Further apropos(1) speed optimization was trickier than anticipated.

[mandoc.git] / mandoc.3

diff --git a/mandoc.3 b/mandoc.3
index ec765c6bd9c7f3b3572fda003efdd840ebc4d6e2..2e6b78b96a3f9eb5e146ee2be6ee4ed1ef31f420 100644 (file)
--- a/mandoc.3
+++ b/mandoc.3
@@ -1,4 +1,4 @@
-.\"    $Id: mandoc.3,v 1.3 2011/04/09 15:53:48 kristaps Exp $
+.\"    $Id: mandoc.3,v 1.24 2014/03/23 11:25:26 schwarze Exp $

 .\"
 .\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
 .\" Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
 .\"
 .\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
 .\" Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>


@@ -15,61 +15,114 @@
 .\" 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: April 9 2011 $
+.Dd $Mdocdate: March 23 2014 $

 .Dt MANDOC 3
 .Os
 .Sh NAME
 .Nm mandoc ,
 .Dt MANDOC 3
 .Os
 .Sh NAME
 .Nm mandoc ,

+.Nm mandoc_calloc ,

 .Nm mandoc_escape ,
 .Nm mandoc_escape ,

+.Nm mandoc_malloc ,
+.Nm mandoc_realloc ,
+.Nm mandoc_strdup ,
+.Nm mandoc_strndup ,

 .Nm man_meta ,
 .Nm man_meta ,

+.Nm man_mparse ,

 .Nm man_node ,
 .Nm man_node ,

+.Nm mchars_alloc ,
+.Nm mchars_free ,
+.Nm mchars_num2char ,
+.Nm mchars_num2uc ,
+.Nm mchars_spec2cp ,
+.Nm mchars_spec2str ,

 .Nm mdoc_meta ,
 .Nm mdoc_node ,
 .Nm mparse_alloc ,
 .Nm mparse_free ,
 .Nm mdoc_meta ,
 .Nm mdoc_node ,
 .Nm mparse_alloc ,
 .Nm mparse_free ,

+.Nm mparse_getkeep ,
+.Nm mparse_keep ,

 .Nm mparse_readfd ,
 .Nm mparse_reset ,
 .Nm mparse_result ,
 .Nm mparse_strerror ,
 .Nm mparse_strlevel
 .Nd mandoc macro compiler library
 .Nm mparse_readfd ,
 .Nm mparse_reset ,
 .Nm mparse_result ,
 .Nm mparse_strerror ,
 .Nm mparse_strlevel
 .Nd mandoc macro compiler library

+.Sh LIBRARY
+.Lb libmandoc

 .Sh SYNOPSIS
 .Sh SYNOPSIS

-.In man.h
-.In mdoc.h

 .In mandoc.h
 .In mandoc.h

+.Fd "#define ASCII_NBRSP"
+.Fd "#define ASCII_HYPH"
+.Fd "#define ASCII_BREAK"
+.Ft "void *"
+.Fo mandoc_calloc
+.Fa "size_t nmemb"
+.Fa "size_t size"
+.Fc

 .Ft "enum mandoc_esc"
 .Fo mandoc_escape
 .Ft "enum mandoc_esc"
 .Fo mandoc_escape

-.Fa "const char **in"
-.Fa "const char **seq"
-.Fa "int *len"
-.Fc
-.Ft "const struct man_meta *"
-.Fo man_meta
-.Fa "const struct man *man"
+.Fa "const char **end"
+.Fa "const char **start"
+.Fa "int *sz"

 .Fc
 .Fc

-.Ft "const struct man_node *"
-.Fo man_node
-.Fa "const struct man *man"
+.Ft "void *"
+.Fn mandoc_malloc "size_t size"
+.Ft "struct mchars *"
+.Fo mandoc_realloc
+.Fa "void *ptr"
+.Fa "size_t size"

