summaryrefslogtreecommitdiff
path: root/src/tdict.cc
diff options
context:
space:
mode:
authorChris Dyer <redpony@gmail.com>2009-12-14 20:35:11 -0500
committerChris Dyer <redpony@gmail.com>2009-12-14 20:35:11 -0500
commit851e389dffdd6996ea32d70defb8906de80b9edc (patch)
tree8c68ee77205badc056b8ab5b332e67e3e98017df /src/tdict.cc
parentdc6930c00b4b276883280cff1ed6dcd9ddef03c7 (diff)
few small fixes of alignment tools, add new orthographic similarity feature for word aligner, final naming of directories, libraries in cdec
Diffstat (limited to 'src/tdict.cc')
-rw-r--r--src/tdict.cc49
1 files changed, 0 insertions, 49 deletions
diff --git a/src/tdict.cc b/src/tdict.cc
deleted file mode 100644
index c00d20b8..00000000
--- a/src/tdict.cc
+++ /dev/null
@@ -1,49 +0,0 @@
-#include "Ngram.h"
-#include "dict.h"
-#include "tdict.h"
-#include "Vocab.h"
-
-using namespace std;
-
-Vocab* TD::dict_ = new Vocab;
-
-static const string empty;
-static const string space = " ";
-
-WordID TD::Convert(const std::string& s) {
- return dict_->addWord((VocabString)s.c_str());
-}
-
-const char* TD::Convert(const WordID& w) {
- return dict_->getWord((VocabIndex)w);
-}
-
-void TD::GetWordIDs(const std::vector<std::string>& strings, std::vector<WordID>* ids) {
- ids->clear();
- for (vector<string>::const_iterator i = strings.begin(); i != strings.end(); ++i)
- ids->push_back(TD::Convert(*i));
-}
-
-std::string TD::GetString(const std::vector<WordID>& str) {
- string res;
- for (vector<WordID>::const_iterator i = str.begin(); i != str.end(); ++i)
- res += (i == str.begin() ? empty : space) + TD::Convert(*i);
- return res;
-}
-
-void TD::ConvertSentence(const std::string& sent, std::vector<WordID>* ids) {
- string s = sent;
- int last = 0;
- ids->clear();
- for (int i=0; i < s.size(); ++i)
- if (s[i] == 32 || s[i] == '\t') {
- s[i]=0;
- if (last != i) {
- ids->push_back(Convert(&s[last]));
- }
- last = i + 1;
- }
- if (last != s.size())
- ids->push_back(Convert(&s[last]));
-}
-