third_codes/cppjieba
1
0
Fork 0
mirror of https://github.com/yanyiwu/cppjieba.git synced 2025-07-18 00:00:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

[code style] uppercase function name

Browse Source
This commit is contained in:
yanyiwu 2015-10-29 12:39:10 +08:00
parent f17c2d10e2
commit 83cc67cb15
20 changed files with 98 additions and 98 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/DictTrie.hpp
View File

@ -127,8 +127,8 @@ class DictTrie {
const string& word,
double weight,
const string& tag) {
if (!TransCode::decode(word, node_info.word)) {
LogError("decode %s failed.", word.c_str());
if (!TransCode::Decode(word, node_info.word)) {
LogError("Decode %s failed.", word.c_str());
return false;
}
node_info.weight = weight;

2
src/FullSegment.hpp
View File

@ -36,7 +36,7 @@ class FullSegment: public SegmentBase {
range = pre_filter.Next();
Cut(range.begin, range.end, uwords);
}
TransCode::encode(uwords, words);
TransCode::Encode(uwords, words);
}
void Cut(Unicode::const_iterator begin,
Unicode::const_iterator end,

2
src/HMMModel.hpp
View File

@ -118,7 +118,7 @@ struct HMMModel {
LogError("emitProb illegal.");
return false;
}
if (!TransCode::decode(tmp2[0], unicode) || unicode.size() != 1) {
if (!TransCode::Decode(tmp2[0], unicode) || unicode.size() != 1) {
LogError("TransCode failed.");
return false;
}

8
src/HMMSegment.hpp
View File

@ -33,7 +33,7 @@ class HMMSegment: public SegmentBase {
range = pre_filter.Next();
Cut(range.begin, range.end, uwords);
}
TransCode::encode(uwords, words);
TransCode::Encode(uwords, words);
}
void Cut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res) const {
Unicode::const_iterator left = begin;
@ -41,7 +41,7 @@ class HMMSegment: public SegmentBase {
while (right != end) {
if (*right < 0x80) {
if (left != right) {
Cut(left, right, res);
InternalCut(left, right, res);
}
left = right;
do {
@ -62,7 +62,7 @@ class HMMSegment: public SegmentBase {
}
}
if (left != right) {
Cut(left, right, res);
InternalCut(left, right, res);
}
}
private:
@ -102,7 +102,7 @@ class HMMSegment: public SegmentBase {
}
return begin;
}
void Cut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res) const {
void InternalCut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res) const {
vector<size_t> status;
Viterbi(begin, end, status);

8
src/KeywordExtractor.hpp
View File

@ -31,9 +31,9 @@ class KeywordExtractor {
~KeywordExtractor() {
}
bool extract(const string& sentence, vector<string>& keywords, size_t topN) const {
bool Extract(const string& sentence, vector<string>& keywords, size_t topN) const {
vector<pair<string, double> > topWords;
if (!extract(sentence, topWords, topN)) {
if (!Extract(sentence, topWords, topN)) {
return false;
}
for (size_t i = 0; i < topWords.size(); i++) {
@ -42,7 +42,7 @@ class KeywordExtractor {
return true;
}
bool extract(const string& sentence, vector<pair<string, double> >& keywords, size_t topN) const {
bool Extract(const string& sentence, vector<pair<string, double> >& keywords, size_t topN) const {
vector<string> words;
segment_.Cut(sentence, words);
@ -122,7 +122,7 @@ class KeywordExtractor {
bool IsSingleWord(const string& str) const {
Unicode unicode;
TransCode::decode(str, unicode);
TransCode::Decode(str, unicode);
if (unicode.size() == 1)
return true;
return false;

4
src/LevelSegment.hpp
View File

@ -51,12 +51,12 @@ class LevelSegment: public SegmentBase{
vector<pair<string, size_t> >& words) const {
words.clear();
Unicode unicode;
TransCode::decode(sentence, unicode);
TransCode::Decode(sentence, unicode);
vector<pair<Unicode, size_t> > unicodeWords;
Cut(unicode.begin(), unicode.end(), unicodeWords);
words.resize(unicodeWords.size());
for (size_t i = 0; i < words.size(); i++) {
TransCode::encode(unicodeWords[i].first, words[i].first);
TransCode::Encode(unicodeWords[i].first, words[i].first);
words[i].second = unicodeWords[i].second;
}
}

