.\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 .\" .\" Standard preamble: .\" ======================================================================== .de Sh \" Subsection heading .br .if t .Sp .ne 5 .PP \fB\\$1\fR .PP .. .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. | will give a .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' .\" expand to `' in nroff, nothing in troff, for use with C<>. .tr \(*W-|\(bv\*(Tr .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' 'br\} .\" .\" If the F register is turned on, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .if \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . nr % 0 . rr F .\} .\" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .hy 0 .if n .na .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. . \" fudge factors for nroff and troff .if n \{\ . ds #H 0 . ds #V .8m . ds #F .3m . ds #[ \f1 . ds #] \fP .\} .if t \{\ . ds #H ((1u-(\\\\n(.fu%2u))*.13m) . ds #V .6m . ds #F 0 . ds #[ \& . ds #] \& .\} . \" simple accents for nroff and troff .if n \{\ . ds ' \& . ds ` \& . ds ^ \& . ds , \& . ds ~ ~ . ds / .\} .if t \{\ . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' .\} . \" troff and (daisy-wheel) nroff accents .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' .ds 8 \h'\*(#H'\(*b\h'-\*(#H' .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] .ds ae a\h'-(\w'a'u*4/10)'e .ds Ae A\h'-(\w'A'u*4/10)'E . \" corrections for vroff .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' . \" for low resolution devices (crt and lpr) .if \n(.H>23 .if \n(.V>19 \ \{\ . ds : e . ds 8 ss . ds o a . ds d- d\h'-1'\(ga . ds D- D\h'-1'\(hy . ds th \o'bp' . ds Th \o'LP' . ds ae ae . ds Ae AE .\} .rm #[ #] #H #V #F C .\" ======================================================================== .\" .IX Title "Encode::PerlIO 3" .TH Encode::PerlIO 3 "2002-06-01" "perl v5.8.0" "Perl Programmers Reference Guide" .SH "NAME" Encode::PerlIO \-\- a detailed document on Encode and PerlIO .SH "Overview" .IX Header "Overview" It is very common to want to do encoding transformations when reading or writing files, network connections, pipes etc. If Perl is configured to use the new 'perlio' \s-1IO\s0 system then \&\f(CW\*(C`Encode\*(C'\fR provides a \*(L"layer\*(R" (see PerlIO) which can transform data as it is read or written. .PP Here is how the blind poet would modernise the encoding: .PP .Vb 7 \& use Encode; \& open(my $iliad,'<:encoding(iso-8859-7)','iliad.greek'); \& open(my $utf8,'>:utf8','iliad.utf8'); \& my @epic = <$iliad>; \& print $utf8 @epic; \& close($utf8); \& close($illiad); .Ve .PP In addition, the new \s-1IO\s0 system can also be configured to read/write \&\s-1UTF\-8\s0 encoded characters (as noted above, this is efficient): .PP .Vb 2 \& open(my $fh,'>:utf8','anything'); \& print $fh "Any \ex{0021} string \eN{SMILEY FACE}\en"; .Ve .PP Either of the above forms of \*(L"layer\*(R" specifications can be made the default for a lexical scope with the \f(CW\*(C`use open ...\*(C'\fR pragma. See open. .PP Once a handle is open, its layers can be altered using \f(CW\*(C`binmode\*(C'\fR. .PP Without any such configuration, or if Perl itself is built using the system's own \s-1IO\s0, then write operations assume that the file handle accepts only \fIbytes\fR and will \f(CW\*(C`die\*(C'\fR if a character larger than 255 is written to the handle. When reading, each octet from the handle becomes a byte\-in\-a\-character. Note that this default is the same behaviour as bytes-only languages (including Perl before v5.6) would have, and is sufficient to handle native 8\-bit encodings e.g. iso\-8859\-1, \&\s-1EBCDIC\s0 etc. and any legacy mechanisms for handling other encodings and binary data. .PP In other cases, it is the program's responsibility to transform characters into bytes using the \s-1API\s0 above before doing writes, and to transform the bytes read from a handle into characters before doing \&\*(L"character operations\*(R" (e.g. \f(CW\*(C`lc\*(C'\fR, \f(CW\*(C`/\eW+/\*(C'\fR, ...). .PP You can also use PerlIO to convert larger amounts of data you don't want to bring into memory. For example, to convert between \s-1ISO\-8859\-1\s0 (Latin 1) and \s-1UTF\-8\s0 (or UTF-EBCDIC in \s-1EBCDIC\s0 machines): .PP .Vb 3 \& open(F, "<:encoding(iso-8859-1)", "data.txt") or die $!; \& open(G, ">:utf8", "data.utf") or die $!; \& while () { print G } .Ve .PP .Vb 2 \& # Could also do "print G " but that would pull \& # the whole file into memory just to write it out again. .Ve .PP More examples: .PP .Vb 3 \& open(my $f, "<:encoding(cp1252)") \& open(my $g, ">:encoding(iso-8859-2)") \& open(my $h, ">:encoding(latin9)") # iso-8859-15 .Ve .PP See also encoding for how to change the default encoding of the data in your script. .SH "How does it work?" .IX Header "How does it work?" Here is a crude diagram of how filehandle, PerlIO, and Encode interact. .PP .Vb 3 \& filehandle <-> PerlIO PerlIO <-> scalar (read/printed) \& \e / \& Encode .Ve .PP When PerlIO receives data from either direction, it fills a buffer (currently with 1024 bytes) and passes the buffer to Encode. Encode tries to convert the valid part and passes it back to PerlIO, leaving invalid parts (usually a partial character) in the buffer. PerlIO then appends more data to the buffer, calls Encode again, and so on until the data stream ends. .PP To do so, PerlIO always calls (de|en)code methods with \s-1CHECK\s0 set to 1. This ensures that the method stops at the right place when it encounters partial character. The following is what happens when PerlIO and Encode tries to encode (from utf8) more than 1024 bytes and the buffer boundary happens to be in the middle of a character. .PP .Vb 5 \& A B C .... ~ \ex{3000} .... \& 41 42 43 .... 7E e3 80 80 .... \& <- buffer ---------------> \& << encoded >>>>>>>>>> \& <- next buffer ------ .Ve .PP Encode converts from the beginning to \ex7E, leaving \exe3 in the buffer because it is invalid (partial character). .PP Unfortunately, this scheme does not work well with escape-based encodings such as \s-1ISO\-2022\-JP\s0. Let's see what happens in that case in the next chapter. .SH "BUGS" .IX Header "BUGS" Now let's see what happens when you try to decode from \s-1ISO\-2022\-JP\s0 and the buffer ends in the middle of a character. .PP .Vb 5 \& JIS208-ESC \ex{5f3e} \& A B C .... ~ \ee $ B |DAN | .... \& 41 42 43 .... 7E 1b 24 41 43 46 .... \& <- buffer ---------------------------> \& << encoded >>>>>>>>>>>>>>>>>>>>>>> .Ve .PP As you see, the next buffer begins with \ex43. But \ex43 is 'C' in \&\s-1ASCII\s0, which is wrong in this case because we are now in \s-1JISX\s0 0208 area so it has to convert \ex43\ex46, not \ex43. Unlike utf8 and \s-1EUC\s0, in escape-based encodings you can't tell if a given octet is a whole character or just part of it. .PP There are actually several ways to solve this problem but none of them is fast enough to be practical. From Encode's point of view, the easiest solution is for PerlIO to implement a line buffer instead of a fixed-length buffer, but that makes PerlIO really complicated. .PP So for the time being, using escape-based encodings in the \&\*(L":\fIencoding()\fR\*(R" layer of PerlIO does not work well. .Sh "Workaround" .IX Subsection "Workaround" If you still insist, you can at least use \*(L":\fIencoding()\fR\*(R" by making sure the buffer never gets full. Here is an example. .PP .Vb 6 \& use FileHandle; \& binmode(STDOUT, ":encoding(7bit-jis)"); \& STDOUT->autoflush(1); # don't forget this! \& for my $l (@lines){ # $l cannot be longer than 1023 bytes \& print $l; \& } .Ve .Sh "How can I tell whether my encoding fully supports PerlIO ?" .IX Subsection "How can I tell whether my encoding fully supports PerlIO ?" As of this writing, any encoding whose class belongs to Encode::XS and Encode::Unicode works. The Encode module has a \f(CW\*(C`perlio_ok\*(C'\fR method which you can use before appling PerlIO encoding to the filehandle. Here is an example: .PP .Vb 7 \& my $use_perlio = perlio_ok($enc); \& my $layer = $use_perlio ? "<:raw" : "<:encoding($enc)"; \& open my $fh, $layer, $file or die "$file : $!"; \& while(<$fh>){ \& $_ = decode($enc, $_) unless $use_perlio; \& # .... \& } .Ve .SH "SEE ALSO" .IX Header "SEE ALSO" Encode::Encoding, Encode::Supported, Encode::PerlIO, encoding, perlebcdic, \&\*(L"open\*(R" in perlfunc, perlunicode, utf8, the Perl Unicode Mailing List