Implement unaccent Unicode data update in meson

The meson/ninja update-unicode target did not cover the required
updates in contrib/unaccent/.  This is fixed now.

Reviewed-by: Chao Li <li.evan.chao@gmail.com>
Reviewed-by: Alexander Borisov <lex.borisov@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/2a668979-ed92-49a3-abf9-a3ec2d460ec2%40eisentraut.org

diff --git a/contrib/unaccent/meson.build b/contrib/unaccent/meson.build
index 7f582fc04a780de8cb113c36d7c28e0989885e9f..938d9522da33ca7f44abb972336486b739a7a09f 100644 (file)
--- a/contrib/unaccent/meson.build
+++ b/contrib/unaccent/meson.build
@@ -28,7 +28,6 @@ install_data(
   install_dir: dir_data / 'tsearch_data'
 )
 
-# XXX: Implement downlo
 tests += {
   'name': 'unaccent',
   'sd': meson.current_source_dir(),
@@ -39,3 +38,43 @@ tests += {
     ],
   },
 }
+
+
+# Download CLDR files on demand.
+
+cldr_baseurl = 'https://raw.githubusercontent.com/unicode-org/cldr/release-@0@/common/transforms/@1@'
+
+if not wget.found() or not cp.found()
+  subdir_done()
+endif
+
+foreach f : ['Latin-ASCII.xml']
+  # XXX could use .replace when we require meson 0.58
+  cldr_version_dashed = '-'.join(CLDR_VERSION.split('.'))
+  url = cldr_baseurl.format(cldr_version_dashed, f)
+  target = custom_target(f,
+    output: f,
+    command: [wget, wget_flags, url],
+    build_by_default: false,
+  )
+  unicode_data += {f: target}
+endforeach
+
+unaccent_update_unicode_targets = \
+  custom_target('unaccent.rules',
+    input: [unicode_data['UnicodeData.txt'], unicode_data['Latin-ASCII.xml']],
+    output: ['unaccent.rules'],
+    command: [python, files('generate_unaccent_rules.py'), '--unicode-data-file', '@INPUT0@', '--latin-ascii-file', '@INPUT1@'],
+    build_by_default: false,
+    capture: true,
+  )
+
+update_unicode_unaccent = custom_target('update-unicode',
+  output: ['dont-exist'],
+  input: unaccent_update_unicode_targets,
+  command: [cp, '@INPUT@', '@SOURCE_ROOT@/contrib/unaccent/'],
+  build_by_default: false,
+  build_always_stale: true,
+)
+
+update_unicode_targets += update_unicode_unaccent

diff --git a/meson.build b/meson.build
index 10cdd26cc2a2756c19d2b847316e81176a558a22..c6e7cae505536a6448bb398e09b8747ae60f468f 100644 (file)
--- a/meson.build
+++ b/meson.build
@@ -3263,6 +3263,7 @@ pl_targets = []
 contrib_targets = []
 testprep_targets = []
 nls_targets = []
+update_unicode_targets = []
 
 
 # Define the tests to distribute them to the correct test styles later
@@ -4051,6 +4052,10 @@ alias_target('testprep', testprep_targets)
 alias_target('world', all_built, docs)
 alias_target('install-world', install_quiet, installdocs)
 
+if update_unicode_targets.length() > 0
+  alias_target('update-unicode', update_unicode_targets)
+endif
+
 run_target('help',
   command: [
     perl, '-ne', 'next if /^#/; print',

diff --git a/src/common/unicode/README b/src/common/unicode/README
index 4974c3c885df8369058d13629bd6e34071fa50e3..fdb8b66fa58b8bbfab9b08f01f0215f374f46037 100644 (file)
--- a/src/common/unicode/README
+++ b/src/common/unicode/README
@@ -10,7 +10,7 @@ Update Unicode Version
 ----------------------
 
 Edit src/Makefile.global.in and src/common/unicode/meson.build
-to update the UNICODE_VERSION.
+to update the UNICODE_VERSION and the CLDR_VERSION.
 