2
src/MPSegment.hpp
View File

@ -38,7 +38,7 @@ class MPSegment: public SegmentBase {
range = pre_filter.Next();
Cut(range.begin, range.end, uwords, max_word_len);
}
TransCode::encode(uwords, words);
TransCode::Encode(uwords, words);
}
void Cut(Unicode::const_iterator begin,
Unicode::const_iterator end,

2
src/MixSegment.hpp
View File

@ -30,7 +30,7 @@ class MixSegment: public SegmentBase {
range = pre_filter.Next();
Cut(range.begin, range.end, uwords, hmm);
}
TransCode::encode(uwords, words);
TransCode::Encode(uwords, words);
}
void Cut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res, bool hmm) const {

6
src/PosTagger.hpp
View File

@ -25,7 +25,7 @@ class PosTagger {
~PosTagger() {
}
bool tag(const string& src, vector<pair<string, string> >& res) const {
bool Tag(const string& src, vector<pair<string, string> >& res) const {
vector<string> CutRes;
segment_.Cut(src, CutRes);
@ -34,8 +34,8 @@ class PosTagger {
const DictTrie * dict = segment_.GetDictTrie();
assert(dict != NULL);
for (vector<string>::iterator itr = CutRes.begin(); itr != CutRes.end(); ++itr) {
if (!TransCode::decode(*itr, unico)) {
LogError("decode failed.");
if (!TransCode::Decode(*itr, unico)) {
LogError("Decode failed.");
return false;
}
tmp = dict->Find(unico.begin(), unico.end());

2
src/PreFilter.hpp
View File

@ -26,7 +26,7 @@ class PreFilter {
PreFilter(const unordered_set<Rune>& symbols,
const string& sentence)
: symbols_(symbols) {
TransCode::decode(sentence, sentence_);
TransCode::Decode(sentence, sentence_);
cursor_ = sentence_.begin();
}
~PreFilter() {

2
src/QuerySegment.hpp
View File

@ -35,7 +35,7 @@ class QuerySegment: public SegmentBase {
range = pre_filter.Next();
Cut(range.begin, range.end, uwords, hmm);
}
TransCode::encode(uwords, words);
TransCode::Encode(uwords, words);
}
void Cut(Unicode::const_iterator begin, Unicode::const_iterator end, vector<Unicode>& res, bool hmm) const {
//use mix Cut first

24
src/TransCode.hpp
View File

@ -17,7 +17,7 @@ typedef uint16_t Rune;
typedef limonp::LocalVector<Rune> Unicode;
namespace TransCode {
inline bool decode(const string& str, Unicode& res) {
inline bool Decode(const string& str, Unicode& res) {
#ifdef CPPJIEBA_GBK
return gbkTrans(str, res);
#else
@ -25,7 +25,7 @@ inline bool decode(const string& str, Unicode& res) {
#endif
}
inline void encode(Unicode::const_iterator begin, Unicode::const_iterator end, string& res) {
inline void Encode(Unicode::const_iterator begin, Unicode::const_iterator end, string& res) {
#ifdef CPPJIEBA_GBK
gbkTrans(begin, end, res);
#else
@ -33,34 +33,34 @@ inline void encode(Unicode::const_iterator begin, Unicode::const_iterator end, s
#endif
}
inline void encode(const Unicode& uni, string& res) {
encode(uni.begin(), uni.end(), res);
inline void Encode(const Unicode& uni, string& res) {
Encode(uni.begin(), uni.end(), res);
}
// compiler is expected to optimized this function to avoid return value copy
inline string encode(Unicode::const_iterator begin, Unicode::const_iterator end) {
inline string Encode(Unicode::const_iterator begin, Unicode::const_iterator end) {
string res;
res.reserve(end - begin);
encode(begin, end, res);
Encode(begin, end, res);
return res;
}
inline string encode(const Unicode& unicode) {
return encode(unicode.begin(), unicode.end());
inline string Encode(const Unicode& unicode) {
return Encode(unicode.begin(), unicode.end());
}
// compiler is expected to optimized this function to avoid return value copy
inline Unicode decode(const string& str) {
inline Unicode Decode(const string& str) {
Unicode unicode;
unicode.reserve(str.size());
decode(str, unicode);
Decode(str, unicode);
return unicode;
}
inline void encode(const vector<Unicode>& input, vector<string>& output) {
inline void Encode(const vector<Unicode>& input, vector<string>& output) {
output.resize(input.size());
for (size_t i = 0; i < output.size(); i++) {
encode(input[i], output[i]);
Encode(input[i], output[i]);
}
}

