL"

◆ esperanto

const char esperanto[]

static

Initial value:

=
    "& C < \\u0109 <<< \\u0108"
    "& G < \\u011D <<< \\u011C"
    "& H < \\u0125 <<< \\u0124"
    "& J < \\u0135 <<< \\u0134"
    "& S < \\u015d <<< \\u015c"
    "& U < \\u016d <<< \\u016c"

◆ estonian

const char estonian[]

static

Initial value:

=
    "& S < \\u0161 <<< \\u0160 "
    " < \\u007A <<< \\u005A "
    " < \\u017E <<< \\u017D "
    "& W < \\u00F5 <<< \\u00D5 "
    "< \\u00E4 <<< \\u00C4 "
    "< \\u00F6 <<< \\u00D6 "
    "< \\u00FC <<< \\u00DC "

◆ et_cldr_30

const char et_cldr_30[]

static

Initial value:

=
    "&[before 1]T <   \\u0161 <<< \\u0160 < z         <<< Z "
    "<   \\u017E <<< \\u017D "
    "&[before 1]X <   \\u00F5 <<< \\u00D5 <   \\u00E4 <<< \\u00C4 "
    "<   \\u00F6 <<< \\u00D6 <   \\u00FC <<< \\u00DC"

◆ german2

const char german2[]

static

Initial value:

=
    "&AE << \\u00E6 <<< \\u00C6 << \\u00E4 <<< \\u00C4 "
    "&OE << \\u0153 <<< \\u0152 << \\u00F6 <<< \\u00D6 "
    "&UE << \\u00FC <<< \\u00DC "

◆ hr_cldr_30

const char hr_cldr_30[]

static

Initial value:

=
    "&C <   \\u010D  <<< \\u010C <   \\u0107  <<< \\u0106 "
    "&D <   d\\u017E <<< \\u01C6 <<< D\\u017E <<< \\u01C5 <<< D\\u017D "
    "<<< \\u01C4  <   \\u0111 <<< \\u0110 "
    "&L <   lj       <<< \\u01C9 <<< Lj       <<< \\u01C8 <<< LJ "
    "<<< \\u01C7 "
    "&N <   nj       <<< \\u01CC <<< Nj       <<< \\u01CB <<< NJ "
    "<<< \\u01CA "
    "&S <   \\u0161  <<< \\u0160 "
    "&Z <   \\u017E  <<< \\u017D "

◆ hr_coll_param

Coll_param hr_coll_param = {&hr_reorder_param, false, CASE_FIRST_OFF}

static

◆ hr_reorder_param

Reorder_param hr_reorder_param

static

Initial value:

= {

{CHARGRP_LATIN, CHARGRP_CYRILLIC, CHARGRP_NONE}, {{{0, 0}, {0, 0}}}, 0, 0}

CHARGRP_NONE

@ CHARGRP_NONE

Definition: str_uca_type.h:46

CHARGRP_LATIN

@ CHARGRP_LATIN

Definition: str_uca_type.h:48

CHARGRP_CYRILLIC

@ CHARGRP_CYRILLIC

Definition: str_uca_type.h:49

◆ hu_cldr_30

const char hu_cldr_30[]

static

◆ hungarian

const char hungarian[]

static

Initial value:

=
    "&O < \\u00F6 <<< \\u00D6 << \\u0151 <<< \\u0150"
    "&U < \\u00FC <<< \\u00DC << \\u0171 <<< \\u0170"

◆ icelandic

const char icelandic[]

static

Initial value:

=
    "& A < \\u00E1 <<< \\u00C1 "
    "& D < \\u00F0 <<< \\u00D0 "
    "& E < \\u00E9 <<< \\u00C9 "
    "& I < \\u00ED <<< \\u00CD "
    "& O < \\u00F3 <<< \\u00D3 "
    "& U < \\u00FA <<< \\u00DA "
    "& Y < \\u00FD <<< \\u00DD "
    "& Z < \\u00FE <<< \\u00DE "
    "< \\u00E6 <<< \\u00C6 << \\u00E4 <<< \\u00C4 "
    "< \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 "
    "< \\u00E5 <<< \\u00C5 "

◆ is_cldr_30

const char is_cldr_30[]

static

Initial value:

=
    "&[before 1]b       <  \\u00E1 <<< \\u00C1 "
    "&          d       << \\u0111 <<< \\u0110 < \\u00F0 <<< \\u00D0 "
    "&[before 1]f       <  \\u00E9 <<< \\u00C9 "
    "&[before 1]j       <  \\u00ED <<< \\u00CD "
    "&[before 1]p       <  \\u00F3 <<< \\u00D3 "
    "&[before 1]v       <  \\u00FA <<< \\u00DA "
    "&[before 1]z       <  \\u00FD <<< \\u00DD "
    "&[before 1]\\u01C0 <  \\u00E6 <<< \\u00C6 << \\u00E4 <<< \\u00C4 "
    "<  \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 "
    "<  \\u00E5 <<< \\u00C5"

◆ ja_coll_param

Coll_param ja_coll_param

static

Initial value:

= {&ja_reorder_param, false ,

CASE_FIRST_OFF}

ja_reorder_param

static Reorder_param ja_reorder_param

Definition: ctype-uca.cc:691

CASE_FIRST_OFF

@ CASE_FIRST_OFF

Definition: str_uca_type.h:72

◆ ja_reorder_param

Reorder_param ja_reorder_param

static

Initial value:

= {
    
    {CHARGRP_LATIN, CHARGRP_KANA, CHARGRP_NONE},
    {{{0, 0}, {0, 0}}},
    0,
    0}

◆ latvian

const char latvian[]

static

Initial value:

=
    "& C < \\u010D <<< \\u010C "
    "& G < \\u0123 <<< \\u0122 "
    "& I < \\u0079 <<< \\u0059 "
    "& K < \\u0137 <<< \\u0136 "
    "& L < \\u013C <<< \\u013B "
    "& N < \\u0146 <<< \\u0145 "
    "& R < \\u0157 <<< \\u0156 "
    "& S < \\u0161 <<< \\u0160 "
    "& Z < \\u017E <<< \\u017D "

