| 1 | .\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32 |
| 2 | .\" |
| 3 | .\" Standard preamble: |
| 4 | .\" ======================================================================== |
| 5 | .de Sh \" Subsection heading |
| 6 | .br |
| 7 | .if t .Sp |
| 8 | .ne 5 |
| 9 | .PP |
| 10 | \fB\\$1\fR |
| 11 | .PP |
| 12 | .. |
| 13 | .de Sp \" Vertical space (when we can't use .PP) |
| 14 | .if t .sp .5v |
| 15 | .if n .sp |
| 16 | .. |
| 17 | .de Vb \" Begin verbatim text |
| 18 | .ft CW |
| 19 | .nf |
| 20 | .ne \\$1 |
| 21 | .. |
| 22 | .de Ve \" End verbatim text |
| 23 | .ft R |
| 24 | .fi |
| 25 | .. |
| 26 | .\" Set up some character translations and predefined strings. \*(-- will |
| 27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left |
| 28 | .\" double quote, and \*(R" will give a right double quote. | will give a |
| 29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to |
| 30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' |
| 31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. |
| 32 | .tr \(*W-|\(bv\*(Tr |
| 33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' |
| 34 | .ie n \{\ |
| 35 | . ds -- \(*W- |
| 36 | . ds PI pi |
| 37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch |
| 38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch |
| 39 | . ds L" "" |
| 40 | . ds R" "" |
| 41 | . ds C` "" |
| 42 | . ds C' "" |
| 43 | 'br\} |
| 44 | .el\{\ |
| 45 | . ds -- \|\(em\| |
| 46 | . ds PI \(*p |
| 47 | . ds L" `` |
| 48 | . ds R" '' |
| 49 | 'br\} |
| 50 | .\" |
| 51 | .\" If the F register is turned on, we'll generate index entries on stderr for |
| 52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index |
| 53 | .\" entries marked with X<> in POD. Of course, you'll have to process the |
| 54 | .\" output yourself in some meaningful fashion. |
| 55 | .if \nF \{\ |
| 56 | . de IX |
| 57 | . tm Index:\\$1\t\\n%\t"\\$2" |
| 58 | .. |
| 59 | . nr % 0 |
| 60 | . rr F |
| 61 | .\} |
| 62 | .\" |
| 63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 64 | .\" way too many mistakes in technical documents. |
| 65 | .hy 0 |
| 66 | .if n .na |
| 67 | .\" |
| 68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). |
| 69 | .\" Fear. Run. Save yourself. No user-serviceable parts. |
| 70 | . \" fudge factors for nroff and troff |
| 71 | .if n \{\ |
| 72 | . ds #H 0 |
| 73 | . ds #V .8m |
| 74 | . ds #F .3m |
| 75 | . ds #[ \f1 |
| 76 | . ds #] \fP |
| 77 | .\} |
| 78 | .if t \{\ |
| 79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) |
| 80 | . ds #V .6m |
| 81 | . ds #F 0 |
| 82 | . ds #[ \& |
| 83 | . ds #] \& |
| 84 | .\} |
| 85 | . \" simple accents for nroff and troff |
| 86 | .if n \{\ |
| 87 | . ds ' \& |
| 88 | . ds ` \& |
| 89 | . ds ^ \& |
| 90 | . ds , \& |
| 91 | . ds ~ ~ |
| 92 | . ds / |
| 93 | .\} |
| 94 | .if t \{\ |
| 95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" |
| 96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' |
| 97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' |
| 98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' |
| 99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' |
| 100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' |
| 101 | .\} |
| 102 | . \" troff and (daisy-wheel) nroff accents |
| 103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' |
| 104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' |
| 105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] |
| 106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' |
| 107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' |
| 108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] |
| 109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] |
| 110 | .ds ae a\h'-(\w'a'u*4/10)'e |
| 111 | .ds Ae A\h'-(\w'A'u*4/10)'E |
| 112 | . \" corrections for vroff |
| 113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' |
| 114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' |
| 115 | . \" for low resolution devices (crt and lpr) |
| 116 | .if \n(.H>23 .if \n(.V>19 \ |
| 117 | \{\ |
| 118 | . ds : e |
| 119 | . ds 8 ss |
| 120 | . ds o a |
| 121 | . ds d- d\h'-1'\(ga |
| 122 | . ds D- D\h'-1'\(hy |
| 123 | . ds th \o'bp' |
| 124 | . ds Th \o'LP' |
| 125 | . ds ae ae |
| 126 | . ds Ae AE |
| 127 | .\} |
| 128 | .rm #[ #] #H #V #F C |
| 129 | .\" ======================================================================== |
| 130 | .\" |
| 131 | .IX Title "PERLEBCDIC 1" |
| 132 | .TH PERLEBCDIC 1 "2006-01-07" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | perlebcdic \- Considerations for running Perl on EBCDIC platforms |
| 135 | .SH "DESCRIPTION" |
| 136 | .IX Header "DESCRIPTION" |
| 137 | An exploration of some of the issues facing Perl programmers |
| 138 | on \s-1EBCDIC\s0 based computers. We do not cover localization, |
| 139 | internationalization, or multi byte character set issues other |
| 140 | than some discussion of \s-1UTF\-8\s0 and \s-1UTF\-EBCDIC\s0. |
| 141 | .PP |
| 142 | Portions that are still incomplete are marked with \s-1XXX\s0. |
| 143 | .SH "COMMON CHARACTER CODE SETS" |
| 144 | .IX Header "COMMON CHARACTER CODE SETS" |
| 145 | .Sh "\s-1ASCII\s0" |
| 146 | .IX Subsection "ASCII" |
| 147 | The American Standard Code for Information Interchange is a set of |
| 148 | integers running from 0 to 127 (decimal) that imply character |
| 149 | interpretation by the display and other system(s) of computers. |
| 150 | The range 0..127 can be covered by setting the bits in a 7\-bit binary |
| 151 | digit, hence the set is sometimes referred to as a \*(L"7\-bit \s-1ASCII\s0\*(R". |
| 152 | \&\s-1ASCII\s0 was described by the American National Standards Institute |
| 153 | document \s-1ANSI\s0 X3.4\-1986. It was also described by \s-1ISO\s0 646:1991 |
| 154 | (with localization for currency symbols). The full \s-1ASCII\s0 set is |
| 155 | given in the table below as the first 128 elements. Languages that |
| 156 | can be written adequately with the characters in \s-1ASCII\s0 include |
| 157 | English, Hawaiian, Indonesian, Swahili and some Native American |
| 158 | languages. |
| 159 | .PP |
| 160 | There are many character sets that extend the range of integers |
| 161 | from 0..2**7\-1 up to 2**8\-1, or 8 bit bytes (octets if you prefer). |
| 162 | One common one is the \s-1ISO\s0 8859\-1 character set. |
| 163 | .Sh "\s-1ISO\s0 8859" |
| 164 | .IX Subsection "ISO 8859" |
| 165 | The \s-1ISO\s0 8859\-$n are a collection of character code sets from the |
| 166 | International Organization for Standardization (\s-1ISO\s0) each of which |
| 167 | adds characters to the \s-1ASCII\s0 set that are typically found in European |
| 168 | languages many of which are based on the Roman, or Latin, alphabet. |
