From 5bc429aacb3722e55638a776332eebfa88dd60e5 Mon Sep 17 00:00:00 2001 From: John Naylor Date: Thu, 26 Aug 2021 13:07:34 -0400 Subject: Extend collection of Unicode combining characters to beyond the BMP The former limit was perhaps a carryover from an older hand-coded table. Since commit bab982161 we have enough space in mbinterval to store larger codepoints, so collect all combining characters. Discussion: https://www.postgresql.org/message-id/49ad1fa0-174e-c901-b14c-c484b60907f1%40enterprisedb.com --- src/common/unicode/generate-unicode_combining_table.pl | 2 -- 1 file changed, 2 deletions(-) (limited to 'src/common/unicode/generate-unicode_combining_table.pl') diff --git a/src/common/unicode/generate-unicode_combining_table.pl b/src/common/unicode/generate-unicode_combining_table.pl index 86aed789070..093a802f5f9 100644 --- a/src/common/unicode/generate-unicode_combining_table.pl +++ b/src/common/unicode/generate-unicode_combining_table.pl @@ -25,8 +25,6 @@ foreach my $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 -- cgit v1.2.3