From 5f26d5fd39994d2ecb568aeb7efdba685fe9a350 Mon Sep 17 00:00:00 2001 From: Karl Williamson Date: Tue, 18 May 2010 08:43:31 -0600 Subject: [PATCH] Replace wrong tr/// table in perlebcdic.pod perlebcdic.pod contains a helpful table to use in tr/// to convert between EBCDIC and Latin1/ASCII. Unfortunately, the table is the inverse of the one it describes, as I discovered in following the directions on how it was extracted. The actual code that uses the table uses it in the inverse way, so it actually works correctly, but if you follow the instructions to get the tables corresponding to the other recognized code pages, you will get the inverse of the ones you wanted, and things won't work out. This patch changes the table to its inverse, and changes the sample code to correspond, as this is easier for the person trying to follow the instructions since deriving the old table is somewhat more complicated. I also changed the table to hex from octal, as that is more the norm these days, and I changed to recipes in the pod to print out leading zeros to make all the values the same length, as the table that they can generate has them. --- pod/perlebcdic.pod | 106 ++++++++++++++++++++++++++++++----------------------- 1 file changed, 61 insertions(+), 45 deletions(-) diff --git a/pod/perlebcdic.pod b/pod/perlebcdic.pod index f690595..d4fffee 100644 --- a/pod/perlebcdic.pod +++ b/pod/perlebcdic.pod @@ -254,7 +254,8 @@ work with a pod2_other_format translation) through: =back perl -ne 'if(/(.{43})(\d+)\s+(\d+)\s+(\d+)\s+(\d+)/)' \ - -e '{printf("%s%-9o%-9o%-9o%o\n",$1,$2,$3,$4,$5)}' perlebcdic.pod + -e '{printf("%s%-9.03o%-9.03o%-9.03o%.03o\n",$1,$2,$3,$4,$5)}' \ + perlebcdic.pod If you want to retain the UTF-x code points then in script form you might want to write: @@ -267,17 +268,20 @@ might want to write: open(FH,") { - if (/(.{43})(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\.?(\d*)\s+(\d+)\.?(\d*)/) { + if (/(.{43})(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\.?(\d*)\s+(\d+)\.?(\d*)/) + { if ($7 ne '' && $9 ne '') { - printf("%s%-9o%-9o%-9o%-9o%-3o.%-5o%-3o.%o\n", - $1,$2,$3,$4,$5,$6,$7,$8,$9); + printf( + "%s%-9.03o%-9.03o%-9.03o%-9.03o%-3o.%-5o%-3o.%.03o\n", + $1,$2,$3,$4,$5,$6,$7,$8,$9); } elsif ($7 ne '') { - printf("%s%-9o%-9o%-9o%-9o%-3o.%-5o%o\n", + printf("%s%-9.03o%-9.03o%-9.03o%-9.03o%-3o.%-5o%.03o\n", $1,$2,$3,$4,$5,$6,$7,$8); } else { - printf("%s%-9o%-9o%-9o%-9o%-9o%o\n",$1,$2,$3,$4,$5,$6,$8); + printf("%s%-9.03o%-9.03o%-9.03o%-9.03o%-9.03o%.03o\n", + $1,$2,$3,$4,$5,$6,$8); } } } @@ -292,7 +296,8 @@ run the table through: =back perl -ne 'if(/(.{43})(\d+)\s+(\d+)\s+(\d+)\s+(\d+)/)' \ - -e '{printf("%s%-9X%-9X%-9X%X\n",$1,$2,$3,$4,$5)}' perlebcdic.pod + -e '{printf("%s%-9.02X%-9.02X%-9.02X%.02X\n",$1,$2,$3,$4,$5)}' \ + perlebcdic.pod Or, in order to retain the UTF-x code points in hexadecimal: @@ -304,17 +309,20 @@ Or, in order to retain the UTF-x code points in hexadecimal: open(FH,") { - if (/(.{43})(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\.?(\d*)\s+(\d+)\.?(\d*)/) { + if (/(.{43})(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\.?(\d*)\s+(\d+)\.?(\d*)/) + { if ($7 ne '' && $9 ne '') { - printf("%s%-9X%-9X%-9X%-9X%-2X.