X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=pod%2Fperlreref.pod;h=700814140d759e48c2c63d99dc21598e6abd2fee;hb=6168cf9995a8bfcfe4ab9350ebc7de70215ae9af;hp=9f083c7e8637a2e594fd4b4008f43bfb5a89c2c4;hpb=6d014f17427cba892ebb4fb2b45f28cc737c7c9e;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/pod/perlreref.pod b/pod/perlreref.pod
index 9f083c7..7008141 100644
--- a/pod/perlreref.pod
+++ b/pod/perlreref.pod
@@ -8,7 +8,7 @@ This is a quick reference to Perl's regular expressions.
 For full information see L<perlre> and L<perlop>, as well
 as the L</"SEE ALSO"> section in this document.
 
-=head1 OPERATORS
+=head2 OPERATORS
 
   =~ determines to which variable the regex is applied.
      In its absence, $_ is used.
@@ -52,7 +52,7 @@ as the L</"SEE ALSO"> section in this document.
   ?pattern? is like m/pattern/ but matches only once. No alternate
       delimiters can be used. Must be reset with L<reset|perlfunc/reset>.
 
-=head1 SYNTAX
+=head2 SYNTAX
 
    \       Escapes the character immediately following it
    .       Matches any single character except a newline (unless /s is used)
@@ -85,12 +85,14 @@ These work as in normal strings.
    \N{name} A named character
 
    \l  Lowercase next character
-   \u  Uppercase next character
+   \u  Titlecase next character
    \L  Lowercase until \E
    \U  Uppercase until \E
    \Q  Disable pattern metacharacters until \E
    \E  End case modification
 
+For Titlecase, see L</Titlecase>.
+
 This one works differently from normal strings:
 
    \b  An assertion, not backspace, except in a character class
@@ -102,15 +104,19 @@ This one works differently from normal strings:
    [f-j-]   Dash escaped or at start or end means 'dash'
    [^f-j]   Caret indicates "match any character _except_ these"
 
-The following work within or without a character class:
+The following sequences work within or without a character class.
+The first six are locale aware, all are Unicode aware.  The default
+character class equivalent are given.  See L<perllocale> and
+L<perlunicode> for details.
+
+   \d      A digit                     [0-9]
+   \D      A nondigit                  [^0-9]
+   \w      A word character            [a-zA-Z0-9_]
+   \W      A non-word character        [^a-zA-Z0-9_]
+   \s      A whitespace character      [ \t\n\r\f]
+   \S      A non-whitespace character  [^ \t\n\r\f]
 
-   \d      A digit, same as [0-9]
-   \D      A nondigit, same as [^0-9]
-   \w      A word character (alphanumeric), same as [a-zA-Z0-9_]
-   \W      A non-word character, [^a-zA-Z0-9_]
-   \s      A whitespace character, same as [ \t\n\r\f]
-   \S      A non-whitespace character, [^ \t\n\r\f]
-   \C      Match a byte (with Unicode, '.' matches char)
+   \C      Match a byte (with Unicode, '.' matches a character)
    \pP     Match P-named (Unicode) property
    \p{...} Match Unicode property with long name
    \PP     Match non-P
@@ -119,21 +125,21 @@ The following work within or without a character class:
 
 POSIX character classes and their Unicode and Perl equivalents:
 
-   alnum   IsAlnum             Alphanumeric
-   alpha   IsAlpha             Alphabetic
-   ascii   IsASCII             Any ASCII char
-   blank   IsSpace  [ \t]      Horizontal whitespace (GNU)
-   cntrl   IsCntrl             Control characters
-   digit   IsDigit  \d         Digits
-   graph   IsGraph             Alphanumeric and punctuation
-   lower   IsLower             Lowercase chars (locale aware)
-   print   IsPrint             Alphanumeric, punct, and space
-   punct   IsPunct             Punctuation
-   space   IsSpace  [\s\ck]    Whitespace
-           IsSpacePerl   \s    Perl's whitespace definition
-   upper   IsUpper             Uppercase chars (locale aware)
-   word    IsWord   \w         Alphanumeric plus _ (Perl)
-   xdigit  IsXDigit [\dA-Fa-f] Hexadecimal digit
+   alnum   IsAlnum              Alphanumeric
+   alpha   IsAlpha              Alphabetic
+   ascii   IsASCII              Any ASCII char
+   blank   IsSpace  [ \t]       Horizontal whitespace (GNU extension)
+   cntrl   IsCntrl              Control characters
+   digit   IsDigit  \d          Digits
+   graph   IsGraph              Alphanumeric and punctuation
+   lower   IsLower              Lowercase chars (locale and Unicode aware)
+   print   IsPrint              Alphanumeric, punct, and space
+   punct   IsPunct              Punctuation
+   space   IsSpace  [\s\ck]     Whitespace
+           IsSpacePerl   \s     Perl's whitespace definition
+   upper   IsUpper              Uppercase chars (locale and Unicode aware)
+   word    IsWord   \w          Alphanumeric plus _ (Perl extension)
+   xdigit  IsXDigit [0-9A-Fa-f] Hexadecimal digit
 
 Within a character class:
 
@@ -183,7 +189,7 @@ There is no quantifier {,n} -- that gets understood as a literal string.
    (?(cond)yes|no)  cond being integer corresponding to capturing parens
    (?(cond)yes)        or a lookaround/eval zero-width assertion
 
-=head1 VARIABLES
+=head2 VARIABLES
 
    $_    Default variable for operators to use
    $*    Enable multiline matching (deprecated; not in 5.9.0 or later)
@@ -206,12 +212,13 @@ See also L<Devel::SawAmpersand>.
 
 Captured groups are numbered according to their I<opening> paren.
 
-=head1 FUNCTIONS
+=head2 FUNCTIONS
 
    lc          Lowercase a string
    lcfirst     Lowercase first char of a string
    uc          Uppercase a string
-   ucfirst     Uppercase first char of a string
+   ucfirst     Titlecase first char of a string
+
    pos         Return or set current match position
    quotemeta   Quote metacharacters
    reset       Reset ?pattern? status
@@ -219,6 +226,16 @@ Captured groups are numbered according to their I<opening> paren.
 
    split       Use regex to split a string into parts
 
+The first four of these are like the escape sequences C<\L>, C<\l>,
+C<\U>, and C<\u>.  For Titlecase, see L</Titlecase>.
+
+=head2 TERMINOLOGY
+
+=head3 Titlecase
+
+Unicode concept which most often is equal to uppercase, but for
+certain characters like the German "sharp s" there is a difference.
+
 =head1 AUTHOR
 
 Iain Truskett.