summaryrefslogtreecommitdiff
path: root/doc
diff options
context:
space:
mode:
authorJörg Frings-Fürst <debian@jff.email>2020-04-20 20:34:10 +0200
committerJörg Frings-Fürst <debian@jff.email>2020-04-20 20:34:10 +0200
commitf3d6e46ce3762b6f51a166119d3982fd3715507a (patch)
tree0935fb6da7f1d9728b42ddf08395a0e977e1c228 /doc
parent043fff5b6f2461aeccb1c62cb771826cfe301832 (diff)
parent73c6133c32cddae59813cbadf655cb50a3a7356a (diff)
Merge branch 'feature/upstream' into develop
Diffstat (limited to 'doc')
-rw-r--r--doc/API60
-rw-r--r--doc/API.ja63
-rw-r--r--doc/RE50
-rw-r--r--doc/RE.ja47
-rw-r--r--doc/SYNTAX.md137
-rw-r--r--doc/UNICODE_PROPERTIES1455
6 files changed, 981 insertions, 831 deletions
diff --git a/doc/API b/doc/API
index 43d5338..bb7b010 100644
--- a/doc/API
+++ b/doc/API
@@ -1,4 +1,4 @@
-Oniguruma API Version 6.9.4 2019/09/30
+Oniguruma API Version 6.9.5 2020/03/25
#include <oniguruma.h>
@@ -273,6 +273,18 @@ Oniguruma API Version 6.9.4 2019/09/30
normal return: ONIG_NORMAL
+# int onig_set_retry_limit_in_search_of_match_param(OnigMatchParam* mp, unsigned long limit)
+
+ Set a retry limit count of a search process.
+ 0 means unlimited.
+
+ arguments
+ 1 mp: match-param pointer
+ 2 limit: number of limit
+
+ normal return: ONIG_NORMAL
+
+
# int onig_set_progress_callout_of_match_param(OnigMatchParam* mp, OnigCalloutFunc f)
Set a function for callouts of contents in progress.
@@ -333,7 +345,7 @@ Oniguruma API Version 6.9.4 2019/09/30
arguments
1-7: same as onig_search()
- 8 mp: match parameter values (match_stack_limit, retry_limit_in_match)
+ 8 mp: match parameter values (match_stack_limit, retry_limit_in_match, retry_limit_in_search)
# int onig_match(regex_t* reg, const UChar* str, const UChar* end, const UChar* at,
@@ -368,7 +380,7 @@ Oniguruma API Version 6.9.4 2019/09/30
arguments
1-6: same as onig_match()
- 7 mp: match parameter values (match_stack_limit, retry_limit_in_match)
+ 7 mp: match parameter values (match_stack_limit, retry_limit_in_match, retry_limit_in_search)
# int onig_scan(regex_t* reg, const UChar* str, const UChar* end,
@@ -599,8 +611,8 @@ Oniguruma API Version 6.9.4 2019/09/30
# int onig_foreach_name(regex_t* reg,
- int (*func)(const UChar*, const UChar*, int,int*,regex_t*,void*),
- void* arg)
+ int (*func)(const UChar*, const UChar*, int,int*,regex_t*,void*),
+ void* arg)
Iterate function call for all names.
@@ -866,19 +878,51 @@ Oniguruma API Version 6.9.4 2019/09/30
# unsigned long onig_get_retry_limit_in_match(void)
- Return the limit of retry counts in matching process.
+ Return the limit of retry counts in a matching process.
(default: 10000000)
- normal return: limit value
+ normal return: current limit value
+
+
+# unsigned long onig_get_retry_limit_in_search(void)
+
+ Return the limit of retry counts in a search process.
+ 0 means unlimited.
+ (default: 0)
+
+ normal return: current limit value
-# int onig_set_retry_limit_in_match(unsigned long n)
+# int onig_set_retry_limit_in_match(unsigned long limit)
Set the limit of retry counts in matching process.
normal return: ONIG_NORMAL
+# int onig_set_retry_limit_in_search(unsigned long limit)
+
+ Set a retry limit count of a search process.
+ 0 means unlimited.
+
+ normal return: ONIG_NORMAL
+
+
+# int onig_get_subexp_call_max_nest_level(void)
+
+ Return the limit of subexp call nest level.
+ (default: 24)
+
+ normal return: current limit value
+
+
+# int onig_set_subexp_call_max_nest_level(int max_level)
+
+ Set a limit level of subexp call nest level.
+
+ normal return: ONIG_NORMAL
+
+
# OnigCalloutFunc onig_get_progress_callout(void)
Get a function for callouts of contents in progress.
diff --git a/doc/API.ja b/doc/API.ja
index 10ee1cd..38ce8d6 100644
--- a/doc/API.ja
+++ b/doc/API.ja
@@ -1,4 +1,4 @@
-鬼車インターフェース Version 6.9.4 2019/09/30
+鬼車インターフェース Version 6.9.5 2020/03/25
#include <oniguruma.h>
@@ -263,7 +263,19 @@
# int onig_set_retry_limit_in_match_of_match_param(OnigMatchParam* mp, unsigned long limit)
- 一回のマッチでのリトライ数の最大値をセットする。
+ 一回のマッチでのリトライ数の制限値をセットする。
+
+ 引数
+ 1 mp: マッチパラメタオブジェクトアドレス
+ 2 limit: 制限回数
+
+ 正常終了戻り値: ONIG_NORMAL
+
+
+# int onig_set_retry_limit_in_search_of_match_param(OnigMatchParam* mp, unsigned long limit)
+
+ 一回の検索でのリトライ数の制限値をセットする。
+ 0は無制限を意味する。
引数
1 mp: マッチパラメタオブジェクトアドレス
@@ -331,7 +343,7 @@
引数
1-7: onig_search()と同じ
- 8 mp: マッチパラメタ値 (match_stack_limit, retry_limit_in_match)
+ 8 mp: マッチパラメタ値 (match_stack_limit, retry_limit_in_match, retry_limit_in_search)
# int onig_match(regex_t* reg, const UChar* str, const UChar* end,
@@ -365,7 +377,7 @@
引数
1-6: onig_match()と同じ
- 7 mp: マッチパラメタ値 (match_stack_limit, retry_limit_in_match)
+ 7 mp: マッチパラメタ値 (match_stack_limit, retry_limit_in_match, retry_limit_in_search)
# int onig_scan(regex_t* reg, const UChar* str, const UChar* end,
@@ -600,8 +612,8 @@
# int onig_foreach_name(regex_t* reg,
- int (*func)(const UChar*, const UChar*, int,int*,regex_t*,void*),
- void* arg)
+ int (*func)(const UChar*, const UChar*, int,int*,regex_t*,void*),
+ void* arg)
全ての名前に対してコールバック関数呼び出しを実行する。
@@ -872,15 +884,48 @@
# unsigned long onig_get_retry_limit_in_match(void)
- マッチング関数内でのリトライ数の制限値を返す。
+ 一回のマッチングでのリトライ数の制限値を返す。
(デフォルト: 10000000)
正常終了戻り値: 制限値
-# int onig_set_retry_limit_in_match(unsigned long n)
+# unsigned long onig_get_retry_limit_in_search(void)
+
+ 一回の検索でのリトライ数の制限値を返す。
+ 0は無制限を意味する。
+ (デフォルト: 0)
+
+ 正常終了戻り値: 制限値
+
+
+# int onig_set_retry_limit_in_match(unsigned long limit)
+
+ 一回のマッチング内でのリトライ数の制限値を指定する。
+
+ 正常終了戻り値: ONIG_NORMAL
+
+
+# int onig_set_retry_limit_in_search(unsigned long limit)
+
+ 一回の検索でのリトライ数の制限値をセットする。
+ 0は無制限を意味する。
+ (デフォルト: 0)
+
+ 正常終了戻り値: ONIG_NORMAL
+
+
+# int onig_get_subexp_call_max_nest_level(void)
+
+ 部分式呼出しのネストレベルの最大値を返す。
+ (デフォルト: 24)
+
+ 正常終了戻り値: 制限値
+
+
+# int onig_set_subexp_call_max_nest_level(int max_level)
- マッチング関数内でのリトライ数の制限値を指定する。
+ 部分式呼出しのネストレベルの最大値を指定する。
正常終了戻り値: ONIG_NORMAL
diff --git a/doc/RE b/doc/RE
index 599d2a6..f96efe7 100644
--- a/doc/RE
+++ b/doc/RE
@@ -1,6 +1,6 @@
-Oniguruma Regular Expressions Version 6.9.4 2019/10/31
+Oniguruma Regular Expressions Version 6.9.5 2020/04/09
-syntax: ONIG_SYNTAX_ONIGURUMA (default)
+syntax: ONIG_SYNTAX_ONIGURUMA (default syntax)
1. Syntax elements
@@ -21,19 +21,28 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
\f form feed (0x0C)
\a bell (0x07)
\e escape (0x1B)
- \nnn octal char (encoded byte value)
- \o{17777777777} wide octal char (character code point value)
- \uHHHH wide hexadecimal char (character code point value)
- \xHH hexadecimal char (encoded byte value)
- \x{7HHHHHHH} wide hexadecimal char (character code point value)
- \cx control char (character code point value)
- \C-x control char (character code point value)
- \M-x meta (x|0x80) (character code point value)
- \M-\C-x meta control char (character code point value)
+ \nnn octal char (encoded byte value)
+ \xHH hexadecimal char (encoded byte value)
+ \x{7HHHHHHH} (1-8 digits) hexadecimal char (code point value)
+ \o{17777777777} (1-11 digits) octal char (code point value)
+ \uHHHH hexadecimal char (code point value)
+ \cx control char (code point value)
+ \C-x control char (code point value)
+ \M-x meta (x|0x80) (code point value)
+ \M-\C-x meta control char (code point value)
(* \b as backspace is effective in character class only)
+2.1 Code point sequences
+
+ Hexadecimal code point (1-8 digits)
+ \x{7HHHHHHH 7HHHHHHH ... 7HHHHHHH}
+
+ Octal code point (1-11 digits)
+ \o{17777777777 17777777777 ... 17777777777}
+
+
3. Character types
. any character (except newline)
@@ -132,6 +141,7 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
{,n} at least 0 but no more than n times ({0,n})
{n} n times
+
reluctant
?? 0 or 1 times
@@ -141,6 +151,11 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
{n,}? at least n times
{,n}? at least 0 but not more than n times (== {0,n}?)
+ {n}? is reluctant operator in ONIG_SYNTAX_JAVA and ONIG_SYNTAX_PERL only.
+ (In that case, it doesn't make sense to write so.)
