summaryrefslogtreecommitdiff
path: root/gi/pf/corpus.h
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2011-10-20 02:31:25 +0200
committerPatrick Simianer <p@simianer.de>2011-10-20 02:31:25 +0200
commit92e48b652530d2d2bb4f2694501f95a60d727cb2 (patch)
treeb484bd0c4216525690de8b14fb654c9581a300c2 /gi/pf/corpus.h
parent0e70073cec6cdcafaf60d4fbcbd1adf82ae21c8e (diff)
parent082b6c77e0703ccd1c85947828c33d4b0eef20f0 (diff)
finalized merge
Diffstat (limited to 'gi/pf/corpus.h')
-rw-r--r--gi/pf/corpus.h19
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