Support for badly nested blocks, written around the time of

[mandoc.git] / mdoc.3

diff --git a/mdoc.3 b/mdoc.3
index 22087afb3b2a83f11be72595b943a15acc591293..f65b4c39e35fc17e6b56c60cea8fcceca60bed31 100644 (file)
--- a/mdoc.3
+++ b/mdoc.3
@@ -1,4 +1,4 @@
-.\"    $Id: mdoc.3,v 1.37 2010/02/17 19:22:01 kristaps Exp $
+.\"    $Id: mdoc.3,v 1.45 2010/06/29 19:20:38 schwarze Exp $

 .\"
 .\" Copyright (c) 2009-2010 Kristaps Dzonsons <kristaps@bsd.lv>
 .\"
 .\"
 .\" Copyright (c) 2009-2010 Kristaps Dzonsons <kristaps@bsd.lv>
 .\"


@@ -14,48 +14,55 @@
 .\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 .\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 .\"
 .\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 .\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 .\"

-.Dd $Mdocdate: February 17 2010 $
+.Dd $Mdocdate: June 29 2010 $

 .Dt MDOC 3
 .Os
 .Dt MDOC 3
 .Os

-.\" SECTION

 .Sh NAME
 .Sh NAME

+.Nm mdoc ,

 .Nm mdoc_alloc ,
 .Nm mdoc_alloc ,

-.Nm mdoc_parseln ,

 .Nm mdoc_endparse ,
 .Nm mdoc_endparse ,

-.Nm mdoc_node ,
-.Nm mdoc_meta ,

 .Nm mdoc_free ,
 .Nm mdoc_free ,

+.Nm mdoc_meta ,
+.Nm mdoc_node ,
+.Nm mdoc_parseln ,

 .Nm mdoc_reset
 .Nd mdoc macro compiler library
 .Nm mdoc_reset
 .Nd mdoc macro compiler library

-.\" SECTION

 .Sh SYNOPSIS
 .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 *"
 .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" "const struct mdoc_cb *cb"
+.Fo mdoc_alloc
+.Fa "struct regset *regs"
+.Fa "void *data"
+.Fa "int pflags"
+.Fa "mandocmsg msgs"
+.Fc

 .Ft int
 .Ft int

-.Fn mdoc_reset "struct mdoc *mdoc"
+.Fn mdoc_endparse "struct mdoc *mdoc"

 .Ft void
 .Fn mdoc_free "struct mdoc *mdoc"
 .Ft void
 .Fn mdoc_free "struct mdoc *mdoc"

-.Ft int
-.Fn mdoc_parseln "struct mdoc *mdoc" "int line" "char *buf"
-.Ft "const struct mdoc_node *"
-.Fn mdoc_node "const struct mdoc *mdoc"

 .Ft "const struct mdoc_meta *"
 .Fn mdoc_meta "const struct mdoc *mdoc"
 .Ft "const struct mdoc_meta *"
 .Fn mdoc_meta "const struct mdoc *mdoc"

+.Ft "const struct mdoc_node *"
+.Fn mdoc_node "const struct mdoc *mdoc"

 .Ft int
 .Ft int

-.Fn mdoc_endparse "struct mdoc *mdoc"
-.\" SECTION
+.Fo mdoc_parseln
+.Fa "struct mdoc *mdoc"
+.Fa "int line"
+.Fa "char *buf"
+.Fc
+.Ft int
+.Fn mdoc_reset "struct mdoc *mdoc"

 .Sh DESCRIPTION
 The
 .Nm mdoc
 library parses lines of
 .Xr mdoc 7
 .Sh DESCRIPTION
 The
 .Nm mdoc
 library parses lines of
 .Xr mdoc 7

-input (and
-.Em only
-mdoc) into an abstract syntax tree (AST).
-.\" PARAGRAPH
+input
+into an abstract syntax tree (AST).