+ In default syntax, /a{n}?/ === /(?:a{n})?/
+
+
possessive (greedy and does not backtrack once match)
?+ 1 or 0 times
@@ -148,8 +163,8 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
++ 1 or more times
{n,m} (n > m) at least m but not more than n times
- {n,m}+, {n,}+, {n}+ are possessive operators in ONIG_SYNTAX_JAVA and
- ONIG_SYNTAX_PERL only.
+ {n,m}+, {n,}+, {n}+ are possessive operators in ONIG_SYNTAX_JAVA and
+ ONIG_SYNTAX_PERL only.
ex. /a*+/ === /(?>a*)/
@@ -279,15 +294,12 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
(?=subexp) look-ahead
(?!subexp) negative look-ahead
+
(?<=subexp) look-behind
(?<!subexp) negative look-behind
- Subexp of look-behind must be fixed-width.
- But top-level alternatives can be of various lengths.
- ex. (?<=a|bc) is OK. (?<=aaa(?:b|cd)) is not allowed.
-
- In negative look-behind, capturing group isn't allowed,
- but non-capturing group (?:) is allowed.
+ * Cannot use Absent stopper (?~|expr) and Range clear
+ (?~|) operators in look-behind and negative look-behind.
* In look-behind and negative look-behind, support for
ignore-case option is limited. Only supports conversion
diff --git a/doc/RE.ja b/doc/RE.ja
index 2156d93..6eacc8d 100644
--- a/doc/RE.ja
+++ b/doc/RE.ja
@@ -1,4 +1,4 @@
-鬼車 正規表現 Version 6.9.4 2019/10/31
+鬼車 正規表現 Version 6.9.5 2020/04/09
使用文法: ONIG_SYNTAX_ONIGURUMA (既定値)
@@ -21,19 +21,28 @@
\f 改頁 (0x0C)
\a 鐘 (0x07)
\e 退避修飾 (0x1B)
- \nnn 八進数表現 符号化バイト値
- \o{17777777777} 拡張八進数表現 コードポイント値
- \uHHHH 拡張十六進数表現 コードポイント値
- \xHH 十六進数表現 符号化バイト値
- \x{7HHHHHHH} 拡張十六進数表現 コードポイント値
- \cx 制御文字表現 コードポイント値
- \C-x 制御文字表現 コードポイント値
- \M-x 超 (x|0x80) コードポイント値
- \M-\C-x 超 + 制御文字表現 コードポイント値
+ \nnn 八進数表現 符号化バイト値
+ \xHH 十六進数表現 符号化バイト値
+ \x{7HHHHHHH} (1-8桁) 拡張十六進数表現 コードポイント値
+ \o{17777777777} (1-11桁) 拡張八進数表現 コードポイント値
+ \uHHHH 拡張十六進数表現 コードポイント値
+ \cx 制御文字表現 コードポイント値
+ \C-x 制御文字表現 コードポイント値
+ \M-x 超 (x|0x80) コードポイント値
+ \M-\C-x 超 + 制御文字表現 コードポイント値
※ \bは、文字集合内でのみ有効
+2.1 コードポイント連続表記
+
+ 十六進数表現コードポイント (1-8桁)
+ \x{7HHHHHHH 7HHHHHHH ... 7HHHHHHH}
+
+ 八進数表現コードポイント (1-11桁)
+ \o{17777777777 17777777777 ... 17777777777}
+
+
3. 文字種
. 任意文字 (改行を除く: オプションに依存)
@@ -131,6 +140,7 @@
{,n} 零回以上n回以下 ({0,n})
{n} n回
+
無欲
?? 零回または一回
@@ -140,6 +150,11 @@
{n,}? n回以上
{,n}? 零回以上n回以下 (== {0,n}?)
+ {n}? はONIG_SYNTAX_JAVAとONIG_SYNTAX_PERLでのみ無欲な指定子
+ (その場合には、態々そう書く意味はないが)
+ デフォルトの文法では、/a{n}?/ === /(?:a{n})?/
+
+
強欲 (欲張りで、繰り返しに成功した後は回数を減らすような後退再試行をしない)
?+ 一回または零回
@@ -147,7 +162,8 @@
++ 一回以上
{n,m} (n > m) m回以上 かつ n回以下
- {n,m}+, {n,}+, {n}+ は、ONIG_SYNTAX_JAVAとONIG_SYNTAX_PERLでのみ強欲な指定子
+ {n,m}+, {n,}+, {n}+ は、ONIG_SYNTAX_JAVAとONIG_SYNTAX_PERLでのみ
+ 強欲な指定子
例. /a*+/ === /(?>a*)/
@@ -274,15 +290,12 @@
(?=式) 先読み
(?!式) 否定先読み
+
(?<=式) 戻り読み
(?<!式) 否定戻り読み
- 戻り読みの式は固定文字長でなければならない。
- しかし、最上位の選択子だけは異なった文字長が許される。
- 例. (?<=a|bc) は許可. (?<=aaa(?:b|cd)) は不許可
-
- 否定戻り読みでは、捕獲式集合は許されないが、
- 非捕獲式集合は許される。
+ * 戻り読み、否定戻り読みの式の中では、不在停止演算子
+ (?~|expr)と範囲消去演算子(?~|)を使用することはできない
* 戻り読み、否定戻り読みの中では、ignore-caseオプションの
対応が制限される。一文字と一文字の間の変換しか対応しない。
diff --git a/doc/SYNTAX.md b/doc/SYNTAX.md
index 69ecf3a..c38e5c8 100644
--- a/doc/SYNTAX.md
+++ b/doc/SYNTAX.md
@@ -1,7 +1,7 @@
# Oniguruma syntax (operator) configuration
-_Documented for Oniguruma 6.9.3 (2019/08/08)_
+_Documented for Oniguruma 6.9.5 (2020/01/23)_
----------
@@ -75,7 +75,7 @@ data set by `onig_set_meta_char()` will be ignored.
### 1. ONIG_SYN_OP_DOT_ANYCHAR (enable `.`)
-_Set in: PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Java, Perl, Perl_NG, Ruby_
Enables support for the standard `.` metacharacter, meaning "any one character." You
usually want this flag on unless you have turned on `ONIG_SYN_OP_VARIABLE_META_CHARACTERS`
@@ -84,7 +84,7 @@ so that you can use a metacharacter other than `.` instead.
### 2. ONIG_SYN_OP_ASTERISK_ZERO_INF (enable `r*`)
-_Set in: PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the standard `r*` metacharacter, meaning "zero or more r's."
You usually want this flag set unless you have turned on `ONIG_SYN_OP_VARIABLE_META_CHARACTERS`
@@ -103,7 +103,7 @@ behavior.
### 4. ONIG_SYN_OP_PLUS_ONE_INF (enable `r+`)
-_Set in: PosixExtended, Emacs, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, Emacs, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the standard `r+` metacharacter, meaning "one or more r's."
You usually want this flag set unless you have turned on `ONIG_SYN_OP_VARIABLE_META_CHARACTERS`
@@ -122,7 +122,7 @@ behavior.
### 6. ONIG_SYN_OP_QMARK_ZERO_ONE (enable `r?`)
-_Set in: PosixExtended, Emacs, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, Emacs, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the standard `r?` metacharacter, meaning "zero or one r" or "an optional r."
You usually want this flag set unless you have turned on `ONIG_SYN_OP_VARIABLE_META_CHARACTERS`
@@ -141,7 +141,7 @@ you want `?` to simply match a literal `?` character, but you still want some wa
### 8. ONIG_SYN_OP_BRACE_INTERVAL (enable `r{l,u}`)
-_Set in: PosixExtended, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the `r{lower,upper}` range form, common to more advanced
regex engines, which lets you specify precisely a minimum and maximum range on how many r's
@@ -168,7 +168,7 @@ match literal curly brace characters, but you still want some way of activating
### 10. ONIG_SYN_OP_VBAR_ALT (enable `r|s`)
-_Set in: PosixExtended, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `r|s` alternation operator. You usually want this
flag set.
@@ -185,7 +185,7 @@ match a literal `|` character, but you still want some way of activating "altern
### 12. ONIG_SYN_OP_LPAREN_SUBEXP (enable `(r)`)
-_Set in: PosixExtended, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `(...)` grouping-and-capturing operators. You usually
want this flag set.
@@ -203,7 +203,7 @@ activating "grouping" or "capturing" behavior.
### 14. ONIG_SYN_OP_ESC_AZ_BUF_ANCHOR (enable `\A` and `\Z` and `\z`)
-_Set in: GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the anchors `\A` (start-of-string), `\Z` (end-of-string or
newline-at-end-of-string), and `\z` (end-of-string) escapes.
@@ -214,7 +214,7 @@ option will recognize that metacharacter instead.)
### 15. ONIG_SYN_OP_ESC_CAPITAL_G_BEGIN_ANCHOR (enable `\G`)
-_Set in: GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the special anchor `\G` (start-of-previous-match).
@@ -231,7 +231,7 @@ exactly the same as `\A`.
### 16. ONIG_SYN_OP_DECIMAL_BACKREF (enable `\num`)
-_Set in: PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for subsequent matches to back references to prior capture groups `(...)` using
the common `\num` syntax (like `\3`).
@@ -244,7 +244,7 @@ You usually want this enabled, and it is enabled by default in every built-in sy
### 17. ONIG_SYN_OP_BRACKET_CC (enable `[...]`)
-_Set in: PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixBasic, PosixExtended, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for recognizing character classes, like `[a-z]`. If this flag is not set, `[`
and `]` will be treated as ordinary literal characters instead of as metacharacters.
@@ -254,7 +254,7 @@ You usually want this enabled, and it is enabled by default in every built-in sy
### 18. ONIG_SYN_OP_ESC_W_WORD (enable `\w` and `\W`)
-_Set in: Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `\w` and `\W` shorthand forms. These match "word characters,"
whose meaning varies depending on the encoding being used.
@@ -285,7 +285,7 @@ Most regex syntaxes do _not_ support these metacharacters.
### 20. ONIG_SYN_OP_ESC_B_WORD_BOUND (enable `\b` and `\B`)
-_Set in: Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `\b` and `\B` word-boundary metacharacters. The `\b` metacharacter
matches a zero-width position at a transition from word-characters to non-word-characters, or vice
@@ -297,7 +297,7 @@ are considered "word characters."
### 21. ONIG_SYN_OP_ESC_S_WHITE_SPACE (enable `\s` and `\S`)
-_Set in: GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `\s` and `\S` whitespace-matching metacharacters.
@@ -319,7 +319,7 @@ Unicode-equivalent code points, and then matching according to Unicode rules.
### 22. ONIG_SYN_OP_ESC_D_DIGIT (enable `\d` and `\D`)
-_Set in: GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `\d` and `\D` digit-matching metacharacters.
