lib/charnames.t: Move initialization line

[perl5.git] / lib / PerlIO.pm

diff --git a/lib/PerlIO.pm b/lib/PerlIO.pm
index 9a4da3a..7658ce4 100644 (file)
--- a/lib/PerlIO.pm
+++ b/lib/PerlIO.pm
@@ -1,6 +1,6 @@
 package PerlIO;
 
 package PerlIO;
 

-our $VERSION = '1.01';
+our $VERSION = '1.10';

 
 # Map layer name to package that defines it
 our %alias;
 
 # Map layer name to package that defines it
 our %alias;


@@ -19,11 +19,13 @@ sub import
     {
      $layer = "${class}::$layer";
     }
     {
      $layer = "${class}::$layer";
     }

-   eval "require $layer";
+   eval { require $layer =~ s{::}{/}gr . '.pm' };

    warn $@ if $@;
   }
 }
 
    warn $@ if $@;
   }
 }
 

+sub F_UTF8 () { 0x8000 }
+

 1;
 __END__
 
 1;
 __END__
 


@@ -33,9 +35,10 @@ PerlIO - On demand loader for PerlIO layers and root of PerlIO::* name space
 
 =head1 SYNOPSIS
 
 
 =head1 SYNOPSIS
 

-  open($fh,">:crlf", "my.txt"); # portably open a text file for writing
+  open($fh, "<:crlf", "my.txt"); # support platform-native and 
+                                 # CRLF text files

 
 

-  open($fh,"<","his.jpg");      # portably open a binary file for reading
+  open($fh, "<", "his.jpg"); # portably open a binary file for reading

   binmode($fh);
 
   Shell:
   binmode($fh);
 
   Shell:


@@ -59,36 +62,50 @@ The following layers are currently defined:
 
 =over 4
 
 
 =over 4
 

-=item unix
+=item :unix

 
 

-Low level layer which calls C<read>, C<write> and C<lseek> etc.
+Lowest level layer which provides basic PerlIO operations in terms of
+UNIX/POSIX numeric file descriptor calls
+(open(), read(), write(), lseek(), close()).

 
 

-=item stdio
+=item :stdio

 
 Layer which calls C<fread>, C<fwrite> and C<fseek>/C<ftell> etc.  Note
 that as this is "real" stdio it will ignore any layers beneath it and
 
 Layer which calls C<fread>, C<fwrite> and C<fseek>/C<ftell> etc.  Note
 that as this is "real" stdio it will ignore any layers beneath it and

-got straight to the operating system via the C library as usual.
+go straight to the operating system via the C library as usual.
+
+=item :perlio
+
+A from scratch implementation of buffering for PerlIO. Provides fast
+access to the buffer for C<sv_gets> which implements perl's readline/E<lt>E<gt>
+and in general attempts to minimize data copying.
+
+C<:perlio> will insert a C<:unix> layer below itself to do low level IO.

 
 

-=item perlio
+=item :crlf

 
 

-This is a re-implementation of "stdio-like" buffering written as a
-PerlIO "layer".  As such it will call whatever layer is below it for
-its operations.
+A layer that implements DOS/Windows like CRLF line endings.  On read
+converts pairs of CR,LF to a single "\n" newline character.  On write
+converts each "\n" to a CR,LF pair.  Note that this layer will silently
+refuse to be pushed on top of itself.

 
 

-=item crlf
+It currently does I<not> mimic MS-DOS as far as treating of Control-Z
+as being an end-of-file marker.

 
 

-A layer which does CRLF to "\n" translation distinguishing "text" and
-"binary" files in the manner of MS-DOS and similar operating systems.
+Based on the C<:perlio> layer.

 
 

-=item utf8
+=item :utf8

 
 

-Declares that the stream accepts perl's internal encoding of
+Declares that the stream accepts perl's I<internal> encoding of

 characters.  (Which really is UTF-8 on ASCII machines, but is
 UTF-EBCDIC on EBCDIC machines.)  This allows any character perl can
 represent to be read from or written to the stream. The UTF-X encoding
 is chosen to render simple text parts (i.e.  non-accented letters,
 digits and common punctuation) human readable in the encoded file.
 
 characters.  (Which really is UTF-8 on ASCII machines, but is
 UTF-EBCDIC on EBCDIC machines.)  This allows any character perl can
 represent to be read from or written to the stream. The UTF-X encoding
 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(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.
 
 Here is how to write your native data out using UTF-8 (or UTF-EBCDIC)
 and then read it back in.
 