 .Fc
 .Fc

-.Ft "const struct mdoc_meta *"
-.Fo mdoc_meta
-.Fa "const struct mdoc *mdoc"
+.Ft "char *"
+.Fn mandoc_strdup
+.Fn mchars_alloc "void"
+.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_spec2str
+.Fa "const struct mchars *p"
+.Fa "const char *cp"
+.Fa "size_t sz"
+.Fa "size_t *rsz"

 .Fc
 .Fc

-.Ft "const struct mdoc_node *"
-.Fo mdoc_node
-.Fa "const struct mdoc *mdoc"
+.Ft int
+.Fo mchars_spec2cp
+.Fa "const struct mchars *p"
+.Fa "const char *cp"
+.Fa "size_t sz"

 .Fc
 .Ft void
 .Fo mparse_alloc
 .Fc
 .Ft void
 .Fo mparse_alloc

-.Fa "enum mparset type"
+.Fa "enum mparset inttype"

 .Fa "enum mandoclevel wlevel"
 .Fa "enum mandoclevel wlevel"

-.Fa "mandocmsg msg"
-.Fa "void *msgarg"
+.Fa "mandocmsg mmsg"
+.Fa "char *defos"
+.Fa "int quick"
+.Fc
+.Ft void
+.Fo (*mandocmsg)
+.Fa "enum mandocerr errtype"
+.Fa "enum mandoclevel level"
+.Fa "const char *file"
+.Fa "int line"
+.Fa "int col"
+.Fa "const char *msg"

 .Fc
 .Ft void
 .Fo mparse_free
 .Fa "struct mparse *parse"
 .Fc
 .Fc
 .Ft void
 .Fo mparse_free
 .Fa "struct mparse *parse"
 .Fc

+.Ft const char *
+.Fo mparse_getkeep
+.Fa "const struct mparse *parse"
+.Fc
+.Ft void
+.Fo mparse_keep
+.Fa "struct mparse *parse"
+.Fc

 .Ft "enum mandoclevel"
 .Fo mparse_readfd
 .Fa "struct mparse *parse"
 .Ft "enum mandoclevel"
 .Fo mparse_readfd
 .Fa "struct mparse *parse"


@@ -94,9 +147,33 @@
 .Fo mparse_strlevel
 .Fa "enum mandoclevel"
 .Fc
 .Fo mparse_strlevel
 .Fa "enum mandoclevel"
 .Fc

-.Vt extern const char * const * man_macronames;
+.In mandoc.h
+.In mdoc.h
+.Ft "const struct mdoc_meta *"
+.Fo mdoc_meta
+.Fa "const struct mdoc *mdoc"
+.Fc
+.Ft "const struct mdoc_node *"
+.Fo mdoc_node
+.Fa "const struct mdoc *mdoc"
+.Fc

 .Vt extern const char * const * mdoc_argnames;
 .Vt extern const char * const * mdoc_macronames;
 .Vt extern const char * const * mdoc_argnames;
 .Vt extern const char * const * mdoc_macronames;

+.In mandoc.h
+.In man.h
+.Ft "const struct man_meta *"
+.Fo man_meta
+.Fa "const struct man *man"
+.Fc
+.Ft "const struct mparse *"
+.Fo man_mparse
+.Fa "const struct man *man"
+.Fc
+.Ft "const struct man_node *"
+.Fo man_node
+.Fa "const struct man *man"
+.Fc
+.Vt extern const char * const * man_macronames;

 .Sh DESCRIPTION
 The
 .Nm mandoc
 .Sh DESCRIPTION
 The
 .Nm mandoc


@@ -138,6 +215,13 @@ or invoke
 .Fn mparse_reset
 and parse new files.
 .El
 .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 .

 .Sh REFERENCE
 This section documents the functions, types, and variables available
 via
 .Sh REFERENCE
 This section documents the functions, types, and variables available
 via


@@ -145,39 +229,329 @@ via
 .Ss Types
 .Bl -ohang
 .It Vt "enum mandoc_esc"
 .Ss Types
 .Bl -ohang
 .It Vt "enum mandoc_esc"

+An escape sequence classification.