%-6X%-2X.%X\n", + printf( + "%s%-9.02X%-9.02X%-9.02X%-9.02X%-2X.%-6.02X%02X.%02X\n", $1,$2,$3,$4,$5,$6,$7,$8,$9); } elsif ($7 ne '') { - printf("%s%-9X%-9X%-9X%-9X%-2X.%-6X%X\n", + printf("%s%-9.02X%-9.02X%-9.02X%-9.02X%-2X.%-6.02X%02X\n", $1,$2,$3,$4,$5,$6,$7,$8); } else { - printf("%s%-9X%-9X%-9X%-9X%-9X%X\n",$1,$2,$3,$4,$5,$6,$8); + printf("%s%-9.02X%-9.02X%-9.02X%-9.02X%-9.02X%02X\n", + $1,$2,$3,$4,$5,$6,$8); } } } @@ -589,7 +597,8 @@ ASCII + Latin-1 order then run the table through: =back - perl -ne 'if(/.{43}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}/)'\ + perl \ + -ne 'if(/.{43}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}/)'\ -e '{push(@l,$_)}' \ -e 'END{print map{$_->[0]}' \ -e ' sort{$a->[1] <=> $b->[1]}' \ @@ -604,11 +613,12 @@ If you would rather see it in CCSID 1047 order then change the number =back - perl -ne 'if(/.{43}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}/)'\ - -e '{push(@l,$_)}' \ - -e 'END{print map{$_->[0]}' \ - -e ' sort{$a->[1] <=> $b->[1]}' \ - -e ' map{[$_,substr($_,61,3)]}@l;}' perlebcdic.pod + perl \ + -ne 'if(/.{43}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}/)'\ + -e '{push(@l,$_)}' \ + -e 'END{print map{$_->[0]}' \ + -e ' sort{$a->[1] <=> $b->[1]}' \ + -e ' map{[$_,substr($_,61,3)]}@l;}' perlebcdic.pod If you would rather see it in POSIX-BC order then change the number 61 in the last line to 70, like this: @@ -619,7 +629,8 @@ If you would rather see it in POSIX-BC order then change the number =back - perl -ne 'if(/.{43}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}/)'\ + perl \ + -ne 'if(/.{43}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}\s{6,8}\d{1,3}/)'\ -e '{push(@l,$_)}' \ -e 'END{print map{$_->[0]}' \ -e ' sort{$a->[1] <=> $b->[1]}' \ @@ -678,44 +689,49 @@ code page you can use the Config module like so: 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 ASCII order hence the EBCDIC columns -provide easy to use ASCII to EBCDIC operations that are also easily +The data in the table are in ASCII/Latin1 order, hence the EBCDIC columns +provide easy to use ASCII/Latin1 to EBCDIC operations that are also easily reversed. -For example, to convert ASCII to code page 037 take the output of the second -column from the output of recipe 0 (modified to add \\ characters) and use -it in tr/// like so: +For example, to convert ASCII/Latin1 to code page 037 take the output of the +second numbers column from the output of recipe 2 (modified to add '\' +characters) and use it in tr/// like so: $cp_037 = - '\000\001\002\003\234\011\206\177\227\215\216\013\014\015\016\017' . - '\020\021\022\023\235\205\010\207\030\031\222\217\034\035\036\037' . - '\200\201\202\203\204\012\027\033\210\211\212\213\214\005\006\007' . - '\220\221\026\223\224\225\226\004\230\231\232\233\024\025\236\032' . - '\040\240\342\344\340\341\343\345\347\361\242\056\074\050\053\174' . - '\046\351\352\353\350\355\356\357\354\337\041\044\052\051\073\254' . - '\055\057\302\304\300\301\303\305\307\321\246\054\045\137\076\077' . - '\370\311\312\313\310\315\316\317\314\140\072\043\100\047\075\042' . - '\330\141\142\143\144\145\146\147\150\151\253\273\360\375\