| 169 | .Sh "Latin 1 (\s-1ISO\s0 8859\-1)" |
| 170 | .IX Subsection "Latin 1 (ISO 8859-1)" |
| 171 | A particular 8\-bit extension to \s-1ASCII\s0 that includes grave and acute |
| 172 | accented Latin characters. Languages that can employ \s-1ISO\s0 8859\-1 |
| 173 | include all the languages covered by \s-1ASCII\s0 as well as Afrikaans, |
| 174 | Albanian, Basque, Catalan, Danish, Faroese, Finnish, Norwegian, |
| 175 | Portuguese, Spanish, and Swedish. Dutch is covered albeit without |
| 176 | the ij ligature. French is covered too but without the oe ligature. |
| 177 | German can use \s-1ISO\s0 8859\-1 but must do so without German-style |
| 178 | quotation marks. This set is based on Western European extensions |
| 179 | to \s-1ASCII\s0 and is commonly encountered in world wide web work. |
| 180 | In \s-1IBM\s0 character code set identification terminology \s-1ISO\s0 8859\-1 is |
| 181 | also known as \s-1CCSID\s0 819 (or sometimes 0819 or even 00819). |
| 182 | .Sh "\s-1EBCDIC\s0" |
| 183 | .IX Subsection "EBCDIC" |
| 184 | The Extended Binary Coded Decimal Interchange Code refers to a |
| 185 | large collection of slightly different single and multi byte |
| 186 | coded character sets that are different from \s-1ASCII\s0 or \s-1ISO\s0 8859\-1 |
| 187 | and typically run on host computers. The \s-1EBCDIC\s0 encodings derive |
| 188 | from 8 bit byte extensions of Hollerith punched card encodings. |
| 189 | The layout on the cards was such that high bits were set for the |
| 190 | upper and lower case alphabet characters [a\-z] and [A\-Z], but there |
| 191 | were gaps within each latin alphabet range. |
| 192 | .PP |
| 193 | Some \s-1IBM\s0 \s-1EBCDIC\s0 character sets may be known by character code set |
| 194 | identification numbers (\s-1CCSID\s0 numbers) or code page numbers. Leading |
| 195 | zero digits in \s-1CCSID\s0 numbers within this document are insignificant. |
| 196 | E.g. \s-1CCSID\s0 0037 may be referred to as 37 in places. |
| 197 | .Sh "13 variant characters" |
| 198 | .IX Subsection "13 variant characters" |
| 199 | Among \s-1IBM\s0 \s-1EBCDIC\s0 character code sets there are 13 characters that |
| 200 | are often mapped to different integer values. Those characters |
| 201 | are known as the 13 \*(L"variant\*(R" characters and are: |
| 202 | .PP |
| 203 | .Vb 1 |
| 204 | \& \e [ ] { } ^ ~ ! # | $ @ ` |
| 205 | .Ve |
| 206 | .Sh "0037" |
| 207 | .IX Subsection "0037" |
| 208 | Character code set \s-1ID\s0 0037 is a mapping of the \s-1ASCII\s0 plus Latin\-1 |
| 209 | characters (i.e. \s-1ISO\s0 8859\-1) to an \s-1EBCDIC\s0 set. 0037 is used |
| 210 | in North American English locales on the \s-1OS/400\s0 operating system |
| 211 | that runs on \s-1AS/400\s0 computers. \s-1CCSID\s0 37 differs from \s-1ISO\s0 8859\-1 |
| 212 | in 237 places, in other words they agree on only 19 code point values. |
| 213 | .Sh "1047" |
| 214 | .IX Subsection "1047" |
| 215 | Character code set \s-1ID\s0 1047 is also a mapping of the \s-1ASCII\s0 plus |
| 216 | Latin\-1 characters (i.e. \s-1ISO\s0 8859\-1) to an \s-1EBCDIC\s0 set. 1047 is |
| 217 | used under Unix System Services for \s-1OS/390\s0 or z/OS, and OpenEdition |
| 218 | for \s-1VM/ESA\s0. \s-1CCSID\s0 1047 differs from \s-1CCSID\s0 0037 in eight places. |
| 219 | .Sh "POSIX-BC" |
| 220 | .IX Subsection "POSIX-BC" |
| 221 | The \s-1EBCDIC\s0 code page in use on Siemens' \s-1BS2000\s0 system is distinct from |
| 222 | 1047 and 0037. It is identified below as the POSIX-BC set. |
| 223 | .Sh "Unicode code points versus \s-1EBCDIC\s0 code points" |
| 224 | .IX Subsection "Unicode code points versus EBCDIC code points" |
| 225 | In Unicode terminology a \fIcode point\fR is the number assigned to a |
| 226 | character: for example, in \s-1EBCDIC\s0 the character \*(L"A\*(R" is usually assigned |
| 227 | the number 193. In Unicode the character \*(L"A\*(R" is assigned the number 65. |
| 228 | This causes a problem with the semantics of the pack/unpack \*(L"U\*(R", which |
| 229 | are supposed to pack Unicode code points to characters and back to numbers. |
| 230 | The problem is: which code points to use for code points less than 256? |
| 231 | (for 256 and over there's no problem: Unicode code points are used) |
| 232 | In \s-1EBCDIC\s0, for the low 256 the \s-1EBCDIC\s0 code points are used. This |
| 233 | means that the equivalences |
| 234 | .PP |
| 235 | .Vb 2 |
| 236 | \& pack("U", ord($character)) eq $character |
| 237 | \& unpack("U", $character) == ord $character |
| 238 | .Ve |
| 239 | .PP |
| 240 | will hold. (If Unicode code points were applied consistently over |
| 241 | all the possible code points, pack(\*(L"U\*(R",ord(\*(L"A\*(R")) would in \s-1EBCDIC\s0 |
| 242 | equal \fIA with acute\fR or chr(101), and unpack(\*(L"U\*(R", \*(L"A\*(R") would equal |
| 243 | 65, or \fInon-breaking space\fR, not 193, or ord \*(L"A\*(R".) |
| 244 | .Sh "Remaining Perl Unicode problems in \s-1EBCDIC\s0" |
| 245 | .IX Subsection "Remaining Perl Unicode problems in EBCDIC" |
| 246 | .IP "\(bu" 4 |
| 247 | Many of the remaining seem to be related to case-insensitive matching: |
| 248 | for example, \f(CW\*(C`/[\ex{131}]/\*(C'\fR (\s-1LATIN\s0 \s-1SMALL\s0 \s-1LETTER\s0 \s-1DOTLESS\s0 I) does |
| 249 | not match \*(L"I\*(R" case\-insensitively, as it should under Unicode. |
| 250 | (The match succeeds in ASCII-derived platforms.) |
| 251 | .IP "\(bu" 4 |
| 252 | The extensions Unicode::Collate and Unicode::Normalized are not |
| 253 | supported under \s-1EBCDIC\s0, likewise for the encoding pragma. |
| 254 | .Sh "Unicode and \s-1UTF\s0" |
| 255 | .IX Subsection "Unicode and UTF" |
| 256 | \&\s-1UTF\s0 is a Unicode Transformation Format. \s-1UTF\-8\s0 is a Unicode conforming |
| 257 | representation of the Unicode standard that looks very much like \s-1ASCII\s0. |
| 258 | UTF-EBCDIC is an attempt to represent Unicode characters in an \s-1EBCDIC\s0 |
| 259 | transparent manner. |
| 260 | .Sh "Using Encode" |
| 261 | .IX Subsection "Using Encode" |
| 262 | Starting from Perl 5.8 you can use the standard new module Encode |
| 263 | to translate from \s-1EBCDIC\s0 to Latin\-1 code points |
| 264 | .PP |
| 265 | .Vb 1 |
| 266 | \& use Encode 'from_to'; |
| 267 | .Ve |
| 268 | .PP |
| 269 | .Vb 1 |
| 270 | \& my %ebcdic = ( 176 => 'cp37', 95 => 'cp1047', 106 => 'posix-bc' ); |
| 271 | .Ve |
| 272 | .PP |
| 273 | .Vb 3 |
| 274 | \& # $a is in EBCDIC code points |
| 275 | \& from_to($a, $ebcdic{ord '^'}, 'latin1'); |
| 276 | \& # $a is ISO 8859-1 code points |
| 277 | .Ve |
| 278 | .PP |
| 279 | and from Latin\-1 code points to \s-1EBCDIC\s0 code points |
| 280 | .PP |
| 281 | .Vb 1 |
| 282 | \& use Encode 'from_to'; |
| 283 | .Ve |
