Add support for automatically updating Unicode derived files

petere · petere · commit f85a485f89e2 · 2020-01-09T10:08:14.000+01:00
We currently have several sets of files generated from data provided by Unicode. These all have ad hoc rules and instructions for updating when new Unicode versions appear, and it's not done consistently. This patch centralizes and automates the process and makes it part of the release checklist. The Unicode and CLDR versions are specified in Makefile.global.in. There is a new make target "update-unicode" that downloads all the relevant files and runs the generation script. There is also a new script for generating the table of combining characters for ucs_wcwidth(). That table is now in a separate include file rather than hardcoded into the middle of other code. This is based on the script that was used for generating d8594d1, but the script itself wasn't committed at that time. Reviewed-by: John Naylor <john.naylor@2ndquadrant.com> Discussion: https://www.postgresql.org/message-id/flat/c8d05f42-443e-6c23-819b-05b31759a37c@2ndquadrant.com
diff --git a/GNUmakefile.in b/GNUmakefile.in
@@ -75,6 +75,10 @@ $(call recurse,installcheck-world,src/test src/pl src/interfaces/ecpg contrib sr
 GNUmakefile: GNUmakefile.in $(top_builddir)/config.status
 	./config.status $@
 
+update-unicode: | submake-generated-headers submake-libpgport
+	$(MAKE) -C src/common/unicode $@
+	$(MAKE) -C contrib/unaccent $@
+
 
 ##########################################################################
 
diff --git a/contrib/unaccent/.gitignore b/contrib/unaccent/.gitignore
@@ -2,3 +2,6 @@
 /log/
 /results/
 /tmp_check/
+
+# Downloaded files
+/Latin-ASCII.xml
diff --git a/contrib/unaccent/Makefile b/contrib/unaccent/Makefile
@@ -26,3 +26,22 @@ top_builddir = ../..
 include $(top_builddir)/src/Makefile.global
 include $(top_srcdir)/contrib/contrib-global.mk
 endif
+
+update-unicode: unaccent.rules
+
+# Allow running this even without --with-python
+PYTHON ?= python
+
+unaccent.rules: generate_unaccent_rules.py ../../src/common/unicode/UnicodeData.txt Latin-ASCII.xml
+	$(PYTHON) $< --unicode-data-file $(word 2,$^) --latin-ascii-file $(word 3,$^) >$@
+
+# Only download it once; dependencies must match src/common/unicode/
+../../src/common/unicode/UnicodeData.txt: $(top_builddir)/src/Makefile.global
+	$(MAKE) -C $(@D) $(@F)
+
+# Dependency on Makefile.global is for CLDR_VERSION
+Latin-ASCII.xml: $(top_builddir)/src/Makefile.global
+	$(DOWNLOAD) https://raw.githubusercontent.com/unicode-org/cldr/release-$(subst .,-,$(CLDR_VERSION))/common/transforms/Latin-ASCII.xml
+
+distclean:
+	rm -f Latin-ASCII.xml
diff --git a/contrib/unaccent/generate_unaccent_rules.py b/contrib/unaccent/generate_unaccent_rules.py
@@ -20,13 +20,11 @@
 # option is enabled, the XML file of this transliterator [2] -- given as a
 # command line argument -- will be parsed and used.
 #
-# Ideally you should use the latest release for each data set.  For
-# Latin-ASCII.xml, the latest data sets released can be browsed directly
-# via [3].  Note that this script is compatible with at least release 29.
+# Ideally you should use the latest release for each data set.  This
+# script is compatible with at least CLDR release 29.
 #
-# [1] https://www.unicode.org/Public/8.0.0/ucd/UnicodeData.txt
-# [2] https://raw.githubusercontent.com/unicode-org/cldr/release-34/common/transforms/Latin-ASCII.xml
-# [3] https://github.com/unicode-org/cldr/tags
+# [1] https://www.unicode.org/Public/${UNICODE_VERSION}/ucd/UnicodeData.txt
+# [2] https://raw.githubusercontent.com/unicode-org/cldr/${TAG}/common/transforms/Latin-ASCII.xml
 
 # BEGIN: Python 2/3 compatibility - remove when Python 2 compatibility dropped
 # The approach is to be Python3 compatible with Python2 "backports".
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
@@ -23,7 +23,7 @@ standard_targets = all install installdirs uninstall distprep clean distclean ma
 # these targets should recurse even into subdirectories not being built:
 standard_always_targets = distprep clean distclean maintainer-clean
 
-.PHONY: $(standard_targets) install-strip html man installcheck-parallel
+.PHONY: $(standard_targets) install-strip html man installcheck-parallel update-unicode
 
