mirror of
https://github.com/postgres/postgres.git
synced 2025-09-05 02:22:28 +03:00
f85a485f89
We currently have several sets of files generated from data provided
by Unicode. These all have ad hoc rules and instructions for updating
when new Unicode versions appear, and it's not done consistently.
This patch centralizes and automates the process and makes it part of
the release checklist. The Unicode and CLDR versions are specified in
Makefile.global.in. There is a new make target "update-unicode" that
downloads all the relevant files and runs the generation script.
There is also a new script for generating the table of combining
characters for ucs_wcwidth(). That table is now in a separate include
file rather than hardcoded into the middle of other code. This is
based on the script that was used for generating
d8594d123c, but the script itself wasn't
committed at that time.
Reviewed-by: John Naylor <john.naylor@2ndquadrant.com>
Discussion: https://www.postgresql.org/message-id/flat/c8d05f42-443e-6c23-819b-05b31759a37c@2ndquadrant.com
53 lines
1.2 KiB
Perl
53 lines
1.2 KiB
Perl
#!/usr/bin/perl
|
|
#
|
|
# Generate sorted list of non-overlapping intervals of non-spacing
|
|
# characters, using Unicode data files as input. Pass UnicodeData.txt
|
|
# as argument. The output is on stdout.
|
|
#
|
|
# Copyright (c) 2019, PostgreSQL Global Development Group
|
|
|
|
use strict;
|
|
use warnings;
|
|
|
|
my $range_start = undef;
|
|
my $codepoint;
|
|
my $prev_codepoint;
|
|
my $count = 0;
|
|
|
|
print "/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */\n\n";
|
|
|
|
print "static const struct mbinterval combining[] = {\n";
|
|
|
|
foreach my $line (<ARGV>)
|
|
{
|
|
chomp $line;
|
|
my @fields = split ';', $line;
|
|
$codepoint = hex $fields[0];
|
|
|
|
next if $codepoint > 0xFFFF;
|
|
|
|
if ($fields[2] eq 'Me' || $fields[2] eq 'Mn')
|
|
{
|
|
# combining character, save for start of range
|
|
if (!defined($range_start))
|
|
{
|
|
$range_start = $codepoint;
|
|
}
|
|
}
|
|
else
|
|
{
|
|
# not a combining character, print out previous range if any
|
|
if (defined($range_start))
|
|
{
|
|
printf "\t{0x%04X, 0x%04X},\n", $range_start, $prev_codepoint;
|
|
$range_start = undef;
|
|
}
|
|
}
|
|
}
|
|
continue
|
|
{
|
|
$prev_codepoint = $codepoint;
|
|
}
|
|
|
|
print "};\n";
|