diff options
author | Paul Baltescu <pauldb89@gmail.com> | 2013-11-23 17:33:47 +0000 |
---|---|---|
committer | Paul Baltescu <pauldb89@gmail.com> | 2013-11-23 17:33:47 +0000 |
commit | cc6313b23cac25eb05976b6cf64f96faf1ed4163 (patch) | |
tree | 3dc28060ad25b43773e875bea7388ab1cefcd927 /extractor/grammar_extractor.cc | |
parent | 7990c750829af93f0a1e0fc14534582f52ee9e8c (diff) | |
parent | f2fb69b10a897e8beb4e6e6d6cbb4327096235ef (diff) |
Merge branch 'master' of https://github.com/redpony/cdec
Diffstat (limited to 'extractor/grammar_extractor.cc')
-rw-r--r-- | extractor/grammar_extractor.cc | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/extractor/grammar_extractor.cc b/extractor/grammar_extractor.cc index 8050ce7b..487abcaf 100644 --- a/extractor/grammar_extractor.cc +++ b/extractor/grammar_extractor.cc @@ -3,11 +3,13 @@ #include <iterator> #include <sstream> #include <vector> +#include <unordered_set> #include "grammar.h" #include "rule.h" #include "rule_factory.h" #include "vocabulary.h" +#include "data_array.h" using namespace std; @@ -32,10 +34,10 @@ GrammarExtractor::GrammarExtractor( vocabulary(vocabulary), rule_factory(rule_factory) {} -Grammar GrammarExtractor::GetGrammar(const string& sentence) { +Grammar GrammarExtractor::GetGrammar(const string& sentence, const unordered_set<int>& blacklisted_sentence_ids, const shared_ptr<DataArray> source_data_array) { vector<string> words = TokenizeSentence(sentence); vector<int> word_ids = AnnotateWords(words); - return rule_factory->GetGrammar(word_ids); + return rule_factory->GetGrammar(word_ids, blacklisted_sentence_ids, source_data_array); } vector<string> GrammarExtractor::TokenizeSentence(const string& sentence) { |