◆ lithuanian

const char lithuanian[]

static

Initial value:

=
    "& C << ch <<< Ch <<< CH< \\u010D <<< \\u010C"
    "& E << \\u0119 <<< \\u0118 << \\u0117 <<< \\u0116"
    "& I << y <<< Y"
    "& S  < \\u0161 <<< \\u0160"
    "& Z  < \\u017E <<< \\u017D"

◆ lt_cldr_30

const char lt_cldr_30[]

static

Initial value:

=
    "&\\u0300 = \\u0307\\u0300 "
    "&\\u0301 = \\u0307\\u0301 "
    "&\\u0303 = \\u0307\\u0303 "
    "&A << \\u0105 <<< \\u0104 "
    "&C <  \\u010D <<< \\u010C "
    "&E << \\u0119 <<< \\u0118 << \\u0117 <<< \\u0116"
    "&I << \\u012F <<< \\u012E << y       <<< Y "
    "&S <  \\u0161 <<< \\u0160 "
    "&U << \\u0173 <<< \\u0172 << \\u016B <<< \\u016A "
    "&Z <  \\u017E <<< \\u017D"

◆ lv_cldr_30

const char lv_cldr_30[]

static

Initial value:

=
    "&[before 1]D       <  \\u010D <<< \\u010C "
    "&[before 1]H       <  \\u0123 <<< \\u0122 "
    "&          I       << y       <<< Y "
    "&[before 1]L       <  \\u0137 <<< \\u0136 "
    "&[before 1]M       <  \\u013C <<< \\u013B "
    "&[before 1]O       <  \\u0146 <<< \\u0145 "
    "&[before 1]S       <  \\u0157 <<< \\u0156 "
    "&[before 1]T       <  \\u0161 <<< \\u0160 "
    "&[before 1]\\u01B7 <  \\u017E <<< \\u017D"

