sbosrcarch: cosmetics

1 files changed, 24 insertions, 19 deletions

diff --git a/sbosrcarch b/sbosrcarch
index dc9b8e7..9f188e8 100755
--- a/sbosrcarch
+++ b/sbosrcarch
@@ -61,11 +61,11 @@ Rough guideline for choosing filesize:
       100.0M  |                     16.6G  |  98%
    unlimited  |                     43.0G  | 100%
 
-Note: these numbers will tend to increase over time, as the SBo
-repository grows.
+Note: these numbers will tend to increase over time, as the SBo repository
+grows. To be safe, add 25% or so to the total sizes above.
 
 "Coverage" is the percentage of all the URLs in all the .info files
-that will be kept in this archive. Notice that about 75% of the storage
+that will be kept in this archive. Notice that about 60% of the storage
 space is eaten up by 2% of the files, in the unlimited case. These
 large files are mostly games, if that influences your decision any.
 
@@ -179,7 +179,7 @@ the section B<CONFIG FILE> for details.
 
 The archive created by sbosrcarch consists of two top-level directories
 called B<by-name> and B<by-md5>. All files are present in both hierarchies
-(as hard or symbolic links, to save space).
+(but the by-md5 tree is hard or symbolic links, to save space).
 
 B<by-name> is organized by the familiar category and PRGNAM, like SBo
 itself. Example:
@@ -283,6 +283,8 @@ B. Watson <yalhcru@gmail.com>
 
 # use only modules that ship with Slackware, which pretty much
 # means only modules that ship with core perl.
+# use the 'legacy' 2.0 API for File::Path, since we want to support
+# the older perl in Slackware 13.0.
 use warnings;
 use strict; # I hate strict, but I'll use it anyway...
 use File::Temp qw/tempfile tempdir/;
@@ -386,7 +388,12 @@ sub url_to_filename {
 sub parse_info {
 	local $/ = "";
 	my $file = shift;
-	open my $fh, "<", $file or die "$file: $!";
+
+	open my $fh, "<", $file or do {
+		warn "$file: $!";
+		return undef;
+	};
+
 	my $got = <$fh>;
 
 	$got =~ s/\\\s*\n//gs; # join \ continuation lines
@@ -433,9 +440,8 @@ sub download_http {
 
 sub download_file {
 	my $url = shift;
-	my $filename = url_to_filename($url);
-
 	my $dlresult;
+
 	if($url =~ /^ftp:/) {
 		$dlresult = download_ftp($url);
 	} else {
@@ -500,7 +506,7 @@ sub toobig {
 # code it up & send a patch to the wget maintainers?
 
 # I've just discovered a better way to do this:
-# curl --head -sS -X GET $url
+# curl --head -L -sS -X GET $url
 # Stops downloading and exits after the headers are received.
 # Not as familiar with curl as I am with wget, have to see about
 # options... and if this works as well as I expect, there's never going
@@ -529,11 +535,11 @@ sub wget_fake_head {
 	close $fh;
 
 	if($size && toobig($size)) {
-		printf "file too large: %0.2fMB\n", $size / (1024 * 1024);
+		printf "  file too large: %0.2fMB\n", $size / (1024 * 1024);
 		$skipcount++;
 		$size = 0;
 	} elsif(not defined $size) {
-		print "can't determine file size, skipping\n";
+		print "  can't determine file size, skipping\n";
 	}
 
 	return $size;
@@ -547,8 +553,8 @@ sub wget {
 	our $wget_config_arg;
 
 	if($url =~ /'/) {
-		print "Refusing to deal with URL \"$url\" due to embedded single-quote.\n" .
-			"Please contact the maintainer of the SlackBuild to have this fixed.\n";
+		print "! refusing to deal with URL \"$url\" due to embedded single-quote.\n" .
+			"! please contact the maintainer of the SlackBuild to have this fixed.\n";
 		return undef;
 	}
 
@@ -573,9 +579,8 @@ sub wget {
 		}
 		close $fh;
 		if(not $wget_config_arg) {
-			print "\n| wget version is too old to support --config option.\n";
+			print "| wget version is too old to support --config option.\n";
 			print "| continuing without it...\n";
-			sleep 1;
 		}
 	}
 
@@ -605,7 +610,7 @@ sub wget {
 		/^Length:\s*(\d+).*\[(.*?)\]/ && do {
 			$size = $1; # TODO: $content_type = $2, check for text/html or such
 			if(toobig($size)) {
-				printf "file too large: %0.2fMB\n", $size / (1024 * 1024);
+				printf "  file too large: %0.2fMB\n", $size / (1024 * 1024);
 				$skipcount++;
 				$size = 0;
 			}
@@ -662,7 +667,7 @@ sub download_ftp {
 	};
 
 	if($@) {
-		print "$_[0]: $@";
+		print "! $@";
 		undef $size;
 	}
 
@@ -1048,7 +1053,7 @@ sub add_by_md5 {
 
 	for my $filename (@_) {
 		my $infile = $filename;
-		$infile = "$oldcwd/$infile" unless -f $infile;
+		$infile = "$oldcwd/$infile" unless $infile =~ m,^/,;
 
 		my $md5 = md5sum_file($infile);
 		next unless defined $md5;
@@ -1073,7 +1078,7 @@ sub add_or_rm_mode {
 	init_git();
 	my $mode = shift @ARGV;
 
-	if($mode eq 'add' && @ARGV && -f $ARGV[0] || -f "$oldcwd/$ARGV[0]") {
+	if($mode eq 'add' && @ARGV && (-f $ARGV[0] || -f "$oldcwd/$ARGV[0]")) {
 		add_by_md5($oldcwd, @ARGV);
 		exit 0;
 	}
@@ -1121,7 +1126,7 @@ sub add_or_rm_mode {
 # Find all files in by-name, make sure the md5sums match, make sure the
 # by-md5 file exists and is either a hardlink or symlink to the by-name
 # file. If the size is over the limit, make a note of it. If the file
-# isn't found in the hash of filenames, it's extraneous (and so its its
+# isn't found in the hash of filenames, it's extraneous (and so is its
 # by-md5 counterpart).
 
 # Do the same thing for the by-md5 tree, more or less. If both hard and