esruby 0.0.0

data/resources/mruby/build/mrbgems/mruby-regexp-pcre/pcre/testdata/testoutputEBC

@@ -0,0 +1,182 @@
+/-- This is a specialized test for checking, when PCRE is compiled with the
+EBCDIC option but in an ASCII environment, that newline and white space
+functionality is working. It catches cases where explicit values such as 0x0a
+have been used instead of names like CHAR_LF. Needless to say, it is not a
+genuine EBCDIC test! In patterns, alphabetic characters that follow a backslash
+must be in EBCDIC code. In data, newlines and other spacing characters must be
+in EBCDIC, but can be specified as escapes. --/
+
+/-- Test default newline and variations --/
+
+/^A/m
+    ABC
+ 0: A
+    12\x15ABC
+ 0: A
+
+/^A/m<any>
+    12\x15ABC
+ 0: A
+    12\x0dABC
+ 0: A
+    12\x0d\x15ABC
+ 0: A
+    12\x25ABC
+ 0: A
+
+/^A/m<anycrlf>
+    12\x15ABC
+ 0: A
+    12\x0dABC
+ 0: A
+    12\x0d\x15ABC
+ 0: A
+    ** Fail
+No match
+    12\x25ABC
+No match
+
+/-- Test \h --/
+
+/^A\�/
+    A B
+ 0: A\x20
+
+/-- Test \H --/
+
+/^A\�/
+    AB
+ 0: AB
+    ** Fail
+No match
+    A B
+No match
+
+/-- Test \R --/
+
+/^A\�/
+    A\x15B
+ 0: A\x15
+    A\x0dB
+ 0: A\x0d
+    A\x25B
+ 0: A\x25
+    A\x0bB
+ 0: A\x0b
+    A\x0cB
+ 0: A\x0c
+    ** Fail
+No match
+    A B
+No match
+
+/-- Test \v --/
+
+/^A\�/
+    A\x15B
+ 0: A\x15
+    A\x0dB
+ 0: A\x0d
+    A\x25B
+ 0: A\x25
+    A\x0bB
+ 0: A\x0b
+    A\x0cB
+ 0: A\x0c
+    ** Fail
+No match
+    A B
+No match
+
+/-- Test \V --/
+
+/^A\�/
+    A B
+ 0: A\x20
+    ** Fail
+No match
+    A\x15B
+No match
+    A\x0dB
+No match
+    A\x25B
+No match
+    A\x0bB
+No match
+    A\x0cB
+No match
+    
+/-- For repeated items, use an atomic group so that the output is the same
+for DFA matching (otherwise it may show multiple matches). --/ 
+
+/-- Test \h+ --/
+
+/^A(?>\�+)/
+    A B
+ 0: A\x20
+
+/-- Test \H+ --/
+
+/^A(?>\�+)/
+    AB
+ 0: AB
+    ** Fail
+No match
+    A B
+No match
+
+/-- Test \R+ --/
+
+/^A(?>\�+)/
+    A\x15B
+ 0: A\x15
+    A\x0dB
+ 0: A\x0d
+    A\x25B
+ 0: A\x25
+    A\x0bB
+ 0: A\x0b
+    A\x0cB
+ 0: A\x0c
+    ** Fail
+No match
+    A B
+No match
+
+/-- Test \v+ --/
+
+/^A(?>\�+)/
+    A\x15B
+ 0: A\x15
+    A\x0dB
+ 0: A\x0d
+    A\x25B
+ 0: A\x25
+    A\x0bB
+ 0: A\x0b
+    A\x0cB
+ 0: A\x0c
+    ** Fail
+No match
+    A B
+No match
+
+/-- Test \V+ --/
+
+/^A(?>\�+)/
+    A B
+ 0: A\x20B
+    ** Fail
+No match
+    A\x15B
+No match
+    A\x0dB
+No match
+    A\x25B
+No match
+    A\x0bB
+No match
+    A\x0cB
+No match
+
+/-- End --/