| 284 | .PP |
| 285 | .Vb 1 |
| 286 | \& my %ebcdic = ( 176 => 'cp37', 95 => 'cp1047', 106 => 'posix-bc' ); |
| 287 | .Ve |
| 288 | .PP |
| 289 | .Vb 3 |
| 290 | \& # $a is ISO 8859-1 code points |
| 291 | \& from_to($a, 'latin1', $ebcdic{ord '^'}); |
| 292 | \& # $a is in EBCDIC code points |
| 293 | .Ve |
| 294 | .PP |
| 295 | For doing I/O it is suggested that you use the autotranslating features |
| 296 | of PerlIO, see perluniintro. |
| 297 | .PP |
| 298 | Since version 5.8 Perl uses the new PerlIO I/O library. This enables |
| 299 | you to use different encodings per \s-1IO\s0 channel. For example you may use |
| 300 | .PP |
| 301 | .Vb 9 |
| 302 | \& use Encode; |
| 303 | \& open($f, ">:encoding(ascii)", "test.ascii"); |
| 304 | \& print $f "Hello World!\en"; |
| 305 | \& open($f, ">:encoding(cp37)", "test.ebcdic"); |
| 306 | \& print $f "Hello World!\en"; |
| 307 | \& open($f, ">:encoding(latin1)", "test.latin1"); |
| 308 | \& print $f "Hello World!\en"; |
| 309 | \& open($f, ">:encoding(utf8)", "test.utf8"); |
| 310 | \& print $f "Hello World!\en"; |
| 311 | .Ve |
| 312 | .PP |
| 313 | to get two files containing \*(L"Hello World!\en\*(R" in \s-1ASCII\s0, \s-1CP\s0 37 \s-1EBCDIC\s0, |
| 314 | \&\s-1ISO\s0 8859\-1 (Latin\-1) (in this example identical to \s-1ASCII\s0) respective |
| 315 | UTF-EBCDIC (in this example identical to normal \s-1EBCDIC\s0). See the |
| 316 | documentation of Encode::PerlIO for details. |
| 317 | .PP |
| 318 | As the PerlIO layer uses raw \s-1IO\s0 (bytes) internally, all this totally |
| 319 | ignores things like the type of your filesystem (\s-1ASCII\s0 or \s-1EBCDIC\s0). |
| 320 | .SH "SINGLE OCTET TABLES" |
| 321 | .IX Header "SINGLE OCTET TABLES" |
| 322 | The following tables list the \s-1ASCII\s0 and Latin 1 ordered sets including |
| 323 | the subsets: C0 controls (0..31), \s-1ASCII\s0 graphics (32..7e), delete (7f), |
| 324 | C1 controls (80..9f), and Latin\-1 (a.k.a. \s-1ISO\s0 8859\-1) (a0..ff). In the |
| 325 | table non-printing control character names as well as the Latin 1 |
| 326 | extensions to \s-1ASCII\s0 have been labelled with character names roughly |
| 327 | corresponding to \fIThe Unicode Standard, Version 3.0\fR albeit with |
| 328 | substitutions such as s/LATIN// and s/VULGAR// in all cases, |
| 329 | s/CAPITAL \s-1LETTER//\s0 in some cases, and s/SMALL \s-1LETTER\s0 ([A\-Z])/\el$1/ |
| 330 | in some other cases (the \f(CW\*(C`charnames\*(C'\fR pragma names unfortunately do |
| 331 | not list explicit names for the C0 or C1 control characters). The |
| 332 | \&\*(L"names\*(R" of the C1 control set (128..159 in \s-1ISO\s0 8859\-1) listed here are |
| 333 | somewhat arbitrary. The differences between the 0037 and 1047 sets are |
| 334 | flagged with ***. The differences between the 1047 and POSIX-BC sets |
| 335 | are flagged with ###. All \fIord()\fR numbers listed are decimal. If you |
| 336 | would rather see this table listing octal values then run the table |
| 337 | (that is, the pod version of this document since this recipe may not |
| 338 | work with a pod2_other_format translation) through: |
| 339 | .IP "recipe 0" 4 |
| 340 | .IX Item "recipe 0" |
| 341 | .PP |
| 342 | .Vb 2 |
| 343 | \& perl -ne 'if(/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)/)' \e |
| 344 | \& -e '{printf("%s%-9o%-9o%-9o%o\en",$1,$2,$3,$4,$5)}' perlebcdic.pod |
| 345 | .Ve |
| 346 | .PP |
| 347 | If you want to retain the UTF-x code points then in script form you |
| 348 | might want to write: |
| 349 | .IP "recipe 1" 4 |
| 350 | .IX Item "recipe 1" |
| 351 | .PP |
| 352 | .Vb 14 |
| 353 | \& open(FH,"<perlebcdic.pod") or die "Could not open perlebcdic.pod: $!"; |
| 354 | \& while (<FH>) { |
| 355 | \& if (/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\e.?(\ed*)\es+(\ed+)\e.?(\ed*)/) { |
| 356 | \& if ($7 ne '' && $9 ne '') { |
| 357 | \& printf("%s%-9o%-9o%-9o%-9o%-3o.%-5o%-3o.%o\en",$1,$2,$3,$4,$5,$6,$7,$8,$9); |
| 358 | \& } |
| 359 | \& elsif ($7 ne '') { |
| 360 | \& printf("%s%-9o%-9o%-9o%-9o%-3o.%-5o%o\en",$1,$2,$3,$4,$5,$6,$7,$8); |
| 361 | \& } |
| 362 | \& else { |
| 363 | \& printf("%s%-9o%-9o%-9o%-9o%-9o%o\en",$1,$2,$3,$4,$5,$6,$8); |
| 364 | \& } |
| 365 | \& } |
| 366 | \& } |
| 367 | .Ve |
| 368 | .PP |
| 369 | If you would rather see this table listing hexadecimal values then |
| 370 | run the table through: |
| 371 | .IP "recipe 2" 4 |
| 372 | .IX Item "recipe 2" |
| 373 | .PP |
| 374 | .Vb 2 |
| 375 | \& perl -ne 'if(/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)/)' \e |
| 376 | \& -e '{printf("%s%-9X%-9X%-9X%X\en",$1,$2,$3,$4,$5)}' perlebcdic.pod |
| 377 | .Ve |
| 378 | .PP |
| 379 | Or, in order to retain the UTF-x code points in hexadecimal: |
| 380 | .IP "recipe 3" 4 |
| 381 | .IX Item "recipe 3" |
| 382 | .PP |
| 383 | .Vb 14 |
| 384 | \& open(FH,"<perlebcdic.pod") or die "Could not open perlebcdic.pod: $!"; |
| 385 | \& while (<FH>) { |
| 386 | \& if (/(.{33})(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\es+(\ed+)\e.?(\ed*)\es+(\ed+)\e.?(\ed*)/) { |
| 387 | \& if ($7 ne '' && $9 ne '') { |
| 388 | \& printf("%s%-9X%-9X%-9X%-9X%-2X.%-6X%-2X.%X\en",$1,$2,$3,$4,$5,$6,$7,$8,$9); |
| 389 | \& } |
| 390 | \& elsif ($7 ne '') { |
| 391 | \& printf("%s%-9X%-9X%-9X%-9X%-2X.%-6X%X\en",$1,$2,$3,$4,$5,$6,$7,$8); |
| 392 | \& } |
| 393 | \& else { |
| 394 | \& printf("%s%-9X%-9X%-9X%-9X%-9X%X\en",$1,$2,$3,$4,$5,$6,$8); |
| 395 | \& } |
| 396 | \& } |
| 397 | \& } |
| 398 | .Ve |
| 399 | .PP |
| 400 | .Vb 260 |
| 401 | \& incomp- incomp- |
| 402 | \& 8859-1 lete lete |
| 403 | \& chr 0819 0037 1047 POSIX-BC UTF-8 UTF-EBCDIC |
| 404 | \& ------------------------------------------------------------------------------------ |
| 405 | \& <NULL> 0 0 0 0 0 0 |
| 406 | \& <START OF HEADING> 1 1 1 1 1 1 |
| 407 | \& <START OF TEXT> 2 2 2 2 2 2 |
| 408 | \& <END OF TEXT> 3 3 3 3 3 3 |
| 409 | \& <END OF TRANSMISSION> 4 55 55 55 4 55 |
| 410 | \& <ENQUIRY> 5 45 45 45 5 45 |
| 411 | \& <ACKNOWLEDGE> 6 46 46 46 6 46 |
| 412 | \& <BELL> 7 47 47 47 7 47 |
| 413 | \& <BACKSPACE> 8 22 22 22 8 22 |
| 414 | \& <HORIZONTAL TABULATION> 9 5 5 5 9 5 |
| 415 | \& <LINE FEED> 10 37 21 21 10 21 *** |
| 416 | \& <VERTICAL TABULATION> 11 11 11 11 11 11 |
| 417 | \& <FORM FEED> 12 12 12 12 12 12 |
| 418 | \& <CARRIAGE RETURN> 13 13 13 13 13 13 |
| 419 | \& <SHIFT OUT> 14 14 14 14 14 14 |
| 420 | \& <SHIFT IN> 15 15 15 15 15 15 |
| 421 | \& <DATA LINK ESCAPE> 16 16 16 16 16 16 |
| 422 | \& <DEVICE CONTROL ONE> 17 17 17 17 17 17 |
| 423 | \& <DEVICE CONTROL TWO> 18 18 18 18 18 18 |
| 424 | \& <DEVICE CONTROL THREE> 19 19 19 19 19 19 |
| 425 | \& <DEVICE CONTROL FOUR> 20 60 60 60 20 60 |
| 426 | \& <NEGATIVE ACKNOWLEDGE> 21 61 61 61 21 61 |
