Plan 9 from Bell Labs’s /usr/web/sources/contrib/gabidiaz/root/sys/man/1perl/perlebcdic

Copyright © 2021 Plan 9 Foundation.
Distributed under the MIT License.
Download the Plan 9 distribution.


.\" 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 "PERLEBCDIC 1"
.TH PERLEBCDIC 1 "2002-11-24" "perl v5.8.0" "Perl Programmers Reference Guide"
.SH "NAME"
perlebcdic \- Considerations for running Perl on EBCDIC platforms
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
An exploration of some of the issues facing Perl programmers
on \s-1EBCDIC\s0 based computers.  We do not cover localization, 
internationalization, or multi byte character set issues other
than some discussion of \s-1UTF\-8\s0 and \s-1UTF\-EBCDIC\s0.
.PP
Portions that are still incomplete are marked with \s-1XXX\s0.
.SH "COMMON CHARACTER CODE SETS"
.IX Header "COMMON CHARACTER CODE SETS"
.Sh "\s-1ASCII\s0"
.IX Subsection "ASCII"
The American Standard Code for Information Interchange is a set of
integers running from 0 to 127 (decimal) that imply character 
interpretation by the display and other system(s) of computers.  
The range 0..127 can be covered by setting the bits in a 7\-bit binary 
digit, hence the set is sometimes referred to as a \*(L"7\-bit \s-1ASCII\s0\*(R".  
\&\s-1ASCII\s0 was described by the American National Standards Institute 
document \s-1ANSI\s0 X3.4\-1986.  It was also described by \s-1ISO\s0 646:1991 
(with localization for currency symbols).  The full \s-1ASCII\s0 set is 
given in the table below as the first 128 elements.  Languages that 
can be written adequately with the characters in \s-1ASCII\s0 include 
English, Hawaiian, Indonesian, Swahili and some Native American 
languages.
.PP
There are many character sets that extend the range of integers
from 0..2**7\-1 up to 2**8\-1, or 8 bit bytes (octets if you prefer).
One common one is the \s-1ISO\s0 8859\-1 character set.
.Sh "\s-1ISO\s0 8859"
.IX Subsection "ISO 8859"
The \s-1ISO\s0 8859\-$n are a collection of character code sets from the 
International Organization for Standardization (\s-1ISO\s0) each of which 
adds characters to the \s-1ASCII\s0 set that are typically found in European 
languages many of which are based on the Roman, or Latin, alphabet.
.Sh "Latin 1 (\s-1ISO\s0 8859\-1)"
.IX Subsection "Latin 1 (ISO 8859-1)"
A particular 8\-bit extension to \s-1ASCII\s0 that includes grave and acute 
accented Latin characters.  Languages that can employ \s-1ISO\s0 8859\-1 
include all the languages covered by \s-1ASCII\s0 as well as Afrikaans, 
Albanian, Basque, Catalan, Danish, Faroese, Finnish, Norwegian, 
Portuguese, Spanish, and Swedish.  Dutch is covered albeit without 
the ij ligature.  French is covered too but without the oe ligature. 
German can use \s-1ISO\s0 8859\-1 but must do so without German-style
quotation marks.  This set is based on Western European extensions 
to \s-1ASCII\s0 and is commonly encountered in world wide web work.
In \s-1IBM\s0 character code set identification terminology \s-1ISO\s0 8859\-1 is
also known as \s-1CCSID\s0 819 (or sometimes 0819 or even 00819).
.Sh "\s-1EBCDIC\s0"
.IX Subsection "EBCDIC"
The Extended Binary Coded Decimal Interchange Code refers to a 
large collection of slightly different single and multi byte 
coded character sets that are different from \s-1ASCII\s0 or \s-1ISO\s0 8859\-1 
and typically run on host computers.  The \s-1EBCDIC\s0 encodings derive 
from 8 bit byte extensions of Hollerith punched card encodings.
The layout on the cards was such that high bits were set for the
upper and lower case alphabet characters [a\-z] and [A\-Z], but there
were gaps within each latin alphabet range.
.PP
Some \s-1IBM\s0 \s-1EBCDIC\s0 character sets may be known by character code set 
identification numbers (\s-1CCSID\s0 numbers) or code page numbers.  Leading
zero digits in \s-1CCSID\s0 numbers within this document are insignificant.
E.g. \s-1CCSID\s0 0037 may be referred to as 37 in places.
.Sh "13 variant characters"
.IX Subsection "13 variant characters"
Among \s-1IBM\s0 \s-1EBCDIC\s0 character code sets there are 13 characters that
are often mapped to different integer values.  Those characters
are known as the 13 \*(L"variant\*(R" characters and are:
.PP
.Vb 1
\&    \e [ ] { } ^ ~ ! # | $ @ `
.Ve
.Sh "0037"
.IX Subsection "0037"
Character code set \s-1ID\s0 0037 is a mapping of the \s-1ASCII\s0 plus Latin\-1 
characters (i.e. \s-1ISO\s0 8859\-1) to an \s-1EBCDIC\s0 set.  0037 is used 
in North American English locales on the \s-1OS/400\s0 operating system 
that runs on \s-1AS/400\s0 computers.  \s-1CCSID\s0 37 differs from \s-1ISO\s0 8859\-1 
in 237 places, in other words they agree on only 19 code point values.
.Sh "1047"
.IX Subsection "1047"
Character code set \s-1ID\s0 1047 is also a mapping of the \s-1ASCII\s0 plus 
Latin\-1 characters (i.e. \s-1ISO\s0 8859\-1) to an \s-1EBCDIC\s0 set.  1047 is 
used under Unix System Services for \s-1OS/390\s0 or z/OS, and OpenEdition 
for \s-1VM/ESA\s0.  \s-1CCSID\s0 1047 differs from \s-1CCSID\s0 0037 in eight places.
.Sh "POSIX-BC"
.IX Subsection "POSIX-BC"
The \s-1EBCDIC\s0 code page in use on Siemens' \s-1BS2000\s0 system is distinct from
1047 and 0037.  It is identified below as the POSIX-BC set.
.Sh "Unicode code points versus \s-1EBCDIC\s0 code points"
.IX Subsection "Unicode code points versus EBCDIC code points"
In Unicode terminology a \fIcode point\fR is the number assigned to a
character: for example, in \s-1EBCDIC\s0 the character \*(L"A\*(R" is usually assigned
the number 193.  In Unicode the character \*(L"A\*(R" is assigned the number 65.
This causes a problem with the semantics of the pack/unpack \*(L"U\*(R", which
are supposed to pack Unicode code points to characters and back to numbers.
The problem is: which code points to use for code points less than 256?
(for 256 and over there's no problem: Unicode code points are used)
In \s-1EBCDIC\s0, for the low 256 the \s-1EBCDIC\s0 code points are used.  This
means that the equivalences
.PP
.Vb 2
\&        pack("U", ord($character)) eq $character
\&        unpack("U", $character) == ord $character
.Ve
.PP
will hold.  (If Unicode code points were applied consistently over
all the possible code points, pack(\*(L"U\*(R",ord(\*(L"A\*(R")) would in \s-1EBCDIC\s0
equal \fIA with acute\fR or chr(101), and unpack(\*(L"U\*(R", \*(L"A\*(R") would equal
65, or \fInon-breaking space\fR, not 193, or ord \*(L"A\*(R".)
.Sh "Remaining Perl Unicode problems in \s-1EBCDIC\s0"
.IX Subsection "Remaining Perl Unicode problems in EBCDIC"
.IP "\(bu" 4
Many of the remaining seem to be related to case-insensitive matching:
for example, \f(CW\*(C`/[\ex{131}]/\*(C'\fR (\s-1LATIN\s0 \s-1SMALL\s0 \s-1LETTER\s0 \s-1DOTLESS\s0 I) does
not match \*(L"I\*(R" case\-insensitively, as it should under Unicode.
(The match succeeds in ASCII-derived platforms.)
.IP "\(bu" 4
The extensions Unicode::Collate and Unicode::Normalized are not
supported under \s-1EBCDIC\s0, likewise for the encoding pragma.
.Sh "Unicode and \s-1UTF\s0"
.IX Subsection "Unicode and UTF"
\&\s-1UTF\s0 is a Unicode Transformation Format.  \s-1UTF\-8\s0 is a Unicode conforming
representation of the Unicode standard that looks very much like \s-1ASCII\s0.
UTF-EBCDIC is an attempt to represent Unicode characters in an \s-1EBCDIC\s0
transparent manner.
.Sh "Using Encode"
.IX Subsection "Using Encode"
Starting from Perl 5.8 you can use the standard new module Encode
to translate from \s-1EBCDIC\s0 to Latin\-1 code points
.PP
.Vb 1
\&        use Encode 'from_to';
.Ve
.PP
.Vb 1
\&        my %ebcdic = ( 176 => 'cp37', 95 => 'cp1047', 106 => 'posix-bc' );
.Ve
.PP
.Vb 3
\&        # $a is in EBCDIC code points
\&        from_to($a, $ebcdic{ord '^'}, 'latin1');
\&        # $a is ISO 8859-1 code points
.Ve
.PP
and from Latin\-1 code points to \s-1EBCDIC\s0 code points
.PP
.Vb 1
\&        use Encode 'from_to';
.Ve
.PP
.Vb 1
\&        my %ebcdic = ( 176 => 'cp37', 95 => 'cp1047', 106 => 'posix-bc' );
.Ve
.PP
.Vb 3
\&        # $a is ISO 8859-1 code points
\&        from_to($a, 'latin1', $ebcdic{ord '^'});
\&        # $a is in EBCDIC code points
.Ve
.PP
For doing I/O it is suggested that you use the autotranslating features
of PerlIO, see perluniintro.
