zerokarmaleft

require 'java'
require 'jbundler'
require 'stunted'

%w{ PersistentArrayMap, PersistentHashMap, PersistentHashSet, PersistentList,
    PersistentQueue, PersistentStructMap, PersistentTreeMap, PersistentTreeSet,
    PersistentVector }.each do |data_structure|
  java_import "clojure.lang.#{ data_structure }"
end

zerokarmaleft

# -*- mode: ruby -*-
# vi: set ft=ruby :

Vagrant::Config.run do |config|
  config.vm.box = "precise32"

  config.vm.network :hostonly, "33.33.33.10"

  config.vm.provision :chef_client do |chef|
    chef.chef_server_url = "https://api.opscode.com/organizations/#{ENV['ORGNAME']}"

zerokarmaleft

map = [
#general
    {name: "Patient Control ID", value: nil},
    {name: "SSN", value: nil},
    {name: "Other ID", source: :ldap, source_name: "datatelid"},
    {name: "Last Name", source: :ldap, source_name: "sn"},
    {name: "First Name", source: :ldap, source_name: "givenName"},
    {name: "Middle Initial", source: :ldap, source_name: "initials", mapper: Proc.new {|v| v[0]}},
    {name: "Sex", source_name: "gender", source: :ods},
    {name: "Address", source: :ods, source_name: ["home_address_line_1","home_address_line_2"], mapper: Proc.new{|v| v.join " "}},

zerokarmaleft

./rfc101.txt: ISO-8859 English text
./rfc1061.txt: ASCII text
./rfc1182.txt: ASCII text
./rfc1260.txt: ASCII text
./rfc1305.txt: ISO-8859 English text
./rfc14.txt: ASCII text
./rfc1489.txt: ASCII FORTRAN program text
./rfc159.txt: ASCII text
./rfc16.txt: ASCII text
./rfc162.txt: ASCII Pascal program text

zerokarmaleft

# encoding: utf-8

merged_file = File.open("rfc-all.txt", "w")
Dir.entries(".").each do |file|
  if (file != "rfc-all.txt" and File.extname(file) == ".txt")
    merged_file.print "#{ file }\t"
    File.open(file).each do |line|
      merged_file.print line.chomp.delete "\t"
    end
    merged_file.print "\n"

zerokarmaleft

ERROR - caught Throwable, no trap available, rethrowing
cascading.pipe.OperatorException: [803c4175-eb65-4168-bec...][cascalog.workflow$buffer$fn__572.invoke(workflow.clj:249)] operator Every failed executing operation: ClojureBuffer[decl:'?minhash-sig']
	at cascading.flow.stream.BufferEveryWindow.receive(BufferEveryWindow.java:139)
	at cascading.flow.stream.BufferEveryWindow.receive(BufferEveryWindow.java:41)
	at cascading.flow.hadoop.stream.HadoopGroupGate.run(HadoopGroupGate.java:90)
	at cascading.flow.hadoop.FlowReducer.reduce(FlowReducer.java:129)
	at org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:463)
	at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:411)
	at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:215)
Caused by: java.lang.StackOverflowError

zerokarmaleft

(defmapcatop [extract-shingles [k]] [line] (shingles k line))

(defmapop [multihash [n]] [shingle]
  [(map (fn [seed]
          (.asInt (.hashString (Hashing/murmur3_32 seed) shingle)))
        (range n))])

(defn merge-vectors
  [v1 v2]
  (map #(map min %1 %2) v1 v2))

zerokarmaleft

@book{Jacky:1996,
 author = {Jacky, Jonathan},
 title = {The Way of Z: Practical Programming with Formal Methods},
 year = {1996},
 publisher = {Cambridge University Press},
 address = {New York, NY, USA},
}

zerokarmaleft

(def books
  {{:title "Eloquent Ruby"                                     :tags [:ruby]}
   {:title "Design Patterns in Ruby"                           :tags [:ruby :oop]}
   {:title "Practical Object-Oriented Design in Ruby"          :tags [:ruby :oop]}
   {:title "Let Over Lambda"                                   :tags [:common-lisp :lisp :fp]}
   {:title "Pearls of Functional Algorithms"                   :tags [:haskell :fp]}
   {:title "Functional Data Structures"                        :tags [:ml :haskell :fp]}
   {:title "Learn You a Haskell for Great Good"                :tags [:haskell :fp]}
   {:title "The Little MLer"                                   :tags [:ml :fp]}
   {:title "Hadoop: The Definitive Guide"                      :tags [:java :hadoop :data]}

zerokarmaleft

;; matrix M
;;    0 1 2 3
;; ========== 
;; 0: 1 0 0 1
;; 1: 0 0 1 0
;; 2: 0 1 0 1
;; 3: 1 0 1 1
;; 4: 0 0 1 0

;; index correspond to checking rows of M