reorganize + general improvements

patch · patch · commit 9370560d27bc · 2013-09-04T18:16:02.000-04:00
diff --git a/count-characters/perl5.md b/count-characters/perl5.md
@@ -0,0 +1,32 @@
+# Count characters of a string in Perl 5
+
+## Code points
+
+The core `length` function returns the number of code points when called on a
+character string (instead of a byte string).
+
+    $count = length $str;
+
+## Grapheme clusters
+
+There is no core function to count the number of grapheme clusters; however,
+either of the following examples will perform the task.
+
+    $count = () = $str =~ /\X/g;
+
+    $count++ while $str =~ /\X/g;
+
+The CPAN module
+[Unicode::GCString](https://metacpan.org/module/Unicode::GCString) can also be
+used on character strings.
+
+    use Unicode::GCString;
+
+    $count = Unicode::GCString->new($str)->length;
+
+As well as the CPAN module
+[Unicode::Util](Unicode::GCStrin://metacpan.org/module/Unicode::Util).
+
+    use Unicode::Util qw( grapheme_length );
+
+    $count = grapheme_length($str);
diff --git a/count-characters/perl6.md b/count-characters/perl6.md
@@ -0,0 +1,13 @@
+# Count characters of a string in Perl 6
+
+## Code points
+
+The `codes` method is available for strings (`Str` objects).
+
+    $count = $str.codes;
+
+## Grapheme clusters
+
+The `graphemes` method is available for strings (`Str` objects).
+
+    $count = $str.graphemes;
diff --git a/count-characters/php.md b/count-characters/php.md
@@ -0,0 +1,16 @@
+# Count characters of a string in PHP
+
+## Code points
+
+The `mb_strlen` function is available for strings in PHP 4.0.6 and requires the
+encoding of the string to either passed as the second argument or set in
+`mbstring.internal_encoding`.
+
+    $count = mb_strlen($str, 'UTF-8');
+
+## Grapheme clusters
+
+The `grapheme_strlen` function is available for UTF-8 strings in PHP 5.3.0 or
+the PECL extension [intl](http://pecl.php.net/package/intl).
+
+    $count = grapheme_strlen($str);
diff --git a/count-codepoints/perl5.md b/count-codepoints/perl5.md
diff --git a/count-codepoints/perl6.md b/count-codepoints/perl6.md
diff --git a/encode-decode/perl6.md b/encode-decode/perl6.md
@@ -1,9 +1,11 @@
 # Encode and decode in Perl 6
 
+UTF-8 is the default.
+
     $utf8 = $str.encode;
     $str  = $utf8.decode;
 
-or
+Other encodings can be explicitly specified.
 
-    $utf8 = $str.encode('UTF-8');
-    $str  = $utf8.decode('UTF-8');
+    $utf16 = $str.encode('UTF-16');
+    $str   = $utf16.decode('UTF-16');
diff --git a/io/perl5.md b/io/perl5.md
@@ -1,19 +1,21 @@
-# I/O
+# I/O encoding in Perl 5
 
-## everything
+## All I/O
+
+All standard streams and filehandles.
 
     use open qw( :encoding(UTF-8) :std );
 
-## input
+## Standard streams
 
-    open my $fh, '<:encoding(UTF-8)', $file;
+    binmode STDIN, ':encoding(UTF-8)';
+    binmode STDOUT, ':encoding(UTF-8)';
+    binmode STDERR, ':encoding(UTF-8)';
 
-## output
+## Filehandle input
 
-    open my $fh, '>:encoding(UTF-8)', $file;
+    open my $fh, '<:encoding(UTF-8)', $file;
 
-## standard streams
+## Filehandle output
 
-    binmode STDIN, ':encoding(UTF-8)';
-    binmode STDOUT, ':encoding(UTF-8)';
-    binmode STDERR, ':encoding(UTF-8)';
+    open my $fh, '>:encoding(UTF-8)', $file;
diff --git a/io/perl6.md b/io/perl6.md
@@ -1,15 +1,17 @@
-# I/O
+# I/O encoding in Perl 6
 
-## input
+All I/O is UTF-8 by default.
 