@@ -100,37 +117,121 @@ and then read it back in.
        $in = <F>;
        close(F);
 
        $in = <F>;
        close(F);
 

-=item bytes

 
 

-This is the inverse of C<:utf8> layer. It turns off the flag
+=item :bytes
+
+This is the inverse of the C<:utf8> layer. It turns off the flag

 on the layer below so that data read from it is considered to
 on the layer below so that data read from it is considered to

-be "octets" i.e. characters in range 0..255 only. Likewise
+be "octets" i.e. characters in the range 0..255 only. Likewise

 on output perl will warn if a "wide" character is written
 to a such a stream.
 
 on output perl will warn if a "wide" character is written
 to a such a stream.
 

-=item raw
+=item :raw
+
+The C<:raw> layer is I<defined> as being identical to calling
+C<binmode($fh)> - the stream is made suitable for passing binary data,
+i.e. each byte is passed as-is. The stream will still be
+buffered.
+
+In Perl 5.6 and some books the C<:raw> layer (previously sometimes also
+referred to as a "discipline") is documented as the inverse of the
+C<:crlf> layer. That is no longer the case - other layers which would
+alter the binary nature of the stream are also disabled.  If you want UNIX
+line endings on a platform that normally does CRLF translation, but still
+want UTF-8 or encoding defaults, the appropriate thing to do is to add
+C<:perlio> to the PERLIO environment variable.
+
+The implementation of C<:raw> is as a pseudo-layer which when "pushed"
+pops itself and then any layers which do not declare themselves as suitable
+for binary data. (Undoing :utf8 and :crlf are implemented by clearing
+flags rather than popping layers but that is an implementation detail.)
+
+As a consequence of the fact that C<:raw> normally pops layers,
+it usually only makes sense to have it as the only or first element in
+a layer specification.  When used as the first element it provides
+a known base on which to build e.g.
+
+    open($fh,":raw:utf8",...)
+
+will construct a "binary" stream, but then enable UTF-8 translation.
+
+=item :pop
+
+A pseudo layer that removes the top-most layer. Gives perl code a
+way to manipulate the layer stack.  Note that C<:pop> only works on
+real layers and will not undo the effects of pseudo layers like
+C<:utf8>.  An example of a possible use might be:
+
+    open($fh,...)
+    ...
+    binmode($fh,":encoding(...)");  # next chunk is encoded
+    ...
+    binmode($fh,":pop");            # back to un-encoded
+
+A more elegant (and safer) interface is needed.
+
+=item :win32
+
+On Win32 platforms this I<experimental> layer uses the native "handle" IO
+rather than the unix-like numeric file descriptor layer. Known to be
+buggy as of perl 5.8.2.
+
+=back
+
+=head2 Custom Layers
+
+It is possible to write custom layers in addition to the above builtin
+ones, both in C/XS and Perl.  Two such layers (and one example written
+in Perl using the latter) come with the Perl distribution.
+
+=over 4
+
+=item :encoding

 
 

-B<Note that the explicit use of the C<raw> layer is deprecated.>
+Use C<:encoding(ENCODING)> either in open() or binmode() to install
+a layer that transparently does character set and encoding transformations,
+for example from Shift-JIS to Unicode.  Note that under C<stdio>
+an C<:encoding> also enables C<:utf8>.  See L<PerlIO::encoding>
+for more information.

 
 

-A pseudo-layer which performs two functions (which is messy, but
-necessary to maintain compatibility with non-PerlIO builds of Perl
-and their way things have been documented elsewhere).
+=item :mmap

 
 

-Firstly it forces the file handle to be considered binary at that
-point in the layer stack, i.e. it turns off any CRLF translation.
+A layer which implements "reading" of files by using C<mmap()> to
+make a (whole) file appear in the process's address space, and then
+using that as PerlIO's "buffer". This I<may> be faster in certain
+circumstances for large files, and may result in less physical memory
+use when multiple processes are reading the same file.

 
 

-Secondly in prevents the IO system seaching back before it in the
-layer specification.  Thus:
+Files which are not C<mmap()>-able revert to behaving like the C<:perlio>
+layer. Writes also behave like the C<:perlio> layer, as C<mmap()> for write
+needs extra house-keeping (to extend the file) which negates any advantage.

 
 

-    open($fh,":raw:perlio",...)
+The C<:mmap> layer will not exist if the platform does not support C<mmap()>.

 
 

-Forces the use of C<perlio> layer even if the platform default, or
-C<use open> default is something else (such as ":encoding(iso-8859-7)")
-(the C<:encoding> requires C<use Encode>) which would interfere with
-binary nature of the stream.
+=item :via
+
+Use C<:via(MODULE)> either in open() or binmode() to install a layer
+that does whatever transformation (for example compression /
+decompression, encryption / decryption) to the filehandle.
+See L<PerlIO::via> for more information.