376\261' . - '\260\152\153\154\155\156\157\160\161\162\252\272\346\270\306\244' . - '\265\176\163\164\165\166\167\170\171\172\241\277\320\335\336\256' . - '\136\243\245\267\251\247\266\274\275\276\133\135\257\250\264\327' . - '\173\101\102\103\104\105\106\107\110\111\255\364\366\362\363\365' . - '\175\112\113\114\115\116\117\120\121\122\271\373\374\371\372\377' . - '\134\367\123\124\125\126\127\130\131\132\262\324\326\322\323\325' . - '\060\061\062\063\064\065\066\067\070\071\263\333\334\331\332\237' ; + '\x00\x01\x02\x03\x37\x2D\x2E\x2F\x16\x05\x25\x0B\x0C\x0D\x0E\x0F' . + '\x10\x11\x12\x13\x3C\x3D\x32\x26\x18\x19\x3F\x27\x1C\x1D\x1E\x1F' . + '\x40\x5A\x7F\x7B\x5B\x6C\x50\x7D\x4D\x5D\x5C\x4E\x6B\x60\x4B\x61' . + '\xF0\xF1\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\x7A\x5E\x4C\x7E\x6E\x6F' . + '\x7C\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xD1\xD2\xD3\xD4\xD5\xD6' . + '\xD7\xD8\xD9\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xBA\xE0\xBB\xB0\x6D' . + '\x79\x81\x82\x83\x84\x85\x86\x87\x88\x89\x91\x92\x93\x94\x95\x96' . + '\x97\x98\x99\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xC0\x4F\xD0\xA1\x07' . + '\x20\x21\x22\x23\x24\x15\x06\x17\x28\x29\x2A\x2B\x2C\x09\x0A\x1B' . + '\x30\x31\x1A\x33\x34\x35\x36\x08\x38\x39\x3A\x3B\x04\x14\x3E\xFF' . + '\x41\xAA\x4A\xB1\x9F\xB2\x6A\xB5\xBD\xB4\x9A\x8A\x5F\xCA\xAF\xBC' . + '\x90\x8F\xEA\xFA\xBE\xA0\xB6\xB3\x9D\xDA\x9B\x8B\xB7\xB8\xB9\xAB' . + '\x64\x65\x62\x66\x63\x67\x9E\x68\x74\x71\x72\x73\x78\x75\x76\x77' . + '\xAC\x69\xED\xEE\xEB\xEF\xEC\xBF\x80\xFD\xFE\xFB\xFC\xAD\xAE\x59' . + '\x44\x45\x42\x46\x43\x47\x9C\x48\x54\x51\x52\x53\x58\x55\x56\x57' . + '\x8C\x49\xCD\xCE\xCB\xCF\xCC\xE1\x70\xDD\xDE\xDB\xDC\x8D\x8E\xDF'; my $ebcdic_string = $ascii_string; - eval '$ebcdic_string =~ tr/' . $cp_037 . '/\000-\377/'; + eval '$ebcdic_string =~ tr/\000-\377/' . $cp_037 . '/'; To convert from EBCDIC 037 to ASCII just reverse the order of the tr/// arguments like so: my $ascii_string = $ebcdic_string; - eval '$ascii_string =~ tr/\000-\377/' . $cp_037 . '/'; + eval '$ascii_string =~ tr/' . $cp_037 . '/\000-\377/'; + +Similarly one could take the output of the third numbers column from recipe 2 +to obtain a C<$cp_1047> table. The fourth numbers column of the output from +recipe 2 could provide a C<$cp_posix_bc> table suitable for transcoding as +well. -Similarly one could take the output of the third column from recipe 0 to -obtain a C<$cp_1047> table. The fourth column of the output from recipe -0 could provide a C<$cp_posix_bc> table suitable for transcoding as well. +If you wanted to see the inverse tables, you would first have to sort on the +desired numbers column as in recipes 4, 5 or 6, then take the output of the +first numbers column. =head2 iconv @@ -857,7 +873,7 @@ recommend something similar to: Under the IBM OS/390 USS Web Server or WebSphere on z/OS for example you should instead write that as: - print "Content-type:\ttext/html\r\n\r\n"; # OK for DGW et alia + print "Content-type:\ttext/html\r\n\r\n"; # OK for DGW et al That is because the translation from EBCDIC to ASCII is done by the web server in this case (such code will not be appropriate for -- 2.7.4