From 0a53f7eca74c165b5ce1c238f1999ddf1febea55 Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Fri, 1 Feb 2013 16:11:10 +0000 Subject: Second working commit. --- extractor/precomputation_test.cc | 138 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 138 insertions(+) create mode 100644 extractor/precomputation_test.cc (limited to 'extractor/precomputation_test.cc') diff --git a/extractor/precomputation_test.cc b/extractor/precomputation_test.cc new file mode 100644 index 00000000..9edb29db --- /dev/null +++ b/extractor/precomputation_test.cc @@ -0,0 +1,138 @@ +#include + +#include +#include + +#include "mocks/mock_data_array.h" +#include "mocks/mock_suffix_array.h" +#include "precomputation.h" + +using namespace std; +using namespace ::testing; + +namespace { + +class PrecomputationTest : public Test { + protected: + virtual void SetUp() { + data = {4, 2, 3, 5, 7, 2, 3, 5, 2, 3, 4, 2, 1}; + data_array = make_shared(); + EXPECT_CALL(*data_array, GetData()).WillRepeatedly(ReturnRef(data)); + + vector suffixes{12, 8, 5, 1, 9, 6, 2, 0, 10, 7, 3, 4, 13}; + vector lcp{-1, 0, 2, 3, 1, 0, 1, 2, 0, 2, 0, 1, 0, 0}; + suffix_array = make_shared(); + EXPECT_CALL(*suffix_array, GetData()).WillRepeatedly(Return(data_array)); + for (size_t i = 0; i < suffixes.size(); ++i) { + EXPECT_CALL(*suffix_array, + GetSuffix(i)).WillRepeatedly(Return(suffixes[i])); + } + EXPECT_CALL(*suffix_array, BuildLCPArray()).WillRepeatedly(Return(lcp)); + } + + vector data; + shared_ptr data_array; + shared_ptr suffix_array; +}; + +TEST_F(PrecomputationTest, TestInvertedIndex) { + Precomputation precomputation(suffix_array, 100, 3, 10, 5, 1, 4, 2); + Index inverted_index = precomputation.GetInvertedIndex(); + + EXPECT_EQ(8, inverted_index.size()); + vector key = {2}; + vector expected_value = {1, 5, 8, 11}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {3}; + expected_value = {2, 6, 9}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {4}; + expected_value = {0, 10}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {5}; + expected_value = {3, 7}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {4, 2}; + expected_value = {0, 10}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {2, 3}; + expected_value = {1, 5, 8}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {3, 5}; + expected_value = {2, 6}; + EXPECT_EQ(expected_value, inverted_index[key]); + key = {2, 3, 5}; + expected_value = {1, 5}; + EXPECT_EQ(expected_value, inverted_index[key]); + + key = {2, 4}; + EXPECT_EQ(0, inverted_index.count(key)); +} + +TEST_F(PrecomputationTest, TestCollocations) { + Precomputation precomputation(suffix_array, 3, 3, 10, 5, 1, 4, 2); + Index collocations = precomputation.GetCollocations(); + + EXPECT_EQ(-1, precomputation.NON_TERMINAL); + vector key = {2, 3, -1, 2}; + vector expected_value = {1, 5, 1, 8, 5, 8, 5, 11, 8, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, 3, -1, 2, 3}; + expected_value = {1, 5, 1, 8, 5, 8}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, 3, -1, 3}; + expected_value = {1, 6, 1, 9, 5, 9}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 2}; + expected_value = {2, 5, 2, 8, 2, 11, 6, 8, 6, 11, 9, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 3}; + expected_value = {2, 6, 2, 9, 6, 9}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 2, 3}; + expected_value = {2, 5, 2, 8, 6, 8}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, -1, 2}; + expected_value = {1, 5, 1, 8, 5, 8, 5, 11, 8, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, -1, 2, 3}; + expected_value = {1, 5, 1, 8, 5, 8}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, -1, 3}; + expected_value = {1, 6, 1, 9, 5, 9}; + EXPECT_EQ(expected_value, collocations[key]); + + key = {2, -1, 2, -1, 2}; + expected_value = {1, 5, 8, 5, 8, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, -1, 2, -1, 3}; + expected_value = {1, 5, 9}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, -1, 3, -1, 2}; + expected_value = {1, 6, 8, 5, 9, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {2, -1, 3, -1, 3}; + expected_value = {1, 6, 9}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 2, -1, 2}; + expected_value = {2, 5, 8, 2, 5, 11, 2, 8, 11, 6, 8, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 2, -1, 3}; + expected_value = {2, 5, 9}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 3, -1, 2}; + expected_value = {2, 6, 8, 2, 6, 11, 2, 9, 11, 6, 9, 11}; + EXPECT_EQ(expected_value, collocations[key]); + key = {3, -1, 3, -1, 3}; + expected_value = {2, 6, 9}; + EXPECT_EQ(expected_value, collocations[key]); + + // Exceeds max_rule_symbols. + key = {2, -1, 2, -1, 2, 3}; + EXPECT_EQ(0, collocations.count(key)); + // Contains non frequent pattern. + key = {2, -1, 5}; + EXPECT_EQ(0, collocations.count(key)); +} + +} // namespace -- cgit v1.2.3 From 245e705ac7b6fca80a7aa4898f5467053ec2c585 Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Wed, 6 Mar 2013 11:43:16 +0000 Subject: Fix memory leak in trie. --- extractor/matchings_trie.cc | 3 +++ extractor/mocks/mock_precomputation.h | 1 - extractor/precomputation.cc | 19 +------------------ extractor/precomputation.h | 2 -- extractor/precomputation_test.cc | 34 ---------------------------------- extractor/run_extractor.cc | 15 ++++++--------- python/pkg/cdec/sa/compile.py | 11 ----------- python/src/sa/_sa.c | 2 +- 8 files changed, 11 insertions(+), 76 deletions(-) (limited to 'extractor/precomputation_test.cc') diff --git a/extractor/matchings_trie.cc b/extractor/matchings_trie.cc index 921ec582..8ea795db 100644 --- a/extractor/matchings_trie.cc +++ b/extractor/matchings_trie.cc @@ -14,6 +14,9 @@ void MatchingsTrie::ResetTree(shared_ptr root) { for (auto child: root->children) { ResetTree(child.second); } + if (root->suffix_link != NULL) { + root->suffix_link.reset(); + } root.reset(); } } diff --git a/extractor/mocks/mock_precomputation.h b/extractor/mocks/mock_precomputation.h index 987bdb2f..9bc72235 100644 --- a/extractor/mocks/mock_precomputation.h +++ b/extractor/mocks/mock_precomputation.h @@ -4,6 +4,5 @@ class MockPrecomputation : public Precomputation { public: - MOCK_CONST_METHOD0(GetInvertedIndex, const Index&()); MOCK_CONST_METHOD0(GetCollocations, const Index&()); }; diff --git a/extractor/precomputation.cc b/extractor/precomputation.cc index 8a76beb1..189ac42c 100644 --- a/extractor/precomputation.cc +++ b/extractor/precomputation.cc @@ -41,7 +41,6 @@ Precomputation::Precomputation( for (int j = 1; j <= max_frequent_phrase_len && i + j <= data.size(); ++j) { pattern.push_back(data[i + j - 1]); if (frequent_patterns_set.count(pattern)) { - inverted_index[pattern].push_back(i); int is_super_frequent = super_frequent_patterns_set.count(pattern); matchings.push_back(make_tuple(i, j, is_super_frequent)); } else { @@ -158,19 +157,7 @@ void Precomputation::WriteBinary(const fs::path& filepath) const { FILE* file = fopen(filepath.string().c_str(), "w"); // TODO(pauldb): Refactor this code. - int size = inverted_index.size(); - fwrite(&size, sizeof(int), 1, file); - for (auto entry: inverted_index) { - size = entry.first.size(); - fwrite(&size, sizeof(int), 1, file); - fwrite(entry.first.data(), sizeof(int), size, file); - - size = entry.second.size(); - fwrite(&size, sizeof(int), 1, file); - fwrite(entry.second.data(), sizeof(int), size, file); - } - - size = collocations.size(); + int size = collocations.size(); fwrite(&size, sizeof(int), 1, file); for (auto entry: collocations) { size = entry.first.size(); @@ -183,10 +170,6 @@ void Precomputation::WriteBinary(const fs::path& filepath) const { } } -const Index& Precomputation::GetInvertedIndex() const { - return inverted_index; -} - const Index& Precomputation::GetCollocations() const { return collocations; } diff --git a/extractor/precomputation.h b/extractor/precomputation.h index 28426bfa..3d44c2a6 100644 --- a/extractor/precomputation.h +++ b/extractor/precomputation.h @@ -30,7 +30,6 @@ class Precomputation { void WriteBinary(const fs::path& filepath) const; - virtual const Index& GetInvertedIndex() const; virtual const Index& GetCollocations() const; static int NON_TERMINAL; @@ -49,7 +48,6 @@ class Precomputation { void AddStartPositions(vector& positions, int pos1, int pos2); void AddStartPositions(vector& positions, int pos1, int pos2, int pos3); - Index inverted_index; Index collocations; }; diff --git a/extractor/precomputation_test.cc b/extractor/precomputation_test.cc index 9edb29db..6b77b9c0 100644 --- a/extractor/precomputation_test.cc +++ b/extractor/precomputation_test.cc @@ -35,40 +35,6 @@ class PrecomputationTest : public Test { shared_ptr suffix_array; }; -TEST_F(PrecomputationTest, TestInvertedIndex) { - Precomputation precomputation(suffix_array, 100, 3, 10, 5, 1, 4, 2); - Index inverted_index = precomputation.GetInvertedIndex(); - - EXPECT_EQ(8, inverted_index.size()); - vector key = {2}; - vector expected_value = {1, 5, 8, 11}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {3}; - expected_value = {2, 6, 9}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {4}; - expected_value = {0, 10}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {5}; - expected_value = {3, 7}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {4, 2}; - expected_value = {0, 10}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {2, 3}; - expected_value = {1, 5, 8}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {3, 5}; - expected_value = {2, 6}; - EXPECT_EQ(expected_value, inverted_index[key]); - key = {2, 3, 5}; - expected_value = {1, 5}; - EXPECT_EQ(expected_value, inverted_index[key]); - - key = {2, 4}; - EXPECT_EQ(0, inverted_index.count(key)); -} - TEST_F(PrecomputationTest, TestCollocations) { Precomputation precomputation(suffix_array, 3, 3, 10, 5, 1, 4, 2); Index collocations = precomputation.GetCollocations(); diff --git a/extractor/run_extractor.cc b/extractor/run_extractor.cc index 36dbd7a0..5255737d 100644 --- a/extractor/run_extractor.cc +++ b/extractor/run_extractor.cc @@ -31,14 +31,6 @@ namespace fs = boost::filesystem; namespace po = boost::program_options; using namespace std; -void my_pause() { - cerr << "pausing..." << endl; - for (int i = 0; i < 10000000; ++i) { - cerr << endl; - } - cerr << "end pause" << endl; -} - int main(int argc, char** argv) { // TODO(pauldb): Also take arguments from config file. po::options_description desc("Command line options"); @@ -122,7 +114,7 @@ int main(int argc, char** argv) { cerr << "Reading alignment took " << GetDuration(start_time, stop_time) << " seconds" << endl; - cerr << "Precomputating collocations..." << endl; + cerr << "Precomputing collocations..." << endl; start_time = Clock::now(); shared_ptr precomputation = make_shared( source_suffix_array, @@ -150,6 +142,8 @@ int main(int argc, char** argv) { << GetDuration(preprocess_start_time, preprocess_stop_time) << " seconds" << endl; + cerr << "creating grammar extractor" << endl; + Clock::time_point extraction_start_time = Clock::now(); vector > features = { make_shared(), @@ -176,6 +170,9 @@ int main(int argc, char** argv) { vm["max_samples"].as(), vm["tight_phrases"].as()); + // Release extra memory used by the initial precomputation. + precomputation.reset(); + int grammar_id = 0; fs::path grammar_path = vm["grammars"].as(); if (!fs::is_directory(grammar_path)) { diff --git a/python/pkg/cdec/sa/compile.py b/python/pkg/cdec/sa/compile.py index 1362e7b5..d4cd8387 100644 --- a/python/pkg/cdec/sa/compile.py +++ b/python/pkg/cdec/sa/compile.py @@ -21,10 +21,6 @@ def precompute(f_sa, max_len, max_nt, max_size, min_gap, rank1, rank2, tight_phr train_min_gap_size=min_gap) return precomp -def my_pause(): - for i in range(10000000): - print >> sys.stderr, "" - def main(): preprocess_start_time = monitor_cpu() sys.setrecursionlimit(sys.getrecursionlimit() * 100) @@ -89,8 +85,6 @@ def main(): stop_time = monitor_cpu() logger.info('Compiling source suffix array took %f seconds', stop_time - start_time) - my_pause() - start_time = monitor_cpu() logger.info('Compiling target data array') if args.bitext: @@ -100,7 +94,6 @@ def main(): e.write_binary(e_bin) stop_time = monitor_cpu() logger.info('Compiling target data array took %f seconds', stop_time - start_time) - my_pause() start_time = monitor_cpu() logger.info('Precomputing frequent phrases') @@ -108,15 +101,12 @@ def main(): stop_time = monitor_cpu() logger.info('Compiling precomputations took %f seconds', stop_time - start_time) - my_pause() - start_time = monitor_cpu() logger.info('Compiling alignment') a = cdec.sa.Alignment(from_text=args.alignment) a.write_binary(a_bin) stop_time = monitor_cpu() logger.info('Compiling alignment took %f seonds', stop_time - start_time) - my_pause() start_time = monitor_cpu() logger.info('Compiling bilexical dictionary') @@ -124,7 +114,6 @@ def main(): lex.write_binary(lex_bin) stop_time = monitor_cpu() logger.info('Compiling bilexical dictionary took %f seconds', stop_time - start_time) - my_pause() # Write configuration config = cdec.configobj.ConfigObj(args.config, unrepr=True) diff --git a/python/src/sa/_sa.c b/python/src/sa/_sa.c index 92abd4c3..4bdabc17 100644 --- a/python/src/sa/_sa.c +++ b/python/src/sa/_sa.c @@ -1,4 +1,4 @@ -/* Generated by Cython 0.16 on Fri Feb 22 16:52:09 2013 */ +/* Generated by Cython 0.16 on Wed Mar 6 11:06:18 2013 */ #define PY_SSIZE_T_CLEAN #include "Python.h" -- cgit v1.2.3 From ab5367aa2c42126a04034cd7d3cec125bca399ca Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Wed, 6 Mar 2013 15:25:54 +0000 Subject: Namespace for extractor. --- extractor/alignment.cc | 4 ++++ extractor/alignment.h | 4 ++++ extractor/alignment_test.cc | 4 +++- extractor/compile.cc | 1 + extractor/data_array.cc | 4 ++++ extractor/data_array.h | 4 ++++ extractor/data_array_test.cc | 4 +++- extractor/fast_intersector.cc | 4 ++++ extractor/fast_intersector.h | 4 ++++ extractor/fast_intersector_test.cc | 8 ++++---- extractor/features/count_source_target.cc | 6 ++++++ extractor/features/count_source_target.h | 6 ++++++ extractor/features/count_source_target_test.cc | 6 +++++- extractor/features/feature.cc | 6 ++++++ extractor/features/feature.h | 6 ++++++ extractor/features/is_source_singleton.cc | 6 ++++++ extractor/features/is_source_singleton.h | 6 ++++++ extractor/features/is_source_singleton_test.cc | 6 +++++- extractor/features/is_source_target_singleton.cc | 6 ++++++ extractor/features/is_source_target_singleton.h | 6 ++++++ extractor/features/is_source_target_singleton_test.cc | 6 +++++- extractor/features/max_lex_source_given_target.cc | 6 ++++++ extractor/features/max_lex_source_given_target.h | 7 +++++++ extractor/features/max_lex_source_given_target_test.cc | 6 +++++- extractor/features/max_lex_target_given_source.cc | 6 ++++++ extractor/features/max_lex_target_given_source.h | 7 +++++++ extractor/features/max_lex_target_given_source_test.cc | 6 +++++- extractor/features/sample_source_count.cc | 6 ++++++ extractor/features/sample_source_count.h | 6 ++++++ extractor/features/sample_source_count_test.cc | 6 +++++- extractor/features/target_given_source_coherent.cc | 6 ++++++ extractor/features/target_given_source_coherent.h | 6 ++++++ extractor/features/target_given_source_coherent_test.cc | 6 +++++- extractor/grammar.cc | 4 ++++ extractor/grammar.h | 4 ++++ extractor/grammar_extractor.cc | 5 +++++ extractor/grammar_extractor.h | 9 +++++++-- extractor/grammar_extractor_test.cc | 4 +++- extractor/matchings_finder.cc | 4 ++++ extractor/matchings_finder.h | 4 ++++ extractor/matchings_finder_test.cc | 4 +++- extractor/matchings_trie.cc | 4 ++++ extractor/matchings_trie.h | 4 ++++ extractor/mocks/mock_alignment.h | 4 ++++ extractor/mocks/mock_data_array.h | 4 ++++ extractor/mocks/mock_fast_intersector.h | 4 ++++ extractor/mocks/mock_feature.h | 6 ++++++ extractor/mocks/mock_matchings_finder.h | 4 ++++ extractor/mocks/mock_precomputation.h | 4 ++++ extractor/mocks/mock_rule_extractor.h | 4 ++++ extractor/mocks/mock_rule_extractor_helper.h | 4 ++++ extractor/mocks/mock_rule_factory.h | 4 ++++ extractor/mocks/mock_sampler.h | 4 ++++ extractor/mocks/mock_scorer.h | 7 ++++++- extractor/mocks/mock_suffix_array.h | 4 ++++ extractor/mocks/mock_target_phrase_extractor.h | 4 ++++ extractor/mocks/mock_translation_table.h | 4 ++++ extractor/mocks/mock_vocabulary.h | 4 ++++ extractor/phrase.cc | 4 ++++ extractor/phrase.h | 4 ++++ extractor/phrase_builder.cc | 4 ++++ extractor/phrase_builder.h | 4 ++++ extractor/phrase_location.cc | 4 ++++ extractor/phrase_location.h | 4 ++++ extractor/phrase_test.cc | 4 +++- extractor/precomputation.cc | 4 ++++ extractor/precomputation.h | 6 +++++- extractor/precomputation_test.cc | 5 ++++- extractor/rule.cc | 4 ++++ extractor/rule.h | 4 ++++ extractor/rule_extractor.cc | 6 +++++- extractor/rule_extractor.h | 8 ++++++-- extractor/rule_extractor_helper.cc | 4 ++++ extractor/rule_extractor_helper.h | 4 ++++ extractor/rule_extractor_helper_test.cc | 4 +++- extractor/rule_extractor_test.cc | 4 +++- extractor/rule_factory.cc | 5 +++++ extractor/rule_factory.h | 8 ++++++-- extractor/rule_factory_test.cc | 4 +++- extractor/run_extractor.cc | 17 ++++++++++------- extractor/sampler.cc | 4 ++++ extractor/sampler.h | 4 ++++ extractor/sampler_test.cc | 4 +++- extractor/scorer.cc | 8 ++++++-- extractor/scorer.h | 16 +++++++++++----- extractor/scorer_test.cc | 16 +++++++++------- extractor/suffix_array.cc | 4 ++++ extractor/suffix_array.h | 4 ++++ extractor/suffix_array_test.cc | 4 +++- extractor/target_phrase_extractor.cc | 4 ++++ extractor/target_phrase_extractor.h | 8 ++++++-- extractor/target_phrase_extractor_test.cc | 4 +++- extractor/time_util.cc | 4 ++++ extractor/time_util.h | 4 ++++ extractor/translation_table.cc | 4 ++++ extractor/translation_table.h | 8 ++++++-- extractor/translation_table_test.cc | 4 +++- extractor/vocabulary.cc | 3 +++ extractor/vocabulary.h | 4 ++++ 99 files changed, 460 insertions(+), 58 deletions(-) (limited to 'extractor/precomputation_test.cc') diff --git a/extractor/alignment.cc b/extractor/alignment.cc index ff39d484..f9bbcf6a 100644 --- a/extractor/alignment.cc +++ b/extractor/alignment.cc @@ -13,6 +13,8 @@ namespace fs = boost::filesystem; using namespace std; +namespace extractor { + Alignment::Alignment(const string& filename) { ifstream infile(filename.c_str()); string line; @@ -49,3 +51,5 @@ void Alignment::WriteBinary(const fs::path& filepath) { fwrite(alignment.data(), sizeof(pair), size, file); } } + +} // namespace extractor diff --git a/extractor/alignment.h b/extractor/alignment.h index f7e79585..ef89dc0c 100644 --- a/extractor/alignment.h +++ b/extractor/alignment.h @@ -9,6 +9,8 @@ namespace fs = boost::filesystem; using namespace std; +namespace extractor { + class Alignment { public: Alignment(const string& filename); @@ -26,4 +28,6 @@ class Alignment { vector > > alignments; }; +} // namespace extractor + #endif diff --git a/extractor/alignment_test.cc b/extractor/alignment_test.cc index 1bc51a56..a7defb66 100644 --- a/extractor/alignment_test.cc +++ b/extractor/alignment_test.cc @@ -8,6 +8,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class AlignmentTest : public Test { @@ -28,4 +29,5 @@ TEST_F(AlignmentTest, TestGetLinks) { EXPECT_EQ(expected_links, alignment->GetLinks(1)); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/compile.cc b/extractor/compile.cc index f5cd41f4..7062ef03 100644 --- a/extractor/compile.cc +++ b/extractor/compile.cc @@ -14,6 +14,7 @@ namespace fs = boost::filesystem; namespace po = boost::program_options; using namespace std; +using namespace extractor; int main(int argc, char** argv) { po::options_description desc("Command line options"); diff --git a/extractor/data_array.cc b/extractor/data_array.cc index cd430c69..481abb80 100644 --- a/extractor/data_array.cc +++ b/extractor/data_array.cc @@ -10,6 +10,8 @@ namespace fs = boost::filesystem; using namespace std; +namespace extractor { + int DataArray::NULL_WORD = 0; int DataArray::END_OF_LINE = 1; string DataArray::NULL_WORD_STR = "__NULL__"; @@ -154,3 +156,5 @@ int DataArray::GetWordId(const string& word) const { string DataArray::GetWord(int