Revert "Rename unicode_combining_table to unicode_width_table"

j-naylor · j-naylor · commit 1563ecbc1be8 · 2021-08-26T10:06:12.000-04:00
This reverts commit eb0d0d2. After I had committed eb0d0d2 and 78ab944, I decided to add a sanity check for a "can't happen" scenario just to be cautious. It turned out that it already happened in the official Unicode source data, namely that a character can be both wide and a combining character. This fact renders the aforementioned commits unnecessary, so revert both of them. Discussion: https://www.postgresql.org/message-id/CAFBsxsH5ejH4-1xaTLpSK8vWoK1m6fA1JBtTM6jmBsLfmDki1g%40mail.gmail.com
diff --git 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_width_table.h unicode_normprops_table.h unicode_norm_hashfunc.h
+update-unicode: unicode_norm_table.h unicode_combining_table.h unicode_normprops_table.h unicode_norm_hashfunc.h
 	mv $^ ../../../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) generate-unicode_norm_table.pl
 
-unicode_width_table.h: generate-unicode_width_table.pl UnicodeData.txt
+unicode_combining_table.h: generate-unicode_combining_table.pl UnicodeData.txt
 	$(PERL) $^ >$@
 
 unicode_normprops_table.h: generate-unicode_normprops_table.pl DerivedNormalizationProps.txt
diff --git a/src/common/unicode/generate-unicode_combining_table.pl b/src/common/unicode/generate-unicode_combining_table.pl
@@ -15,7 +15,7 @@
 my $count = 0;
 
 print
-  "/* generated by src/common/unicode/generate-unicode_width_table.pl, do not edit */\n\n";
+  "/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */\n\n";
 
 print "static const struct mbinterval combining[] = {\n";
 
diff --git a/src/common/wchar.c b/src/common/wchar.c
@@ -644,7 +644,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
 static int
 ucs_wcwidth(pg_wchar ucs)
 {
-#include "common/unicode_width_table.h"
+#include "common/unicode_combining_table.h"
 
 	/* test for 8-bit control characters */
 	if (ucs == 0)
diff --git a/src/include/common/unicode_combining_table.h b/src/include/common/unicode_combining_table.h
@@ -1,4 +1,4 @@
-/* generated by src/common/unicode/generate-unicode_width_table.pl, do not edit */
+/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */
 
 static const struct mbinterval combining[] = {
 	{0x0300, 0x036F},

Original file line number	Diff line number	Diff line change
`@@ -644,7 +644,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)`
`644`	`644`	`static int`
`645`	`645`	`ucs_wcwidth(pg_wchar ucs)`
`646`	`646`	`{`
`647`		`-#include "common/unicode_width_table.h"`
	`647`	`+#include "common/unicode_combining_table.h"`
`648`	`648`
`649`	`649`	`/* test for 8-bit control characters */`
`650`	`650`	`if (ucs == 0)`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-/* generated by src/common/unicode/generate-unicode_width_table.pl, do not edit */`
	`1`	`+/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */`
`2`	`2`
`3`	`3`	`static const struct mbinterval combining[] = {`
`4`	`4`	`{0x0300, 0x036F},`