In perl.git, the branch blead has been updated

<http://perl5.git.perl.org/perl.git/commitdiff/f34228d67754c62c57c3533a692e29f905d8f15a?hp=42e9b60980bb8e29e76629e14c6aa945194c0647>

- Log -----------------------------------------------------------------
commit f34228d67754c62c57c3533a692e29f905d8f15a
Author: Pali <[email protected]>
Date:   Sun Sep 18 17:52:36 2016 +0200

    perluniintro: Use uppercase UTF-8 encoding name
    
    Reason is consistency with other documentation files.

M       pod/perluniintro.pod

commit 2426b0d31ace94812fc516e3680266d55d1781c0
Author: Pali <[email protected]>
Date:   Sun Sep 18 17:45:57 2016 +0200

    perluniintro: Fix comment, Encode::decode does not have to return string 
with UTF8 flag set

M       pod/perluniintro.pod

commit 016b3422ad385c1af7faa4f0a71c244fdf999e5c
Author: Pali <[email protected]>
Date:   Sun Sep 18 17:44:22 2016 +0200

    perluniintro: Suggest to use utf8::decode() instead heavy Encode when 
sequence of bytes is valid UTF-8

M       pod/perluniintro.pod

commit 6d8e74506f971081362433e3d39fe2e4da9fb302
Author: Pali <[email protected]>
Date:   Sun Sep 18 17:19:59 2016 +0200

    pod: Suggest to use strict :encoding(UTF-8) PerlIO layer over not strict 
:encoding(utf8)
    
    For data exchange it is better to use strict UTF-8 encoding and not perl's 
utf8.

M       lib/PerlIO.pm
M       lib/open.pm
M       pod/perlfunc.pod
M       pod/perlrun.pod
M       pod/perlunicode.pod
M       pod/perluniintro.pod
-----------------------------------------------------------------------

Summary of changes:
 lib/PerlIO.pm        |  4 ++--
 lib/open.pm          | 12 ++++++------
 pod/perlfunc.pod     | 10 +++++-----
 pod/perlrun.pod      |  2 +-
 pod/perlunicode.pod  |  2 +-
 pod/perluniintro.pod | 20 ++++++++++----------
 6 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/lib/PerlIO.pm b/lib/PerlIO.pm
index 2e27f98bba..7658ce497b 100644
--- a/lib/PerlIO.pm
+++ b/lib/PerlIO.pm
@@ -1,6 +1,6 @@
 package PerlIO;
 
-our $VERSION = '1.09';
+our $VERSION = '1.10';
 
 # Map layer name to package that defines it
 our %alias;
@@ -104,7 +104,7 @@ is chosen to render simple text parts (i.e.  non-accented 
letters,
 digits and common punctuation) human readable in the encoded file.
 
 (B<CAUTION>: This layer does not validate byte sequences.  For reading input,
-you should instead use C<:encoding(utf8)> instead of bare C<:utf8>.)
+you should instead use C<:encoding(UTF-8)> instead of bare C<:utf8>.)
 
 Here is how to write your native data out using UTF-8 (or UTF-EBCDIC)
 and then read it back in.
diff --git a/lib/open.pm b/lib/open.pm
index fd22e1b9e7..ca3cf7b409 100644
--- a/lib/open.pm
+++ b/lib/open.pm
@@ -1,7 +1,7 @@
 package open;
 use warnings;
 
-our $VERSION = '1.10';
+our $VERSION = '1.11';
 
 require 5.008001; # for PerlIO::get_layers()
 
@@ -153,7 +153,7 @@ open - perl pragma to set default PerlIO layers for input 
and output
 
     use open IO  => ':locale';
 
-    use open ':encoding(utf8)';
+    use open ':encoding(UTF-8)';
     use open ':locale';
     use open ':encoding(iso-8859-7)';
 
@@ -195,8 +195,8 @@ For example:
 