4
test/demo.cpp
View File

@ -35,13 +35,13 @@ int main(int argc, char** argv) {
//cout << "[demo] TAGGING" << endl;
//vector<pair<string, string> > tagres;
//jieba.tag(s, tagres);
//jieba.Tag(s, tagres);
//cout << s << endl;
//cout << tagres << endl;;
//cout << "[demo] KEYWORD" << endl;
//vector<pair<string, double> > keywordres;
//jieba.extract(s, keywordres, 5);
//jieba.Extract(s, keywordres, 5);
//cout << s << endl;
//cout << keywordres << endl;

18
test/load_test.cpp
View File

@ -9,7 +9,7 @@
using namespace cppjieba;
void cut(size_t times = 50) {
void Cut(size_t times = 50) {
MixSegment seg("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
vector<string> res;
string doc;
@ -21,15 +21,15 @@ void cut(size_t times = 50) {
printf("process [%3.0lf %%]\r", 100.0*(i+1)/times);
fflush(stdout);
res.clear();
seg.cut(doc, res);
seg.Cut(doc, res);
}
printf("\n");
long endTime = clock();
ColorPrintln(GREEN, "cut: [%.3lf seconds]time consumed.", double(endTime - beginTime)/CLOCKS_PER_SEC);
ColorPrintln(GREEN, "Cut: [%.3lf seconds]time consumed.", double(endTime - beginTime)/CLOCKS_PER_SEC);
}
void extract(size_t times = 400) {
KeywordExtractor extractor("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
void Extract(size_t times = 400) {
KeywordExtractor Extractor("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
vector<string> words;
string doc;
ifstream ifs("../test/testdata/review.100");
@ -40,15 +40,15 @@ void extract(size_t times = 400) {
printf("process [%3.0lf %%]\r", 100.0*(i+1)/times);
fflush(stdout);
words.clear();
extractor.extract(doc, words, 5);
Extractor.Extract(doc, words, 5);
}
printf("\n");
long endTime = clock();
ColorPrintln(GREEN, "extract: [%.3lf seconds]time consumed.", double(endTime - beginTime)/CLOCKS_PER_SEC);
ColorPrintln(GREEN, "Extract: [%.3lf seconds]time consumed.", double(endTime - beginTime)/CLOCKS_PER_SEC);
}
int main(int argc, char ** argv) {
cut();
extract();
Cut();
Extract();
return EXIT_SUCCESS;
}

4
test/unittest/jieba_test.cpp
View File

@ -47,12 +47,12 @@ TEST(JiebaTest, Test1) {
ASSERT_EQ("[\"南京市:0\", \"长江大桥:0\", \"南京:1\", \"长江:1\", \"大桥:1\"]", result);
//vector<pair<string, string> > tagres;
//jieba.tag("iPhone6手机的最大特点是很容易弯曲。", tagres);
//jieba.Tag("iPhone6手机的最大特点是很容易弯曲。", tagres);
//result << tagres;
//ASSERT_EQ("[\"iPhone6:eng\", \"手机:n\", \"的:uj\", \"最大:a\", \"特点:n\", \"是:v\", \"很:zg\", \"容易:a\", \"弯曲:v\", \"。:x\"]", result);
//vector<pair<string, double> > keywordres;
//jieba.extract("我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。", keywordres, 5);
//jieba.Extract("我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。", keywordres, 5);
//result << keywordres;
//ASSERT_EQ(result, "[\"CEO:11.7392\", \"升职:10.8562\", \"加薪:10.6426\", \"手扶拖拉机:10.0089\", \"巅峰:9.49396\"]");
}

