wholefile.clj

(defn whole-file
  "Custom scheme for dealing with entire files."
  [field-name]
  (WholeFile. (w/fields field-name)))

(defn hfs-wholefile
  "Creates a tap on HDFS using the wholefile format. Guaranteed not
   to chop files up! Required for unsupported compression formats like HDF."
  [path]
  (w/hfs-tap (whole-file ["file"]) path))

(defn files-with-name
  "Query to return all files in the supplied directory, along with filenames."
  [dir]
  (let [source (hfs-wholefile dir)]
    (?<- (stdout) [?file ?filename]
         (source ?file)
         ((AddYearFunction.) ?file :> ?filename))))

Hey, something like this should really really be part of cascalogs standard taps. :)