stricter parsing of Unicode escape names

[mandoc.git] / mandoc.3

diff --git a/mandoc.3 b/mandoc.3
index 3c3dcc085050e294988c933ab4f2db488f565621..2ee6eae181d3ebcb39409dcdece29be7e8f27c40 100644 (file)
--- a/mandoc.3
+++ b/mandoc.3
@@ -1,4 +1,4 @@
-.\"    $Id: mandoc.3,v 1.4 2011/04/19 16:30:00 kristaps Exp $
+.\"    $Id: mandoc.3,v 1.26 2014/09/03 23:21:47 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>


@@ -15,60 +15,72 @@
 .\" 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 19 2011 $
+.Dd $Mdocdate: September 3 2014 $

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

-.Nm mandoc_escape ,
+.Nm man_deroff ,

 .Nm man_meta ,
 .Nm man_meta ,

+.Nm man_mparse ,

 .Nm man_node ,
 .Nm man_node ,

+.Nm mdoc_deroff ,

 .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_open ,

 .Nm mparse_readfd ,
 .Nm mparse_reset ,
 .Nm mparse_result ,
 .Nm mparse_strerror ,
 .Nm mparse_strlevel
 .Nm mparse_readfd ,
 .Nm mparse_reset ,
 .Nm mparse_result ,
 .Nm mparse_strerror ,
 .Nm mparse_strlevel

+.Nm mparse_wait ,

 .Nd mandoc macro compiler library
 .Nd mandoc macro compiler library

+.Sh LIBRARY
+.Lb libmandoc

 .Sh SYNOPSIS
 .Sh SYNOPSIS

-.In man.h
-.In mdoc.h
+.In sys/types.h

 .In mandoc.h
 .In mandoc.h

-.Ft "enum mandoc_esc"
-.Fo mandoc_escape
-.Fa "const char **in"
-.Fa "const char **seq"
-.Fa "int *len"
+.Fd "#define ASCII_NBRSP"
+.Fd "#define ASCII_HYPH"
+.Fd "#define ASCII_BREAK"
+.Ft struct mparse *
+.Fo mparse_alloc
+.Fa "int options"
+.Fa "enum mandoclevel wlevel"
+.Fa "mandocmsg mmsg"
+.Fa "char *defos"

 .Fc
 .Fc

-.Ft "const struct man_meta *"
-.Fo man_meta
-.Fa "const struct man *man"
+.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
 .Fc

-.Ft "const struct man_node *"
-.Fo man_node
-.Fa "const struct man *man"
+.Ft void
+.Fo mparse_free
+.Fa "struct mparse *parse"

 .Fc
 .Fc

-.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"
+.Ft const char *
+.Fo mparse_getkeep
+.Fa "const struct mparse *parse"

 .Fc
 .Ft void
 .Fc
 .Ft void

-.Fo mparse_alloc
-.Fa "enum mparset type"
-.Fa "enum mandoclevel wlevel"
-.Fa "mandocmsg msg"
-.Fa "void *msgarg"
+.Fo mparse_keep
+.Fa "struct mparse *parse"

 .Fc
 .Fc

-.Ft void
-.Fo mparse_free
+.Ft "enum mandoclevel"
+.Fo mparse_open

 .Fa "struct mparse *parse"
 .Fa "struct mparse *parse"

+.Fa "int *fd"
+.Fa "const char *fname"
+.Fa "pid_t *child_pid"

 .Fc
 .Ft "enum mandoclevel"
 .Fo mparse_readfd
 .Fc
 .Ft "enum mandoclevel"
 .Fo mparse_readfd


@@ -85,6 +97,7 @@
 .Fa "struct mparse *parse"
 .Fa "struct mdoc **mdoc"
 .Fa "struct man **man"
 .Fa "struct mparse *parse"
 .Fa "struct mdoc **mdoc"
 .Fa "struct man **man"

+.Fa "char **sodest"

 .Fc
 .Ft "const char *"
 .Fo mparse_strerror
 .Fc
 .Ft "const char *"
 .Fo mparse_strerror