word_id) const { return id2word[word_id]; } + +} // namespace extractor diff --git a/extractor/data_array.h b/extractor/data_array.h index 96950789..42e12135 100644 --- a/extractor/data_array.h +++ b/extractor/data_array.h @@ -10,6 +10,8 @@ namespace fs = boost::filesystem; using namespace std; +namespace extractor { + enum Side { SOURCE, TARGET @@ -73,4 +75,6 @@ class DataArray { vector sentence_start; }; +} // namespace extractor + #endif diff --git a/extractor/data_array_test.cc b/extractor/data_array_test.cc index ba5ce09e..71175fda 100644 --- a/extractor/data_array_test.cc +++ b/extractor/data_array_test.cc @@ -11,6 +11,7 @@ using namespace std; using namespace ::testing; namespace fs = boost::filesystem; +namespace extractor { namespace { class DataArrayTest : public Test { @@ -93,4 +94,5 @@ TEST_F(DataArrayTest, TestSentenceData) { } } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/fast_intersector.cc b/extractor/fast_intersector.cc index 8c7a7af8..cec3d30b 100644 --- a/extractor/fast_intersector.cc +++ b/extractor/fast_intersector.cc @@ -9,6 +9,8 @@ #include "suffix_array.h" #include "vocabulary.h" +namespace extractor { + FastIntersector::FastIntersector(shared_ptr suffix_array, shared_ptr precomputation, shared_ptr vocabulary, @@ -189,3 +191,5 @@ pair FastIntersector::GetSearchRange(bool has_marginal_x) const { return make_pair(1, 2); } } + +} // namespace extractor diff --git a/extractor/fast_intersector.h b/extractor/fast_intersector.h index 785e428e..32c88a30 100644 --- a/extractor/fast_intersector.h +++ b/extractor/fast_intersector.h @@ -9,6 +9,8 @@ using namespace std; +namespace extractor { + typedef boost::hash > VectorHash; typedef unordered_map, vector, VectorHash> Index; @@ -62,4 +64,6 @@ class FastIntersector { Index collocations; }; +} // namespace extractor + #endif diff --git a/extractor/fast_intersector_test.cc b/extractor/fast_intersector_test.cc index 0d6ef367..76c3aaea 100644 --- a/extractor/fast_intersector_test.cc +++ b/extractor/fast_intersector_test.cc @@ -4,8 +4,8 @@ #include "fast_intersector.h" #include "mocks/mock_data_array.h" -#include "mocks/mock_suffix_array.h" #include "mocks/mock_precomputation.h" +#include "mocks/mock_suffix_array.h" #include "mocks/mock_vocabulary.h" #include "phrase.h" #include "phrase_location.h" @@ -14,6 +14,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class FastIntersectorTest : public Test { @@ -112,7 +113,6 @@ TEST_F(FastIntersectorTest, TestIntersectaXbXcExtendSuffix) { EXPECT_EQ(PhraseLocation(expected_locs, 3), result); } -/* TEST_F(FastIntersectorTest, TestIntersectaXbExtendPrefix) { vector symbols = {1, -1, 3}; Phrase phrase = phrase_builder->Build(symbols); @@ -141,6 +141,6 @@ TEST_F(FastIntersectorTest, TestIntersectCheckEstimates) { EXPECT_EQ(PhraseLocation(expected_locs, 2), result); EXPECT_EQ(PhraseLocation(10, 12), suffix_location); } -*/ -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/features/count_source_target.cc b/extractor/features/count_source_target.cc index 9441b451..db0385e0 100644 --- a/extractor/features/count_source_target.cc +++ b/extractor/features/count_source_target.cc @@ -2,6 +2,9 @@ #include +namespace extractor { +namespace features { + double CountSourceTarget::Score(const FeatureContext& context) const { return log10(1 + context.pair_count); } @@ -9,3 +12,6 @@ double CountSourceTarget::Score(const FeatureContext& context) const { string CountSourceTarget::GetName() const { return "CountEF"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/count_source_target.h b/extractor/features/count_source_target.h index a2481944..dec78883 100644 --- a/extractor/features/count_source_target.h +++ b/extractor/features/count_source_target.h @@ -3,6 +3,9 @@ #include "feature.h" +namespace extractor { +namespace features { + class CountSourceTarget : public Feature { public: double Score(const FeatureContext& context) const; @@ -10,4 +13,7 @@ class CountSourceTarget : public Feature { string GetName() const; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/count_source_target_test.cc b/extractor/features/count_source_target_test.cc index 22633bb6..1fd0c2aa 100644 --- a/extractor/features/count_source_target_test.cc +++ b/extractor/features/count_source_target_test.cc @@ -8,6 +8,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class CountSourceTargetTest : public Test { @@ -29,4 +31,6 @@ TEST_F(CountSourceTargetTest, TestScore) { EXPECT_EQ(1.0, feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/features/feature.cc b/extractor/features/feature.cc index 876f5f8f..939bcc59 100644 --- a/extractor/features/feature.cc +++ b/extractor/features/feature.cc @@ -1,5 +1,11 @@ #include "feature.h" +namespace extractor { +namespace features { + const double Feature::MAX_SCORE = 99.0; Feature::~Feature() {} + +} // namespace features +} // namespace extractor diff --git a/extractor/features/feature.h b/extractor/features/feature.h index aca58401..de2827bc 100644 --- a/extractor/features/feature.h +++ b/extractor/features/feature.h @@ -8,6 +8,9 @@ using namespace std; +namespace extractor { +namespace features { + struct FeatureContext { FeatureContext(const Phrase& source_phrase, const Phrase& target_phrase, double source_phrase_count, int pair_count, int num_samples) : @@ -33,4 +36,7 @@ class Feature { static const double MAX_SCORE; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/is_source_singleton.cc b/extractor/features/is_source_singleton.cc index 98d4e5fe..ab54e51a 100644 --- a/extractor/features/is_source_singleton.cc +++ b/extractor/features/is_source_singleton.cc @@ -2,6 +2,9 @@ #include +namespace extractor { +namespace features { + double IsSourceSingleton::Score(const FeatureContext& context) const { return context.source_phrase_count == 1; } @@ -9,3 +12,6 @@ double IsSourceSingleton::Score(const FeatureContext& context) const { string IsSourceSingleton::GetName() const { return "IsSingletonF"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/is_source_singleton.h b/extractor/features/is_source_singleton.h index 7cc72828..30f76c6d 100644 --- a/extractor/features/is_source_singleton.h +++ b/extractor/features/is_source_singleton.h @@ -3,6 +3,9 @@ #include "feature.h" +namespace extractor { +namespace features { + class IsSourceSingleton : public Feature { public: double Score(const FeatureContext& context) const; @@ -10,4 +13,7 @@ class IsSourceSingleton : public Feature { string GetName() const; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/is_source_singleton_test.cc b/extractor/features/is_source_singleton_test.cc index 8c71e593..f4266671 100644 --- a/extractor/features/is_source_singleton_test.cc +++ b/extractor/features/is_source_singleton_test.cc @@ -8,6 +8,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class IsSourceSingletonTest : public Test { @@ -32,4 +34,6 @@ TEST_F(IsSourceSingletonTest, TestScore) { EXPECT_EQ(1, feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/features/is_source_target_singleton.cc b/extractor/features/is_source_target_singleton.cc index 31d36532..03b3c62c 100644 --- a/extractor/features/is_source_target_singleton.cc +++ b/extractor/features/is_source_target_singleton.cc @@ -2,6 +2,9 @@ #include +namespace extractor { +namespace features { + double IsSourceTargetSingleton::Score(const FeatureContext& context) const { return context.pair_count == 1; } @@ -9,3 +12,6 @@ double IsSourceTargetSingleton::Score(const FeatureContext& context) const { string IsSourceTargetSingleton::GetName() const { return "IsSingletonFE"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/is_source_target_singleton.h b/extractor/features/is_source_target_singleton.h index 58913b74..12fb6ee6 100644 --- a/extractor/features/is_source_target_singleton.h +++ b/extractor/features/is_source_target_singleton.h @@ -3,6 +3,9 @@ #include "feature.h" +namespace extractor { +namespace features { + class IsSourceTargetSingleton : public Feature { public: double Score(const FeatureContext& context) const; @@ -10,4 +13,7 @@ class IsSourceTargetSingleton : public Feature { string GetName() const; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/is_source_target_singleton_test.cc b/extractor/features/is_source_target_singleton_test.cc index a51f77c9..929635b0 100644 --- a/extractor/features/is_source_target_singleton_test.cc +++ b/extractor/features/is_source_target_singleton_test.cc @@ -8,6 +8,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class IsSourceTargetSingletonTest : public Test { @@ -32,4 +34,6 @@ TEST_F(IsSourceTargetSingletonTest, TestScore) { EXPECT_EQ(1, feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/features/max_lex_source_given_target.cc b/extractor/features/max_lex_source_given_target.cc index 21f5c76a..3ffe598c 100644 --- a/extractor/features/max_lex_source_given_target.cc +++ b/extractor/features/max_lex_source_given_target.cc @@ -5,6 +5,9 @@ #include "../data_array.h" #include "../translation_table.h" +namespace extractor { +namespace features { + MaxLexSourceGivenTarget::MaxLexSourceGivenTarget( shared_ptr table) : table(table) {} @@ -29,3 +32,6 @@ double MaxLexSourceGivenTarget::Score(const FeatureContext& context) const { string MaxLexSourceGivenTarget::GetName() const { return "MaxLexFgivenE"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/max_lex_source_given_target.h b/extractor/features/max_lex_source_given_target.h index e87c1c8e..bfa7ef1b 100644 --- a/extractor/features/max_lex_source_given_target.h +++ b/extractor/features/max_lex_source_given_target.h @@ -7,8 +7,12 @@ using namespace std; +namespace extractor { + class TranslationTable; +namespace features { + class MaxLexSourceGivenTarget : public Feature { public: MaxLexSourceGivenTarget(shared_ptr table); @@ -21,4 +25,7 @@ class MaxLexSourceGivenTarget : public Feature { shared_ptr table; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/max_lex_source_given_target_test.cc b/extractor/features/max_lex_source_given_target_test.cc index 5fd41f8b..c1edb483 100644 --- a/extractor/features/max_lex_source_given_target_test.cc +++ b/extractor/features/max_lex_source_given_target_test.cc @@ -13,6 +13,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class MaxLexSourceGivenTargetTest : public Test { @@ -71,4 +73,6 @@ TEST_F(MaxLexSourceGivenTargetTest, TestScore) { EXPECT_EQ(99 - log10(18), feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/features/max_lex_target_given_source.cc b/extractor/features/max_lex_target_given_source.cc index f2bc2474..30140d80 100644 --- a/extractor/features/max_lex_target_given_source.cc +++ b/extractor/features/max_lex_target_given_source.cc @@ -5,6 +5,9 @@ #include "../data_array.h" #include "../translation_table.h" +namespace extractor { +namespace features { + MaxLexTargetGivenSource::MaxLexTargetGivenSource( shared_ptr table) : table(table) {} @@ -29,3 +32,6 @@ double MaxLexTargetGivenSource::Score(const FeatureContext& context) const { string MaxLexTargetGivenSource::GetName() const { return "MaxLexEgivenF"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/max_lex_target_given_source.h b/extractor/features/max_lex_target_given_source.h index 9585ff04..66cf0914 100644 --- a/extractor/features/max_lex_target_given_source.h +++ b/extractor/features/max_lex_target_given_source.h @@ -7,8 +7,12 @@ using namespace std; +namespace extractor { + class TranslationTable; +namespace features { + class MaxLexTargetGivenSource : public Feature { public: MaxLexTargetGivenSource(shared_ptr table); @@ -21,4 +25,7 @@ class MaxLexTargetGivenSource : public Feature { shared_ptr table; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/max_lex_target_given_source_test.cc b/extractor/features/max_lex_target_given_source_test.cc index c8701bf7..9ceb13e5 100644 --- a/extractor/features/max_lex_target_given_source_test.cc +++ b/extractor/features/max_lex_target_given_source_test.cc @@ -13,6 +13,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class MaxLexTargetGivenSourceTest : public Test { @@ -71,4 +73,6 @@ TEST_F(MaxLexTargetGivenSourceTest, TestScore) { EXPECT_EQ(-log10(36), feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/features/sample_source_count.cc b/extractor/features/sample_source_count.cc index 88b645b1..b110fc51 100644 --- a/extractor/features/sample_source_count.cc +++ b/extractor/features/sample_source_count.cc @@ -2,6 +2,9 @@ #include +namespace extractor { +namespace features { + double SampleSourceCount::Score(const FeatureContext& context) const { return log10(1 + context.num_samples); } @@ -9,3 +12,6 @@ double SampleSourceCount::Score(const FeatureContext& context) const { string SampleSourceCount::GetName() const { return "SampleCountF"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/sample_source_count.h b/extractor/features/sample_source_count.h index 62d236c8..53c7f954 100644 --- a/extractor/features/sample_source_count.h +++ b/extractor/features/sample_source_count.h @@ -3,6 +3,9 @@ #include "feature.h" +namespace extractor { +namespace features { + class SampleSourceCount : public Feature { public: double Score(const FeatureContext& context) const; @@ -10,4 +13,7 @@ class SampleSourceCount : public Feature { string GetName() const; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/sample_source_count_test.cc b/extractor/features/sample_source_count_test.cc index 7d226104..63856b9d 100644 --- a/extractor/features/sample_source_count_test.cc +++ b/extractor/features/sample_source_count_test.cc @@ -9,6 +9,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class SampleSourceCountTest : public Test { @@ -33,4 +35,6 @@ TEST_F(SampleSourceCountTest, TestScore) { EXPECT_EQ(1.0, feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/features/target_given_source_coherent.cc b/extractor/features/target_given_source_coherent.cc index 274b3364..c4551d88 100644 --- a/extractor/features/target_given_source_coherent.cc +++ b/extractor/features/target_given_source_coherent.cc @@ -2,6 +2,9 @@ #include +namespace extractor { +namespace features { + double TargetGivenSourceCoherent::Score(const FeatureContext& context) const { double prob = (double) context.pair_count / context.num_samples; return prob > 0 ? -log10(prob) : MAX_SCORE; @@ -10,3 +13,6 @@ double TargetGivenSourceCoherent::Score(const FeatureContext& context) const { string TargetGivenSourceCoherent::GetName() const { return "EgivenFCoherent"; } + +} // namespace features +} // namespace extractor diff --git a/extractor/features/target_given_source_coherent.h b/extractor/features/target_given_source_coherent.h index 09c8edb1..80d9f617 100644 --- a/extractor/features/target_given_source_coherent.h +++ b/extractor/features/target_given_source_coherent.h @@ -3,6 +3,9 @@ #include "feature.h" +namespace extractor { +namespace features { + class TargetGivenSourceCoherent : public Feature { public: double Score(const FeatureContext& context) const; @@ -10,4 +13,7 @@ class TargetGivenSourceCoherent : public Feature { string GetName() const; }; +} // namespace features +} // namespace extractor + #endif diff --git a/extractor/features/target_given_source_coherent_test.cc b/extractor/features/target_given_source_coherent_test.cc index c54c06c2..454105e1 100644 --- a/extractor/features/target_given_source_coherent_test.cc +++ b/extractor/features/target_given_source_coherent_test.cc @@ -8,6 +8,8 @@ using namespace std; using namespace ::testing; +namespace extractor { +namespace features { namespace { class TargetGivenSourceCoherentTest : public Test { @@ -32,4 +34,6 @@ TEST_F(TargetGivenSourceCoherentTest, TestScore) { EXPECT_EQ(99.0, feature->Score(context)); } -} // namespace +} // namespace +} // namespace features +} // namespace extractor diff --git a/extractor/grammar.cc b/extractor/grammar.cc index 8124a804..8e5bcd45 100644 --- a/extractor/grammar.cc +++ b/extractor/grammar.cc @@ -6,6 +6,8 @@ using namespace std; +namespace extractor { + Grammar::Grammar(const vector& rules, const vector& feature_names) : rules(rules), feature_names(feature_names) {} @@ -37,3 +39,5 @@ ostream& operator<<(ostream& os, const Grammar& grammar) { return os; } + +} // namespace extractor diff --git a/extractor/grammar.h b/extractor/grammar.h index 889cc2f3..a424d65a 100644 --- a/extractor/grammar.h +++ b/extractor/grammar.h @@ -7,6 +7,8 @@ using namespace std; +namespace extractor { + class Rule; class Grammar { @@ -24,4 +26,6 @@ class Grammar { vector feature_names; }; +} // namespace extractor + #endif diff --git a/extractor/grammar_extractor.cc b/extractor/grammar_extractor.cc index b8f6f0c7..8050ce7b 100644 --- a/extractor/grammar_extractor.cc +++ b/extractor/grammar_extractor.cc @@ -6,10 +6,13 @@ #include "grammar.h" #include "rule.h" +#include "rule_factory.h" #include "vocabulary.h" using namespace std; +namespace extractor { + GrammarExtractor::GrammarExtractor( shared_ptr source_suffix_array, shared_ptr target_data_array, @@ -55,3 +58,5 @@ vector GrammarExtractor::AnnotateWords(const vector& words) { } return result; } + +} // namespace extractor diff --git a/extractor/grammar_extractor.h b/extractor/grammar_extractor.h index f50a8d14..6b1dcf98 100644 --- a/extractor/grammar_extractor.h +++ b/extractor/grammar_extractor.h @@ -1,18 +1,21 @@ #ifndef _GRAMMAR_EXTRACTOR_H_ #define _GRAMMAR_EXTRACTOR_H_ +#include #include #include -#include "rule_factory.h" - using namespace std; +namespace extractor { + class Alignment; class DataArray; class Grammar; +class HieroCachingRuleFactory; class Precomputation; class Rule; +class Scorer; class SuffixArray; class Vocabulary; @@ -46,4 +49,6 @@ class GrammarExtractor { shared_ptr rule_factory; }; +} // namespace extractor + #endif diff --git a/extractor/grammar_extractor_test.cc b/extractor/grammar_extractor_test.cc index d4ed7d4f..823bb8b4 100644 --- a/extractor/grammar_extractor_test.cc +++ b/extractor/grammar_extractor_test.cc @@ -13,6 +13,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { TEST(GrammarExtractorTest, TestAnnotatingWords) { @@ -46,4 +47,5 @@ TEST(GrammarExtractorTest, TestAnnotatingWords) { extractor.GetGrammar(sentence); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/matchings_finder.cc b/extractor/matchings_finder.cc index eaf493b2..ceed6891 100644 --- a/extractor/matchings_finder.cc +++ b/extractor/matchings_finder.cc @@ -3,6 +3,8 @@ #include "suffix_array.h" #include "phrase_location.h" +namespace extractor { + MatchingsFinder::MatchingsFinder(shared_ptr suffix_array) : suffix_array(suffix_array) {} @@ -19,3 +21,5 @@ PhraseLocation MatchingsFinder::Find(PhraseLocation& location, return suffix_array->Lookup(location.sa_low, location.sa_high, word, offset); } + +} // namespace extractor diff --git a/extractor/matchings_finder.h b/extractor/matchings_finder.h index ed04d8b8..fbb504ef 100644 --- a/extractor/matchings_finder.h +++ b/extractor/matchings_finder.h @@ -6,6 +6,8 @@ using namespace std; +namespace extractor { + class PhraseLocation; class SuffixArray; @@ -25,4 +27,6 @@ class MatchingsFinder { shared_ptr suffix_array; }; +} // namespace extractor + #endif diff --git a/extractor/matchings_finder_test.cc b/extractor/matchings_finder_test.cc index 817f1635..d40e5191 100644 --- a/extractor/matchings_finder_test.cc +++ b/extractor/matchings_finder_test.cc @@ -9,6 +9,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class MatchingsFinderTest : public Test { @@ -39,4 +40,5 @@ TEST_F(MatchingsFinderTest, ResizeUnsetRange) { EXPECT_EQ(PhraseLocation(0, 10), phrase_location); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/matchings_trie.cc b/extractor/matchings_trie.cc index 8ea795db..c7b98765 100644 --- a/extractor/matchings_trie.cc +++ b/extractor/matchings_trie.cc @@ -1,5 +1,7 @@ #include "matchings_trie.h" +namespace extractor { + void MatchingsTrie::Reset() { ResetTree(root); root = make_shared(); @@ -20,3 +22,5 @@ void MatchingsTrie::ResetTree(shared_ptr root) { root.reset(); } } + +} // namespace extractor diff --git a/extractor/matchings_trie.h b/extractor/matchings_trie.h index 6e72b2db..a54671d2 100644 --- a/extractor/matchings_trie.h +++ b/extractor/matchings_trie.h @@ -9,6 +9,8 @@ using namespace std; +namespace extractor { + struct TrieNode { TrieNode(shared_ptr suffix_link = shared_ptr(), Phrase phrase = Phrase(), @@ -44,4 +46,6 @@ class MatchingsTrie { shared_ptr root; }; +} // namespace extractor + #endif diff --git a/extractor/mocks/mock_alignment.h b/extractor/mocks/mock_alignment.h index 4a5077ad..3d745e9d 100644 --- a/extractor/mocks/mock_alignment.h +++ b/extractor/mocks/mock_alignment.h @@ -2,9 +2,13 @@ #include "../alignment.h" +namespace extractor { + typedef vector > SentenceLinks; class MockAlignment : public Alignment { public: MOCK_CONST_METHOD1(GetLinks, SentenceLinks(int sentence_id)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_data_array.h b/extractor/mocks/mock_data_array.h index 004e8906..cf9f3671 100644 --- a/extractor/mocks/mock_data_array.h +++ b/extractor/mocks/mock_data_array.h @@ -2,6 +2,8 @@ #include "../data_array.h" +namespace extractor { + class MockDataArray : public DataArray { public: MOCK_CONST_METHOD0(GetData, const vector&()); @@ -17,3 +19,5 @@ class MockDataArray : public DataArray { MOCK_CONST_METHOD1(GetSentenceStart, int(int sentence_id)); MOCK_CONST_METHOD1(GetSentenceId, int(int position)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_fast_intersector.h b/extractor/mocks/mock_fast_intersector.h index 201386f2..665add65 100644 --- a/extractor/mocks/mock_fast_intersector.h +++ b/extractor/mocks/mock_fast_intersector.h @@ -4,8 +4,12 @@ #include "../phrase.h" #include "../phrase_location.h" +namespace extractor { + class MockFastIntersector : public FastIntersector { public: MOCK_METHOD3(Intersect, PhraseLocation(PhraseLocation&, PhraseLocation&, const Phrase&)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_feature.h b/extractor/mocks/mock_feature.h index d2137629..19ba4de9 100644 --- a/extractor/mocks/mock_feature.h +++ b/extractor/mocks/mock_feature.h @@ -2,8 +2,14 @@ #include "../features/feature.h" +namespace extractor { +namespace features { + class MockFeature : public Feature { public: MOCK_CONST_METHOD1(Score, double(const FeatureContext& context)); MOCK_CONST_METHOD0(GetName, string()); }; + +} // namespace features +} // namespace extractor diff --git a/extractor/mocks/mock_matchings_finder.h b/extractor/mocks/mock_matchings_finder.h index 3e80d266..ffbb06c7 100644 --- a/extractor/mocks/mock_matchings_finder.h +++ b/extractor/mocks/mock_matchings_finder.h @@ -3,7 +3,11 @@ #include "../matchings_finder.h" #include "../phrase_location.h" +namespace extractor { + class MockMatchingsFinder : public MatchingsFinder { public: MOCK_METHOD3(Find, PhraseLocation(PhraseLocation&, const string&, int)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_precomputation.h b/extractor/mocks/mock_precomputation.h index 9bc72235..64934b94 100644 --- a/extractor/mocks/mock_precomputation.h +++ b/extractor/mocks/mock_precomputation.h @@ -2,7 +2,11 @@ #include "../precomputation.h" +namespace extractor { + class MockPrecomputation : public Precomputation { public: MOCK_CONST_METHOD0(GetCollocations, const Index&()); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_rule_extractor.h b/extractor/mocks/mock_rule_extractor.h index f18e009a..28b644b0 100644 --- a/extractor/mocks/mock_rule_extractor.h +++ b/extractor/mocks/mock_rule_extractor.h @@ -5,8 +5,12 @@ #include "../rule.h" #include "../rule_extractor.h" +namespace extractor { + class MockRuleExtractor : public RuleExtractor { public: MOCK_CONST_METHOD2(ExtractRules, vector(const Phrase&, const PhraseLocation&)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_rule_extractor_helper.h b/extractor/mocks/mock_rule_extractor_helper.h index 63ff1048..3b0ac0f5 100644 --- a/extractor/mocks/mock_rule_extractor_helper.h +++ b/extractor/mocks/mock_rule_extractor_helper.h @@ -6,6 +6,8 @@ using namespace std; +namespace extractor { + typedef unordered_map Indexes; class MockRuleExtractorHelper : public RuleExtractorHelper { @@ -76,3 +78,5 @@ class MockRuleExtractorHelper : public RuleExtractorHelper { bool met_constraints; bool get_gaps; }; + +} // namespace extractor diff --git a/extractor/mocks/mock_rule_factory.h b/extractor/mocks/mock_rule_factory.h index 2a96be93..11cb9ab5 100644 --- a/extractor/mocks/mock_rule_factory.h +++ b/extractor/mocks/mock_rule_factory.h @@ -3,7 +3,11 @@ #include "../grammar.h" #include "../rule_factory.h" +namespace extractor { + class MockHieroCachingRuleFactory : public HieroCachingRuleFactory { public: MOCK_METHOD1(GetGrammar, Grammar(const vector& word_ids)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_sampler.h b/extractor/mocks/mock_sampler.h index b2306109..7022f7b3 100644 --- a/extractor/mocks/mock_sampler.h +++ b/extractor/mocks/mock_sampler.h @@ -3,7 +3,11 @@ #include "../phrase_location.h" #include "../sampler.h" +namespace extractor { + class MockSampler : public Sampler { public: MOCK_CONST_METHOD1(Sample, PhraseLocation(const PhraseLocation& location)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_scorer.h b/extractor/mocks/mock_scorer.h index 48115ef4..4d593ddf 100644 --- a/extractor/mocks/mock_scorer.h +++ b/extractor/mocks/mock_scorer.h @@ -3,8 +3,13 @@ #include "../scorer.h" #include "../features/feature.h" +namespace extractor { + class MockScorer : public Scorer { public: - MOCK_CONST_METHOD1(Score, vector(const FeatureContext& context)); + MOCK_CONST_METHOD1(Score, vector( + const features::FeatureContext& context)); MOCK_CONST_METHOD0(GetFeatureNames, vector()); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_suffix_array.h b/extractor/mocks/mock_suffix_array.h index 11a3a443..6886232a 100644 --- a/extractor/mocks/mock_suffix_array.h +++ b/extractor/mocks/mock_suffix_array.h @@ -9,6 +9,8 @@ using namespace std; +namespace extractor { + class MockSuffixArray : public SuffixArray { public: MOCK_CONST_METHOD0(GetSize, int()); @@ -17,3 +19,5 @@ class MockSuffixArray : public SuffixArray { MOCK_CONST_METHOD1(GetSuffix, int(int)); MOCK_CONST_METHOD4(Lookup, PhraseLocation(int, int, const string& word, int)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_target_phrase_extractor.h b/extractor/mocks/mock_target_phrase_extractor.h index 6dc6bba6..e5e9aeab 100644 --- a/extractor/mocks/mock_target_phrase_extractor.h +++ b/extractor/mocks/mock_target_phrase_extractor.h @@ -2,6 +2,8 @@ #include "../target_phrase_extractor.h" +namespace extractor { + typedef pair PhraseExtract; class MockTargetPhraseExtractor : public TargetPhraseExtractor { @@ -10,3 +12,5 @@ class MockTargetPhraseExtractor : public TargetPhraseExtractor { const vector > &, const vector&, int, int, const unordered_map&, int)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_translation_table.h b/extractor/mocks/mock_translation_table.h index a35c9327..358c854f 100644 --- a/extractor/mocks/mock_translation_table.h +++ b/extractor/mocks/mock_translation_table.h @@ -2,8 +2,12 @@ #include "../translation_table.h" +namespace extractor { + class MockTranslationTable : public TranslationTable { public: MOCK_METHOD2(GetSourceGivenTargetScore, double(const string&, const string&)); MOCK_METHOD2(GetTargetGivenSourceScore, double(const string&, const string&)); }; + +} // namespace extractor diff --git a/extractor/mocks/mock_vocabulary.h b/extractor/mocks/mock_vocabulary.h index e5c191f5..802c29b4 100644 --- a/extractor/mocks/mock_vocabulary.h +++ b/extractor/mocks/mock_vocabulary.h @@ -2,8 +2,12 @@ #include "../vocabulary.h" +namespace extractor { + class MockVocabulary : public Vocabulary { public: MOCK_METHOD1(GetTerminalValue, string(int word_id)); MOCK_METHOD1(GetTerminalIndex, int(const string& word)); }; + +} // namespace extractor diff --git a/extractor/phrase.cc b/extractor/phrase.cc index 6dc242db..244fab07 100644 --- a/extractor/phrase.cc +++ b/extractor/phrase.cc @@ -1,5 +1,7 @@ #include "phrase.h" +namespace extractor { + int Phrase::Arity() const { return var_pos.size(); } @@ -52,3 +54,5 @@ ostream& operator<<(ostream& os, const Phrase& phrase) { } return os; } + +} // namspace extractor diff --git a/extractor/phrase.h b/extractor/phrase.h index f40a8169..8c98a025 100644 --- a/extractor/phrase.h +++ b/extractor/phrase.h @@ -9,6 +9,8 @@ using namespace std; +namespace extractor { + class Phrase { public: friend Phrase PhraseBuilder::Build(const vector& phrase); @@ -38,4 +40,6 @@ class Phrase { vector words; }; +} // namespace extractor + #endif diff --git a/extractor/phrase_builder.cc b/extractor/phrase_builder.cc index 4325390c..9faee4be 100644 --- a/extractor/phrase_builder.cc +++ b/extractor/phrase_builder.cc @@ -3,6 +3,8 @@ #include "phrase.h" #include "vocabulary.h" +namespace extractor { + PhraseBuilder::PhraseBuilder(shared_ptr vocabulary) : vocabulary(vocabulary) {} @@ -42,3 +44,5 @@ Phrase PhraseBuilder::Extend(const Phrase& phrase, bool start_x, bool end_x) { return Build(symbols); } + +} // namespace extractor diff --git a/extractor/phrase_builder.h b/extractor/phrase_builder.h index a49af457..2956fd35 100644 --- a/extractor/phrase_builder.h +++ b/extractor/phrase_builder.h @@ -6,6 +6,8 @@ using namespace std; +namespace extractor { + class Phrase; class Vocabulary; @@ -21,4 +23,6 @@ class PhraseBuilder { shared_ptr vocabulary; }; +} // namespace extractor + #endif diff --git a/extractor/phrase_location.cc b/extractor/phrase_location.cc index b0bfed80..678ae270 100644 --- a/extractor/phrase_location.cc +++ b/extractor/phrase_location.cc @@ -1,5 +1,7 @@ #include "phrase_location.h" +namespace extractor { + PhraseLocation::PhraseLocation(int sa_low, int sa_high) : sa_low(sa_low), sa_high(sa_high), num_subpatterns(0) {} @@ -37,3 +39,5 @@ bool operator==(const PhraseLocation& a, const PhraseLocation& b) { return *a.matchings == *b.matchings; } + +} // namespace extractor diff --git a/extractor/phrase_location.h b/extractor/phrase_location.h index a0eb36c8..e5f3cf08 100644 --- a/extractor/phrase_location.h +++ b/extractor/phrase_location.h @@ -6,6 +6,8 @@ using namespace std; +namespace extractor { + struct PhraseLocation { PhraseLocation(int sa_low = -1, int sa_high = -1); @@ -22,4 +24,6 @@ struct PhraseLocation { int num_subpatterns; }; +} // namespace extractor + #endif diff --git a/extractor/phrase_test.cc b/extractor/phrase_test.cc index 2b553b6f..c8176178 100644 --- a/extractor/phrase_test.cc +++ b/extractor/phrase_test.cc @@ -10,6 +10,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class PhraseTest : public Test { @@ -58,4 +59,5 @@ TEST_F(PhraseTest, TestGetSymbol) { } } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/precomputation.cc b/extractor/precomputation.cc index 189ac42c..8cc32ffd 100644 --- a/extractor/precomputation.cc +++ b/extractor/precomputation.cc @@ -8,6 +8,8 @@ using namespace std; +namespace extractor { + int Precomputation::NON_TERMINAL = -1; Precomputation::Precomputation( @@ -173,3 +175,5 @@ void Precomputation::WriteBinary(const fs::path& filepath) const { const Index& Precomputation::GetCollocations() const { return collocations; } + +} // namespace extractor diff --git a/extractor/precomputation.h b/extractor/precomputation.h index 3d44c2a6..dbd99c14 100644 --- a/extractor/precomputation.h +++ b/extractor/precomputation.h @@ -13,11 +13,13 @@ namespace fs = boost::filesystem; using namespace std; -class SuffixArray; +namespace extractor { typedef boost::hash > VectorHash; typedef unordered_map, vector, VectorHash> Index; +class SuffixArray; + class Precomputation { public: Precomputation( @@ -51,4 +53,6 @@ class Precomputation { Index collocations; }; +} // namespace extractor + #endif diff --git a/extractor/precomputation_test.cc b/extractor/precomputation_test.cc index 6b77b9c0..04e3850d 100644 --- a/extractor/precomputation_test.cc +++ b/extractor/precomputation_test.cc @@ -10,6 +10,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class PrecomputationTest : public Test { @@ -101,4 +102,6 @@ TEST_F(PrecomputationTest, TestCollocations) { EXPECT_EQ(0, collocations.count(key)); } -} // namespace +} // namespace +} // namespace extractor + diff --git a/extractor/rule.cc b/extractor/rule.cc index 9c7ac9b5..b6c7d783 100644 --- a/extractor/rule.cc +++ b/extractor/rule.cc @@ -1,5 +1,7 @@ #include "rule.h" +namespace extractor { + Rule::Rule(const Phrase& source_phrase, const Phrase& target_phrase, const vector& scores, @@ -8,3 +10,5 @@ Rule::Rule(const Phrase& source_phrase, target_phrase(target_phrase), scores(scores), alignment(alignment) {} + +} // namespace extractor diff --git a/extractor/rule.h b/extractor/rule.h index 64ff8794..b4d45fc1 100644 --- a/extractor/rule.h +++ b/extractor/rule.h @@ -7,6 +7,8 @@ using namespace std; +namespace extractor { + struct Rule { Rule(const Phrase& source_phrase, const Phrase& target_phrase, const vector& scores, const vector >& alignment); @@ -17,4 +19,6 @@ struct Rule { vector > alignment; }; +} // namespace extractor + #endif diff --git a/extractor/rule_extractor.cc b/extractor/rule_extractor.cc index 92343241..b9286472 100644 --- a/extractor/rule_extractor.cc +++ b/extractor/rule_extractor.cc @@ -14,6 +14,8 @@ using namespace std; +namespace extractor { + RuleExtractor::RuleExtractor( shared_ptr source_data_array, shared_ptr target_data_array, @@ -106,7 +108,7 @@ vector RuleExtractor::ExtractRules(const Phrase& phrase, } } - FeatureContext context(source_phrase, target_phrase, + features::FeatureContext context(source_phrase, target_phrase, source_phrase_counter[source_phrase], num_locations, num_samples); vector scores = scorer->Score(context); rules.push_back(Rule(source_phrase, target_phrase, scores, @@ -313,3 +315,5 @@ void RuleExtractor::AddNonterminalExtremities( AddExtracts(extracts, new_source_phrase, source_indexes, target_gaps, target_low, target_x_low, target_x_high, sentence_id); } + +} // namespace extractor diff --git a/extractor/rule_extractor.h b/extractor/rule_extractor.h index a087dc6d..8b6daeea 100644 --- a/extractor/rule_extractor.h +++ b/extractor/rule_extractor.h @@ -9,6 +9,10 @@ using namespace std; +namespace extractor { + +typedef vector > PhraseAlignment; + class Alignment; class DataArray; class PhraseBuilder; @@ -18,8 +22,6 @@ class RuleExtractorHelper; class Scorer; class TargetPhraseExtractor; -typedef vector > PhraseAlignment; - struct Extract { Extract(const Phrase& source_phrase, const Phrase& target_phrase, double pairs_count, const PhraseAlignment& alignment) : @@ -101,4 +103,6 @@ class RuleExtractor { bool require_tight_phrases; }; +} // namespace extractor + #endif diff --git a/extractor/rule_extractor_helper.cc b/extractor/rule_extractor_helper.cc index ed6ae3a1..553b56d4 100644 --- a/extractor/rule_extractor_helper.cc +++ b/extractor/rule_extractor_helper.cc @@ -3,6 +3,8 @@ #include "data_array.h" #include "alignment.h" +namespace extractor { + RuleExtractorHelper::RuleExtractorHelper( shared_ptr source_data_array, shared_ptr target_data_array, @@ -354,3 +356,5 @@ unordered_map RuleExtractorHelper::GetSourceIndexes( } return source_indexes; } + +} // namespace extractor diff --git a/extractor/rule_extractor_helper.h b/extractor/rule_extractor_helper.h index 3478bfc8..95274df6 100644 --- a/extractor/rule_extractor_helper.h +++ b/extractor/rule_extractor_helper.h @@ -7,6 +7,8 @@ using namespace std; +namespace extractor { + class Alignment; class DataArray; @@ -79,4 +81,6 @@ class RuleExtractorHelper { bool require_tight_phrases; }; +} // namespace extractor + #endif diff --git a/extractor/rule_extractor_helper_test.cc b/extractor/rule_extractor_helper_test.cc index 29213312..ec0635b1 100644 --- a/extractor/rule_extractor_helper_test.cc +++ b/extractor/rule_extractor_helper_test.cc @@ -9,6 +9,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class RuleExtractorHelperTest : public Test { @@ -619,4 +620,5 @@ TEST_F(RuleExtractorHelperTest, TestGetGapIntegrityChecksFailed) { met_constraints)); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/rule_extractor_test.cc b/extractor/rule_extractor_test.cc index 0be44d4d..1b543fc9 100644 --- a/extractor/rule_extractor_test.cc +++ b/extractor/rule_extractor_test.cc @@ -17,6 +17,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class RuleExtractorTest : public Test { @@ -163,4 +164,5 @@ TEST_F(RuleExtractorTest, TestExtractRulesAddExtremities) { EXPECT_EQ(4, rules.size()); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/rule_factory.cc b/extractor/rule_factory.cc index 4908dac0..51f85c30 100644 --- a/extractor/rule_factory.cc +++ b/extractor/rule_factory.cc @@ -9,6 +9,7 @@ #include "fast_intersector.h" #include "matchings_finder.h" #include "phrase.h" +#include "phrase_builder.h" #include "rule.h" #include "rule_extractor.h" #include "sampler.h" @@ -20,6 +21,8 @@ using namespace std; using namespace chrono; +namespace extractor { + typedef high_resolution_clock Clock; struct State { @@ -282,3 +285,5 @@ vector HieroCachingRuleFactory::ExtendState( return new_states; } + +} // namespace extractor diff --git a/extractor/rule_factory.h b/extractor/rule_factory.h index 2d1c7f5a..0de04e40 100644 --- a/extractor/rule_factory.h +++ b/extractor/rule_factory.h @@ -5,15 +5,17 @@ #include #include "matchings_trie.h" -#include "phrase_builder.h" using namespace std; +namespace extractor { + class Alignment; class DataArray; +class FastIntersector; class Grammar; class MatchingsFinder; -class FastIntersector; +class PhraseBuilder; class Precomputation; class Rule; class RuleExtractor; @@ -92,4 +94,6 @@ class HieroCachingRuleFactory { int max_rule_symbols; }; +} // namespace extractor + #endif diff --git a/extractor/rule_factory_test.cc b/extractor/rule_factory_test.cc index fc709461..2129dfa0 100644 --- a/extractor/rule_factory_test.cc +++ b/extractor/rule_factory_test.cc @@ -18,6 +18,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class RuleFactoryTest : public Test { @@ -98,4 +99,5 @@ TEST_F(RuleFactoryTest, TestGetGrammarRepeatingWords) { EXPECT_EQ(28, grammar.GetRules().size()); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/run_extractor.cc b/extractor/run_extractor.cc index 5255737d..c701c8d0 100644 --- a/extractor/run_extractor.cc +++ b/extractor/run_extractor.cc @@ -1,6 +1,7 @@ #include #include #include +#include #include #include @@ -30,6 +31,8 @@ namespace fs = boost::filesystem; namespace po = boost::program_options; using namespace std; +using namespace extractor; +using namespace features; int main(int argc, char** argv) { // TODO(pauldb): Also take arguments from config file. @@ -146,13 +149,13 @@ int main(int argc, char** argv) { Clock::time_point extraction_start_time = Clock::now(); vector > features = { - make_shared(), - make_shared(), - make_shared(), - make_shared(table), - make_shared(table), - make_shared(), - make_shared() +// make_shared(), +// make_shared(), +// make_shared(), +// make_shared(table), +// make_shared(table), +// make_shared(), +// make_shared() }; shared_ptr scorer = make_shared(features); diff --git a/extractor/sampler.cc b/extractor/sampler.cc index 5067ca8a..d128913f 100644 --- a/extractor/sampler.cc +++ b/extractor/sampler.cc @@ -3,6 +3,8 @@ #include "phrase_location.h" #include "suffix_array.h" +namespace extractor { + Sampler::Sampler(shared_ptr suffix_array, int max_samples) : suffix_array(suffix_array), max_samples(max_samples) {} @@ -39,3 +41,5 @@ int Sampler::Round(double x) const { // TODO(pauldb): Remove EPS. return x + 0.5 + 1e-8; } + +} // namespace extractor diff --git a/extractor/sampler.h b/extractor/sampler.h index 9cf321fb..cda28b10 100644 --- a/extractor/sampler.h +++ b/extractor/sampler.h @@ -5,6 +5,8 @@ using namespace std; +namespace extractor { + class PhraseLocation; class SuffixArray; @@ -26,4 +28,6 @@ class Sampler { int max_samples; }; +} // namespace extractor + #endif diff --git a/extractor/sampler_test.cc b/extractor/sampler_test.cc index 4f91965b..e9abebfa 100644 --- a/extractor/sampler_test.cc +++ b/extractor/sampler_test.cc @@ -9,6 +9,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class SamplerTest : public Test { @@ -69,4 +70,5 @@ TEST_F(SamplerTest, TestSubstringsSample) { EXPECT_EQ(PhraseLocation(expected_locations, 