Make the SCRIPT_NAME logic simpler, safer, and make it actually work;

in part based on ideas by bentley@.
While here, improve the documentation.

3 files changed, 68 insertions, 66 deletions

diff --git a/cgi.c b/cgi.c
index ddb318d6..ffef5031 100644
--- a/cgi.c
+++ b/cgi.c
@@ -1,4 +1,4 @@
-/*	$Id: cgi.c,v 1.118 2016/03/17 22:06:44 schwarze Exp $ */
+/*	$Id: cgi.c,v 1.119 2016/03/18 13:22:27 schwarze Exp $ */
 /*
  * Copyright (c) 2011, 2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2014, 2015, 2016 Ingo Schwarze <schwarze@usta.de>
@@ -84,7 +84,7 @@ static	int		 validate_filename(const char *);
 static	int		 validate_manpath(const struct req *, const char *);
 static	int		 validate_urifrag(const char *);
 
-static	const char	 *scriptname; /* CGI script name */
+static	const char	 *scriptname = SCRIPT_NAME;
 
 static	const int sec_prios[] = {1, 4, 5, 8, 6, 3, 7, 2, 9};
 static	const char *const sec_numbers[] = {
@@ -370,7 +370,7 @@ resp_searchform(const struct req *req)
 
 	puts("<!-- Begin search form. //-->");
 	printf("<DIV ID=\"mancgi\">\n"
-	       "<FORM ACTION=\"%s\" METHOD=\"get\">\n"
+	       "<FORM ACTION=\"/%s\" METHOD=\"get\">\n"
 	       "<FIELDSET>\n"
 	       "<LEGEND>Manual Page Search Parameters</LEGEND>\n",
 	       scriptname);
@@ -507,12 +507,13 @@ pg_index(const struct req *req)
 	resp_searchform(req);
 	printf("<P>\n"
 	       "This web interface is documented in the\n"
-	       "<A HREF=\"%s/mandoc/man8/man.cgi.8\">man.cgi</A>\n"
+	       "<A HREF=\"/%s%smandoc/man8/man.cgi.8\">man.cgi</A>\n"
 	       "manual, and the\n"
-	       "<A HREF=\"%s/mandoc/man1/apropos.1\">apropos</A>\n"
+	       "<A HREF=\"/%s%smandoc/man1/apropos.1\">apropos</A>\n"
 	       "manual explains the query syntax.\n"
 	       "</P>\n",
-	       scriptname, scriptname);
+	       scriptname, *scriptname == '\0' ? "" : "/",
+	       scriptname, *scriptname == '\0' ? "" : "/");
 	resp_end_html();
 }
 
@@ -536,7 +537,7 @@ pg_error_badrequest(const char *msg)
 	     "<P>\n");
 	puts(msg);
 	printf("Try again from the\n"
-	       "<A HREF=\"%s\">main page</A>.\n"
+	       "<A HREF=\"/%s\">main page</A>.\n"
 	       "</P>", scriptname);
 	resp_end_html();
 }
@@ -573,8 +574,10 @@ pg_searchres(const struct req *req, struct manpage *r, size_t sz)
 		 * without any delay.
 		 */
 		printf("Status: 303 See Other\r\n");
-		printf("Location: http://%s%s/%s/%s",
-		    HTTP_HOST, scriptname, req->q.manpath, r[0].file);
+		printf("Location: http://%s/%s%s%s/%s",
+		    HTTP_HOST, scriptname,
+		    *scriptname == '\0' ? "" : "/",
+		    req->q.manpath, r[0].file);
 		printf("\r\n"
 		     "Content-Type: text/html; charset=utf-8\r\n"
 		     "\r\n");
@@ -589,8 +592,9 @@ pg_searchres(const struct req *req, struct manpage *r, size_t sz)
 	for (i = 0; i < sz; i++) {
 		printf("<TR>\n"
 		       "<TD CLASS=\"title\">\n"
-		       "<A HREF=\"%s/%s/%s",
-		    scriptname, req->q.manpath, r[i].file);
+		       "<A HREF=\"/%s%s%s/%s",
+		    scriptname, *scriptname == '\0' ? "" : "/",
+		    req->q.manpath, r[i].file);
 		printf("\">");
 		html_print(r[i].names);
 		printf("</A>\n"
@@ -808,7 +812,7 @@ format(const struct req *req, const char *file)
 	memset(&conf, 0, sizeof(conf));
 	conf.fragment = 1;
 	usepath = strcmp(req->q.manpath, req->p[0]);
-	mandoc_asprintf(&conf.man, "%s?query=%%N&sec=%%S%s%s%s%s",
+	mandoc_asprintf(&conf.man, "/%s?query=%%N&sec=%%S%s%s%s%s",
 	    scriptname,
 	    req->q.arch	? "&arch="       : "",
 	    req->q.arch	? req->q.arch    : "",
@@ -1006,18 +1010,6 @@ main(void)
 		return EXIT_FAILURE;
 	}
 
