index 6a1321bab84eed95dd6d2059fbd70b6d09779ded..bfd4511d724ca8ad595ae3f3e504625b53a451d8 100755 (executable)
# UCS-2 code in hex
# # and Unicode name (not used in this script)
-
-require "convutils.pm";
+use strict;
+require convutils;
# Load BIG5.TXT
my $all = &read_source("BIG5.TXT");
index 8df23f8be65fae3ff3b90c32328b2dc49c592b32..6b65c11a65475653428c145e8df0ff3f1e4b84c0 100755 (executable)
# where the "u" field is the Unicode code point in hex,
# and the "b" field is the hex byte sequence for GB18030
-require "convutils.pm";
+use strict;
+require convutils;
# Read the input
-$in_file = "gb-18030-2000.xml";
+my $in_file = "gb-18030-2000.xml";
-open(FILE, $in_file) || die("cannot open $in_file");
+open(my $in, '<', $in_file) || die("cannot open $in_file");
my @mapping;
-while (<FILE>)
+while (<$in>)
{
next if (!m/<a u="([0-9A-F]+)" b="([0-9A-F ]+)"/);
- $u = 1ドル;
- $c = 2ドル;
+ my ($u, $c) = (1,ドル 2ドル);
$c =~ s/ //g;
- $ucs = hex($u);
- $code = hex($c);
+ my $ucs = hex($u);
+ my $code = hex($c);
# The GB-18030 character set, which we use as the source, contains
# a lot of extra characters on top of the GB2312 character set that
direction => 'both'
}
}
-close(FILE);
+close($in);
print_tables("EUC_CN", \@mapping);
index b4e140b657c993be291dfafa3ea66d13181341af..b1ad19a69d8929d4564064ab0aa3a234b93d1b48 100755 (executable)
# Generate UTF-8 <--> EUC_JIS_2004 code conversion tables from
# "euc-jis-2004-std.txt" (http://x0213.org)
-require "convutils.pm";
+use strict;
+require convutils;
# first generate UTF-8 --> EUC_JIS_2004 table
-$in_file = "euc-jis-2004-std.txt";
+my $in_file = "euc-jis-2004-std.txt";
-open(FILE, $in_file) || die("cannot open $in_file");
+open(my $in, '<', $in_file) || die("cannot open $in_file");
my @all;
-while ($line = <FILE>)
+while (my $line = <$in>)
{
if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/)
{
- $c = 1ドル;
- $u1 =わ 2ドル;
- $u2 =わ 3ドル;
- $rest = "U+" . $u1 . "+" . $u2 . 4ドル;
- $code = hex($c);
- $ucs1 = hex($u1);
- $ucs2 = hex($u2);
+ # combined characters
+ my ($c, $u1, $u2) = (1,ドル 2,ドル 3ドル);
+ my $rest = "U+" . $u1 . "+" . $u2 . 4ドル;
+ my $code = hex($c);
+ my $ucs1 = hex($u1);
+ my $ucs2 = hex($u2);
push @all, { direction => 'both',
ucs => $ucs1,
}
elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/)
{
- $c = 1ドル;
- $u = 2ドル;
- $rest = "U+" . $u . 3ドル;
- }
- else
- {
- next;
- }
-
- $ucs = hex($u);
- $code = hex($c);
+ # non-combined characters
+ my ($c, $u, $rest) = (1,ドル 2,ドル "U+" . 2ドル . 3ドル);
+ my $ucs = hex($u);
+ my $code = hex($c);
- next if ($code < 0x80 && $ucs < 0x80);
+ next if ($code < 0x80 && $ucs < 0x80);
- push @all, { direction => 'both', ucs => $ucs, code => $code, comment => $rest };
+ push @all, { direction => 'both', ucs => $ucs, code => $code, comment => $rest };
+ }
}
-close(FILE);
+close($in);
print_tables("EUC_JIS_2004", \@all, 1);
index 0e9dd292bff11c58df0000cd563cbc59c5b76229..1bfd3b850e0906b4f1041079438d37728eacaa2f 100755 (executable)