| 427 | \& <SYNCHRONOUS IDLE> 22 50 50 50 22 50 |
| 428 | \& <END OF TRANSMISSION BLOCK> 23 38 38 38 23 38 |
| 429 | \& <CANCEL> 24 24 24 24 24 24 |
| 430 | \& <END OF MEDIUM> 25 25 25 25 25 25 |
| 431 | \& <SUBSTITUTE> 26 63 63 63 26 63 |
| 432 | \& <ESCAPE> 27 39 39 39 27 39 |
| 433 | \& <FILE SEPARATOR> 28 28 28 28 28 28 |
| 434 | \& <GROUP SEPARATOR> 29 29 29 29 29 29 |
| 435 | \& <RECORD SEPARATOR> 30 30 30 30 30 30 |
| 436 | \& <UNIT SEPARATOR> 31 31 31 31 31 31 |
| 437 | \& <SPACE> 32 64 64 64 32 64 |
| 438 | \& ! 33 90 90 90 33 90 |
| 439 | \& " 34 127 127 127 34 127 |
| 440 | \& # 35 123 123 123 35 123 |
| 441 | \& $ 36 91 91 91 36 91 |
| 442 | \& % 37 108 108 108 37 108 |
| 443 | \& & 38 80 80 80 38 80 |
| 444 | \& ' 39 125 125 125 39 125 |
| 445 | \& ( 40 77 77 77 40 77 |
| 446 | \& ) 41 93 93 93 41 93 |
| 447 | \& * 42 92 92 92 42 92 |
| 448 | \& + 43 78 78 78 43 78 |
| 449 | \& , 44 107 107 107 44 107 |
| 450 | \& - 45 96 96 96 45 96 |
| 451 | \& . 46 75 75 75 46 75 |
| 452 | \& / 47 97 97 97 47 97 |
| 453 | \& 0 48 240 240 240 48 240 |
| 454 | \& 1 49 241 241 241 49 241 |
| 455 | \& 2 50 242 242 242 50 242 |
| 456 | \& 3 51 243 243 243 51 243 |
| 457 | \& 4 52 244 244 244 52 244 |
| 458 | \& 5 53 245 245 245 53 245 |
| 459 | \& 6 54 246 246 246 54 246 |
| 460 | \& 7 55 247 247 247 55 247 |
| 461 | \& 8 56 248 248 248 56 248 |
| 462 | \& 9 57 249 249 249 57 249 |
| 463 | \& : 58 122 122 122 58 122 |
| 464 | \& ; 59 94 94 94 59 94 |
| 465 | \& < 60 76 76 76 60 76 |
| 466 | \& = 61 126 126 126 61 126 |
| 467 | \& > 62 110 110 110 62 110 |
| 468 | \& ? 63 111 111 111 63 111 |
| 469 | \& @ 64 124 124 124 64 124 |
| 470 | \& A 65 193 193 193 65 193 |
| 471 | \& B 66 194 194 194 66 194 |
| 472 | \& C 67 195 195 195 67 195 |
| 473 | \& D 68 196 196 196 68 196 |
| 474 | \& E 69 197 197 197 69 197 |
| 475 | \& F 70 198 198 198 70 198 |
| 476 | \& G 71 199 199 199 71 199 |
| 477 | \& H 72 200 200 200 72 200 |
| 478 | \& I 73 201 201 201 73 201 |
| 479 | \& J 74 209 209 209 74 209 |
| 480 | \& K 75 210 210 210 75 210 |
| 481 | \& L 76 211 211 211 76 211 |
| 482 | \& M 77 212 212 212 77 212 |
| 483 | \& N 78 213 213 213 78 213 |
| 484 | \& O 79 214 214 214 79 214 |
| 485 | \& P 80 215 215 215 80 215 |
| 486 | \& Q 81 216 216 216 81 216 |
| 487 | \& R 82 217 217 217 82 217 |
| 488 | \& S 83 226 226 226 83 226 |
| 489 | \& T 84 227 227 227 84 227 |
| 490 | \& U 85 228 228 228 85 228 |
| 491 | \& V 86 229 229 229 86 229 |
| 492 | \& W 87 230 230 230 87 230 |
| 493 | \& X 88 231 231 231 88 231 |
| 494 | \& Y 89 232 232 232 89 232 |
| 495 | \& Z 90 233 233 233 90 233 |
| 496 | \& [ 91 186 173 187 91 173 *** ### |
| 497 | \& \e 92 224 224 188 92 224 ### |
| 498 | \& ] 93 187 189 189 93 189 *** |
| 499 | \& ^ 94 176 95 106 94 95 *** ### |
| 500 | \& _ 95 109 109 109 95 109 |
| 501 | \& ` 96 121 121 74 96 121 ### |
| 502 | \& a 97 129 129 129 97 129 |
| 503 | \& b 98 130 130 130 98 130 |
| 504 | \& c 99 131 131 131 99 131 |
| 505 | \& d 100 132 132 132 100 132 |
| 506 | \& e 101 133 133 133 101 133 |
| 507 | \& f 102 134 134 134 102 134 |
| 508 | \& g 103 135 135 135 103 135 |
| 509 | \& h 104 136 136 136 104 136 |
| 510 | \& i 105 137 137 137 105 137 |
| 511 | \& j 106 145 145 145 106 145 |
| 512 | \& k 107 146 146 146 107 146 |
| 513 | \& l 108 147 147 147 108 147 |
| 514 | \& m 109 148 148 148 109 148 |
| 515 | \& n 110 149 149 149 110 149 |
| 516 | \& o 111 150 150 150 111 150 |
| 517 | \& p 112 151 151 151 112 151 |
| 518 | \& q 113 152 152 152 113 152 |
| 519 | \& r 114 153 153 153 114 153 |
| 520 | \& s 115 162 162 162 115 162 |
| 521 | \& t 116 163 163 163 116 163 |
| 522 | \& u 117 164 164 164 117 164 |
| 523 | \& v 118 165 165 165 118 165 |
| 524 | \& w 119 166 166 166 119 166 |
| 525 | \& x 120 167 167 167 120 167 |
| 526 | \& y 121 168 168 168 121 168 |
| 527 | \& z 122 169 169 169 122 169 |
| 528 | \& { 123 192 192 251 123 192 ### |
| 529 | \& | 124 79 79 79 124 79 |
| 530 | \& } 125 208 208 253 125 208 ### |
| 531 | \& ~ 126 161 161 255 126 161 ### |
| 532 | \& <DELETE> 127 7 7 7 127 7 |
| 533 | \& <C1 0> 128 32 32 32 194.128 32 |
| 534 | \& <C1 1> 129 33 33 33 194.129 33 |
| 535 | \& <C1 2> 130 34 34 34 194.130 34 |
| 536 | \& <C1 3> 131 35 35 35 194.131 35 |
| 537 | \& <C1 4> 132 36 36 36 194.132 36 |
| 538 | \& <C1 5> 133 21 37 37 194.133 37 *** |
| 539 | \& <C1 6> 134 6 6 6 194.134 6 |
| 540 | \& <C1 7> 135 23 23 23 194.135 23 |
| 541 | \& <C1 8> 136 40 40 40 194.136 40 |
| 542 | \& <C1 9> 137 41 41 41 194.137 41 |
| 543 | \& <C1 10> 138 42 42 42 194.138 42 |
| 544 | \& <C1 11> 139 43 43 43 194.139 43 |
| 545 | \& <C1 12> 140 44 44 44 194.140 44 |
| 546 | \& <C1 13> 141 9 9 9 194.141 9 |
| 547 | \& <C1 14> 142 10 10 10 194.142 10 |
| 548 | \& <C1 15> 143 27 27 27 194.143 27 |
| 549 | \& <C1 16> 144 48 48 48 194.144 48 |
| 550 | \& <C1 17> 145 49 49 49 194.145 49 |
| 551 | \& <C1 18> 146 26 26 26 194.146 26 |
| 552 | \& <C1 19> 147 51 51 51 194.147 51 |
| 553 | \& <C1 20> 148 52 52 52 194.148 52 |
| 554 | \& <C1 21> 149 53 53 53 194.149 53 |
| 555 | \& <C1 22> 150 54 54 54 194.150 54 |
| 556 | \& <C1 23> 151 8 8 8 194.151 8 |
| 557 | \& <C1 24> 152 56 56 56 194.152 56 |
| 558 | \& <C1 25> 153 57 57 57 194.153 57 |
| 559 | \& <C1 26> 154 58 58 58 194.154 58 |
| 560 | \& <C1 27> 155 59 59 59 194.155 59 |
| 561 | \& <C1 28> 156 4 4 4 194.156 4 |
| 562 | \& <C1 29> 157 20 20 20 194.157 20 |
| 563 | \& <C1 30> 158 62 62 62 194.158 62 |
| 564 | \& <C1 31> 159 255 255 95 194.159 255 ### |
| 565 | \& <NON-BREAKING SPACE> 160 65 65 65 194.160 128.65 |
| 566 | \& <INVERTED EXCLAMATION MARK> 161 170 170 170 194.161 128.66 |
| 567 | \& <CENT SIGN> 162 74 74 176 194.162 128.67 ### |
| 568 | \& <POUND SIGN> 163 177 177 177 194.163 128.68 |
| 569 | \& <CURRENCY SIGN> 164 159 159 159 194.164 128.69 |
| 570 | \& <YEN SIGN> 165 178 178 178 194.165 128.70 |
| 571 | \& <BROKEN BAR> 166 106 106 208 194.166 128.71 ### |
| 572 | \& <SECTION SIGN> 167 181 181 181 194.167 128.72 |
| 573 | \& <DIAERESIS> 168 189 187 121 194.168 128.73 *** ### |
| 574 | \& <COPYRIGHT SIGN> 169 180 180 180 194.169 128.74 |
| 575 | \& <FEMININE ORDINAL INDICATOR> 170 154 154 154 194.170 128.81 |
| 576 | \& <LEFT POINTING GUILLEMET> 171 138 138 138 194.171 128.82 |
| 577 | \& <NOT SIGN> 172 95 176 186 194.172 128.83 *** ### |
| 578 | \& <SOFT HYPHEN> 173 202 202 202 194.173 128.84 |
| 579 | \& <REGISTERED TRADE MARK SIGN> 174 175 175 175 194.174 128.85 |
| 580 | \& <MACRON> 175 188 188 161 194.175 128.86 ### |
| 581 | \& <DEGREE SIGN> 176 144 144 144 194.176 128.87 |
| 582 | \& <PLUS-OR-MINUS SIGN> 177 143 143 143 194.177 128.88 |
| 583 | \& <SUPERSCRIPT TWO> 178 234 234 234 194.178 128.89 |