.SH "SINGLE OCTET TABLES"
.IX Header "SINGLE OCTET TABLES"
The following tables list the \s-1ASCII\s0 and Latin 1 ordered sets including
the subsets: C0 controls (0..31), \s-1ASCII\s0 graphics (32..7e), delete (7f),
C1 controls (80..9f), and Latin\-1 (a.k.a. \s-1ISO\s0 8859\-1) (a0..ff).  In the 
table non-printing control character names as well as the Latin 1 
extensions to \s-1ASCII\s0 have been labelled with character names roughly 
corresponding to \fIThe Unicode Standard, Version 3.0\fR albeit with 
substitutions such as s/LATIN// and s/VULGAR// in all cases, 
s/CAPITAL \s-1LETTER//\s0 in some cases, and s/SMALL \s-1LETTER\s0 ([A\-Z])/\el$1/ 
in some other cases (the \f(CW\*(C`charnames\*(C'\fR pragma names unfortunately do 
not list explicit names for the C0 or C1 control characters).  The 
\&\*(L"names\*(R" of the C1 control set (128..159 in \s-1ISO\s0 8859\-1) listed here are 
somewhat arbitrary.  The differences between the 0037 and 1047 sets are 
flagged with ***.  The differences between the 1047 and POSIX-BC sets 
are flagged with ###.  All \fIord()\fR numbers listed are decimal.  If you 
would rather see this table listing octal values then run the table 
(that is, the pod version of this document since this recipe may not 
work with a pod2_other_format translation) through:
.IP "recipe 0" 4
.IX Item "recipe 0"
.PP
.Vb 2
\&    perl -ne 'if(/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)/)' \e
\&     -e '{printf("%s%-9o%-9o%-9o%o\en",$1,$2,$3,$4,$5)}' perlebcdic.pod
.Ve
.PP
If you want to retain the UTF-x code points then in script form you
might want to write:
.IP "recipe 1" 4
.IX Item "recipe 1"
.PP
.Vb 14
\&    open(FH,"<perlebcdic.pod") or die "Could not open perlebcdic.pod: $!";
\&    while (<FH>) {
\&        if (/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\e.?(\ed*)\es+(\ed+)\e.?(\ed*)/)  {
\&            if ($7 ne '' && $9 ne '') {
\&                printf("%s%-9o%-9o%-9o%-9o%-3o.%-5o%-3o.%o\en",$1,$2,$3,$4,$5,$6,$7,$8,$9);
\&            }
\&            elsif ($7 ne '') {
\&                printf("%s%-9o%-9o%-9o%-9o%-3o.%-5o%o\en",$1,$2,$3,$4,$5,$6,$7,$8);
\&            }
\&            else {
\&                printf("%s%-9o%-9o%-9o%-9o%-9o%o\en",$1,$2,$3,$4,$5,$6,$8);
\&            }
\&        }
\&    }
.Ve
.PP
If you would rather see this table listing hexadecimal values then
run the table through:
.IP "recipe 2" 4
.IX Item "recipe 2"
.PP
.Vb 2
\&    perl -ne 'if(/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)/)' \e
\&     -e '{printf("%s%-9X%-9X%-9X%X\en",$1,$2,$3,$4,$5)}' perlebcdic.pod
.Ve
.PP
Or, in order to retain the UTF-x code points in hexadecimal:
.IP "recipe 3" 4
.IX Item "recipe 3"
.PP
.Vb 14
\&    open(FH,"<perlebcdic.pod") or die "Could not open perlebcdic.pod: $!";
\&    while (<FH>) {
\&        if (/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\e.?(\ed*)\es+(\ed+)\e.?(\ed*)/)  {
\&            if ($7 ne '' && $9 ne '') {
\&                printf("%s%-9X%-9X%-9X%-9X%-2X.%-6X%-2X.%X\en",$1,$2,$3,$4,$5,$6,$7,$8,$9);
\&            }
\&            elsif ($7 ne '') {
\&                printf("%s%-9X%-9X%-9X%-9X%-2X.%-6X%X\en",$1,$2,$3,$4,$5,$6,$7,$8);
\&            }
\&            else {
\&                printf("%s%-9X%-9X%-9X%-9X%-9X%X\en",$1,$2,$3,$4,$5,$6,$8);
\&            }
\&        }
\&    }
.Ve
.PP
.Vb 260
\&                                                                     incomp-  incomp-
\&                                 8859-1                              lete     lete
\&    chr                          0819     0037     1047     POSIX-BC UTF-8    UTF-EBCDIC
\&    ------------------------------------------------------------------------------------
\&    <NULL>                       0        0        0        0        0        0 
\&    <START OF HEADING>           1        1        1        1        1        1
\&    <START OF TEXT>              2        2        2        2        2        2
\&    <END OF TEXT>                3        3        3        3        3        3
\&    <END OF TRANSMISSION>        4        55       55       55       4        55 
\&    <ENQUIRY>                    5        45       45       45       5        45 
\&    <ACKNOWLEDGE>                6        46       46       46       6        46 
\&    <BELL>                       7        47       47       47       7        47 
\&    <BACKSPACE>                  8        22       22       22       8        22 
\&    <HORIZONTAL TABULATION>      9        5        5        5        9        5 
\&    <LINE FEED>                  10       37       21       21       10       21       ***
\&    <VERTICAL TABULATION>        11       11       11       11       11       11
\&    <FORM FEED>                  12       12       12       12       12       12
\&    <CARRIAGE RETURN>            13       13       13       13       13       13
\&    <SHIFT OUT>                  14       14       14       14       14       14
\&    <SHIFT IN>                   15       15       15       15       15       15
\&    <DATA LINK ESCAPE>           16       16       16       16       16       16
\&    <DEVICE CONTROL ONE>         17       17       17       17       17       17
\&    <DEVICE CONTROL TWO>         18       18       18       18       18       18
\&    <DEVICE CONTROL THREE>       19       19       19       19       19       19
\&    <DEVICE CONTROL FOUR>        20       60       60       60       20       60
\&    <NEGATIVE ACKNOWLEDGE>       21       61       61       61       21       61
\&    <SYNCHRONOUS IDLE>           22       50       50       50       22       50
\&    <END OF TRANSMISSION BLOCK>  23       38       38       38       23       38
\&    <CANCEL>                     24       24       24       24       24       24
\&    <END OF MEDIUM>              25       25       25       25       25       25
\&    <SUBSTITUTE>                 26       63       63       63       26       63
\&    <ESCAPE>                     27       39       39       39       27       39
\&    <FILE SEPARATOR>             28       28       28       28       28       28
\&    <GROUP SEPARATOR>            29       29       29       29       29       29
\&    <RECORD SEPARATOR>           30       30       30       30       30       30
\&    <UNIT SEPARATOR>             31       31       31       31       31       31
\&    <SPACE>                      32       64       64       64       32       64
\&    !                            33       90       90       90       33       90
\&    "                            34       127      127      127      34       127
\&    #                            35       123      123      123      35       123
\&    $                            36       91       91       91       36       91
\&    %                            37       108      108      108      37       108
\&    &                            38       80       80       80       38       80
\&    '                            39       125      125      125      39       125
\&    (                            40       77       77       77       40       77
\&    )                            41       93       93       93       41       93
\&    *                            42       92       92       92       42       92
\&    +                            43       78       78       78       43       78
\&    ,                            44       107      107      107      44       107
\&    -                            45       96       96       96       45       96
\&    .                            46       75       75       75       46       75
\&    /                            47       97       97       97       47       97
\&    0                            48       240      240      240      48       240
\&    1                            49       241      241      241      49       241
\&    2                            50       242      242      242      50       242
\&    3                            51       243      243      243      51       243
\&    4                            52       244      244      244      52       244
\&    5                            53       245      245      245      53       245
\&    6                            54       246      246      246      54       246
\&    7                            55       247      247      247      55       247
\&    8                            56       248      248      248      56       248
\&    9                            57       249      249      249      57       249
\&    :                            58       122      122      122      58       122
\&    ;                            59       94       94       94       59       94
\&    <                            60       76       76       76       60       76
\&    =                            61       126      126      126      61       126
\&    >                            62       110      110      110      62       110
\&    ?                            63       111      111      111      63       111
\&    @                            64       124      124      124      64       124
\&    A                            65       193      193      193      65       193
\&    B                            66       194      194      194      66       194
\&    C                            67       195      195      195      67       195
\&    D                            68       196      196      196      68       196
\&    E                            69       197      197      197      69       197
\&    F                            70       198      198      198      70       198
\&    G                            71       199      199      199      71       199
\&    H                            72       200      200      200      72       200
\&    I                            73       201      201      201      73       201
\&    J                            74       209      209      209      74       209
\&    K                            75       210      210      210      75       210
\&    L                            76       211      211      211      76       211
\&    M                            77       212      212      212      77       212
\&    N                            78       213      213      213      78       213
\&    O                            79       214      214      214      79       214
\&    P                            80       215      215      215      80       215
\&    Q                            81       216      216      216      81       216
\&    R                            82       217      217      217      82       217
\&    S                            83       226      226      226      83       226
\&    T                            84       227      227      227      84       227
