From 181c0bd79b0e7db2891047305dc87d20ca04097b Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Fri, 29 May 2015 09:17:43 +0200
Subject: add_ln: add line numbers, filter_features: filter text reps of sparse
 vectors, split_*: split kbest lists and by line

---
 split_kbest | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100755 split_kbest

(limited to 'split_kbest')

diff --git a/split_kbest b/split_kbest
new file mode 100755
index 0000000..ab425b0
--- /dev/null
+++ b/split_kbest
@@ -0,0 +1,24 @@
+#!/usr/bin/env ruby
+
+require 'zipf'
+
+def write_kbest l, fn
+  f = WriteFile.new fn
+  f.write l.join("")
+  f.close
+end
+
+dir = ARGV[0]
+i = 0
+l = []
+while line = STDIN.gets
+  j = line.split.first.to_i
+  if j == 0 && l.size > 0
+    write_kbest l, "#{dir}/#{i}.gz"
+    l = []
+    i += 1
+  end
+  l << line
+end
+write_kbest l, "#{dir}/#{i}.gz" # last one
+
-- 
cgit v1.2.3