===================================================================
RCS file: /cvs/mandoc/mandoc.3,v
retrieving revision 1.3
retrieving revision 1.8
diff -u -p -r1.3 -r1.8
--- mandoc/mandoc.3	2011/04/09 15:53:48	1.3
+++ mandoc/mandoc.3	2011/05/17 12:22:15	1.8
@@ -1,4 +1,4 @@
-.\"	$Id: mandoc.3,v 1.3 2011/04/09 15:53:48 kristaps Exp $
+.\"	$Id: mandoc.3,v 1.8 2011/05/17 12:22:15 kristaps Exp $
 .\"
 .\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
 .\" Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
@@ -15,7 +15,7 @@
 .\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 .\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 .\"
-.Dd $Mdocdate: April 9 2011 $
+.Dd $Mdocdate: May 17 2011 $
 .Dt MANDOC 3
 .Os
 .Sh NAME
@@ -23,6 +23,14 @@
 .Nm mandoc_escape ,
 .Nm man_meta ,
 .Nm man_node ,
+.Nm mchars_alloc ,
+.Nm mchars_free ,
+.Nm mchars_num2char ,
+.Nm mchars_num2uc ,
+.Nm mchars_res2cp ,
+.Nm mchars_res2str ,
+.Nm mchars_spec2cp ,
+.Nm mchars_spec2str ,
 .Nm mdoc_meta ,
 .Nm mdoc_node ,
 .Nm mparse_alloc ,
@@ -33,6 +41,8 @@
 .Nm mparse_strerror ,
 .Nm mparse_strlevel
 .Nd mandoc macro compiler library
+.Sh LIBRARY
+.Lb mandoc
 .Sh SYNOPSIS
 .In man.h
 .In mdoc.h
@@ -51,6 +61,42 @@
 .Fo man_node
 .Fa "const struct man *man"
 .Fc
+.Ft "struct mchars *"
+.Fn mchars_alloc
+.Ft void
+.Fn mchars_free "struct mchars *p"
+.Ft char
+.Fn mchars_num2char "const char *cp" "size_t sz"
+.Ft int
+.Fn mchars_num2uc "const char *cp" "size_t sz"
+.Ft "const char *"
+.Fo mchars_res2str
+.Fa "struct mchars *p"
+.Fa "const char *cp"
+.Fa "size_t sz"
+.Fa "size_t *rsz"
+.Fc
+.Ft int
+.Fo mchars_res2cp
+.Fa "struct mchars *p"
+.Fa "const char *cp"
+.Fa "size_t sz"
+.Ft "const char *"
+.Fc
+.Ft "const char *"
+.Fo mchars_spec2str
+.Fa "struct mchars *p"
+.Fa "const char *cp"
+.Fa "size_t sz"
+.Fa "size_t *rsz"
+.Fc
+.Ft int
+.Fo mchars_spec2cp
+.Fa "struct mchars *p"
+.Fa "const char *cp"
+.Fa "size_t sz"
+.Ft "const char *"
+.Fc
 .Ft "const struct mdoc_meta *"
 .Fo mdoc_meta
 .Fa "const struct mdoc *mdoc"
@@ -97,6 +143,8 @@
 .Vt extern const char * const * man_macronames;
 .Vt extern const char * const * mdoc_argnames;
 .Vt extern const char * const * mdoc_macronames;
+.Fd "#define ASCII_NBRSP"
+.Fd "#define ASCII_HYPH"
 .Sh DESCRIPTION
 The
 .Nm mandoc
@@ -138,6 +186,16 @@ or invoke
 .Fn mparse_reset
 and parse new files.
 .El
+.Pp
+The
+.Nm
+library also contains routines for translating character strings into glyphs
+.Pq see Fn mchars_alloc
+and parsing escape sequences from strings
+.Pq see Fn mandoc_escape .
+.Pp
+This library is
+.Ud
 .Sh REFERENCE
 This section documents the functions, types, and variables available
 via
@@ -147,6 +205,11 @@ via
 .It Vt "enum mandoc_esc"
 .It Vt "enum mandocerr"
 .It Vt "enum mandoclevel"
+.It Vt "struct mchars"
+An opaque pointer to an object allowing for translation between
+character strings and glyphs.
+See
+.Fn mchars_alloc .
 .It Vt "enum mparset"
 .It Vt "struct mparse"
 .It Vt "mandocmsg"
@@ -154,23 +217,129 @@ via
 .Ss Functions
 .Bl -ohang
 .It Fn mandoc_escape
+Scan an escape sequence, i.e., a character string beginning with
+.Sq \e .
