diff options
| -rw-r--r-- | regress/usr.bin/mandoc/char/unicode/man.in | 6 | ||||
| -rw-r--r-- | regress/usr.bin/mandoc/char/unicode/man.out_utf8 | 6 | ||||
| -rw-r--r-- | regress/usr.bin/mandoc/char/unicode/mdoc.in | 6 | ||||
| -rw-r--r-- | regress/usr.bin/mandoc/char/unicode/mdoc.out_utf8 | 6 | ||||
| -rw-r--r-- | share/man/man7/mandoc_char.7 | 8 | ||||
| -rw-r--r-- | usr.bin/mandoc/mandoc.c | 7 |
6 files changed, 21 insertions, 18 deletions
diff --git a/regress/usr.bin/mandoc/char/unicode/man.in b/regress/usr.bin/mandoc/char/unicode/man.in index bc2bffc0ea9..392b4e57fd4 100644 --- a/regress/usr.bin/mandoc/char/unicode/man.in +++ b/regress/usr.bin/mandoc/char/unicode/man.in @@ -2,8 +2,8 @@ .SH NAME char-unicode-mdoc \- unicode characters in man code .SH DESCRIPTION -Copyright symbol: \[u00A9] +Copyright symbol: \[u00A9] = \C'u00A9' .PP -m-dash: \[u2014] +m-dash: \[u2014] = \C'u2014' .PP -nabla: \[u1D6C1] +nabla: \[u1D6C1] = \C'u1D6C1' diff --git a/regress/usr.bin/mandoc/char/unicode/man.out_utf8 b/regress/usr.bin/mandoc/char/unicode/man.out_utf8 index 746734786b5..3e445a8f8bb 100644 --- a/regress/usr.bin/mandoc/char/unicode/man.out_utf8 +++ b/regress/usr.bin/mandoc/char/unicode/man.out_utf8 @@ -6,11 +6,11 @@ NNAAMMEE char-unicode-mdoc - unicode characters in man code DDEESSCCRRIIPPTTIIOONN - Copyright symbol: © + Copyright symbol: © = © - m-dash: — + m-dash: — = — - nabla: 𝛁 + nabla: 𝛁 = 𝛁 diff --git a/regress/usr.bin/mandoc/char/unicode/mdoc.in b/regress/usr.bin/mandoc/char/unicode/mdoc.in index aef138080f1..47a5911e645 100644 --- a/regress/usr.bin/mandoc/char/unicode/mdoc.in +++ b/regress/usr.bin/mandoc/char/unicode/mdoc.in @@ -5,8 +5,8 @@ .Nm char-unicode-mdoc .Nd unicode characters in mdoc code .Sh DESCRIPTION -Copyright symbol: \[u00A9] +Copyright symbol: \[u00A9] = \C'u00A9' .Pp -m-dash: \[u2014] +m-dash: \[u2014] = \C'u2014' .Pp -nabla: \[u1D6C1] +nabla: \[u1D6C1] = \C'u1D6C1' diff --git a/regress/usr.bin/mandoc/char/unicode/mdoc.out_utf8 b/regress/usr.bin/mandoc/char/unicode/mdoc.out_utf8 index 2f46654efd8..04b5bca9456 100644 --- a/regress/usr.bin/mandoc/char/unicode/mdoc.out_utf8 +++ b/regress/usr.bin/mandoc/char/unicode/mdoc.out_utf8 @@ -4,10 +4,10 @@ NNAAMMEE cchhaarr--uunniiccooddee--mmddoocc – unicode characters in mdoc code DDEESSCCRRIIPPTTIIOONN - Copyright symbol: © + Copyright symbol: © = © - m-dash: — + m-dash: — = — - nabla: 𝛁 + nabla: 𝛁 = 𝛁 OpenBSD November 10, 2013 OpenBSD diff --git a/share/man/man7/mandoc_char.7 b/share/man/man7/mandoc_char.7 index f630d01edeb..0cbb81dca75 100644 --- a/share/man/man7/mandoc_char.7 +++ b/share/man/man7/mandoc_char.7 @@ -1,4 +1,4 @@ -.\" $OpenBSD: mandoc_char.7,v 1.18 2013/11/10 17:47:42 jmc Exp $ +.\" $OpenBSD: mandoc_char.7,v 1.19 2013/11/10 20:17:14 schwarze Exp $ .\" .\" Copyright (c) 2003 Jason McIntyre <jmc@openbsd.org> .\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> @@ -655,11 +655,11 @@ manual. .It \e*(Ai Ta \*(Ai Ta ANSI standard name .El .Sh UNICODE CHARACTERS -The escape sequence +The escape sequences .Pp -.Dl \e[uXXXX] +.Dl \e[uXXXX] and \eC'uXXXX' .Pp -is interpreted as a Unicode codepoint. +are interpreted as Unicode codepoints. The codepoint must be in the range above U+0080 and less than U+10FFFF. For compatibility, the hexadecimal digits .Sq A diff --git a/usr.bin/mandoc/mandoc.c b/usr.bin/mandoc/mandoc.c index f24da3895e8..b96077b4e70 100644 --- a/usr.bin/mandoc/mandoc.c +++ b/usr.bin/mandoc/mandoc.c @@ -1,4 +1,4 @@ -/* $Id: mandoc.c,v 1.38 2013/10/05 21:17:29 schwarze Exp $ */ +/* $Id: mandoc.c,v 1.39 2013/11/10 20:17:14 schwarze Exp $ */ /* * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> * Copyright (c) 2011, 2012, 2013 Ingo Schwarze <schwarze@openbsd.org> @@ -89,8 +89,11 @@ mandoc_escape(const char const **end, const char const **start, int *sz) case ('C'): if ('\'' != **start) return(ESCAPE_ERROR); - gly = ESCAPE_SPECIAL; *start = ++*end; + if ('u' == (*start)[0] && '\'' != (*start)[1]) + gly = ESCAPE_UNICODE; + else + gly = ESCAPE_SPECIAL; term = '\''; break; |