Simplify the mparse_open()/mparse_wait() interface.

Don't bother the user with the PID of the child process,
store it inside the opaque mparse handle.

6 files changed, 27 insertions, 39 deletions

diff --git a/TODO b/TODO
index b6322622..98cb687e 100644
--- a/TODO
+++ b/TODO
@@ -1,6 +1,6 @@
 ************************************************************************
 * Official mandoc TODO.
-* $Id: TODO,v 1.188 2014/11/20 02:21:27 schwarze Exp $
+* $Id: TODO,v 1.189 2014/11/26 21:40:17 schwarze Exp $
 ************************************************************************
 
 Many issues are annotated for difficulty as follows:
@@ -564,6 +564,9 @@ Several areas can be cleaned up to make mandoc even faster.  These are
 * structural issues
 ************************************************************************
 
+- Use libz directly instead of forking gunzip(1).
+  Suggested by bapt at FreeBSD among others.
+
 - We use the input line number at several places to distinguish
   same-line from different-line input.  That plainly doesn't work
   with user-defined macros, leading to random breakage.
diff --git a/main.c b/main.c
index 63ac45e8..34784994 100644
--- a/main.c
+++ b/main.c
@@ -1,4 +1,4 @@
-/*	$Id: main.c,v 1.199 2014/11/11 19:04:55 schwarze Exp $ */
+/*	$Id: main.c,v 1.200 2014/11/26 21:40:17 schwarze Exp $ */
 /*
  * Copyright (c) 2008-2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010, 2011, 2012, 2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -115,7 +115,6 @@ main(int argc, char *argv[])
 #endif
 	enum mandoclevel rc;
 	enum outmode	 outmode;
-	pid_t		 child_pid;
 	int		 fd;
 	int		 show_usage;
 	int		 use_pager;
@@ -388,8 +387,7 @@ main(int argc, char *argv[])
 	while (argc) {
 #if HAVE_SQLITE3
 		if (resp != NULL) {
-			rc = mparse_open(curp.mp, &fd, resp->file,
-			    &child_pid);
+			rc = mparse_open(curp.mp, &fd, resp->file);
 			if (fd == -1)
 				/* nothing */;
 			else if (resp->form & FORM_SRC) {
@@ -403,14 +401,12 @@ main(int argc, char *argv[])
 		} else
 #endif
 		{
-			rc = mparse_open(curp.mp, &fd, *argv++,
-			    &child_pid);
+			rc = mparse_open(curp.mp, &fd, *argv++);
 			if (fd != -1)
 				parse(&curp, fd, argv[-1], &rc);
 		}
 
-		if (child_pid &&
-		    mparse_wait(curp.mp, child_pid) != MANDOCLEVEL_OK)
+		if (mparse_wait(curp.mp) != MANDOCLEVEL_OK)
 			rc = MANDOCLEVEL_SYSERR;
 
 		if (MANDOCLEVEL_OK != rc && curp.wstop)
diff --git a/mandoc.3 b/mandoc.3
index f03b0307..08a0d168 100644
--- a/mandoc.3
+++ b/mandoc.3
@@ -1,4 +1,4 @@
-.\"	$Id: mandoc.3,v 1.27 2014/10/28 17:36:19 schwarze Exp $
+.\"	$Id: mandoc.3,v 1.28 2014/11/26 21:40:17 schwarze 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: October 28 2014 $
+.Dd $Mdocdate: November 26 2014 $
 .Dt MANDOC 3
 .Os
 .Sh NAME
@@ -81,7 +81,6 @@
 .Fa "struct mparse *parse"
 .Fa "int *fd"
 .Fa "const char *fname"
-.Fa "pid_t *child_pid"
 .Fc
 .Ft "enum mandoclevel"
 .Fo mparse_readfd
@@ -111,7 +110,6 @@
 .Ft "enum mandoclevel"
 .Fo mparse_wait
 .Fa "struct mparse *parse"
-.Fa "pid_t child_pid"
 .Fc
 .In sys/types.h
 .In mandoc.h
@@ -404,14 +402,6 @@ 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
diff --git a/mandoc.h b/mandoc.h
index f3dff946..80a7bfc1 100644
--- a/mandoc.h
+++ b/mandoc.h
@@ -1,4 +1,4 @@
-/*	$Id: mandoc.h,v 1.168 2014/10/29 00:17:43 schwarze Exp $ */
+/*	$Id: mandoc.h,v 1.169 2014/11/26 21:40:17 schwarze Exp $ */
 /*
  * Copyright (c) 2010, 2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -436,8 +436,7 @@ struct mparse	 *mparse_alloc(int, enum mandoclevel, mandocmsg,
 			const struct mchars *, const char *);
 void		  mparse_free(struct mparse *);
 void		  mparse_keep(struct mparse *);
-enum mandoclevel  mparse_open(struct mparse *, int *, const char *,
-			pid_t *);
+enum mandoclevel  mparse_open(struct mparse *, int *, const char *);
 enum mandoclevel  mparse_readfd(struct mparse *, int, const char *);
 enum mandoclevel  mparse_readmem(struct mparse *, const void *, size_t,
 			const char *);
@@ -447,7 +446,7 @@ void		  mparse_result(struct mparse *,
 const char	 *mparse_getkeep(const struct mparse *);
 const char	 *mparse_strerror(enum mandocerr);
 const char	 *mparse_strlevel(enum mandoclevel);
-enum mandoclevel  mparse_wait(struct mparse *, pid_t);
+enum mandoclevel  mparse_wait(struct mparse *);
 
