From 35e13e4c9637f5bf7bef6039c8c813207780a174 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B6rg=20Frings-F=C3=BCrst?= Date: Mon, 20 Nov 2023 20:10:50 +0100 Subject: New upstream version 6.9.9 --- doc/API | 8 +++++--- doc/API.ja | 11 +++++++---- doc/RE | 11 ++++++----- doc/RE.ja | 9 +++++---- doc/UNICODE_PROPERTIES | 19 ++++++++++++++++++- 5 files changed, 41 insertions(+), 17 deletions(-) (limited to 'doc') diff --git a/doc/API b/doc/API index 30e9a26..600aa96 100644 --- a/doc/API +++ b/doc/API @@ -1,4 +1,4 @@ -Oniguruma API Version 6.9.7 2021/03/03 +Oniguruma API Version 6.9.9 2022/10/28 #include @@ -366,6 +366,8 @@ Oniguruma API Version 6.9.7 2021/03/03 The user_data specified by onig_set_callout_user_data_of_match_param() will be shared with callout. + ONIG_OPTION_MATCH_WHOLE_STRING Try to match the whole of (str), rather than returning after the first match is found. + # int onig_search_with_param(regex_t* reg, const UChar* str, const UChar* end, const UChar* start, const UChar* range, OnigRegion* region, @@ -407,7 +409,7 @@ Oniguruma API Version 6.9.7 2021/03/03 ONIG_OPTION_NOT_END_STRING Do not regard the (end) as a string endpoint (* fail \z, \Z) ONIG_OPTION_NOT_BEGIN_POSITION Do not regard the (start) as start position of search (* fail \G) ONIG_OPTION_CALLBACK_EACH_MATCH Call back for all successful matches. - + ONIG_OPTION_MATCH_WHOLE_STRING Try to match the whole of (str), rather than returning after the first match is found. # int onig_match_with_param(regex_t* reg, const UChar* str, const UChar* end, const UChar* at, OnigRegion* region, @@ -641,7 +643,7 @@ Oniguruma API Version 6.9.7 2021/03/03 return value normal: number of groups for the name. (ex. /(?..)(?..)/ ==> 2) - name not found: -1 + name not found: ONIGERR_UNDEFINED_NAME_REFERENCE arguments 1 reg: regex object. diff --git a/doc/API.ja b/doc/API.ja index 8979589..af02b33 100644 --- a/doc/API.ja +++ b/doc/API.ja @@ -1,4 +1,4 @@ -鬼車インターフェース Version 6.9.7 2022/02/04 +鬼車インターフェース Version 6.9.9 2022/11/16 #include @@ -361,6 +361,8 @@ onig_set_callout_user_data_of_match_param()で指定するuser_dataは、 calloutで使用されるuser_dataと共用される。 + ONIG_OPTION_MATCH_WHOLE_STRING マッチした終端の位置がendになることを要求 + # int onig_search_with_param(regex_t* reg, const UChar* str, const UChar* end, const UChar* start, const UChar* range, OnigRegion* region, @@ -400,6 +402,7 @@ ONIG_OPTION_NOT_END_STRING endを文字列終端と看做さない (\z, \Z 失敗) ONIG_OPTION_NOT_BEGIN_POSITION startを検索開始位置と看做さない (\G 失敗) ONIG_OPTION_CALLBACK_EACH_MATCH 全てのマッチ成功に対してコールバック関数が呼び出される。 + ONIG_OPTION_MATCH_WHOLE_STRING マッチした終端の位置がendになることを要求 # int onig_match_with_param(regex_t* reg, const UChar* str, const UChar* end, @@ -445,7 +448,7 @@ 引数 1 rset: regsetオブジェクトを返すためのアドレス - 2 n: 正規表現オブジェクトの個数 + 2 n: 正規表現の個数 3 regs: 正規表現オブジェクトの配列 戻り値 @@ -476,7 +479,7 @@ 引数 1 set: regsetオブジェクト 2 at: 変更する場所のインデックス - 2 reg: 正規表現オブジェクト + 3 reg: 正規表現オブジェクト 戻り値 正常終了: ONIG_NORMAL == 0 @@ -635,7 +638,7 @@ 戻り値 正常終了: 指定された名前に対するグループ数 (例 /(?..)(?..)/ ==> 2) - 名前に対するグループが存在しない: -1 + 名前に対するグループが存在しない: ONIGERR_UNDEFINED_NAME_REFERENCE 引数 1 reg: 正規表現オブジェクト diff --git a/doc/RE b/doc/RE index 9eb816a..f5bf3d2 100644 --- a/doc/RE +++ b/doc/RE @@ -1,4 +1,4 @@ -Oniguruma Regular Expressions Version 6.9.8 2022/04/11 +Oniguruma Regular Expressions Version 6.9.9 2023/03/27 syntax: ONIG_SYNTAX_ONIGURUMA (default syntax) @@ -246,9 +246,7 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default syntax) graph [[:^space:]] && ^Control && ^Unassigned && ^Surrogate lower Lowercase_Letter print [[:graph:]] | [[:space:]] - punct Connector_Punctuation | Dash_Punctuation | Close_Punctuation | - Final_Punctuation | Initial_Punctuation | Other_Punctuation | - Open_Punctuation + punct Punctuation | Symbol space Space_Separator | Line_Separator | Paragraph_Separator | U+0009 | U+000A | U+000B | U+000C | U+000D | U+0085 upper Uppercase_Letter @@ -288,7 +286,10 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default syntax) * It makes a group to the next ')' or end of the pattern. /ab(?i)c|def|gh/ == /ab(?i:c|def|gh)/ - /(?CIL).../, /(?CIL:...)