Support groff's escape for Unicode input. See

  http://mdocml.bsd.lv/archives/tech/0368.html

For the time being, we just throw it away.

3 files changed, 23 insertions, 0 deletions

diff --git a/mandoc.c b/mandoc.c
index 4a9be8e7..9991978d 100644
--- a/mandoc.c
+++ b/mandoc.c
@@ -125,6 +125,14 @@ mandoc_escape(const char **end, const char **start, int *sz)
 		break;
 	case ('['):
 		gly = ESCAPE_SPECIAL;
+		/*
+		 * Unicode escapes are defined in groff as \[uXXXX] to
+		 * \[u10FFFF], where the contained value must be a valid
+		 * Unicode codepoint.  Here, however, only check whether
+		 * it's not a zero-width escape.
+		 */
+		if ('u' == cp[i] && ']' != cp[i + 1])
+			gly = ESCAPE_UNICODE;
 		term = ']';
 		break;
 	case ('C'):
diff --git a/mandoc.h b/mandoc.h
index 0b14038e..07070d88 100644
--- a/mandoc.h
+++ b/mandoc.h
@@ -299,6 +299,7 @@ enum	mandoc_esc {
 	ESCAPE_FONTROMAN, /* roman font mode */
 	ESCAPE_FONTPREV, /* previous font mode */
 	ESCAPE_NUMBERED, /* a numbered glyph */
+	ESCAPE_UNICODE, /* a unicode codepoint */
 	ESCAPE_NOSPACE /* suppress space if the last on a line */
 };
 
diff --git a/mandoc_char.7 b/mandoc_char.7
index 10a64167..f61d3a07 100644
--- a/mandoc_char.7
+++ b/mandoc_char.7
@@ -520,6 +520,20 @@ portable.
 .It \e*(Px   Ta \*(Px       Ta POSIX standard name
 .It \e*(Ai   Ta \*(Ai       Ta ANSI standard name
 .El
+.Sh UNICODE CHARACTERS
+The escape sequence
+.Pp
+.Dl \e[uXXXX]
+.Pp
+is interpreted as a Unicode codepoint.
+The codepoint must be in the range above U+0080 and less than U+10FFFF.
+For compatibility, points must be zero-padded to four characters; if
+greater than four characters, no zero padding is allowed.
+Unicode surrogates are not allowed.
+.\" .Pp
+.\" Unicode glyphs attenuate to the
+.\" .Sq \&?
+.\" character if invalid or not rendered by current output media.
 .Sh NUMBERED CHARACTERS
 For backward compatibility with existing manuals,
 .Xr mandoc 1