| 1 |
#!/usr/bin/perl |
| 2 |
|
| 3 |
################################################################################# |
| 4 |
# Author: Serge Kozlov # |
| 5 |
# Date: 09/21/2005 # |
| 6 |
# Purpose: The script produces a text file ../data/charset_utf8.txt # |
| 7 |
# in UTF8 format. Each line contains one UTF8 character # |
| 8 |
# between 20 and 07FF # |
| 9 |
################################################################################# |
| 10 |
|
| 11 |
genfile("../data/charset_utf8.txt", 33, 2047, "utf8"); |
| 12 |
genfile(">../data/charset_utf8.txt", 19968, 20479,"utf8"); |
| 13 |
|
| 14 |
|
| 15 |
#genfile("../data/charset_utf8.txt", 33, 2047, "utf8"); |
| 16 |
|
| 17 |
sub genfile ($$$$) |
| 18 |
{ |
| 19 |
my $fn = shift; |
| 20 |
my $i_from = shift; |
| 21 |
my $i_to = shift; |
| 22 |
my $typ = shift; |
| 23 |
open F, ">$fn"; |
| 24 |
for ($i = $i_from; $i <= $i_to; $i++) |
| 25 |
{ |
| 26 |
if (($i > 32) && ($i < 65533) && ($i != 65279)) |
| 27 |
{ |
| 28 |
if ($typ eq "utf8") |
| 29 |
{ |
| 30 |
if ($i < 128) |
| 31 |
{ |
| 32 |
print F pack("C", $i), "\n"; |
| 33 |
} |
| 34 |
elsif (($i > 127) && ($i < 2048)) |
| 35 |
{ |
| 36 |
$b1 = (($i & 1984) >> 6) + 192; |
| 37 |
$b2 = ($i & 63) + 128; |
| 38 |
print F pack("C", $b1); |
| 39 |
print F pack("C", $b2), "\n"; |
| 40 |
} |
| 41 |
else |
| 42 |
{ |
| 43 |
$b1 = (($i & 61440) >> 12) + 224; |
| 44 |
$b2 = (($i & 4032) >> 6) + 128; |
| 45 |
$b3 = ($i & 63) + 128; |
| 46 |
print F pack("C", $b1); |
| 47 |
print F pack("C", $b2); |
| 48 |
print F pack("C", $b3), "\n"; |
| 49 |
} |
| 50 |
} |
| 51 |
elsif ($typ eq "ucs2") |
| 52 |
{ |
| 53 |
print F pack("C", 0); |
| 54 |
print F pack("C", $i); |
| 55 |
print F pack("C", 0), "\n"; |
| 56 |
} |
| 57 |
} |
| 58 |
} |
| 59 |
close F; |
| 60 |
} |