importfeed --force: re-download urls that have been seen before

2 files changed, 16 insertions, 10 deletions

diff --git a/Command/ImportFeed.hs b/Command/ImportFeed.hs
index 27ccf07ff..7e59c556d 100644
--- a/Command/ImportFeed.hs
+++ b/Command/ImportFeed.hs
@@ -15,6 +15,7 @@ import qualified Data.Map as M
 import Data.Char
 
 import Common.Annex
+import qualified Annex
 import Command
 import qualified Utility.Url as Url
 import Logs.Web
@@ -68,12 +69,15 @@ data Cache = Cache
 	}
 
 getCache :: Maybe String -> Annex Cache
-getCache opttemplate = do
-	showSideAction "checking known urls"
-	us <- S.fromList <$> knownUrls
-	return $ Cache us tmpl
+getCache opttemplate = ifM (Annex.getState Annex.force)
+	( ret S.empty
+	, do
+		showSideAction "checking known urls"
+		ret =<< S.fromList <$> knownUrls
+	)
   where
 	tmpl = Utility.Format.gen $ fromMaybe defaultTemplate opttemplate
+	ret s = return $ Cache s tmpl
 
 findEnclosures :: URLString -> Annex (Maybe [ToDownload])
 findEnclosures url = go =<< downloadFeed url
@@ -96,19 +100,21 @@ downloadFeed url = do
 			)
 
 {- Avoids downloading any urls that are already known to be associated
- - with a file in the annex. -}
+ - with a file in the annex, unless forced. -}
 downloadEnclosure :: Bool -> Cache -> ToDownload -> Annex ()
 downloadEnclosure relaxed cache enclosure
-	| S.member url (knownurls cache) = noop
-	| otherwise = do
+	| S.member url (knownurls cache) =
+		whenM (Annex.getState Annex.force) go
+	| otherwise = go
+  where
+  	url = location enclosure
+	go = do
 		dest <- liftIO $ feedFile (template cache) enclosure
 		showStart "addurl" dest
 		ifM (addUrlFile relaxed url dest)
 			( showEndOk
 			, showEndFail
 			)
-  where
-  	url = location enclosure
 	
 defaultTemplate :: String
 defaultTemplate = "${feedtitle}/${itemtitle}${extension}"
diff --git a/doc/git-annex.mdwn b/doc/git-annex.mdwn
index 7b2a0bce5..1169c97ba 100644
--- a/doc/git-annex.mdwn
+++ b/doc/git-annex.mdwn
@@ -195,7 +195,7 @@ subdirectories).
   Imports the contents of podcast feeds. Only downloads files whose
   urls have not already been added to the repository before, so you can
   delete, rename, etc the resulting files and repeated runs won't duplicate
-  them.
+  them. (Use --force to force downloading files it's seen before.)
 
   Use --template to control where the files are stored.
   The default template is '${feedtitle}/${itemtitle}${extension}'