| 584 | \& <SUPERSCRIPT THREE> 179 250 250 250 194.179 128.98 |
| 585 | \& <ACUTE ACCENT> 180 190 190 190 194.180 128.99 |
| 586 | \& <MICRO SIGN> 181 160 160 160 194.181 128.100 |
| 587 | \& <PARAGRAPH SIGN> 182 182 182 182 194.182 128.101 |
| 588 | \& <MIDDLE DOT> 183 179 179 179 194.183 128.102 |
| 589 | \& <CEDILLA> 184 157 157 157 194.184 128.103 |
| 590 | \& <SUPERSCRIPT ONE> 185 218 218 218 194.185 128.104 |
| 591 | \& <MASC. ORDINAL INDICATOR> 186 155 155 155 194.186 128.105 |
| 592 | \& <RIGHT POINTING GUILLEMET> 187 139 139 139 194.187 128.106 |
| 593 | \& <FRACTION ONE QUARTER> 188 183 183 183 194.188 128.112 |
| 594 | \& <FRACTION ONE HALF> 189 184 184 184 194.189 128.113 |
| 595 | \& <FRACTION THREE QUARTERS> 190 185 185 185 194.190 128.114 |
| 596 | \& <INVERTED QUESTION MARK> 191 171 171 171 194.191 128.115 |
| 597 | \& <A WITH GRAVE> 192 100 100 100 195.128 138.65 |
| 598 | \& <A WITH ACUTE> 193 101 101 101 195.129 138.66 |
| 599 | \& <A WITH CIRCUMFLEX> 194 98 98 98 195.130 138.67 |
| 600 | \& <A WITH TILDE> 195 102 102 102 195.131 138.68 |
| 601 | \& <A WITH DIAERESIS> 196 99 99 99 195.132 138.69 |
| 602 | \& <A WITH RING ABOVE> 197 103 103 103 195.133 138.70 |
| 603 | \& <CAPITAL LIGATURE AE> 198 158 158 158 195.134 138.71 |
| 604 | \& <C WITH CEDILLA> 199 104 104 104 195.135 138.72 |
| 605 | \& <E WITH GRAVE> 200 116 116 116 195.136 138.73 |
| 606 | \& <E WITH ACUTE> 201 113 113 113 195.137 138.74 |
| 607 | \& <E WITH CIRCUMFLEX> 202 114 114 114 195.138 138.81 |
| 608 | \& <E WITH DIAERESIS> 203 115 115 115 195.139 138.82 |
| 609 | \& <I WITH GRAVE> 204 120 120 120 195.140 138.83 |
| 610 | \& <I WITH ACUTE> 205 117 117 117 195.141 138.84 |
| 611 | \& <I WITH CIRCUMFLEX> 206 118 118 118 195.142 138.85 |
| 612 | \& <I WITH DIAERESIS> 207 119 119 119 195.143 138.86 |
| 613 | \& <CAPITAL LETTER ETH> 208 172 172 172 195.144 138.87 |
| 614 | \& <N WITH TILDE> 209 105 105 105 195.145 138.88 |
| 615 | \& <O WITH GRAVE> 210 237 237 237 195.146 138.89 |
| 616 | \& <O WITH ACUTE> 211 238 238 238 195.147 138.98 |
| 617 | \& <O WITH CIRCUMFLEX> 212 235 235 235 195.148 138.99 |
| 618 | \& <O WITH TILDE> 213 239 239 239 195.149 138.100 |
| 619 | \& <O WITH DIAERESIS> 214 236 236 236 195.150 138.101 |
| 620 | \& <MULTIPLICATION SIGN> 215 191 191 191 195.151 138.102 |
| 621 | \& <O WITH STROKE> 216 128 128 128 195.152 138.103 |
| 622 | \& <U WITH GRAVE> 217 253 253 224 195.153 138.104 ### |
| 623 | \& <U WITH ACUTE> 218 254 254 254 195.154 138.105 |
| 624 | \& <U WITH CIRCUMFLEX> 219 251 251 221 195.155 138.106 ### |
| 625 | \& <U WITH DIAERESIS> 220 252 252 252 195.156 138.112 |
| 626 | \& <Y WITH ACUTE> 221 173 186 173 195.157 138.113 *** ### |
| 627 | \& <CAPITAL LETTER THORN> 222 174 174 174 195.158 138.114 |
| 628 | \& <SMALL LETTER SHARP S> 223 89 89 89 195.159 138.115 |
| 629 | \& <a WITH GRAVE> 224 68 68 68 195.160 139.65 |
| 630 | \& <a WITH ACUTE> 225 69 69 69 195.161 139.66 |
| 631 | \& <a WITH CIRCUMFLEX> 226 66 66 66 195.162 139.67 |
| 632 | \& <a WITH TILDE> 227 70 70 70 195.163 139.68 |
| 633 | \& <a WITH DIAERESIS> 228 67 67 67 195.164 139.69 |
| 634 | \& <a WITH RING ABOVE> 229 71 71 71 195.165 139.70 |
| 635 | \& <SMALL LIGATURE ae> 230 156 156 156 195.166 139.71 |
| 636 | \& <c WITH CEDILLA> 231 72 72 72 195.167 139.72 |
| 637 | \& <e WITH GRAVE> 232 84 84 84 195.168 139.73 |
| 638 | \& <e WITH ACUTE> 233 81 81 81 195.169 139.74 |
| 639 | \& <e WITH CIRCUMFLEX> 234 82 82 82 195.170 139.81 |
| 640 | \& <e WITH DIAERESIS> 235 83 83 83 195.171 139.82 |
| 641 | \& <i WITH GRAVE> 236 88 88 88 195.172 139.83 |
| 642 | \& <i WITH ACUTE> 237 85 85 85 195.173 139.84 |
| 643 | \& <i WITH CIRCUMFLEX> 238 86 86 86 195.174 139.85 |
| 644 | \& <i WITH DIAERESIS> 239 87 87 87 195.175 139.86 |
| 645 | \& <SMALL LETTER eth> 240 140 140 140 195.176 139.87 |
| 646 | \& <n WITH TILDE> 241 73 73 73 195.177 139.88 |
| 647 | \& <o WITH GRAVE> 242 205 205 205 195.178 139.89 |
| 648 | \& <o WITH ACUTE> 243 206 206 206 195.179 139.98 |
| 649 | \& <o WITH CIRCUMFLEX> 244 203 203 203 195.180 139.99 |
| 650 | \& <o WITH TILDE> 245 207 207 207 195.181 139.100 |
| 651 | \& <o WITH DIAERESIS> 246 204 204 204 195.182 139.101 |
| 652 | \& <DIVISION SIGN> 247 225 225 225 195.183 139.102 |
| 653 | \& <o WITH STROKE> 248 112 112 112 195.184 139.103 |
| 654 | \& <u WITH GRAVE> 249 221 221 192 195.185 139.104 ### |
| 655 | \& <u WITH ACUTE> 250 222 222 222 195.186 139.105 |
| 656 | \& <u WITH CIRCUMFLEX> 251 219 219 219 195.187 139.106 |
| 657 | \& <u WITH DIAERESIS> 252 220 220 220 195.188 139.112 |
| 658 | \& <y WITH ACUTE> 253 141 141 141 195.189 139.113 |
| 659 | \& <SMALL LETTER thorn> 254 142 142 142 195.190 139.114 |
| 660 | \& <y WITH DIAERESIS> 255 223 223 223 195.191 139.115 |
| 661 | .Ve |
| 662 | .PP |
| 663 | If you would rather see the above table in \s-1CCSID\s0 0037 order rather than |
| 664 | \&\s-1ASCII\s0 + Latin\-1 order then run the table through: |
| 665 | .IP "recipe 4" 4 |
| 666 | .IX Item "recipe 4" |
| 667 | .PP |
| 668 | .Vb 5 |
| 669 | \& 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 |
| 670 | \& -e '{push(@l,$_)}' \e |
| 671 | \& -e 'END{print map{$_->[0]}' \e |
| 672 | \& -e ' sort{$a->[1] <=> $b->[1]}' \e |
| 673 | \& -e ' map{[$_,substr($_,42,3)]}@l;}' perlebcdic.pod |
| 674 | .Ve |
| 675 | .PP |
| 676 | If you would rather see it in \s-1CCSID\s0 1047 order then change the digit |
| 677 | 42 in the last line to 51, like this: |
| 678 | .IP "recipe 5" 4 |
| 679 | .IX Item "recipe 5" |
| 680 | .PP |
| 681 | .Vb 5 |
| 682 | \& perl -ne 'if(/.{33}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}/)'\e |
| 683 | \& -e '{push(@l,$_)}' \e |
| 684 | \& -e 'END{print map{$_->[0]}' \e |
| 685 | \& -e ' sort{$a->[1] <=> $b->[1]}' \e |
| 686 | \& -e ' map{[$_,substr($_,51,3)]}@l;}' perlebcdic.pod |
| 687 | .Ve |
| 688 | .PP |
| 689 | If you would rather see it in POSIX-BC order then change the digit |
| 690 | 51 in the last line to 60, like this: |
| 691 | .IP "recipe 6" 4 |
| 692 | .IX Item "recipe 6" |
| 693 | .PP |
| 694 | .Vb 5 |
| 695 | \& perl -ne 'if(/.{33}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}\es{6,8}\ed{1,3}/)'\e |
| 696 | \& -e '{push(@l,$_)}' \e |
| 697 | \& -e 'END{print map{$_->[0]}' \e |
| 698 | \& -e ' sort{$a->[1] <=> $b->[1]}' \e |
| 699 | \& -e ' map{[$_,substr($_,60,3)]}@l;}' perlebcdic.pod |
| 700 | .Ve |
| 701 | .SH "IDENTIFYING CHARACTER CODE SETS" |
| 702 | .IX Header "IDENTIFYING CHARACTER CODE SETS" |
| 703 | To determine the character set you are running under from perl one |
| 704 | could use the return value of \fIord()\fR or \fIchr()\fR to test one or more |
| 705 | character values. For example: |
| 706 | .PP |
| 707 | .Vb 2 |
| 708 | \& $is_ascii = "A" eq chr(65); |