◆ my_charset_gb18030_uca_handler

MY_CHARSET_HANDLER my_charset_gb18030_uca_handler

extern

◆ my_charset_gb18030_unicode_520_ci

CHARSET_INFO my_charset_gb18030_unicode_520_ci

◆ my_charset_ucs2_croatian_uca_ci

CHARSET_INFO my_charset_ucs2_croatian_uca_ci

◆ my_charset_ucs2_czech_uca_ci

CHARSET_INFO my_charset_ucs2_czech_uca_ci

◆ my_charset_ucs2_danish_uca_ci

CHARSET_INFO my_charset_ucs2_danish_uca_ci

◆ my_charset_ucs2_esperanto_uca_ci

CHARSET_INFO my_charset_ucs2_esperanto_uca_ci

◆ my_charset_ucs2_estonian_uca_ci

CHARSET_INFO my_charset_ucs2_estonian_uca_ci

◆ my_charset_ucs2_german2_uca_ci

CHARSET_INFO my_charset_ucs2_german2_uca_ci

◆ my_charset_ucs2_hungarian_uca_ci

CHARSET_INFO my_charset_ucs2_hungarian_uca_ci

◆ my_charset_ucs2_icelandic_uca_ci

CHARSET_INFO my_charset_ucs2_icelandic_uca_ci

◆ my_charset_ucs2_latvian_uca_ci

CHARSET_INFO my_charset_ucs2_latvian_uca_ci

◆ my_charset_ucs2_lithuanian_uca_ci

CHARSET_INFO my_charset_ucs2_lithuanian_uca_ci

◆ my_charset_ucs2_persian_uca_ci

CHARSET_INFO my_charset_ucs2_persian_uca_ci

◆ my_charset_ucs2_polish_uca_ci

CHARSET_INFO my_charset_ucs2_polish_uca_ci

◆ my_charset_ucs2_roman_uca_ci

CHARSET_INFO my_charset_ucs2_roman_uca_ci

◆ my_charset_ucs2_romanian_uca_ci

CHARSET_INFO my_charset_ucs2_romanian_uca_ci

◆ my_charset_ucs2_sinhala_uca_ci

CHARSET_INFO my_charset_ucs2_sinhala_uca_ci

◆ my_charset_ucs2_slovak_uca_ci

CHARSET_INFO my_charset_ucs2_slovak_uca_ci

◆ my_charset_ucs2_slovenian_uca_ci

CHARSET_INFO my_charset_ucs2_slovenian_uca_ci

◆ my_charset_ucs2_spanish2_uca_ci

CHARSET_INFO my_charset_ucs2_spanish2_uca_ci

◆ my_charset_ucs2_spanish_uca_ci

CHARSET_INFO my_charset_ucs2_spanish_uca_ci

◆ my_charset_ucs2_swedish_uca_ci

CHARSET_INFO my_charset_ucs2_swedish_uca_ci

◆ my_charset_ucs2_turkish_uca_ci

CHARSET_INFO my_charset_ucs2_turkish_uca_ci

◆ my_charset_ucs2_unicode_520_ci

CHARSET_INFO my_charset_ucs2_unicode_520_ci

◆ my_charset_ucs2_unicode_ci

CHARSET_INFO my_charset_ucs2_unicode_ci

◆ my_charset_ucs2_vietnamese_ci

CHARSET_INFO my_charset_ucs2_vietnamese_ci

◆ my_charset_utf16_croatian_uca_ci

CHARSET_INFO my_charset_utf16_croatian_uca_ci

◆ my_charset_utf16_czech_uca_ci

CHARSET_INFO my_charset_utf16_czech_uca_ci

◆ my_charset_utf16_danish_uca_ci

CHARSET_INFO my_charset_utf16_danish_uca_ci

◆ my_charset_utf16_esperanto_uca_ci

CHARSET_INFO my_charset_utf16_esperanto_uca_ci

◆ my_charset_utf16_estonian_uca_ci

CHARSET_INFO my_charset_utf16_estonian_uca_ci

◆ my_charset_utf16_german2_uca_ci

CHARSET_INFO my_charset_utf16_german2_uca_ci

◆ my_charset_utf16_handler

MY_CHARSET_HANDLER my_charset_utf16_handler

extern

◆ my_charset_utf16_hungarian_uca_ci

CHARSET_INFO my_charset_utf16_hungarian_uca_ci

◆ my_charset_utf16_icelandic_uca_ci

CHARSET_INFO my_charset_utf16_icelandic_uca_ci

◆ my_charset_utf16_latvian_uca_ci

CHARSET_INFO my_charset_utf16_latvian_uca_ci

◆ my_charset_utf16_lithuanian_uca_ci

CHARSET_INFO my_charset_utf16_lithuanian_uca_ci

◆ my_charset_utf16_persian_uca_ci

CHARSET_INFO my_charset_utf16_persian_uca_ci

◆ my_charset_utf16_polish_uca_ci

CHARSET_INFO my_charset_utf16_polish_uca_ci

◆ my_charset_utf16_roman_uca_ci

CHARSET_INFO my_charset_utf16_roman_uca_ci

◆ my_charset_utf16_romanian_uca_ci

CHARSET_INFO my_charset_utf16_romanian_uca_ci

◆ my_charset_utf16_sinhala_uca_ci

CHARSET_INFO my_charset_utf16_sinhala_uca_ci

◆ my_charset_utf16_slovak_uca_ci

CHARSET_INFO my_charset_utf16_slovak_uca_ci

◆ my_charset_utf16_slovenian_uca_ci

CHARSET_INFO my_charset_utf16_slovenian_uca_ci

◆ my_charset_utf16_spanish2_uca_ci

CHARSET_INFO my_charset_utf16_spanish2_uca_ci

◆ my_charset_utf16_spanish_uca_ci

CHARSET_INFO my_charset_utf16_spanish_uca_ci

◆ my_charset_utf16_swedish_uca_ci

CHARSET_INFO my_charset_utf16_swedish_uca_ci

◆ my_charset_utf16_turkish_uca_ci

CHARSET_INFO my_charset_utf16_turkish_uca_ci

◆ my_charset_utf16_unicode_520_ci

CHARSET_INFO my_charset_utf16_unicode_520_ci

◆ my_charset_utf16_unicode_ci

CHARSET_INFO my_charset_utf16_unicode_ci

◆ my_charset_utf16_vietnamese_ci

CHARSET_INFO my_charset_utf16_vietnamese_ci

◆ my_charset_utf32_croatian_uca_ci

CHARSET_INFO my_charset_utf32_croatian_uca_ci

◆ my_charset_utf32_czech_uca_ci

CHARSET_INFO my_charset_utf32_czech_uca_ci

◆ my_charset_utf32_danish_uca_ci

CHARSET_INFO my_charset_utf32_danish_uca_ci

◆ my_charset_utf32_esperanto_uca_ci

CHARSET_INFO my_charset_utf32_esperanto_uca_ci

◆ my_charset_utf32_estonian_uca_ci

CHARSET_INFO my_charset_utf32_estonian_uca_ci

◆ my_charset_utf32_german2_uca_ci

CHARSET_INFO my_charset_utf32_german2_uca_ci

◆ my_charset_utf32_handler

MY_CHARSET_HANDLER my_charset_utf32_handler

extern

◆ my_charset_utf32_hungarian_uca_ci

CHARSET_INFO my_charset_utf32_hungarian_uca_ci

◆ my_charset_utf32_icelandic_uca_ci

CHARSET_INFO my_charset_utf32_icelandic_uca_ci

◆ my_charset_utf32_latvian_uca_ci

CHARSET_INFO my_charset_utf32_latvian_uca_ci

◆ my_charset_utf32_lithuanian_uca_ci

CHARSET_INFO my_charset_utf32_lithuanian_uca_ci

◆ my_charset_utf32_persian_uca_ci

CHARSET_INFO my_charset_utf32_persian_uca_ci

◆ my_charset_utf32_polish_uca_ci

CHARSET_INFO my_charset_utf32_polish_uca_ci

◆ my_charset_utf32_roman_uca_ci

CHARSET_INFO my_charset_utf32_roman_uca_ci

◆ my_charset_utf32_romanian_uca_ci

CHARSET_INFO my_charset_utf32_romanian_uca_ci

◆ my_charset_utf32_sinhala_uca_ci

CHARSET_INFO my_charset_utf32_sinhala_uca_ci

◆ my_charset_utf32_slovak_uca_ci

CHARSET_INFO my_charset_utf32_slovak_uca_ci

◆ my_charset_utf32_slovenian_uca_ci

CHARSET_INFO my_charset_utf32_slovenian_uca_ci

◆ my_charset_utf32_spanish2_uca_ci