12
test/unittest/keyword_extractor_test.cpp
View File

@ -4,14 +4,14 @@
using namespace cppjieba;
TEST(KeywordExtractorTest, Test1) {
KeywordExtractor extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
KeywordExtractor Extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8");
{
string s("我是拖拉机学院手扶拖拉机专业的。不用多久，我就会升职加薪，当上CEO，走上人生巅峰。");
string res;
vector<pair<string, double> > wordweights;
size_t topN = 5;
extractor.extract(s, wordweights, topN);
Extractor.Extract(s, wordweights, topN);
res << wordweights;
ASSERT_EQ(res, "[\"CEO:11.7392\", \"升职:10.8562\", \"加薪:10.6426\", \"手扶拖拉机:10.0089\", \"巅峰:9.49396\"]");
}
@ -21,21 +21,21 @@ TEST(KeywordExtractorTest, Test1) {
string res;
vector<pair<string, double> > wordweights;
size_t topN = 5;
extractor.extract(s, wordweights, topN);
Extractor.Extract(s, wordweights, topN);
res << wordweights;
ASSERT_EQ(res, "[\"iPhone6:11.7392\", \"一部:6.47592\"]");
}
}
TEST(KeywordExtractorTest, Test2) {
KeywordExtractor extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8", "../test/testdata/userdict.utf8");
KeywordExtractor Extractor("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8", "../dict/idf.utf8", "../dict/stop_words.utf8", "../test/testdata/userdict.utf8");
{
string s("蓝翔优秀毕业生");
string res;
vector<pair<string, double> > wordweights;
size_t topN = 5;
extractor.extract(s, wordweights, topN);
Extractor.Extract(s, wordweights, topN);
res << wordweights;
ASSERT_EQ(res, "[\"蓝翔:11.7392\", \"毕业生:8.13549\", \"优秀:6.78347\"]");
}
@ -45,7 +45,7 @@ TEST(KeywordExtractorTest, Test2) {
string res;
vector<pair<string, double> > wordweights;
size_t topN = 5;
extractor.extract(s, wordweights, topN);
Extractor.Extract(s, wordweights, topN);
res << wordweights;
ASSERT_EQ(res, "[\"iPhone6:11.7392\", \"一部:6.47592\"]");
}

6
test/unittest/pos_tagger_test.cpp
View File

@ -16,7 +16,7 @@ TEST(PosTaggerTest, Test) {
PosTagger tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8");
{
vector<pair<string, string> > res;
tagger.tag(QUERY_TEST1, res);
tagger.Tag(QUERY_TEST1, res);
string s;
s << res;
ASSERT_TRUE(s == ANS_TEST1);
@ -26,14 +26,14 @@ TEST(PosTagger, TestUserDict) {
PosTagger tagger("../dict/jieba.dict.utf8", "../dict/hmm_model.utf8", "../test/testdata/userdict.utf8");
{
vector<pair<string, string> > res;
tagger.tag(QUERY_TEST2, res);
tagger.Tag(QUERY_TEST2, res);
string s;
s << res;
ASSERT_EQ(s, ANS_TEST2);
}
{
vector<pair<string, string> > res;
tagger.tag(QUERY_TEST3, res);
tagger.Tag(QUERY_TEST3, res);
string s;
s << res;
ASSERT_EQ(s, ANS_TEST3);

4
test/unittest/pre_filter_test.cpp
View File

@ -18,7 +18,7 @@ TEST(PreFilterTest, Test1) {
while (filter.HasNext()) {
PreFilter::Range range;
range = filter.Next();
words.push_back(TransCode::encode(range.begin, range.end));
words.push_back(TransCode::Encode(range.begin, range.end));
}
res = join(words.begin(), words.end(), "/");
ASSERT_EQ(res, expected);
@ -32,7 +32,7 @@ TEST(PreFilterTest, Test1) {
while (filter.HasNext()) {
PreFilter::Range range;
range = filter.Next();
words.push_back(TransCode::encode(range.begin, range.end));
words.push_back(TransCode::Encode(range.begin, range.end));
}
res = join(words.begin(), words.end(), "/");
for (size_t i = 0; i < words.size(); i++) {