| 709 | \& $is_ebcdic = "A" eq chr(193); |
| 710 | .Ve |
| 711 | .PP |
| 712 | Also, \*(L"\et\*(R" is a \f(CW\*(C`HORIZONTAL TABULATION\*(C'\fR character so that: |
| 713 | .PP |
| 714 | .Vb 2 |
| 715 | \& $is_ascii = ord("\et") == 9; |
| 716 | \& $is_ebcdic = ord("\et") == 5; |
| 717 | .Ve |
| 718 | .PP |
| 719 | To distinguish \s-1EBCDIC\s0 code pages try looking at one or more of |
| 720 | the characters that differ between them. For example: |
| 721 | .PP |
| 722 | .Vb 2 |
| 723 | \& $is_ebcdic_37 = "\en" eq chr(37); |
| 724 | \& $is_ebcdic_1047 = "\en" eq chr(21); |
| 725 | .Ve |
| 726 | .PP |
| 727 | Or better still choose a character that is uniquely encoded in any |
| 728 | of the code sets, e.g.: |
| 729 | .PP |
| 730 | .Vb 4 |
| 731 | \& $is_ascii = ord('[') == 91; |
| 732 | \& $is_ebcdic_37 = ord('[') == 186; |
| 733 | \& $is_ebcdic_1047 = ord('[') == 173; |
| 734 | \& $is_ebcdic_POSIX_BC = ord('[') == 187; |
| 735 | .Ve |
| 736 | .PP |
| 737 | However, it would be unwise to write tests such as: |
| 738 | .PP |
| 739 | .Vb 2 |
| 740 | \& $is_ascii = "\er" ne chr(13); # WRONG |
| 741 | \& $is_ascii = "\en" ne chr(10); # ILL ADVISED |
| 742 | .Ve |
| 743 | .PP |
| 744 | Obviously the first of these will fail to distinguish most \s-1ASCII\s0 machines |
| 745 | from either a \s-1CCSID\s0 0037, a 1047, or a POSIX-BC \s-1EBCDIC\s0 machine since \*(L"\er\*(R" eq |
| 746 | chr(13) under all of those coded character sets. But note too that |
| 747 | because \*(L"\en\*(R" is chr(13) and \*(L"\er\*(R" is chr(10) on the MacIntosh (which is an |
| 748 | \&\s-1ASCII\s0 machine) the second \f(CW$is_ascii\fR test will lead to trouble there. |
| 749 | .PP |
| 750 | To determine whether or not perl was built under an \s-1EBCDIC\s0 |
| 751 | code page you can use the Config module like so: |
| 752 | .PP |
| 753 | .Vb 2 |
| 754 | \& use Config; |
| 755 | \& $is_ebcdic = $Config{'ebcdic'} eq 'define'; |
| 756 | .Ve |
| 757 | .SH "CONVERSIONS" |
| 758 | .IX Header "CONVERSIONS" |
| 759 | .Sh "tr///" |
| 760 | .IX Subsection "tr///" |
| 761 | In order to convert a string of characters from one character set to |
| 762 | another a simple list of numbers, such as in the right columns in the |
| 763 | above table, along with perl's tr/// operator is all that is needed. |
| 764 | The data in the table are in \s-1ASCII\s0 order hence the \s-1EBCDIC\s0 columns |
| 765 | provide easy to use \s-1ASCII\s0 to \s-1EBCDIC\s0 operations that are also easily |
| 766 | reversed. |
| 767 | .PP |
| 768 | For example, to convert \s-1ASCII\s0 to code page 037 take the output of the second |
| 769 | column from the output of recipe 0 (modified to add \e\e characters) and use |
| 770 | it in tr/// like so: |
| 771 | .PP |
| 772 | .Vb 17 |
| 773 | \& $cp_037 = |
| 774 | \& '\e000\e001\e002\e003\e234\e011\e206\e177\e227\e215\e216\e013\e014\e015\e016\e017' . |
| 775 | \& '\e020\e021\e022\e023\e235\e205\e010\e207\e030\e031\e222\e217\e034\e035\e036\e037' . |
| 776 | \& '\e200\e201\e202\e203\e204\e012\e027\e033\e210\e211\e212\e213\e214\e005\e006\e007' . |
| 777 | \& '\e220\e221\e026\e223\e224\e225\e226\e004\e230\e231\e232\e233\e024\e025\e236\e032' . |
| 778 | \& '\e040\e240\e342\e344\e340\e341\e343\e345\e347\e361\e242\e056\e074\e050\e053\e174' . |
| 779 | \& '\e046\e351\e352\e353\e350\e355\e356\e357\e354\e337\e041\e044\e052\e051\e073\e254' . |
| 780 | \& '\e055\e057\e302\e304\e300\e301\e303\e305\e307\e321\e246\e054\e045\e137\e076\e077' . |
| 781 | \& '\e370\e311\e312\e313\e310\e315\e316\e317\e314\e140\e072\e043\e100\e047\e075\e042' . |
| 782 | \& '\e330\e141\e142\e143\e144\e145\e146\e147\e150\e151\e253\e273\e360\e375\e376\e261' . |
| 783 | \& '\e260\e152\e153\e154\e155\e156\e157\e160\e161\e162\e252\e272\e346\e270\e306\e244' . |
| 784 | \& '\e265\e176\e163\e164\e165\e166\e167\e170\e171\e172\e241\e277\e320\e335\e336\e256' . |
| 785 | \& '\e136\e243\e245\e267\e251\e247\e266\e274\e275\e276\e133\e135\e257\e250\e264\e327' . |
| 786 | \& '\e173\e101\e102\e103\e104\e105\e106\e107\e110\e111\e255\e364\e366\e362\e363\e365' . |
| 787 | \& '\e175\e112\e113\e114\e115\e116\e117\e120\e121\e122\e271\e373\e374\e371\e372\e377' . |
| 788 | \& '\e134\e367\e123\e124\e125\e126\e127\e130\e131\e132\e262\e324\e326\e322\e323\e325' . |
| 789 | \& '\e060\e061\e062\e063\e064\e065\e066\e067\e070\e071\e263\e333\e334\e331\e332\e237' ; |
| 790 | .Ve |
| 791 | .PP |
| 792 | .Vb 2 |
| 793 | \& my $ebcdic_string = $ascii_string; |
| 794 | \& eval '$ebcdic_string =~ tr/' . $cp_037 . '/\e000-\e377/'; |
| 795 | .Ve |
| 796 | .PP |
| 797 | To convert from \s-1EBCDIC\s0 037 to \s-1ASCII\s0 just reverse the order of the tr/// |
| 798 | arguments like so: |
| 799 | .PP |
| 800 | .Vb 2 |
| 801 | \& my $ascii_string = $ebcdic_string; |
| 802 | \& eval '$ascii_string =~ tr/\e000-\e377/' . $cp_037 . '/'; |
| 803 | .Ve |
| 804 | .PP |
| 805 | Similarly one could take the output of the third column from recipe 0 to |
| 806 | obtain a \f(CW$cp_1047\fR table. The fourth column of the output from recipe |
| 807 | 0 could provide a \f(CW$cp_posix_bc\fR table suitable for transcoding as well. |
| 808 | .Sh "iconv" |
| 809 | .IX Subsection "iconv" |
| 810 | \&\s-1XPG\s0 operability often implies the presence of an \fIiconv\fR utility |
| 811 | available from the shell or from the C library. Consult your system's |
| 812 | documentation for information on iconv. |
| 813 | .PP |
| 814 | On \s-1OS/390\s0 or z/OS see the \fIiconv\fR\|(1) manpage. One way to invoke the iconv |
| 815 | shell utility from within perl would be to: |
| 816 | .PP |
| 817 | .Vb 2 |
| 818 | \& # OS/390 or z/OS example |
| 819 | \& $ascii_data = `echo '$ebcdic_data'| iconv -f IBM-1047 -t ISO8859-1` |
| 820 | .Ve |
| 821 | .PP |
| 822 | or the inverse map: |
| 823 | .PP |
| 824 | .Vb 2 |
| 825 | \& # OS/390 or z/OS example |
| 826 | \& $ebcdic_data = `echo '$ascii_data'| iconv -f ISO8859-1 -t IBM-1047` |
| 827 | .Ve |
| 828 | .PP |
| 829 | For other perl based conversion options see the Convert::* modules on \s-1CPAN\s0. |
| 830 | .Sh "C \s-1RTL\s0" |
| 831 | .IX Subsection "C RTL" |
| 832 | The \s-1OS/390\s0 and z/OS C run time libraries provide \fI_atoe()\fR and \fI_etoa()\fR functions. |
| 833 | .SH "OPERATOR DIFFERENCES" |
| 834 | .IX Header "OPERATOR DIFFERENCES" |
| 835 | The \f(CW\*(C`..\*(C'\fR range operator treats certain character ranges with |
| 836 | care on \s-1EBCDIC\s0 machines. For example the following array |
| 837 | will have twenty six elements on either an \s-1EBCDIC\s0 machine |
| 838 | or an \s-1ASCII\s0 machine: |
| 839 | .PP |
| 840 | .Vb 1 |
| 841 | \& @alphabet = ('A'..'Z'); # $#alphabet == 25 |
| 842 | .Ve |
| 843 | .PP |
| 844 | The bitwise operators such as & ^ | may return different results |
