From: Karl Williamson <khw@khw-desktop.(none)>
Date: Mon, 24 May 2010 16:50:13 +0000 (-0600)
Subject: Add functions to test.pl for easier EBCDIC testing
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=f69d9fdf3f3cf041b8398a5d897daef24f0e5fa0;p=p5sagit%2Fp5-mst-13.2.git

Add functions to test.pl for easier EBCDIC testing

This patch adds functions native_to_latin1($) and latin1_to_native($) to
test.pl.  Use of these in test scripts allows for less special case code
(or deciding to blow it off and just skip EBCDIC platforms).  If a
string is all ASCII, one has always been able to just use it and not
worry about EBCDIC.  But non-ASCII, latin1 characters have been a
different matter.  This allows one to wrap those characters in a
function call and get automatic EBCDIC compatibility.

The functions do not handle UTF-8/UTF-EBCDIC conversions.  This is more
complicated, and I was worried that that part was not appropriate for
test.pl which should use the bare minimum of Perl functionality.  These
functions use tr///, beyond what other parts of test.pl use.
---

diff --git a/t/test.pl b/t/test.pl
index d39c010..88e52ee 100644
--- a/t/test.pl
+++ b/t/test.pl
@@ -1,5 +1,7 @@
 #
-# t/test.pl - most of Test::More functionality without the fuss
+# t/test.pl - most of Test::More functionality without the fuss, plus
+# has mappings native_to_latin1 and latin1_to_native so that fewer tests
+# on non ASCII-ish platforms need to be skipped
 
 
 # NOTE:
@@ -935,4 +937,127 @@ sub watchdog ($)
     }
 }
 
+my $cp_0037 =   # EBCDIC code page 0037
+    '\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 $cp_1047 =   # EBCDIC code page 1047
+    '\x00\x01\x02\x03\x37\x2D\x2E\x2F\x16\x05\x15\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\xAD\xE0\xBD\x5F\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\x25\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\xBB\xB4\x9A\x8A\xB0\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\xBA\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 $cp_bc = # EBCDIC code page POSiX-BC
+    '\x00\x01\x02\x03\x37\x2D\x2E\x2F\x16\x05\x15\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\xBB\xBC\xBD\x6A\x6D' .
+    '\x4A\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\xFB\x4F\xFD\xFF\x07' .
+    '\x20\x21\x22\x23\x24\x25\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\x5F' .
+    '\x41\xAA\xB0\xB1\x9F\xB2\xD0\xB5\x79\xB4\x9A\x8A\xBA\xCA\xAF\xA1' .
+    '\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\xE0\xFE\xDD\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\xC0\xDE\xDB\xDC\x8D\x8E\xDF';
+
+my $straight =  # Avoid ranges
+    '\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F' .
+    '\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F' .
+    '\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2A\x2B\x2C\x2D\x2E\x2F' .
+    '\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3A\x3B\x3C\x3D\x3E\x3F' .
+    '\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4A\x4B\x4C\x4D\x4E\x4F' .
+    '\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5A\x5B\x5C\x5D\x5E\x5F' .
+    '\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6A\x6B\x6C\x6D\x6E\x6F' .
+    '\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7A\x7B\x7C\x7D\x7E\x7F' .
+    '\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F' .
+    '\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F' .
+    '\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF' .
+    '\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF' .
+    '\xC0\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xCB\xCC\xCD\xCE\xCF' .
+    '\xD0\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xDB\xDC\xDD\xDE\xDF' .
+    '\xE0\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xEA\xEB\xEC\xED\xEE\xEF' .
+    '\xF0\xF1\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA\xFB\xFC\xFD\xFE\xFF';
+
+# The following 2 functions allow tests to work on both EBCDIC and
+# ASCII-ish platforms.  They convert string scalars between the native
+# character set and the set of 256 characters which is usually called
+# Latin1.
+#
+# These routines don't work on UTF-EBCDIC and UTF-8.
+
+sub native_to_latin1($) {
+    my $string = shift;
+
+    return $string if ord('^') == 94;   # ASCII, Latin1
+    my $cp;
+    if (ord('^') == 95) {    # EBCDIC 1047
+        $cp = \$cp_1047;
+    }
+    elsif (ord('^') == 106) {   # EBCDIC POSIX-BC
+        $cp = \$cp_bc;
+    }
+    elsif (ord('^') == 176)  {   # EBCDIC 037 */
+        $cp = \$cp_0037;
+    }
+    else {
+        die "Unknown native character set";
+    }
+
+    eval '$string =~ tr/' . $$cp . '/' . $straight . '/';
+    return $string;
+}
+
+sub latin1_to_native($) {
+    my $string = shift;
+
+    return $string if ord('^') == 94;   # ASCII, Latin1
+    my $cp;
+    if (ord('^') == 95) {    # EBCDIC 1047
+        $cp = \$cp_1047;
+    }
+    elsif (ord('^') == 106) {   # EBCDIC POSIX-BC
+        $cp = \$cp_bc;
+    }
+    elsif (ord('^') == 176)  {   # EBCDIC 037 */
+        $cp = \$cp_0037;
+    }
+    else {
+        die "Unknown native character set";
+    }
+
+    eval '$string =~ tr/' . $straight . '/' . $$cp . '/';
+    return $string;
+}
+
 1;