60
test/unittest/segments_test.cpp
View File

@ -19,7 +19,7 @@ TEST(MixSegmentTest, Test1) {
{
sentence = "我来自北京邮电大学。。。学号123456，用AK47";
expected = "我/来自/北京邮电大学/。/。/。/学号/123456/，/用/AK47";
segment.cut(sentence, words);
segment.Cut(sentence, words);
actual = join(words.begin(), words.end(), "/");
ASSERT_EQ(actual, expected);
}
@ -27,7 +27,7 @@ TEST(MixSegmentTest, Test1) {
{
sentence = "B超 T恤";
expected = "B超/ /T恤";
segment.cut(sentence, words);
segment.Cut(sentence, words);
actual = join(words.begin(), words.end(), "/");
ASSERT_EQ(actual, expected);
}
@ -35,7 +35,7 @@ TEST(MixSegmentTest, Test1) {
{
sentence = "他来到了网易杭研大厦";
expected = "他/来到/了/网易/杭/研/大厦";
segment.cut(sentence, words, false);
segment.Cut(sentence, words, false);
actual = join(words.begin(), words.end(), "/");
ASSERT_EQ(actual, expected);
}
@ -43,7 +43,7 @@ TEST(MixSegmentTest, Test1) {
{
sentence = "他来到了网易杭研大厦";
expected = "他/来到/了/网易/杭研/大厦";
segment.cut(sentence, words);
segment.Cut(sentence, words);
actual = join(words.begin(), words.end(), "/");
ASSERT_EQ(actual, expected);
}
@ -53,7 +53,7 @@ TEST(MixSegmentTest, NoUserDict) {
MixSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8", "../dict/hmm_model.utf8");
const char* str = "令狐冲是云计算方面的专家";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string res;
ASSERT_EQ("[\"令狐冲\", \"是\", \"云\", \"计算\", \"方面\", \"的\", \"专家\"]", res << words);
@ -63,14 +63,14 @@ TEST(MixSegmentTest, UserDict) {
{
const char* str = "令狐冲是云计算方面的专家";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string res;
ASSERT_EQ("[\"令狐冲\", \"是\", \"云计算\", \"方面\", \"的\", \"专家\"]", res << words);
}
{
const char* str = "小明先就职于IBM,后在日本京都大学深造";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string res;
res << words;
ASSERT_EQ("[\"小明\", \"先\", \"就职\", \"于\", \"IBM\", \",\", \"后\", \"在\", \"日本\", \"京都大学\", \"深造\"]", res);
@ -78,7 +78,7 @@ TEST(MixSegmentTest, UserDict) {
{
const char* str = "IBM,3.14";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string res;
res << words;
ASSERT_EQ("[\"IBM\", \",\", \"3.14\"]", res);
@ -90,18 +90,18 @@ TEST(MixSegmentTest, TestUserDict) {
vector<string> words;
string res;
segment.cut("令狐冲是云计算方面的专家", words);
segment.Cut("令狐冲是云计算方面的专家", words);
ASSERT_EQ("[\"令狐冲\", \"是\", \"云计算\", \"方面\", \"的\", \"专家\"]", res << words);
segment.cut("小明先就职于IBM,后在日本京都大学深造", words);
segment.Cut("小明先就职于IBM,后在日本京都大学深造", words);
res << words;
ASSERT_EQ("[\"小明\", \"先\", \"就职\", \"于\", \"I\", \"B\", \"M\", \",\", \"后\", \"在\", \"日本\", \"京都大学\", \"深造\"]", res);
segment.cut("IBM,3.14", words);
segment.Cut("IBM,3.14", words);
res << words;
ASSERT_EQ("[\"I\", \"B\", \"M\", \",\", \"3.14\"]", res);
segment.cut("忽如一夜春风来，千树万树梨花开", words);
segment.Cut("忽如一夜春风来，千树万树梨花开", words);
res = limonp::join(words.begin(), words.end(), "/");
ASSERT_EQ("忽如一夜春风来/，/千树/万树/梨花/开", res);
}
@ -112,7 +112,7 @@ TEST(MixSegmentTest, TestMultiUserDict) {
vector<string> words;
string res;
segment.cut("忽如一夜春风来，千树万树梨花开", words);
segment.Cut("忽如一夜春风来，千树万树梨花开", words);
res = limonp::join(words.begin(), words.end(), "/");
ASSERT_EQ("忽如一夜春风来/，/千树万树梨花开", res);
}
@ -121,27 +121,27 @@ TEST(MPSegmentTest, Test1) {