| 845 | when operating on string or character data in a perl program running |
| 846 | on an \s-1EBCDIC\s0 machine than when run on an \s-1ASCII\s0 machine. Here is |
| 847 | an example adapted from the one in perlop: |
| 848 | .PP |
| 849 | .Vb 5 |
| 850 | \& # EBCDIC-based examples |
| 851 | \& print "j p \en" ^ " a h"; # prints "JAPH\en" |
| 852 | \& print "JA" | " ph\en"; # prints "japh\en" |
| 853 | \& print "JAPH\enJunk" & "\e277\e277\e277\e277\e277"; # prints "japh\en"; |
| 854 | \& print 'p N$' ^ " E<H\en"; # prints "Perl\en"; |
| 855 | .Ve |
| 856 | .PP |
| 857 | An interesting property of the 32 C0 control characters |
| 858 | in the \s-1ASCII\s0 table is that they can \*(L"literally\*(R" be constructed |
| 859 | as control characters in perl, e.g. \f(CW\*(C`(chr(0) eq "\ec@")\*(C'\fR |
| 860 | \&\f(CW\*(C`(chr(1) eq "\ecA")\*(C'\fR, and so on. Perl on \s-1EBCDIC\s0 machines has been |
| 861 | ported to take \*(L"\ec@\*(R" to \fIchr\fR\|(0) and \*(L"\ecA\*(R" to \fIchr\fR\|(1) as well, but the |
| 862 | thirty three characters that result depend on which code page you are |
| 863 | using. The table below uses the character names from the previous table |
| 864 | but with substitutions such as s/START \s-1OF/S\s0.O./; s/END \s-1OF\s0 /E.O./; |
| 865 | s/TRANSMISSION/TRANS./; s/TABULATION/TAB./; s/VERTICAL/VERT./; |
| 866 | s/HORIZONTAL/HORIZ./; s/DEVICE \s-1CONTROL/D\s0.C./; s/SEPARATOR/SEP./; |
| 867 | s/NEGATIVE \s-1ACKNOWLEDGE/NEG\s0. \s-1ACK\s0./;. The POSIX-BC and 1047 sets are |
| 868 | identical throughout this range and differ from the 0037 set at only |
| 869 | one spot (21 decimal). Note that the \f(CW\*(C`LINE FEED\*(C'\fR character |
| 870 | may be generated by \*(L"\ecJ\*(R" on \s-1ASCII\s0 machines but by \*(L"\ecU\*(R" on 1047 or POSIX-BC |
| 871 | machines and cannot be generated as a \f(CW"\ec.letter."\fR control character on |
| 872 | 0037 machines. Note also that \*(L"\ec\e\e\*(R" maps to two characters |
| 873 | not one. |
| 874 | .PP |
| 875 | .Vb 35 |
| 876 | \& chr ord 8859-1 0037 1047 && POSIX-BC |
| 877 | \& ------------------------------------------------------------------------ |
| 878 | \& "\ec?" 127 <DELETE> " " ***>< |
| 879 | \& "\ec@" 0 <NULL> <NULL> <NULL> ***>< |
| 880 | \& "\ecA" 1 <S.O. HEADING> <S.O. HEADING> <S.O. HEADING> |
| 881 | \& "\ecB" 2 <S.O. TEXT> <S.O. TEXT> <S.O. TEXT> |
| 882 | \& "\ecC" 3 <E.O. TEXT> <E.O. TEXT> <E.O. TEXT> |
| 883 | \& "\ecD" 4 <E.O. TRANS.> <C1 28> <C1 28> |
| 884 | \& "\ecE" 5 <ENQUIRY> <HORIZ. TAB.> <HORIZ. TAB.> |
| 885 | \& "\ecF" 6 <ACKNOWLEDGE> <C1 6> <C1 6> |
| 886 | \& "\ecG" 7 <BELL> <DELETE> <DELETE> |
| 887 | \& "\ecH" 8 <BACKSPACE> <C1 23> <C1 23> |
| 888 | \& "\ecI" 9 <HORIZ. TAB.> <C1 13> <C1 13> |
| 889 | \& "\ecJ" 10 <LINE FEED> <C1 14> <C1 14> |
| 890 | \& "\ecK" 11 <VERT. TAB.> <VERT. TAB.> <VERT. TAB.> |
| 891 | \& "\ecL" 12 <FORM FEED> <FORM FEED> <FORM FEED> |
| 892 | \& "\ecM" 13 <CARRIAGE RETURN> <CARRIAGE RETURN> <CARRIAGE RETURN> |
| 893 | \& "\ecN" 14 <SHIFT OUT> <SHIFT OUT> <SHIFT OUT> |
| 894 | \& "\ecO" 15 <SHIFT IN> <SHIFT IN> <SHIFT IN> |
| 895 | \& "\ecP" 16 <DATA LINK ESCAPE> <DATA LINK ESCAPE> <DATA LINK ESCAPE> |
| 896 | \& "\ecQ" 17 <D.C. ONE> <D.C. ONE> <D.C. ONE> |
| 897 | \& "\ecR" 18 <D.C. TWO> <D.C. TWO> <D.C. TWO> |
| 898 | \& "\ecS" 19 <D.C. THREE> <D.C. THREE> <D.C. THREE> |
| 899 | \& "\ecT" 20 <D.C. FOUR> <C1 29> <C1 29> |
| 900 | \& "\ecU" 21 <NEG. ACK.> <C1 5> <LINE FEED> *** |
| 901 | \& "\ecV" 22 <SYNCHRONOUS IDLE> <BACKSPACE> <BACKSPACE> |
| 902 | \& "\ecW" 23 <E.O. TRANS. BLOCK> <C1 7> <C1 7> |
| 903 | \& "\ecX" 24 <CANCEL> <CANCEL> <CANCEL> |
| 904 | \& "\ecY" 25 <E.O. MEDIUM> <E.O. MEDIUM> <E.O. MEDIUM> |
| 905 | \& "\ecZ" 26 <SUBSTITUTE> <C1 18> <C1 18> |
| 906 | \& "\ec[" 27 <ESCAPE> <C1 15> <C1 15> |
| 907 | \& "\ec\e\e" 28 <FILE SEP.>\e <FILE SEP.>\e <FILE SEP.>\e |
| 908 | \& "\ec]" 29 <GROUP SEP.> <GROUP SEP.> <GROUP SEP.> |
| 909 | \& "\ec^" 30 <RECORD SEP.> <RECORD SEP.> <RECORD SEP.> ***>< |
| 910 | \& "\ec_" 31 <UNIT SEP.> <UNIT SEP.> <UNIT SEP.> ***>< |
| 911 | .Ve |
| 912 | .SH "FUNCTION DIFFERENCES" |
| 913 | .IX Header "FUNCTION DIFFERENCES" |
| 914 | .IP "\fIchr()\fR" 8 |
| 915 | .IX Item "chr()" |
| 916 | \&\fIchr()\fR must be given an \s-1EBCDIC\s0 code number argument to yield a desired |
| 917 | character return value on an \s-1EBCDIC\s0 machine. For example: |
| 918 | .Sp |
| 919 | .Vb 1 |
| 920 | \& $CAPITAL_LETTER_A = chr(193); |
| 921 | .Ve |
| 922 | .IP "\fIord()\fR" 8 |
| 923 | .IX Item "ord()" |
| 924 | \&\fIord()\fR will return \s-1EBCDIC\s0 code number values on an \s-1EBCDIC\s0 machine. |
| 925 | For example: |
| 926 | .Sp |
| 927 | .Vb 1 |
| 928 | \& $the_number_193 = ord("A"); |
| 929 | .Ve |
| 930 | .IP "\fIpack()\fR" 8 |
| 931 | .IX Item "pack()" |
| 932 | The c and C templates for \fIpack()\fR are dependent upon character set |
| 933 | encoding. Examples of usage on \s-1EBCDIC\s0 include: |
| 934 | .Sp |
| 935 | .Vb 4 |
| 936 | \& $foo = pack("CCCC",193,194,195,196); |
| 937 | \& # $foo eq "ABCD" |
| 938 | \& $foo = pack("C4",193,194,195,196); |
| 939 | \& # same thing |
| 940 | .Ve |
| 941 | .Sp |
| 942 | .Vb 2 |
| 943 | \& $foo = pack("ccxxcc",193,194,195,196); |
| 944 | \& # $foo eq "AB\e0\e0CD" |
| 945 | .Ve |
| 946 | .IP "\fIprint()\fR" 8 |
| 947 | .IX Item "print()" |
| 948 | One must be careful with scalars and strings that are passed to |
| 949 | print that contain \s-1ASCII\s0 encodings. One common place |
| 950 | for this to occur is in the output of the \s-1MIME\s0 type header for |
| 951 | \&\s-1CGI\s0 script writing. For example, many perl programming guides |
| 952 | recommend something similar to: |
| 953 | .Sp |
| 954 | .Vb 2 |
| 955 | \& print "Content-type:\ettext/html\e015\e012\e015\e012"; |
| 956 | \& # this may be wrong on EBCDIC |
| 957 | .Ve |
| 958 | .Sp |
| 959 | Under the \s-1IBM\s0 \s-1OS/390\s0 \s-1USS\s0 Web Server or WebSphere on z/OS for example |
| 960 | you should instead write that as: |
| 961 | .Sp |
| 962 | .Vb 1 |
| 963 | \& print "Content-type:\ettext/html\er\en\er\en"; # OK for DGW et alia |
| 964 | .Ve |
| 965 | .Sp |
| 966 | That is because the translation from \s-1EBCDIC\s0 to \s-1ASCII\s0 is done |
| 967 | by the web server in this case (such code will not be appropriate for |
| 968 | the Macintosh however). Consult your web server's documentation for |
| 969 | further details. |
| 970 | .IP "\fIprintf()\fR" 8 |
| 971 | .IX Item "printf()" |
| 972 | The formats that can convert characters to numbers and vice versa |
| 973 | will be different from their \s-1ASCII\s0 counterparts when executed |
| 974 | on an \s-1EBCDIC\s0 machine. Examples include: |
| 975 | .Sp |