data/resources/mruby/build/mrbgems/mruby-regexp-pcre/pcre/testdata/wintestinput3

@@ -0,0 +1,91 @@
+/^[\w]+/
+    *** Failers
+    �cole
+
+/^[\w]+/Lfrench
+    �cole
+
+/^[\w]+/
+    *** Failers
+    �cole
+
+/^[\W]+/
+    �cole
+
+/^[\W]+/Lfrench
+    *** Failers
+    �cole
+
+/[\b]/
+    \b
+    *** Failers
+    a
+
+/[\b]/Lfrench
+    \b
+    *** Failers
+    a
+
+/^\w+/
+    *** Failers
+    �cole
+
+/^\w+/Lfrench
+    �cole
+
+/(.+)\b(.+)/
+    �cole
+
+/(.+)\b(.+)/Lfrench
+    *** Failers
+    �cole
+
+/�cole/i
+    �cole
+    *** Failers
+    �cole
+
+/�cole/iLfrench
+    �cole
+    �cole
+
+/\w/IS
+
+/\w/ISLfrench
+
+/^[\xc8-\xc9]/iLfrench
+    �cole
+    �cole
+
+/^[\xc8-\xc9]/Lfrench
+    �cole
+    *** Failers 
+    �cole
+
+/\W+/Lfrench
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[\W]+/Lfrench
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[^[:alpha:]]+/Lfrench
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/\w+/Lfrench
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[\w]+/Lfrench
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[[:alpha:]]+/Lfrench
+    >>>\xaa<<<
+    >>>\xba<<< 
+    
+/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench 
+
+/ End of testinput3 /

data/resources/mruby/build/mrbgems/mruby-regexp-pcre/pcre/testdata/wintestoutput3

@@ -0,0 +1,166 @@
+/^[\w]+/
+    *** Failers
+No match
+    �cole
+No match
+
+/^[\w]+/Lfrench
+    �cole
+ 0: �cole
+
+/^[\w]+/
+    *** Failers
+No match
+    �cole
+No match
+
+/^[\W]+/
+    �cole
+ 0: \xc9
+
+/^[\W]+/Lfrench
+    *** Failers
+ 0: *** 
+    �cole
+No match
+
+/[\b]/
+    \b
+ 0: \x08
+    *** Failers
+No match
+    a
+No match
+
+/[\b]/Lfrench
+    \b
+ 0: \x08
+    *** Failers
+No match
+    a
+No match
+
+/^\w+/
+    *** Failers
+No match
+    �cole
+No match
+
+/^\w+/Lfrench
+    �cole
+ 0: �cole
+
+/(.+)\b(.+)/
+    �cole
+ 0: \xc9cole
+ 1: \xc9
+ 2: cole
+
+/(.+)\b(.+)/Lfrench
+    *** Failers
+ 0: *** Failers
+ 1: *** 
+ 2: Failers
+    �cole
+No match
+
+/�cole/i
+    �cole
+ 0: \xc9cole
+    *** Failers
+No match
+    �cole
+No match
+
+/�cole/iLfrench
+    �cole
+ 0: �cole
+    �cole
+ 0: �cole
+
+/\w/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
+  Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
+
+/\w/ISLfrench
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
+  Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
+  � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � 
+  � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � 
+  � � 
+
+/^[\xc8-\xc9]/iLfrench
+    �cole
+ 0: �
+    �cole
+ 0: �
+
+/^[\xc8-\xc9]/Lfrench
+    �cole
+ 0: �
+    *** Failers 
+No match
+    �cole
+No match
+
+/\W+/Lfrench
+    >>>\xaa<<<
+ 0: >>>
+    >>>\xba<<< 
+ 0: >>>
+
+/[\W]+/Lfrench
+    >>>\xaa<<<
+ 0: >>>
+    >>>\xba<<< 
+ 0: >>>
+
+/[^[:alpha:]]+/Lfrench
+    >>>\xaa<<<
+ 0: >>>
+    >>>\xba<<< 
+ 0: >>>
+
+/\w+/Lfrench
+    >>>\xaa<<<
+ 0: �
+    >>>\xba<<< 
+ 0: �
+
+/[\w]+/Lfrench
+    >>>\xaa<<<
+ 0: �
+    >>>\xba<<< 
+ 0: �
+
+/[[:alpha:]]+/Lfrench
+    >>>\xaa<<<
+ 0: �
+    >>>\xba<<< 
+ 0: �
+    
+/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench 
+------------------------------------------------------------------
+        Bra
+        [A-Za-z\x83\x8a\x8c\x8e\x9a\x9c\x9e\x9f\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff]
+        [a-z\x83\x9a\x9c\x9e\xaa\xb5\xba\xdf-\xf6\xf8-\xff]
+        [A-Z\x8a\x8c\x8e\x9f\xc0-\xd6\xd8-\xde]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/ End of testinput3 /