-	/* Scan our run-time environment. */
-
-	if (NULL == (scriptname = getenv("SCRIPT_NAME")))
-		scriptname = "";
-
-	if ( ! validate_urifrag(scriptname)) {
-		fprintf(stderr, "unsafe SCRIPT_NAME \"%s\"\n",
-		    scriptname);
-		pg_error_internal();
-		return EXIT_FAILURE;
-	}
-
 	/*
 	 * First we change directory into the MAN_DIR so that
 	 * subsequent scanning for manpath directories is rooted
diff --git a/cgi.h.example b/cgi.h.example
index c4878d34..7e5f3917 100644
--- a/cgi.h.example
+++ b/cgi.h.example
@@ -1,7 +1,8 @@
 /* Example compile-time configuration file for man.cgi(8). */
 
 #define	HTTP_HOST "mdocml.bsd.lv"
-#define	MAN_DIR "/var/www/man"
+#define	SCRIPT_NAME "cgi-bin/man.cgi"
+#define	MAN_DIR "/man"
 #define	CSS_DIR ""
 #define	CUSTOMIZE_TITLE "Manual pages with mandoc"
 #define	COMPAT_OLDURI Yes
diff --git a/man.cgi.8 b/man.cgi.8
index e60649b4..c27fb65d 100644
--- a/man.cgi.8
+++ b/man.cgi.8
@@ -1,4 +1,4 @@
-.\"     $Id: man.cgi.8,v 1.14 2016/03/18 01:22:56 schwarze Exp $
+.\"     $Id: man.cgi.8,v 1.15 2016/03/18 13:22:27 schwarze Exp $
 .\"
 .\" Copyright (c) 2014, 2015, 2016 Ingo Schwarze <schwarze@openbsd.org>
 .\"
@@ -183,31 +183,42 @@ Only useful for running on www.openbsd.org to deal with old URIs containing
 .Qq "manpath=OpenBSD "
 where the blank character has to be translated to a hyphen.
 When compiling for other sites, this definition can be deleted.
-.It Ev CSS_DIR
-An optional path to the directory containing the CSS files,
+.It Dv CSS_DIR
+An optional file system path to the directory containing the file
+.Pa mandoc.css ,
 to be specified relative to the server's document root,
 and to be specified without a trailing slash.
-When not specified, the CSS files
-are assumed to be in the document root.
+When empty, the CSS file is assumed to be in the document root.
+Otherwise, a leading slash is needed.
 This is used in generated HTML code.
-.It Ev CUSTOMIZE_TITLE
+.It Dv CUSTOMIZE_TITLE
 An ASCII string to be used for the HTML <TITLE> element.
-.It Ev HTTP_HOST
+.It Dv HTTP_HOST
 The FQDN of the (possibly virtual) host the HTTP server is running on.
 This is used for
 .Ic Location:
 headers in HTTP 303 responses.
-.It Ev MAN_DIR
-A path to the
+.It Dv MAN_DIR
+A file system path to the
 .Nm
-data directory to be used instead of
-.Pa /var/www/man ,
-relative to the web server
+data directory relative to the web server
 .Xr chroot 2
-directory, to be specified without a trailing slash.
-This is prepended to the manpath when opening
+directory, to be specified with a leading slash and without a trailing slash.
+It needs to have at least one component; the root directory cannot be used
+for this purpose.
+The files
+.Pa manpath.conf ,
+.Pa header.html ,
+and
+.Pa footer.html
+are looked up in this directory.
+It is also prepended to the manpath when opening
 .Xr mandoc.db 5
 and manual page files.
