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
commiteb14e36d0b29f19321d44dd7dfa73cc703838d86 (patch)
tree1285e9e56959bc3a4b506e36bbc3b49f4e938fa0 /gi/pf/corpus.h
parent68f158b11df9f4072699fe6a4c8022ea54102b28 (diff)
parent04e38a57b19ea012895ac2efb39382c2e77833a9 (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