| 976 | .Vb 1 |
| 977 | \& printf("%c%c%c",193,194,195); # prints ABC |
| 978 | .Ve |
| 979 | .IP "\fIsort()\fR" 8 |
| 980 | .IX Item "sort()" |
| 981 | \&\s-1EBCDIC\s0 sort results may differ from \s-1ASCII\s0 sort results especially for |
| 982 | mixed case strings. This is discussed in more detail below. |
| 983 | .IP "\fIsprintf()\fR" 8 |
| 984 | .IX Item "sprintf()" |
| 985 | See the discussion of \fIprintf()\fR above. An example of the use |
| 986 | of sprintf would be: |
| 987 | .Sp |
| 988 | .Vb 1 |
| 989 | \& $CAPITAL_LETTER_A = sprintf("%c",193); |
| 990 | .Ve |
| 991 | .IP "\fIunpack()\fR" 8 |
| 992 | .IX Item "unpack()" |
| 993 | See the discussion of \fIpack()\fR above. |
| 994 | .SH "REGULAR EXPRESSION DIFFERENCES" |
| 995 | .IX Header "REGULAR EXPRESSION DIFFERENCES" |
| 996 | As of perl 5.005_03 the letter range regular expression such as |
| 997 | [A\-Z] and [a\-z] have been especially coded to not pick up gap |
| 998 | characters. For example, characters such as o\*^ \f(CW\*(C`o WITH CIRCUMFLEX\*(C'\fR |
| 999 | that lie between I and J would not be matched by the |
| 1000 | regular expression range \f(CW\*(C`/[H\-K]/\*(C'\fR. This works in |
| 1001 | the other direction, too, if either of the range end points is |
| 1002 | explicitly numeric: \f(CW\*(C`[\ex89\-\ex91]\*(C'\fR will match \f(CW\*(C`\ex8e\*(C'\fR, even |
| 1003 | 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 |
| 1004 | is a gap character from the alphabetic viewpoint. |
| 1005 | .PP |
| 1006 | If you do want to match the alphabet gap characters in a single octet |
| 1007 | regular expression try matching the hex or octal code such |
| 1008 | as \f(CW\*(C`/\e313/\*(C'\fR on \s-1EBCDIC\s0 or \f(CW\*(C`/\e364/\*(C'\fR on \s-1ASCII\s0 machines to |
| 1009 | have your regular expression match \f(CW\*(C`o WITH CIRCUMFLEX\*(C'\fR. |
| 1010 | .PP |
| 1011 | Another construct to be wary of is the inappropriate use of hex or |
| 1012 | octal constants in regular expressions. Consider the following |
| 1013 | set of subs: |
| 1014 | .PP |
| 1015 | .Vb 4 |
| 1016 | \& sub is_c0 { |
| 1017 | \& my $char = substr(shift,0,1); |
| 1018 | \& $char =~ /[\e000-\e037]/; |
| 1019 | \& } |
| 1020 | .Ve |
| 1021 | .PP |
| 1022 | .Vb 4 |
| 1023 | \& sub is_print_ascii { |
| 1024 | \& my $char = substr(shift,0,1); |
| 1025 | \& $char =~ /[\e040-\e176]/; |
| 1026 | \& } |
| 1027 | .Ve |
| 1028 | .PP |
| 1029 | .Vb 4 |
| 1030 | \& sub is_delete { |
| 1031 | \& my $char = substr(shift,0,1); |
| 1032 | \& $char eq "\e177"; |
| 1033 | \& } |
| 1034 | .Ve |
| 1035 | .PP |
| 1036 | .Vb 4 |
| 1037 | \& sub is_c1 { |
| 1038 | \& my $char = substr(shift,0,1); |
| 1039 | \& $char =~ /[\e200-\e237]/; |
| 1040 | \& } |
| 1041 | .Ve |
| 1042 | .PP |
| 1043 | .Vb 4 |
| 1044 | \& sub is_latin_1 { |
| 1045 | \& my $char = substr(shift,0,1); |
| 1046 | \& $char =~ /[\e240-\e377]/; |
| 1047 | \& } |
| 1048 | .Ve |
| 1049 | .PP |
| 1050 | The above would be adequate if the concern was only with numeric code points. |
| 1051 | However, the concern may be with characters rather than code points |
| 1052 | and on an \s-1EBCDIC\s0 machine it may be desirable for constructs such as |
| 1053 | \&\f(CW\*(C`if (is_print_ascii("A")) {print "A is a printable character\en";}\*(C'\fR to print |
| 1054 | out the expected message. One way to represent the above collection |
| 1055 | of character classification subs that is capable of working across the |
| 1056 | four coded character sets discussed in this document is as follows: |
| 1057 | .PP |
| 1058 | .Vb 12 |
| 1059 | \& sub Is_c0 { |
| 1060 | \& my $char = substr(shift,0,1); |
| 1061 | \& if (ord('^')==94) { # ascii |
| 1062 | \& return $char =~ /[\e000-\e037]/; |
| 1063 | \& } |
| 1064 | \& if (ord('^')==176) { # 37 |
| 1065 | \& return $char =~ /[\e000-\e003\e067\e055-\e057\e026\e005\e045\e013-\e023\e074\e075\e062\e046\e030\e031\e077\e047\e034-\e037]/; |
| 1066 | \& } |
| 1067 | \& if (ord('^')==95 || ord('^')==106) { # 1047 || posix-bc |
| 1068 | \& return $char =~ /[\e000-\e003\e067\e055-\e057\e026\e005\e025\e013-\e023\e074\e075\e062\e046\e030\e031\e077\e047\e034-\e037]/; |
| 1069 | \& } |
| 1070 | \& } |
| 1071 | .Ve |
| 1072 | .PP |
| 1073 | .Vb 4 |
| 1074 | \& sub Is_print_ascii { |
| 1075 | \& my $char = substr(shift,0,1); |
| 1076 | \& $char =~ /[ !"\e#\e$%&'()*+,\e-.\e/0-9:;<=>?\e@A-Z[\e\e\e]^_`a-z{|}~]/; |
| 1077 | \& } |
| 1078 | .Ve |
| 1079 | .PP |
| 1080 | .Vb 9 |
| 1081 | \& sub Is_delete { |
| 1082 | \& my $char = substr(shift,0,1); |
| 1083 | \& if (ord('^')==94) { # ascii |
| 1084 | \& return $char eq "\e177"; |
| 1085 | \& } |
| 1086 | \& else { # ebcdic |
| 1087 | \& return $char eq "\e007"; |
| 1088 | \& } |
| 1089 | \& } |
| 1090 | .Ve |
| 1091 | .PP |
| 1092 | .Vb 16 |
| 1093 | \& sub Is_c1 { |
| 1094 | \& my $char = substr(shift,0,1); |
| 1095 | \& if (ord('^')==94) { # ascii |
| 1096 | \& return $char =~ /[\e200-\e237]/; |
| 1097 | \& } |
| 1098 | \& if (ord('^')==176) { # 37 |
| 1099 | \& return $char =~ /[\e040-\e044\e025\e006\e027\e050-\e054\e011\e012\e033\e060\e061\e032\e063-\e066\e010\e070-\e073\e040\e024\e076\e377]/; |
| 1100 | \& } |
| 1101 | \& if (ord('^')==95) { # 1047 |
| 1102 | \& return $char =~ /[\e040-\e045\e006\e027\e050-\e054\e011\e012\e033\e060\e061\e032\e063-\e066\e010\e070-\e073\e040\e024\e076\e377]/; |
| 1103 | \& } |
| 1104 | \& if (ord('^')==106) { # posix-bc |
| 1105 | \& return $char =~ |
| 1106 | \& /[\e040-\e045\e006\e027\e050-\e054\e011\e012\e033\e060\e061\e032\e063-\e066\e010\e070-\e073\e040\e024\e076\e137]/; |
| 1107 | \& } |
| 1108 | \& } |
| 1109 | .Ve |
| 1110 | .PP |
| 1111 | .Vb 18 |
| 1112 | \& sub Is_latin_1 { |
| 1113 | \& my $char = substr(shift,0,1); |
| 1114 | \& if (ord('^')==94) { # ascii |
| 1115 | \& return $char =~ /[\e240-\e377]/; |
| 1116 | \& } |
| 1117 | \& if (ord('^')==176) { # 37 |
| 1118 | \& return $char =~ |
| 1119 | \& /[\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]/; |
| 1120 | \& } |
| 1121 | \& if (ord('^')==95) { # 1047 |
| 1122 | \& return $char =~ |
| 1123 | \& /[\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]/; |
| 1124 | \& } |
| 1125 | \& if (ord('^')==106) { # posix-bc |
| 1126 | \& return $char =~ |
| 1127 | \& /[\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]/; |
| 1128 | \& } |
| 1129 | \& } |
| 1130 | .Ve |
| 1131 | .PP |
| 1132 | Note however that only the \f(CW\*(C`Is_ascii_print()\*(C'\fR sub is really independent |
| 1133 | of coded character set. Another way to write \f(CW\*(C`Is_latin_1()\*(C'\fR would be |
| 1134 | to use the characters in the range explicitly: |
| 1135 | .PP |
| 1136 | .Vb 4 |
| 1137 | \& sub Is_latin_1 { |
| 1138 | \& my $char = substr(shift,0,1); |
| 1139 |