Cleanup for unicode-update build target and test.

In preparation for adding more Unicode tables.

Discussion: https://postgr.es/m/63cd8625-68fa-4760-844a-6b7f643336f2@ardentperf.com
Reviewed-by: Jeremy Schneider

Author: jeff-davis

src/common/unicode/Makefile

@@ -21,15 +21,15 @@ CPPFLAGS += $(ICU_CFLAGS)
 # By default, do nothing.
 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/
 	$(MAKE) category-check
 	$(MAKE) normalization-check
 
 # These files are part of the Unicode Character Database. Download
 # them on demand.  The dependency on Makefile.global is for
 # 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)
 
 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
 
 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

src/common/unicode/category_test.c

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

src/common/unicode/meson.build

@@ -11,7 +11,7 @@ endif
 
 # These files are part of the Unicode Character Database. Download them on
 # 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)
   target = custom_target(f,
     output: f,
@@ -24,15 +24,6 @@ endforeach
 
 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 += \
   custom_target('unicode_category_table.h',
     input: [unicode_data['UnicodeData.txt']],
@@ -44,14 +35,12 @@ update_unicode_targets += \
   )
 
 update_unicode_targets += \
-  custom_target('unicode_norm_table.h',
-    input: [unicode_data['UnicodeData.txt'], unicode_data['CompositionExclusions.txt']],
-    output: ['unicode_norm_table.h', 'unicode_norm_hashfunc.h'],
-    depend_files: perfect_hash_pm,
-    command: [
-      perl, files('generate-unicode_norm_table.pl'),
-      '--outdir', '@OUTDIR@', '@INPUT@'],
+  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 += \
@@ -65,12 +54,14 @@ update_unicode_targets += \
   )
 
 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@'],
+  custom_target('unicode_norm_table.h',
+    input: [unicode_data['UnicodeData.txt'], unicode_data['CompositionExclusions.txt']],
+    output: ['unicode_norm_table.h', 'unicode_norm_hashfunc.h'],
+    depend_files: perfect_hash_pm,
+    command: [
+      perl, files('generate-unicode_norm_table.pl'),
+      '--outdir', '@OUTDIR@', '@INPUT@'],
     build_by_default: false,
-    capture: true,
   )
 
 update_unicode_targets += \
@@ -83,6 +74,15 @@ update_unicode_targets += \
     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',
     input: [unicode_data['NormalizationTest.txt']],
     output: ['norm_test_table.h'],