\&    U                            85       228      228      228      85       228
\&    V                            86       229      229      229      86       229
\&    W                            87       230      230      230      87       230
\&    X                            88       231      231      231      88       231
\&    Y                            89       232      232      232      89       232
\&    Z                            90       233      233      233      90       233
\&    [                            91       186      173      187      91       173      *** ###
\&    \e                            92       224      224      188      92       224      ### 
\&    ]                            93       187      189      189      93       189      ***
\&    ^                            94       176      95       106      94       95       *** ###
\&    _                            95       109      109      109      95       109
\&    `                            96       121      121      74       96       121      ###
\&    a                            97       129      129      129      97       129
\&    b                            98       130      130      130      98       130
\&    c                            99       131      131      131      99       131
\&    d                            100      132      132      132      100      132
\&    e                            101      133      133      133      101      133
\&    f                            102      134      134      134      102      134
\&    g                            103      135      135      135      103      135
\&    h                            104      136      136      136      104      136
\&    i                            105      137      137      137      105      137
\&    j                            106      145      145      145      106      145
\&    k                            107      146      146      146      107      146
\&    l                            108      147      147      147      108      147
\&    m                            109      148      148      148      109      148
\&    n                            110      149      149      149      110      149
\&    o                            111      150      150      150      111      150
\&    p                            112      151      151      151      112      151
\&    q                            113      152      152      152      113      152
\&    r                            114      153      153      153      114      153
\&    s                            115      162      162      162      115      162
\&    t                            116      163      163      163      116      163
\&    u                            117      164      164      164      117      164
\&    v                            118      165      165      165      118      165
\&    w                            119      166      166      166      119      166
\&    x                            120      167      167      167      120      167
\&    y                            121      168      168      168      121      168
\&    z                            122      169      169      169      122      169
\&    {                            123      192      192      251      123      192      ###
\&    |                            124      79       79       79       124      79
\&    }                            125      208      208      253      125      208      ###
\&    ~                            126      161      161      255      126      161      ###
\&    <DELETE>                     127      7        7        7        127      7
\&    <C1 0>                       128      32       32       32       194.128  32
\&    <C1 1>                       129      33       33       33       194.129  33
\&    <C1 2>                       130      34       34       34       194.130  34
\&    <C1 3>                       131      35       35       35       194.131  35
\&    <C1 4>                       132      36       36       36       194.132  36
\&    <C1 5>                       133      21       37       37       194.133  37       ***
\&    <C1 6>                       134      6        6        6        194.134  6
\&    <C1 7>                       135      23       23       23       194.135  23
\&    <C1 8>                       136      40       40       40       194.136  40
\&    <C1 9>                       137      41       41       41       194.137  41
\&    <C1 10>                      138      42       42       42       194.138  42
\&    <C1 11>                      139      43       43       43       194.139  43
\&    <C1 12>                      140      44       44       44       194.140  44
\&    <C1 13>                      141      9        9        9        194.141  9
\&    <C1 14>                      142      10       10       10       194.142  10
\&    <C1 15>                      143      27       27       27       194.143  27
\&    <C1 16>                      144      48       48       48       194.144  48
\&    <C1 17>                      145      49       49       49       194.145  49
\&    <C1 18>                      146      26       26       26       194.146  26
\&    <C1 19>                      147      51       51       51       194.147  51
\&    <C1 20>                      148      52       52       52       194.148  52
\&    <C1 21>                      149      53       53       53       194.149  53
\&    <C1 22>                      150      54       54       54       194.150  54
\&    <C1 23>                      151      8        8        8        194.151  8
\&    <C1 24>                      152      56       56       56       194.152  56
\&    <C1 25>                      153      57       57       57       194.153  57
\&    <C1 26>                      154      58       58       58       194.154  58
\&    <C1 27>                      155      59       59       59       194.155  59
\&    <C1 28>                      156      4        4        4        194.156  4
\&    <C1 29>                      157      20       20       20       194.157  20
\&    <C1 30>                      158      62       62       62       194.158  62
\&    <C1 31>                      159      255      255      95       194.159  255      ###
\&    <NON-BREAKING SPACE>         160      65       65       65       194.160  128.65
\&    <INVERTED EXCLAMATION MARK>  161      170      170      170      194.161  128.66
\&    <CENT SIGN>                  162      74       74       176      194.162  128.67   ###
\&    <POUND SIGN>                 163      177      177      177      194.163  128.68
\&    <CURRENCY SIGN>              164      159      159      159      194.164  128.69
\&    <YEN SIGN>                   165      178      178      178      194.165  128.70
\&    <BROKEN BAR>                 166      106      106      208      194.166  128.71   ###
\&    <SECTION SIGN>               167      181      181      181      194.167  128.72
\&    <DIAERESIS>                  168      189      187      121      194.168  128.73   *** ###
\&    <COPYRIGHT SIGN>             169      180      180      180      194.169  128.74
\&    <FEMININE ORDINAL INDICATOR> 170      154      154      154      194.170  128.81
\&    <LEFT POINTING GUILLEMET>    171      138      138      138      194.171  128.82
\&    <NOT SIGN>                   172      95       176      186      194.172  128.83   *** ###
\&    <SOFT HYPHEN>                173      202      202      202      194.173  128.84
\&    <REGISTERED TRADE MARK SIGN> 174      175      175      175      194.174  128.85
\&    <MACRON>                     175      188      188      161      194.175  128.86   ###
\&    <DEGREE SIGN>                176      144      144      144      194.176  128.87
\&    <PLUS-OR-MINUS SIGN>         177      143      143      143      194.177  128.88
\&    <SUPERSCRIPT TWO>            178      234      234      234      194.178  128.89
\&    <SUPERSCRIPT THREE>          179      250      250      250      194.179  128.98
\&    <ACUTE ACCENT>               180      190      190      190      194.180  128.99
\&    <MICRO SIGN>                 181      160      160      160      194.181  128.100
\&    <PARAGRAPH SIGN>             182      182      182      182      194.182  128.101
\&    <MIDDLE DOT>                 183      179      179      179      194.183  128.102
\&    <CEDILLA>                    184      157      157      157      194.184  128.103
\&    <SUPERSCRIPT ONE>            185      218      218      218      194.185  128.104
\&    <MASC. ORDINAL INDICATOR>    186      155      155      155      194.186  128.105
\&    <RIGHT POINTING GUILLEMET>   187      139      139      139      194.187  128.106
\&    <FRACTION ONE QUARTER>       188      183      183      183      194.188  128.112
\&    <FRACTION ONE HALF>          189      184      184      184      194.189  128.113
\&    <FRACTION THREE QUARTERS>    190      185      185      185      194.190  128.114
\&    <INVERTED QUESTION MARK>     191      171      171      171      194.191  128.115
\&    <A WITH GRAVE>               192      100      100      100      195.128  138.65
\&    <A WITH ACUTE>               193      101      101      101      195.129  138.66
\&    <A WITH CIRCUMFLEX>          194      98       98       98       195.130  138.67
\&    <A WITH TILDE>               195      102      102      102      195.131  138.68
\&    <A WITH DIAERESIS>           196      99       99       99       195.132  138.69
\&    <A WITH RING ABOVE>          197      103      103      103      195.133  138.70
\&    <CAPITAL LIGATURE AE>        198      158      158      158      195.134  138.71
\&    <C WITH CEDILLA>             199      104      104      104      195.135  138.72
\&    <E WITH GRAVE>               200      116      116      116      195.136  138.73
\&    <E WITH ACUTE>               201      113      113      113      195.137  138.74
\&    <E WITH CIRCUMFLEX>          202      114      114      114      195.138  138.81
\&    <E WITH DIAERESIS>           203      115      115      115      195.139  138.82
\&    <I WITH GRAVE>               204      120      120      120      195.140  138.83
\&    <I WITH ACUTE>               205      117      117      117      195.141  138.84
\&    <I WITH CIRCUMFLEX>          206      118      118      118      195.142  138.85
\&    <I WITH DIAERESIS>           207      119      119      119      195.143  138.86
\&    <CAPITAL LETTER ETH>         208      172      172      172      195.144  138.87
\&    <N WITH TILDE>               209      105      105      105      195.145  138.88