 .It Vt "enum mandocerr"
 .It Vt "enum mandocerr"

+A fatal error, error, or warning message during parsing.

 .It Vt "enum mandoclevel"
 .It Vt "enum mandoclevel"

+A classification of an
+.Vt "enum mandocerr"
+as regards system operation.
+.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 "enum mparset"

+The type of parser when reading input.
+This should usually be
+.Dv MPARSE_AUTO
+for auto-detection.

 .It Vt "struct mparse"
 .It Vt "struct mparse"

+An opaque pointer to a running parse sequence.
+Created with
+.Fn mparse_alloc
+and freed with
+.Fn mparse_free .
+This may be used across parsed input if
+.Fn mparse_reset
+is called between parses.

 .It Vt "mandocmsg"
 .It Vt "mandocmsg"

+A prototype for a function to handle fatal error, error, and warning
+messages emitted by the parser.

 .El
 .Ss Functions
 .Bl -ohang
 .It Fn mandoc_escape
 .El
 .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 the character after the
+.Sq \e
+as
+.Va end ;
+it will be set to the supremum of the parsed escape sequence unless
+returning
+.Dv ESCAPE_ERROR ,
+in which case the string is bogus and should be
+thrown away.
+If not
+.Dv ESCAPE_ERROR
+or
+.Dv 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
+.Dv NULL .
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa mandoc.c .

 .It Fn man_meta
 .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 .
+Declared in
+.In man.h ,
+implemented in
+.Pa man.c .
+.It Fn man_mparse
+Get the parser used for the current output.
+Declared in
+.In man.h ,
+implemented in
+.Pa man.c .

 .It Fn man_node
 .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 .
+Declared in
+.In man.h ,
+implemented in
+.Pa man.c .
+.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 .
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa chars.c .
+.It Fn mchars_free
+Free an object created with
+.Fn mchars_alloc .
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa chars.c .
+.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.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa chars.c .
+.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.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa chars.c .
+.It Fn mchars_spec2cp
+Convert a special character into a valid Unicode codepoint.
+Returns \-1 on failure or a non-zero Unicode codepoint on success.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa chars.c .
+.It Fn mchars_spec2str
+Convert a special character into an ASCII string.
+Returns
+.Dv NULL
+on failure.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa chars.c .

 .It Fn mdoc_meta
 .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 .
+Declared in
+.In mdoc.h ,
+implemented in
+.Pa mdoc.c .

 .It Fn mdoc_node
 .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 .
+Declared in
+.In mdoc.h ,
+implemented in
+.Pa mdoc.c .

 .It Fn mparse_alloc
 .It Fn mparse_alloc

+Allocate a parser.
+The arguments have the following effect:
+.Bl -tag -offset 5n -width inttype
+.It Ar inttype
+When set to
+.Dv MPARSE_MDOC
+or
+.Dv MPARSE_MAN ,
+only that parser will be used.
+With
+.Dv MPARSE_AUTO ,
+the document type will be automatically detected.
+.It Ar wlevel
+Can be set to
+.Dv MANDOCLEVEL_FATAL ,
+.Dv MANDOCLEVEL_ERROR ,
+or
+.Dv MANDOCLEVEL_WARNING .
+Messages below the selected level will be suppressed.
+.It Ar mmsg
+A callback function to handle errors and warnings.
+See
+.Pa main.c
+for an example.
+.It Ar defos
+A default string for the
+.Xr mdoc 7
+.Sq \&Os
+macro, overriding the
+.Dv OSNAME
+preprocessor definition and the results of
+.Xr uname 3 .
+.It Ar quick
+When set, parsing is aborted after the NAME section.
+This is for example useful to quickly build minimal databases.
+.El
+.Pp
+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.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_free
 .It Fn mparse_free

+Free all memory allocated by
+.Fn mparse_alloc .
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .
+.It Fn mparse_getkeep
+Acquire the keep buffer.
+Must follow a call of
+.Fn mparse_keep .
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .
+.It Fn mparse_keep
+Instruct the parser to retain a copy of its parsed input.
+This can be acquired with subsequent
+.Fn mparse_getkeep
+calls.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_readfd
 .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.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_reset
 .It Fn mparse_reset