 .Pp
 In general, applications initiate a parsing sequence with
 .Fn mdoc_alloc ,
 .Pp
 In general, applications initiate a parsing sequence with
 .Fn mdoc_alloc ,


@@ -72,20 +79,20 @@ then free all allocated memory with
 The
 .Fn mdoc_reset
 function may be used in order to reset the parser for another input
 The
 .Fn mdoc_reset
 function may be used in order to reset the parser for another input

-sequence.  See the
+sequence.
+See the

 .Sx EXAMPLES
 .Sx EXAMPLES

-section for a full example.
-.\" PARAGRAPH
+section for a simple example.

 .Pp
 This section further defines the
 .Sx Types ,
 .Sx Functions
 and
 .Sx Variables
 .Pp
 This section further defines the
 .Sx Types ,
 .Sx Functions
 and
 .Sx Variables

-available to programmers.  Following that, the
+available to programmers.
+Following that, the

 .Sx Abstract Syntax Tree
 section documents the output tree.
 .Sx Abstract Syntax Tree
 section documents the output tree.

-.\" SUBSECTION

 .Ss Types
 Both functions (see
 .Sx Functions )
 .Ss Types
 Both functions (see
 .Sx Functions )


@@ -93,95 +100,90 @@ and variables (see
 .Sx Variables )
 may use the following types:
 .Bl -ohang
 .Sx Variables )
 may use the following types:
 .Bl -ohang

-.\" LIST-ITEM

 .It Vt struct mdoc
 An opaque type defined in
 .Pa mdoc.c .
 Its values are only used privately within the library.
 .It Vt struct mdoc
 An opaque type defined in
 .Pa mdoc.c .
 Its values are only used privately within the library.

-.\" LIST-ITEM
-.It Vt struct mdoc_cb
-A set of message callbacks defined in
-.Pa mdoc.h .
-.\" LIST-ITEM

 .It Vt struct mdoc_node
 .It Vt struct mdoc_node

-A parsed node.  Defined in
+A parsed node.
+Defined in

 .Pa mdoc.h .
 See
 .Sx Abstract Syntax Tree
 for details.
 .Pa mdoc.h .
 See
 .Sx Abstract Syntax Tree
 for details.

+.It Vt mandocmsg
+A function callback type defined in
+.Pa mandoc.h .

 .El
 .El

-.\" SUBSECTION

 .Ss Functions
 Function descriptions follow:
 .Bl -ohang
 .Ss Functions
 Function descriptions follow:
 .Bl -ohang

-.\" LIST-ITEM

 .It Fn mdoc_alloc
 .It Fn mdoc_alloc

-Allocates a parsing structure.  The
+Allocates a parsing structure.
+The

 .Fa data
 .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
 .Pa mdoc.h .
 The
 .Fa pflags
 arguments are defined in
 .Pa mdoc.h .

-Returns NULL on failure.  If non-NULL, the pointer must be freed with
+Returns NULL on failure.
+If non-NULL, the pointer must be freed with

 .Fn mdoc_free .
 .Fn mdoc_free .

-.\" LIST-ITEM

 .It Fn mdoc_reset
 .It Fn mdoc_reset

-Reset the parser for another parse routine.  After its use,
+Reset the parser for another parse routine.
+After its use,

 .Fn mdoc_parseln
 .Fn mdoc_parseln

-behaves as if invoked for the first time.  If it returns 0, memory could
-not be allocated.
-.\" LIST-ITEM
+behaves as if invoked for the first time.
+If it returns 0, memory could not be allocated.

 .It Fn mdoc_free
 .It Fn mdoc_free

-Free all resources of a parser.  The pointer is no longer valid after
-invocation.
-.\" LIST-ITEM
+Free all resources of a parser.
+The pointer is no longer valid after invocation.

 .It Fn mdoc_parseln
 .It Fn mdoc_parseln

-Parse a nil-terminated line of input.  This line should not contain the
-trailing newline.  Returns 0 on failure, 1 on success.  The input buffer
+Parse a nil-terminated line of input.
+This line should not contain the trailing newline.
+Returns 0 on failure, 1 on success.
+The input buffer

 .Fa buf
 is modified by this function.
 .Fa buf
 is modified by this function.

