model lenght properly, clean up

1 files changed, 19 insertions, 0 deletions

diff --git a/gi/pf/corpus.h b/gi/pf/corpus.h
new file mode 100644
index 00000000..e7febdb7
--- /dev/null
+++ b/gi/pf/corpus.h
@@ -0,0 +1,19 @@
+#ifndef _CORPUS_H_
+#define _CORPUS_H_
+
+#include <string>
+#include <vector>
+#include <set>
+#include "wordid.h"
+
+namespace corpus {
+
+void ReadParallelCorpus(const std::string& filename,
+                std::vector<std::vector<WordID> >* f,
+                std::vector<std::vector<WordID> >* e,
+                std::set<WordID>* vocab_f,
+                std::set<WordID>* vocab_e);
+
+}
+
+#endif