# organization's ftp site.
use strict;
-require "convutils.pm";
+require convutils;
# Load JIS0212.TXT
my $jis0212 = &read_source("JIS0212.TXT");
index a917d067172a25c53fad45a840b2f1f792e68474..dffcdc40ded63aa9500564f27113e99397d67a34 100755 (executable)
# UCS-2 code in hex
# # and Unicode name (not used in this script)
-require "convutils.pm";
+use strict;
+require convutils;
# Load the source file.
index aceef5433c28bd59590c164ec58019893957cbc1..cb81c4650d53fcb8a2f436f9411827ffdca4d616 100755 (executable)
# UCS-2 code in hex
# # and Unicode name (not used in this script)
-require "convutils.pm";
+use strict;
+require convutils;
my $mapping = &read_source("CNS11643.TXT");
index f58361024e4c67e375b25a11cf90728fb36cbdb8..7be4b7b0abebf3a4ff299f6138f26e61795f69bc 100755 (executable)
# where the "u" field is the Unicode code point in hex,
# and the "b" field is the hex byte sequence for GB18030
-require "convutils.pm";
+use strict;
+require convutils;
# Read the input
-$in_file = "gb-18030-2000.xml";
+my $in_file = "gb-18030-2000.xml";
-open(FILE, $in_file) || die("cannot open $in_file");
+open(my $in, '<', $in_file) || die("cannot open $in_file");
my @mapping;
-while (<FILE>)
+while (<$in>)
{
next if (!m/<a u="([0-9A-F]+)" b="([0-9A-F ]+)"/);
- $u = 1ドル;
- $c = 2ドル;
+ my ($u, $c) = (1,ドル 2ドル);
$c =~ s/ //g;
- $ucs = hex($u);
- $code = hex($c);
+ my $ucs = hex($u);
+ my $code = hex($c);
if ($code >= 0x80 && $ucs >= 0x0080)
{
push @mapping, {
}
}
}
-close(FILE);
+close($in);
print_tables("GB18030", \@mapping);
index b98f9a7bf55b56521eafb89e510e533fb76bd709..b249b81096cdc79de19a1bcbd819b729a299dd20 100755 (executable)
# UCS-2 code in hex
# # and Unicode name (not used in this script)
-require "convutils.pm";
+use strict;
+require convutils;
# Load the source file.
index 16a53ad1d9fa74d46f80f61de5c178db13efa775..6be56b5b526d640f80709e981ae276f3d3f2863b 100755 (executable)
# Generate UTF-8 <--> SHIFT_JIS_2004 code conversion tables from
# "sjis-0213-2004-std.txt" (http://x0213.org)
-require "convutils.pm";
+use strict;
+require convutils;
# first generate UTF-8 --> SHIFT_JIS_2004 table
-$in_file = "sjis-0213-2004-std.txt";
+my $in_file = "sjis-0213-2004-std.txt";
-open(FILE, $in_file) || die("cannot open $in_file");
+open(my $in, '<', $in_file) || die("cannot open $in_file");
my @mapping;
-while ($line = <FILE>)
+while (my $line = <$in>)
{
if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/)
{
- $c = 1ドル;
- $u1 =わ 2ドル;
- $u2 =わ 3ドル;
- $rest = "U+" . $u1 . "+" . $u2 . 4ドル;
- $code = hex($c);
- $ucs1 = hex($u1);
- $ucs2 = hex($u2);
+ # combined characters
+ my ($c, $u1, $u2) = (1,ドル 2,ドル 3ドル);
+ my $rest = "U+" . $u1 . "+" . $u2 . 4ドル;
+ my $code = hex($c);
+ my $ucs1 = hex($u1);
+ my $ucs2 = hex($u2);
push @mapping, {
code => $code,
}
elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/)