CHARSET_INFO my_charset_utf32_spanish2_uca_ci

◆ my_charset_utf32_spanish_uca_ci

CHARSET_INFO my_charset_utf32_spanish_uca_ci

◆ my_charset_utf32_swedish_uca_ci

CHARSET_INFO my_charset_utf32_swedish_uca_ci

◆ my_charset_utf32_turkish_uca_ci

CHARSET_INFO my_charset_utf32_turkish_uca_ci

◆ my_charset_utf32_unicode_520_ci

CHARSET_INFO my_charset_utf32_unicode_520_ci

◆ my_charset_utf32_unicode_ci

CHARSET_INFO my_charset_utf32_unicode_ci

◆ my_charset_utf32_vietnamese_ci

CHARSET_INFO my_charset_utf32_vietnamese_ci

◆ my_charset_utf8mb3_croatian_uca_ci

CHARSET_INFO my_charset_utf8mb3_croatian_uca_ci

◆ my_charset_utf8mb3_czech_uca_ci

CHARSET_INFO my_charset_utf8mb3_czech_uca_ci

◆ my_charset_utf8mb3_danish_uca_ci

CHARSET_INFO my_charset_utf8mb3_danish_uca_ci

◆ my_charset_utf8mb3_esperanto_uca_ci

CHARSET_INFO my_charset_utf8mb3_esperanto_uca_ci

◆ my_charset_utf8mb3_estonian_uca_ci

CHARSET_INFO my_charset_utf8mb3_estonian_uca_ci

◆ my_charset_utf8mb3_german2_uca_ci

CHARSET_INFO my_charset_utf8mb3_german2_uca_ci

◆ my_charset_utf8mb3_handler

MY_CHARSET_HANDLER my_charset_utf8mb3_handler

extern

◆ my_charset_utf8mb3_hungarian_uca_ci

CHARSET_INFO my_charset_utf8mb3_hungarian_uca_ci

◆ my_charset_utf8mb3_icelandic_uca_ci

CHARSET_INFO my_charset_utf8mb3_icelandic_uca_ci

◆ my_charset_utf8mb3_latvian_uca_ci

CHARSET_INFO my_charset_utf8mb3_latvian_uca_ci

◆ my_charset_utf8mb3_lithuanian_uca_ci

CHARSET_INFO my_charset_utf8mb3_lithuanian_uca_ci

◆ my_charset_utf8mb3_persian_uca_ci

CHARSET_INFO my_charset_utf8mb3_persian_uca_ci

◆ my_charset_utf8mb3_polish_uca_ci

CHARSET_INFO my_charset_utf8mb3_polish_uca_ci

◆ my_charset_utf8mb3_roman_uca_ci

CHARSET_INFO my_charset_utf8mb3_roman_uca_ci

◆ my_charset_utf8mb3_romanian_uca_ci

CHARSET_INFO my_charset_utf8mb3_romanian_uca_ci

◆ my_charset_utf8mb3_sinhala_uca_ci

CHARSET_INFO my_charset_utf8mb3_sinhala_uca_ci

◆ my_charset_utf8mb3_slovak_uca_ci

CHARSET_INFO my_charset_utf8mb3_slovak_uca_ci

◆ my_charset_utf8mb3_slovenian_uca_ci

CHARSET_INFO my_charset_utf8mb3_slovenian_uca_ci

◆ my_charset_utf8mb3_spanish2_uca_ci

CHARSET_INFO my_charset_utf8mb3_spanish2_uca_ci

◆ my_charset_utf8mb3_spanish_uca_ci

CHARSET_INFO my_charset_utf8mb3_spanish_uca_ci

◆ my_charset_utf8mb3_swedish_uca_ci

CHARSET_INFO my_charset_utf8mb3_swedish_uca_ci

◆ my_charset_utf8mb3_turkish_uca_ci

CHARSET_INFO my_charset_utf8mb3_turkish_uca_ci

◆ my_charset_utf8mb3_unicode_520_ci

CHARSET_INFO my_charset_utf8mb3_unicode_520_ci

◆ my_charset_utf8mb3_unicode_ci

CHARSET_INFO my_charset_utf8mb3_unicode_ci

◆ my_charset_utf8mb3_vietnamese_ci

CHARSET_INFO my_charset_utf8mb3_vietnamese_ci

◆ my_charset_utf8mb4_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_0900_ai_ci

◆ my_charset_utf8mb4_0900_as_ci

CHARSET_INFO my_charset_utf8mb4_0900_as_ci

◆ my_charset_utf8mb4_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_0900_as_cs

◆ my_charset_utf8mb4_0900_bin

CHARSET_INFO my_charset_utf8mb4_0900_bin

◆ my_charset_utf8mb4_bg_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_bg_0900_ai_ci

◆ my_charset_utf8mb4_bg_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_bg_0900_as_cs

◆ my_charset_utf8mb4_bs_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_bs_0900_ai_ci

◆ my_charset_utf8mb4_bs_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_bs_0900_as_cs

◆ my_charset_utf8mb4_croatian_uca_ci

CHARSET_INFO my_charset_utf8mb4_croatian_uca_ci

◆ my_charset_utf8mb4_cs_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_cs_0900_ai_ci

◆ my_charset_utf8mb4_cs_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_cs_0900_as_cs

◆ my_charset_utf8mb4_czech_uca_ci

CHARSET_INFO my_charset_utf8mb4_czech_uca_ci

◆ my_charset_utf8mb4_da_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_da_0900_ai_ci

◆ my_charset_utf8mb4_da_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_da_0900_as_cs

◆ my_charset_utf8mb4_danish_uca_ci

CHARSET_INFO my_charset_utf8mb4_danish_uca_ci

◆ my_charset_utf8mb4_de_pb_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_de_pb_0900_ai_ci

◆ my_charset_utf8mb4_de_pb_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_de_pb_0900_as_cs

◆ my_charset_utf8mb4_eo_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_eo_0900_ai_ci

◆ my_charset_utf8mb4_eo_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_eo_0900_as_cs

◆ my_charset_utf8mb4_es_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_es_0900_ai_ci

◆ my_charset_utf8mb4_es_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_es_0900_as_cs

◆ my_charset_utf8mb4_es_trad_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_es_trad_0900_ai_ci

◆ my_charset_utf8mb4_es_trad_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_es_trad_0900_as_cs

◆ my_charset_utf8mb4_esperanto_uca_ci

CHARSET_INFO my_charset_utf8mb4_esperanto_uca_ci

◆ my_charset_utf8mb4_estonian_uca_ci

CHARSET_INFO my_charset_utf8mb4_estonian_uca_ci

◆ my_charset_utf8mb4_et_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_et_0900_ai_ci

◆ my_charset_utf8mb4_et_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_et_0900_as_cs

◆ my_charset_utf8mb4_german2_uca_ci

CHARSET_INFO my_charset_utf8mb4_german2_uca_ci

◆ my_charset_utf8mb4_gl_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_gl_0900_ai_ci

◆ my_charset_utf8mb4_gl_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_gl_0900_as_cs

◆ my_charset_utf8mb4_handler

MY_CHARSET_HANDLER my_charset_utf8mb4_handler

extern

◆ my_charset_utf8mb4_hr_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_hr_0900_ai_ci

◆ my_charset_utf8mb4_hr_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_hr_0900_as_cs