@@ -337,7 +337,7 @@ Unicode-equivalent code points, and then matching according to Unicode rules.
### 23. ONIG_SYN_OP_LINE_ANCHOR (enable `^r` and `r$`)
-_Set in: Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Emacs, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the common `^` and `$` line-anchor metacharacters.
@@ -352,7 +352,7 @@ and not any other form.)
### 24. ONIG_SYN_OP_POSIX_BRACKET (enable POSIX `[:xxxx:]`)
-_Set in: PosixBasic, PosixExtended, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixBasic, PosixExtended, Grep, GnuRegex, Perl, Java, Perl_NG, Ruby_
Enables support for the POSIX `[:xxxx:]` character classes, like `[:alpha:]` and `[:digit:]`.
The supported POSIX character classes are `alnum`, `alpha`, `blank`, `cntrl`, `digit`,
@@ -361,7 +361,7 @@ The supported POSIX character classes are `alnum`, `alpha`, `blank`, `cntrl`, `d
### 25. ONIG_SYN_OP_QMARK_NON_GREEDY (enable `r??`, `r*?`, `r+?`, and `r{n,m}?`)
-_Set in: Perl, Java, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Java, Perl_NG, Ruby_
Enables support for lazy (non-greedy) quantifiers: That is, if you append a `?` after
another quantifier such as `?`, `*`, `+`, or `{n,m}`, Oniguruma will try to match
@@ -370,7 +370,7 @@ as _little_ as possible instead of as _much_ as possible.
### 26. ONIG_SYN_OP_ESC_CONTROL_CHARS (enable `\n`, `\r`, `\t`, etc.)
-_Set in: PosixBasic, PosixExtended, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixBasic, PosixExtended, Java, Perl, Perl_NG, Ruby_
Enables support for C-style control-code escapes, like `\n` and `\r`. Specifically,
this recognizes `\a` (7), `\b` (8), `\t` (9), `\n` (10), `\f` (12), `\r` (13), and
@@ -380,7 +380,7 @@ support for recognizing `\v` as code point 11.
### 27. ONIG_SYN_OP_ESC_C_CONTROL (enable `\cx` control codes)
-_Set in: Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Perl, Perl_NG, Ruby_
Enables support for named control-code escapes, like `\cm` or `\cM` for code-point
13. In this shorthand form, control codes may be specified by `\c` (for "Control")
@@ -390,7 +390,7 @@ followed by an alphabetic letter, a-z or A-Z, indicating which code point to rep
### 28. ONIG_SYN_OP_ESC_OCTAL3 (enable `\OOO` octal codes)
-_Set in: Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Perl, Perl_NG, Ruby_
Enables support for octal-style escapes of up to three digits, like `\1` for code
point 1, and `\177` for code point 127. Octal values greater than 255 will result
@@ -399,7 +399,7 @@ in an error message.
### 29. ONIG_SYN_OP_ESC_X_HEX2 (enable `\xHH` hex codes)
-_Set in: Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Perl, Perl_NG, Ruby_
Enables support for hexadecimal-style escapes of up to two digits, like `\x1` for code
point 1, and `\x7F` for code point 127.
@@ -407,7 +407,7 @@ point 1, and `\x7F` for code point 127.
### 30. ONIG_SYN_OP_ESC_X_BRACE_HEX8 (enable `\x{7HHHHHHH}` hex codes)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
Enables support for brace-wrapped hexadecimal-style escapes of up to eight digits,
like `\x{1}` for code point 1, and `\x{FFFE}` for code point 65534.
@@ -415,7 +415,7 @@ like `\x{1}` for code point 1, and `\x{FFFE}` for code point 65534.
### 31. ONIG_SYN_OP_ESC_O_BRACE_OCTAL (enable `\o{1OOOOOOOOOO}` octal codes)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
Enables support for brace-wrapped octal-style escapes of up to eleven digits,
like `\o{1}` for code point 1, and `\o{177776}` for code point 65534.
@@ -444,7 +444,7 @@ longer be treated as metacharacters, and instead will be matched as literal
### 1. ONIG_SYN_OP2_QMARK_GROUP_EFFECT (enable `(?...)`)
-_Set in: Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Perl, Perl_NG, Ruby_
Enables support for the fairly-common `(?...)` grouping operator, which
controls precedence but which does _not_ capture its contents.
@@ -465,7 +465,7 @@ The supported toggle-able options for this flag are:
### 3. ONIG_SYN_OP2_OPTION_RUBY (enable options `(?imx)` and `(?-imx)`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
Enables support of regex options. (i,m,x)
The supported toggle-able options for this flag are:
@@ -477,7 +477,7 @@ The supported toggle-able options for this flag are:
### 4. ONIG_SYN_OP2_PLUS_POSSESSIVE_REPEAT (enable `r?+`, `r*+`, and `r++`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
Enables support for the _possessive_ quantifiers `?+`, `*+`, and `++`, which
work similarly to `?` and `*` and `+`, respectively, but which do not backtrack
@@ -499,7 +499,7 @@ extent if subsequent parts of the pattern fail to match.
### 6. ONIG_SYN_OP2_CCLASS_SET_OP (enable `&&` within `[...]`)
-_Set in: Java, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Ruby_
Enables support for character-class _intersection_. For example, with this
feature enabled, you can write `[a-z&&[^aeiou]]` to produce a character class
@@ -509,7 +509,7 @@ all control codes _except_ newlines.
### 7. ONIG_SYN_OP2_QMARK_LT_NAMED_GROUP (enable named captures `(?<name>...)`)
-_Set in: Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl_NG, Ruby_
Enables support for _naming_ capture groups, so that instead of having to
refer to captures by position (like `\3` or `$3`), you can refer to them by names
@@ -519,7 +519,7 @@ and `(?'name'...)`, but not the Python `(?P<name>...)` syntax.
### 8. ONIG_SYN_OP2_ESC_K_NAMED_BACKREF (enable named backreferences `\k<name>`)
-_Set in: Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl_NG, Ruby_
Enables support for substituted backreferences by name, not just by position.
This supports using `\k'name'` in addition to supporting `\k<name>`. This also
@@ -530,7 +530,7 @@ the match, if the capture matched multiple times, by writing `\k<name+n>` or
### 9. ONIG_SYN_OP2_ESC_G_SUBEXP_CALL (enable backreferences `\g<name>` and `\g<n>`)
-_Set in: Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl_NG, Ruby_
Enables support for substituted backreferences by both name and position using
the same syntax. This supports using `\g'name'` and `\g'1'` in addition to
@@ -554,7 +554,7 @@ enabled by default in any syntax.
### 11. ONIG_SYN_OP2_ESC_CAPITAL_C_BAR_CONTROL (enable `\C-x`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
Enables support for Ruby legacy control-code escapes, like `\C-m` or `\C-M` for code-point
13. In this shorthand form, control codes may be specified by `\C-` (for "Control")
@@ -567,7 +567,7 @@ See also ONIG_SYN_OP_ESC_C_CONTROL, which enables the more-common `\cx` syntax.
### 12. ONIG_SYN_OP2_ESC_CAPITAL_M_BAR_META (enable `\M-x`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
Enables support for Ruby legacy meta-code escapes. When you write `\M-x`, Oniguruma
will match an `x` whose 8th bit is set (i.e., the character code of `x` will be or'ed
@@ -577,7 +577,7 @@ with `0x80`). So, for example, you can match `\x81` using `\x81`, or you can wr
### 13. ONIG_SYN_OP2_ESC_V_VTAB (enable `\v` as vertical tab)
-_Set in: Java, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Ruby_
Enables support for a C-style `\v` escape code, meaning "vertical tab." If enabled,
`\v` will be equivalent to ASCII code point 11.
@@ -585,7 +585,7 @@ Enables support for a C-style `\v` escape code, meaning "vertical tab." If enab
### 14. ONIG_SYN_OP2_ESC_U_HEX4 (enable `\uHHHH` for Unicode)
-_Set in: Java, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Ruby_
Enables support for a Java-style `\uHHHH` escape code for representing Unicode
code-points by number, using up to four hexadecimal digits (up to `\uFFFF`). So,
@@ -611,7 +611,7 @@ These anchor forms are very obscure, and rarely supported by other regex librari
### 16. ONIG_SYN_OP2_ESC_P_BRACE_CHAR_PROPERTY (enable `\p{...}` and `\P{...}`)
-_Set in: Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Perl, Perl_NG, Ruby_
Enables support for an alternate syntax for POSIX character classes; instead of
writing `[:alpha:]` when this is enabled, you can instead write `\p{alpha}`.
@@ -621,7 +621,7 @@ See also ONIG_SYN_OP_POSIX_BRACKET for the classic POSIX form.
### 17. ONIG_SYN_OP2_ESC_P_BRACE_CIRCUMFLEX_NOT (enable `\p{^...}` and `\P{^...}`)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
Enables support for an alternate syntax for POSIX character classes; instead of
writing `[:^alpha:]` when this is enabled, you can instead write `\p{^alpha}`.
@@ -636,7 +636,7 @@ _(not presently used)_
### 19. ONIG_SYN_OP2_ESC_H_XDIGIT (enable `\h` and `\H`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
Enables support for the Ruby-specific shorthand `\h` and `\H` metacharacters.
Somewhat like `\d` matches decimal digits, `\h` matches hexadecimal digits — that is,
@@ -658,7 +658,7 @@ You usually do not want this flag to be enabled.
### 21. ONIG_SYN_OP2_QMARK_LPAREN_IF_ELSE (enable `(?(...)then|else)`)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
Enables support for conditional inclusion of subsequent regex patterns based on whether
a prior named or numbered capture matched, or based on whether a pattern will
@@ -676,7 +676,7 @@ match. This supports many different forms, including:
### 22. ONIG_SYN_OP2_ESC_CAPITAL_K_KEEP (enable `\K`)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
Enables support for `\K`, which excludes all content before it from the overall
regex match (i.e., capture #0). So, for example, pattern `foo\Kbar` would match
@@ -687,7 +687,7 @@ regex match (i.e., capture #0). So, for example, pattern `foo\Kbar` would match
### 23. ONIG_SYN_OP2_ESC_CAPITAL_R_GENERAL_NEWLINE (enable `\R`)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
Enables support for `\R`, the "general newline" shorthand, which matches
`(\r\n|[\n\v\f\r\u0085\u2028\u2029])` (obviously, the Unicode values are cannot be
@@ -698,7 +698,7 @@ matched in ASCII encodings).