+Pass a pointer to this string as
+.Va end ;
+it will be set to the supremum of the parsed escape sequence unless
+returning ESCAPE_ERROR, in which case the string is bogus and should be
+thrown away.
+If not ESCAPE_ERROR or ESCAPE_IGNORE,
+.Va start
+is set to the first relevant character of the substring (font, glyph,
+whatever) of length
+.Va sz .
+Both
+.Va start
+and
+.Va sz
+may be NULL.
 .It Fn man_meta
+Obtain the meta-data of a successful parse.
+This may only be used on a pointer returned by
+.Fn mparse_result .
 .It Fn man_node
+Obtain the root node of a successful parse.
+This may only be used on a pointer returned by
+.Fn mparse_result .
+.It Fn mchars_alloc
+Allocate an
+.Vt "struct mchars *"
+object for translating special characters into glyphs.
+See
+.Xr mandoc_char 7
+for an overview of special characters.
+The object must be freed with
+.Fn mchars_free .
+.It Fn mchars_free
+Free an object created with
+.Fn mchars_alloc .
+.It Fn mchars_num2char
+Convert a character index (e.g., the \eN\(aq\(aq escape) into a
+printable ASCII character.
+Returns \e0 (the nil character) if the input sequence is malformed.
+.It Fn mchars_num2uc
+Convert a hexadecimal character index (e.g., the \e[uNNNN] escape) into
+a Unicode codepoint.
+Returns \e0 (the nil character) if the input sequence is malformed.
+.It Fn mchars_res2cp
+Convert a predefined character into a valid Unicode codepoint.
+Returns \-1 on failure and 0 if no code-point exists (if this occurs,
+the caller should fall back to
+.Fn mchars_res2str ) .
+.It Fn mchars_res2str
+Convert a predefined character into an ASCII string.
+Returns NULL on failure.
+.It Fn mchars_spec2cp
+Convert a special character into a valid Unicode codepoint.
+Returns \-1 on failure and 0 if no code-point exists (if this occurs,
+the caller should fall back to
+.Fn mchars_spec2str ) .
+.It Fn mchars_spec2str
+Convert a special character into an ASCII string.
+Returns NULL on failure.
 .It Fn mdoc_meta
+Obtain the meta-data of a successful parse.
+This may only be used on a pointer returned by
+.Fn mparse_result .
 .It Fn mdoc_node
+Obtain the root node of a successful parse.
+This may only be used on a pointer returned by
+.Fn mparse_result .
 .It Fn mparse_alloc
+Allocate a parser.
+The same parser may be used for multiple files so long as
+.Fn mparse_reset
+is called between parses.
+.Fn mparse_free
+must be called to free the memory allocated by this function.
 .It Fn mparse_free
+Free all memory allocated by
+.Fn mparse_alloc .
 .It Fn mparse_readfd
+Parse a file or file descriptor.
+If
+.Va fd
+is -1,
+.Va fname
+is opened for reading.
+Otherwise,
+.Va fname
+is assumed to be the name associated with
+.Va fd .
+This may be called multiple times with different parameters; however,
+.Fn mparse_reset
+should be invoked between parses.
 .It Fn mparse_reset
+Reset a parser so that
+.Fn mparse_readfd
+may be used again.
 .It Fn mparse_result
+Obtain the result of a parse.
+Only successful parses
+.Po
+i.e., those where
+.Fn mparse_readfd
+returned less than MANDOCLEVEL_FATAL
+.Pc
+should invoke this function, in which case one of the two pointers will
+be filled in.
 .It Fn mparse_strerror
+Return a statically-allocated string representation of an error code.
 .It Fn mparse_strlevel
+Return a statically-allocated string representation of a level code.
 .El
 .Ss Variables
 .Bl -ohang
 .It Va man_macronames
+The string representation of a man macro as indexed by
+.Vt "enum mant" .
 .It Va mdoc_argnames
+The string representation of a mdoc macro argument as indexed by
+.Vt "enum mdocargt" .
 .It Va mdoc_macronames
+The string representation of a mdoc macro as indexed by
+.Vt "enum mdoct" .
 .El
 .Sh IMPLEMENTATION NOTES
 This section consists of structural documentation for
@@ -292,7 +461,7 @@ where a new body introduces a new phrase.
 .Pp
 The
 .Xr mdoc 7
-syntax tree accomodates for broken block structures as well.
+syntax tree accommodates for broken block structures as well.
 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
@@ -364,6 +533,7 @@ levels of badly-nested blocks.
 .Xr mandoc 1 ,
 .Xr eqn 7 ,
 .Xr man 7 ,
+.Xr mandoc_char 7 ,
 .Xr mdoc 7 ,
 .Xr roff 7 ,
 .Xr tbl 7