 # make `all' the default target
 all:
@@ -352,6 +352,22 @@ XGETTEXT = @XGETTEXT@
 GZIP	= gzip
 BZIP2	= bzip2
 
+DOWNLOAD = wget -O $@ --no-use-server-timestamps
+#DOWNLOAD = curl -o $@
+
+
+# Unicode data information
+
+# Before each major release, update these and run make update-unicode.
+
+# Pick a release from here: <https://www.unicode.org/Public/>.  Note
+# that the most recent release listed there is often a pre-release;
+# don't pick that one, except for testing.
+UNICODE_VERSION = 12.1.0
+
+# Pick a release from here: <http://cldr.unicode.org/index/downloads>
+CLDR_VERSION = 34
+
 
 # Tree-wide build support
 
diff --git a/src/backend/utils/mb/Unicode/Makefile b/src/backend/utils/mb/Unicode/Makefile
@@ -115,9 +115,6 @@ maintainer-clean: distclean
 	rm -f $(MAPS)
 
 
-DOWNLOAD = wget -O $@ --no-use-server-timestamps
-#DOWNLOAD = curl -o $@
-
 BIG5.TXT CNS11643.TXT:
 	$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/OTHER/$(@F)
 
diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c
@@ -643,73 +643,7 @@ mbbisearch(pg_wchar ucs, const struct mbinterval *table, int max)
 static int
 ucs_wcwidth(pg_wchar ucs)
 {
-	/* sorted list of non-overlapping intervals of non-spacing characters */
-	static const struct mbinterval combining[] = {
-		{0x0300, 0x036F}, {0x0483, 0x0489}, {0x0591, 0x05BD},
-		{0x05BF, 0x05BF}, {0x05C1, 0x05C2}, {0x05C4, 0x05C5},
-		{0x05C7, 0x05C7}, {0x0610, 0x061A}, {0x064B, 0x065F},
-		{0x0670, 0x0670}, {0x06D6, 0x06DC}, {0x06DF, 0x06E4},
-		{0x06E7, 0x06E8}, {0x06EA, 0x06ED}, {0x0711, 0x0711},
-		{0x0730, 0x074A}, {0x07A6, 0x07B0}, {0x07EB, 0x07F3},
-		{0x07FD, 0x07FD}, {0x0816, 0x0819}, {0x081B, 0x0823},
-		{0x0825, 0x0827}, {0x0829, 0x082D}, {0x0859, 0x085B},
-		{0x08D3, 0x08E1}, {0x08E3, 0x0902}, {0x093A, 0x093A},
-		{0x093C, 0x093C}, {0x0941, 0x0948}, {0x094D, 0x094D},
-		{0x0951, 0x0957}, {0x0962, 0x0963}, {0x0981, 0x0981},
-		{0x09BC, 0x09BC}, {0x09C1, 0x09C4}, {0x09CD, 0x09CD},
-		{0x09E2, 0x09E3}, {0x09FE, 0x0A02}, {0x0A3C, 0x0A3C},
-		{0x0A41, 0x0A51}, {0x0A70, 0x0A71}, {0x0A75, 0x0A75},
-		{0x0A81, 0x0A82}, {0x0ABC, 0x0ABC}, {0x0AC1, 0x0AC8},
-		{0x0ACD, 0x0ACD}, {0x0AE2, 0x0AE3}, {0x0AFA, 0x0B01},
-		{0x0B3C, 0x0B3C}, {0x0B3F, 0x0B3F}, {0x0B41, 0x0B44},
-		{0x0B4D, 0x0B56}, {0x0B62, 0x0B63}, {0x0B82, 0x0B82},
-		{0x0BC0, 0x0BC0}, {0x0BCD, 0x0BCD}, {0x0C00, 0x0C00},
-		{0x0C04, 0x0C04}, {0x0C3E, 0x0C40}, {0x0C46, 0x0C56},
-		{0x0C62, 0x0C63}, {0x0C81, 0x0C81}, {0x0CBC, 0x0CBC},