### 24. ONIG_SYN_OP2_ESC_CAPITAL_N_O_SUPER_DOT (enable `\N` and `\O`)
-_Set in: Perl, Perl_NG, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG_
Enables support for `\N` and `\O`. `\N` is "not a line break," which is much
like the standard `.` metacharacter, except that while `.` can be affected by
@@ -713,7 +713,7 @@ multi-line mode are enabled or disabled.
### 25. ONIG_SYN_OP2_QMARK_TILDE_ABSENT_GROUP (enable `(?~...)`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
Enables support for the `(?~r)` "absent operator" syntax, which matches
as much as possible as long as the result _doesn't_ match pattern `r`. This is
@@ -731,7 +731,7 @@ excellent article about it is [available on Medium](https://medium.com/rubyinsid
### 26. ONIG_SYN_OP2_ESC_X_Y_TEXT_SEGMENT (enable `\X` and `\Y` and `\y`)
-_Set in: Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG, Ruby_
`\X` is another variation on `.`, designed to support Unicode, in that it matches
a full _grapheme cluster_. In Unicode, `à` can be encoded as one code point,
@@ -764,7 +764,7 @@ backreferences.
### 28. ONIG_SYN_OP2_QMARK_BRACE_CALLOUT_CONTENTS (enable `(?{...})`)
-_Set in: Perl, Perl_NG, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG_
Enables support for Perl-style "callouts" — pattern substitutions that result from
invoking a callback method. When `(?{foo})` is reached in a pattern, the callback
@@ -779,7 +779,7 @@ Full documentation for this advanced feature can be found in the Oniguruma
### 29. ONIG_SYN_OP2_ASTERISK_CALLOUT_NAME (enable `(*name)`)
-_Set in: Perl, Perl_NG, Oniguruma_
+_Set in: Oniguruma, Perl, Perl_NG_
Enables support for Perl-style "callouts" — pattern substitutions that result from
invoking a callback method. When `(*foo)` is reached in a pattern, the callback
@@ -820,7 +820,7 @@ some syntaxes but not in others.
### 0. ONIG_SYN_CONTEXT_INDEP_REPEAT_OPS (independent `?`, `*`, `+`, `{n,m}`)
-_Set in: PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby_
This flag specifies how to handle operators like `?` and `*` when they aren't
directly attached to an operand, as in `^*` or `(*)`: Are they an error, are
@@ -830,7 +830,7 @@ determines if they are errors or if they are discarded.
### 1. ONIG_SYN_CONTEXT_INVALID_REPEAT_OPS (error or ignore independent operators)
-_Set in: PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby_
If ONIG_SYN_CONTEXT_INDEP_REPEAT_OPS is set, this flag controls what happens when
independent operators appear in a pattern: If this flag is set, then independent
@@ -847,7 +847,7 @@ character will produce an error message.
### 3. ONIG_SYN_ALLOW_INVALID_INTERVAL (allow `{???`)
-_Set in: GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, GnuRegex, Java, Perl, Perl_NG, Ruby_
This flag, if set, causes an invalid range, like `foo{bar}` or `foo{}`, to be
silently discarded, as if `foo` had been written instead. If clear, an invalid
@@ -855,7 +855,7 @@ range will produce an error message.
### 4. ONIG_SYN_ALLOW_INTERVAL_LOW_ABBREV (allow `{,n}` to mean `{0,n}`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
If this flag is set, then `r{,n}` will be treated as equivalent to writing
`{0,n}`. If this flag is clear, then `r{,n}` will produce an error message.
@@ -876,7 +876,7 @@ No built-in syntax has this flag enabled.
### 6. ONIG_SYN_DIFFERENT_LEN_ALT_LOOK_BEHIND (allow `(?<=a|bc)`)
-_Set in: Java, Ruby, Oniguruma_
+_Set in: Oniguruma, Java, Ruby_
If this flag is set, lookbehind patterns with alternate options may have differing
lengths among those options. If this flag is clear, lookbehind patterns with options
@@ -888,7 +888,7 @@ depend on this rule.
### 7. ONIG_SYN_CAPTURE_ONLY_NAMED_GROUP (prefer `\k<name>` over `\3`)
-_Set in: Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl_NG, Ruby_
If this flag is set on the syntax *and* ONIG_OPTION_CAPTURE_GROUP is set when calling
Oniguruma, then if a name is used on any capture, all captures must also use names: A
@@ -896,20 +896,33 @@ single use of a named capture prohibits the use of numbered captures.
### 8. ONIG_SYN_ALLOW_MULTIPLEX_DEFINITION_NAME (allow `(?<x>)...(?<x>)`)
-_Set in: Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, Perl_NG, Ruby_
If this flag is set, multiple capture groups may use the same name. If this flag is
clear, then reuse of a name will produce an error message.
### 9. ONIG_SYN_FIXED_INTERVAL_IS_GREEDY_ONLY (`a{n}?` is equivalent to `(?:a{n})?`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
If this flag is set, then intervals of a fixed size will ignore a lazy (non-greedy)
`?` quantifier and treat it as an optional match (an ordinary `r?`), since "match as
little as possible" is meaningless for a fixed-size interval. If this flag is clear,
then `r{n}?` will mean the same as `r{n}`, and the useless `?` will be discarded.
+### 10. ONIG_SYN_ISOLATED_OPTION_CONTINUE_BRANCH (`..(?i)..`)
+
+_Set in: Perl, Perl_NG, Java_
+
+If this flag is set, then an isolated option doesn't break the branch and affects until the end of the group (or end of the pattern).
+If this flag is not set, then an isolated option is interpreted as the starting point of a new branch. /a(?i)b|c/ ==> /a(?i:b|c)/
+
+### 11. ONIG_SYN_VARIABLE_LEN_LOOK_BEHIND (`(?<=...a+...)`)
+
+_Set in: Oniguruma, Java_
+
+If this flag is set, then a variable length expressions are allowed in look-behind.
+
### 20. ONIG_SYN_NOT_NEWLINE_IN_NEGATIVE_CC (add `\n` to `[^...]`)
_Set in: Grep_
@@ -921,7 +934,7 @@ only exclude those characters and ranges written in them.
### 21. ONIG_SYN_BACKSLASH_ESCAPE_IN_CC (allow `[...\w...]`)
-_Set in: GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, GnuRegex, Java, Perl, Perl_NG, Ruby_
If this flag is set, shorthands like `\w` are allowed to describe characters in character
classes. If this flag is clear, shorthands like `\w` are treated as a redundantly-escaped
@@ -937,7 +950,7 @@ character ranges will produce an error message.
### 23. ONIG_SYN_ALLOW_DOUBLE_RANGE_OP_IN_CC (treat `[0-9-a]` as `[0-9\-a]`)
-_Set in: PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby_
If this flag is set, then a trailing `-` after a character range will be taken as a
literal `-`, as if it had been escaped as `\-`. If this flag is clear, then a trailing
@@ -945,7 +958,7 @@ literal `-`, as if it had been escaped as `\-`. If this flag is clear, then a t
### 24. ONIG_SYN_WARN_CC_OP_NOT_ESCAPED (warn on `[[...]` and `[-x]`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
If this flag is set, Oniguruma will be stricter about warning for bad forms in
character classes: `[[...]` will produce a warning, but `[\[...]` will not;
@@ -955,7 +968,7 @@ will be silently discarded.
### 25. ONIG_SYN_WARN_REDUNDANT_NESTED_REPEAT (warn on `(?:a*)+`)
-_Set in: Ruby, Oniguruma_
+_Set in: Oniguruma, Ruby_
If this flag is set, Oniguruma will warn about nested repeat operators those have no meaning, like `(?:a*)+`.
If this flag is clear, Oniguruma will allow the nested repeat operators without warning about them.
@@ -968,7 +981,7 @@ If this flag is set, then invalid code points at the end of range in character c
### 31. ONIG_SYN_CONTEXT_INDEP_ANCHORS
-_Set in: PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby, Oniguruma_
+_Set in: Oniguruma, PosixExtended, GnuRegex, Java, Perl, Perl_NG, Ruby_
Not currently used, and does nothing. (But still set in several syntaxes for some
reason.)
