Use grep to generate Uppercase.txt and Lowercase.txt
authorGraham Inggs <ginggs@debian.org>
Wed, 22 Dec 2021 16:25:14 +0000 (18:25 +0200)
committerGraham Inggs <ginggs@debian.org>
Wed, 22 Dec 2021 16:25:14 +0000 (18:25 +0200)
debian/changelog
debian/patches/use-unicode-data.patch

index 4ccc1e0d62e33df6718d92be650d387db7b9ea3d..b4f9bcda7d76bb0bc5ae3194351236c60510ebd1 100644 (file)
@@ -1,6 +1,7 @@
 utf8proc (2.7.0-2) UNRELEASED; urgency=medium
 
   * Use GraphemeBreakTest.txt as is, re-enable graphemetest
+  * Use grep to generate Uppercase.txt and Lowercase.txt
 
  -- Graham Inggs <ginggs@debian.org>  Wed, 22 Dec 2021 16:12:17 +0000
 
index 52aabae814dfa6608c4f21a2c4e62f5584c3a078..ea81298e5e43d391920fb8eeb019abb9affa0b0b 100644 (file)
@@ -8,7 +8,7 @@ Last-Update: 2021-12-22
 This patch header follows DEP-3: http://dep.debian.net/deps/dep3/
 --- a/data/Makefile
 +++ b/data/Makefile
-@@ -25,31 +25,31 @@
+@@ -25,37 +25,37 @@
  UNICODE_VERSION=14.0.0
  
  UnicodeData.txt:
@@ -48,4 +48,12 @@ This patch header follows DEP-3: http://dep.debian.net/deps/dep3/
 +      cp /usr/share/unicode/emoji/emoji-data.txt $@
  
  Uppercase.txt: DerivedCoreProperties.txt
-       $(RUBY) -e 'puts File.read("DerivedCoreProperties.txt")[/# Derived Property: Uppercase.*?# Total code points:/m]' > $@
+-      $(RUBY) -e 'puts File.read("DerivedCoreProperties.txt")[/# Derived Property: Uppercase.*?# Total code points:/m]' > $@
++      grep -zoP '(?s)# Derived Property: Uppercase.*?# Total code points:' DerivedCoreProperties.txt > $@
+ Lowercase.txt: DerivedCoreProperties.txt
+-      $(RUBY) -e 'puts File.read("DerivedCoreProperties.txt")[/# Derived Property: Lowercase.*?# Total code points:/m]' > $@
++      grep -zoP '(?s)# Derived Property: Lowercase.*?# Total code points:' DerivedCoreProperties.txt > $@
+ clean:
+       rm -f UnicodeData.txt EastAsianWidth.txt GraphemeBreakProperty.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt NormalizationTest.txt GraphemeBreakTest.txt CharWidths.txt emoji-data.txt