New upstream version 6.9.2upstream/6.9.2

1 files changed, 69 insertions, 54 deletions

diff --git a/doc/RE b/doc/RE
index 963d009..72957dd 100644
--- a/doc/RE
+++ b/doc/RE
@@ -1,4 +1,4 @@
-Oniguruma Regular Expressions Version 6.8.0    2018/07/26
+Oniguruma Regular Expressions Version 6.9.2    2019/03/29
 
 syntax: ONIG_SYNTAX_ONIGURUMA (default)
 
@@ -81,15 +81,23 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
 
   \O       true anychar      (?m:.)    (* original function)
 
-  \X       Extended Grapheme Cluster    (?>\O(?:\Y\O)*)
+  \X       Text Segment    \X === (?>\O(?:\Y\O)*)
 
-           \X doesn't check whether matching start position is boundary.
-           Write as \y\X if you want to ensure it.
+           The meaning of this operator changes depending on the setting of
+           the option (?y{..}).
 
-           Unicode case:
-             See [Unicode Standard Annex #29: http://unicode.org/reports/tr29/]
+           \X doesn't check whether matching start position is boundary or not.
+           Please write as \y\X if you want to ensure it.
 
-           Not Unicode:   (?>\r\n|\O)
+           [Extended Grapheme Cluster mode] (default)
+             Unicode case:
+               See [Unicode Standard Annex #29: http://unicode.org/reports/tr29/]
+
+             Not Unicode case:  \X === (?>\r\n|\O)
+
+           [Word mode]
+             Currently, this mode is supported in Unicode only.
+             See [Unicode Standard Annex #29: http://unicode.org/reports/tr29/]
 
 
   Character Property
@@ -119,17 +127,17 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
     ?       1 or 0 times
     *       0 or more times
     +       1 or more times
-    {n,m}   at least n but no more than m times
+    {n,m}   (n <= m)  at least n but no more than m times
     {n,}    at least n times
     {,n}    at least 0 but no more than n times ({0,n})
     {n}     n times
 
   reluctant
 
-    ??      1 or 0 times
+    ??      0 or 1 times
     *?      0 or more times
     +?      1 or more times
-    {n,m}?  at least n but not more than m times
+    {n,m}?  (n <= m)  at least n but not more than m times
     {n,}?   at least n times
     {,n}?   at least 0 but not more than n times (== {0,n}?)
 
@@ -138,8 +146,10 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
     ?+      1 or 0 times
     *+      0 or more times
     ++      1 or more times
+    {n,m}   (n > m)  at least m but not more than n times
 
-    ({n,m}+, {n,}+, {n}+ are possessive op. in ONIG_SYNTAX_JAVA only)
+    {n,m}+, {n,}+, {n}+ are possessive operators in ONIG_SYNTAX_JAVA and
+    ONIG_SYNTAX_PERL only.
 
     ex. /a*+/ === /(?>a*)/
 
@@ -150,8 +160,6 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
   $       end of the line
   \b      word boundary
   \B      non-word boundary
-  \y      Extended Grapheme Cluster boundary
-  \Y      Extended Grapheme Cluster non-boundary
 
   \A      beginning of string
   \Z      end of string, or before newline at the end
@@ -160,6 +168,24 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
   \K      keep (keep start position of the result string)
 
 
+  \y      Text Segment boundary
+  \Y      Text Segment non-boundary
+
+          The meaning of these operators(\y, \Y) changes depending on the setting
+          of the option (?y{..}).
+
+          [Extended Grapheme Cluster mode] (default)
+            Unicode case:
+              See [Unicode Standard Annex #29: http://unicode.org/reports/tr29/]
+
+            Not Unicode:
+              All positions except between \r and \n.
+
+          [Word mode]
+            Currently, this mode is supported in Unicode only.
+            See [Unicode Standard Annex #29: http://unicode.org/reports/tr29/]
+
+
 
