summaryrefslogtreecommitdiff
path: root/gi/pf/corpus.h
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2011-10-19 14:02:34 +0200
committerPatrick Simianer <p@simianer.de>2011-10-19 14:02:34 +0200
commit9beaeb42b71fa504bfa41a402cb17eb6ac4001af (patch)
tree0add4afabc526391753e4e6b9443a7bf21e3e2c3 /gi/pf/corpus.h
parentce3b4db94d40c111ede321ac6de2bb061a81c4af (diff)
parent09297047e446f49804d3f48bf320cdbd38d6396a (diff)
merge upstream/master
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