From 925087356b853e2099c1b60d8b757d7aa02121a9 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@cab.ark.cs.cmu.edu>
Date: Tue, 2 Oct 2012 00:19:43 -0400
Subject: cdec cleanup, remove bayesian stuff, parsing stuff

---
 gi/pf/corpus.cc | 62 ---------------------------------------------------------
 1 file changed, 62 deletions(-)
 delete mode 100644 gi/pf/corpus.cc

(limited to 'gi/pf/corpus.cc')

diff --git a/gi/pf/corpus.cc b/gi/pf/corpus.cc
deleted file mode 100644
index cb6e4ed7..00000000
--- a/gi/pf/corpus.cc
+++ /dev/null
@@ -1,62 +0,0 @@
-#include "corpus.h"
-
-#include <set>
-#include <vector>
-#include <string>
-
-#include "tdict.h"
-#include "filelib.h"
-
-using namespace std;
-
-namespace corpus {
-
-void ReadParallelCorpus(const string& filename,
-                vector<vector<WordID> >* f,
-                vector<vector<WordID> >* e,
-                set<WordID>* vocab_f,
-                set<WordID>* vocab_e) {
-  f->clear();
-  e->clear();
-  vocab_f->clear();
-  vocab_e->clear();
-  ReadFile rf(filename);
-  istream* in = rf.stream();
-  assert(*in);
-  string line;
-  unsigned lc = 0;
-  const WordID kDIV = TD::Convert("|||");
-  vector<WordID> tmp;
-  while(getline(*in, line)) {
-    ++lc;
-    e->push_back(vector<int>());
-    f->push_back(vector<int>());
-    vector<int>& le = e->back();
-    vector<int>& lf = f->back();
-    tmp.clear();
-    TD::ConvertSentence(line, &tmp);
-    bool isf = true;
-    for (unsigned i = 0; i < tmp.size(); ++i) {
-      const int cur = tmp[i];
-      if (isf) {
-        if (kDIV == cur) {
-          isf = false;
-        } else {
-          lf.push_back(cur);
-          vocab_f->insert(cur);
-        }
-      } else {
-        if (cur == kDIV) {
-          cerr << "ERROR in " << lc << ": " << line << endl << endl;
-          abort();
-        }
-        le.push_back(cur);
-        vocab_e->insert(cur);
-      }
-    }
-    assert(isf == false);
-  }
-}
-
-}
-
-- 
cgit v1.2.3