Change mbbisearch to return the character range

j-naylor · j-naylor · commit 78ab944cd4b9 · 2021-08-25T13:08:11.000-04:00
Add a width field to mbinterval and have mbbisearch return a pointer to the found range rather than just bool for success. A future commit will add another width besides zero, and this will allow that to use the same search. Reviewed by Jacob Champion Discussion: https://www.postgresql.org/message-id/CAFBsxsGOCpzV7c-f3a8ADsA1n4uZ%3D8puCctQp%2Bx7W0vgkv%3Dw%2Bg%40mail.gmail.com
diff --git a/src/common/unicode/generate-unicode_width_table.pl b/src/common/unicode/generate-unicode_width_table.pl
@@ -17,7 +17,7 @@
 print
   "/* generated by src/common/unicode/generate-unicode_width_table.pl, do not edit */\n\n";
 
-print "static const struct mbinterval combining[] = {\n";
+print "static const struct mbinterval wcwidth[] = {\n";
 
 foreach my $line (<ARGV>)
 {
@@ -40,7 +40,7 @@
 		# not a combining character, print out previous range if any
 		if (defined($range_start))
 		{
-			printf "\t{0x%04X, 0x%04X},\n", $range_start, $prev_codepoint;
+			printf "\t{0x%04X, 0x%04X, 0},\n", $range_start, $prev_codepoint;
 			$range_start = undef;
 		}
 	}
diff --git a/src/common/wchar.c b/src/common/wchar.c
@@ -585,17 +585,18 @@ struct mbinterval
 {
 	unsigned short first;
 	unsigned short last;
+	signed int	width;
 };
 
 /* auxiliary function for binary search in interval table */
-static int
+static const struct mbinterval *
 mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
 {
 	int			min = 0;
 	int			mid;
 
 	if (ucs < table[0].first || ucs > table[max].last)
-		return 0;
+		return NULL;
 	while (max >= min)
 	{
 		mid = (min + max) / 2;
@@ -604,10 +605,10 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
 		else if (ucs < table[mid].first)
 			max = mid - 1;
 		else
-			return 1;
+			return &table[mid];
 	}
 
-	return 0;
+	return NULL;
 }
 
 
@@ -646,17 +647,21 @@ ucs_wcwidth(pg_wchar ucs)
 {
 #include "common/unicode_width_table.h"
 
+	const struct mbinterval *range;
+
 	/* test for 8-bit control characters */
 	if (ucs == 0)
 		return 0;
 
 	if (ucs < 0x20 || (ucs >= 0x7f && ucs < 0xa0) || ucs > 0x0010ffff)
 		return -1;
 
-	/* binary search in table of non-spacing characters */
-	if (mbbisearch(ucs, combining,
-				   sizeof(combining) / sizeof(struct mbinterval) - 1))
-		return 0;
+	/* binary search in table of character widths */
+	range = mbbisearch(ucs, wcwidth,
+					   sizeof(wcwidth) / sizeof(struct mbinterval) - 1);
+
+	if (range != NULL)
+		return range->width;
 
 	/*
 	 * if we arrive here, ucs is not a combining or C0/C1 control character
diff --git a/src/include/common/unicode_width_table.h b/src/include/common/unicode_width_table.h

Original file line number	Diff line number	Diff line change
`@@ -17,7 +17,7 @@`
`17`	`17`	`print`
`18`	`18`	`"/* generated by src/common/unicode/generate-unicode_width_table.pl, do not edit */\n\n";`
`19`	`19`
`20`		`-print "static const struct mbinterval combining[] = {\n";`
	`20`	`+print "static const struct mbinterval wcwidth[] = {\n";`
`21`	`21`
`22`	`22`	`foreach my $line (<ARGV>)`
`23`	`23`	`{`
`@@ -40,7 +40,7 @@`
`40`	`40`	`# not a combining character, print out previous range if any`
`41`	`41`	`if (defined($range_start))`
`42`	`42`	`{`
`43`		`- printf "\t{0x%04X, 0x%04X},\n", $range_start, $prev_codepoint;`
	`43`	`+ printf "\t{0x%04X, 0x%04X, 0},\n", $range_start, $prev_codepoint;`
`44`	`44`	`$range_start = undef;`
`45`	`45`	`}`
`46`	`46`	`}`