Add unicode-ucd.

The Unicode Character Database (UCD) consists of a number of data files
listing Unicode character properties and related data. It also includes
data files containing test data for conformance to several important
Unicode algorithms.

Also contains the data files for the Unified Han database of
Hanzi/Kanji/Hanja Chinese characters.

5 files changed, 116 insertions, 0 deletions

diff --git a/misc/Makefile b/misc/Makefile
index dbf8e9b78ca3..2526d41ceb28 100644
--- a/misc/Makefile
+++ b/misc/Makefile
@@ -474,6 +474,7 @@
     SUBDIR += uk-postcodes
     SUBDIR += umodunpack
     SUBDIR += unclutter
+    SUBDIR += unicode-ucd
     SUBDIR += upclient
     SUBDIR += us-zipcodes
     SUBDIR += usbids
diff --git a/misc/unicode-ucd/Makefile b/misc/unicode-ucd/Makefile
new file mode 100644
index 000000000000..efe711b36223
--- /dev/null
+++ b/misc/unicode-ucd/Makefile
@@ -0,0 +1,30 @@
+# $FreeBSD$
+
+PORTNAME=	unicode-ucd
+PORTVERSION=	9.0.0
+CATEGORIES=	misc
+MASTER_SITES=	http://www.unicode.org/Public/zipped/${PORTVERSION}/
+DISTFILES=	UCD.zip \
+		Unihan.zip
+DIST_SUBDIR=	unicode/${PORTVERSION}
+
+MAINTAINER=	gnome@FreeBSD.org
+COMMENT=	Unicode Character Database
+
+# https://fedoraproject.org/wiki/Licensing/MIT#Modern_Style_without_sublicense_.28Unicode.29
+LICENSE=	MIT
+
+USES=		zip
+
+NO_WRKSUBDIR=	yes
+NO_BUILD=	yes
+
+do-install:
+	@${MKDIR} ${STAGEDIR}${PREFIX}/share/${PORTNAME}
+	cd ${WRKSRC} && ${COPYTREE_SHARE} . \
+		${STAGEDIR}${PREFIX}/share/${PORTNAME}/
+# we unpack Unihan.zip but gucharmap wants the Unihan.zip to be present
+	${INSTALL_DATA} ${DISTDIR}${DIST_SUBDIR}/Unihan.zip \
+		${STAGEDIR}${PREFIX}/share/${PORTNAME}/
+
+.include <bsd.port.mk>
diff --git a/misc/unicode-ucd/distinfo b/misc/unicode-ucd/distinfo
new file mode 100644
index 000000000000..2c94d424e414
--- /dev/null
+++ b/misc/unicode-ucd/distinfo
@@ -0,0 +1,5 @@
+TIMESTAMP = 1470738390
+SHA256 (unicode/9.0.0/UCD.zip) = df9e028425816fd5117eaea7173704056f88f7cd030681e457c6f3827f9390ec
+SIZE (unicode/9.0.0/UCD.zip) = 5655592
+SHA256 (unicode/9.0.0/Unihan.zip) = 6afdd48fb3c5d79a527ed27ce2582b2f684c09e16f5d0837fe7e5b0204f46362
+SIZE (unicode/9.0.0/Unihan.zip) = 6558824
diff --git a/misc/unicode-ucd/pkg-descr b/misc/unicode-ucd/pkg-descr
new file mode 100644
index 000000000000..85bf44399451
--- /dev/null
+++ b/misc/unicode-ucd/pkg-descr
@@ -0,0 +1,9 @@
+The Unicode Character Database (UCD) consists of a number of data files
+listing Unicode character properties and related data. It also includes
+data files containing test data for conformance to several important
+Unicode algorithms.
+
+This package contains Unihan.zip which contains the data files for the
+Unified Han database of Hanzi/Kanji/Hanja Chinese characters.
+
+WWW: http://www.unicode.org/ucd/