 These are equivalent
 
-    use open ':encoding(utf8)';
-    use open IO => ':encoding(utf8)';
+    use open ':encoding(UTF-8)';
+    use open IO => ':encoding(UTF-8)';
 
 as are these
 
@@ -221,8 +221,8 @@ The C<:std> subpragma on its own has no effect, but if 
combined with
 the C<:utf8> or C<:encoding> subpragmas, it converts the standard
 filehandles (STDIN, STDOUT, STDERR) to comply with encoding selected
 for input/output handles.  For example, if both input and out are
-chosen to be C<:encoding(utf8)>, a C<:std> will mean that STDIN, STDOUT,
-and STDERR are also in C<:encoding(utf8)>.  On the other hand, if only
+chosen to be C<:encoding(UTF-8)>, a C<:std> will mean that STDIN, STDOUT,
+and STDERR are also in C<:encoding(UTF-8)>.  On the other hand, if only
 output is chosen to be in C<< :encoding(koi8r) >>, a C<:std> will cause
 only the STDOUT and STDERR to be in C<koi8r>.  The C<:locale> subpragma
 implicitly turns on C<:std>.
diff --git a/pod/perlfunc.pod b/pod/perlfunc.pod
index 2b962aa9a3..6f62f3fb40 100644
--- a/pod/perlfunc.pod
+++ b/pod/perlfunc.pod
@@ -6090,7 +6090,7 @@ Note the I<characters>: depending on the status of the 
socket, either
 (8-bit) bytes or characters are received.  By default all sockets
 operate on bytes, but for example if the socket has been changed using
 L<C<binmode>|/binmode FILEHANDLE, LAYER> to operate with the
-C<:encoding(utf8)> I/O layer (see the L<open> pragma), the I/O will
+C<:encoding(UTF-8)> I/O layer (see the L<open> pragma), the I/O will
 operate on UTF8-encoded Unicode
 characters, not bytes.  Similarly for the C<:encoding> layer: in that
 case pretty much any characters can be read.
@@ -6650,7 +6650,7 @@ of the file) from the L<Fcntl> module.  Returns C<1> on 
success, false
 otherwise.
 
 Note the emphasis on bytes: even if the filehandle has been set to operate
-on characters (for example using the C<:encoding(utf8)> I/O layer), the
+on characters (for example using the C<:encoding(UTF-8)> I/O layer), the
 L<C<seek>|/seek FILEHANDLE,POSITION,WHENCE>,
 L<C<tell>|/tell FILEHANDLE>, and
 L<C<sysseek>|/sysseek FILEHANDLE,POSITION,WHENCE>
@@ -6889,7 +6889,7 @@ Note the I<characters>: depending on the status of the 
socket, either
 (8-bit) bytes or characters are sent.  By default all sockets operate
 on bytes, but for example if the socket has been changed using
 L<C<binmode>|/binmode FILEHANDLE, LAYER> to operate with the
-C<:encoding(utf8)> I/O layer (see L<C<open>|/open FILEHANDLE,EXPR>, or
+C<:encoding(UTF-8)> I/O layer (see L<C<open>|/open FILEHANDLE,EXPR>, or
 the L<open> pragma), the I/O will operate on UTF-8
 encoded Unicode characters, not bytes.  Similarly for the C<:encoding>
 layer: in that case pretty much any characters can be sent.
@@ -8535,7 +8535,7 @@ to the current position plus POSITION; and C<2> to set it 
to EOF plus
 POSITION, typically negative.
 
 Note the emphasis on bytes: even if the filehandle has been set to operate
-on characters (for example using the C<:encoding(utf8)> I/O layer), the
+on characters (for example using the C<:encoding(UTF-8)> I/O layer), the
 L<C<seek>|/seek FILEHANDLE,POSITION,WHENCE>,
 L<C<tell>|/tell FILEHANDLE>, and
 L<C<sysseek>|/sysseek FILEHANDLE,POSITION,WHENCE>
@@ -8702,7 +8702,7 @@ the actual filehandle.  If FILEHANDLE is omitted, assumes 
the file
 last read.
 
 Note the emphasis on bytes: even if the filehandle has been set to operate
-on characters (for example using the C<:encoding(utf8)> I/O layer), the
+on characters (for example using the C<:encoding(UTF-8)> I/O layer), the
 L<C<seek>|/seek FILEHANDLE,POSITION,WHENCE>,
 L<C<tell>|/tell FILEHANDLE>, and
 L<C<sysseek>|/sysseek FILEHANDLE,POSITION,WHENCE>
diff --git a/pod/perlrun.pod b/pod/perlrun.pod
index 9d59a6af36..b4bb5a3c6a 100644
--- a/pod/perlrun.pod
+++ b/pod/perlrun.pod
@@ -1121,7 +1121,7 @@ A pseudolayer that enables a flag in the layer below to 
tell Perl
 that output should be in utf8 and that input should be regarded as
 already in valid utf8 form. B<WARNING: It does not check for validity and as 
such
 should be handled with extreme caution for input, because security violations
-can occur with non-shortest UTF-8 encodings, etc.> Generally 
C<:encoding(utf8)> is
+can occur with non-shortest UTF-8 encodings, etc.> Generally 
C<:encoding(UTF-8)> is
 the best option when reading UTF-8 encoded data.
 