\&    <O WITH GRAVE>               210      237      237      237      195.146  138.89
\&    <O WITH ACUTE>               211      238      238      238      195.147  138.98
\&    <O WITH CIRCUMFLEX>          212      235      235      235      195.148  138.99
\&    <O WITH TILDE>               213      239      239      239      195.149  138.100
\&    <O WITH DIAERESIS>           214      236      236      236      195.150  138.101
\&    <MULTIPLICATION SIGN>        215      191      191      191      195.151  138.102
\&    <O WITH STROKE>              216      128      128      128      195.152  138.103
\&    <U WITH GRAVE>               217      253      253      224      195.153  138.104  ###
\&    <U WITH ACUTE>               218      254      254      254      195.154  138.105
\&    <U WITH CIRCUMFLEX>          219      251      251      221      195.155  138.106  ###
\&    <U WITH DIAERESIS>           220      252      252      252      195.156  138.112
\&    <Y WITH ACUTE>               221      173      186      173      195.157  138.113  *** ###
\&    <CAPITAL LETTER THORN>       222      174      174      174      195.158  138.114
\&    <SMALL LETTER SHARP S>       223      89       89       89       195.159  138.115
\&    <a WITH GRAVE>               224      68       68       68       195.160  139.65
\&    <a WITH ACUTE>               225      69       69       69       195.161  139.66
\&    <a WITH CIRCUMFLEX>          226      66       66       66       195.162  139.67
\&    <a WITH TILDE>               227      70       70       70       195.163  139.68
\&    <a WITH DIAERESIS>           228      67       67       67       195.164  139.69
\&    <a WITH RING ABOVE>          229      71       71       71       195.165  139.70
\&    <SMALL LIGATURE ae>          230      156      156      156      195.166  139.71
\&    <c WITH CEDILLA>             231      72       72       72       195.167  139.72
\&    <e WITH GRAVE>               232      84       84       84       195.168  139.73
\&    <e WITH ACUTE>               233      81       81       81       195.169  139.74
\&    <e WITH CIRCUMFLEX>          234      82       82       82       195.170  139.81
\&    <e WITH DIAERESIS>           235      83       83       83       195.171  139.82
\&    <i WITH GRAVE>               236      88       88       88       195.172  139.83
\&    <i WITH ACUTE>               237      85       85       85       195.173  139.84
\&    <i WITH CIRCUMFLEX>          238      86       86       86       195.174  139.85
\&    <i WITH DIAERESIS>           239      87       87       87       195.175  139.86
\&    <SMALL LETTER eth>           240      140      140      140      195.176  139.87
\&    <n WITH TILDE>               241      73       73       73       195.177  139.88
\&    <o WITH GRAVE>               242      205      205      205      195.178  139.89
\&    <o WITH ACUTE>               243      206      206      206      195.179  139.98
\&    <o WITH CIRCUMFLEX>          244      203      203      203      195.180  139.99
\&    <o WITH TILDE>               245      207      207      207      195.181  139.100
\&    <o WITH DIAERESIS>           246      204      204      204      195.182  139.101
\&    <DIVISION SIGN>              247      225      225      225      195.183  139.102
\&    <o WITH STROKE>              248      112      112      112      195.184  139.103
\&    <u WITH GRAVE>               249      221      221      192      195.185  139.104  ###
\&    <u WITH ACUTE>               250      222      222      222      195.186  139.105
\&    <u WITH CIRCUMFLEX>          251      219      219      219      195.187  139.106
\&    <u WITH DIAERESIS>           252      220      220      220      195.188  139.112
\&    <y WITH ACUTE>               253      141      141      141      195.189  139.113
\&    <SMALL LETTER thorn>         254      142      142      142      195.190  139.114
\&    <y WITH DIAERESIS>           255      223      223      223      195.191  139.115
.Ve
.PP
If you would rather see the above table in \s-1CCSID\s0 0037 order rather than
\&\s-1ASCII\s0 + Latin\-1 order then run the table through:
.IP "recipe 4" 4
.IX Item "recipe 4"
.PP
.Vb 5
\&    perl -ne 'if(/.{33}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}/)'\e
\&     -e '{push(@l,$_)}' \e
\&     -e 'END{print map{$_->[0]}' \e
\&     -e '          sort{$a->[1] <=> $b->[1]}' \e
\&     -e '          map{[$_,substr($_,42,3)]}@l;}' perlebcdic.pod
.Ve
.PP
If you would rather see it in \s-1CCSID\s0 1047 order then change the digit
42 in the last line to 51, like this:
.IP "recipe 5" 4
.IX Item "recipe 5"
.PP
.Vb 5
\&    perl -ne 'if(/.{33}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}/)'\e
\&     -e '{push(@l,$_)}' \e
\&     -e 'END{print map{$_->[0]}' \e
\&     -e '          sort{$a->[1] <=> $b->[1]}' \e
\&     -e '          map{[$_,substr($_,51,3)]}@l;}' perlebcdic.pod
.Ve
.PP
If you would rather see it in POSIX-BC order then change the digit
51 in the last line to 60, like this:
.IP "recipe 6" 4
.IX Item "recipe 6"
.PP
.Vb 5
\&    perl -ne 'if(/.{33}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}/)'\e
\&     -e '{push(@l,$_)}' \e
\&     -e 'END{print map{$_->[0]}' \e
\&     -e '          sort{$a->[1] <=> $b->[1]}' \e
\&     -e '          map{[$_,substr($_,60,3)]}@l;}' perlebcdic.pod
.Ve
.SH "IDENTIFYING CHARACTER CODE SETS"
.IX Header "IDENTIFYING CHARACTER CODE SETS"
To determine the character set you are running under from perl one 
could use the return value of \fIord()\fR or \fIchr()\fR to test one or more 
character values.  For example:
.PP
.Vb 2
\&    $is_ascii  = "A" eq chr(65);
\&    $is_ebcdic = "A" eq chr(193);
.Ve
.PP
Also, \*(L"\et\*(R" is a \f(CW\*(C`HORIZONTAL TABULATION\*(C'\fR character so that:
.PP
.Vb 2
\&    $is_ascii  = ord("\et") == 9;
\&    $is_ebcdic = ord("\et") == 5;
.Ve
.PP
To distinguish \s-1EBCDIC\s0 code pages try looking at one or more of
the characters that differ between them.  For example:
.PP
.Vb 2
\&    $is_ebcdic_37   = "\en" eq chr(37);
\&    $is_ebcdic_1047 = "\en" eq chr(21);
.Ve
.PP
Or better still choose a character that is uniquely encoded in any
of the code sets, e.g.:
.PP
.Vb 4
\&    $is_ascii           = ord('[') == 91;
\&    $is_ebcdic_37       = ord('[') == 186;
\&    $is_ebcdic_1047     = ord('[') == 173;
\&    $is_ebcdic_POSIX_BC = ord('[') == 187;
.Ve
.PP
However, it would be unwise to write tests such as:
.PP
.Vb 2
\&    $is_ascii = "\er" ne chr(13);  #  WRONG
\&    $is_ascii = "\en" ne chr(10);  #  ILL ADVISED
.Ve
.PP
Obviously the first of these will fail to distinguish most \s-1ASCII\s0 machines
from either a \s-1CCSID\s0 0037, a 1047, or a POSIX-BC \s-1EBCDIC\s0 machine since \*(L"\er\*(R" eq 
chr(13) under all of those coded character sets.  But note too that 
because \*(L"\en\*(R" is chr(13) and \*(L"\er\*(R" is chr(10) on the MacIntosh (which is an 
\&\s-1ASCII\s0 machine) the second \f(CW$is_ascii\fR test will lead to trouble there.
.PP
To determine whether or not perl was built under an \s-1EBCDIC\s0 
code page you can use the Config module like so:
.PP
.Vb 2
\&    use Config;
\&    $is_ebcdic = $Config{'ebcdic'} eq 'define';
.Ve
.SH "CONVERSIONS"
.IX Header "CONVERSIONS"
.Sh "tr///"
.IX Subsection "tr///"
In order to convert a string of characters from one character set to 
another a simple list of numbers, such as in the right columns in the
above table, along with perl's tr/// operator is all that is needed.  
The data in the table are in \s-1ASCII\s0 order hence the \s-1EBCDIC\s0 columns 
provide easy to use \s-1ASCII\s0 to \s-1EBCDIC\s0 operations that are also easily 
reversed.
.PP
For example, to convert \s-1ASCII\s0 to code page 037 take the output of the second 
column from the output of recipe 0 (modified to add \e\e characters) and use 
it in tr/// like so:
.PP
.Vb 17
\&    $cp_037 = 
\&    '\e000\e001\e002\e003\e234\e011\e206\e177\e227\e215\e216\e013\e014\e015\e016\e017' .
\&    '\e020\e021\e022\e023\e235\e205\e010\e207\e030\e031\e222\e217\e034\e035\e036\e037' .
\&    '\e200\e201\e202\e203\e204\e012\e027\e033\e210\e211\e212\e213\e214\e005\e006\e007' .
\&    '\e220\e221\e026\e223\e224\e225\e226\e004\e230\e231\e232\e233\e024\e025\e236\e032' .
\&    '\e040\e240\e342\e344\e340\e341\e343\e345\e347\e361\e242\e056\e074\e050\e053\e174' .
\&    '\e046\e351\e352\e353\e350\e355\e356\e357\e354\e337\e041\e044\e052\e051\e073\e254' .
\&    '\e055\e057\e302\e304\e300\e301\e303\e305\e307\e321\e246\e054\e045\e137\e076\e077' .
\&    '\e370\e311\e312\e313\e310\e315\e316\e317\e314\e140\e072\e043\e100\e047\e075\e042' .
\&    '\e330\e141\e142\e143\e144\e145\e146\e147\e150\e151\e253\e273\e360\e375\e376\e261' .
\&    '\e260\e152\e153\e154\e155\e156\e157\e160\e161\e162\e252\e272\e346\e270\e306\e244' .
\&    '\e265\e176\e163\e164\e165\e166\e167\e170\e171\e172\e241\e277\e320\e335\e336\e256' .
\&    '\e136\e243\e245\e267\e251\e247\e266\e274\e275\e276\e133\e135\e257\e250\e264\e327' .
\&    '\e173\e101\e102\e103\e104\e105\e106\e107\e110\e111\e255\e364\e366\e362\e363\e365' .
\&    '\e175\e112\e113\e114\e115\e116\e117\e120\e121\e122\e271\e373\e374\e371\e372\e377' .
\&    '\e134\e367\e123\e124\e125\e126\e127\e130\e131\e132\e262\e324\e326\e322\e323\e325' .
\&    '\e060\e061\e062\e063\e064\e065\e066\e067\e070\e071\e263\e333\e334\e331\e332\e237' ;
.Ve
.PP
.Vb 2
\&    my $ebcdic_string = $ascii_string;
\&    eval '$ebcdic_string =~ tr/\e000-\e377/' . $cp_037 . '/';
.Ve
.PP
To convert from \s-1EBCDIC\s0 037 to \s-1ASCII\s0 just reverse the order of the tr/// 
arguments like so:
.PP
.Vb 2
\&    my $ascii_string = $ebcdic_string;
\&    eval '$ascii_string = tr/' . $cp_037 . '/\e000-\e377/';
.Ve
.PP
Similarly one could take the output of the third column from recipe 0 to
obtain a \f(CW$cp_1047\fR table.  The fourth column of the output from recipe
0 could provide a \f(CW$cp_posix_bc\fR table suitable for transcoding as well.
.Sh "iconv"
.IX Subsection "iconv"
\&\s-1XPG\s0 operability often implies the presence of an \fIiconv\fR utility
available from the shell or from the C library.  Consult your system's
documentation for information on iconv.
.PP
On \s-1OS/390\s0 or z/OS see the \fIiconv\fR\|(1) manpage.  One way to invoke the iconv 
shell utility from within perl would be to:
.PP
.Vb 2
\&    # OS/390 or z/OS example
\&    $ascii_data = `echo '$ebcdic_data'| iconv -f IBM-1047 -t ISO8859-1`
.Ve
.PP
or the inverse map:
.PP
.Vb 2
\&    # OS/390 or z/OS example
\&    $ebcdic_data = `echo '$ascii_data'| iconv -f ISO8859-1 -t IBM-1047`
.Ve
.PP
For other perl based conversion options see the Convert::* modules on \s-1CPAN\s0.
.Sh "C \s-1RTL\s0"
.IX Subsection "C RTL"
The \s-1OS/390\s0 and z/OS C run time libraries provide \fI_atoe()\fR and \fI_etoa()\fR functions.
