Let mparse_readfd() use mparse_open() and mparse_wait()

and let mparse_open() fall back to .gz files
such that .so works even when the target is zipped,
requested by and in part using ideas from <bapt at FreeBSD>.
While here, make sure files are readable before forking,
both for efficiency and for better error reporting.

2 files changed, 61 insertions, 30 deletions

diff --git a/mandoc.3 b/mandoc.3
index 08a0d168..f05fdac9 100644
--- a/mandoc.3
+++ b/mandoc.3
@@ -1,4 +1,4 @@
-.\"	$Id: mandoc.3,v 1.28 2014/11/26 21:40:17 schwarze Exp $
+.\"	$Id: mandoc.3,v 1.29 2014/11/26 23:42:14 schwarze Exp $
 .\"
 .\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
 .\" Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org>
@@ -396,6 +396,12 @@ open with
 .Xr gunzip 1 ;
 otherwise, with
 .Xr open 2 .
+If
+.Xr open 2
+fails, append
+.Pa .gz
+and try with
+.Xr gunzip 1 .
 Return a file descriptor open for reading in
 .Fa fd ,
 or -1 on failure.
@@ -410,14 +416,18 @@ implemented in
 Parse a file or file descriptor.
 If
 .Va fd
-is -1,
+is -1, open
 .Va fname
-is opened for reading.
+with
+.Fn mparse_open .
 Otherwise,
 .Va fname
 is assumed to be the name associated with
 .Va fd .
-This may be called multiple times with different parameters; however,
+Calls
+.Fn mparse_wait
+before returning.
+This function may be called multiple times with different parameters; however,
 .Fn mparse_reset
 should be invoked between parses.
 Declared in
@@ -461,11 +471,12 @@ implemented in
 .It Fn mparse_wait
 Bury a
 .Xr gunzip 1
-child process
-.Fa child_pid
-that was spawned with
+child process that was spawned with
 .Fn mparse_open .
 To be called after the parse sequence is complete.
+Not needed after
+.Fn mparse_readfd ,
+but does no harm in that case, either.
 Returns
 .Dv MANDOCLEVEL_OK
 on success and
diff --git a/read.c b/read.c
index cad96e2d..6ef75e51 100644
--- a/read.c
+++ b/read.c
@@ -1,4 +1,4 @@
-/*	$Id: read.c,v 1.97 2014/11/26 21:40:17 schwarze Exp $ */
+/*	$Id: read.c,v 1.98 2014/11/26 23:42:14 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2010-2014 Ingo Schwarze <schwarze@openbsd.org>
@@ -780,28 +780,25 @@ mparse_readmem(struct mparse *curp, const void *buf, size_t len,
 	return(curp->file_status);
 }
 
+/*
+ * If a file descriptor is given, use it and assume it points
+ * to the named file.  Otherwise, open the named file.
+ * Read the whole file into memory and call the parsers.
+ * Called recursively when an .so request is encountered.
+ */
 enum mandoclevel
 mparse_readfd(struct mparse *curp, int fd, const char *file)
 {
 	struct buf	 blk;
 	int		 with_mmap;
 	int		 save_filenc;
+	pid_t		 save_child;
 
-	if (-1 == fd && -1 == (fd = open(file, O_RDONLY, 0))) {
-		curp->file_status = MANDOCLEVEL_SYSERR;
-		if (curp->mmsg)
-			(*curp->mmsg)(MANDOCERR_SYSOPEN,
-			    curp->file_status,
-			    file, 0, 0, strerror(errno));
-		return(curp->file_status);
-	}
-
-	/*
-	 * Run for each opened file; may be called more than once for
-	 * each full parse sequence if the opened file is nested (i.e.,
-	 * from `so').  Simply sucks in the whole file and moves into
-	 * the parse phase for the file.
-	 */
+	save_child = curp->child;
+	if (fd != -1)
+		curp->child = 0;
+	else if (mparse_open(curp, &fd, file) >= MANDOCLEVEL_SYSERR)
+		goto out;
 
 	if (read_whole_file(curp, file, fd, &blk, &with_mmap)) {
 		save_filenc = curp->filenc;
@@ -817,9 +814,12 @@ mparse_readfd(struct mparse *curp, int fd, const char *file)
 			free(blk.buf);
 	}
 
-	if (STDIN_FILENO != fd && -1 == close(fd))
+	if (fd != STDIN_FILENO && close(fd) == -1)
 		perror(file);
 
+	mparse_wait(curp);
+out:
+	curp->child = save_child;
 	return(curp->file_status);
 }
 
@@ -827,21 +827,40 @@ enum mandoclevel
 mparse_open(struct mparse *curp, int *fd, const char *file)
 {
 	int		  pfd[2];
+	int		  save_errno;
 	char		 *cp;
 	enum mandocerr	  err;
 
 	pfd[1] = -1;
 	curp->file = file;
+
+	/* Unless zipped, try to just open the file. */
+
 	if ((cp = strrchr(file, '.')) == NULL ||
 	    strcmp(cp + 1, "gz")) {
 		curp->child = 0;
-		if ((*fd = open(file, O_RDONLY)) == -1) {
-			err = MANDOCERR_SYSOPEN;
-			goto out;
-		}
-		return(MANDOCLEVEL_OK);
+		if ((*fd = open(file, O_RDONLY)) != -1)
+			return(MANDOCLEVEL_OK);
+
+		/* Open failed; try to append ".gz". */
+
+		mandoc_asprintf(&cp, "%s.gz", file);
+		file = cp;
+	} else
+		cp = NULL;
+
+	/* Before forking, make sure the file can be read. */
+
+	save_errno = errno;
+	if (access(file, R_OK) == -1) {
+		if (cp != NULL)
+			errno = save_errno;
+		err = MANDOCERR_SYSOPEN;
+		goto out;
 	}
 
+	/* Run gunzip(1). */
+
 	if (pipe(pfd) == -1) {
 		err = MANDOCERR_SYSPIPE;
 		goto out;
@@ -870,11 +889,12 @@ mparse_open(struct mparse *curp, int *fd, const char *file)
 	}
 
 out:
+	free(cp);
 	*fd = -1;
 	curp->child = 0;
 	curp->file_status = MANDOCLEVEL_SYSERR;
 	if (curp->mmsg)
-		(*curp->mmsg)(err, curp->file_status, file,
+		(*curp->mmsg)(err, curp->file_status, curp->file,
 		    0, 0, strerror(errno));
 	if (pfd[1] != -1)
 		exit(1);