-.\" LIST-ITEM

 .It Fn mdoc_endparse
 .It Fn mdoc_endparse

-Signals that the parse is complete.  Note that if
+Signals that the parse is complete.
+Note that if

 .Fn mdoc_endparse
 is called subsequent to
 .Fn mdoc_node ,
 .Fn mdoc_endparse
 is called subsequent to
 .Fn mdoc_node ,

-the resulting tree is incomplete.  Returns 0 on failure, 1 on success.
-.\" LIST-ITEM
+the resulting tree is incomplete.
+Returns 0 on failure, 1 on success.

 .It Fn mdoc_node
 .It Fn mdoc_node

-Returns the first node of the parse.  Note that if
+Returns the first node of the parse.
+Note that if

 .Fn mdoc_parseln
 or
 .Fn mdoc_endparse
 return 0, the tree will be incomplete.
 .It Fn mdoc_meta
 .Fn mdoc_parseln
 or
 .Fn mdoc_endparse
 return 0, the tree will be incomplete.
 .It Fn mdoc_meta

-Returns the document's parsed meta-data.  If this information has not
-yet been supplied or
+Returns the document's parsed meta-data.
+If this information has not yet been supplied or

 .Fn mdoc_parseln
 or
 .Fn mdoc_endparse
 return 0, the data will be incomplete.
 .El
 .Fn mdoc_parseln
 or
 .Fn mdoc_endparse
 return 0, the data will be incomplete.
 .El

-.\" SUBSECTION

 .Ss Variables
 The following variables are also defined:
 .Bl -ohang
 .Ss Variables
 The following variables are also defined:
 .Bl -ohang

-.\" LIST-ITEM

 .It Va mdoc_macronames
 An array of string-ified token names.
 .It Va mdoc_macronames
 An array of string-ified token names.

-.\" LIST-ITEM

 .It Va mdoc_argnames
 An array of string-ified token argument names.
 .El
 .It Va mdoc_argnames
 An array of string-ified token argument names.
 .El

-.\" SUBSECTION

 .Ss Abstract Syntax Tree
 The
 .Nm
 functions produce an abstract syntax tree (AST) describing input in a
 .Ss Abstract Syntax Tree
 The
 .Nm
 functions produce an abstract syntax tree (AST) describing input in a

-regular form.  It may be reviewed at any time with
+regular form.
+It may be reviewed at any time with

 .Fn mdoc_nodes ;
 however, if called before
 .Fn mdoc_endparse ,
 .Fn mdoc_nodes ;
 however, if called before
 .Fn mdoc_endparse ,


@@ -190,7 +192,6 @@ or after
 or
 .Fn mdoc_parseln
 fail, it may be incomplete.
 or
 .Fn mdoc_parseln
 fail, it may be incomplete.

-.\" PARAGRAPH

 .Pp
 This AST is governed by the ontological
 rules dictated in
 .Pp
 This AST is governed by the ontological
 rules dictated in


@@ -201,14 +202,14 @@ elements described in
 .Xr mdoc 7
 are described simply as
 .Qq elements .
 .Xr mdoc 7
 are described simply as
 .Qq elements .

-.\" PARAGRAPH

 .Pp
 The AST is composed of
 .Vt struct mdoc_node
 nodes with block, head, body, element, root and text types as declared
 by the
 .Va type
 .Pp
 The AST is composed of
 .Vt struct mdoc_node
 nodes with block, head, body, element, root and text types as declared
 by the
 .Va type

-field.  Each node also provides its parse point (the
+field.
+Each node also provides its parse point (the

 .Va line ,
 .Va sec ,
 and
 .Va line ,
 .Va sec ,
 and


@@ -216,59 +217,121 @@ and
 fields), its position in the tree (the
 .Va parent ,
 .Va child ,
 fields), its position in the tree (the
 .Va parent ,
 .Va child ,

+.Va nchild ,

 .Va next
 and
 .Va prev
 .Va next
 and
 .Va prev

-fields) and some type-specific data.
-.\" PARAGRAPH
+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.
 .Pp
 .Bl -tag -width "ELEMENTXX" -compact
 .Pp
 The tree itself is arranged according to the following normal form,
 where capitalised non-terminals represent nodes.
 .Pp
 .Bl -tag -width "ELEMENTXX" -compact

