mirrors/postgres
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Cleanup for unicode-update build target and test.

Browse Source 
In preparation for adding more Unicode tables.

Discussion: https://postgr.es/m/63cd8625-68fa-4760-844a-6b7f643336f2@ardentperf.com
Reviewed-by: Jeremy Schneider
This commit is contained in:
Jeff Davis 2024-01-11 12:20:25 -08:00
parent 29f114b6ff
commit cf64d4e99f
3 changed files with 44 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/common/unicode/Makefile
View File

@ -21,7 +21,7 @@ CPPFLAGS += $(ICU_CFLAGS)
# By default, do nothing. # By default, do nothing.
all: all:
update-unicode: unicode_category_table.h unicode_norm_table.h unicode_nonspacing_table.h unicode_east_asian_fw_table.h unicode_normprops_table.h unicode_norm_hashfunc.h unicode_version.h update-unicode: unicode_category_table.h unicode_east_asian_fw_table.h unicode_nonspacing_table.h unicode_norm_hashfunc.h unicode_norm_table.h unicode_normprops_table.h unicode_version.h
mv $^ $(top_srcdir)/src/include/common/ mv $^ $(top_srcdir)/src/include/common/
$(MAKE) category-check $(MAKE) category-check
$(MAKE) normalization-check $(MAKE) normalization-check
@ -29,7 +29,7 @@ update-unicode: unicode_category_table.h unicode_norm_table.h unicode_nonspacing
# These files are part of the Unicode Character Database. Download # These files are part of the Unicode Character Database. Download
# them on demand. The dependency on Makefile.global is for # them on demand. The dependency on Makefile.global is for
# UNICODE_VERSION. # UNICODE_VERSION.
UnicodeData.txt EastAsianWidth.txt DerivedNormalizationProps.txt CompositionExclusions.txt NormalizationTest.txt: $(top_builddir)/src/Makefile.global CompositionExclusions.txt DerivedNormalizationProps.txt EastAsianWidth.txt NormalizationTest.txt UnicodeData.txt: $(top_builddir)/src/Makefile.global
$(DOWNLOAD) https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/$(@F) $(DOWNLOAD) https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/$(@F)
unicode_version.h: generate-unicode_version.pl unicode_version.h: generate-unicode_version.pl
@ -82,4 +82,4 @@ clean:
rm -f $(OBJS) category_test category_test.o norm_test norm_test.o rm -f $(OBJS) category_test category_test.o norm_test norm_test.o
distclean: clean distclean: clean
rm -f UnicodeData.txt EastAsianWidth.txt CompositionExclusions.txt NormalizationTest.txt norm_test_table.h unicode_norm_table.h rm -f CompositionExclusions.txt DerivedNormalizationProps.txt EastAsianWidth.txt NormalizationTest.txt UnicodeData.txt norm_test_table.h unicode_category_table.h unicode_norm_table.h

24
src/common/unicode/category_test.c
View File

@ -28,9 +28,9 @@
static int static int
parse_unicode_version(const char *version) parse_unicode_version(const char *version)
{ {
int n, int n PG_USED_FOR_ASSERTS_ONLY;
major, int major;
minor; int minor;
n = sscanf(version, "%d.%d", &major, &minor); n = sscanf(version, "%d.%d", &major, &minor);
@ -54,8 +54,8 @@ main(int argc, char **argv)
int pg_skipped_codepoints = 0; int pg_skipped_codepoints = 0;
int icu_skipped_codepoints = 0; int icu_skipped_codepoints = 0;
printf("Postgres Unicode Version:\t%s\n", PG_UNICODE_VERSION); printf("category_test: Postgres Unicode version:\t%s\n", PG_UNICODE_VERSION);
printf("ICU Unicode Version:\t\t%s\n", U_UNICODE_VERSION); printf("category_test: ICU Unicode version:\t\t%s\n", U_UNICODE_VERSION);
for (UChar32 code = 0; code <= 0x10ffff; code++) for (UChar32 code = 0; code <= 0x10ffff; code++)
{ {
@ -79,11 +79,11 @@ main(int argc, char **argv)
icu_skipped_codepoints++; icu_skipped_codepoints++;
else else
{ {
printf("FAILURE for codepoint %06x\n", code); printf("category_test: FAILURE for codepoint 0x%06x\n", code);
printf("Postgres category: %02d %s %s\n", pg_category, printf("category_test: Postgres category: %02d %s %s\n", pg_category,
unicode_category_abbrev(pg_category), unicode_category_abbrev(pg_category),
unicode_category_string(pg_category)); unicode_category_string(pg_category));
printf("ICU category: %02d %s %s\n", icu_category, printf("category_test: ICU category: %02d %s %s\n", icu_category,
unicode_category_abbrev(icu_category), unicode_category_abbrev(icu_category),
unicode_category_string(icu_category)); unicode_category_string(icu_category));
printf("\n"); printf("\n");
@ -93,16 +93,16 @@ main(int argc, char **argv)
} }
if (pg_skipped_codepoints > 0) if (pg_skipped_codepoints > 0)
printf("Skipped %d codepoints unassigned in Postgres due to Unicode version mismatch.\n", printf("category_test: skipped %d codepoints unassigned in Postgres due to Unicode version mismatch\n",
pg_skipped_codepoints); pg_skipped_codepoints);
if (icu_skipped_codepoints > 0) if (icu_skipped_codepoints > 0)
printf("Skipped %d codepoints unassigned in ICU due to Unicode version mismatch.\n", printf("category_test: skipped %d codepoints unassigned in ICU due to Unicode version mismatch\n",
icu_skipped_codepoints); icu_skipped_codepoints);
printf("category_test: All tests successful!\n"); printf("category_test: success\n");
exit(0); exit(0);
#else #else
printf("ICU support required for test; skipping.\n"); printf("category_test: ICU support required for test; skipping\n");
exit(0); exit(0);
#endif #endif
} }