-    my $fh = open $file, :r, :enc<UTF-8>;
+## Standard streams
 
-## output
+    $*IN.encoding  = 'UTF-16';
+    $*OUT.encoding = 'UTF-16';
+    $*ERR.encoding = 'UTF-16';
 
-    my $fh = open $file, :w, :enc<UTF-8>;
+## Filehandle input
 
-## standard streams
+    my $fh = open $file, :r, :enc<UTF-16>;
 
-    $*IN.encoding  = 'UTF-8';
-    $*OUT.encoding = 'UTF-8';
-    $*ERR.encoding = 'UTF-8';
+## Filehandle output
+
+    my $fh = open $file, :w, :enc<UTF-16>;
diff --git a/normalization/javascript.md b/normalization/javascript.md
@@ -1,3 +1,5 @@
+# Unicode normalization in JavaScript
+
     var unorm = require('unorm');
 
     nfd  = unorm.nfd(str);
diff --git a/normalization/perl5.md b/normalization/perl5.md
@@ -1,3 +1,5 @@
+# Unicode normalization in Perl 5
+
     use Unicode::Normalize;
 
     $nfd  = NFD($str);
diff --git a/normalization/perl6.md b/normalization/perl6.md
@@ -1,3 +1,5 @@
+# Unicode normalization in Perl 6
+
     $nfd  = $str.nfd;
     $nfc  = $str.nfc;
     $nfkd = $str.nfkd;
diff --git a/normalization/php.md b/normalization/php.md
@@ -1,3 +1,5 @@
+# Unicode normalization in PHP
+
     $nfd  = Normalizer::normalize($str, Normalizer::Form_D);
     $nfc  = Normalizer::normalize($str, Normalizer::Form_C);
     $nfkd = Normalizer::normalize($str, Normalizer::Form_KD);
diff --git a/normalization/python.md b/normalization/python.md
@@ -1,3 +1,5 @@
+# Unicode normalization in Python
+
     import unicodedata;
 
     nfd  = unicodedata.normalize('NFD', str)
diff --git a/normalization/ruby.md b/normalization/ruby.md
@@ -1,3 +1,5 @@
+# Unicode normalization in Ruby
+
     require 'unicode';
 
     nfd = Unicode::normalize_D(str)
diff --git a/sorting-with-locale/perl5.md b/sorting-with-locale/perl5.md
diff --git a/sorting/perl5.md b/sorting/perl5.md
@@ -1,5 +1,23 @@
+# Sorting with the UCA in Perl 5
+
+The core module
+[Unicode::Collate](https://metacpan.org/module/Unicode::Collate) is used for
+sorting using the Unicode Collation Algorithm.
+
     use Unicode::Collate;
 
     $collator = Unicode::Collate->new;
 
     @sorted = $collator->sort(@unsorted);
+
+## Specific locale
+
+The core module
+[Unicode::Collate::Locale](https://metacpan.org/module/Unicode::Collate::Locale)
+is used for sorting using the UCA with localization.
+
+    use Unicode::Collate::Locale;
+
+    $collator = Unicode::Collate::Locale->new(locale => 'de');
+
+    @sorted = $collator->sort(@unsorted);
diff --git a/source-code/perl5.md b/source-code/perl5.md
@@ -1 +1,7 @@
+# UTF-8 source code in Perl 5
+
     use utf8;
+
+## Pod documentation
+
+    =encoding UTF-8
diff --git a/source-code/perl6.md b/source-code/perl6.md
@@ -0,0 +1,3 @@
+# UTF-8 source code in Perl 6
+
+Source code is expected to be UTF-8 by default.
diff --git a/source-code/python.md b/source-code/python.md
@@ -1 +1,3 @@
+# UTF-8 source code in Python
+
     #-*- coding: UTF-8 -*-
diff --git a/source-code/ruby.md b/source-code/ruby.md
@@ -1,3 +1,5 @@
+# UTF-8 source code in Ruby
+
     # encoding: UTF-8
 
 or

Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Unicode normalization in JavaScript`
	`2`	`+`
`1`	`3`	`var unorm = require('unorm');`
`2`	`4`
`3`	`5`	`nfd = unorm.nfd(str);`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# Unicode normalization in Perl 5`
	`2`	`+`
`1`	`3`	`use Unicode::Normalize;`
`2`	`4`
`3`	`5`	`$nfd = NFD($str);`