+.It Dv SCRIPT_NAME
+The initial component of URIs, to be specified without leading
+and trailing slashes.
+It can be empty.
 .El
 .Pp
 After editing
@@ -234,14 +245,11 @@ The
 .Cm http://
 protocol specifier.
 .It
-The host name and a following slash.
+The host name.
 .It
-The path to the program, normally
-.Pa cgi-bin/man.cgi/ .
-On
-.Lk http://man.openbsd.org/ ,
-.Xr httpd 8
-is configured such that the path to the program can be omitted.
+The
+.Dv SCRIPT_NAME ,
+preceded by a slash unless empty.
 .It
 To show a single page, a slash, the manpath, another slash,
 and the name of the requested file, for example
@@ -304,13 +312,20 @@ the underscore
 .Pq Sq _
 .El
 .Pp
-In particular, this applies to the
-.Ev SCRIPT_NAME ,
-to all manpaths, and to all architecture names.
+In particular, this applies to all manpaths and architecture names.
 .Sh ENVIRONMENT
 The web server may pass the following CGI variables to
 .Nm :
 .Bl -tag -width Ds
+.It Ev SCRIPT_NAME
+The initial part of the the URI passed from the client to the server,
+starting after the server's host name and ending before
+.Ev PATH_INFO .
+This is ignored by
+.Nm .
+When constructing URIs for links and redirections, the
+.Dv SCRIPT_NAME
+preprocessor constant is used instead.
 .It Ev PATH_INFO
 The final part of the URI path passed from the client to the server,
 starting after the
@@ -326,17 +341,6 @@ It is the final part of the URI, after the question mark.
 It is used by the
 .Cm search
 page to acquire the named parameters it needs.
-.It Ev SCRIPT_NAME
-The path to the
-.Nm
-binary relative to the server root, usually
-.Pa /cgi-bin/man.cgi .
-This is used for generating URIs to be embedded
-in generated HTML code and HTTP headers.
-If this contains any character not contained in the
-.Sx Restricted character set ,
-.Nm
-reports an internal server error and exits without doing anything.
 .El
 .Sh FILES
 .Bl -tag -width Ds
@@ -346,13 +350,18 @@ Default web server
 directory.
 All the following paths are specified relative to this directory.
 .It Pa /cgi-bin/man.cgi
-The path to the
+The usual file system path to the
 .Nm
-program relative to the server root.
-Can be overridden by
-.Ev SCRIPT_NAME .
+program inside the web server
+.Xr chroot 2
+directory.
+A different name can be chosen, but in any case, it needs to be configured in
+.Xr httpd.conf 5 .
 .It Pa /htdocs
-The path to the server document root relative to the server root.
+The file system path to the server document root directory
+relative to the server
+.Xr chroot 2
+directory.
 This is part of the web server configuration and not specific to
 .Nm .
 .It Pa /htdocs/mandoc.css
@@ -364,7 +373,7 @@ Default
 .Nm
 data directory containing all the manual trees.
 Can be overridden by
-.Ev MAN_DIR .
+.Dv MAN_DIR .
 .It Pa /man/mandoc/man1/apropos.1 , /man/mandoc/man8/man.cgi.8
 Manual pages documenting
 .Nm