Shrink Unicode category table.

jeff-davis · jeff-davis · commit 719b342d36ce · 2023-12-07T15:44:03.000-08:00
Missing entries can implicitly be considered "unassigned". Discussion: https://postgr.es/m/ff4c2f2f9c8fc7ca27c1c24ae37ecaeaeaff6b53.camel@j-davis.com
diff --git a/src/common/unicode/generate-unicode_category_table.pl b/src/common/unicode/generate-unicode_category_table.pl
@@ -72,15 +72,21 @@
 	# the current range, emit the current range and initialize a new
 	# range representing the gap.
 	if ($range_end + 1 != $code && $range_category ne $gap_category) {
-		push(@category_ranges, {start => $range_start, end => $range_end, category => $range_category});
+		if ($range_category ne $CATEGORY_UNASSIGNED) {
+			push(@category_ranges, {start => $range_start, end => $range_end,
+									category => $range_category});
+		}
 		$range_start = $range_end + 1;
 		$range_end = $code - 1;
 		$range_category = $gap_category;
 	}
 
 	# different category; new range
 	if ($range_category ne $category) {
-		push(@category_ranges, {start => $range_start, end => $range_end, category => $range_category});
+		if ($range_category ne $CATEGORY_UNASSIGNED) {
+			push(@category_ranges, {start => $range_start, end => $range_end,
+									category => $range_category});
+		}
 		$range_start = $code;
 		$range_end = $code;
 		$range_category = $category;
@@ -109,14 +115,9 @@
   if $gap_category ne $CATEGORY_UNASSIGNED;
 
 # emit final range
-push(@category_ranges, {start => $range_start, end => $range_end, category => $range_category});
-
-# emit range for any unassigned code points after last entry
-if ($range_end < 0x10FFFF) {
-	$range_start = $range_end + 1;
-	$range_end = 0x10FFFF;
-	$range_category = $CATEGORY_UNASSIGNED;
-	push(@category_ranges, {start => $range_start, end => $range_end, category => $range_category});
+if ($range_category ne $CATEGORY_UNASSIGNED) {
+	push(@category_ranges, {start => $range_start, end => $range_end,
+							category => $range_category});
 }
 
 my $num_ranges = scalar @category_ranges;
diff --git a/src/common/unicode_category.c b/src/common/unicode_category.c
@@ -28,8 +28,7 @@ unicode_category(pg_wchar ucs)
 	int			mid;
 	int			max = lengthof(unicode_categories) - 1;
 
-	Assert(ucs >= unicode_categories[0].first &&
-		   ucs <= unicode_categories[max].last);
+	Assert(ucs <= 0x10ffff);
 
 	while (max >= min)
 	{
@@ -42,8 +41,7 @@ unicode_category(pg_wchar ucs)
 			return unicode_categories[mid].category;
 	}
 
-	Assert(false);
-	return (pg_unicode_category) - 1;
+	return PG_U_UNASSIGNED;
 }
 
 /*
diff --git a/src/include/common/unicode_category_table.h b/src/include/common/unicode_category_table.h

Original file line number	Diff line number	Diff line change
`@@ -28,8 +28,7 @@ unicode_category(pg_wchar ucs)`
`28`	`28`	`int mid;`
`29`	`29`	`int max = lengthof(unicode_categories) - 1;`
`30`	`30`
`31`		`- Assert(ucs >= unicode_categories[0].first &&`
`32`		`- ucs <= unicode_categories[max].last);`
	`31`	`+ Assert(ucs <= 0x10ffff);`
`33`	`32`
`34`	`33`	`while (max >= min)`
`35`	`34`	`{`
`@@ -42,8 +41,7 @@ unicode_category(pg_wchar ucs)`
`42`	`41`	`return unicode_categories[mid].category;`
`43`	`42`	`}`
`44`	`43`
`45`		`- Assert(false);`
`46`		`- return (pg_unicode_category) - 1;`
	`44`	`+ return PG_U_UNASSIGNED;`
`47`	`45`	`}`
`48`	`46`
`49`	`47`	`/*`