data/resources/mruby/build/mrbgems/mruby-regexp-pcre/pcre/ucp.h

@@ -0,0 +1,197 @@
+/*************************************************
+*          Unicode Property Table handler        *
+*************************************************/
+
+#ifndef _UCP_H
+#define _UCP_H
+
+/* This file contains definitions of the property values that are returned by
+the UCD access macros. New values that are added for new releases of Unicode
+should always be at the end of each enum, for backwards compatibility.
+
+IMPORTANT: Note also that the specific numeric values of the enums have to be
+the same as the values that are generated by the maint/MultiStage2.py script,
+where the equivalent property descriptive names are listed in vectors. */
+
+/* These are the general character categories. */
+
+enum {
+  ucp_C,     /* Other */
+  ucp_L,     /* Letter */
+  ucp_M,     /* Mark */
+  ucp_N,     /* Number */
+  ucp_P,     /* Punctuation */
+  ucp_S,     /* Symbol */
+  ucp_Z      /* Separator */
+};
+
+/* These are the particular character categories. */
+
+enum {
+  ucp_Cc,    /* Control */
+  ucp_Cf,    /* Format */
+  ucp_Cn,    /* Unassigned */
+  ucp_Co,    /* Private use */
+  ucp_Cs,    /* Surrogate */
+  ucp_Ll,    /* Lower case letter */
+  ucp_Lm,    /* Modifier letter */
+  ucp_Lo,    /* Other letter */
+  ucp_Lt,    /* Title case letter */
+  ucp_Lu,    /* Upper case letter */
+  ucp_Mc,    /* Spacing mark */
+  ucp_Me,    /* Enclosing mark */
+  ucp_Mn,    /* Non-spacing mark */
+  ucp_Nd,    /* Decimal number */
+  ucp_Nl,    /* Letter number */
+  ucp_No,    /* Other number */
+  ucp_Pc,    /* Connector punctuation */
+  ucp_Pd,    /* Dash punctuation */
+  ucp_Pe,    /* Close punctuation */
+  ucp_Pf,    /* Final punctuation */
+  ucp_Pi,    /* Initial punctuation */
+  ucp_Po,    /* Other punctuation */
+  ucp_Ps,    /* Open punctuation */
+  ucp_Sc,    /* Currency symbol */
+  ucp_Sk,    /* Modifier symbol */
+  ucp_Sm,    /* Mathematical symbol */
+  ucp_So,    /* Other symbol */
+  ucp_Zl,    /* Line separator */
+  ucp_Zp,    /* Paragraph separator */
+  ucp_Zs     /* Space separator */
+};
+
+/* These are grapheme break properties. Note that the code for processing them
+assumes that the values are less than 16. If more values are added that take
+the number to 16 or more, the code will have to be rewritten. */
+
+enum {
+  ucp_gbCR,                /*  0 */
+  ucp_gbLF,                /*  1 */
+  ucp_gbControl,           /*  2 */
