diff options
| author | John Naylor | 2022-09-13 09:13:33 +0000 |
|---|---|---|
| committer | John Naylor | 2022-09-13 09:13:33 +0000 |
| commit | 0bd9c629732375e21d3ca6fba16c4a6a2808411a (patch) | |
| tree | 1cdbc6743a69559f62755232d550a7fc9534731b /src/common/unicode | |
| parent | bb629c294bea533884a379eee5f8ed6307c17bf2 (diff) | |
Treat Unicode codepoints of category "Format" as non-spacing
Commit d8594d123 updated the list of non-spacing codepoints used
for calculating display width, but in doing so inadvertently removed
some, since the script used for that commit only considered combining
characters.
For complete coverage for zero-width characters, include codepoints in
the category Cf (Format). To reflect the wider purpose, also rename files
and update comments that referred specifically to combining characters.
Some of these ranges have been missing since v12, but due to lack of
field complaints it was determined not important enough to justify adding
special-case logic the backbranches.
Kyotaro Horiguchi
Report by Pavel Stehule
Discussion: https://www.postgresql.org/message-id/flat/CAFj8pRBE8yvpQ0FSkPCoe0Ny1jAAsAQ6j3qMgVwWvkqAoaaNmQ%40mail.gmail.com
Diffstat (limited to 'src/common/unicode')
| -rw-r--r-- | src/common/unicode/Makefile | 4 | ||||
| -rw-r--r-- | src/common/unicode/generate-unicode_nonspacing_table.pl (renamed from src/common/unicode/generate-unicode_combining_table.pl) | 12 |
2 files changed, 9 insertions, 7 deletions
diff --git a/src/common/unicode/Makefile b/src/common/unicode/Makefile index 60e01e748f8..382da476cf9 100644 --- a/src/common/unicode/Makefile +++ b/src/common/unicode/Makefile @@ -18,7 +18,7 @@ LIBS += $(PTHREAD_LIBS) # By default, do nothing. all: -update-unicode: unicode_norm_table.h unicode_combining_table.h unicode_east_asian_fw_table.h unicode_normprops_table.h unicode_norm_hashfunc.h +update-unicode: unicode_norm_table.h unicode_nonspacing_table.h unicode_east_asian_fw_table.h unicode_normprops_table.h unicode_norm_hashfunc.h mv $^ $(top_srcdir)/src/include/common/ $(MAKE) normalization-check @@ -35,7 +35,7 @@ unicode_norm_hashfunc.h: unicode_norm_table.h unicode_norm_table.h: generate-unicode_norm_table.pl UnicodeData.txt CompositionExclusions.txt $(PERL) $< -unicode_combining_table.h: generate-unicode_combining_table.pl UnicodeData.txt +unicode_nonspacing_table.h: generate-unicode_nonspacing_table.pl UnicodeData.txt $(PERL) $^ >$@ unicode_east_asian_fw_table.h: generate-unicode_east_asian_fw_table.pl EastAsianWidth.txt diff --git a/src/common/unicode/generate-unicode_combining_table.pl b/src/common/unicode/generate-unicode_nonspacing_table.pl index 8177c20260b..3161eed4a26 100644 --- a/src/common/unicode/generate-unicode_combining_table.pl +++ b/src/common/unicode/generate-unicode_nonspacing_table.pl @@ -15,9 +15,9 @@ my $prev_codepoint; my $count = 0; print - "/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */\n\n"; + "/* generated by src/common/unicode/generate-unicode_nonspacing_table.pl, do not edit */\n\n"; -print "static const struct mbinterval combining[] = {\n"; +print "static const struct mbinterval nonspacing[] = {\n"; foreach my $line (<ARGV>) { @@ -25,9 +25,11 @@ foreach my $line (<ARGV>) my @fields = split ';', $line; $codepoint = hex $fields[0]; - if ($fields[2] eq 'Me' || $fields[2] eq 'Mn') + # Me and Mn refer to combining characters + # Cf refers to format characters + if ($fields[2] eq 'Me' || $fields[2] eq 'Mn' || $fields[2] eq 'Cf') { - # combining character, save for start of range + # non-spacing character, save for start of range if (!defined($range_start)) { $range_start = $codepoint; @@ -35,7 +37,7 @@ foreach my $line (<ARGV>) } else { - # not a combining character, print out previous range if any + # not a non-spacing character, print out previous range if any if (defined($range_start)) { printf "\t{0x%04X, 0x%04X},\n", $range_start, $prev_codepoint; |