@@ -1062,10 +1075,12 @@ These tables show which of the built-in syntaxes use which flags and options, fo
| 3 | `ONIG_SYN_ALLOW_INVALID_INTERVAL` | - | - | - | - | Yes | Yes | Yes | Yes | Yes | Yes |
| 4 | `ONIG_SYN_ALLOW_INTERVAL_LOW_ABBREV` | - | - | - | - | - | - | - | - | Yes | Yes |
| 5 | `ONIG_SYN_STRICT_CHECK_BACKREF` | - | - | - | - | - | - | - | - | - | - |
-| 6 | `ONIG_SYN_DIFFERENT_LEN_ALT_LOOK_BEHIND` | - | - | - | - | - | - | - | Yes | Yes | Yes |
+| 6 | `ONIG_SYN_DIFFERENT_LEN_ALT_LOOK_BEHIND` | - | - | - | - | - | Yes | - | - | Yes | Yes |
| 7 | `ONIG_SYN_CAPTURE_ONLY_NAMED_GROUP` | - | - | - | - | - | - | - | Yes | Yes | Yes |
| 8 | `ONIG_SYN_ALLOW_MULTIPLEX_DEFINITION_NAME` | - | - | - | - | - | - | - | Yes | Yes | Yes |
| 9 | `ONIG_SYN_FIXED_INTERVAL_IS_GREEDY_ONLY` | - | - | - | - | - | - | - | - | Yes | Yes |
+| 10 | `ONIG_SYN_ISOLATED_OPTION_CONTINUE_BRANCH` | - | - | - | - | - | Yes | Yes | Yes | - | - |
+| 11 | `ONIG_SYN_VARIABLE_LEN_LOOK_BEHIND` | - | - | - | - | - | Yes | - | - | - | Yes |
| 20 | `ONIG_SYN_NOT_NEWLINE_IN_NEGATIVE_CC` | - | - | - | Yes | - | - | - | - | - | - |
| 21 | `ONIG_SYN_BACKSLASH_ESCAPE_IN_CC` | - | - | - | - | Yes | Yes | Yes | Yes | Yes | Yes |
| 22 | `ONIG_SYN_ALLOW_EMPTY_RANGE_IN_CC` | - | - | Yes | Yes | - | - | - | - | - | - |
diff --git a/doc/UNICODE_PROPERTIES b/doc/UNICODE_PROPERTIES
index 24c2031..2227ada 100644
--- a/doc/UNICODE_PROPERTIES
+++ b/doc/UNICODE_PROPERTIES
@@ -1,4 +1,4 @@
-Unicode Properties (Unicode Version: 12.1.0, Emoji: 12.1)
+Unicode Properties (Unicode Version: 13.0.0, Emoji: 13.0)
15: ASCII_Hex_Digit
16: Adlam
@@ -38,225 +38,229 @@ Unicode Properties (Unicode Version: 12.1.0, Emoji: 12.1)
50: Changes_When_Titlecased
51: Changes_When_Uppercased
52: Cherokee
- 53: Cn
- 54: Co
- 55: Common
- 56: Coptic
- 57: Cs
- 58: Cuneiform
- 59: Cypriot
- 60: Cyrillic
- 61: Dash
- 62: Default_Ignorable_Code_Point
- 63: Deprecated
- 64: Deseret
- 65: Devanagari
- 66: Diacritic
- 67: Dogra
- 68: Duployan
- 69: Egyptian_Hieroglyphs
- 70: Elbasan
- 71: Elymaic
- 72: Emoji
- 73: Emoji_Component
- 74: Emoji_Modifier
- 75: Emoji_Modifier_Base
- 76: Emoji_Presentation
- 77: Ethiopic
- 78: Extended_Pictographic
- 79: Extender
- 80: Georgian
- 81: Glagolitic
- 82: Gothic
- 83: Grantha
- 84: Grapheme_Base
- 85: Grapheme_Extend
- 86: Grapheme_Link
- 87: Greek
- 88: Gujarati
- 89: Gunjala_Gondi
- 90: Gurmukhi
- 91: Han
- 92: Hangul
- 93: Hanifi_Rohingya
- 94: Hanunoo
- 95: Hatran
- 96: Hebrew
- 97: Hex_Digit
- 98: Hiragana
- 99: Hyphen
-100: IDS_Binary_Operator
-101: IDS_Trinary_Operator
-102: ID_Continue
-103: ID_Start
-104: Ideographic
-105: Imperial_Aramaic
-106: Inherited
-107: Inscriptional_Pahlavi
-108: Inscriptional_Parthian
-109: Javanese
-110: Join_Control
-111: Kaithi
-112: Kannada
-113: Katakana
-114: Kayah_Li
-115: Kharoshthi
-116: Khmer
-117: Khojki
-118: Khudawadi
-119: L
-120: LC
-121: Lao
-122: Latin
-123: Lepcha
-124: Limbu
-125: Linear_A
-126: Linear_B
-127: Lisu
-128: Ll
-129: Lm
-130: Lo
-131: Logical_Order_Exception
-132: Lowercase
-133: Lt
-134: Lu
-135: Lycian
-136: Lydian
-137: M
-138: Mahajani
-139: Makasar
-140: Malayalam
-141: Mandaic
-142: Manichaean
-143: Marchen
-144: Masaram_Gondi
-145: Math
-146: Mc
-147: Me
-148: Medefaidrin
-149: Meetei_Mayek
-150: Mende_Kikakui
-151: Meroitic_Cursive
-152: Meroitic_Hieroglyphs
-153: Miao
-154: Mn
-155: Modi
-156: Mongolian
-157: Mro
-158: Multani
-159: Myanmar
-160: N
-161: Nabataean
-162: Nandinagari
-163: Nd
-164: New_Tai_Lue
-165: Newa
-166: Nko
-167: Nl
-168: No
-169: Noncharacter_Code_Point
-170: Nushu
-171: Nyiakeng_Puachue_Hmong
-172: Ogham
-173: Ol_Chiki
-174: Old_Hungarian
-175: Old_Italic
-176: Old_North_Arabian
-177: Old_Permic
-178: Old_Persian
-179: Old_Sogdian
-180: Old_South_Arabian
-181: Old_Turkic
-182: Oriya
-183: Osage
-184: Osmanya
-185: Other_Alphabetic
-186: Other_Default_Ignorable_Code_Point
-187: Other_Grapheme_Extend
-188: Other_ID_Continue
-189: Other_ID_Start
-190: Other_Lowercase
-191: Other_Math
-192: Other_Uppercase
-193: P
-194: Pahawh_Hmong
-195: Palmyrene
-196: Pattern_Syntax
-197: Pattern_White_Space
-198: Pau_Cin_Hau
-199: Pc
-200: Pd
-201: Pe
-202: Pf
-203: Phags_Pa
-204: Phoenician
-205: Pi
-206: Po
-207: Prepended_Concatenation_Mark
-208: Ps
-209: Psalter_Pahlavi
-210: Quotation_Mark
-211: Radical
-212: Regional_Indicator
-213: Rejang
-214: Runic
-215: S
-216: Samaritan
-217: Saurashtra
-218: Sc
-219: Sentence_Terminal
-220: Sharada
-221: Shavian
-222: Siddham
-223: SignWriting
-224: Sinhala
-225: Sk
-226: Sm
-227: So
-228: Soft_Dotted
-229: Sogdian
-230: Sora_Sompeng
-231: Soyombo
-232: Sundanese
-233: Syloti_Nagri
-234: Syriac
-235: Tagalog
-236: Tagbanwa
-237: Tai_Le
-238: Tai_Tham
-239: Tai_Viet
-240: Takri
-241: Tamil
-242: Tangut
-243: Telugu
-244: Terminal_Punctuation
-245: Thaana
-246: Thai
-247: Tibetan
-248: Tifinagh
-249: Tirhuta
-250: Ugaritic
-251: Unified_Ideograph
-252: Unknown
-253: Uppercase
-254: Vai
-255: Variation_Selector
-256: Wancho
-257: Warang_Citi
-258: White_Space
-259: XID_Continue
-260: XID_Start
-261: Yi
-262: Z
-263: Zanabazar_Square
-264: Zl
-265: Zp
-266: Zs
+ 53: Chorasmian
+ 54: Cn
+ 55: Co
+ 56: Common
+ 57: Coptic
+ 58: Cs
+ 59: Cuneiform
+ 60: Cypriot
+ 61: Cyrillic
+ 62: Dash
+ 63: Default_Ignorable_Code_Point
+ 64: Deprecated
+ 65: Deseret
+ 66: Devanagari
+ 67: Diacritic
+ 68: Dives_Akuru
+ 69: Dogra
+ 70: Duployan
+ 71: Egyptian_Hieroglyphs
+ 72: Elbasan
+ 73: Elymaic
+ 74: Emoji
+ 75: Emoji_Component
+ 76: Emoji_Modifier
+ 77: Emoji_Modifier_Base
+ 78: Emoji_Presentation
+ 79: Ethiopic
+ 80: Extended_Pictographic
+ 81: Extender
+ 82: Georgian
+ 83: Glagolitic
+ 84: Gothic
+ 85: Grantha
+ 86: Grapheme_Base
+ 87: Grapheme_Extend
+ 88: Grapheme_Link
+ 89: Greek
+ 90: Gujarati
+ 91: Gunjala_Gondi
+ 92: Gurmukhi
+ 93: Han
+ 94: Hangul
+ 95: Hanifi_Rohingya
+ 96: Hanunoo
+ 97: Hatran
+ 98: Hebrew
+ 99: Hex_Digit
+100: Hiragana
+101: Hyphen
+102: IDS_Binary_Operator
+103: IDS_Trinary_Operator
+104: ID_Continue
+105: ID_Start
+106: Ideographic
+107: Imperial_Aramaic
+108: Inherited
+109: Inscriptional_Pahlavi
+110: Inscriptional_Parthian
+111: Javanese
+112: Join_Control
+113: Kaithi
+114: Kannada
+115: Katakana
+116: Kayah_Li
+117: Kharoshthi
+118: Khitan_Small_Script
+119: Khmer
+120: Khojki
+121: Khudawadi
+122: L
+123: LC
+124: Lao
+125: Latin
+126: Lepcha
+127: Limbu
+128: Linear_A
+129: Linear_B
+130: Lisu
+131: Ll
+132: Lm
+133: Lo
+134: Logical_Order_Exception
+135: Lowercase
+136: Lt
+137: Lu
+138: Lycian
+139: Lydian
+140: M
+141: Mahajani
+142: Makasar
+143: Malayalam
+144: Mandaic
+145: Manichaean
+146: Marchen
+147: Masaram_Gondi
+148: Math
+149: Mc
+150: Me
+151: Medefaidrin
+152: Meetei_Mayek
+153: Mende_Kikakui
+154: Meroitic_Cursive
+155: Meroitic_Hieroglyphs
+156: Miao
+157: Mn
+158: Modi
+159: Mongolian
+160: Mro
+161: Multani
+162: Myanmar
+163: N
+164: Nabataean
+165: Nandinagari
+166: Nd
+167: New_Tai_Lue
+168: Newa
+169: Nko
+170: Nl
+171: No
+172: Noncharacter_Code_Point
+173: Nushu
+174: Nyiakeng_Puachue_Hmong
+175: Ogham
+176: Ol_Chiki
+177: Old_Hungarian
+178: Old_Italic
+179: Old_North_Arabian
+180: Old_Permic
+181: Old_Persian
+182: Old_Sogdian
+183: Old_South_Arabian
+184: Old_Turkic
+185: Oriya
+186: Osage
+187: Osmanya
+188: Other_Alphabetic
+189: Other_Default_Ignorable_Code_Point
+190: Other_Grapheme_Extend
+191: Other_ID_Continue
+192: Other_ID_Start