/ whole opiton + * (?i) option has no effect on word types (\w, \p{Word}). However, if the word types are used within a character class, it is valid. But, this would only be a concern when word types are used with the (?W) option. + + + /(?CIL).../, /(?CIL:...)/ whole option This option must be placed in a position that affects the entire regular expression. diff --git a/doc/RE.ja b/doc/RE.ja index 9fcf682..10a4dc7 100644 --- a/doc/RE.ja +++ b/doc/RE.ja @@ -1,4 +1,4 @@ -鬼車 正規表現 Version 6.9.8 2022/04/11 +鬼車 正規表現 Version 6.9.9 2022/08/28 使用文法: ONIG_SYNTAX_ONIGURUMA (既定値) @@ -243,9 +243,7 @@ graph [[:^space:]] && ^Control && ^Unassigned && ^Surrogate lower Lowercase_Letter print [[:graph:]] | [[:space:]] - punct Connector_Punctuation | Dash_Punctuation | Close_Punctuation | - Final_Punctuation | Initial_Punctuation | Other_Punctuation | - Open_Punctuation + punct Punctuation | Symbol space Space_Separator | Line_Separator | Paragraph_Separator | U+0009 | U+000A | U+000B | U+000C | U+000D | U+0085 upper Uppercase_Letter @@ -284,6 +282,9 @@ * これは次の')'またはパターンの終わりまでのグループを形成する /ab(?i)c|def|gh/ == /ab(?i:c|def|gh)/ + * (?i)オプションは、wordタイプ(\w, \p{Word})には有効ではない。但しwordタイプが文字クラスの中で使用された場合は有効になる。しかし、このことはwordタイプを(?W)オプションと共に使用した時にしか気にする必要はないであろう。 + + /(?CIL).../, /(?CIL:...)/ 全体オプション このオプションは、正規表現全体に影響を及ぼす位置 diff --git a/doc/UNICODE_PROPERTIES b/doc/UNICODE_PROPERTIES index 879f559..3d2dc09 100644 --- a/doc/UNICODE_PROPERTIES +++ b/doc/UNICODE_PROPERTIES @@ -1,4 +1,4 @@ -Unicode Properties (Unicode Version: 14.0.0, Emoji: 14.0) +Unicode Properties (Unicode Version: 15.1.0, Emoji: 15.1) ASCII_Hex_Digit Adlam @@ -90,10 +90,14 @@ Hiragana Hyphen IDS_Binary_Operator IDS_Trinary_Operator +IDS_Unary_Operator +ID_Compat_Math_Continue +ID_Compat_Math_Start ID_Continue ID_Start Ideographic Imperial_Aramaic +InCB Inherited Inscriptional_Pahlavi Inscriptional_Parthian @@ -102,6 +106,7 @@ Join_Control Kaithi Kannada Katakana +Kawi Kayah_Li Kharoshthi Khitan_Small_Script @@ -151,6 +156,7 @@ Multani Myanmar N Nabataean +Nag_Mundari Nandinagari Nd New_Tai_Lue @@ -352,6 +358,7 @@ Ideo IDS IDSB IDST +IDSU Initial_Punctuation Ital Java @@ -397,6 +404,7 @@ Mroo Mtei Mult Mymr +Nagm Nand Narb Nbat @@ -440,6 +448,7 @@ Phnx Plrd Private_Use Prti +punct Punctuation Qaac Qaai @@ -716,6 +725,7 @@ In_Old_Hungarian In_Hanifi_Rohingya In_Rumi_Numeral_Symbols In_Yezidi +In_Arabic_Extended_C In_Old_Sogdian In_Sogdian In_Old_Uyghur @@ -747,11 +757,13 @@ In_Zanabazar_Square In_Soyombo In_Unified_Canadian_Aboriginal_Syllabics_Extended_A In_Pau_Cin_Hau +In_Devanagari_Extended_A In_Bhaiksuki In_Marchen In_Masaram_Gondi In_Gunjala_Gondi In_Makasar +In_Kawi In_Lisu_Supplement In_Tamil_Supplement In_Cuneiform @@ -784,6 +796,7 @@ In_Znamenny_Musical_Notation In_Byzantine_Musical_Symbols In_Musical_Symbols In_Ancient_Greek_Musical_Notation +In_Kaktovik_Numerals In_Mayan_Numerals In_Tai_Xuan_Jing_Symbols In_Counting_Rod_Numerals @@ -791,9 +804,11 @@ In_Mathematical_Alphanumeric_Symbols In_Sutton_SignWriting In_Latin_Extended_G In_Glagolitic_Supplement +In_Cyrillic_Extended_D In_Nyiakeng_Puachue_Hmong In_Toto In_Wancho +In_Nag_Mundari In_Ethiopic_Extended_B In_Mende_Kikakui In_Adlam @@ -821,8 +836,10 @@ In_CJK_Unified_Ideographs_Extension_C In_CJK_Unified_Ideographs_Extension_D In_CJK_Unified_Ideographs_Extension_E In_CJK_Unified_Ideographs_Extension_F +In_CJK_Unified_Ideographs_Extension_I In_CJK_Compatibility_Ideographs_Supplement In_CJK_Unified_Ideographs_Extension_G +In_CJK_Unified_Ideographs_Extension_H In_Tags In_Variation_Selectors_Supplement In_Supplementary_Private_Use_Area_A -- cgit v1.2.3