-		{0x0CBF, 0x0CBF}, {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD},
-		{0x0CE2, 0x0CE3}, {0x0D00, 0x0D01}, {0x0D3B, 0x0D3C},
-		{0x0D41, 0x0D44}, {0x0D4D, 0x0D4D}, {0x0D62, 0x0D63},
-		{0x0DCA, 0x0DCA}, {0x0DD2, 0x0DD6}, {0x0E31, 0x0E31},
-		{0x0E34, 0x0E3A}, {0x0E47, 0x0E4E}, {0x0EB1, 0x0EB1},
-		{0x0EB4, 0x0EBC}, {0x0EC8, 0x0ECD}, {0x0F18, 0x0F19},
-		{0x0F35, 0x0F35}, {0x0F37, 0x0F37}, {0x0F39, 0x0F39},
-		{0x0F71, 0x0F7E}, {0x0F80, 0x0F84}, {0x0F86, 0x0F87},
-		{0x0F8D, 0x0FBC}, {0x0FC6, 0x0FC6}, {0x102D, 0x1030},
-		{0x1032, 0x1037}, {0x1039, 0x103A}, {0x103D, 0x103E},
-		{0x1058, 0x1059}, {0x105E, 0x1060}, {0x1071, 0x1074},
-		{0x1082, 0x1082}, {0x1085, 0x1086}, {0x108D, 0x108D},
-		{0x109D, 0x109D}, {0x135D, 0x135F}, {0x1712, 0x1714},
-		{0x1732, 0x1734}, {0x1752, 0x1753}, {0x1772, 0x1773},
-		{0x17B4, 0x17B5}, {0x17B7, 0x17BD}, {0x17C6, 0x17C6},
-		{0x17C9, 0x17D3}, {0x17DD, 0x17DD}, {0x180B, 0x180D},
-		{0x1885, 0x1886}, {0x18A9, 0x18A9}, {0x1920, 0x1922},
-		{0x1927, 0x1928}, {0x1932, 0x1932}, {0x1939, 0x193B},
-		{0x1A17, 0x1A18}, {0x1A1B, 0x1A1B}, {0x1A56, 0x1A56},
-		{0x1A58, 0x1A60}, {0x1A62, 0x1A62}, {0x1A65, 0x1A6C},
-		{0x1A73, 0x1A7F}, {0x1AB0, 0x1B03}, {0x1B34, 0x1B34},
-		{0x1B36, 0x1B3A}, {0x1B3C, 0x1B3C}, {0x1B42, 0x1B42},
-		{0x1B6B, 0x1B73}, {0x1B80, 0x1B81}, {0x1BA2, 0x1BA5},
-		{0x1BA8, 0x1BA9}, {0x1BAB, 0x1BAD}, {0x1BE6, 0x1BE6},
-		{0x1BE8, 0x1BE9}, {0x1BED, 0x1BED}, {0x1BEF, 0x1BF1},
-		{0x1C2C, 0x1C33}, {0x1C36, 0x1C37}, {0x1CD0, 0x1CD2},
-		{0x1CD4, 0x1CE0}, {0x1CE2, 0x1CE8}, {0x1CED, 0x1CED},
-		{0x1CF4, 0x1CF4}, {0x1CF8, 0x1CF9}, {0x1DC0, 0x1DFF},
-		{0x20D0, 0x20F0}, {0x2CEF, 0x2CF1}, {0x2D7F, 0x2D7F},
-		{0x2DE0, 0x2DFF}, {0x302A, 0x302D}, {0x3099, 0x309A},
-		{0xA66F, 0xA672}, {0xA674, 0xA67D}, {0xA69E, 0xA69F},
-		{0xA6F0, 0xA6F1}, {0xA802, 0xA802}, {0xA806, 0xA806},
-		{0xA80B, 0xA80B}, {0xA825, 0xA826}, {0xA8C4, 0xA8C5},
-		{0xA8E0, 0xA8F1}, {0xA8FF, 0xA8FF}, {0xA926, 0xA92D},
-		{0xA947, 0xA951}, {0xA980, 0xA982}, {0xA9B3, 0xA9B3},
-		{0xA9B6, 0xA9B9}, {0xA9BC, 0xA9BD}, {0xA9E5, 0xA9E5},
-		{0xAA29, 0xAA2E}, {0xAA31, 0xAA32}, {0xAA35, 0xAA36},
-		{0xAA43, 0xAA43}, {0xAA4C, 0xAA4C}, {0xAA7C, 0xAA7C},
-		{0xAAB0, 0xAAB0}, {0xAAB2, 0xAAB4}, {0xAAB7, 0xAAB8},
-		{0xAABE, 0xAABF}, {0xAAC1, 0xAAC1}, {0xAAEC, 0xAAED},
-		{0xAAF6, 0xAAF6}, {0xABE5, 0xABE5}, {0xABE8, 0xABE8},
-		{0xABED, 0xABED}, {0xFB1E, 0xFB1E}, {0xFE00, 0xFE0F},
-		{0xFE20, 0xFE2F},
-	};
+#include "common/unicode_combining_table.h"
 