 Then, generate the new header files with:
 

diff --git a/src/common/unicode/meson.build b/src/common/unicode/meson.build
index f650dd95b5c7b508bc44566672d03d41833a0c5c..94d02f0070d408740215c042cb46c19c9119601f 100644 (file)
--- a/src/common/unicode/meson.build
+++ b/src/common/unicode/meson.build
@@ -1,6 +1,7 @@
 # Copyright (c) 2022-2026, PostgreSQL Global Development Group
 
 UNICODE_VERSION = '16.0.0'
+CLDR_VERSION = '47'
 
 unicode_data = {}
 unicode_baseurl = 'https://www.unicode.org/Public/@0@/ucd/@1@'
@@ -22,9 +23,9 @@ foreach f : ['CompositionExclusions.txt', 'CaseFolding.txt', 'DerivedCorePropert
 endforeach
 
 
-update_unicode_targets = []
+update_unicode_common_targets = []
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_case_table.h',
     input: [unicode_data['CaseFolding.txt'], unicode_data['SpecialCasing.txt'], unicode_data['UnicodeData.txt']],
     output: ['unicode_case_table.h'],
@@ -34,7 +35,7 @@ update_unicode_targets += \
     build_by_default: false,
   )
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_category_table.h',
     input: [unicode_data['UnicodeData.txt'], unicode_data['DerivedCoreProperties.txt'], unicode_data['PropList.txt']],
     output: ['unicode_category_table.h'],
@@ -44,7 +45,7 @@ update_unicode_targets += \
     build_by_default: false,
   )
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_east_asian_fw_table.h',
     input: [unicode_data['EastAsianWidth.txt']],
     output: ['unicode_east_asian_fw_table.h'],
@@ -53,7 +54,7 @@ update_unicode_targets += \
     capture: true,
   )
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_nonspacing_table.h',
     input: [unicode_data['UnicodeData.txt']],
     output: ['unicode_nonspacing_table.h'],
@@ -63,7 +64,7 @@ update_unicode_targets += \
     capture: true,
   )
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_norm_table.h',
     input: [unicode_data['UnicodeData.txt'], unicode_data['CompositionExclusions.txt']],
     output: ['unicode_norm_table.h', 'unicode_norm_hashfunc.h'],
@@ -74,7 +75,7 @@ update_unicode_targets += \
     build_by_default: false,
   )
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_normprops_table.h',
     input: [unicode_data['DerivedNormalizationProps.txt']],
     output: ['unicode_normprops_table.h'],
@@ -84,7 +85,7 @@ update_unicode_targets += \
     capture: true,
   )
 
-update_unicode_targets += \
+update_unicode_common_targets += \
   custom_target('unicode_version.h',
     output: ['unicode_version.h'],
     command: [
@@ -140,7 +141,7 @@ update_unicode_dep = []
 if not meson.is_cross_build()
   update_unicode_dep += custom_target('case_test.run',
     output: 'case_test.run',
-    input: update_unicode_targets,
+    input: update_unicode_common_targets,
     command: [case_test, UNICODE_VERSION],
     build_by_default: false,
     build_always_stale: true,
@@ -150,7 +151,7 @@ endif
 if not meson.is_cross_build()
   update_unicode_dep += custom_target('category_test.run',
     output: 'category_test.run',
-    input: update_unicode_targets,
+    input: update_unicode_common_targets,
     command: [category_test, UNICODE_VERSION],
     build_by_default: false,
     build_always_stale: true,
@@ -160,7 +161,7 @@ endif
 if not meson.is_cross_build()
   update_unicode_dep += custom_target('norm_test.run',
     output: 'norm_test.run',
-    input: update_unicode_targets,
+    input: update_unicode_common_targets,
     command: [norm_test],
     build_by_default: false,
     build_always_stale: true,
@@ -170,13 +171,13 @@ endif
 
 # Use a custom target, as run targets serialize the output, making this harder
 # to debug, and don't deal well with targets with multiple outputs.
-update_unicode = custom_target('update-unicode',
+update_unicode_common = custom_target('update-unicode',
   depends: update_unicode_dep,
   output: ['dont-exist'],
-  input: update_unicode_targets,
+  input: update_unicode_common_targets,
   command: [cp, '@INPUT@', '@SOURCE_ROOT@/src/include/common/'],
   build_by_default: false,
   build_always_stale: true,
 )
 
-alias_target('update-unicode', update_unicode)
+update_unicode_targets += update_unicode_common