Generate EUC_CN mappings from gb18030-2022.ucm

In the wake of cfa6cd2, EUC_CN was the only encoding that used
gb-18030-2000.xml to generate the .map files. Since EUC_CN is a subset
of GB18030, we can easily use the same UCM file. This allows deleting
the XML file from our repository.

Author: Chao Li <[email protected]>
Discussion: https://postgr.es/m/CANWCAZaNRXZ-5NuXmsaMA2mKvMZnCGHZqQusLkpE%2B8YX%2Bi5OYg%40mail.gmail.com

Author: j-naylor

src/backend/utils/mb/Unicode/Makefile

@@ -50,7 +50,7 @@ $(eval $(call map_rule,gbk,UCS_to_most.pl,CP936.TXT,GBK))
 $(eval $(call map_rule,johab,UCS_to_JOHAB.pl,JOHAB.TXT))
 $(eval $(call map_rule,uhc,UCS_to_UHC.pl,windows-949-2000.xml))
 $(eval $(call map_rule,euc_jp,UCS_to_EUC_JP.pl,CP932.TXT JIS0212.TXT))
-$(eval $(call map_rule,euc_cn,UCS_to_EUC_CN.pl,gb-18030-2000.xml))
+$(eval $(call map_rule,euc_cn,UCS_to_EUC_CN.pl,gb18030-2022.ucm))
 $(eval $(call map_rule,euc_kr,UCS_to_EUC_KR.pl,KSX1001.TXT))
 $(eval $(call map_rule,euc_tw,UCS_to_EUC_TW.pl,CNS11643.TXT))
 $(eval $(call map_rule,sjis,UCS_to_SJIS.pl,CP932.TXT))
@@ -75,7 +75,7 @@ BIG5.TXT CNS11643.TXT:
 euc-jis-2004-std.txt sjis-0213-2004-std.txt:
 	$(DOWNLOAD) http://x0213.org/codetable/$(@F)
 
-gb-18030-2000.xml windows-949-2000.xml:
+windows-949-2000.xml:
 	$(DOWNLOAD) https://raw.githubusercontent.com/unicode-org/icu-data/master/charset/data/xml/$(@F)
 
 gb18030-2022.ucm:

src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl

@@ -2,16 +2,17 @@
 #
 # Copyright (c) 2007-2025, PostgreSQL Global Development Group
 #
-# src/backend/utils/mb/Unicode/UCS_to_GB18030.pl
+# src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl
 #
-# Generate UTF-8 <--> GB18030 code conversion tables from
-# "gb-18030-2000.xml", obtained from
-# http://source.icu-project.org/repos/icu/data/trunk/charset/data/xml/
+# Generate UTF-8 <--> EUC_CN code conversion tables from
+# "gb18030-2022.ucm", obtained from
+# https://github.com/unicode-org/icu/blob/main/icu4c/source/data/mappings/
 #
 # The lines we care about in the source file look like
-#    <a u="009A" b="81 30 83 36"/>
-# where the "u" field is the Unicode code point in hex,
-# and the "b" field is the hex byte sequence for GB18030
+#   <UXXXX> \xYY[\xYY...] |n
+# where XXXX is the Unicode code point in hex,
+# and the \xYY... is the hex byte sequence for GB18030,
+# and n is a flag indicating the type of mapping.
 
 use strict;
 use warnings FATAL => 'all';
@@ -22,17 +23,26 @@
 
 # Read the input
 
-my $in_file = "gb-18030-2000.xml";
+my $in_file = "gb18030-2022.ucm";
 
 open(my $in, '<', $in_file) || die("cannot open $in_file");
 
 my @mapping;
 
 while (<$in>)
 {
-	next if (!m/<a u="([0-9A-F]+)" b="([0-9A-F ]+)"/);
-	my ($u, $c) = ($1, $2);
-	$c =~ s/ //g;
+	# Mappings may have been removed by commenting out
+	next if /^#/;
+
+	next if !/^<U([0-9A-Fa-f]+)>\s+
+			((?:\\x[0-9A-Fa-f]{2})+)\s+
+			\|(\d+)/x;
+	my ($u, $c, $flag) = ($1, $2, $3);
+	$c =~ s/\\x//g;
+
+	# We only want round-trip mappings
+	next if ($flag ne '0');
+
 	my $ucs = hex($u);
 	my $code = hex($c);