@@ -94,11 +107,50 @@
 .Fo mparse_strlevel
 .Fa "enum mandoclevel"
 .Fc
 .Fo mparse_strlevel
 .Fa "enum mandoclevel"
 .Fc

-.Vt extern const char * const * man_macronames;
+.Ft "enum mandoclevel"
+.Fo mparse_wait
+.Fa "struct mparse *parse"
+.Fa "pid_t child_pid"
+.Fc
+.In sys/types.h
+.In mandoc.h
+.In mdoc.h
+.Ft void
+.Fo mdoc_deroff
+.Fa "char **dest"
+.Fa "const struct mdoc_node *node"
+.Fc
+.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;

-.Fd "#define ASCII_NBRSP"
-.Fd "#define ASCII_HYPH"
+.In sys/types.h
+.In mandoc.h
+.In man.h
+.Ft void
+.Fo man_deroff
+.Fa "char **dest"
+.Fa "const struct man_node *node"
+.Fc
+.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


@@ -143,62 +195,213 @@ and parse new files.
 .Sh REFERENCE
 This section documents the functions, types, and variables available
 via
 .Sh REFERENCE
 This section documents the functions, types, and variables available
 via

-.In mandoc.h .
+.In mandoc.h ,
+with the exception of those documented in
+.Xr mandoc_escape 3
+and
+.Xr mchars_alloc 3 .

 .Ss Types
 .Bl -ohang
 .Ss Types
 .Bl -ohang

-.It Vt "enum mandoc_esc"

 .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"

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

 .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
 .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 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_deroff
+Obtain a text-only representation of a
+.Vt struct man_node ,
+including text contained in its child nodes.
+To be used on children of the pointer returned from
+.Fn man_node .
+When it is no longer needed, the pointer returned from
+.Fn man_deroff
+can be passed to
+.Xr free 3 .

 .It Fn man_meta
 .It Fn man_meta

-Obtain the meta-data of a successful parse.
+Obtain the meta-data of a successful
+.Xr man 7
+parse.

 This may only be used on a pointer returned by
 .Fn mparse_result .
 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.
+Obtain the root node of a successful
+.Xr man 7
+parse.

 This may only be used on a pointer returned by
 .Fn mparse_result .
 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 mdoc_deroff
+Obtain a text-only representation of a
+.Vt struct mdoc_node ,
+including text contained in its child nodes.
+To be used on children of the pointer returned from
+.Fn mdoc_node .
+When it is no longer needed, the pointer returned from
+.Fn mdoc_deroff
+can be passed to
+.Xr free 3 .

 .It Fn mdoc_meta
 .It Fn mdoc_meta

-Obtain the meta-data of a successful parse.
+Obtain the meta-data of a successful
+.Xr mdoc
+parse.

 This may only be used on a pointer returned by
 .Fn mparse_result .
 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.
+Obtain the root node of a successful
+.Xr mdoc
+parse.

 This may only be used on a pointer returned by
 .Fn mparse_result .
 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
 Allocate a parser.
 .It Fn mparse_alloc
 Allocate a parser.

+The arguments have the following effect:
+.Bl -tag -offset 5n -width inttype
+.It Ar options
+When the
+.Dv MPARSE_MDOC
+or
+.Dv MPARSE_MAN
+bit is set, only that parser is used.
+Otherwise, the document type is automatically detected.
+.Pp
+When the
+.Dv MPARSE_SO
+bit is set,
+.Xr roff 7
+.Ic \&so
+file inclusion requests are always honoured.
+Otherwise, if the request is the only content in an input file,
+only the file name is remembered, to be returned in the
+.Fa sodest
+argument of
+.Fn mparse_result .
+.Pp
+When the
+.Dv MPARSE_QUICK
+bit is set, parsing is aborted after the NAME section.
+This is for example useful in
+.Xr makewhatis 8
+.Fl Q
+to quickly build minimal databases.
+.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 .
+.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.
 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
 Free all memory allocated by
 .Fn mparse_alloc .
 .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_open
+If the
+.Fa fname
+ends in
+.Pa .gz ,
+open with
+.Xr gunzip 1 ;
+otherwise, with
+.Xr open 2 .
+Return a file descriptor open for reading in
+.Fa fd ,
+or -1 on failure.
+It can be passed to
+.Fn mparse_readfd
+or used directly.
+If applicable, return the
+.Xr gunzip 1
+child process ID in
+.Fa child_pid ,
+or otherwise 0.
+If non-zero, it should be passed to
+.Fn mparse_wait
+after completing the parse sequence.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .It Fn mparse_readfd
 Parse a file or file descriptor.
 If
 .It Fn mparse_readfd
 Parse a file or file descriptor.
 If