 	/* test for 8-bit control characters */
 	if (ucs == 0)
diff --git a/src/common/unicode/.gitignore b/src/common/unicode/.gitignore
@@ -1,7 +1,7 @@
 /norm_test
 /norm_test_table.h
 
-# Files downloaded from the Unicode Character Database
+# Downloaded files
 /CompositionExclusions.txt
 /NormalizationTest.txt
 /UnicodeData.txt
diff --git a/src/common/unicode/Makefile b/src/common/unicode/Makefile
@@ -18,18 +18,24 @@ LIBS += $(PTHREAD_LIBS)
 # By default, do nothing.
 all:
 
-DOWNLOAD = wget -O $@ --no-use-server-timestamps
+update-unicode: unicode_norm_table.h unicode_combining_table.h
+	$(MAKE) normalization-check
+	mv unicode_norm_table.h unicode_combining_table.h ../../../src/include/common/
 
 # These files are part of the Unicode Character Database. Download
-# them on demand.
-UnicodeData.txt CompositionExclusions.txt NormalizationTest.txt:
-	$(DOWNLOAD) https://www.unicode.org/Public/UNIDATA/$(@F)
+# them on demand.  The dependency on Makefile.global is for
+# UNICODE_VERSION.
+UnicodeData.txt CompositionExclusions.txt NormalizationTest.txt: $(top_builddir)/src/Makefile.global
+	$(DOWNLOAD) https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/$(@F)
 
 # Generation of conversion tables used for string normalization with
 # UTF-8 strings.
 unicode_norm_table.h: generate-unicode_norm_table.pl UnicodeData.txt CompositionExclusions.txt
 	$(PERL) generate-unicode_norm_table.pl
 
+unicode_combining_table.h: generate-unicode_combining_table.pl UnicodeData.txt
+	$(PERL) $^ >$@
+
 # Test suite
 normalization-check: norm_test
 	./norm_test
diff --git a/src/common/unicode/README b/src/common/unicode/README
@@ -8,20 +8,11 @@ of Unicode.
 Generating unicode_norm_table.h
 -------------------------------
 
-1. Download the Unicode data file, UnicodeData.txt, from the Unicode
-consortium and place it to the current directory. Run the perl script
-"generate-unicode_norm_table.pl", to process it, and to generate the
-"unicode_norm_table.h" file. The Makefile contains a rule to download the
-data files if they don't exist.
-
-    make unicode_norm_table.h
-
-2. Inspect the resulting header file. Once you're happy with it, copy it to
-the right location.
-
-    cp unicode_norm_table.h ../../../src/include/common/
+Run
 
+    make update-unicode
 
+from the top level of the source tree and commit the result.
 
 Tests
 -----
@@ -33,3 +24,5 @@ normalization code with all the test strings in NormalizationTest.txt.
 To download NormalizationTest.txt and run the tests:
 
     make normalization-check
+
+This is also run as part of the update-unicode target.
diff --git a/src/common/unicode/generate-unicode_combining_table.pl b/src/common/unicode/generate-unicode_combining_table.pl
@@ -0,0 +1,52 @@
+#!/usr/bin/perl
+#
+# Generate sorted list of non-overlapping intervals of non-spacing
+# characters, using Unicode data files as input.  Pass UnicodeData.txt
+# as argument.  The output is on stdout.
+#
+# Copyright (c) 2019, PostgreSQL Global Development Group
+
+use strict;
+use warnings;
+
+my $range_start = undef;
+my $codepoint;
+my $prev_codepoint;
+my $count = 0;
+
+print "/* generated by src/common/unicode/generate-unicode_combining_table.pl, do not edit */\n\n";
+
+print "static const struct mbinterval combining[] = {\n";
+
+foreach my $line (<ARGV>)
+{
+    chomp $line;
+    my @fields = split ';', $line;
+    $codepoint = hex $fields[0];
+
+    next if $codepoint > 0xFFFF;
+
+    if ($fields[2] eq 'Me' || $fields[2] eq 'Mn')
+    {
+        # combining character, save for start of range
+        if (!defined($range_start))
+        {
+            $range_start = $codepoint;
+        }
+    }
+    else
+    {
+        # not a combining character, print out previous range if any
+        if (defined($range_start))
+        {
+            printf "\t{0x%04X, 0x%04X},\n", $range_start, $prev_codepoint;
+            $range_start = undef;
+        }
+    }
+}
+continue
+{
+    $prev_codepoint = $codepoint;
+}
+
+print "};\n";
diff --git a/src/include/common/unicode_combining_table.h b/src/include/common/unicode_combining_table.h
diff --git a/src/tools/RELEASE_CHANGES b/src/tools/RELEASE_CHANGES