MPSegment segment("../dict/jieba.dict.utf8");;
string s;
vector<string> words;
segment.cut("我来自北京邮电大学。", words);
segment.Cut("我来自北京邮电大学。", words);
ASSERT_EQ("[\"我\", \"来自\", \"北京邮电大学\", \"。\"]", s << words);
segment.cut("B超 T恤", words);
segment.Cut("B超 T恤", words);
ASSERT_EQ(s << words, "[\"B超\", \" \", \"T恤\"]");
segment.cut("南京市长江大桥", words);
segment.Cut("南京市长江大桥", words);
ASSERT_EQ("[\"南京市\", \"长江大桥\"]", s << words);
// MaxWordLen
segment.cut("南京市长江大桥", words, 3);
segment.Cut("南京市长江大桥", words, 3);
ASSERT_EQ("[\"南京市\", \"长江\", \"大桥\"]", s << words);
segment.cut("南京市长江大桥", words, 0);
segment.Cut("南京市长江大桥", words, 0);
ASSERT_EQ("[\"南\", \"京\", \"市\", \"长\", \"江\", \"大\", \"桥\"]", s << words);
segment.cut("湖南长沙市天心区", words);
segment.Cut("湖南长沙市天心区", words);
s = join(words.begin(), words.end(), "/");
ASSERT_EQ("湖南长沙市/天心区", s);
segment.cut("湖南长沙市天心区", words, 3);
segment.Cut("湖南长沙市天心区", words, 3);
s = join(words.begin(), words.end(), "/");
ASSERT_EQ("湖南/长沙市/天心区", s);
}
@ -164,7 +164,7 @@ TEST(MPSegmentTest, Test1) {
// res += line;
// res += '\n';
//
// segment.cut(line, words);
// segment.Cut(line, words);
// string s;
// s << words;
// res += s;
@ -182,7 +182,7 @@ TEST(HMMSegmentTest, Test1) {
const char* str = "我来自北京邮电大学。。。学号123456";
const char* res[] = {"我来", "自北京", "邮电大学", "。", "。", "。", "学号", "123456"};
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
ASSERT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}
@ -190,7 +190,7 @@ TEST(HMMSegmentTest, Test1) {
const char* str = "IBM,1.2,123";
const char* res[] = {"IBM", ",", "1.2", ",", "123"};
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
ASSERT_EQ(words, vector<string>(res, res + sizeof(res)/sizeof(res[0])));
}
}
@ -200,12 +200,12 @@ TEST(FullSegment, Test1) {
vector<string> words;
string s;
segment.cut("我来自北京邮电大学", words);
segment.Cut("我来自北京邮电大学", words);
s << words;
ASSERT_EQ(s, "[\"我\", \"来自\", \"北京\", \"北京邮电大学\", \"邮电\", \"电大\", \"大学\"]");
segment.cut("上市公司CEO", words);
segment.Cut("上市公司CEO", words);
s << words;
ASSERT_EQ(s, "[\"上市\", \"公司\", \"C\", \"E\", \"O\"]");
}
@ -215,7 +215,7 @@ TEST(QuerySegment, Test1) {
const char* str = "小明硕士毕业于中国科学院计算所，后在日本京都大学深造";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string s1, s2;
s1 << words;
@ -231,7 +231,7 @@ TEST(QuerySegment, Test2) {
const char* str = "小明硕士毕业于中国科学院计算所，后在日本京都大学深造";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string s1, s2;
s1 << words;
@ -243,7 +243,7 @@ TEST(QuerySegment, Test2) {
const char* str = "小明硕士毕业于中国科学院计算所iPhone6";
vector<string> words;
segment.cut(str, words);
segment.Cut(str, words);
string s1, s2;
s1 << words;
@ -257,10 +257,10 @@ TEST(LevelSegmentTest, Test0) {
string s;
LevelSegment segment("../test/testdata/extra_dict/jieba.dict.small.utf8");
vector<pair<string, size_t> > words;
segment.cut("南京市长江大桥", words);
segment.Cut("南京市长江大桥", words);
ASSERT_EQ("[\"南京市:0\", \"长江大桥:0\", \"南京:1\", \"长江:1\", \"大桥:1\"]", s << words);
vector<string> res;
segment.cut("南京市长江大桥", res);
segment.Cut("南京市长江大桥", res);
ASSERT_EQ("[\"南京市\", \"长江大桥\", \"南京\", \"长江\", \"大桥\"]", s << res);
}