 
 =back
 
 
 =back
 

+=head2 Alternatives to raw
+
+To get a binary stream an alternate method is to use:
+
+    open($fh,"whatever")
+    binmode($fh);
+
+this has the advantage of being backward compatible with how such things have
+had to be coded on some platforms for years.
+
+To get an unbuffered stream specify an unbuffered layer (e.g. C<:unix>)
+in the open call:
+
+    open($fh,"<:unix",$path)
+

 =head2 Defaults and how to override them
 
 If the platform is MS-DOS like and normally does CRLF to "\n"
 =head2 Defaults and how to override them
 
 If the platform is MS-DOS like and normally does CRLF to "\n"


@@ -141,8 +242,8 @@ translation for text files then the default layers are :
 (The low level "unix" layer may be replaced by a platform specific low
 level layer.)
 
 (The low level "unix" layer may be replaced by a platform specific low
 level layer.)
 

-Otherwise if C<Configure> found out how to do "fast" IO using system's
-stdio, then the default layers are :
+Otherwise if C<Configure> found out how to do "fast" IO using the system's
+stdio, then the default layers are:

 
   unix stdio
 
 
   unix stdio
 


@@ -153,8 +254,8 @@ Otherwise the default layers are
 These defaults may change once perlio has been better tested and tuned.
 
 The default can be overridden by setting the environment variable
 These defaults may change once perlio has been better tested and tuned.
 
 The default can be overridden by setting the environment variable

-PERLIO to a space separated list of layers (unix or platform low level
-layer is always pushed first).
+PERLIO to a space separated list of layers (C<unix> or platform low
+level layer is always pushed first).

 
 This can be used to see the effect of/bugs in the various layers e.g.
 
 
 This can be used to see the effect of/bugs in the various layers e.g.
 


@@ -162,13 +263,69 @@ This can be used to see the effect of/bugs in the various layers e.g.
   PERLIO=stdio  ./perl harness
   PERLIO=perlio ./perl harness
 
   PERLIO=stdio  ./perl harness
   PERLIO=perlio ./perl harness
 

+For the various values of PERLIO see L<perlrun/PERLIO>.
+
+=head2 Querying the layers of filehandles
+
+The following returns the B<names> of the PerlIO layers on a filehandle.
+
+   my @layers = PerlIO::get_layers($fh); # Or FH, *FH, "FH".
+
+The layers are returned in the order an open() or binmode() call would
+use them.  Note that the "default stack" depends on the operating
+system and on the Perl version, and both the compile-time and
+runtime configurations of Perl.
+
+The following table summarizes the default layers on UNIX-like and
+DOS-like platforms and depending on the setting of C<$ENV{PERLIO}>:
+
+ PERLIO     UNIX-like                   DOS-like
+ ------     ---------                   --------
+ unset / "" unix perlio / stdio [1]     unix crlf
+ stdio      unix perlio / stdio [1]     stdio
+ perlio     unix perlio                 unix perlio
+
+ # [1] "stdio" if Configure found out how to do "fast stdio" (depends
+ # on the stdio implementation) and in Perl 5.8, otherwise "unix perlio"
+
+By default the layers from the input side of the filehandle are
+returned; to get the output side, use the optional C<output> argument:
+
+   my @layers = PerlIO::get_layers($fh, output => 1);
+
+(Usually the layers are identical on either side of a filehandle but
+for example with sockets there may be differences, or if you have
+been using the C<open> pragma.)
+
+There is no set_layers(), nor does get_layers() return a tied array
+mirroring the stack, or anything fancy like that.  This is not
+accidental or unintentional.  The PerlIO layer stack is a bit more
+complicated than just a stack (see for example the behaviour of C<:raw>).
+You are supposed to use open() and binmode() to manipulate the stack.
+
+B<Implementation details follow, please close your eyes.>
+
+The arguments to layers are by default returned in parentheses after
+the name of the layer, and certain layers (like C<utf8>) are not real
+layers but instead flags on real layers; to get all of these returned
+separately, use the optional C<details> argument:
+
+   my @layer_and_args_and_flags = PerlIO::get_layers($fh, details => 1);
+
+The result will be up to be three times the number of layers:
+the first element will be a name, the second element the arguments
+(unspecified arguments will be C<undef>), the third element the flags,
+the fourth element a name again, and so forth.
+
+B<You may open your eyes now.>
+

 =head1 AUTHOR
 
 Nick Ing-Simmons E<lt>nick@ing-simmons.netE<gt>
 
 =head1 SEE ALSO
 
 =head1 AUTHOR
 
 Nick Ing-Simmons E<lt>nick@ing-simmons.netE<gt>
 
 =head1 SEE ALSO
 

-L<perlfunc/"binmode">, L<perlfunc/"open">, L<perlunicode>, L<Encode>
+L<perlfunc/"binmode">, L<perlfunc/"open">, L<perlunicode>, L<perliol>,
+L<Encode>

 
 =cut
 
 =cut

-