Add utf8-cpp 2.3.4

UTF8-CPP: UTF-8 with C++ in a Portable Way

Many C++ developers miss an easy and portable way of handling Unicode
encoded strings. The original C++ Standard (known as C++98 or C++03) is
Unicode agnostic. C++11 provides some support for Unicode on core
language and library level: u8, u, and U character and string literals,
char16_t and char32_t character types, u16string and u32string library
classes, and codecvt support for conversions between Unicode encoding
forms. In the meantime, developers use third party libraries like ICU,
OS specific capabilities, or simply roll out their own solutions.

In order to easily handle UTF-8 encoded Unicode strings, I came up with
a small generic library. For anybody used to work with STL algorithms
and iterators, it should be easy and natural to use. The code is freely
available for any purpose - check out the license at the beginning of
the utf8.h file. If you run into bugs or performance issues, please let
me know and I'll do my best to address them.

6 files changed, 69 insertions, 1 deletions

diff --git a/textproc/Makefile b/textproc/Makefile
index e322ef9556f..161dcd4a335 100644
--- a/textproc/Makefile
+++ b/textproc/Makefile
@@ -1,4 +1,4 @@
-# $NetBSD: Makefile,v 1.1222 2021/05/04 14:19:51 prlw1 Exp $
+# $NetBSD: Makefile,v 1.1223 2021/05/04 14:24:33 prlw1 Exp $
 #
 
 COMMENT=	Text processing utilities (does not include desktop publishing)
@@ -1188,6 +1188,7 @@ SUBDIR+=	untex
 SUBDIR+=	upmendex
 SUBDIR+=	uriparser
 SUBDIR+=	urlview
+SUBDIR+=	utf8-cpp
 SUBDIR+=	verify-synopsis
 SUBDIR+=	vis
 SUBDIR+=	wbxml2
diff --git a/textproc/utf8-cpp/DESCR b/textproc/utf8-cpp/DESCR
new file mode 100644
index 00000000000..2bcf3a01bd7
--- /dev/null
+++ b/textproc/utf8-cpp/DESCR
@@ -0,0 +1,17 @@
+UTF8-CPP: UTF-8 with C++ in a Portable Way
+
+Many C++ developers miss an easy and portable way of handling Unicode
+encoded strings. The original C++ Standard (known as C++98 or C++03) is
+Unicode agnostic. C++11 provides some support for Unicode on core
+language and library level: u8, u, and U character and string literals,
+char16_t and char32_t character types, u16string and u32string library
+classes, and codecvt support for conversions between Unicode encoding
+forms. In the meantime, developers use third party libraries like ICU,
+OS specific capabilities, or simply roll out their own solutions.
+
+In order to easily handle UTF-8 encoded Unicode strings, I came up with
+a small generic library. For anybody used to work with STL algorithms
+and iterators, it should be easy and natural to use. The code is freely
+available for any purpose - check out the license at the beginning of
+the utf8.h file. If you run into bugs or performance issues, please let
+me know and I'll do my best to address them.
diff --git a/textproc/utf8-cpp/Makefile b/textproc/utf8-cpp/Makefile
new file mode 100644
index 00000000000..854c78f48a0
--- /dev/null
+++ b/textproc/utf8-cpp/Makefile
@@ -0,0 +1,26 @@
+# $NetBSD: Makefile,v 1.1 2021/05/04 14:24:33 prlw1 Exp $
+
+DISTNAME=	utf8-cpp-2.3.4
+CATEGORIES=	textproc
+MASTER_SITES=	${MASTER_SITE_GITHUB:=jjones646/}
+GITHUB_TAG=	v2.3.4
+
+MAINTAINER=	prlw1@cam.ac.uk
+HOMEPAGE=	https://github.com/jjones646/utf8-cpp/
+COMMENT=	UTF-8 header library for C++
+LICENSE=	boost-license
+
+USE_LANGUAGES=	# none
+
+NO_CONFIGURE=	yes
+NO_BUILD=	yes
+
+INSTALLATION_DIRS+=	include/utf8
+
+do-install:
+	${INSTALL_DATA} ${WRKSRC}/source/utf8.h ${DESTDIR}${PREFIX}/include
+.for f in checked.h core.h unchecked.h
+	${INSTALL_DATA} ${WRKSRC}/source/utf8/${f} ${DESTDIR}${PREFIX}/include/utf8
+.endfor
+
+.include "../../mk/bsd.pkg.mk"
diff --git a/textproc/utf8-cpp/PLIST b/textproc/utf8-cpp/PLIST
new file mode 100644
index 00000000000..ac4c9c7cd2d
--- /dev/null
+++ b/textproc/utf8-cpp/PLIST
@@ -0,0 +1,5 @@
+@comment $NetBSD: PLIST,v 1.1 2021/05/04 14:24:33 prlw1 Exp $
+include/utf8.h
+include/utf8/checked.h
+include/utf8/core.h
+include/utf8/unchecked.h
diff --git a/textproc/utf8-cpp/buildlink3.mk b/textproc/utf8-cpp/buildlink3.mk
new file mode 100644
index 00000000000..84313ac6453
--- /dev/null
+++ b/textproc/utf8-cpp/buildlink3.mk
@@ -0,0 +1,13 @@
+# $NetBSD: buildlink3.mk,v 1.1 2021/05/04 14:24:33 prlw1 Exp $
+
+BUILDLINK_TREE+=	utf8-cpp
+
+.if !defined(UTF8_CPP_BUILDLINK3_MK)
+UTF8_CPP_BUILDLINK3_MK:=
+
+BUILDLINK_API_DEPENDS.utf8-cpp+=	utf8-cpp>=2.3.4
+BUILDLINK_PKGSRCDIR.utf8-cpp?=		../../textproc/utf8-cpp
+BUILDLINK_DEPMETHOD.utf8-cpp?=		build
+.endif	# UTF8_CPP_BUILDLINK3_MK
+
+BUILDLINK_TREE+=	-utf8-cpp
diff --git a/textproc/utf8-cpp/distinfo b/textproc/utf8-cpp/distinfo
new file mode 100644
index 00000000000..8b708a442ca
--- /dev/null
+++ b/textproc/utf8-cpp/distinfo
@@ -0,0 +1,6 @@
+$NetBSD: distinfo,v 1.1 2021/05/04 14:24:33 prlw1 Exp $
+
+SHA1 (utf8-cpp-2.3.4.tar.gz) = 18dcdcbfffffd9f7447b1bc318bacbc370516cfa
+RMD160 (utf8-cpp-2.3.4.tar.gz) = 81fffac81afc989a200eae827135a048237c5c27
+SHA512 (utf8-cpp-2.3.4.tar.gz) = c454513321b22658afe7c2c8fbba3f5d113f230b1f110c6c402f61f7bffa5c51d6442c4783e5d26a5f358c0ee4ee9d7f7fb9573db1c2cd1271ec2ae06666f8c6
+Size (utf8-cpp-2.3.4.tar.gz) = 18083 bytes