◆ my_charset_utf8mb4_hu_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_hu_0900_ai_ci

◆ my_charset_utf8mb4_hu_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_hu_0900_as_cs

◆ my_charset_utf8mb4_hungarian_uca_ci

CHARSET_INFO my_charset_utf8mb4_hungarian_uca_ci

◆ my_charset_utf8mb4_icelandic_uca_ci

CHARSET_INFO my_charset_utf8mb4_icelandic_uca_ci

◆ my_charset_utf8mb4_is_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_is_0900_ai_ci

◆ my_charset_utf8mb4_is_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_is_0900_as_cs

◆ my_charset_utf8mb4_ja_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_ja_0900_as_cs

◆ my_charset_utf8mb4_ja_0900_as_cs_ks

CHARSET_INFO my_charset_utf8mb4_ja_0900_as_cs_ks

◆ my_charset_utf8mb4_la_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_la_0900_ai_ci

◆ my_charset_utf8mb4_la_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_la_0900_as_cs

◆ my_charset_utf8mb4_latvian_uca_ci

CHARSET_INFO my_charset_utf8mb4_latvian_uca_ci

◆ my_charset_utf8mb4_lithuanian_uca_ci

CHARSET_INFO my_charset_utf8mb4_lithuanian_uca_ci

◆ my_charset_utf8mb4_lt_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_lt_0900_ai_ci

◆ my_charset_utf8mb4_lt_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_lt_0900_as_cs

◆ my_charset_utf8mb4_lv_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_lv_0900_ai_ci

◆ my_charset_utf8mb4_lv_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_lv_0900_as_cs

◆ my_charset_utf8mb4_mn_cyrl_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_mn_cyrl_0900_ai_ci

◆ my_charset_utf8mb4_mn_cyrl_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_mn_cyrl_0900_as_cs

◆ my_charset_utf8mb4_nb_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_nb_0900_ai_ci

◆ my_charset_utf8mb4_nb_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_nb_0900_as_cs

◆ my_charset_utf8mb4_nn_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_nn_0900_ai_ci

◆ my_charset_utf8mb4_nn_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_nn_0900_as_cs

◆ my_charset_utf8mb4_persian_uca_ci

CHARSET_INFO my_charset_utf8mb4_persian_uca_ci

◆ my_charset_utf8mb4_pl_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_pl_0900_ai_ci

◆ my_charset_utf8mb4_pl_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_pl_0900_as_cs

◆ my_charset_utf8mb4_polish_uca_ci

CHARSET_INFO my_charset_utf8mb4_polish_uca_ci

◆ my_charset_utf8mb4_ro_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_ro_0900_ai_ci

◆ my_charset_utf8mb4_ro_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_ro_0900_as_cs

◆ my_charset_utf8mb4_roman_uca_ci

CHARSET_INFO my_charset_utf8mb4_roman_uca_ci

◆ my_charset_utf8mb4_romanian_uca_ci

CHARSET_INFO my_charset_utf8mb4_romanian_uca_ci

◆ my_charset_utf8mb4_ru_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_ru_0900_ai_ci

◆ my_charset_utf8mb4_ru_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_ru_0900_as_cs

◆ my_charset_utf8mb4_sinhala_uca_ci

CHARSET_INFO my_charset_utf8mb4_sinhala_uca_ci

◆ my_charset_utf8mb4_sk_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_sk_0900_ai_ci

◆ my_charset_utf8mb4_sk_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_sk_0900_as_cs

◆ my_charset_utf8mb4_sl_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_sl_0900_ai_ci

◆ my_charset_utf8mb4_sl_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_sl_0900_as_cs

◆ my_charset_utf8mb4_slovak_uca_ci

CHARSET_INFO my_charset_utf8mb4_slovak_uca_ci

◆ my_charset_utf8mb4_slovenian_uca_ci

CHARSET_INFO my_charset_utf8mb4_slovenian_uca_ci

◆ my_charset_utf8mb4_spanish2_uca_ci

CHARSET_INFO my_charset_utf8mb4_spanish2_uca_ci

◆ my_charset_utf8mb4_spanish_uca_ci

CHARSET_INFO my_charset_utf8mb4_spanish_uca_ci

◆ my_charset_utf8mb4_sr_latn_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_sr_latn_0900_ai_ci

◆ my_charset_utf8mb4_sr_latn_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_sr_latn_0900_as_cs

◆ my_charset_utf8mb4_sv_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_sv_0900_ai_ci

◆ my_charset_utf8mb4_sv_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_sv_0900_as_cs

◆ my_charset_utf8mb4_swedish_uca_ci

CHARSET_INFO my_charset_utf8mb4_swedish_uca_ci

◆ my_charset_utf8mb4_tr_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_tr_0900_ai_ci

◆ my_charset_utf8mb4_tr_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_tr_0900_as_cs

◆ my_charset_utf8mb4_turkish_uca_ci

CHARSET_INFO my_charset_utf8mb4_turkish_uca_ci

◆ my_charset_utf8mb4_unicode_520_ci

CHARSET_INFO my_charset_utf8mb4_unicode_520_ci

◆ my_charset_utf8mb4_unicode_ci

CHARSET_INFO my_charset_utf8mb4_unicode_ci

◆ my_charset_utf8mb4_vi_0900_ai_ci

CHARSET_INFO my_charset_utf8mb4_vi_0900_ai_ci

◆ my_charset_utf8mb4_vi_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_vi_0900_as_cs

◆ my_charset_utf8mb4_vietnamese_ci

CHARSET_INFO my_charset_utf8mb4_vietnamese_ci

◆ my_charset_utf8mb4_zh_0900_as_cs

CHARSET_INFO my_charset_utf8mb4_zh_0900_as_cs

◆ my_collation_any_uca_handler

MY_COLLATION_HANDLER my_collation_any_uca_handler

Initial value:

= {
    my_coll_init_uca, 
    my_coll_uninit_uca,   my_strnncoll_any_uca,  my_strnncollsp_any_uca,
    my_strnxfrm_any_uca,  my_strnxfrmlen_simple, my_like_range_mb,
    my_wildcmp_uca,       my_strcasecmp_uca,     my_instr_mb,
    my_hash_sort_any_uca, my_propagate_complex}