.SH "OPERATOR DIFFERENCES"
.IX Header "OPERATOR DIFFERENCES"
The \f(CW\*(C`..\*(C'\fR range operator treats certain character ranges with 
care on \s-1EBCDIC\s0 machines.  For example the following array
will have twenty six elements on either an \s-1EBCDIC\s0 machine
or an \s-1ASCII\s0 machine:
.PP
.Vb 1
\&    @alphabet = ('A'..'Z');   #  $#alphabet == 25
.Ve
.PP
The bitwise operators such as & ^ | may return different results
when operating on string or character data in a perl program running 
on an \s-1EBCDIC\s0 machine than when run on an \s-1ASCII\s0 machine.  Here is
an example adapted from the one in perlop:
.PP
.Vb 5
\&    # EBCDIC-based examples
\&    print "j p \en" ^ " a h";                      # prints "JAPH\en"
\&    print "JA" | "  ph\en";                        # prints "japh\en" 
\&    print "JAPH\enJunk" & "\e277\e277\e277\e277\e277";  # prints "japh\en";
\&    print 'p N$' ^ " E<H\en";                      # prints "Perl\en";
.Ve
.PP
An interesting property of the 32 C0 control characters
in the \s-1ASCII\s0 table is that they can \*(L"literally\*(R" be constructed
as control characters in perl, e.g. \f(CW\*(C`(chr(0) eq "\ec@")\*(C'\fR 
\&\f(CW\*(C`(chr(1) eq "\ecA")\*(C'\fR, and so on.  Perl on \s-1EBCDIC\s0 machines has been 
ported to take \*(L"\ec@\*(R" to \fIchr\fR\|(0) and \*(L"\ecA\*(R" to \fIchr\fR\|(1) as well, but the
thirty three characters that result depend on which code page you are
using.  The table below uses the character names from the previous table 
but with substitutions such as s/START \s-1OF/S\s0.O./; s/END \s-1OF\s0 /E.O./; 
s/TRANSMISSION/TRANS./; s/TABULATION/TAB./; s/VERTICAL/VERT./; 
s/HORIZONTAL/HORIZ./; s/DEVICE \s-1CONTROL/D\s0.C./; s/SEPARATOR/SEP./; 
s/NEGATIVE \s-1ACKNOWLEDGE/NEG\s0. \s-1ACK\s0./;.  The POSIX-BC and 1047 sets are
identical throughout this range and differ from the 0037 set at only 
one spot (21 decimal).  Note that the \f(CW\*(C`LINE FEED\*(C'\fR character
may be generated by \*(L"\ecJ\*(R" on \s-1ASCII\s0 machines but by \*(L"\ecU\*(R" on 1047 or POSIX-BC 
machines and cannot be generated as a \f(CW"\ec.letter."\fR control character on 
0037 machines.  Note also that \*(L"\ec\e\e\*(R" maps to two characters
not one.
.PP
.Vb 35
\&    chr   ord  8859-1               0037                1047 && POSIX-BC     
\&    ------------------------------------------------------------------------
\&    "\ec?" 127  <DELETE>             "                   "              ***><
\&    "\ec@"   0  <NULL>               <NULL>              <NULL>         ***><
\&    "\ecA"   1  <S.O. HEADING>       <S.O. HEADING>      <S.O. HEADING> 
\&    "\ecB"   2  <S.O. TEXT>          <S.O. TEXT>         <S.O. TEXT>
\&    "\ecC"   3  <E.O. TEXT>          <E.O. TEXT>         <E.O. TEXT>
\&    "\ecD"   4  <E.O. TRANS.>        <C1 28>             <C1 28> 
\&    "\ecE"   5  <ENQUIRY>            <HORIZ. TAB.>       <HORIZ. TAB.>    
\&    "\ecF"   6  <ACKNOWLEDGE>        <C1 6>              <C1 6>   
\&    "\ecG"   7  <BELL>               <DELETE>            <DELETE>   
\&    "\ecH"   8  <BACKSPACE>          <C1 23>             <C1 23>
\&    "\ecI"   9  <HORIZ. TAB.>        <C1 13>             <C1 13>
\&    "\ecJ"  10  <LINE FEED>          <C1 14>             <C1 14>
\&    "\ecK"  11  <VERT. TAB.>         <VERT. TAB.>        <VERT. TAB.>
\&    "\ecL"  12  <FORM FEED>          <FORM FEED>         <FORM FEED>    
\&    "\ecM"  13  <CARRIAGE RETURN>    <CARRIAGE RETURN>   <CARRIAGE RETURN> 
\&    "\ecN"  14  <SHIFT OUT>          <SHIFT OUT>         <SHIFT OUT>
\&    "\ecO"  15  <SHIFT IN>           <SHIFT IN>          <SHIFT IN>
\&    "\ecP"  16  <DATA LINK ESCAPE>   <DATA LINK ESCAPE>  <DATA LINK ESCAPE> 
\&    "\ecQ"  17  <D.C. ONE>           <D.C. ONE>          <D.C. ONE>
\&    "\ecR"  18  <D.C. TWO>           <D.C. TWO>          <D.C. TWO>
\&    "\ecS"  19  <D.C. THREE>         <D.C. THREE>        <D.C. THREE> 
\&    "\ecT"  20  <D.C. FOUR>          <C1 29>             <C1 29> 
\&    "\ecU"  21  <NEG. ACK.>          <C1 5>              <LINE FEED>    ***
\&    "\ecV"  22  <SYNCHRONOUS IDLE>   <BACKSPACE>         <BACKSPACE>
\&    "\ecW"  23  <E.O. TRANS. BLOCK>  <C1 7>              <C1 7>
\&    "\ecX"  24  <CANCEL>             <CANCEL>            <CANCEL>
\&    "\ecY"  25  <E.O. MEDIUM>        <E.O. MEDIUM>       <E.O. MEDIUM>
\&    "\ecZ"  26  <SUBSTITUTE>         <C1 18>             <C1 18>
\&    "\ec["  27  <ESCAPE>             <C1 15>             <C1 15>
\&    "\ec\e\e" 28  <FILE SEP.>\e         <FILE SEP.>\e        <FILE SEP.>\e
\&    "\ec]"  29  <GROUP SEP.>         <GROUP SEP.>        <GROUP SEP.>
\&    "\ec^"  30  <RECORD SEP.>        <RECORD SEP.>       <RECORD SEP.>  ***><
\&    "\ec_"  31  <UNIT SEP.>          <UNIT SEP.>         <UNIT SEP.>    ***><
.Ve
.SH "FUNCTION DIFFERENCES"
.IX Header "FUNCTION DIFFERENCES"
.IP "\fIchr()\fR" 8
.IX Item "chr()"
\&\fIchr()\fR must be given an \s-1EBCDIC\s0 code number argument to yield a desired 
character return value on an \s-1EBCDIC\s0 machine.  For example:
.Sp
.Vb 1
\&    $CAPITAL_LETTER_A = chr(193);
.Ve
.IP "\fIord()\fR" 8
.IX Item "ord()"
\&\fIord()\fR will return \s-1EBCDIC\s0 code number values on an \s-1EBCDIC\s0 machine.
For example:
.Sp
.Vb 1
\&    $the_number_193 = ord("A");
.Ve
.IP "\fIpack()\fR" 8
.IX Item "pack()"
The c and C templates for \fIpack()\fR are dependent upon character set 
encoding.  Examples of usage on \s-1EBCDIC\s0 include:
.Sp
.Vb 4
\&    $foo = pack("CCCC",193,194,195,196);
\&    # $foo eq "ABCD"
\&    $foo = pack("C4",193,194,195,196);
\&    # same thing
.Ve
.Sp
.Vb 2
\&    $foo = pack("ccxxcc",193,194,195,196);
\&    # $foo eq "AB\e0\e0CD"
.Ve
.IP "\fIprint()\fR" 8
.IX Item "print()"
One must be careful with scalars and strings that are passed to
print that contain \s-1ASCII\s0 encodings.  One common place
for this to occur is in the output of the \s-1MIME\s0 type header for
\&\s-1CGI\s0 script writing.  For example, many perl programming guides 
recommend something similar to:
.Sp
.Vb 2
\&    print "Content-type:\ettext/html\e015\e012\e015\e012"; 
\&    # this may be wrong on EBCDIC
.Ve
.Sp
Under the \s-1IBM\s0 \s-1OS/390\s0 \s-1USS\s0 Web Server or WebSphere on z/OS for example 
you should instead write that as:
.Sp
.Vb 1
\&    print "Content-type:\ettext/html\er\en\er\en"; # OK for DGW et alia
.Ve
.Sp
That is because the translation from \s-1EBCDIC\s0 to \s-1ASCII\s0 is done
by the web server in this case (such code will not be appropriate for
the Macintosh however).  Consult your web server's documentation for 
further details.
.IP "\fIprintf()\fR" 8
.IX Item "printf()"
The formats that can convert characters to numbers and vice versa
will be different from their \s-1ASCII\s0 counterparts when executed
on an \s-1EBCDIC\s0 machine.  Examples include:
.Sp
.Vb 1
\&    printf("%c%c%c",193,194,195);  # prints ABC
.Ve
.IP "\fIsort()\fR" 8
.IX Item "sort()"
\&\s-1EBCDIC\s0 sort results may differ from \s-1ASCII\s0 sort results especially for 
mixed case strings.  This is discussed in more detail below.
.IP "\fIsprintf()\fR" 8
.IX Item "sprintf()"
See the discussion of \fIprintf()\fR above.  An example of the use
of sprintf would be:
.Sp
.Vb 1
\&    $CAPITAL_LETTER_A = sprintf("%c",193);
.Ve
.IP "\fIunpack()\fR" 8
.IX Item "unpack()"
See the discussion of \fIpack()\fR above.
.SH "REGULAR EXPRESSION DIFFERENCES"
.IX Header "REGULAR EXPRESSION DIFFERENCES"
As of perl 5.005_03 the letter range regular expression such as 
[A\-Z] and [a\-z] have been especially coded to not pick up gap 
characters.  For example, characters such as o\*^ \f(CW\*(C`o WITH CIRCUMFLEX\*(C'\fR 
that lie between I and J would not be matched by the 
regular expression range \f(CW\*(C`/[H\-K]/\*(C'\fR.  This works in
the other direction, too, if either of the range end points is
explicitly numeric: \f(CW\*(C`[\ex89\-\ex91]\*(C'\fR will match \f(CW\*(C`\ex8e\*(C'\fR, even
though \f(CW\*(C`\ex89\*(C'\fR is \f(CW\*(C`i\*(C'\fR and \f(CW\*(C`\ex91 \*(C'\fR is \f(CW\*(C`j\*(C'\fR, and \f(CW\*(C`\ex8e\*(C'\fR
is a gap character from the alphabetic viewpoint.