 =item :win32
diff --git a/pod/perlunicode.pod b/pod/perlunicode.pod
index ba5e312d02..23818a1ee4 100644
--- a/pod/perlunicode.pod
+++ b/pod/perlunicode.pod
@@ -1889,7 +1889,7 @@ work under 5.6, so you should be safe to try them out.
 A filehandle that should read or write UTF-8
 
   if ($] > 5.008) {
-    binmode $fh, ":encoding(utf8)";
+    binmode $fh, ":encoding(UTF-8)";
   }
 
 =item *
diff --git a/pod/perluniintro.pod b/pod/perluniintro.pod
index 5a865c9912..d35de34581 100644
--- a/pod/perluniintro.pod
+++ b/pod/perluniintro.pod
@@ -358,7 +358,7 @@ The C<Encode> module knows about many encodings and has 
interfaces
 for doing conversions between those encodings:
 
     use Encode 'decode';
-    $data = decode("iso-8859-3", $data); # convert from legacy to utf-8
+    $data = decode("iso-8859-3", $data); # convert from legacy
 
 =head2 Unicode I/O
 
@@ -393,7 +393,7 @@ many encodings have several aliases.  Note that the 
C<:utf8> layer
 must always be specified exactly like that; it is I<not> subject to
 the loose matching of encoding names. Also note that currently C<:utf8> is 
unsafe for
 input, because it accepts the data without validating that it is indeed valid
-UTF-8; you should instead use C<:encoding(utf-8)> (with or without a
+UTF-8; you should instead use C<:encoding(UTF-8)> (with or without a
 hyphen).
 
 See L<PerlIO> for the C<:utf8> layer, L<PerlIO::encoding> and
@@ -406,7 +406,7 @@ Unicode or legacy encodings does not magically turn the 
data into
 Unicode in Perl's eyes.  To do that, specify the appropriate
 layer when opening files
 
-    open(my $fh,'<:encoding(utf8)', 'anything');
+    open(my $fh,'<:encoding(UTF-8)', 'anything');
     my $line_of_unicode = <$fh>;
 
     open(my $fh,'<:encoding(Big5)', 'anything');
@@ -415,8 +415,8 @@ layer when opening files
 The I/O layers can also be specified more flexibly with
 the C<open> pragma.  See L<open>, or look at the following example.
 
-    use open ':encoding(utf8)'; # input/output default encoding will be
-                                # UTF-8
+    use open ':encoding(UTF-8)'; # input/output default encoding will be
+                                 # UTF-8
     open X, ">file";
     print X chr(0x100), "\n";
     close X;
@@ -485,12 +485,12 @@ by repeatedly encoding the data:
     local $/; ## read in the whole file of 8-bit characters
     $t = <F>;
     close F;
-    open F, ">:encoding(utf8)", "file";
+    open F, ">:encoding(UTF-8)", "file";
     print F $t; ## convert to UTF-8 on output
     close F;
 
 If you run this code twice, the contents of the F<file> will be twice
-UTF-8 encoded.  A C<use open ':encoding(utf8)'> would have avoided the
+UTF-8 encoded.  A C<use open ':encoding(UTF-8)'> would have avoided the
 bug, or explicitly opening also the F<file> for input as UTF-8.
 
 B<NOTE>: the C<:utf8> and C<:encoding> features work only if your
@@ -788,7 +788,7 @@ If you have a raw sequence of bytes that you know should be
 interpreted via a particular encoding, you can use C<Encode>:
 
     use Encode 'from_to';
-    from_to($data, "iso-8859-1", "utf-8"); # from latin-1 to utf-8
+    from_to($data, "iso-8859-1", "UTF-8"); # from latin-1 to UTF-8
 
 The call to C<from_to()> changes the bytes in C<$data>, but nothing
 material about the nature of the string has changed as far as Perl is
@@ -817,8 +817,8 @@ pack/unpack to convert to/from Unicode.
 If you have a sequence of bytes you B<know> is valid UTF-8,
 but Perl doesn't know it yet, you can make Perl a believer, too:
 
-    use Encode 'decode_utf8';
-    $Unicode = decode_utf8($bytes);
+    $Unicode = $bytes;
+    utf8::decode($Unicode);
 
 or:
 

--
Perl5 Master Repository

Reply via email to