If -Tman is specified and input is -man, echo the preprocessed (`so'

replaced by file) input.  This replaces earlier behaviour of doing
nothing, which I found unexpected (mandoc should always output).

This requires a buffer in read.c that saves the input lines before being
parsed, with a special hook if `so' is invoked.  This buffer is just
flushed to output if -mman is the input.

While mucking around doing this, I also alpha-ordered the mandoc.h
functions.

Ok schwarze@, with no screaming when the polished patch was published.

9 files changed, 141 insertions, 20 deletions

diff --git a/main.c b/main.c
index 1316fdf7..36d02e3a 100644
--- a/main.c
+++ b/main.c
@@ -127,6 +127,12 @@ main(int argc, char *argv[])
 
 	curp.mp = mparse_alloc(type, curp.wlevel, mmsg, &curp);
 
+	/*
+	 * Conditionally start up the lookaside buffer before parsing.
+	 */
+	if (OUTT_MAN == curp.outtype)
+		mparse_keep(curp.mp);
+
 	argc -= optind;
 	argv += optind;
 
@@ -252,6 +258,7 @@ parse(struct curparse *curp, int fd,
 			break;
 		case (OUTT_MAN):
 			curp->outmdoc = man_mdoc;
+			curp->outman = man_man;
 			break;
 		case (OUTT_PDF):
 			/* FALLTHROUGH */
diff --git a/main.h b/main.h
index c652bb53..d08c609b 100644
--- a/main.h
+++ b/main.h
@@ -42,6 +42,7 @@ void		  tree_mdoc(void *, const struct mdoc *);
 void		  tree_man(void *, const struct man *);
 
 void		  man_mdoc(void *, const struct mdoc *);
+void		  man_man(void *, const struct man *);
 
 void		 *locale_alloc(char *);
 void		 *utf8_alloc(char *);
diff --git a/man.c b/man.c
index 3321bf63..70ec1e64 100644
--- a/man.c
+++ b/man.c
@@ -648,3 +648,11 @@ man_node_unlink(struct man *m, struct man_node *n)
 	if (m && m->first == n)
 		m->first = NULL;
 }
+
+const struct mparse *
+man_mparse(const struct man *m)
+{
+
+	assert(m && m->parse);
+	return(m->parse);
+}
diff --git a/man.h b/man.h
index 3cf3e766..5096a611 100644
--- a/man.h
+++ b/man.h
@@ -105,6 +105,7 @@ struct	man;
 
 const struct man_node *man_node(const struct man *);
 const struct man_meta *man_meta(const struct man *);
+const struct mparse   *man_mparse(const struct man *);
 