-.\" LIST-ITEM

 .It ROOT
 \(<- mnode+
 .It mnode
 \(<- BLOCK | ELEMENT | TEXT
 .It BLOCK
 .It ROOT
 \(<- mnode+
 .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
 .It ELEMENT
 \(<- TEXT*
 .It HEAD

-\(<- mnode+
+\(<- mnode*

 .It BODY
 .It BODY

-\(<- mnode+
+\(<- mnode* [ENDBODY mnode*]

 .It TAIL
 .It TAIL

-\(<- mnode+
+\(<- mnode*

 .It TEXT
 .It TEXT

-\(<- [[:alpha:]]*
+\(<- [[:printable:],0x1e]*

 .El
 .El

-.\" PARAGRAPH

 .Pp
 Of note are the TEXT nodes following the HEAD, BODY and TAIL nodes of
 .Pp
 Of note are the TEXT nodes following the HEAD, BODY and TAIL nodes of

-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
+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.
 .Sq \&.Bd \-literal ,
 an empty line will produce a zero-length string.

-.\" SECTION
+Multiple body parts are only found in invocations of
+.Sq \&Bl \-column ,
+where a new body introduces a new phrase.
+.Ss Badly nested blocks
+A special kind of node is available to end the formatting
+associated with a given block before the physical end of that block.
+Such an ENDBODY node 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 Ao block extends from TEXT ao to TEXT ac,
+while the formatting of the Bo block extends from TEXT bo to TEXT bc,
+rendering like this in
+.Fl T Ns Cm ascii
+mode:
+.Dl <ao [bo ac> bc] end
+Support for badly nested blocks is only provided for backward
+compatibility with some older
+.Xr mdoc 7
+implementations.
+Using them in new code is stronly discouraged:
+Some frontends, in particular
+.Fl T Ns Cm html ,
+are unable to render them in any meaningful way,
+many other
+.Xr mdoc 7
+implementations do not support them, and even for those that do,
+the behaviour is not well-defined, in particular 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
 .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;
 
 struct mdoc *mdoc;
 const struct mdoc_node *node;
 char *buf;
 size_t len;
 int line;
 

+bzero(&regs, sizeof(struct regset));

 line = 1;
 line = 1;

-mdoc = mdoc_alloc(NULL, 0, NULL);
+mdoc = mdoc_alloc(&regs, NULL, 0, NULL);

 buf = NULL;
 alloc_len = 0;
 
 buf = NULL;
 alloc_len = 0;
 


@@ -288,49 +351,15 @@ if (NULL == (node = mdoc_node(mdoc)))
 parsed(mdoc, node);
 mdoc_free(mdoc);
 .Ed
 parsed(mdoc, node);
 mdoc_free(mdoc);
 .Ed

-.\" SECTION
+.Pp
+Please see
+.Pa main.c
+in the source archive for a rigorous reference.

 .Sh SEE ALSO
 .Xr mandoc 1 ,
 .Xr mdoc 7
 .Sh SEE ALSO
 .Xr mandoc 1 ,
 .Xr mdoc 7

-.\" SECTION

 .Sh AUTHORS
 The
 .Nm
 .Sh AUTHORS
 The
 .Nm

-utility was written by
+library was written by

 .An Kristaps Dzonsons Aq kristaps@bsd.lv .
 .An Kristaps Dzonsons Aq kristaps@bsd.lv .

-.\" SECTION
-.Sh CAVEATS
-.Bl -dash -compact
-.\" LIST-ITEM
-.It
-The
-.Sq \&.Xc
-and
-.Sq \&.Xo
-macros aren't handled when used to span lines for the
-.Sq \&.It
-macro.
-.\" LIST-ITEM
-.It
-The
-.Sq \&.Bsx
-macro family doesn't yet understand version arguments.
-.\" LIST-ITEM
-.It
-If not given a value, the \-offset argument to
-.Sq \&.Bd
-and
-.Sq \&.Bl
-should be the width of
-.Qq <string> ;
-instead, a value of
-.Li 10n
-is provided.
-.\" LIST-ITEM
-.It
-Columns widths in
-.Sq \&.Bl \-column
-should default to width
-.Qq <stringx>
-if not included.
-.El