From 671c21451542e2dd20e45b4033d44d8e8735f87b Mon Sep 17 00:00:00 2001
From: Chris Dyer <redpony@gmail.com>
Date: Thu, 3 Dec 2009 16:33:55 -0500
Subject: initial check in

---
 src/freqdict.cc | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 src/freqdict.cc

(limited to 'src/freqdict.cc')

diff --git a/src/freqdict.cc b/src/freqdict.cc
new file mode 100644
index 00000000..4cfffe58
--- /dev/null
+++ b/src/freqdict.cc
@@ -0,0 +1,23 @@
+#include <iostream>
+#include <fstream>
+#include <cassert>
+#include "freqdict.h"
+
+void FreqDict::load(const std::string& fname) {
+  std::ifstream ifs(fname.c_str());
+  int cc=0;
+  while (!ifs.eof()) {
+    std::string word;
+    ifs >> word;
+    if (word.size() == 0) continue;
+    if (word[0] == '#') continue;
+    double count = 0;
+    ifs >> count;
+    assert(count > 0.0);  // use -log(f)
+    counts_[word]=count;
+    ++cc;
+    if (cc % 10000 == 0) { std::cerr << "."; }
+  }
+  std::cerr << "\n";
+  std::cerr << "Loaded " << cc << " words\n";
+}
-- 
cgit v1.2.3