S3: Try to ensure bucket name is valid for archive.org.

4 files changed, 24 insertions, 20 deletions

diff --git a/Remote/S3.hs b/Remote/S3.hs
index e9c62eb25..348b240d4 100644
--- a/Remote/S3.hs
+++ b/Remote/S3.hs
@@ -102,23 +102,24 @@ s3Setup' u c = if isIA c then archiveorg else defaulthost
 
 	archiveorg = do
 		showNote "Internet Archive mode"
-		maybe (error "specify bucket=") (const noop) $
-			getBucket archiveconfig
-		writeUUIDFile archiveconfig u
-		use archiveconfig
-	  where
-		archiveconfig =
+		-- Ensure user enters a valid bucket name, since
+		-- this determines the name of the archive.org item.
+		let bucket = replace " " "-" $ map toLower $
+			fromMaybe (error "specify bucket=") $
+				getBucket c
+		let archiveconfig = 
 			-- hS3 does not pass through x-archive-* headers
 			M.mapKeys (replace "x-archive-" "x-amz-") $
 			-- encryption does not make sense here
 			M.insert "encryption" "none" $
+			M.insert "bucket" bucket $
 			M.union c $
 			-- special constraints on key names
 			M.insert "mungekeys" "ia" $
 			-- bucket created only when files are uploaded
-			M.insert "x-amz-auto-make-bucket" "1" $
-			-- no default bucket name; should be human-readable
-			M.delete "bucket" defaults
+			M.insert "x-amz-auto-make-bucket" "1" defaults
+		writeUUIDFile archiveconfig u
+		use archiveconfig
 
 store :: Remote -> Key -> AssociatedFile -> MeterUpdate -> Annex Bool
 store r k _f p = s3Action r False $ \(conn, bucket) -> 
diff --git a/debian/changelog b/debian/changelog
index 67aae5e2c..1a7b5f1ab 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -25,6 +25,7 @@ git-annex (4.20131003) UNRELEASED; urgency=low
     on OSX.
   * sync: Fix automatic resolution of merge conflicts where one side is an
     annexed file, and the other side is a non-annexed file, or a directory.
+  * S3: Try to ensure bucket name is valid for archive.org.
 
  -- Joey Hess <joeyh@debian.org>  Thu, 03 Oct 2013 15:41:24 -0400
 
diff --git a/doc/bugs/S3_buckets_with_capital_letters_breaks_authentication.mdwn b/doc/bugs/S3_buckets_with_capital_letters_breaks_authentication.mdwn
index 886f0491e..9a67db0c6 100644
--- a/doc/bugs/S3_buckets_with_capital_letters_breaks_authentication.mdwn
+++ b/doc/bugs/S3_buckets_with_capital_letters_breaks_authentication.mdwn
@@ -28,3 +28,5 @@ initremote archive-moglenrepublica (Internet Archive mode) git-annex: The reques
 """]]
 
 Just thought it would be better to have a separate thread for this bug. :)
+
+> [[fixed|done]] --[[Joey]]
diff --git a/doc/tips/Internet_Archive_via_S3.mdwn b/doc/tips/Internet_Archive_via_S3.mdwn
index 39da2c60f..eba28961d 100644
--- a/doc/tips/Internet_Archive_via_S3.mdwn
+++ b/doc/tips/Internet_Archive_via_S3.mdwn
@@ -30,12 +30,6 @@ rather than having git-annex pick a random one; and you can optionally
 specify `x-archive-meta*` headers to add metadata as explained in their
 [documentation](http://www.archive.org/help/abouts3.txt).
 
-[[!template id=note text="""
-/!\ There seems to be a [[bug|bugs/S3 buckets with capital letters breaks authentication]] in either hS3 or the archive that breaks
-authentication when the bucket name contains spaces or upper-case letters..
-use all lowercase and no spaces when making the bucket with `initremote`.
-"""]]
-
 	# git annex initremote archive-panama type=S3 \
 		host=s3.us.archive.org bucket=panama-canal-lock-blueprints \
 		x-archive-meta-mediatype=texts x-archive-meta-language=eng \
@@ -51,8 +45,14 @@ Then you can annex files and copy them to the remote as usual:
 	# git annex copy photo1.jpeg --fast --to archive-panama
 	copy (to archive-panama...) ok
 
-Note the use of the SHA1E [[backend|backends]]. It makes most sense 
-to use the WORM or SHA1E backend for files that will be stored in
-the Internet Archive, since the key name will be exposed as the filename
-there, and since the Archive does special processing of files based on
-their extension.
+Once a file has been stored on archive.org, it cannot be (easily) removed
+from it. Also, git-annex whereis will tell you a public url for the file
+on archive.org. (It may take a while for archive.org to make the file
+publically visibile.)
+
+Note the use of the SHA1E [[backend|backends]] when adding files. That is
+the default backend used by git-annex, but even if you don't normally use
+it, it makes most sense to use the WORM or SHA1E backend for files that
+will be stored in the Internet Archive, since the key name will be exposed
+as the filename there, and since the Archive does special processing of
+files based on their extension.