@@ -213,10 +416,18 @@ is assumed to be the name associated with
 This may be called multiple times with different parameters; however,
 .Fn mparse_reset
 should be invoked between parses.
 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
 Reset a parser so that
 .Fn mparse_readfd
 may be used again.
 .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
 Obtain the result of a parse.
 Only successful parses
 .It Fn mparse_result
 Obtain the result of a parse.
 Only successful parses


@@ -225,12 +436,45 @@ i.e., those where
 .Fn mparse_readfd
 returned less than MANDOCLEVEL_FATAL
 .Pc
 .Fn mparse_readfd
 returned less than MANDOCLEVEL_FATAL
 .Pc

-should invoke this function, in which case one of the two pointers will
+should invoke this function, in which case one of the three pointers will

 be filled in.
 be filled in.

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

 .It Fn mparse_strerror
 Return a statically-allocated string representation of an error code.
 .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
 Return a statically-allocated string representation of a level code.
 .It Fn mparse_strlevel
 Return a statically-allocated string representation of a level code.

+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .
+.It Fn mparse_wait
+Bury a
+.Xr gunzip 1
+child process
+.Fa child_pid
+that was spawned with
+.Fn mparse_open .
+To be called after the parse sequence is complete.
+Returns
+.Dv MANDOCLEVEL_OK
+on success and
+.Dv MANDOCLEVEL_SYSERR
+on failure, that is, when
+.Xr wait 2
+fails, or when
+.Xr gunzip 1
+died from a signal or exited with non-zero status.
+Declared in
+.In mandoc.h ,
+implemented in
+.Pa read.c .

 .El
 .Ss Variables
 .Bl -ohang
 .El
 .Ss Variables
 .Bl -ohang


@@ -249,7 +493,36 @@ This section consists of structural documentation for
 .Xr mdoc 7
 and
 .Xr man 7
 .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.
+.It Dv ASCII_BREAK
+A breakable zero-width space.
+.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
+.Xr mandoc_escape 3
+and converted with one the functions described in
+.Xr mchars_alloc 3 .

 .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


@@ -290,11 +563,11 @@ 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

-next-lint scope as documented in
+next-line scope as documented in

 .Xr man 7 .
 .Ss Mdoc Abstract Syntax Tree
 This AST is governed by the ontological
 .Xr man 7 .
 .Ss Mdoc Abstract Syntax Tree
 This AST is governed by the ontological


@@ -349,7 +622,7 @@ 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


@@ -364,7 +637,7 @@ 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


@@ -430,12 +703,16 @@ front-ends to
 .Xr mandoc 1
 are unable to render them in any meaningful way.
 Furthermore, behaviour when encountering badly-nested blocks is not
 .Xr mandoc 1
 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
+consistent across troff implementations, especially when using multiple

 levels of badly-nested blocks.
 .Sh SEE ALSO
 .Xr mandoc 1 ,
 levels of badly-nested blocks.
 .Sh SEE ALSO
 .Xr mandoc 1 ,

+.Xr mandoc_escape 3 ,
+.Xr mandoc_malloc 3 ,
+.Xr mchars_alloc 3 ,

 .Xr eqn 7 ,
 .Xr man 7 ,
 .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


@@ -443,4 +720,4 @@ 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 .