58
src/common/unicode/meson.build
View File

@ -11,7 +11,7 @@ endif
# These files are part of the Unicode Character Database. Download them on # These files are part of the Unicode Character Database. Download them on
# demand. # demand.
foreach f : ['UnicodeData.txt', 'EastAsianWidth.txt', 'DerivedNormalizationProps.txt', 'CompositionExclusions.txt', 'NormalizationTest.txt'] foreach f : ['CompositionExclusions.txt', 'DerivedNormalizationProps.txt', 'EastAsianWidth.txt', 'NormalizationTest.txt', 'UnicodeData.txt']
url = unicode_baseurl.format(UNICODE_VERSION, f) url = unicode_baseurl.format(UNICODE_VERSION, f)
target = custom_target(f, target = custom_target(f,
output: f, output: f,
@ -24,15 +24,6 @@ endforeach
update_unicode_targets = [] update_unicode_targets = []
update_unicode_targets += \
custom_target('unicode_version.h',
output: ['unicode_version.h'],
command: [
perl, files('generate-unicode_version.pl'),
'--outdir', '@OUTDIR@', '--version', UNICODE_VERSION],
build_by_default: false,
)
update_unicode_targets += \ update_unicode_targets += \
custom_target('unicode_category_table.h', custom_target('unicode_category_table.h',
input: [unicode_data['UnicodeData.txt']], input: [unicode_data['UnicodeData.txt']],
@ -43,6 +34,25 @@ update_unicode_targets += \
build_by_default: false, build_by_default: false,
) )
update_unicode_targets += \
custom_target('unicode_east_asian_fw_table.h',
input: [unicode_data['EastAsianWidth.txt']],
output: ['unicode_east_asian_fw_table.h'],
command: [perl, files('generate-unicode_east_asian_fw_table.pl'), '@INPUT@'],
build_by_default: false,
capture: true,
)
update_unicode_targets += \
custom_target('unicode_nonspacing_table.h',
input: [unicode_data['UnicodeData.txt']],
output: ['unicode_nonspacing_table.h'],
depend_files: perfect_hash_pm,
command: [perl, files('generate-unicode_nonspacing_table.pl'), '@INPUT@'],
build_by_default: false,
capture: true,
)
update_unicode_targets += \ update_unicode_targets += \
custom_target('unicode_norm_table.h', custom_target('unicode_norm_table.h',
input: [unicode_data['UnicodeData.txt'], unicode_data['CompositionExclusions.txt']], input: [unicode_data['UnicodeData.txt'], unicode_data['CompositionExclusions.txt']],
@ -54,25 +64,6 @@ update_unicode_targets += \
build_by_default: false, build_by_default: false,
) )
update_unicode_targets += \
custom_target('unicode_nonspacing_table.h',
input: [unicode_data['UnicodeData.txt']],
output: ['unicode_nonspacing_table.h'],
depend_files: perfect_hash_pm,
command: [perl, files('generate-unicode_nonspacing_table.pl'), '@INPUT@'],
build_by_default: false,
capture: true,
)
update_unicode_targets += \
custom_target('unicode_east_asian_fw_table.h',
input: [unicode_data['EastAsianWidth.txt']],
output: ['unicode_east_asian_fw_table.h'],
command: [perl, files('generate-unicode_east_asian_fw_table.pl'), '@INPUT@'],
build_by_default: false,
capture: true,
)
update_unicode_targets += \ update_unicode_targets += \
custom_target('unicode_normprops_table.h', custom_target('unicode_normprops_table.h',
input: [unicode_data['DerivedNormalizationProps.txt']], input: [unicode_data['DerivedNormalizationProps.txt']],
@ -83,6 +74,15 @@ update_unicode_targets += \
capture: true, capture: true,
) )
update_unicode_targets += \
custom_target('unicode_version.h',
output: ['unicode_version.h'],
command: [
perl, files('generate-unicode_version.pl'),
'--outdir', '@OUTDIR@', '--version', UNICODE_VERSION],
build_by_default: false,
)
norm_test_table = custom_target('norm_test_table.h', norm_test_table = custom_target('norm_test_table.h',
input: [unicode_data['NormalizationTest.txt']], input: [unicode_data['NormalizationTest.txt']],
output: ['norm_test_table.h'], output: ['norm_test_table.h'],