database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-08-27 07:42:10 +03:00
Code Activity

Add support for other normal forms to Unicode normalization API

Browse Source 
It previously only supported NFKC, for use by SASLprep.  This expands
the API to offer the choice of all four normalization forms.  Right
now, there are no internal users of the forms other than NFKC.

Reviewed-by: Daniel Verite <daniel@manitou-mail.org>
Reviewed-by: Andreas Karlsson <andreas@proxel.se>
Discussion: https://www.postgresql.org/message-id/flat/c1909f27-c269-2ed9-12f8-3ab72c8caf7a@2ndquadrant.com
This commit is contained in:
Peter Eisentraut
2020-03-24 08:49:52 +01:00
parent cedffbdb8b
commit d40d564c5a
7 changed files with 3728 additions and 3703 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/common/unicode/generate-norm_test_table.pl
View File

@@ -48,7 +48,7 @@ typedef struct
{
int linenum;
pg_wchar input[50];
pg_wchar output[50];
pg_wchar output[4][50];
} pg_unicode_test;
/* test table */
@@ -89,13 +89,16 @@ while (my $line = <$INPUT>)
my ($source, $nfc, $nfd, $nfkc, $nfkd) = split(';', $line);
my $source_utf8 = codepoint_string_to_hex($source);
my $nfc_utf8 = codepoint_string_to_hex($nfc);
my $nfd_utf8 = codepoint_string_to_hex($nfd);
my $nfkc_utf8 = codepoint_string_to_hex($nfkc);
my $nfkd_utf8 = codepoint_string_to_hex($nfkd);
print $OUTPUT "\t{ $linenum, { $source_utf8 }, { $nfkc_utf8 } },\n";
print $OUTPUT "\t{ $linenum, { $source_utf8 }, { { $nfc_utf8 }, { $nfd_utf8 }, { $nfkc_utf8 }, { $nfkd_utf8 } } },\n";
}
# Output terminator entry
print $OUTPUT "\t{ 0, { 0 }, { 0 } }";
print $OUTPUT "\t{ 0, { 0 }, { { 0 }, { 0 }, { 0 }, { 0 } } }";
print $OUTPUT "\n};\n";
close $OUTPUT;