 __END_DECLS
 
diff --git a/mandocdb.c b/mandocdb.c
index 7d9caf23..7377d847 100644
--- a/mandocdb.c
+++ b/mandocdb.c
@@ -1,4 +1,4 @@
-/*	$Id: mandocdb.c,v 1.169 2014/11/19 20:40:51 schwarze Exp $ */
+/*	$Id: mandocdb.c,v 1.170 2014/11/26 21:40:17 schwarze Exp $ */
 /*
  * Copyright (c) 2011, 2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -1084,7 +1084,6 @@ mpages_merge(struct mchars *mc, struct mparse *mp)
 	struct man		*man;
 	char			*sodest;
 	char			*cp;
-	pid_t			 child_pid;
 	int			 fd;
 	unsigned int		 pslot;
 	enum mandoclevel	 lvl;
@@ -1112,9 +1111,8 @@ mpages_merge(struct mchars *mc, struct mparse *mp)
 		mdoc = NULL;
 		man = NULL;
 		sodest = NULL;
-		child_pid = 0;
 
-		mparse_open(mp, &fd, mpage->mlinks->file, &child_pid);
+		mparse_open(mp, &fd, mpage->mlinks->file);
 		if (fd == -1) {
 			say(mpage->mlinks->file, "&open");
 			goto nextpage;
@@ -1231,8 +1229,7 @@ mpages_merge(struct mchars *mc, struct mparse *mp)
 		dbadd(mpage, mc);
 
 nextpage:
-		if (child_pid &&
-		    mparse_wait(mp, child_pid) != MANDOCLEVEL_OK) {
+		if (mparse_wait(mp) != MANDOCLEVEL_OK) {
 			exitcode = (int)MANDOCLEVEL_SYSERR;
 			say(mpage->mlinks->file, "&wait gunzip");
 		}
diff --git a/read.c b/read.c
index 5bd5de57..cad96e2d 100644
--- a/read.c
+++ b/read.c
@@ -1,4 +1,4 @@
-/*	$Id: read.c,v 1.96 2014/11/01 06:03:13 schwarze Exp $ */
+/*	$Id: read.c,v 1.97 2014/11/26 21:40:17 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -64,6 +64,7 @@ struct	mparse {
 	int		  filenc; /* encoding of the current file */
 	int		  reparse_count; /* finite interp. stack */
 	int		  line; /* line number in the file */
+	pid_t		  child; /* the gunzip(1) process */
 };
 
 static	void	  choose_parser(struct mparse *);
@@ -823,8 +824,7 @@ mparse_readfd(struct mparse *curp, int fd, const char *file)
 }
 
 enum mandoclevel
-mparse_open(struct mparse *curp, int *fd, const char *file,
-	pid_t *child_pid)
+mparse_open(struct mparse *curp, int *fd, const char *file)
 {
 	int		  pfd[2];
 	char		 *cp;
@@ -834,7 +834,7 @@ mparse_open(struct mparse *curp, int *fd, const char *file,
 	curp->file = file;
 	if ((cp = strrchr(file, '.')) == NULL ||
 	    strcmp(cp + 1, "gz")) {
-		*child_pid = 0;
+		curp->child = 0;
 		if ((*fd = open(file, O_RDONLY)) == -1) {
 			err = MANDOCERR_SYSOPEN;
 			goto out;
@@ -847,7 +847,7 @@ mparse_open(struct mparse *curp, int *fd, const char *file,
 		goto out;
 	}
 
-	switch (*child_pid = fork()) {
+	switch (curp->child = fork()) {
 	case -1:
 		err = MANDOCERR_SYSFORK;
 		close(pfd[0]);
@@ -871,7 +871,7 @@ mparse_open(struct mparse *curp, int *fd, const char *file,
 
 out:
 	*fd = -1;
-	*child_pid = 0;
+	curp->child = 0;
 	curp->file_status = MANDOCLEVEL_SYSERR;
 	if (curp->mmsg)
 		(*curp->mmsg)(err, curp->file_status, file,
@@ -882,11 +882,14 @@ out:
 }
 
 enum mandoclevel
-mparse_wait(struct mparse *curp, pid_t child_pid)
+mparse_wait(struct mparse *curp)
 {
 	int	  status;
 
-	if (waitpid(child_pid, &status, 0) == -1) {
+	if (curp->child == 0)
+		return(MANDOCLEVEL_OK);
+
+	if (waitpid(curp->child, &status, 0) == -1) {
 		mandoc_msg(MANDOCERR_SYSWAIT, curp, 0, 0,
 		    strerror(errno));
 		curp->file_status = MANDOCLEVEL_SYSERR;