+  ucp_gbExtend,            /*  3 */
+  ucp_gbPrepend,           /*  4 */
+  ucp_gbSpacingMark,       /*  5 */
+  ucp_gbL,                 /*  6 Hangul syllable type L */
+  ucp_gbV,                 /*  7 Hangul syllable type V */
+  ucp_gbT,                 /*  8 Hangul syllable type T */
+  ucp_gbLV,                /*  9 Hangul syllable type LV */
+  ucp_gbLVT,               /* 10 Hangul syllable type LVT */
+  ucp_gbRegionalIndicator, /* 11 */
+  ucp_gbOther              /* 12 */
+};
+
+/* These are the script identifications. */
+
+enum {
+  ucp_Arabic,
+  ucp_Armenian,
+  ucp_Bengali,
+  ucp_Bopomofo,
+  ucp_Braille,
+  ucp_Buginese,
+  ucp_Buhid,
+  ucp_Canadian_Aboriginal,
+  ucp_Cherokee,
+  ucp_Common,
+  ucp_Coptic,
+  ucp_Cypriot,
+  ucp_Cyrillic,
+  ucp_Deseret,
+  ucp_Devanagari,
+  ucp_Ethiopic,
+  ucp_Georgian,
+  ucp_Glagolitic,
+  ucp_Gothic,
+  ucp_Greek,
+  ucp_Gujarati,
+  ucp_Gurmukhi,
+  ucp_Han,
+  ucp_Hangul,
+  ucp_Hanunoo,
+  ucp_Hebrew,
+  ucp_Hiragana,
+  ucp_Inherited,
+  ucp_Kannada,
+  ucp_Katakana,
+  ucp_Kharoshthi,
+  ucp_Khmer,
+  ucp_Lao,
+  ucp_Latin,
+  ucp_Limbu,
+  ucp_Linear_B,
+  ucp_Malayalam,
+  ucp_Mongolian,
+  ucp_Myanmar,
+  ucp_New_Tai_Lue,
+  ucp_Ogham,
+  ucp_Old_Italic,
+  ucp_Old_Persian,
+  ucp_Oriya,
+  ucp_Osmanya,
+  ucp_Runic,
+  ucp_Shavian,
+  ucp_Sinhala,
+  ucp_Syloti_Nagri,
+  ucp_Syriac,
+  ucp_Tagalog,
+  ucp_Tagbanwa,
+  ucp_Tai_Le,
+  ucp_Tamil,
+  ucp_Telugu,
+  ucp_Thaana,
+  ucp_Thai,
+  ucp_Tibetan,
+  ucp_Tifinagh,
+  ucp_Ugaritic,
+  ucp_Yi,
+  /* New for Unicode 5.0: */
+  ucp_Balinese,
+  ucp_Cuneiform,
+  ucp_Nko,
+  ucp_Phags_Pa,
+  ucp_Phoenician,
+  /* New for Unicode 5.1: */
+  ucp_Carian,
+  ucp_Cham,
+  ucp_Kayah_Li,
+  ucp_Lepcha,
+  ucp_Lycian,
+  ucp_Lydian,
+  ucp_Ol_Chiki,
+  ucp_Rejang,
+  ucp_Saurashtra,
+  ucp_Sundanese,
+  ucp_Vai,
+  /* New for Unicode 5.2: */
+  ucp_Avestan,
+  ucp_Bamum,
+  ucp_Egyptian_Hieroglyphs,
+  ucp_Imperial_Aramaic,
+  ucp_Inscriptional_Pahlavi,
+  ucp_Inscriptional_Parthian,
+  ucp_Javanese,
+  ucp_Kaithi,
+  ucp_Lisu,
+  ucp_Meetei_Mayek,
+  ucp_Old_South_Arabian,
+  ucp_Old_Turkic,
+  ucp_Samaritan,
+  ucp_Tai_Tham,
+  ucp_Tai_Viet,
+  /* New for Unicode 6.0.0: */
+  ucp_Batak,
+  ucp_Brahmi,
+  ucp_Mandaic,
+  /* New for Unicode 6.1.0: */
+  ucp_Chakma,
+  ucp_Meroitic_Cursive,
+  ucp_Meroitic_Hieroglyphs,
+  ucp_Miao,
+  ucp_Sharada,
+  ucp_Sora_Sompeng,
+  ucp_Takri
+};
+
+#endif
+
+/* End of ucp.h */