 __END_DECLS
 
diff --git a/mandoc.1 b/mandoc.1
index 8f842e96..cfe230f3 100644
--- a/mandoc.1
+++ b/mandoc.1
@@ -176,11 +176,11 @@ Encode output using the current locale.
 See
 .Sx Locale Output .
 .It Fl T Ns Cm man
-Produce output in
+Produce
 .Xr man 7
-format; only useful when applied to
-.Fl m Ns Cm doc
-input.
+format output.
+See
+.Sx Man Output .
 .It Fl T Ns Cm pdf
 Produce PDF output.
 See
@@ -311,6 +311,26 @@ will fall back to
 See
 .Sx ASCII Output
 for font style specification and available command-line arguments.
+.Ss Man Output
+Translate input format into
+.Xr man 7
+output format.
+This is useful for distributing manual sources to legancy systems
+lacking 
+.Xr mdoc 7
+formatters.
+.Pp
+If
+.Xr mdoc 7
+is passed as input, it is translated into
+.Xr man 7 ;
+if the input format is
+.Xr man 7 ,
+it is parsed and re-outputted.
+In either case, the
+.Xr roff 7
+.Sq so
+macros are processed prior to producing output.
 .Ss PDF Output
 PDF-1.1 output may be generated by
 .Fl T Ns Cm pdf .
diff --git a/mandoc.3 b/mandoc.3
index 602e0543..70d592c3 100644
--- a/mandoc.3
+++ b/mandoc.3
@@ -22,6 +22,7 @@
 .Nm mandoc ,
 .Nm mandoc_escape ,
 .Nm man_meta ,
+.Nm man_mparse ,
 .Nm man_node ,
 .Nm mchars_alloc ,
 .Nm mchars_free ,
@@ -33,6 +34,8 @@
 .Nm mdoc_node ,
 .Nm mparse_alloc ,
 .Nm mparse_free ,
+.Nm mparse_getkeep ,
+.Nm mparse_keep ,
 .Nm mparse_readfd ,
 .Nm mparse_reset ,
 .Nm mparse_result ,
@@ -55,6 +58,10 @@
 .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"
@@ -100,6 +107,14 @@
 .Fo mparse_free
 .Fa "struct mparse *parse"
 .Fc
+.Ft void
+.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"
@@ -244,6 +259,8 @@ may be
 Obtain the meta-data of a successful parse.
 This may only be used on a pointer returned by
 .Fn mparse_result .
+.It Fn man_mparse
+Get the parser used for the current output.
 .It Fn man_node
 Obtain the root node of a successful parse.
 This may only be used on a pointer returned by
@@ -294,6 +311,15 @@ 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_getkeep
+Acquire the keep buffer.
+Must follow a call of
+.Fn mparse_keep .
+.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.
 .It Fn mparse_readfd
 Parse a file or file descriptor.
 If
diff --git a/mandoc.h b/mandoc.h
index 1c8bc9f6..b3e9ca6e 100644
--- a/mandoc.h
+++ b/mandoc.h
@@ -400,30 +400,31 @@ struct	man;
 
 __BEGIN_DECLS
 
-void		  mparse_free(struct mparse *);
-void		  mparse_reset(struct mparse *);
-struct mparse	 *mparse_alloc(enum mparset, 
-			enum mandoclevel, mandocmsg, void *);
-enum mandoclevel  mparse_readfd(struct mparse *, int, const char *);
-void		  mparse_result(struct mparse *, struct mdoc **, struct man **);
-const char	 *mparse_strerror(enum mandocerr);
-const char	 *mparse_strlevel(enum mandoclevel);
-
 void		 *mandoc_calloc(size_t, size_t);
+enum mandoc_esc	  mandoc_escape(const char **, const char **, int *);
 void		 *mandoc_malloc(size_t);
 void		 *mandoc_realloc(void *, size_t);
 char		 *mandoc_strdup(const char *);
 char		 *mandoc_strndup(const char *, size_t);
-
-enum mandoc_esc	  mandoc_escape(const char **, const char **, int *);
-
 struct mchars	 *mchars_alloc(void);
+void		  mchars_free(struct mchars *);
 char	 	  mchars_num2char(const char *, size_t);
 int		  mchars_num2uc(const char *, size_t);
-const char	 *mchars_spec2str(struct mchars *, const char *, size_t, size_t *);
-int		  mchars_spec2cp(struct mchars *, const char *, size_t);
-void		  mchars_free(struct mchars *);
-
+int		  mchars_spec2cp(struct mchars *, 
+			const char *, size_t);
+const char	 *mchars_spec2str(struct mchars *, 
+			const char *, size_t, size_t *);
+struct mparse	 *mparse_alloc(enum mparset, 
+			enum mandoclevel, mandocmsg, void *);
+void		  mparse_free(struct mparse *);
+void		  mparse_keep(struct mparse *);
+enum mandoclevel  mparse_readfd(struct mparse *, int, const char *);
+void		  mparse_reset(struct mparse *);
+void		  mparse_result(struct mparse *, 
+			struct mdoc **, struct man **);
+const char	 *mparse_getkeep(const struct mparse *);
+const char	 *mparse_strerror(enum mandocerr);
+const char	 *mparse_strlevel(enum mandoclevel);
 