+Reset a parser so that
+.Fn mparse_readfd
+may be used again.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_result
 .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.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_strerror
 .It Fn mparse_strerror

+Return a statically-allocated string representation of an error code.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_strlevel
 .It Fn mparse_strlevel

+Return a statically-allocated string representation of a level code.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .El
 .Ss Variables
 .Bl -ohang
 .It Va man_macronames
 .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
 .It Va mdoc_argnames

+The string representation of a mdoc macro argument as indexed by
+.Vt "enum mdocargt" .

 .It Va mdoc_macronames
 .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
 .Xr mdoc 7
 and
 .Xr man 7
 .El
 .Sh IMPLEMENTATION NOTES
 This section consists of structural documentation for
 .Xr mdoc 7
 and
 .Xr man 7

-syntax trees.
+syntax trees and strings.
+.Ss Man and Mdoc Strings
+Strings may be extracted from mdoc and man meta-data, or from text
+nodes (MDOC_TEXT and MAN_TEXT, respectively).
+These strings have special non-printing formatting cues embedded in the
+text itself, as well as
+.Xr roff 7
+escapes preserved from input.
+Implementing systems will need to handle both situations to produce
+human-readable text.
+In general, strings may be assumed to consist of 7-bit ASCII characters.
+.Pp
+The following non-printing characters may be embedded in text strings:
+.Bl -tag -width Ds
+.It Dv ASCII_NBRSP
+A non-breaking space character.
+.It Dv ASCII_HYPH
+A soft hyphen.
+.El
+.Pp
+Escape characters are also passed verbatim into text strings.
+An escape character is a sequence of characters beginning with the
+backslash
+.Pq Sq \e .
+To construct human-readable text, these should be intercepted with
+.Fn mandoc_escape
+and converted with one of
+.Fn mchars_num2char ,
+.Fn mchars_spec2str ,
+and so on.

 .Ss Man Abstract Syntax Tree
 This AST is governed by the ontological rules dictated in
 .Xr man 7
 .Ss Man Abstract Syntax Tree
 This AST is governed by the ontological rules dictated in
 .Xr man 7


@@ -218,7 +592,7 @@ where capitalised non-terminals represent nodes.
 .It ELEMENT
 \(<- ELEMENT | TEXT*
 .It TEXT
 .It ELEMENT
 \(<- ELEMENT | TEXT*
 .It TEXT

-\(<- [[:alpha:]]*
+\(<- [[:ascii:]]*

 .El
 .Pp
 The only elements capable of nesting other elements are those with
 .El
 .Pp
 The only elements capable of nesting other elements are those with


@@ -277,7 +651,7 @@ where capitalised non-terminals represent nodes.
 .It TAIL
 \(<- mnode*
 .It TEXT
 .It TAIL
 \(<- mnode*
 .It TEXT

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

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


@@ -292,7 +666,7 @@ where a new body introduces a new phrase.
 .Pp
 The
 .Xr mdoc 7
 .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
 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 +738,7 @@ levels of badly-nested blocks.
 .Xr mandoc 1 ,
 .Xr eqn 7 ,
 .Xr man 7 ,
 .Xr mandoc 1 ,
 .Xr eqn 7 ,
 .Xr man 7 ,

+.Xr mandoc_char 7 ,

 .Xr mdoc 7 ,
 .Xr roff 7 ,
 .Xr tbl 7
 .Xr mdoc 7 ,
 .Xr roff 7 ,
 .Xr tbl 7


@@ -371,4 +746,4 @@ levels of badly-nested blocks.
 The
 .Nm
 library was written by
 The
 .Nm
 library was written by

-.An Kristaps Dzonsons Aq kristaps@bsd.lv .
+.An Kristaps Dzonsons Aq Mt kristaps@bsd.lv .