22
test/unittest/trie_test.cpp
View File

@ -15,7 +15,7 @@ TEST(TrieTest, Empty) {
TEST(TrieTest, Construct) {
vector<Unicode> keys;
vector<const DictUnit*> values;
keys.push_back(TransCode::decode("你"));
keys.push_back(TransCode::Decode("你"));
values.push_back((const DictUnit*)(NULL));
Trie trie(keys, values);
}
@ -32,7 +32,7 @@ TEST(DictTrieTest, Test1) {
ASSERT_LT(trie.GetMinWeight() + 15.6479, 0.001);
string word("来到");
Unicode uni;
ASSERT_TRUE(TransCode::decode(word, uni));
ASSERT_TRUE(TransCode::Decode(word, uni));
DictUnit nodeInfo;
nodeInfo.word = uni;
nodeInfo.tag = "v";
@ -45,13 +45,13 @@ TEST(DictTrieTest, Test1) {
LocalVector<pair<size_t, const DictUnit*> > res;
const char * words[] = {"清", "清华", "清华大学"};
for (size_t i = 0; i < sizeof(words)/sizeof(words[0]); i++) {
ASSERT_TRUE(TransCode::decode(words[i], uni));
ASSERT_TRUE(TransCode::Decode(words[i], uni));
res.push_back(make_pair(uni.size() - 1, trie.Find(uni.begin(), uni.end())));
//resMap[uni.size() - 1] = trie.Find(uni.begin(), uni.end());
}
vector<pair<size_t, const DictUnit*> > vec;
vector<struct Dag> dags;
ASSERT_TRUE(TransCode::decode(word, uni));
ASSERT_TRUE(TransCode::Decode(word, uni));
trie.Find(uni.begin(), uni.end(), dags);
ASSERT_EQ(dags.size(), uni.size());
ASSERT_NE(dags.size(), 0u);
@ -65,7 +65,7 @@ TEST(DictTrieTest, UserDict) {
DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8");
string word = "云计算";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
const DictUnit * unit = trie.Find(unicode.begin(), unicode.end());
ASSERT_TRUE(unit);
string res ;
@ -77,7 +77,7 @@ TEST(DictTrieTest, UserDictWithMaxWeight) {
DictTrie trie(DICT_FILE, "../test/testdata/userdict.utf8", DictTrie::WordWeightMax);
string word = "云计算";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
const DictUnit * unit = trie.Find(unicode.begin(), unicode.end());
ASSERT_TRUE(unit);
string res ;
@ -91,7 +91,7 @@ TEST(DictTrieTest, Dag) {
{
string word = "清华大学";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
vector<struct Dag> res;
trie.Find(unicode.begin(), unicode.end(), res);
@ -105,7 +105,7 @@ TEST(DictTrieTest, Dag) {
{
string word = "北京邮电大学";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
vector<struct Dag> res;
trie.Find(unicode.begin(), unicode.end(), res);
@ -119,7 +119,7 @@ TEST(DictTrieTest, Dag) {
{
string word = "长江大桥";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
vector<struct Dag> res;
trie.Find(unicode.begin(), unicode.end(), res);
@ -133,7 +133,7 @@ TEST(DictTrieTest, Dag) {
{
string word = "长江大桥";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
vector<struct Dag> res;
trie.Find(unicode.begin(), unicode.end(), res, 3);
@ -147,7 +147,7 @@ TEST(DictTrieTest, Dag) {
{
string word = "长江大桥";
Unicode unicode;
ASSERT_TRUE(TransCode::decode(word, unicode));
ASSERT_TRUE(TransCode::Decode(word, unicode));
vector<struct Dag> res;
trie.Find(unicode.begin(), unicode.end(), res, 4);