+193: Other_Lowercase
+194: Other_Math
+195: Other_Uppercase
+196: P
+197: Pahawh_Hmong
+198: Palmyrene
+199: Pattern_Syntax
+200: Pattern_White_Space
+201: Pau_Cin_Hau
+202: Pc
+203: Pd
+204: Pe
+205: Pf
+206: Phags_Pa
+207: Phoenician
+208: Pi
+209: Po
+210: Prepended_Concatenation_Mark
+211: Ps
+212: Psalter_Pahlavi
+213: Quotation_Mark
+214: Radical
+215: Regional_Indicator
+216: Rejang
+217: Runic
+218: S
+219: Samaritan
+220: Saurashtra
+221: Sc
+222: Sentence_Terminal
+223: Sharada
+224: Shavian
+225: Siddham
+226: SignWriting
+227: Sinhala
+228: Sk
+229: Sm
+230: So
+231: Soft_Dotted
+232: Sogdian
+233: Sora_Sompeng
+234: Soyombo
+235: Sundanese
+236: Syloti_Nagri
+237: Syriac
+238: Tagalog
+239: Tagbanwa
+240: Tai_Le
+241: Tai_Tham
+242: Tai_Viet
+243: Takri
+244: Tamil
+245: Tangut
+246: Telugu
+247: Terminal_Punctuation
+248: Thaana
+249: Thai
+250: Tibetan
+251: Tifinagh
+252: Tirhuta
+253: Ugaritic
+254: Unified_Ideograph
+255: Unknown
+256: Uppercase
+257: Vai
+258: Variation_Selector
+259: Wancho
+260: Warang_Citi
+261: White_Space
+262: XID_Continue
+263: XID_Start
+264: Yezidi
+265: Yi
+266: Z
+267: Zanabazar_Square
+268: Zl
+269: Zp
+270: Zs
16: Adlm
42: Aghb
15: AHex
21: Arab
-105: Armi
+107: Armi
22: Armn
24: Avst
25: Bali
@@ -274,515 +278,532 @@ Unicode Properties (Unicode Version: 12.1.0, Emoji: 12.1)
45: Cakm
38: Cans
39: Cari
-120: Cased_Letter
+123: Cased_Letter
52: Cher
+ 53: Chrs
40: CI
-201: Close_Punctuation
-137: Combining_Mark
-199: Connector_Punctuation
+204: Close_Punctuation
+140: Combining_Mark
+202: Connector_Punctuation
43: Control
- 56: Copt
- 59: Cprt
-218: Currency_Symbol
+ 57: Copt
+ 60: Cprt
+221: Currency_Symbol
47: CWCF
48: CWCM
49: CWL
50: CWT
51: CWU
- 60: Cyrl
-200: Dash_Punctuation
-163: Decimal_Number
- 63: Dep
- 65: Deva
- 62: DI
- 66: Dia
- 67: Dogr
- 64: Dsrt
- 68: Dupl
- 69: Egyp
- 70: Elba
- 71: Elym
-147: Enclosing_Mark
- 77: Ethi
- 79: Ext
-202: Final_Punctuation
+ 61: Cyrl
+203: Dash_Punctuation
+166: Decimal_Number
+ 64: Dep
+ 66: Deva
+ 63: DI
+ 67: Dia
+ 68: Diak
+ 69: Dogr
+ 65: Dsrt
+ 70: Dupl
+ 77: EBase
+ 75: EComp
+ 71: Egyp
+ 72: Elba
+ 73: Elym
+ 76: EMod
+150: Enclosing_Mark
+ 78: EPres
+ 79: Ethi
+ 81: Ext
+ 80: ExtPict
+205: Final_Punctuation
44: Format
- 80: Geor
- 81: Glag
- 89: Gong
-144: Gonm
- 82: Goth
- 83: Gran
- 84: Gr_Base
- 87: Grek
- 85: Gr_Ext
- 86: Gr_Link
- 88: Gujr
- 90: Guru
- 92: Hang
- 91: Hani
- 94: Hano
- 95: Hatr
- 96: Hebr
- 97: Hex
- 98: Hira
+ 82: Geor
+ 83: Glag
+ 91: Gong
+147: Gonm
+ 84: Goth
+ 85: Gran
+ 86: Gr_Base
+ 89: Grek
+ 87: Gr_Ext
+ 88: Gr_Link
+ 90: Gujr
+ 92: Guru
+ 94: Hang
+ 93: Hani
+ 96: Hano
+ 97: Hatr
+ 98: Hebr
+ 99: Hex
+100: Hira
19: Hluw
-194: Hmng
-171: Hmnp
-174: Hung
-102: IDC
-104: Ideo
-103: IDS
-100: IDSB
-101: IDST
-205: Initial_Punctuation
-175: Ital
-109: Java
-110: Join_C
-114: Kali
-113: Kana
-115: Khar
-116: Khmr
-117: Khoj
-112: Knda
-111: Kthi
-238: Lana
-121: Laoo
-122: Latn
-123: Lepc
-119: Letter
-167: Letter_Number
-124: Limb
-125: Lina
-126: Linb
-264: Line_Separator
-131: LOE
-128: Lowercase_Letter
-135: Lyci
-136: Lydi
-138: Mahj
-139: Maka
-141: Mand
-142: Mani
-143: Marc
-137: Mark
-226: Math_Symbol
-148: Medf
-150: Mend
-151: Merc
-152: Mero
-140: Mlym
-129: Modifier_Letter
-225: Modifier_Symbol
-156: Mong
-157: Mroo
-149: Mtei
-158: Mult
-159: Mymr
-162: Nand
-176: Narb
-161: Nbat
-169: NChar
-166: Nkoo
-154: Nonspacing_Mark
-170: Nshu
-160: Number
-185: OAlpha
-186: ODI
-172: Ogam
-187: OGr_Ext
-188: OIDC
-189: OIDS
-173: Olck
-190: OLower
-191: OMath
-208: Open_Punctuation
-181: Orkh
-182: Orya
-183: Osge
-184: Osma
+197: Hmng
+174: Hmnp
+177: Hung
+104: IDC
+106: Ideo
+105: IDS
+102: IDSB
+103: IDST
+208: Initial_Punctuation
+178: Ital
+111: Java
+112: Join_C
+116: Kali
+115: Kana
+117: Khar
+119: Khmr
+120: Khoj
+118: Kits
+114: Knda
+113: Kthi
+241: Lana
+124: Laoo
+125: Latn
+126: Lepc
+122: Letter
+170: Letter_Number
+127: Limb
+128: Lina
+129: Linb
+268: Line_Separator
+134: LOE
+131: Lowercase_Letter
+138: Lyci
+139: Lydi
+141: Mahj
+142: Maka
+144: Mand
+145: Mani
+146: Marc
+140: Mark
+229: Math_Symbol
+151: Medf
+153: Mend
+154: Merc
+155: Mero
+143: Mlym
+132: Modifier_Letter
+228: Modifier_Symbol
+159: Mong
+160: Mroo
+152: Mtei
+161: Mult
+162: Mymr
+165: Nand
+179: Narb
+164: Nbat
+172: NChar
+169: Nkoo
+157: Nonspacing_Mark
+173: Nshu
+163: Number
+188: OAlpha
+189: ODI
+175: Ogam
+190: OGr_Ext
+191: OIDC
+192: OIDS
+176: Olck
+193: OLower
+194: OMath
+211: Open_Punctuation
+184: Orkh
+185: Orya
+186: Osge
+187: Osma
37: Other
-130: Other_Letter
-168: Other_Number
-206: Other_Punctuation
-227: Other_Symbol
-192: OUpper
-195: Palm
-265: Paragraph_Separator
-196: Pat_Syn
-197: Pat_WS
-198: Pauc
-207: PCM
-177: Perm
-203: Phag
-107: Phli
-209: Phlp
-204: Phnx
-153: Plrd
- 54: Private_Use
-108: Prti
-193: Punctuation
- 56: Qaac
-106: Qaai
-210: QMark
-212: RI
-213: Rjng
- 93: Rohg
-214: Runr
-216: Samr
-180: Sarb
-217: Saur
-228: SD
-262: Separator
-223: Sgnw
-221: Shaw
-220: Shrd
-222: Sidd
-118: Sind
-224: Sinh
-229: Sogd
-179: Sogo
-230: Sora
-231: Soyo
-266: Space_Separator
-146: Spacing_Mark
-219: STerm
-232: Sund
- 57: Surrogate
-233: Sylo
-215: Symbol
-234: Syrc
-236: Tagb
-240: Takr
-237: Tale
-164: Talu
-241: Taml
-242: Tang
-239: Tavt
-243: Telu
-244: Term
-248: Tfng
-235: Tglg
-245: Thaa
-247: Tibt
-249: Tirh
-133: Titlecase_Letter
-250: Ugar
-251: UIdeo
- 53: Unassigned
-134: Uppercase_Letter
-254: Vaii
-255: VS
-257: Wara
-256: Wcho
-258: WSpace
-259: XIDC
-260: XIDS
-178: Xpeo
- 58: Xsux
-261: Yiii
-263: Zanb
-106: Zinh
- 55: Zyyy
-252: Zzzz
-267: In_Basic_Latin
-268: In_Latin_1_Supplement
-269: In_Latin_Extended_A
-270: In_Latin_Extended_B
-271: In_IPA_Extensions
-272: In_Spacing_Modifier_Letters
-273: In_Combining_Diacritical_Marks
-274: In_Greek_and_Coptic
-275: In_Cyrillic
-276: In_Cyrillic_Supplement
-277: In_Armenian
-278: In_Hebrew
-279: In_Arabic
-280: In_Syriac
-281: In_Arabic_Supplement
-282: In_Thaana
-283: In_NKo
-284: In_Samaritan
-285: In_Mandaic
-286: In_Syriac_Supplement
-287: In_Arabic_Extended_A
-288: In_Devanagari
-289: In_Bengali
-290: In_Gurmukhi
-291: In_Gujarati
-292: In_Oriya
-293: In_Tamil
-294: In_Telugu
-295: In_Kannada
-296: In_Malayalam
-297: In_Sinhala
-298: In_Thai
-299: In_Lao
-300: In_Tibetan
-301: In_Myanmar
-302: In_Georgian
-303: In_Hangul_Jamo
-304: In_Ethiopic
-305: In_Ethiopic_Supplement
-306: In_Cherokee
-307: In_Unified_Canadian_Aboriginal_Syllabics
-308: In_Ogham
-309: In_Runic
-310: In_Tagalog
-311: In_Hanunoo
-312: In_Buhid
-313: In_Tagbanwa
-314: In_Khmer
-315: In_Mongolian
-316: In_Unified_Canadian_Aboriginal_Syllabics_Extended
-317: In_Limbu
-318: In_Tai_Le
-319: In_New_Tai_Lue
-320: In_Khmer_Symbols
-321: In_Buginese
-322: In_Tai_Tham
-323: In_Combining_Diacritical_Marks_Extended
-324: In_Balinese
-325: In_Sundanese
-326: In_Batak
-327: In_Lepcha
-328: In_Ol_Chiki
-329: In_Cyrillic_Extended_C
-330: In_Georgian_Extended
-331: In_Sundanese_Supplement
-332: In_Vedic_Extensions
-333: In_Phonetic_Extensions
-334: In_Phonetic_Extensions_Supplement
-335: In_Combining_Diacritical_Marks_Supplement
-336: In_Latin_Extended_Additional
-337: In_Greek_Extended
-338: In_General_Punctuation
-339: In_Superscripts_and_Subscripts
-340: In_Currency_Symbols
-341: In_Combining_Diacritical_Marks_for_Symbols
-342: In_Letterlike_Symbols
-343: In_Number_Forms
-344: In_Arrows
-345: In_Mathematical_Operators