.PP
If you do want to match the alphabet gap characters in a single octet 
regular expression try matching the hex or octal code such 
as \f(CW\*(C`/\e313/\*(C'\fR on \s-1EBCDIC\s0 or \f(CW\*(C`/\e364/\*(C'\fR on \s-1ASCII\s0 machines to 
have your regular expression match \f(CW\*(C`o WITH CIRCUMFLEX\*(C'\fR.
.PP
Another construct to be wary of is the inappropriate use of hex or
octal constants in regular expressions.  Consider the following
set of subs:
.PP
.Vb 4
\&    sub is_c0 {
\&        my $char = substr(shift,0,1);
\&        $char =~ /[\e000-\e037]/;
\&    }
.Ve
.PP
.Vb 4
\&    sub is_print_ascii {
\&        my $char = substr(shift,0,1);
\&        $char =~ /[\e040-\e176]/;
\&    }
.Ve
.PP
.Vb 4
\&    sub is_delete {
\&        my $char = substr(shift,0,1);
\&        $char eq "\e177";
\&    }
.Ve
.PP
.Vb 4
\&    sub is_c1 {
\&        my $char = substr(shift,0,1);
\&        $char =~ /[\e200-\e237]/;
\&    }
.Ve
.PP
.Vb 4
\&    sub is_latin_1 {
\&        my $char = substr(shift,0,1);
\&        $char =~ /[\e240-\e377]/;
\&    }
.Ve
.PP
The above would be adequate if the concern was only with numeric code points.
However, the concern may be with characters rather than code points 
and on an \s-1EBCDIC\s0 machine it may be desirable for constructs such as 
\&\f(CW\*(C`if (is_print_ascii("A")) {print "A is a printable character\en";}\*(C'\fR to print
out the expected message.  One way to represent the above collection
of character classification subs that is capable of working across the
four coded character sets discussed in this document is as follows:
.PP
.Vb 12
\&    sub Is_c0 {
\&        my $char = substr(shift,0,1);
\&        if (ord('^')==94)  { # ascii
\&            return $char =~ /[\e000-\e037]/;
\&        } 
\&        if (ord('^')==176) { # 37
\&            return $char =~ /[\e000-\e003\e067\e055-\e057\e026\e005\e045\e013-\e023\e074\e075\e062\e046\e030\e031\e077\e047\e034-\e037]/;
\&        }
\&        if (ord('^')==95 || ord('^')==106) { # 1047 || posix-bc
\&            return $char =~ /[\e000-\e003\e067\e055-\e057\e026\e005\e025\e013-\e023\e074\e075\e062\e046\e030\e031\e077\e047\e034-\e037]/;
\&        }
\&    }
.Ve
.PP
.Vb 4
\&    sub Is_print_ascii {
\&        my $char = substr(shift,0,1);
\&        $char =~ /[ !"\e#\e$%&'()*+,\e-.\e/0-9:;<=>?\e@A-Z[\e\e\e]^_`a-z{|}~]/;
\&    }
.Ve
.PP
.Vb 9
\&    sub Is_delete {
\&        my $char = substr(shift,0,1);
\&        if (ord('^')==94)  { # ascii
\&            return $char eq "\e177";
\&        }
\&        else  {              # ebcdic
\&            return $char eq "\e007";
\&        }
\&    }
.Ve
.PP
.Vb 16
\&    sub Is_c1 {
\&        my $char = substr(shift,0,1);
\&        if (ord('^')==94)  { # ascii
\&            return $char =~ /[\e200-\e237]/;
\&        }
\&        if (ord('^')==176) { # 37
\&            return $char =~ /[\e040-\e044\e025\e006\e027\e050-\e054\e011\e012\e033\e060\e061\e032\e063-\e066\e010\e070-\e073\e040\e024\e076\e377]/;
\&        }
\&        if (ord('^')==95)  { # 1047
\&            return $char =~ /[\e040-\e045\e006\e027\e050-\e054\e011\e012\e033\e060\e061\e032\e063-\e066\e010\e070-\e073\e040\e024\e076\e377]/;
\&        }
\&        if (ord('^')==106) { # posix-bc
\&            return $char =~ 
\&              /[\e040-\e045\e006\e027\e050-\e054\e011\e012\e033\e060\e061\e032\e063-\e066\e010\e070-\e073\e040\e024\e076\e137]/;
\&        }
\&    }
.Ve
.PP
.Vb 18
\&    sub Is_latin_1 {
\&        my $char = substr(shift,0,1);
\&        if (ord('^')==94)  { # ascii
\&            return $char =~ /[\e240-\e377]/;
\&        }
\&        if (ord('^')==176) { # 37
\&            return $char =~ 
\&              /[\e101\e252\e112\e261\e237\e262\e152\e265\e275\e264\e232\e212\e137\e312\e257\e274\e220\e217\e352\e372\e276\e240\e266\e263\e235\e332\e233\e213\e267\e270\e271\e253\e144\e145\e142\e146\e143\e147\e236\e150\e164\e161-\e163\e170\e165-\e167\e254\e151\e355\e356\e353\e357\e354\e277\e200\e375\e376\e373\e374\e255\e256\e131\e104\e105\e102\e106\e103\e107\e234\e110\e124\e121-\e123\e130\e125-\e127\e214\e111\e315\e316\e313\e317\e314\e341\e160\e335\e336\e333\e334\e215\e216\e337]/;
\&        }
\&        if (ord('^')==95)  { # 1047
\&            return $char =~
\&              /[\e101\e252\e112\e261\e237\e262\e152\e265\e273\e264\e232\e212\e260\e312\e257\e274\e220\e217\e352\e372\e276\e240\e266\e263\e235\e332\e233\e213\e267\e270\e271\e253\e144\e145\e142\e146\e143\e147\e236\e150\e164\e161-\e163\e170\e165-\e167\e254\e151\e355\e356\e353\e357\e354\e277\e200\e375\e376\e373\e374\e272\e256\e131\e104\e105\e102\e106\e103\e107\e234\e110\e124\e121-\e123\e130\e125-\e127\e214\e111\e315\e316\e313\e317\e314\e341\e160\e335\e336\e333\e334\e215\e216\e337]/; 
\&        }
\&        if (ord('^')==106) { # posix-bc
\&            return $char =~ 
\&              /[\e101\e252\e260\e261\e237\e262\e320\e265\e171\e264\e232\e212\e272\e312\e257\e241\e220\e217\e352\e372\e276\e240\e266\e263\e235\e332\e233\e213\e267\e270\e271\e253\e144\e145\e142\e146\e143\e147\e236\e150\e164\e161-\e163\e170\e165-\e167\e254\e151\e355\e356\e353\e357\e354\e277\e200\e340\e376\e335\e374\e255\e256\e131\e104\e105\e102\e106\e103\e107\e234\e110\e124\e121-\e123\e130\e125-\e127\e214\e111\e315\e316\e313\e317\e314\e341\e160\e300\e336\e333\e334\e215\e216\e337]/;
\&        }
\&    }
.Ve
.PP
Note however that only the \f(CW\*(C`Is_ascii_print()\*(C'\fR sub is really independent 
of coded character set.  Another way to write \f(CW\*(C`Is_latin_1()\*(C'\fR would be 
to use the characters in the range explicitly:
.PP
.Vb 4
\&    sub Is_latin_1 {
\&        my $char = substr(shift,0,1);
\&        $char =~ /[������������������������������������������;
\&    }
.Ve
.PP
Although that form may run into trouble in network transit (due to the 
presence of 8 bit characters) or on non ISO-Latin character sets.
.SH "SOCKETS"
.IX Header "SOCKETS"
Most socket programming assumes \s-1ASCII\s0 character encodings in network
byte order.  Exceptions can include \s-1CGI\s0 script writing under a
host web server where the server may take care of translation for you.
Most host web servers convert \s-1EBCDIC\s0 data to \s-1ISO\-8859\-1\s0 or Unicode on
output.
.SH "SORTING"
.IX Header "SORTING"
One big difference between \s-1ASCII\s0 based character sets and \s-1EBCDIC\s0 ones
are the relative positions of upper and lower case letters and the
letters compared to the digits.  If sorted on an \s-1ASCII\s0 based machine the
two letter abbreviation for a physician comes before the two letter
for drive, that is:
.PP
.Vb 2
\&    @sorted = sort(qw(Dr. dr.));  # @sorted holds ('Dr.','dr.') on ASCII,
\&                                  # but ('dr.','Dr.') on EBCDIC
.Ve
.PP
The property of lower case before uppercase letters in \s-1EBCDIC\s0 is
even carried to the Latin 1 \s-1EBCDIC\s0 pages such as 0037 and 1047.
An example would be that E\*: \f(CW\*(C`E WITH DIAERESIS\*(C'\fR (203) comes 
before e\*: \f(CW\*(C`e WITH DIAERESIS\*(C'\fR (235) on an \s-1ASCII\s0 machine, but 
the latter (83) comes before the former (115) on an \s-1EBCDIC\s0 machine.  
(Astute readers will note that the upper case version of \*8 
\&\f(CW\*(C`SMALL LETTER SHARP S\*(C'\fR is simply \*(L"\s-1SS\s0\*(R" and that the upper case version of 
y\*: \f(CW\*(C`y WITH DIAERESIS\*(C'\fR is not in the 0..255 range but it is 
at U+x0178 in Unicode, or \f(CW"\ex{178}"\fR in a Unicode enabled Perl).
.PP
The sort order will cause differences between results obtained on
\&\s-1ASCII\s0 machines versus \s-1EBCDIC\s0 machines.  What follows are some suggestions
on how to deal with these differences.
.Sh "Ignore \s-1ASCII\s0 vs. \s-1EBCDIC\s0 sort differences."
.IX Subsection "Ignore ASCII vs. EBCDIC sort differences."
This is the least computationally expensive strategy.  It may require
some user education.
.Sh "\s-1MONO\s0 \s-1CASE\s0 then sort data."
.IX Subsection "MONO CASE then sort data."
In order to minimize the expense of mono casing mixed test try to
\&\f(CW\*(C`tr///\*(C'\fR towards the character set case most employed within the data.