 __END_DECLS
 
diff --git a/mdoc_man.c b/mdoc_man.c
index 4f67753c..b025f563 100644
--- a/mdoc_man.c
+++ b/mdoc_man.c
@@ -18,6 +18,7 @@
 #include <string.h>
 
 #include "mandoc.h"
+#include "man.h"
 #include "mdoc.h"
 #include "main.h"
 
@@ -219,6 +220,13 @@ print_word(const char *s)
 }
 
 void
+man_man(void *arg, const struct man *man)
+{
+
+	fputs(mparse_getkeep(man_mparse(man)), stdout);
+}
+
+void
 man_mdoc(void *arg, const struct mdoc *mdoc)
 {
 	const struct mdoc_meta *m;
diff --git a/read.c b/read.c
index a5a860a6..29ee4682 100644
--- a/read.c
+++ b/read.c
@@ -63,6 +63,7 @@ struct	mparse {
 	mandocmsg	  mmsg; /* warning/error message handler */
 	void		 *arg; /* argument to mmsg */
 	const char	 *file; 
+	struct buf	 *secondary;
 };
 
 static	void	  resize_buf(struct buf *, size_t);
@@ -411,6 +412,27 @@ mparse_buf_r(struct mparse *curp, struct buf blk, int start)
 
 		of = 0;
 
+		/*
+		 * Maintain a lookaside buffer of all parsed lines.  We
+		 * only do this if mparse_keep() has been invoked (the
+		 * buffer may be accessed with mparse_getkeep()).
+		 */
+
+		if (curp->secondary) {
+			curp->secondary->buf = 
+				mandoc_realloc
+				(curp->secondary->buf, 
+				 curp->secondary->sz + pos + 2);
+			memcpy(curp->secondary->buf + 
+					curp->secondary->sz, 
+					ln.buf, pos);
+			curp->secondary->sz += pos;
+			curp->secondary->buf
+				[curp->secondary->sz] = '\n';
+			curp->secondary->sz++;
+			curp->secondary->buf
+				[curp->secondary->sz] = '\0';
+		}
 rerun:
 		rr = roff_parseln
 			(curp->roff, curp->line, 
@@ -437,6 +459,12 @@ rerun:
 			assert(MANDOCLEVEL_FATAL <= curp->file_status);
 			break;
 		case (ROFF_SO):
+			/*
+			 * We remove `so' clauses from our lookaside
+			 * buffer because we're going to descend into
+			 * the file recursively.
+			 */
+			curp->secondary->sz -= pos + 1;
 			mparse_readfd_r(curp, -1, ln.buf + of, 1);
 			if (MANDOCLEVEL_FATAL <= curp->file_status)
 				break;
@@ -704,6 +732,8 @@ mparse_reset(struct mparse *curp)
 		mdoc_reset(curp->mdoc);
 	if (curp->man)
 		man_reset(curp->man);
+	if (curp->secondary)
+		curp->secondary->sz = 0;
 
 	curp->file_status = MANDOCLEVEL_OK;
 	curp->mdoc = NULL;
@@ -720,7 +750,10 @@ mparse_free(struct mparse *curp)
 		man_free(curp->pman);
 	if (curp->roff)
 		roff_free(curp->roff);
+	if (curp->secondary)
+		free(curp->secondary->buf);
 
+	free(curp->secondary);
 	free(curp);
 }
 
@@ -780,3 +813,19 @@ mparse_strlevel(enum mandoclevel lvl)
 {
 	return(mandoclevels[lvl]);
 }
+
+void
+mparse_keep(struct mparse *p)
+{
+
+	assert(NULL == p->secondary);
+	p->secondary = mandoc_calloc(1, sizeof(struct buf));
+}
+
+const char *
+mparse_getkeep(const struct mparse *p)
+{
+
+	assert(p->secondary);
+	return(p->secondary->sz ? p->secondary->buf : NULL);
+}