-346: In_Miscellaneous_Technical
-347: In_Control_Pictures
-348: In_Optical_Character_Recognition
-349: In_Enclosed_Alphanumerics
-350: In_Box_Drawing
-351: In_Block_Elements
-352: In_Geometric_Shapes
-353: In_Miscellaneous_Symbols
-354: In_Dingbats
-355: In_Miscellaneous_Mathematical_Symbols_A
-356: In_Supplemental_Arrows_A
-357: In_Braille_Patterns
-358: In_Supplemental_Arrows_B
-359: In_Miscellaneous_Mathematical_Symbols_B
-360: In_Supplemental_Mathematical_Operators
-361: In_Miscellaneous_Symbols_and_Arrows
-362: In_Glagolitic
-363: In_Latin_Extended_C
-364: In_Coptic
-365: In_Georgian_Supplement
-366: In_Tifinagh
-367: In_Ethiopic_Extended
-368: In_Cyrillic_Extended_A
-369: In_Supplemental_Punctuation
-370: In_CJK_Radicals_Supplement
-371: In_Kangxi_Radicals
-372: In_Ideographic_Description_Characters
-373: In_CJK_Symbols_and_Punctuation
-374: In_Hiragana
-375: In_Katakana
-376: In_Bopomofo
-377: In_Hangul_Compatibility_Jamo
-378: In_Kanbun
-379: In_Bopomofo_Extended
-380: In_CJK_Strokes
-381: In_Katakana_Phonetic_Extensions
-382: In_Enclosed_CJK_Letters_and_Months
-383: In_CJK_Compatibility
-384: In_CJK_Unified_Ideographs_Extension_A
-385: In_Yijing_Hexagram_Symbols
-386: In_CJK_Unified_Ideographs
-387: In_Yi_Syllables
-388: In_Yi_Radicals
-389: In_Lisu
-390: In_Vai
-391: In_Cyrillic_Extended_B
-392: In_Bamum
-393: In_Modifier_Tone_Letters
-394: In_Latin_Extended_D
-395: In_Syloti_Nagri
-396: In_Common_Indic_Number_Forms
-397: In_Phags_pa
-398: In_Saurashtra
-399: In_Devanagari_Extended
-400: In_Kayah_Li
-401: In_Rejang
-402: In_Hangul_Jamo_Extended_A
-403: In_Javanese
-404: In_Myanmar_Extended_B
-405: In_Cham
-406: In_Myanmar_Extended_A
-407: In_Tai_Viet
-408: In_Meetei_Mayek_Extensions
-409: In_Ethiopic_Extended_A
-410: In_Latin_Extended_E
-411: In_Cherokee_Supplement
-412: In_Meetei_Mayek
-413: In_Hangul_Syllables
-414: In_Hangul_Jamo_Extended_B
-415: In_High_Surrogates
-416: In_High_Private_Use_Surrogates
-417: In_Low_Surrogates
-418: In_Private_Use_Area
-419: In_CJK_Compatibility_Ideographs
-420: In_Alphabetic_Presentation_Forms
-421: In_Arabic_Presentation_Forms_A
-422: In_Variation_Selectors
-423: In_Vertical_Forms
-424: In_Combining_Half_Marks
-425: In_CJK_Compatibility_Forms
-426: In_Small_Form_Variants
-427: In_Arabic_Presentation_Forms_B
-428: In_Halfwidth_and_Fullwidth_Forms
-429: In_Specials
-430: In_Linear_B_Syllabary
-431: In_Linear_B_Ideograms
-432: In_Aegean_Numbers
-433: In_Ancient_Greek_Numbers
-434: In_Ancient_Symbols
-435: In_Phaistos_Disc
-436: In_Lycian
-437: In_Carian
-438: In_Coptic_Epact_Numbers
-439: In_Old_Italic
-440: In_Gothic
-441: In_Old_Permic
-442: In_Ugaritic
-443: In_Old_Persian
-444: In_Deseret
-445: In_Shavian
-446: In_Osmanya
-447: In_Osage
-448: In_Elbasan
-449: In_Caucasian_Albanian
-450: In_Linear_A
-451: In_Cypriot_Syllabary
-452: In_Imperial_Aramaic
-453: In_Palmyrene
-454: In_Nabataean
-455: In_Hatran
-456: In_Phoenician
-457: In_Lydian
-458: In_Meroitic_Hieroglyphs
-459: In_Meroitic_Cursive
-460: In_Kharoshthi
-461: In_Old_South_Arabian
-462: In_Old_North_Arabian
-463: In_Manichaean
-464: In_Avestan
-465: In_Inscriptional_Parthian
-466: In_Inscriptional_Pahlavi
-467: In_Psalter_Pahlavi
-468: In_Old_Turkic
-469: In_Old_Hungarian
-470: In_Hanifi_Rohingya
-471: In_Rumi_Numeral_Symbols
-472: In_Old_Sogdian
-473: In_Sogdian
-474: In_Elymaic
-475: In_Brahmi
-476: In_Kaithi
-477: In_Sora_Sompeng
-478: In_Chakma
-479: In_Mahajani
-480: In_Sharada
-481: In_Sinhala_Archaic_Numbers
-482: In_Khojki
-483: In_Multani
-484: In_Khudawadi
-485: In_Grantha
-486: In_Newa
-487: In_Tirhuta
-488: In_Siddham
-489: In_Modi
-490: In_Mongolian_Supplement
-491: In_Takri
-492: In_Ahom
-493: In_Dogra
-494: In_Warang_Citi
-495: In_Nandinagari
-496: In_Zanabazar_Square
-497: In_Soyombo
-498: In_Pau_Cin_Hau
-499: In_Bhaiksuki
-500: In_Marchen
-501: In_Masaram_Gondi
-502: In_Gunjala_Gondi
-503: In_Makasar
-504: In_Tamil_Supplement
-505: In_Cuneiform
-506: In_Cuneiform_Numbers_and_Punctuation
-507: In_Early_Dynastic_Cuneiform
-508: In_Egyptian_Hieroglyphs
-509: In_Egyptian_Hieroglyph_Format_Controls
-510: In_Anatolian_Hieroglyphs
-511: In_Bamum_Supplement
-512: In_Mro
-513: In_Bassa_Vah
-514: In_Pahawh_Hmong
-515: In_Medefaidrin
-516: In_Miao
-517: In_Ideographic_Symbols_and_Punctuation
-518: In_Tangut
-519: In_Tangut_Components
-520: In_Kana_Supplement
-521: In_Kana_Extended_A
-522: In_Small_Kana_Extension
-523: In_Nushu
-524: In_Duployan
-525: In_Shorthand_Format_Controls
-526: In_Byzantine_Musical_Symbols
-527: In_Musical_Symbols
-528: In_Ancient_Greek_Musical_Notation
-529: In_Mayan_Numerals
-530: In_Tai_Xuan_Jing_Symbols
-531: In_Counting_Rod_Numerals
-532: In_Mathematical_Alphanumeric_Symbols
-533: In_Sutton_SignWriting
-534: In_Glagolitic_Supplement
-535: In_Nyiakeng_Puachue_Hmong
-536: In_Wancho
-537: In_Mende_Kikakui
-538: In_Adlam
-539: In_Indic_Siyaq_Numbers
-540: In_Ottoman_Siyaq_Numbers
-541: In_Arabic_Mathematical_Alphabetic_Symbols
-542: In_Mahjong_Tiles
-543: In_Domino_Tiles
-544: In_Playing_Cards
-545: In_Enclosed_Alphanumeric_Supplement
-546: In_Enclosed_Ideographic_Supplement
-547: In_Miscellaneous_Symbols_and_Pictographs
-548: In_Emoticons
-549: In_Ornamental_Dingbats
-550: In_Transport_and_Map_Symbols
-551: In_Alchemical_Symbols
-552: In_Geometric_Shapes_Extended
-553: In_Supplemental_Arrows_C
-554: In_Supplemental_Symbols_and_Pictographs
-555: In_Chess_Symbols
-556: In_Symbols_and_Pictographs_Extended_A
-557: In_CJK_Unified_Ideographs_Extension_B
-558: In_CJK_Unified_Ideographs_Extension_C
-559: In_CJK_Unified_Ideographs_Extension_D
-560: In_CJK_Unified_Ideographs_Extension_E
-561: In_CJK_Unified_Ideographs_Extension_F
-562: In_CJK_Compatibility_Ideographs_Supplement
-563: In_Tags
-564: In_Variation_Selectors_Supplement
-565: In_Supplementary_Private_Use_Area_A
-566: In_Supplementary_Private_Use_Area_B
-567: In_No_Block
+133: Other_Letter
+171: Other_Number
+209: Other_Punctuation
+230: Other_Symbol
+195: OUpper
+198: Palm
+269: Paragraph_Separator
+199: Pat_Syn
+200: Pat_WS
+201: Pauc
+210: PCM
+180: Perm
+206: Phag
+109: Phli
+212: Phlp
+207: Phnx
+156: Plrd
+ 55: Private_Use
+110: Prti
+196: Punctuation
+ 57: Qaac
+108: Qaai
+213: QMark
+215: RI
+216: Rjng
+ 95: Rohg
+217: Runr
+219: Samr
+183: Sarb
+220: Saur
+231: SD
+266: Separator
+226: Sgnw
+224: Shaw
+223: Shrd
+225: Sidd
+121: Sind
+227: Sinh
+232: Sogd
+182: Sogo
+233: Sora
+234: Soyo
+270: Space_Separator
+149: Spacing_Mark
+222: STerm
+235: Sund
+ 58: Surrogate
+236: Sylo
+218: Symbol
+237: Syrc
+239: Tagb
+243: Takr
+240: Tale
+167: Talu
+244: Taml
+245: Tang
+242: Tavt
+246: Telu
+247: Term
+251: Tfng
+238: Tglg
+248: Thaa
+250: Tibt
+252: Tirh
+136: Titlecase_Letter
+253: Ugar
+254: UIdeo
+ 54: Unassigned
+137: Uppercase_Letter
+257: Vaii
+258: VS
+260: Wara
+259: Wcho
+261: WSpace
+262: XIDC
+263: XIDS
+181: Xpeo
+ 59: Xsux
+264: Yezi
+265: Yiii
+267: Zanb
+108: Zinh
+ 56: Zyyy
+255: Zzzz
+271: In_Basic_Latin
+272: In_Latin_1_Supplement
+273: In_Latin_Extended_A
+274: In_Latin_Extended_B
+275: In_IPA_Extensions
+276: In_Spacing_Modifier_Letters
+277: In_Combining_Diacritical_Marks
+278: In_Greek_and_Coptic
+279: In_Cyrillic
+280: In_Cyrillic_Supplement
+281: In_Armenian
+282: In_Hebrew
+283: In_Arabic
+284: In_Syriac
+285: In_Arabic_Supplement
+286: In_Thaana
+287: In_NKo
+288: In_Samaritan
+289: In_Mandaic
+290: In_Syriac_Supplement
+291: In_Arabic_Extended_A
