From 0172721855098ca02b207231a654dffa5e4eb1c9 Mon Sep 17 00:00:00 2001
From: redpony <redpony@ec762483-ff6d-05da-a07a-a48fb63a330f>
Date: Tue, 22 Jun 2010 05:12:27 +0000
Subject: initial checkin

git-svn-id: https://ws10smt.googlecode.com/svn/trunk@2 ec762483-ff6d-05da-a07a-a48fb63a330f
---
 decoder/freqdict.cc | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100644 decoder/freqdict.cc

(limited to 'decoder/freqdict.cc')

diff --git a/decoder/freqdict.cc b/decoder/freqdict.cc
new file mode 100644
index 00000000..9e25d346
--- /dev/null
+++ b/decoder/freqdict.cc
@@ -0,0 +1,29 @@
+#include <iostream>
+#include <fstream>
+#include <cassert>
+#include "freqdict.h"
+#include "tdict.h"
+#include "filelib.h"
+
+using namespace std;
+
+void FreqDict::Load(const std::string& fname) {
+  cerr << "Reading word frequencies: " << fname << endl;
+  ReadFile rf(fname);
+  istream& ifs = *rf.stream();
+  int cc=0;
+  while (ifs) {
+    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_[TD::Convert(word)]=count;
+    ++cc;
+    if (cc % 10000 == 0) { std::cerr << "."; }
+  }
+  std::cerr << "\n";
+  std::cerr << "Loaded " << cc << " words\n";
+}
-- 
cgit v1.2.3