◆ my_collation_gb18030_uca_handler

MY_COLLATION_HANDLER my_collation_gb18030_uca_handler

Initial value:

= {
    my_coll_init_uca, 
    my_coll_uninit_uca,
    my_strnncoll_any_uca,
    my_strnncollsp_any_uca,
    my_strnxfrm_any_uca,
    my_strnxfrmlen_simple,
    my_like_range_mb,
    my_wildcmp_uca,
    nullptr,
    my_instr_mb,
    my_hash_sort_any_uca,
    my_propagate_complex}

◆ my_collation_uca_900_handler

MY_COLLATION_HANDLER my_collation_uca_900_handler

Initial value:

= {
    my_coll_init_uca, 
    my_coll_uninit_uca,   my_strnncoll_uca_900,   my_strnncollsp_uca_900,
    my_strnxfrm_uca_900,  my_strnxfrmlen_uca_900, my_like_range_mb,
    my_wildcmp_uca,       my_strcasecmp_uca,      my_instr_mb,
    my_hash_sort_uca_900, my_propagate_uca_900}

◆ my_collation_ucs2_uca_handler

MY_COLLATION_HANDLER my_collation_ucs2_uca_handler

Initial value:

= {
    my_coll_init_uca, 
    my_coll_uninit_uca,
    my_strnncoll_ucs2_uca,
    my_strnncollsp_ucs2_uca,
    my_strnxfrm_ucs2_uca,
    my_strnxfrmlen_simple,
    my_like_range_generic,
    my_wildcmp_uca,
    nullptr,
    my_instr_mb,
    my_hash_sort_ucs2_uca,
    my_propagate_complex}

◆ my_collation_utf16_uca_handler

MY_COLLATION_HANDLER my_collation_utf16_uca_handler

Initial value:

= {
    my_coll_init_uca, 
    my_coll_uninit_uca,
    my_strnncoll_any_uca,
    my_strnncollsp_any_uca,
    my_strnxfrm_any_uca,
    my_strnxfrmlen_simple,
    my_like_range_generic,
    my_wildcmp_uca,
    nullptr,
    my_instr_mb,
    my_hash_sort_any_uca,
    my_propagate_complex}

◆ my_collation_utf32_uca_handler

MY_COLLATION_HANDLER my_collation_utf32_uca_handler

Initial value:

= {
    my_coll_init_uca, 
    my_coll_uninit_uca,
    my_strnncoll_any_uca,
    my_strnncollsp_any_uca,
    my_strnxfrm_any_uca,
    my_strnxfrmlen_simple,
    my_like_range_generic,
    my_wildcmp_uca,
    nullptr,
    my_instr_mb,
    my_hash_sort_any_uca,
    my_propagate_complex}

◆ my_collation_utf8mb4_0900_bin_handler

MY_COLLATION_HANDLER my_collation_utf8mb4_0900_bin_handler

static

Initial value:

= {
    nullptr, 
    nullptr,
    my_strnncoll_mb_bin,
    my_strnncollsp_utf8mb4_0900_bin,
    my_strnxfrm_utf8mb4_0900_bin,
    my_strnxfrmlen_simple,
    my_like_range_mb,
    my_wildcmp_mb_bin,
    my_strcasecmp_mb_bin,
    my_instr_mb,
    my_hash_sort_mb_bin,
    my_propagate_simple}

◆ my_uca_v400

MY_UCA_INFO my_uca_v400

◆ my_uca_v520

MY_UCA_INFO my_uca_v520

◆ no_coll_param

Coll_param no_coll_param = {nullptr, false, CASE_FIRST_OFF}

static

◆ nochar

constexpr uint16_t nochar[] = {0, 0}

staticconstexpr

◆ persian

const char persian[]

static

Initial value:

=
    "& \\u066D < \\u064E < \\uFE76 < \\uFE77 < \\u0650 < \\uFE7A < \\uFE7B"
    " < \\u064F < \\uFE78 < \\uFE79 < \\u064B < \\uFE70 < \\uFE71"
    " < \\u064D < \\uFE74 < \\u064C < \\uFE72"
    "& \\uFE7F < \\u0653 < \\u0654 < \\u0655 < \\u0670"
    "& \\u0669 < \\u0622 < \\u0627 < \\u0671 < \\u0621 < \\u0623 < \\u0625"
    " < \\u0624 < \\u0626"
    "& \\u0642 < \\u06A9 < \\u0643"
    "& \\u0648 < \\u0647 < \\u0629 < \\u06C0 < \\u06CC < \\u0649 < \\u064A"
    "& \\uFE80 < \\uFE81 < \\uFE82 < \\uFE8D < \\uFE8E < \\uFB50 < \\uFB51"
    " < \\uFE80 "
    
    " & \\uFE80 < \\uFE83 < \\uFE84 < \\uFE87 < \\uFE88 < \\uFE85"
    " < \\uFE86 < \\u0689 < \\u068A"
    "& \\uFEAE < \\uFDFC"
    "& \\uFED8 < \\uFB8E < \\uFB8F < \\uFB90 < \\uFB91 < \\uFED9 < \\uFEDA"
    " < \\uFEDB < \\uFEDC"
    "& \\uFEEE < \\uFEE9 < \\uFEEA < \\uFEEB < \\uFEEC < \\uFE93 < \\uFE94"
    " < \\uFBA4 < \\uFBA5 < \\uFBFC < \\uFBFD < \\uFBFE < \\uFBFF"
    " < \\uFEEF < \\uFEF0 < \\uFEF1 < \\uFEF2 < \\uFEF3 < \\uFEF4"
    " < \\uFEF5 < \\uFEF6 < \\uFEF7 < \\uFEF8 < \\uFEF9 < \\uFEFA"
    " < \\uFEFB < \\uFEFC"

◆ pl_cldr_30

const char pl_cldr_30[]

static

Initial value:

=
    "&A < \\u0105 <<< \\u0104 "
    "&C < \\u0107 <<< \\u0106 "
    "&E < \\u0119 <<< \\u0118 "
    "&L < \\u0142 <<< \\u0141 "
    "&N < \\u0144 <<< \\u0143 "
    "&O < \\u00F3 <<< \\u00D3 "
    "&S < \\u015B <<< \\u015A "
    "&Z < \\u017A <<< \\u0179 < \\u017C <<< \\u017B"

◆ polish

const char polish[]

static

Initial value:

=
    "& A < \\u0105 <<< \\u0104 "
    "& C < \\u0107 <<< \\u0106 "
    "& E < \\u0119 <<< \\u0118 "
    "& L < \\u0142 <<< \\u0141 "
    "& N < \\u0144 <<< \\u0143 "
    "& O < \\u00F3 <<< \\u00D3 "
    "& S < \\u015B <<< \\u015A "
    "& Z < \\u017A <<< \\u0179 < \\u017C <<< \\u017B"

◆ ro_cldr_30

const char ro_cldr_30[]

static

Initial value:

=
    "&A < \\u0103 <<< \\u0102 <   \\u00E2 <<< \\u00C2 "
    "&I < \\u00EE <<< \\u00CE "
    "&S < \\u015F =   \\u0219 <<< \\u015E =   \\u0218 "
    "&T < \\u0163 =   \\u021B <<< \\u0162 =   \\u021A"

◆ roman

const char roman[]

static

Initial value:

= 
    "& I << j <<< J "
    "& V << u <<< U "

◆ romanian

const char romanian[]

static

Initial value:

=
    "& A < \\u0103 <<< \\u0102 < \\u00E2 <<< \\u00C2 "
    "& I < \\u00EE <<< \\u00CE "
    "& S < \\u0219 <<< \\u0218 << \\u015F <<< \\u015E "
    "& T < \\u021B <<< \\u021A << \\u0163 <<< \\u0162 "

◆ ru_coll_param

Coll_param ru_coll_param

static

Initial value:

= {&ru_reorder_param, false ,

CASE_FIRST_OFF}

ru_reorder_param

static Reorder_param ru_reorder_param

Definition: ctype-uca.cc:742

◆ ru_reorder_param

Reorder_param ru_reorder_param

static

Initial value:

= {

{CHARGRP_CYRILLIC, CHARGRP_NONE}, {{{0, 0}, {0, 0}}}, 0, 0}

◆ sinhala

const char sinhala[]

static

Initial value:

=
    "& \\u0D96 < \\u0D82 < \\u0D83 < \\u0D9A < \\u0D9B < \\u0D9C < \\u0D9D"
    "< \\u0D9E < \\u0D9F < \\u0DA0 < \\u0DA1 < \\u0DA2 < \\u0DA3"
    "< \\u0DA5 < \\u0DA4 < \\u0DA6"
    "< \\u0DA7 < \\u0DA8 < \\u0DA9 < \\u0DAA < \\u0DAB < \\u0DAC"
    "< \\u0DAD < \\u0DAE < \\u0DAF < \\u0DB0 < \\u0DB1"
    "< \\u0DB3 < \\u0DB4 < \\u0DB5 < \\u0DB6 < \\u0DB7 < \\u0DB8"
    "< \\u0DB9 < \\u0DBA < \\u0DBB < \\u0DBD < \\u0DC0 < \\u0DC1"
    "< \\u0DC2 < \\u0DC3 < \\u0DC4 < \\u0DC5 < \\u0DC6"
    "< \\u0DCF"
    "< \\u0DD0 < \\u0DD1 < \\u0DD2 < \\u0DD3 < \\u0DD4 < \\u0DD6"
    "< \\u0DD8 < \\u0DF2 < \\u0DDF < \\u0DF3 < \\u0DD9 < \\u0DDA"
    "< \\u0DDB < \\u0DDC < \\u0DDD < \\u0DDE < \\u0DCA"

◆ sk_cldr_30

const char sk_cldr_30[]

static

Initial value:

=
    "&A < \\u00E4 <<< \\u00C4 "
    "&C < \\u010D <<< \\u010C "
    "&H < ch      <<< cH      <<< Ch <<< CH "
    "&O < \\u00F4 <<< \\u00D4 "
    "&R < \\u0159 <<< \\u0158 "
    "&S < \\u0161 <<< \\u0160 "
    "&Z < \\u017E <<< \\u017D"

◆ sl_cldr_30

const char sl_cldr_30[]

static

Initial value:

=
    "&C < \\u010D <<< \\u010C < \\u0107 <<< \\u0106 "
    "&D < \\u0111 <<< \\u0110 "
    "&S < \\u0161 <<< \\u0160 "
    "&Z < \\u017E <<< \\u017D"

◆ slovak

const char slovak[]

static

Initial value:

=
    "& A < \\u00E4 <<< \\u00C4"
    "& C < \\u010D <<< \\u010C"
    "& H < ch <<< Ch <<< CH"
    "& O < \\u00F4 <<< \\u00D4"
    "& S < \\u0161 <<< \\u0160"
    "& Z < \\u017E <<< \\u017D"

◆ slovenian

const char slovenian[]

static

Initial value:

=
    "& C < \\u010D <<< \\u010C "
    "& S < \\u0161 <<< \\u0160 "
    "& Z < \\u017E <<< \\u017D "

◆ spanish

const char spanish[] = "& N < \\u00F1 <<< \\u00D1 "

static

◆ spanish2

const char spanish2[]

static

Initial value:

= 
    "&C <  ch <<< Ch <<< CH"
    "&L <  ll <<< Ll <<< LL"
    "&N < \\u00F1 <<< \\u00D1"

◆ sv_cldr_30

const char sv_cldr_30[]

static

Initial value:

=
    "&          D       <<  \\u0111   <<< \\u0110 <<  \\u00F0 <<< \\u00D0 "
    "&          t       <<< \\u00FE/h "
    "&          T       <<< \\u00DE/H "
    "&          Y       <<  \\u00FC   <<< \\u00DC <<  \\u0171 <<< \\u0170 "
    "&[before 1]\\u01C0 <   \\u00E5   <<< \\u00C5 <   \\u00E4 <<< \\u00C4 "
    "<< \\u00E6   <<< \\u00C6 <<  \\u0119 <<< \\u0118 "
    "<  \\u00F6   <<< \\u00D6 <<  \\u00F8 <<< \\u00D8 "
    "<< \\u0151   <<< \\u0150 <<  \\u0153 <<< \\u0152 "
    "<< \\u00F4   <<< \\u00D4"

◆ swedish

const char swedish[]

static

Initial value:

=
    "& Y <<\\u00FC <<< \\u00DC "
    "& Z < \\u00E5 <<< \\u00C5 "
    "< \\u00E4 <<< \\u00C4 << \\u00E6 <<< \\u00C6 "
    "< \\u00F6 <<< \\u00D6 << \\u00F8 <<< \\u00D8 "

◆ tr_cldr_30

const char tr_cldr_30[]

static

Initial value:

=
    "&          C <   \\u00E7 <<< \\u00C7 "
    "&          G <   \\u011F <<< \\u011E "
    "&[before 1]i <   \\u0131 <<< I "
    "&          i <<< \\u0130 "
    "&          O <   \\u00F6 <<< \\u00D6 "
    "&          S <   \\u015F <<< \\u015E "
    "&          U <   \\u00FC <<< \\u00DC "

◆ turkish

const char turkish[]

static

Initial value:

=
    "& C < \\u00E7 <<< \\u00C7 "
    "& G < \\u011F <<< \\u011E "
    "& H < \\u0131 <<< \\u0049 "
    "& O < \\u00F6 <<< \\u00D6 "
    "& S < \\u015F <<< \\u015E "
    "& U < \\u00FC <<< \\u00DC "

◆ vi_cldr_30

const char vi_cldr_30[]

static

Initial value:

=
    "&\\u0300 << \\u0309 <<  \\u0303 << \\u0301 <<  \\u0323 "
    "&a       < \\u0103 <<< \\u0102 <  \\u00E2 <<< \\u00C2 "
    "&d       < \\u0111 <<< \\u0110 "
    "&e       < \\u00EA <<< \\u00CA "
    "&o       < \\u00F4 <<< \\u00D4 <  \\u01A1 <<< \\u01A0 "
    "&u       < \\u01B0 <<< \\u01AF"

◆ vi_coll_param

Coll_param vi_coll_param = {nullptr, true, CASE_FIRST_OFF}

static

◆ vietnamese

const char vietnamese[]

static

◆ zh_coll_param

Coll_param zh_coll_param = {&zh_reorder_param, false, CASE_FIRST_OFF}

static

◆ zh_reorder_param

Reorder_param zh_reorder_param

static

Initial value:

= {

{CHARGRP_NONE}, {{{0x1C47, 0x54A3}, {0xBDC4, 0xF620}}}, 1, 0x54A3}

Classes

Macros

Typedefs

Enumerations

Functions

Variables

Macro Definition Documentation

◆ HANGUL_JAMO_MAX_LENGTH

◆ MY_CS_UTF16_UCA_FLAGS

◆ MY_CS_UTF32_UCA_FLAGS

◆ MY_CS_UTF8MB3_UCA_FLAGS

◆ MY_CS_UTF8MB4_UCA_FLAGS

◆ MY_UCA_MAX_EXPANSION

Typedef Documentation

◆ my_coll_lexem_num

Enumeration Type Documentation

◆ my_coll_lexem_num_en

◆ my_coll_shift_method

Function Documentation

◆ add_contraction_to_trie()

◆ add_normalization_rules()

◆ adjust_japanese_weight()

◆ apply_one_rule()

◆ apply_primary_shift_900()

◆ apply_secondary_shift_900()

◆ apply_shift()

◆ apply_shift_900()

◆ apply_tertiary_shift_900()

◆ ch2x()

◆ change_weight_if_case_first()

◆ change_zh_implicit()

◆ check_rules()

◆ combining_mark_in_rulelist()

◆ convert_implicit_to_ch()

◆ copy_ja_han_pages()

◆ copy_zh_han_pages()

◆ create_tailoring()

◆ find_contraction_part_in_trie() [1/2]

◆ find_contraction_part_in_trie() [2/2]

◆ get_decomposition()

◆ init_weight_level()

◆ is_hiragana_char()

◆ is_hiragana_iteration()

◆ is_ja_length_mark()

◆ is_katakana_char()

◆ is_katakana_iteration()

◆ is_tertiary_weight_upper_case()

◆ lex_cmp()

◆ modify_all_zh_pages()

◆ my_calc_char_grp_gap_param()

◆ my_calc_char_grp_param()

◆ my_char_weight_addr()

◆ my_char_weight_addr_900()

◆ my_char_weight_put()

◆ my_char_weight_put_900()

◆ my_coll_add_inherit_rules()

◆ my_coll_check_rule_and_inherit()

◆ my_coll_init_uca()

◆ my_coll_lexem_init()

◆ my_coll_lexem_next()

◆ my_coll_lexem_num_to_str()

◆ my_coll_lexem_print_error()

◆ my_coll_parser_curr()

◆ my_coll_parser_exec()

◆ my_coll_parser_expected_error()

◆ my_coll_parser_init()

◆ my_coll_parser_next()

◆ my_coll_parser_scan()

◆ my_coll_parser_scan_character_list()

◆ my_coll_parser_scan_logical_position()

◆ my_coll_parser_scan_reset_before()

◆ my_coll_parser_scan_reset_sequence()

◆ my_coll_parser_scan_rule()

◆ my_coll_parser_scan_setting()

◆ my_coll_parser_scan_settings()

◆ my_coll_parser_scan_shift()

◆ my_coll_parser_scan_shift_sequence()

◆ my_coll_parser_scan_term()

◆ my_coll_parser_too_long_error()

◆ my_coll_rule_expand()