If the data are primarily \s-1UPPERCASE\s0 non Latin 1 then apply tr/[a\-z]/[A\-Z]/
then \fIsort()\fR.  If the data are primarily lowercase non Latin 1 then
apply tr/[A\-Z]/[a\-z]/ before sorting.  If the data are primarily \s-1UPPERCASE\s0
and include Latin\-1 characters then apply:  
.PP
.Vb 3
\&    tr/[a-z]/[A-Z]/; 
\&    tr/[���������]/[���������������]/;
\&    s/�SS/g;
.Ve
.PP
then \fIsort()\fR.  Do note however that such Latin\-1 manipulation does not 
address the y\*: \f(CW\*(C`y WITH DIAERESIS\*(C'\fR character that will remain at 
code point 255 on \s-1ASCII\s0 machines, but 223 on most \s-1EBCDIC\s0 machines 
where it will sort to a place less than the \s-1EBCDIC\s0 numerals.  With a 
Unicode enabled Perl you might try:
.PP
.Vb 1
\&    tr/^?/\ex{178}/;
.Ve
.PP
The strategy of mono casing data before sorting does not preserve the case 
of the data and may not be acceptable for that reason.
.Sh "Convert, sort data, then re convert."
.IX Subsection "Convert, sort data, then re convert."
This is the most expensive proposition that does not employ a network
connection.
.Sh "Perform sorting on one type of machine only."
.IX Subsection "Perform sorting on one type of machine only."
This strategy can employ a network connection.  As such
it would be computationally expensive.
.SH "TRANSFORMATION FORMATS"
.IX Header "TRANSFORMATION FORMATS"
There are a variety of ways of transforming data with an intra character set 
mapping that serve a variety of purposes.  Sorting was discussed in the 
previous section and a few of the other more popular mapping techniques are 
discussed next.
.Sh "\s-1URL\s0 decoding and encoding"
.IX Subsection "URL decoding and encoding"
Note that some URLs have hexadecimal \s-1ASCII\s0 code points in them in an
attempt to overcome character or protocol limitation issues.  For example 
the tilde character is not on every keyboard hence a \s-1URL\s0 of the form:
.PP
.Vb 1
\&    http://www.pvhp.com/~pvhp/
.Ve
.PP
may also be expressed as either of:
.PP
.Vb 1
\&    http://www.pvhp.com/%7Epvhp/
.Ve
.PP
.Vb 1
\&    http://www.pvhp.com/%7epvhp/
.Ve
.PP
where 7E is the hexadecimal \s-1ASCII\s0 code point for '~'.  Here is an example
of decoding such a \s-1URL\s0 under \s-1CCSID\s0 1047:
.PP
.Vb 21
\&    $url = 'http://www.pvhp.com/%7Epvhp/';
\&    # this array assumes code page 1047
\&    my @a2e_1047 = (
\&          0,  1,  2,  3, 55, 45, 46, 47, 22,  5, 21, 11, 12, 13, 14, 15,
\&         16, 17, 18, 19, 60, 61, 50, 38, 24, 25, 63, 39, 28, 29, 30, 31,
\&         64, 90,127,123, 91,108, 80,125, 77, 93, 92, 78,107, 96, 75, 97,
\&        240,241,242,243,244,245,246,247,248,249,122, 94, 76,126,110,111,
\&        124,193,194,195,196,197,198,199,200,201,209,210,211,212,213,214,
\&        215,216,217,226,227,228,229,230,231,232,233,173,224,189, 95,109,
\&        121,129,130,131,132,133,134,135,136,137,145,146,147,148,149,150,
\&        151,152,153,162,163,164,165,166,167,168,169,192, 79,208,161,  7,
\&         32, 33, 34, 35, 36, 37,  6, 23, 40, 41, 42, 43, 44,  9, 10, 27,
\&         48, 49, 26, 51, 52, 53, 54,  8, 56, 57, 58, 59,  4, 20, 62,255,
\&         65,170, 74,177,159,178,106,181,187,180,154,138,176,202,175,188,
\&        144,143,234,250,190,160,182,179,157,218,155,139,183,184,185,171,
\&        100,101, 98,102, 99,103,158,104,116,113,114,115,120,117,118,119,
\&        172,105,237,238,235,239,236,191,128,253,254,251,252,186,174, 89,
\&         68, 69, 66, 70, 67, 71,156, 72, 84, 81, 82, 83, 88, 85, 86, 87,
\&        140, 73,205,206,203,207,204,225,112,221,222,219,220,141,142,223
\&    );
\&    $url =~ s/%([0-9a-fA-F]{2})/pack("c",$a2e_1047[hex($1)])/ge;
.Ve
.PP
Conversely, here is a partial solution for the task of encoding such 
a \s-1URL\s0 under the 1047 code page:
.PP
.Vb 23
\&    $url = 'http://www.pvhp.com/~pvhp/';
\&    # this array assumes code page 1047
\&    my @e2a_1047 = (
\&          0,  1,  2,  3,156,  9,134,127,151,141,142, 11, 12, 13, 14, 15,
\&         16, 17, 18, 19,157, 10,  8,135, 24, 25,146,143, 28, 29, 30, 31,
\&        128,129,130,131,132,133, 23, 27,136,137,138,139,140,  5,  6,  7,
\&        144,145, 22,147,148,149,150,  4,152,153,154,155, 20, 21,158, 26,
\&         32,160,226,228,224,225,227,229,231,241,162, 46, 60, 40, 43,124,
\&         38,233,234,235,232,237,238,239,236,223, 33, 36, 42, 41, 59, 94,
\&         45, 47,194,196,192,193,195,197,199,209,166, 44, 37, 95, 62, 63,
\&        248,201,202,203,200,205,206,207,204, 96, 58, 35, 64, 39, 61, 34,
\&        216, 97, 98, 99,100,101,102,103,104,105,171,187,240,253,254,177,
\&        176,106,107,108,109,110,111,112,113,114,170,186,230,184,198,164,
\&        181,126,115,116,117,118,119,120,121,122,161,191,208, 91,222,174,
\&        172,163,165,183,169,167,182,188,189,190,221,168,175, 93,180,215,
\&        123, 65, 66, 67, 68, 69, 70, 71, 72, 73,173,244,246,242,243,245,
\&        125, 74, 75, 76, 77, 78, 79, 80, 81, 82,185,251,252,249,250,255,
\&         92,247, 83, 84, 85, 86, 87, 88, 89, 90,178,212,214,210,211,213,
\&         48, 49, 50, 51, 52, 53, 54, 55, 56, 57,179,219,220,217,218,159
\&    );
\&    # The following regular expression does not address the 
\&    # mappings for: ('.' => '%2E', '/' => '%2F', ':' => '%3A') 
\&    $url =~ s/([\et "#%&\e(\e),;<=>\e?\e@\e[\e\e\e]^`{|}~])/sprintf("%%%02X",$e2a_1047[ord($1)])/ge;
.Ve
.PP
where a more complete solution would split the \s-1URL\s0 into components 
and apply a full s/// substitution only to the appropriate parts.
.PP
In the remaining examples a \f(CW@e2a\fR or \f(CW@a2e\fR array may be employed
but the assignment will not be shown explicitly.  For code page 1047
you could use the \f(CW@a2e_1047\fR or \f(CW@e2a_1047\fR arrays just shown.
.Sh "uu encoding and decoding"
.IX Subsection "uu encoding and decoding"
The \f(CW\*(C`u\*(C'\fR template to \fIpack()\fR or \fIunpack()\fR will render \s-1EBCDIC\s0 data in \s-1EBCDIC\s0 
characters equivalent to their \s-1ASCII\s0 counterparts.  For example, the 
following will print \*(L"Yes indeed\en\*(R" on either an \s-1ASCII\s0 or \s-1EBCDIC\s0 computer:
.PP
.Vb 18
\&    $all_byte_chrs = '';
\&    for (0..255) { $all_byte_chrs .= chr($_); }
\&    $uuencode_byte_chrs = pack('u', $all_byte_chrs);
\&    ($uu = <<'ENDOFHEREDOC') =~ s/^\es*//gm;
\&    M``$"`P0%!@<("0H+#`T.#Q`1$A,4%187&!D:&QP='A\e@(2(C)"4F)R@I*BLL
\&    M+2XO,#$R,S0U-C<X.3H[/#T^/T!!0D-$149'2$E*2TQ-3D]045)35%565UA9
\&    M6EM<75Y?8&%B8V1E9F=H:6IK;&UN;W!Q<G-T=79W>'EZ>WQ]?G^`@8*#A(6&
\&    MAXB)BHN,C8Z/D)&2DY25EI>8F9J;G)V>GZ"AHJ.DI::GJ*FJJZRMKJ^PL;*S
\&    MM+6VM[BYNKN\eO;Z_P,'"P\e3%QL?(R<K+S,W.S]#1TM/4U=;7V-G:V]S=WM_@
\&    ?X>+CY.7FY^CIZNOL[>[O\e/'R\e_3U]O?X^?K[_/W^_P``
\&    ENDOFHEREDOC
\&    if ($uuencode_byte_chrs eq $uu) {
\&        print "Yes ";
\&    }
\&    $uudecode_byte_chrs = unpack('u', $uuencode_byte_chrs);
\&    if ($uudecode_byte_chrs eq $all_byte_chrs) {
\&        print "indeed\en";
\&    }
.Ve
.PP
Here is a very spartan uudecoder that will work on \s-1EBCDIC\s0 provided
that the \f(CW@e2a\fR array is filled in appropriately:
.PP
.Vb 14
\&    #!/usr/local/bin/perl
\&    @e2a = ( # this must be filled in
\&           );
\&    $_ = <> until ($mode,$file) = /^begin\es*(\ed*)\es*(\eS*)/;
\&    open(OUT, "> $file") if $file ne "";
\&    while(<>) {
\&        last if /^end/;
\&        next if /[a-z]/;
\&        next unless int(((($e2a[ord()] - 32 ) & 077) + 2) / 3) ==
\&            int(length() / 4);
\&        print OUT unpack("u", $_);
\&    }
\&    close(OUT);
\&    chmod oct($mode), $file;
.Ve
.Sh "Quoted-Printable encoding and decoding"
.IX Subsection "Quoted-Printable encoding and decoding"
On \s-1ASCII\s0 encoded machines it is possible to strip characters outside of
the printable set using:
.PP
.Vb 2
\&    # This QP encoder works on ASCII only
\&    $qp_string =~ s/([=\ex00-\ex1F\ex80-\exFF])/sprintf("=%02X",ord($1))/ge;
.Ve
.PP
Whereas a \s-1QP\s0 encoder that works on both \s-1ASCII\s0 and \s-1EBCDIC\s0 machines 
would look somewhat like the following (where the \s-1EBCDIC\s0 branch \f(CW@e2a\fR 
array is omitted for brevity):
.PP
.Vb 10
\&    if (ord('A') == 65) {    # ASCII
\&        $delete = "\ex7F";    # ASCII
\&        @e2a = (0 .. 255)    # ASCII to ASCII identity map
\&    }
\&    else {                   # EBCDIC
\&        $delete = "\ex07";    # EBCDIC
\&        @e2a =               # EBCDIC to ASCII map (as shown above)
\&    }
\&    $qp_string =~
\&      s/([^ !"\e#\e$%&'()*+,\e-.\e/0-9:;<>?\e@A-Z[\e\e\e]^_`a-z{|}~$delete])/sprintf("=%02X",$e2a[ord($1)])/ge;
.Ve
.PP
(although in production code the substitutions might be done
in the \s-1EBCDIC\s0 branch with the \f(CW@e2a\fR array and separately in the 
\&\s-1ASCII\s0 branch without the expense of the identity map).
