From 40637fdc9bfef0880764c0809d9a2f20c69f9f50 Mon Sep 17 00:00:00 2001
From: Crista Lopes <crista@tagide.com>
Date: Wed, 16 Oct 2013 21:25:43 -0700
Subject: [PATCH] Added lazy rivers style

---
 28-lazy-rivers/README.md | 14 ++++++++++++
 28-lazy-rivers/tf-28.py  | 48 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)
 create mode 100644 28-lazy-rivers/README.md
 create mode 100644 28-lazy-rivers/tf-28.py

diff --git a/28-lazy-rivers/README.md b/28-lazy-rivers/README.md
new file mode 100644
index 0000000..bdb57b1
--- /dev/null
+++ b/28-lazy-rivers/README.md
@@ -0,0 +1,14 @@
+Style #28
+==============================
+
+Constraints:
+
+- Data comes to functions in streams, rather than as a complete whole all at at once
+- Functions are filters / transformers from one kind of data stream to another
+
+Possible names:
+
+- Lazy river
+- Data streams
+- Dataflow
+- Data generators
diff --git a/28-lazy-rivers/tf-28.py b/28-lazy-rivers/tf-28.py
new file mode 100644
index 0000000..99a2d93
--- /dev/null
+++ b/28-lazy-rivers/tf-28.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+
+import sys, operator, string
+
+def characters(filename):
+    for line in open(filename):
+        for c in line:
+            yield c
+
+def all_words(filename):
+    start_char = True
+    for c in characters(filename):
+        if start_char == True:
+            word = ""
+            if c.isalnum():
+                # We found the start of a word
+                word = c.lower()
+                start_char = False
+            else: pass
+        else:
+            if c.isalnum():
+                word += c.lower()
+            else:
+                # We found the end of a word, emit it
+                start_char = True
+                yield word
+
+def non_stop_words(filename):
+    stopwords = set(open('../stop_words.txt').read().split(',')  + list(string.ascii_lowercase))
+    for w in all_words(filename):
+        if not w in stopwords:
+            yield w
+
+def count_and_sort(filename):
+    freqs = {}
+    for w in non_stop_words(filename):
+        freqs[w] = 1 if w not in freqs else freqs[w]+1
+    return sorted(freqs.iteritems(), key=operator.itemgetter(1), reverse=True)
+
+#
+# The main function
+#
+
+word_freqs = count_and_sort(sys.argv[1])
+
+for tf in word_freqs[0:25]:
+    print tf[0], ' - ', tf[1]
+