+292: In_Devanagari
+293: In_Bengali
+294: In_Gurmukhi
+295: In_Gujarati
+296: In_Oriya
+297: In_Tamil
+298: In_Telugu
+299: In_Kannada
+300: In_Malayalam
+301: In_Sinhala
+302: In_Thai
+303: In_Lao
+304: In_Tibetan
+305: In_Myanmar
+306: In_Georgian
+307: In_Hangul_Jamo
+308: In_Ethiopic
+309: In_Ethiopic_Supplement
+310: In_Cherokee
+311: In_Unified_Canadian_Aboriginal_Syllabics
+312: In_Ogham
+313: In_Runic
+314: In_Tagalog
+315: In_Hanunoo
+316: In_Buhid
+317: In_Tagbanwa
+318: In_Khmer
+319: In_Mongolian
+320: In_Unified_Canadian_Aboriginal_Syllabics_Extended
+321: In_Limbu
+322: In_Tai_Le
+323: In_New_Tai_Lue
+324: In_Khmer_Symbols
+325: In_Buginese
+326: In_Tai_Tham
+327: In_Combining_Diacritical_Marks_Extended
+328: In_Balinese
+329: In_Sundanese
+330: In_Batak
+331: In_Lepcha
+332: In_Ol_Chiki
+333: In_Cyrillic_Extended_C
+334: In_Georgian_Extended
+335: In_Sundanese_Supplement
+336: In_Vedic_Extensions
+337: In_Phonetic_Extensions
+338: In_Phonetic_Extensions_Supplement
+339: In_Combining_Diacritical_Marks_Supplement
+340: In_Latin_Extended_Additional
+341: In_Greek_Extended
+342: In_General_Punctuation
+343: In_Superscripts_and_Subscripts
+344: In_Currency_Symbols
+345: In_Combining_Diacritical_Marks_for_Symbols
+346: In_Letterlike_Symbols
+347: In_Number_Forms
+348: In_Arrows
+349: In_Mathematical_Operators
+350: In_Miscellaneous_Technical
+351: In_Control_Pictures
+352: In_Optical_Character_Recognition
+353: In_Enclosed_Alphanumerics
+354: In_Box_Drawing
+355: In_Block_Elements
+356: In_Geometric_Shapes
+357: In_Miscellaneous_Symbols
+358: In_Dingbats
+359: In_Miscellaneous_Mathematical_Symbols_A
+360: In_Supplemental_Arrows_A
+361: In_Braille_Patterns
+362: In_Supplemental_Arrows_B
+363: In_Miscellaneous_Mathematical_Symbols_B
+364: In_Supplemental_Mathematical_Operators
+365: In_Miscellaneous_Symbols_and_Arrows
+366: In_Glagolitic
+367: In_Latin_Extended_C
+368: In_Coptic
+369: In_Georgian_Supplement
+370: In_Tifinagh
+371: In_Ethiopic_Extended
+372: In_Cyrillic_Extended_A
+373: In_Supplemental_Punctuation
+374: In_CJK_Radicals_Supplement
+375: In_Kangxi_Radicals
+376: In_Ideographic_Description_Characters
+377: In_CJK_Symbols_and_Punctuation
+378: In_Hiragana
+379: In_Katakana
+380: In_Bopomofo
+381: In_Hangul_Compatibility_Jamo
+382: In_Kanbun
+383: In_Bopomofo_Extended
+384: In_CJK_Strokes
+385: In_Katakana_Phonetic_Extensions
+386: In_Enclosed_CJK_Letters_and_Months
+387: In_CJK_Compatibility
+388: In_CJK_Unified_Ideographs_Extension_A
+389: In_Yijing_Hexagram_Symbols
+390: In_CJK_Unified_Ideographs
+391: In_Yi_Syllables
+392: In_Yi_Radicals
+393: In_Lisu
+394: In_Vai
+395: In_Cyrillic_Extended_B
+396: In_Bamum
+397: In_Modifier_Tone_Letters
+398: In_Latin_Extended_D
+399: In_Syloti_Nagri
+400: In_Common_Indic_Number_Forms
+401: In_Phags_pa
+402: In_Saurashtra
+403: In_Devanagari_Extended
+404: In_Kayah_Li
+405: In_Rejang
+406: In_Hangul_Jamo_Extended_A
+407: In_Javanese
+408: In_Myanmar_Extended_B
+409: In_Cham
+410: In_Myanmar_Extended_A
+411: In_Tai_Viet
+412: In_Meetei_Mayek_Extensions
+413: In_Ethiopic_Extended_A
+414: In_Latin_Extended_E
+415: In_Cherokee_Supplement
+416: In_Meetei_Mayek
+417: In_Hangul_Syllables
+418: In_Hangul_Jamo_Extended_B
+419: In_High_Surrogates
+420: In_High_Private_Use_Surrogates
+421: In_Low_Surrogates
+422: In_Private_Use_Area
+423: In_CJK_Compatibility_Ideographs
+424: In_Alphabetic_Presentation_Forms
+425: In_Arabic_Presentation_Forms_A
+426: In_Variation_Selectors
+427: In_Vertical_Forms
+428: In_Combining_Half_Marks
+429: In_CJK_Compatibility_Forms
+430: In_Small_Form_Variants
+431: In_Arabic_Presentation_Forms_B
+432: In_Halfwidth_and_Fullwidth_Forms
+433: In_Specials
+434: In_Linear_B_Syllabary
+435: In_Linear_B_Ideograms
+436: In_Aegean_Numbers
+437: In_Ancient_Greek_Numbers
+438: In_Ancient_Symbols
+439: In_Phaistos_Disc
+440: In_Lycian
+441: In_Carian
+442: In_Coptic_Epact_Numbers
+443: In_Old_Italic
+444: In_Gothic
+445: In_Old_Permic
+446: In_Ugaritic
+447: In_Old_Persian
+448: In_Deseret
+449: In_Shavian
+450: In_Osmanya
+451: In_Osage
+452: In_Elbasan
+453: In_Caucasian_Albanian
+454: In_Linear_A
+455: In_Cypriot_Syllabary
+456: In_Imperial_Aramaic
+457: In_Palmyrene
+458: In_Nabataean
+459: In_Hatran
+460: In_Phoenician
+461: In_Lydian
+462: In_Meroitic_Hieroglyphs
+463: In_Meroitic_Cursive
+464: In_Kharoshthi
+465: In_Old_South_Arabian
+466: In_Old_North_Arabian
+467: In_Manichaean
+468: In_Avestan
+469: In_Inscriptional_Parthian
+470: In_Inscriptional_Pahlavi
+471: In_Psalter_Pahlavi
+472: In_Old_Turkic
+473: In_Old_Hungarian
+474: In_Hanifi_Rohingya
+475: In_Rumi_Numeral_Symbols
+476: In_Yezidi
+477: In_Old_Sogdian
+478: In_Sogdian
+479: In_Chorasmian
+480: In_Elymaic
+481: In_Brahmi
+482: In_Kaithi
+483: In_Sora_Sompeng
+484: In_Chakma
+485: In_Mahajani
+486: In_Sharada
+487: In_Sinhala_Archaic_Numbers
+488: In_Khojki
+489: In_Multani
+490: In_Khudawadi
+491: In_Grantha
+492: In_Newa
+493: In_Tirhuta
+494: In_Siddham
+495: In_Modi
+496: In_Mongolian_Supplement
+497: In_Takri
+498: In_Ahom
+499: In_Dogra
+500: In_Warang_Citi
+501: In_Dives_Akuru
+502: In_Nandinagari
+503: In_Zanabazar_Square
+504: In_Soyombo
+505: In_Pau_Cin_Hau
+506: In_Bhaiksuki
+507: In_Marchen
+508: In_Masaram_Gondi
+509: In_Gunjala_Gondi
+510: In_Makasar
+511: In_Lisu_Supplement
+512: In_Tamil_Supplement
+513: In_Cuneiform
+514: In_Cuneiform_Numbers_and_Punctuation
+515: In_Early_Dynastic_Cuneiform
+516: In_Egyptian_Hieroglyphs
+517: In_Egyptian_Hieroglyph_Format_Controls
+518: In_Anatolian_Hieroglyphs
+519: In_Bamum_Supplement
+520: In_Mro
+521: In_Bassa_Vah
+522: In_Pahawh_Hmong
+523: In_Medefaidrin
+524: In_Miao
+525: In_Ideographic_Symbols_and_Punctuation
+526: In_Tangut
+527: In_Tangut_Components
+528: In_Khitan_Small_Script
+529: In_Tangut_Supplement
+530: In_Kana_Supplement
+531: In_Kana_Extended_A
+532: In_Small_Kana_Extension
+533: In_Nushu
+534: In_Duployan
+535: In_Shorthand_Format_Controls
+536: In_Byzantine_Musical_Symbols
+537: In_Musical_Symbols
+538: In_Ancient_Greek_Musical_Notation
+539: In_Mayan_Numerals
+540: In_Tai_Xuan_Jing_Symbols
+541: In_Counting_Rod_Numerals
+542: In_Mathematical_Alphanumeric_Symbols
+543: In_Sutton_SignWriting
+544: In_Glagolitic_Supplement
+545: In_Nyiakeng_Puachue_Hmong
+546: In_Wancho
+547: In_Mende_Kikakui
+548: In_Adlam
+549: In_Indic_Siyaq_Numbers
+550: In_Ottoman_Siyaq_Numbers
+551: In_Arabic_Mathematical_Alphabetic_Symbols
+552: In_Mahjong_Tiles
+553: In_Domino_Tiles
+554: In_Playing_Cards
+555: In_Enclosed_Alphanumeric_Supplement
+556: In_Enclosed_Ideographic_Supplement
+557: In_Miscellaneous_Symbols_and_Pictographs
+558: In_Emoticons
+559: In_Ornamental_Dingbats
+560: In_Transport_and_Map_Symbols
+561: In_Alchemical_Symbols
+562: In_Geometric_Shapes_Extended
+563: In_Supplemental_Arrows_C
+564: In_Supplemental_Symbols_and_Pictographs
+565: In_Chess_Symbols
+566: In_Symbols_and_Pictographs_Extended_A
+567: In_Symbols_for_Legacy_Computing
+568: In_CJK_Unified_Ideographs_Extension_B
+569: In_CJK_Unified_Ideographs_Extension_C
+570: In_CJK_Unified_Ideographs_Extension_D
+571: In_CJK_Unified_Ideographs_Extension_E
+572: In_CJK_Unified_Ideographs_Extension_F
+573: In_CJK_Compatibility_Ideographs_Supplement
+574: In_CJK_Unified_Ideographs_Extension_G
+575: In_Tags
+576: In_Variation_Selectors_Supplement
+577: In_Supplementary_Private_Use_Area_A
+578: In_Supplementary_Private_Use_Area_B
+579: In_No_Block