.PP
Such \s-1QP\s0 strings can be decoded with:
.PP
.Vb 3
\&    # This QP decoder is limited to ASCII only
\&    $string =~ s/=([0-9A-Fa-f][0-9A-Fa-f])/chr hex $1/ge;
\&    $string =~ s/=[\en\er]+$//;
.Ve
.PP
Whereas a \s-1QP\s0 decoder that works on both \s-1ASCII\s0 and \s-1EBCDIC\s0 machines 
would look somewhat like the following (where the \f(CW@a2e\fR array is
omitted for brevity):
.PP
.Vb 2
\&    $string =~ s/=([0-9A-Fa-f][0-9A-Fa-f])/chr $a2e[hex $1]/ge;
\&    $string =~ s/=[\en\er]+$//;
.Ve
.Sh "Caesarian ciphers"
.IX Subsection "Caesarian ciphers"
The practice of shifting an alphabet one or more characters for encipherment
dates back thousands of years and was explicitly detailed by Gaius Julius
Caesar in his \fBGallic Wars\fR text.  A single alphabet shift is sometimes 
referred to as a rotation and the shift amount is given as a number \f(CW$n\fR after
the string 'rot' or \*(L"rot$n\*(R".  Rot0 and rot26 would designate identity maps 
on the 26 letter English version of the Latin alphabet.  Rot13 has the 
interesting property that alternate subsequent invocations are identity maps 
(thus rot13 is its own non-trivial inverse in the group of 26 alphabet 
rotations).  Hence the following is a rot13 encoder and decoder that will 
work on \s-1ASCII\s0 and \s-1EBCDIC\s0 machines:
.PP
.Vb 1
\&    #!/usr/local/bin/perl
.Ve
.PP
.Vb 4
\&    while(<>){
\&        tr/n-za-mN-ZA-M/a-zA-Z/;
\&        print;
\&    }
.Ve
.PP
In one-liner form:
.PP
.Vb 1
\&    perl -ne 'tr/n-za-mN-ZA-M/a-zA-Z/;print'
.Ve
.SH "Hashing order and checksums"
.IX Header "Hashing order and checksums"
To the extent that it is possible to write code that depends on 
hashing order there may be differences between hashes as stored
on an \s-1ASCII\s0 based machine and hashes stored on an \s-1EBCDIC\s0 based machine.
\&\s-1XXX\s0
.SH "I18N AND L10N"
.IX Header "I18N AND L10N"
Internationalization(I18N) and localization(L10N) are supported at least 
in principle even on \s-1EBCDIC\s0 machines.  The details are system dependent 
and discussed under the \*(L"\s-1OS\s0 \s-1ISSUES\s0\*(R" in perlebcdic section below.
.SH "MULTI OCTET CHARACTER SETS"
.IX Header "MULTI OCTET CHARACTER SETS"
Perl may work with an internal UTF-EBCDIC encoding form for wide characters 
on \s-1EBCDIC\s0 platforms in a manner analogous to the way that it works with 
the \s-1UTF\-8\s0 internal encoding form on \s-1ASCII\s0 based platforms.
.PP
Legacy multi byte \s-1EBCDIC\s0 code pages \s-1XXX\s0.
.SH "OS ISSUES"
.IX Header "OS ISSUES"
There may be a few system dependent issues 
of concern to \s-1EBCDIC\s0 Perl programmers.
.Sh "\s-1OS/400\s0"
.IX Subsection "OS/400"
The \s-1PASE\s0 environment.
.IP "\s-1IFS\s0 access" 8
.IX Item "IFS access"
\&\s-1XXX\s0.
.Sh "\s-1OS/390\s0, z/OS"
.IX Subsection "OS/390, z/OS"
Perl runs under Unix Systems Services or \s-1USS\s0.
.IP "chcp" 8
.IX Item "chcp"
\&\fBchcp\fR is supported as a shell utility for displaying and changing 
one's code page.  See also chcp.
.IP "dataset access" 8
.IX Item "dataset access"
For sequential data set access try:
.Sp
.Vb 1
\&    my @ds_records = `cat //DSNAME`;
.Ve
.Sp
or:
.Sp
.Vb 1
\&    my @ds_records = `cat //'HLQ.DSNAME'`;
.Ve
.Sp
See also the OS390::Stdio module on \s-1CPAN\s0.
.IP "\s-1OS/390\s0, z/OS iconv" 8
.IX Item "OS/390, z/OS iconv"
\&\fBiconv\fR is supported as both a shell utility and a C \s-1RTL\s0 routine.
See also the \fIiconv\fR\|(1) and \fIiconv\fR\|(3) manual pages.
.IP "locales" 8
.IX Item "locales"
On \s-1OS/390\s0 or z/OS see locale for information on locales.  The L10N files
are in \fI/usr/nls/locale\fR.  \f(CW$Config\fR{d_setlocale} is 'define' on \s-1OS/390\s0
or z/OS.
.Sh "\s-1VM/ESA\s0?"
.IX Subsection "VM/ESA?"
\&\s-1XXX\s0.
.Sh "\s-1POSIX\-BC\s0?"
.IX Subsection "POSIX-BC?"
\&\s-1XXX\s0.
.SH "BUGS"
.IX Header "BUGS"
This pod document contains literal Latin 1 characters and may encounter 
translation difficulties.  In particular one popular nroff implementation 
was known to strip accented characters to their unaccented counterparts 
while attempting to view this document through the \fBpod2man\fR program 
(for example, you may see a plain \f(CW\*(C`y\*(C'\fR rather than one with a diaeresis 
as in y\*:).  Another nroff truncated the resultant manpage at
the first occurrence of 8 bit characters.
.PP
Not all shells will allow multiple \f(CW\*(C`\-e\*(C'\fR string arguments to perl to
be concatenated together properly as recipes 0, 2, 4, 5, and 6 might 
seem to imply.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
perllocale, perlfunc, perlunicode, utf8.
.SH "REFERENCES"
.IX Header "REFERENCES"
http://anubis.dkuug.dk/i18n/charmaps
.PP
http://www.unicode.org/
.PP
http://www.unicode.org/unicode/reports/tr16/
.PP
http://www.wps.com/texts/codes/
\&\fB\s-1ASCII:\s0 American Standard Code for Information Infiltration\fR Tom Jennings,
September 1999.
.PP
\&\fBThe Unicode Standard, Version 3.0\fR The Unicode Consortium, Lisa Moore ed., 
\&\s-1ISBN\s0 0\-201\-61633\-5, Addison Wesley Developers Press, February 2000. 
.PP
\&\fB\s-1CDRA:\s0 \s-1IBM\s0 \- Character Data Representation Architecture \- 
Reference and Registry\fR, \s-1IBM\s0 \s-1SC09\-2190\-00\s0, December 1996. 
.PP
\&\*(L"Demystifying Character Sets\*(R", Andrea Vine, Multilingual Computing 
& Technology, \fB#26 Vol. 10 Issue 4\fR, August/September 1999;
\&\s-1ISSN\s0 1523\-0309; Multilingual Computing Inc. Sandpoint \s-1ID\s0, \s-1USA\s0.
.PP
\&\fBCodes, Ciphers, and Other Cryptic and Clandestine Communication\fR
Fred B. Wrixon, \s-1ISBN\s0 1\-57912\-040\-7, Black Dog & Leventhal Publishers,
1998.
.PP
http://www.bobbemer.com/P\-BIT.HTM
\&\fB\s-1IBM\s0 \- \s-1EBCDIC\s0 and the P\-bit; The biggest Computer Goof Ever\fR Robert Bemer.
.SH "HISTORY"
.IX Header "HISTORY"
15 April 2001: added \s-1UTF\-8\s0 and UTF-EBCDIC to main table, pvhp.
.SH "AUTHOR"
.IX Header "AUTHOR"
Peter Prymmer [email protected] wrote this in 1999 and 2000 
with \s-1CCSID\s0 0819 and 0037 help from Chris Leach and 
Andre\*' Pirard [email protected] as well as POSIX-BC 
help from Thomas Dorner [email protected].
Thanks also to Vickie Cooper, Philip Newton, William Raffloer, and 
Joe Smith.  Trademarks, registered trademarks, service marks and 
registered service marks used in this document are the property of 
their respective owners.

Bell Labs OSI certified Powered by Plan 9

(Return to Plan 9 Home Page)

Copyright © 2021 Plan 9 Foundation. All Rights Reserved.
Comments to [email protected].