diff --git a/misc/unicode-ucd/pkg-plist b/misc/unicode-ucd/pkg-plist
new file mode 100644
index 000000000000..9c25c3b8dc51
--- /dev/null
+++ b/misc/unicode-ucd/pkg-plist
@@ -0,0 +1,71 @@
+%%DATADIR%%/ArabicShaping.txt
+%%DATADIR%%/BidiBrackets.txt
+%%DATADIR%%/BidiCharacterTest.txt
+%%DATADIR%%/BidiMirroring.txt
+%%DATADIR%%/BidiTest.txt
+%%DATADIR%%/Blocks.txt
+%%DATADIR%%/CJKRadicals.txt
+%%DATADIR%%/CaseFolding.txt
+%%DATADIR%%/CompositionExclusions.txt
+%%DATADIR%%/DerivedAge.txt
+%%DATADIR%%/DerivedCoreProperties.txt
+%%DATADIR%%/DerivedNormalizationProps.txt
+%%DATADIR%%/EastAsianWidth.txt
+%%DATADIR%%/EmojiSources.txt
+%%DATADIR%%/HangulSyllableType.txt
+%%DATADIR%%/Index.txt
+%%DATADIR%%/IndicPositionalCategory.txt
+%%DATADIR%%/IndicSyllabicCategory.txt
+%%DATADIR%%/Jamo.txt
+%%DATADIR%%/LineBreak.txt
+%%DATADIR%%/NameAliases.txt
+%%DATADIR%%/NamedSequences.txt
+%%DATADIR%%/NamedSequencesProv.txt
+%%DATADIR%%/NamesList.html
+%%DATADIR%%/NamesList.txt
+%%DATADIR%%/NormalizationCorrections.txt
+%%DATADIR%%/NormalizationTest.txt
+%%DATADIR%%/PropList.txt
+%%DATADIR%%/PropertyAliases.txt
+%%DATADIR%%/PropertyValueAliases.txt
+%%DATADIR%%/ReadMe.txt
+%%DATADIR%%/ScriptExtensions.txt
+%%DATADIR%%/Scripts.txt
+%%DATADIR%%/SpecialCasing.txt
+%%DATADIR%%/StandardizedVariants.html
+%%DATADIR%%/StandardizedVariants.txt
+%%DATADIR%%/TangutSources.txt
+%%DATADIR%%/USourceData.txt
+%%DATADIR%%/USourceGlyphs.pdf
+%%DATADIR%%/UnicodeData.txt
+%%DATADIR%%/Unihan.zip
+%%DATADIR%%/Unihan_DictionaryIndices.txt
+%%DATADIR%%/Unihan_DictionaryLikeData.txt
+%%DATADIR%%/Unihan_IRGSources.txt
+%%DATADIR%%/Unihan_NumericValues.txt
+%%DATADIR%%/Unihan_OtherMappings.txt
+%%DATADIR%%/Unihan_RadicalStrokeCounts.txt
+%%DATADIR%%/Unihan_Readings.txt
+%%DATADIR%%/Unihan_Variants.txt
+%%DATADIR%%/auxiliary/GraphemeBreakProperty.txt
+%%DATADIR%%/auxiliary/GraphemeBreakTest.html
+%%DATADIR%%/auxiliary/GraphemeBreakTest.txt
+%%DATADIR%%/auxiliary/LineBreakTest.html
+%%DATADIR%%/auxiliary/LineBreakTest.txt
+%%DATADIR%%/auxiliary/SentenceBreakProperty.txt
+%%DATADIR%%/auxiliary/SentenceBreakTest.html
+%%DATADIR%%/auxiliary/SentenceBreakTest.txt
+%%DATADIR%%/auxiliary/WordBreakProperty.txt
+%%DATADIR%%/auxiliary/WordBreakTest.html
+%%DATADIR%%/auxiliary/WordBreakTest.txt
+%%DATADIR%%/extracted/DerivedBidiClass.txt
+%%DATADIR%%/extracted/DerivedBinaryProperties.txt
+%%DATADIR%%/extracted/DerivedCombiningClass.txt
+%%DATADIR%%/extracted/DerivedDecompositionType.txt
+%%DATADIR%%/extracted/DerivedEastAsianWidth.txt
+%%DATADIR%%/extracted/DerivedGeneralCategory.txt
+%%DATADIR%%/extracted/DerivedJoiningGroup.txt
+%%DATADIR%%/extracted/DerivedJoiningType.txt
+%%DATADIR%%/extracted/DerivedLineBreak.txt
+%%DATADIR%%/extracted/DerivedNumericType.txt
+%%DATADIR%%/extracted/DerivedNumericValues.txt