1 files changed, 106 insertions, 0 deletions
diff --git a/src/common/unicode/meson.build b/src/common/unicode/meson.build
new file mode 100644
index 00000000000..13965d59f49
--- /dev/null
+++ b/src/common/unicode/meson.build
@@ -0,0 +1,106 @@
+UNICODE_VERSION = '15.0.0'
+
+unicode_data = {}
+unicode_baseurl = 'https://www.unicode.org/Public/@0@/ucd/@1@'
+
+if not wget.found()
+  subdir_done()
+endif
+
+# These files are part of the Unicode Character Database. Download them on
+# demand.
+foreach f : ['UnicodeData.txt', 'EastAsianWidth.txt', 'DerivedNormalizationProps.txt', 'CompositionExclusions.txt', 'NormalizationTest.txt']
+  url = unicode_baseurl.format(UNICODE_VERSION, f)
+  target = custom_target(f,
+    output: f,
+    command: [wget, wget_flags, url],
+    build_by_default: false,
+  )
+  unicode_data += {f: target}
+endforeach
+
+
+update_unicode_targets = []
+
+update_unicode_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'],
+    command: [
+      perl, files('generate-unicode_norm_table.pl'),
+      '--outdir', '@OUTDIR@', '@INPUT@'],
+    build_by_default: false,
+  )
+
+update_unicode_targets += \
+  custom_target('unicode_nonspacing_table.h',
+    input: [unicode_data['UnicodeData.txt']],
+    output: ['unicode_nonspacing_table.h'],
+    command: [perl, files('generate-unicode_nonspacing_table.pl'), '@INPUT@'],
+    build_by_default: false,
+    capture: true,
+  )
+
+update_unicode_targets += \
+  custom_target('unicode_east_asian_fw_table.h',
+    input: [unicode_data['EastAsianWidth.txt']],
+    output: ['unicode_east_asian_fw_table.h'],
+    command: [perl, files('generate-unicode_east_asian_fw_table.pl'), '@INPUT@'],
+    build_by_default: false,
+    capture: true,
+  )
+
+update_unicode_targets += \
+  custom_target('unicode_normprops_table.h',
+    input: [unicode_data['DerivedNormalizationProps.txt']],
+    output: ['unicode_normprops_table.h'],
+    command: [perl, files('generate-unicode_normprops_table.pl'), '@INPUT@'],
+    build_by_default: false,
+    capture: true,
+  )
+
+norm_test_table = custom_target('norm_test_table.h',
+    input: [unicode_data['NormalizationTest.txt']],
+    output: ['norm_test_table.h'],
+    command: [perl, files('generate-norm_test_table.pl'), '@INPUT@', '@OUTPUT@'],
+    build_by_default: false,
+  )
+
+inc = include_directories('.')
+
+norm_test = executable('norm_test',
+  ['norm_test.c', norm_test_table],
+  dependencies: [frontend_port_code],
+  include_directories: inc,
+  link_with: [common_static, pgport_static],
+  build_by_default: false,
+  kwargs: default_bin_args + {
+    'install': false,
+  }
+)
+
+update_unicode_dep = []
+
+if not meson.is_cross_build()
+  update_unicode_dep += custom_target('norm_test.run',
+    output: 'norm_test.run',
+    input: update_unicode_targets,
+    command: [norm_test],
+    build_by_default: false,
+    build_always_stale: true,
+  )
+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',
+  depends: update_unicode_dep,
+  output: ['dont-exist'],
+  input: update_unicode_targets,
+  command: ['cp', '@INPUT@', '@SOURCE_ROOT@/src/include/common/'],
+  build_by_default: false,
+  build_always_stale: true,
+)
+
+alias_target('update-unicode', update_unicode)