irc-parser.clj

(ns irc-parser
  (:use clojure.contrib.duck-streams
        clojure.contrib.str-utils))

(defn flatten
  "Takes any nested combination of sequential things (lists, vectors,
  etc.) and returns their contents as a single, flat sequence.
  (flatten nil) returns nil."
  [x]
  (filter (complement sequential?)
          (rest (tree-seq sequential? seq x))))

(def dates (file-seq (java.io.File. "/Users/defn/git/clojure-irc/")))

(defn parse-irc-log
  "Gets rid of all the junk in the irc log groupings and gives us a list of strings which is the content found in the channel."
  [logfile]
  (remove (or nil? "")
          (map #(rest (re-split #".*<.*>\s" %))
               (read-lines (str logfile)))))

(def parsed (map flatten (map parse-irc-log (rest dates))))

;;(filter #(re-matches #".*zipmap.*") parsed)

(map #(re-find #"zipmap" (str %)) parsed)