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

4 files changed, 34 insertions, 23 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;
diff --git a/src/common/wchar.c b/src/common/wchar.c
index fa8854d9e9f..3b3fc53009f 100644
--- a/src/common/wchar.c
+++ b/src/common/wchar.c
@@ -620,7 +620,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
  *		value of -1.
  *
  *	  - Non-spacing and enclosing combining characters (general
- *		category code Mn or Me in the Unicode database) have a
+ *		category code Mn, Me or Cf in the Unicode database) have a
  *		column width of 0.
  *
  *	  - Spacing characters in the East Asian Wide (W) or East Asian
@@ -638,7 +638,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
 static int
 ucs_wcwidth(pg_wchar ucs)
 {
-#include "common/unicode_combining_table.h"
+#include "common/unicode_nonspacing_table.h"
 #include "common/unicode_east_asian_fw_table.h"
 
 	/* test for 8-bit control characters */
@@ -657,8 +657,8 @@ ucs_wcwidth(pg_wchar ucs)
 	 * factor for display width leads to the correct behavior, so do that
 	 * search first.
 	 */
-	if (mbbisearch(ucs, combining,
-				   sizeof(combining) / sizeof(struct mbinterval) - 1))
+	if (mbbisearch(ucs, nonspacing,
+				   sizeof(nonspacing) / sizeof(struct mbinterval) - 1))
 		return 0;
 
 	/* binary search in table of wide characters */
diff --git a/src/include/common/unicode_combining_table.h b/src/include/common/unicode_nonspacing_table.h
index de1eab3a954..7605712abc3 100644
--- a/src/include/common/unicode_combining_table.h
+++ b/src/include/common/unicode_nonspacing_table.h
@@ -1,6 +1,7 @@
-/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */
+/* generated by src/common/unicode/generate-unicode_nonspacing_table.pl, do not edit */
 
-static const struct mbinterval combining[] = {
+static const struct mbinterval nonspacing[] = {
+	{0x00AD, 0x00AD},
 	{0x0300, 0x036F},
 	{0x0483, 0x0489},
 	{0x0591, 0x05BD},
@@ -8,13 +9,16 @@ static const struct mbinterval combining[] = {
 	{0x05C1, 0x05C2},
 	{0x05C4, 0x05C5},
 	{0x05C7, 0x05C7},
+	{0x0600, 0x0605},
 	{0x0610, 0x061A},
+	{0x061C, 0x061C},
 	{0x064B, 0x065F},
 	{0x0670, 0x0670},
-	{0x06D6, 0x06DC},
+	{0x06D6, 0x06DD},
 	{0x06DF, 0x06E4},
 	{0x06E7, 0x06E8},
 	{0x06EA, 0x06ED},
+	{0x070F, 0x070F},
 	{0x0711, 0x0711},
 	{0x0730, 0x074A},
 	{0x07A6, 0x07B0},
@@ -25,9 +29,8 @@ static const struct mbinterval combining[] = {
 	{0x0825, 0x0827},
 	{0x0829, 0x082D},
 	{0x0859, 0x085B},
-	{0x0898, 0x089F},
-	{0x08CA, 0x08E1},
-	{0x08E3, 0x0902},
+	{0x0890, 0x089F},
+	{0x08CA, 0x0902},
 	{0x093A, 0x093A},
 	{0x093C, 0x093C},
 	{0x0941, 0x0948},
@@ -114,8 +117,7 @@ static const struct mbinterval combining[] = {
 	{0x17C6, 0x17C6},
 	{0x17C9, 0x17D3},
 	{0x17DD, 0x17DD},
-	{0x180B, 0x180D},
-	{0x180F, 0x180F},
+	{0x180B, 0x180F},
 	{0x1885, 0x1886},
 	{0x18A9, 0x18A9},
 	{0x1920, 0x1922},
@@ -152,6 +154,9 @@ static const struct mbinterval combining[] = {
 	{0x1CF4, 0x1CF4},
 	{0x1CF8, 0x1CF9},
 	{0x1DC0, 0x1DFF},
+	{0x200B, 0x200F},
+	{0x202A, 0x202E},
+	{0x2060, 0x206F},
 	{0x20D0, 0x20F0},
 	{0x2CEF, 0x2CF1},
 	{0x2D7F, 0x2D7F},
@@ -196,6 +201,8 @@ static const struct mbinterval combining[] = {
 	{0xFB1E, 0xFB1E},
 	{0xFE00, 0xFE0F},
 	{0xFE20, 0xFE2F},
+	{0xFEFF, 0xFEFF},
+	{0xFFF9, 0xFFFB},
 	{0x101FD, 0x101FD},
 	{0x102E0, 0x102E0},
 	{0x10376, 0x1037A},
@@ -213,7 +220,8 @@ static const struct mbinterval combining[] = {
 	{0x1107F, 0x11081},
 	{0x110B3, 0x110B6},
 	{0x110B9, 0x110BA},
-	{0x110C2, 0x110C2},
+	{0x110BD, 0x110BD},
+	{0x110C2, 0x110CD},
 	{0x11100, 0x11102},
 	{0x11127, 0x1112B},
 	{0x1112D, 0x11134},
@@ -281,15 +289,16 @@ static const struct mbinterval combining[] = {
 	{0x11D95, 0x11D95},
 	{0x11D97, 0x11D97},
 	{0x11EF3, 0x11EF4},
+	{0x13430, 0x13438},
 	{0x16AF0, 0x16AF4},
 	{0x16B30, 0x16B36},
 	{0x16F4F, 0x16F4F},
 	{0x16F8F, 0x16F92},
 	{0x16FE4, 0x16FE4},
 	{0x1BC9D, 0x1BC9E},
-	{0x1CF00, 0x1CF46},
+	{0x1BCA0, 0x1CF46},
 	{0x1D167, 0x1D169},
-	{0x1D17B, 0x1D182},
+	{0x1D173, 0x1D182},
 	{0x1D185, 0x1D18B},
 	{0x1D1AA, 0x1D1AD},
 	{0x1D242, 0x1D244},
@@ -304,5 +313,5 @@ static const struct mbinterval combining[] = {
 	{0x1E2EC, 0x1E2EF},
 	{0x1E8D0, 0x1E8D6},
 	{0x1E944, 0x1E94A},
-	{0xE0100, 0xE01EF},
+	{0xE0001, 0xE01EF},
 };