 6. Character class
 
@@ -221,20 +247,28 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
 
   (?#...)            comment
 
-  (?imxWDSP-imxWDSP:subexp)  option on/off for subexp
+  (?imxWDSPy-imxWDSP:subexp)  option on/off for subexp
+
+                           i: ignore case
+                           m: multi-line (dot (.) also matches newline)
+                           x: extended form
+                           W: ASCII only word (\w, \p{Word}, [[:word:]])
+                              ASCII only word bound (\b)
+                           D: ASCII only digit (\d, \p{Digit}, [[:digit:]])
+                           S: ASCII only space (\s, \p{Space}, [[:space:]])
+                           P: ASCII only POSIX properties (includes W,D,S)
+                              (alnum, alpha, blank, cntrl, digit, graph,
+                               lower, print, punct, space, upper, xdigit, word)
+
+                           y{?}: Text Segment mode
+                              This option changes the meaning of \X, \y, \Y.
+                              Currently, this option is supported in Unicode only.
 
-                               i: ignore case
-                               m: multi-line (dot (.) also matches newline)
-                               x: extended form
-                               W: ASCII only word (\w, \p{Word}, [[:word:]])
-                                  ASCII only word bound (\b)
-                               D: ASCII only digit (\d, \p{Digit}, [[:digit:]])
-                               S: ASCII only space (\s, \p{Space}, [[:space:]])
-                               P: ASCII only POSIX properties (includes W,D,S)
-                                  (alnum, alpha, blank, cntrl, digit, graph,
-                                   lower, print, punct, space, upper, xdigit, word)
+                              y{g}: Extended Grapheme Cluster mode (default)
+                              y{w}: Word mode
+                              See [Unicode Standard Annex #29]
 
-  (?imxWDSP-imxWDSP)  isolated option
+  (?imxWDSPy-imxWDSP)  isolated option
 
                       * It makes a group to the next ')' or end of the pattern.
                         /ab(?i)c|def|gh/ == /ab(?i:c|def|gh)/
@@ -336,7 +370,7 @@ syntax: ONIG_SYNTAX_ONIGURUMA (default)
                else_exp can be omitted.
                Then it works as a backreference validity checker.
 
-  [ backreference validity checker ]   (* original)
+  [ Backreference validity checker ]   (* original)
 
     (?(n)), (?(-n)), (?(+n)), (?(n+level)) ...
     (?(<n>)), (?('-n')), (?(<+n>)) ...
@@ -470,10 +504,15 @@ A-1. Syntax-dependent options
 
 A-2. Original extensions
 
-   + hexadecimal digit char type  \h, \H
-   + named group                  (?<name>...), (?'name'...)
-   + named backref                \k<name>
-   + subexp call                  \g<name>, \g<group-num>
+   + hexadecimal digit char type     \h, \H
+   + true anychar                    \O
+   + text segment boundary           \y, \Y
+   + backreference validity checker  (?(...))
+   + named group                     (?<name>...), (?'name'...)
+   + named backref                   \k<name>
+   + subexp call                     \g<name>, \g<group-num>
+   + absent expression               (?~|...|...)
+   + absent stopper                  (?|...)
 
 
 A-3. Missing features compared with perl 5.8.0
@@ -528,28 +567,4 @@ A-4. Differences with Japanized GNU regex(version 0.12) of Ruby 1.8
      /(?:()|())*\1\2/ =~ ""
      /(?:\1a|())*/ =~ "a"
 
-
-A-5. Features disabled in default syntax
-
-   + capture history
-
-     (?@...) and (?@<name>...)
-
-     ex. /(?@a)*/.match("aaa") ==> [<0-1>, <1-2>, <2-3>]
-
-     see sample/listcap.c file.
-
-
-A-6. Problems
-
-   + Invalid encoding byte sequence is not checked.
-
-     ex. UTF-8
-
-     * Invalid first byte is treated as a character.
-       /./u =~ "\xa3"
-
-     * Incomplete byte sequence is not checked.
-       /\w+/ =~ "a\xf3\x8ec"
-
 // END