{
- $c = 1ドル;
- $u = 2ドル;
- $rest = "U+" . $u . 3ドル;
- }
- else
- {
- next;
- }
+ # non-combined characters
+ my ($c, $u, $rest) = (1,ドル 2,ドル "U+" . 2ドル . 3ドル);
+ my $ucs = hex($u);
+ my $code = hex($c);
+ my $direction;
- $ucs = hex($u);
- $code = hex($c);
+ if ($code < 0x80 && $ucs < 0x80)
+ {
+ next;
+ }
+ elsif ($code < 0x80)
+ {
+ $direction = 'from_unicode';
+ }
+ elsif ($ucs < 0x80)
+ {
+ $direction = 'to_unicode';
+ }
+ else
+ {
+ $direction = 'both';
+ }
- if ($code < 0x80 && $ucs < 0x80)
- {
- next;
- }
- elsif ($code < 0x80)
- {
- $direction = 'from_unicode';
- }
- elsif ($ucs < 0x80)
- {
- $direction = 'to_unicode';
- }
- else
- {
- $direction = 'both';
+ push @mapping, {
+ code => $code,
+ ucs => $ucs,
+ comment => $rest,
+ direction => $direction
+ };
}
-
- push @mapping, {
- code => $code,
- ucs => $ucs,
- comment => $rest,
- direction => $direction
- };
}
-close(FILE);
+close($in);
print_tables("SHIFT_JIS_2004", \@mapping, 1);
index c8ff712af8fd279349da855752bb848ee6101a6e..17289fc5e3efd21a5ae562fa4626da05df68d722 100755 (executable)
# ftp site.
use strict;
-require "convutils.pm";
+require convutils;
my $charset = read_source("CP932.TXT");
index b6bf3bd8f27aac6db57e678a6d088859b46e6164..667f6c177c77c189e05febf6671538cd8f493a01 100755 (executable)
# where the "u" field is the Unicode code point in hex,
# and the "b" field is the hex byte sequence for UHC
-require "convutils.pm";
+use strict;
+require convutils;
# Read the input
-$in_file = "windows-949-2000.xml";
+my $in_file = "windows-949-2000.xml";
-open(FILE, $in_file) || die("cannot open $in_file");
+open(my $in, '<', $in_file) || die("cannot open $in_file");
my @mapping;
-while (<FILE>)
+while (<$in>)
{
next if (!m/<a u="([0-9A-F]+)" b="([0-9A-F ]+)"/);
- $u = 1ドル;
- $c = 2ドル;
+ my ($u, $c) = (1,ドル 2ドル);
$c =~ s/ //g;
- $ucs = hex($u);
- $code = hex($c);
+ my $ucs = hex($u);
+ my $code = hex($c);
next if ($code == 0x0080 || $code == 0x00FF);
}
}
}
-close(FILE);
+close($in);
# One extra character that's not in the source file.
push @mapping, { direction => 'both', code => 0xa2e8, ucs => 0x327e, comment => 'CIRCLED HANGUL IEUNG U' };
index a3cf436eefd56708788d8ac18bb64fef67c85b9e..b3188f3709a9e36b8764d3bcbf321eb66b74b3a5 100755 (executable)
# UCS-2 code in hex
# # and Unicode name (not used in this script)
-require "convutils.pm";
+use strict;
+require convutils;
-%filename = (
+my %filename = (
'WIN866' => 'CP866.TXT',
'WIN874' => 'CP874.TXT',
'WIN1250' => 'CP1250.TXT',
'KOI8U' => 'KOI8-U.TXT',
'GBK' => 'CP936.TXT');
-@charsets = keys(%filename);
-@charsets = @ARGV if scalar(@ARGV);
-foreach $charset (@charsets)
+# make maps for all encodings if not specified
+my @charsets = (scalar(@ARGV) > 0) ? @ARGV : keys(%filename);
+
+foreach my $charset (@charsets)
{
my $mapping = &read_source($filename{$charset});