2), sampler->Sample(location)); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/scorer.cc b/extractor/scorer.cc index f28b3181..d3ebf1c9 100644 --- a/extractor/scorer.cc +++ b/extractor/scorer.cc @@ -2,14 +2,16 @@ #include "features/feature.h" -Scorer::Scorer(const vector >& features) : +namespace extractor { + +Scorer::Scorer(const vector >& features) : features(features) {} Scorer::Scorer() {} Scorer::~Scorer() {} -vector Scorer::Score(const FeatureContext& context) const { +vector Scorer::Score(const features::FeatureContext& context) const { vector scores; for (auto feature: features) { scores.push_back(feature->Score(context)); @@ -24,3 +26,5 @@ vector Scorer::GetFeatureNames() const { } return feature_names; } + +} // namespace extractor diff --git a/extractor/scorer.h b/extractor/scorer.h index ba71a6ee..c31db0ca 100644 --- a/extractor/scorer.h +++ b/extractor/scorer.h @@ -7,16 +7,20 @@ using namespace std; -class Feature; -class FeatureContext; +namespace extractor { + +namespace features { + class Feature; + class FeatureContext; +} // namespace features class Scorer { public: - Scorer(const vector >& features); + Scorer(const vector >& features); virtual ~Scorer(); - virtual vector Score(const FeatureContext& context) const; + virtual vector Score(const features::FeatureContext& context) const; virtual vector GetFeatureNames() const; @@ -24,7 +28,9 @@ class Scorer { Scorer(); private: - vector > features; + vector > features; }; +} // namespace extractor + #endif diff --git a/extractor/scorer_test.cc b/extractor/scorer_test.cc index 56a85762..3a09c9cc 100644 --- a/extractor/scorer_test.cc +++ b/extractor/scorer_test.cc @@ -10,32 +10,33 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class ScorerTest : public Test { protected: virtual void SetUp() { - feature1 = make_shared(); + feature1 = make_shared(); EXPECT_CALL(*feature1, Score(_)).WillRepeatedly(Return(0.5)); EXPECT_CALL(*feature1, GetName()).WillRepeatedly(Return("f1")); - feature2 = make_shared(); + feature2 = make_shared(); EXPECT_CALL(*feature2, Score(_)).WillRepeatedly(Return(-1.3)); EXPECT_CALL(*feature2, GetName()).WillRepeatedly(Return("f2")); - vector > features = {feature1, feature2}; + vector > features = {feature1, feature2}; scorer = make_shared(features); } - shared_ptr feature1; - shared_ptr feature2; + shared_ptr feature1; + shared_ptr feature2; shared_ptr scorer; }; TEST_F(ScorerTest, TestScore) { vector expected_scores = {0.5, -1.3}; Phrase phrase; - FeatureContext context(phrase, phrase, 0.3, 2, 11); + features::FeatureContext context(phrase, phrase, 0.3, 2, 11); EXPECT_EQ(expected_scores, scorer->Score(context)); } @@ -44,4 +45,5 @@ TEST_F(ScorerTest, TestGetNames) { EXPECT_EQ(expected_names, scorer->GetFeatureNames()); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/suffix_array.cc b/extractor/suffix_array.cc index ab8a0913..9988b1a2 100644 --- a/extractor/suffix_array.cc +++ b/extractor/suffix_array.cc @@ -13,6 +13,8 @@ namespace fs = boost::filesystem; using namespace std; using namespace chrono; +namespace extractor { + SuffixArray::SuffixArray(shared_ptr data_array) : data_array(data_array) { BuildSuffixArray(); @@ -227,3 +229,5 @@ int SuffixArray::LookupRangeStart(int low, int high, int word_id, } return result; } + +} // namespace extractor diff --git a/extractor/suffix_array.h b/extractor/suffix_array.h index 79a22694..7a4f1110 100644 --- a/extractor/suffix_array.h +++ b/extractor/suffix_array.h @@ -10,6 +10,8 @@ namespace fs = boost::filesystem; using namespace std; +namespace extractor { + class DataArray; class PhraseLocation; @@ -51,4 +53,6 @@ class SuffixArray { vector word_start; }; +} // namespace extractor + #endif diff --git a/extractor/suffix_array_test.cc b/extractor/suffix_array_test.cc index 60295567..8431a16e 100644 --- a/extractor/suffix_array_test.cc +++ b/extractor/suffix_array_test.cc @@ -9,6 +9,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class SuffixArrayTest : public Test { @@ -73,4 +74,5 @@ TEST_F(SuffixArrayTest, TestLookup) { EXPECT_EQ(PhraseLocation(11, 11), suffix_array->Lookup(11, 13, "word5", 1)); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/target_phrase_extractor.cc b/extractor/target_phrase_extractor.cc index ac583953..9f8bc6e2 100644 --- a/extractor/target_phrase_extractor.cc +++ b/extractor/target_phrase_extractor.cc @@ -11,6 +11,8 @@ using namespace std; +namespace extractor { + TargetPhraseExtractor::TargetPhraseExtractor( shared_ptr target_data_array, shared_ptr alignment, @@ -142,3 +144,5 @@ void TargetPhraseExtractor::GeneratePhrases( ++subpatterns[index]; } } + +} // namespace extractor diff --git a/extractor/target_phrase_extractor.h b/extractor/target_phrase_extractor.h index 134f24cc..a4b54145 100644 --- a/extractor/target_phrase_extractor.h +++ b/extractor/target_phrase_extractor.h @@ -7,6 +7,10 @@ using namespace std; +namespace extractor { + +typedef vector > PhraseAlignment; + class Alignment; class DataArray; class Phrase; @@ -14,8 +18,6 @@ class PhraseBuilder; class RuleExtractorHelper; class Vocabulary; -typedef vector > PhraseAlignment; - class TargetPhraseExtractor { public: TargetPhraseExtractor(shared_ptr target_data_array, @@ -53,4 +55,6 @@ class TargetPhraseExtractor { bool require_tight_phrases; }; +} // namespace extractor + #endif diff --git a/extractor/target_phrase_extractor_test.cc b/extractor/target_phrase_extractor_test.cc index 7394f4d9..51c753ee 100644 --- a/extractor/target_phrase_extractor_test.cc +++ b/extractor/target_phrase_extractor_test.cc @@ -14,6 +14,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { class TargetPhraseExtractorTest : public Test { @@ -113,4 +114,5 @@ TEST_F(TargetPhraseExtractorTest, TestExtractPhrasesTightPhrasesFalse) { // look like. } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/time_util.cc b/extractor/time_util.cc index 88395f77..e46a0c3d 100644 --- a/extractor/time_util.cc +++ b/extractor/time_util.cc @@ -1,6 +1,10 @@ #include "time_util.h" +namespace extractor { + double GetDuration(const Clock::time_point& start_time, const Clock::time_point& stop_time) { return duration_cast(stop_time - start_time).count() / 1000.0; } + +} // namespace extractor diff --git a/extractor/time_util.h b/extractor/time_util.h index 6f7eda70..45f79199 100644 --- a/extractor/time_util.h +++ b/extractor/time_util.h @@ -6,9 +6,13 @@ using namespace std; using namespace chrono; +namespace extractor { + typedef high_resolution_clock Clock; double GetDuration(const Clock::time_point& start_time, const Clock::time_point& stop_time); +} // namespace extractor + #endif diff --git a/extractor/translation_table.cc b/extractor/translation_table.cc index a48c0657..1852a357 100644 --- a/extractor/translation_table.cc +++ b/extractor/translation_table.cc @@ -10,6 +10,8 @@ using namespace std; +namespace extractor { + TranslationTable::TranslationTable(shared_ptr source_data_array, shared_ptr target_data_array, shared_ptr alignment) : @@ -115,3 +117,5 @@ void TranslationTable::WriteBinary(const fs::path& filepath) const { fwrite(&entry.second, sizeof(entry.second), 1, file); } } + +} // namespace extractor diff --git a/extractor/translation_table.h b/extractor/translation_table.h index 157ad3af..a7be26f5 100644 --- a/extractor/translation_table.h +++ b/extractor/translation_table.h @@ -11,11 +11,13 @@ using namespace std; namespace fs = boost::filesystem; -class Alignment; -class DataArray; +namespace extractor { typedef boost::hash > PairHash; +class Alignment; +class DataArray; + class TranslationTable { public: TranslationTable( @@ -50,4 +52,6 @@ class TranslationTable { translation_probabilities; }; +} // namespace extractor + #endif diff --git a/extractor/translation_table_test.cc b/extractor/translation_table_test.cc index c99f3f93..051b5715 100644 --- a/extractor/translation_table_test.cc +++ b/extractor/translation_table_test.cc @@ -11,6 +11,7 @@ using namespace std; using namespace ::testing; +namespace extractor { namespace { TEST(TranslationTableTest, TestScores) { @@ -79,4 +80,5 @@ TEST(TranslationTableTest, TestScores) { EXPECT_EQ(-1, table->GetSourceGivenTargetScore("c", "d")); } -} // namespace +} // namespace +} // namespace extractor diff --git a/extractor/vocabulary.cc b/extractor/vocabulary.cc index b68d76a9..57f564d9 100644 --- a/extractor/vocabulary.cc +++ b/extractor/vocabulary.cc @@ -1,5 +1,7 @@ #include "vocabulary.h" +namespace extractor { + Vocabulary::~Vocabulary() {} int Vocabulary::GetTerminalIndex(const string& word) { @@ -29,3 +31,4 @@ int Vocabulary::Size() { return words.size(); } +} // namespace extractor diff --git a/extractor/vocabulary.h b/extractor/vocabulary.h index ff3e7a63..dcc2a8fa 100644 --- a/extractor/vocabulary.h +++ b/extractor/vocabulary.h @@ -7,6 +7,8 @@ using namespace std; +namespace extractor { + class Vocabulary { public: virtual ~Vocabulary(); @@ -26,4 +28,6 @@ class Vocabulary { vector words; }; +} // namespace extractor + #endif -- cgit v1.2.3 From bbcd1a02103fa4d9f4dcdc605d438c13e0dc7085 Mon Sep 17 00:00:00 2001 From: Paul Baltescu Date: Wed, 6 Mar 2013 17:13:13 +0000 Subject: Fix broken test & includes. --- extractor/features/feature.h | 3 +-- extractor/features/max_lex_source_given_target.cc | 4 ++-- .../features/max_lex_source_given_target_test.cc | 8 ++++---- extractor/features/max_lex_target_given_source.cc | 4 ++-- .../features/max_lex_target_given_source_test.cc | 8 ++++---- extractor/mocks/mock_alignment.h | 2 +- extractor/mocks/mock_data_array.h | 2 +- extractor/mocks/mock_fast_intersector.h | 6 +++--- extractor/mocks/mock_feature.h | 2 +- extractor/mocks/mock_matchings_finder.h | 4 ++-- extractor/mocks/mock_precomputation.h | 2 +- extractor/mocks/mock_rule_extractor.h | 8 ++++---- extractor/mocks/mock_rule_extractor_helper.h | 2 +- extractor/mocks/mock_rule_factory.h | 4 ++-- extractor/mocks/mock_sampler.h | 4 ++-- extractor/mocks/mock_scorer.h | 4 ++-- extractor/mocks/mock_suffix_array.h | 6 +++--- extractor/mocks/mock_target_phrase_extractor.h | 2 +- extractor/mocks/mock_translation_table.h | 2 +- extractor/mocks/mock_vocabulary.h | 2 +- extractor/precomputation_test.cc | 19 +++++++++---------- 21 files changed, 48 insertions(+), 50 deletions(-) (limited to 'extractor/precomputation_test.cc') diff --git a/extractor/features/feature.h b/extractor/features/feature.h index de2827bc..6693ccbf 100644 --- a/extractor/features/feature.h +++ b/extractor/features/feature.h @@ -3,8 +3,7 @@ #include -//TODO(pauldb): include headers nicely. -#include "../phrase.h" +#include "phrase.h" using namespace std; diff --git a/extractor/features/max_lex_source_given_target.cc b/extractor/features/max_lex_source_given_target.cc index 3ffe598c..65d0ec68 100644 --- a/extractor/features/max_lex_source_given_target.cc +++ b/extractor/features/max_lex_source_given_target.cc @@ -2,8 +2,8 @@ #include -#include "../data_array.h" -#include "../translation_table.h" +#include "data_array.h" +#include "translation_table.h" namespace extractor { namespace features { diff --git a/extractor/features/max_lex_source_given_target_test.cc b/extractor/features/max_lex_source_given_target_test.cc index c1edb483..7f6aae41 100644 --- a/extractor/features/max_lex_source_given_target_test.cc +++ b/extractor/features/max_lex_source_given_target_test.cc @@ -4,10 +4,10 @@ #include #include -#include "../mocks/mock_translation_table.h" -#include "../mocks/mock_vocabulary.h" -#include "../data_array.h" -#include "../phrase_builder.h" +#include "data_array.h" +#include "mocks/mock_translation_table.h" +#include "mocks/mock_vocabulary.h" +#include "phrase_builder.h" #include "max_lex_source_given_target.h" using namespace std; diff --git a/extractor/features/max_lex_target_given_source.cc b/extractor/features/max_lex_target_given_source.cc index 30140d80..33783054 100644 --- a/extractor/features/max_lex_target_given_source.cc +++ b/extractor/features/max_lex_target_given_source.cc @@ -2,8 +2,8 @@ #include -#include "../data_array.h" -#include "../translation_table.h" +#include "data_array.h" +#include "translation_table.h" namespace extractor { namespace features { diff --git a/extractor/features/max_lex_target_given_source_test.cc b/extractor/features/max_lex_target_given_source_test.cc index 9ceb13e5..6d0efd9c 100644 --- a/extractor/features/max_lex_target_given_source_test.cc +++ b/extractor/features/max_lex_target_given_source_test.cc @@ -4,10 +4,10 @@ #include #include -#include "../mocks/mock_translation_table.h" -#include "../mocks/mock_vocabulary.h" -#include "../data_array.h" -#include "../phrase_builder.h" +#include "data_array.h" +#include "mocks/mock_translation_table.h" +#include "mocks/mock_vocabulary.h" +#include "phrase_builder.h" #include "max_lex_target_given_source.h" using namespace std; diff --git a/extractor/mocks/mock_alignment.h b/extractor/mocks/mock_alignment.h index 3d745e9d..299c3d1c 100644 --- a/extractor/mocks/mock_alignment.h +++ b/extractor/mocks/mock_alignment.h @@ -1,6 +1,6 @@ #include -#include "../alignment.h" +#include "alignment.h" namespace extractor { diff --git a/extractor/mocks/mock_data_array.h b/extractor/mocks/mock_data_array.h index cf9f3671..6f85abb4 100644 --- a/extractor/mocks/mock_data_array.h +++ b/extractor/mocks/mock_data_array.h @@ -1,6 +1,6 @@ #include -#include "../data_array.h" +#include "data_array.h" namespace extractor { diff --git a/extractor/mocks/mock_fast_intersector.h b/extractor/mocks/mock_fast_intersector.h index 665add65..f0b628d7 100644 --- a/extractor/mocks/mock_fast_intersector.h +++ b/extractor/mocks/mock_fast_intersector.h @@ -1,8 +1,8 @@ #include -#include "../fast_intersector.h" -#include "../phrase.h" -#include "../phrase_location.h" +#include "fast_intersector.h" +#include "phrase.h" +#include "phrase_location.h" namespace extractor { diff --git a/extractor/mocks/mock_feature.h b/extractor/mocks/mock_feature.h index 19ba4de9..0b0f0ead 100644 --- a/extractor/mocks/mock_feature.h +++ b/extractor/mocks/mock_feature.h @@ -1,6 +1,6 @@ #include -#include "../features/feature.h" +#include "features/feature.h" namespace extractor { namespace features { diff --git a/extractor/mocks/mock_matchings_finder.h b/extractor/mocks/mock_matchings_finder.h index ffbb06c7..827526fd 100644 --- a/extractor/mocks/mock_matchings_finder.h +++ b/extractor/mocks/mock_matchings_finder.h @@ -1,7 +1,7 @@ #include -#include "../matchings_finder.h" -#include "../phrase_location.h" +#include "matchings_finder.h" +#include "phrase_location.h" namespace extractor { diff --git a/extractor/mocks/mock_precomputation.h b/extractor/mocks/mock_precomputation.h index 64934b94..8753343e 100644 --- a/extractor/mocks/mock_precomputation.h +++ b/extractor/mocks/mock_precomputation.h @@ -1,6 +1,6 @@ #include -#include "../precomputation.h" +#include "precomputation.h" namespace extractor { diff --git a/extractor/mocks/mock_rule_extractor.h b/extractor/mocks/mock_rule_extractor.h index 28b644b0..aad11651 100644 --- a/extractor/mocks/mock_rule_extractor.h +++ b/extractor/mocks/mock_rule_extractor.h @@ -1,9 +1,9 @@ #include -#include "../phrase.h" -#include "../phrase_builder.h" -#include "../rule.h" -#include "../rule_extractor.h" +#include "phrase.h" +#include "phrase_builder.h" +#include "rule.h" +#include "rule_extractor.h" namespace extractor { diff --git a/extractor/mocks/mock_rule_extractor_helper.h b/extractor/mocks/mock_rule_extractor_helper.h index 3b0ac0f5..cf196ab5 100644 --- a/extractor/mocks/mock_rule_extractor_helper.h +++ b/extractor/mocks/mock_rule_extractor_helper.h @@ -2,7 +2,7 @@ #include -#include "../rule_extractor_helper.h" +#include "rule_extractor_helper.h" using namespace std; diff --git a/extractor/mocks/mock_rule_factory.h b/extractor/mocks/mock_rule_factory.h index 11cb9ab5..7389b396 100644 --- a/extractor/mocks/mock_rule_factory.h +++ b/extractor/mocks/mock_rule_factory.h @@ -1,7 +1,7 @@ #include -#include "../grammar.h" -#include "../rule_factory.h" +#include "grammar.h" +#include "rule_factory.h" namespace extractor { diff --git a/extractor/mocks/mock_sampler.h b/extractor/mocks/mock_sampler.h index 7022f7b3..75c43c27 100644 --- a/extractor/mocks/mock_sampler.h +++ b/extractor/mocks/mock_sampler.h @@ -1,7 +1,7 @@ #include -#include "../phrase_location.h" -#include "../sampler.h" +#include "phrase_location.h" +#include "sampler.h" namespace extractor { diff --git a/extractor/mocks/mock_scorer.h b/extractor/mocks/mock_scorer.h index 4d593ddf..cc0c444d 100644 --- a/extractor/mocks/mock_scorer.h +++ b/extractor/mocks/mock_scorer.h @@ -1,7 +1,7 @@ #include -#include "../scorer.h" -#include "../features/feature.h" +#include "scorer.h" +#include "features/feature.h" namespace extractor { diff --git a/extractor/mocks/mock_suffix_array.h b/extractor/mocks/mock_suffix_array.h index 6886232a..7018acc7 100644 --- a/extractor/mocks/mock_suffix_array.h +++ b/extractor/mocks/mock_suffix_array.h @@ -3,9 +3,9 @@ #include #include -#include "../data_array.h" -#include "../phrase_location.h" -#include "../suffix_array.h" +#include "data_array.h" +#include "phrase_location.h" +#include "suffix_array.h" using namespace std; diff --git a/extractor/mocks/mock_target_phrase_extractor.h b/extractor/mocks/mock_target_phrase_extractor.h index e5e9aeab..6aad853c 100644 --- a/extractor/mocks/mock_target_phrase_extractor.h +++ b/extractor/mocks/mock_target_phrase_extractor.h @@ -1,6 +1,6 @@ #include -#include "../target_phrase_extractor.h" +#include "target_phrase_extractor.h" namespace extractor { diff --git a/extractor/mocks/mock_translation_table.h b/extractor/mocks/mock_translation_table.h index 358c854f..307e4282 100644 --- a/extractor/mocks/mock_translation_table.h +++ b/extractor/mocks/mock_translation_table.h @@ -1,6 +1,6 @@ #include -#include "../translation_table.h" +#include "translation_table.h" namespace extractor { diff --git a/extractor/mocks/mock_vocabulary.h b/extractor/mocks/mock_vocabulary.h index 802c29b4..042c9ce2 100644 --- a/extractor/mocks/mock_vocabulary.h +++ b/extractor/mocks/mock_vocabulary.h @@ -1,6 +1,6 @@ #include -#include "../vocabulary.h" +#include "vocabulary.h" namespace extractor { diff --git a/extractor/precomputation_test.cc b/extractor/precomputation_test.cc index 04e3850d..363febb7 100644 --- a/extractor/precomputation_test.cc +++ b/extractor/precomputation_test.cc @@ -40,7 +40,6 @@ TEST_F(PrecomputationTest, TestCollocations) { Precomputation precomputation(suffix_array, 3, 3, 10, 5, 1, 4, 2); Index collocations = precomputation.GetCollocations(); - EXPECT_EQ(-1, precomputation.NON_TERMINAL); vector key = {2, 3, -1, 2}; vector expected_value = {1, 5, 1, 8, 5, 8, 5, 11, 8, 11}; EXPECT_EQ(expected_value, collocations[key]); @@ -69,33 +68,33 @@ TEST_F(PrecomputationTest, TestCollocations) { expected_value = {1, 6, 1, 9, 5, 9}; EXPECT_EQ(expected_value, collocations[key]); - key = {2, -1, 2, -1, 2}; + key = {2, -1, 2, -2, 2}; expected_value = {1, 5, 8, 5, 8, 11}; EXPECT_EQ(expected_value, collocations[key]); - key = {2, -1, 2, -1, 3}; + key = {2, -1, 2, -2, 3}; expected_value = {1, 5, 9}; EXPECT_EQ(expected_value, collocations[key]); - key = {2, -1, 3, -1, 2}; + key = {2, -1, 3, -2, 2}; expected_value = {1, 6, 8, 5, 9, 11}; EXPECT_EQ(expected_value, collocations[key]); - key = {2, -1, 3, -1, 3}; + key = {2, -1, 3, -2, 3}; expected_value = {1, 6, 9}; EXPECT_EQ(expected_value, collocations[key]); - key = {3, -1, 2, -1, 2}; + key = {3, -1, 2, -2, 2}; expected_value = {2, 5, 8, 2, 5, 11, 2, 8, 11, 6, 8, 11}; EXPECT_EQ(expected_value, collocations[key]); - key = {3, -1, 2, -1, 3}; + key = {3, -1, 2, -2, 3}; expected_value = {2, 5, 9}; EXPECT_EQ(expected_value, collocations[key]); - key = {3, -1, 3, -1, 2}; + key = {3, -1, 3, -2, 2}; expected_value = {2, 6, 8, 2, 6, 11, 2, 9, 11, 6, 9, 11}; EXPECT_EQ(expected_value, collocations[key]); - key = {3, -1, 3, -1, 3}; + key = {3, -1, 3, -2, 3}; expected_value = {2, 6, 9}; EXPECT_EQ(expected_value, collocations[key]); // Exceeds max_rule_symbols. - key = {2, -1, 2, -1, 2, 3}; + key = {2, -1, 2, -2, 2, 3}; EXPECT_EQ(0, collocations.count(key)); // Contains non frequent pattern. key = {2, -1, 5}; -- cgit v1.2.3