===================================================================
RCS file: /cvs/mandoc/Attic/mdoc.3,v
retrieving revision 1.38
retrieving revision 1.46
diff -u -p -r1.38 -r1.46
--- mandoc/Attic/mdoc.3	2010/05/25 21:38:05	1.38
+++ mandoc/Attic/mdoc.3	2010/07/01 09:33:39	1.46
@@ -1,4 +1,4 @@
-.\"	$Id: mdoc.3,v 1.38 2010/05/25 21:38:05 kristaps Exp $
+.\"	$Id: mdoc.3,v 1.46 2010/07/01 09:33:39 kristaps Exp $
 .\"
 .\" Copyright (c) 2009-2010 Kristaps Dzonsons <kristaps@bsd.lv>
 .\"
@@ -14,10 +14,11 @@
 .\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 .\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 .\"
-.Dd $Mdocdate: May 25 2010 $
+.Dd $Mdocdate: July 1 2010 $
 .Dt MDOC 3
 .Os
 .Sh NAME
+.Nm mdoc ,
 .Nm mdoc_alloc ,
 .Nm mdoc_endparse ,
 .Nm mdoc_free ,
@@ -28,11 +29,17 @@
 .Nd mdoc macro compiler library
 .Sh SYNOPSIS
 .In mandoc.h
+.In regs.h
 .In mdoc.h
 .Vt extern const char * const * mdoc_macronames;
 .Vt extern const char * const * mdoc_argnames;
 .Ft "struct mdoc *"
-.Fn mdoc_alloc "void *data" "int pflags" "mandocmsg msgs"
+.Fo mdoc_alloc
+.Fa "struct regset *regs"
+.Fa "void *data"
+.Fa "int pflags"
+.Fa "mandocmsg msgs"
+.Fc
 .Ft int
 .Fn mdoc_endparse "struct mdoc *mdoc"
 .Ft void
@@ -42,7 +49,11 @@
 .Ft "const struct mdoc_node *"
 .Fn mdoc_node "const struct mdoc *mdoc"
 .Ft int
-.Fn mdoc_parseln "struct mdoc *mdoc" "int line" "char *buf"
+.Fo mdoc_parseln
+.Fa "struct mdoc *mdoc"
+.Fa "int line"
+.Fa "char *buf"
+.Fc
 .Ft int
 .Fn mdoc_reset "struct mdoc *mdoc"
 .Sh DESCRIPTION
@@ -111,9 +122,8 @@ Function descriptions follow:
 Allocates a parsing structure.
 The
 .Fa data
-pointer is passed to callbacks in
-.Fa cb ,
-which are documented further in the header file.
+pointer is passed to
+.Fa msgs .
 The
 .Fa pflags
 arguments are defined in
@@ -207,10 +217,14 @@ and
 fields), its position in the tree (the
 .Va parent ,
 .Va child ,
+.Va nchild ,
 .Va next
 and
 .Va prev
-fields) and some type-specific data.
+fields) and some type-specific data, in particular, for nodes generated
+from macros, the generating macro in the
+.Va tok
+field.
 .Pp
 The tree itself is arranged according to the following normal form,
 where capitalised non-terminals represent nodes.
@@ -221,42 +235,110 @@ where capitalised non-terminals represent nodes.
 .It mnode
 \(<- BLOCK | ELEMENT | TEXT
 .It BLOCK
-\(<- (HEAD [TEXT])+ [BODY [TEXT]] [TAIL [TEXT]]
-.It BLOCK
-\(<- BODY [TEXT] [TAIL [TEXT]]
+\(<- HEAD [TEXT] (BODY [TEXT])+ [TAIL [TEXT]]
 .It ELEMENT
 \(<- TEXT*
 .It HEAD
-\(<- mnode+
+\(<- mnode*
 .It BODY
-\(<- mnode+
+\(<- mnode* [ENDBODY mnode*]
 .It TAIL
-\(<- mnode+
+\(<- mnode*
 .It TEXT
 \(<- [[:printable:],0x1e]*
 .El
 .Pp
 Of note are the TEXT nodes following the HEAD, BODY and TAIL nodes of
-the BLOCK production.
-These refer to punctuation marks.
+the BLOCK production: these refer to punctuation marks.
 Furthermore, although a TEXT node will generally have a non-zero-length
 string, in the specific case of
 .Sq \&.Bd \-literal ,
 an empty line will produce a zero-length string.
+Multiple body parts are only found in invocations of
+.Sq \&Bl \-column ,
+where a new body introduces a new phrase.
+.Ss Badly-nested Blocks
+The ENDBODY node is available to end the formatting associated
+with a given block before the physical end of that block.
+It has a non-null
+.Va end
+field, is of the BODY
+.Va type ,
+has the same
+.Va tok
+as the BLOCK it is ending, and has a
+.Va pending
+field pointing to that BLOCK's BODY node.
+It is an indirect child of that BODY node
+and has no children of its own.
+.Pp
+An ENDBODY node is generated when a block ends while one of its child
+blocks is still open, like in the following example:
+.Bd -literal -offset indent
+\&.Ao ao
+\&.Bo bo ac
+\&.Ac bc
+\&.Bc end
+.Ed
+.Pp
+This example results in the following block structure:
+.Bd -literal -offset indent
+BLOCK Ao
+	HEAD Ao
+	BODY Ao
+		TEXT ao
+		BLOCK Bo, pending -> Ao
+			HEAD Bo
+			BODY Bo
+				TEXT bo
+				TEXT ac
+				ENDBODY Ao, pending -> Ao
+				TEXT bc
+TEXT end
+.Ed
+.Pp
+Here, the formatting of the
+.Sq \&Ao
+block extends from TEXT ao to TEXT ac,
+while the formatting of the
+.Sq \&Bo
+block extends from TEXT bo to TEXT bc.
+It renders as follows in
+.Fl T Ns Cm ascii
+mode:
+.Pp
+.Dl <ao [bo ac> bc] end
+.Pp
+Support for badly-nested blocks is only provided for backward
+compatibility with some older
+.Xr mdoc 7
+implementations.
+Using badly-nested blocks is
+.Em strongly discouraged :
+the
+.Fl T Ns Cm html
+and
+.Fl T Ns Cm xhtml
+front-ends are unable to render them in any meaningful way.
+Furthermore, behaviour when encountering badly-nested blocks is not
+consistent across troff implementations, especially when using  multiple
+levels of badly-nested blocks.
 .Sh EXAMPLES
 The following example reads lines from stdin and parses them, operating
 on the finished parse tree with
 .Fn parsed .
 This example does not error-check nor free memory upon failure.
 .Bd -literal -offset indent
+struct regset regs;
 struct mdoc *mdoc;
 const struct mdoc_node *node;
 char *buf;
 size_t len;
 int line;
 
+bzero(&regs, sizeof(struct regset));
 line = 1;
-mdoc = mdoc_alloc(NULL, 0, NULL);
+mdoc = mdoc_alloc(&regs, NULL, 0, NULL);
 buf = NULL;
 alloc_len = 0;