From 93075eaf07540ee5c51a17371e3ddc1b680adda6 Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Fri, 10 Nov 2017 16:39:41 +0100
Subject: rr

---
 rr | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 rr

diff --git a/rr b/rr
new file mode 100644
index 0000000..30bf2d3
--- /dev/null
+++ b/rr
@@ -0,0 +1,28 @@
+#!/usr/bin/env ruby
+
+require 'zipf'
+
+windows = []
+cur = []
+cur_sz = 0
+while line = STDIN.gets
+  if cur_sz >= 1000
+    windows << cur
+    cur = []
+  else
+    cur << line.strip
+    cur_size += cur[-1].split.size
+  end
+end
+
+windows.each { |w|
+  h = {}
+  h.default = 0
+  w.each { |seg|
+    ngrams(seg, 4) { |ng|
+      h[ng] += 1
+    }
+  }
+  puts h
+}
+
-- 
cgit v1.2.3