mirror/postgresql
2
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2025-01-24 18:55:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Make all unicode perl scripts to use strict, rearrange logic for clarity.

Browse Source 
The loops were a bit difficult to understand, due to breaking out of them
early. Also fix things that perlcritic complained about.

Daniel Gustafsson
This commit is contained in:
Heikki Linnakangas 2016-11-30 18:06:34 +02:00
parent 81c52728f8
commit 021d254d9a
12 changed files with 103 additions and 109 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/backend/utils/mb/Unicode/UCS_to_BIG5.pl
View File

@ -24,8 +24,8 @@
# 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");

18
src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl
View File

@ -13,24 +13,24 @@
# 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;
$c = $2;
my ($u, $c) = ($1, $2);
$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
@ -71,6 +71,6 @@ while (<FILE>)
direction => 'both'
}
}
close(FILE);
close($in);
print_tables("EUC_CN", \@mapping);

46
src/backend/utils/mb/Unicode/UCS_to_EUC_JIS_2004.pl
View File

@ -7,27 +7,27 @@
# 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;
$u1 = $2;
$u2 = $3;
$rest = "U+" . $u1 . "+" . $u2 . $4;
$code = hex($c);
$ucs1 = hex($u1);
$ucs2 = hex($u2);
# combined characters
my ($c, $u1, $u2) = ($1, $2, $3);
my $rest = "U+" . $u1 . "+" . $u2 . $4;
my $code = hex($c);
my $ucs1 = hex($u1);
my $ucs2 = hex($u2);
push @all, { direction => 'both',
ucs => $ucs1,
@ -38,22 +38,16 @@ while ($line = <FILE>)
}
elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/)
{
$c = $1;
$u = $2;
$rest = "U+" . $u . $3;
# non-combined characters
my ($c, $u, $rest) = ($1, $2, "U+" . $2 . $3);
my $ucs = hex($u);
my $code = hex($c);
next if ($code < 0x80 && $ucs < 0x80);
push @all, { direction => 'both', ucs => $ucs, code => $code, comment => $rest };
}
else
{
next;
}
$ucs = hex($u);
$code = hex($c);
next if ($code < 0x80 && $ucs < 0x80);
push @all, { direction => 'both', ucs => $ucs, code => $code, comment => $rest };
}
close(FILE);
close($in);
print_tables("EUC_JIS_2004", \@all, 1);

2
src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl
View File

@ -12,7 +12,7 @@
# organization's ftp site.
use strict;
require "convutils.pm";
require convutils;
# Load JIS0212.TXT
my $jis0212 = &read_source("JIS0212.TXT");

3
src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl
View File

@ -16,7 +16,8 @@
# UCS-2 code in hex
# # and Unicode name (not used in this script)
require "convutils.pm";
use strict;
require convutils;
# Load the source file.

3
src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl
View File

@ -17,7 +17,8 @@
# 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");

18
src/backend/utils/mb/Unicode/UCS_to_GB18030.pl
View File

@ -13,24 +13,24 @@
# 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;
$c = $2;
my ($u, $c) = ($1, $2);
$c =~ s/ //g;
$ucs = hex($u);
$code = hex($c);
my $ucs = hex($u);
my $code = hex($c);
if ($code >= 0x80 && $ucs >= 0x0080)
{
push @mapping, {
@ -40,6 +40,6 @@ while (<FILE>)
}
}
}
close(FILE);
close($in);
print_tables("GB18030", \@mapping);

3
src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl
View File

@ -15,7 +15,8 @@
# UCS-2 code in hex
# # and Unicode name (not used in this script)
require "convutils.pm";
use strict;
require convutils;
# Load the source file.

83
src/backend/utils/mb/Unicode/UCS_to_SHIFT_JIS_2004.pl
View File

@ -7,27 +7,27 @@
# 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;
$u1 = $2;
$u2 = $3;
$rest = "U+" . $u1 . "+" . $u2 . $4;
$code = hex($c);
$ucs1 = hex($u1);
$ucs2 = hex($u2);
# combined characters
my ($c, $u1, $u2) = ($1, $2, $3);
my $rest = "U+" . $u1 . "+" . $u2 . $4;
my $code = hex($c);
my $ucs1 = hex($u1);
my $ucs2 = hex($u2);
push @mapping, {
code => $code,
@ -40,42 +40,37 @@ while ($line = <FILE>)
}
elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/)
{
$c = $1;
$u = $2;
$rest = "U+" . $u . $3;
}
else
{
next;
}
# non-combined characters
my ($c, $u, $rest) = ($1, $2, "U+" . $2 . $3);
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;
push @mapping, {
code => $code,
ucs => $ucs,
comment => $rest,
direction => $direction
};
}
elsif ($code < 0x80)
{
$direction = 'from_unicode';
}
elsif ($ucs < 0x80)
{
$direction = 'to_unicode';
}
else
{
$direction = 'both';
}
push @mapping, {
code => $code,
ucs => $ucs,
comment => $rest,
direction => $direction
};
}
close(FILE);
close($in);
print_tables("SHIFT_JIS_2004", \@mapping, 1);

2
src/backend/utils/mb/Unicode/UCS_to_SJIS.pl
View File

@ -11,7 +11,7 @@
# ftp site.
use strict;
require "convutils.pm";
require convutils;
my $charset = read_source("CP932.TXT");

18
src/backend/utils/mb/Unicode/UCS_to_UHC.pl
View File

@ -13,24 +13,24 @@
# 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;
$c = $2;
my ($u, $c) = ($1, $2);
$c =~ s/ //g;
$ucs = hex($u);
$code = hex($c);
my $ucs = hex($u);
my $code = hex($c);
next if ($code == 0x0080 || $code == 0x00FF);
@ -43,7 +43,7 @@ while (<FILE>)
}
}
}
close(FILE);
close($in);
# One extra character that's not in the source file.
push @mapping, { direction => 'both', code => 0xa2e8, ucs => 0x327e, comment => 'CIRCLED HANGUL IEUNG U' };

12
src/backend/utils/mb/Unicode/UCS_to_most.pl
View File

@ -15,9 +15,10 @@
# 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',
@ -46,9 +47,10 @@ require "convutils.pm";
'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});