add data example and config example

examples/Makefile

@@ -0,0 +1,40 @@
+all: cws pos par ner multi_cws
+
+cws: cws.cpp
+	g++ -o cws cws.cpp -I./ \
+		-I../include/ \
+		-I../thirdparty/boost/include \
+		-L../lib/ -lsegmentor -lboost_regex
+
+pos: pos.cpp
+	g++ -o pos pos.cpp -I./ \
+		-I../include/ \
+		-L../lib/ -lpostagger
+
+ner: ner.cpp
+	g++ -o ner ner.cpp -I./ \
+		-I../src/ner/ \
+		-L../lib/ -lner
+
+par: par.cpp
+	g++ -o par par.cpp -I./ \
+		-I../src/parser/ \
+		-L../lib -lparser
+
+multi_cws: multi_cws.cpp
+	g++ -o multi_cws multi_cws.cpp \
+		thirdparty/tinythreadpp/tinythread.cpp \
+		-I./ \
+		-I../include/ \
+		-I../thirdparty/boost/include/ \
+		-I./thirdparty/tinythreadpp/ \
+		-L../lib/ -lsegmentor -lboost_regex -lpthread
+
+.PHONY: clean
+
+clean:
+	rm cws
+	rm pos
+	rm ner
+	rm par
+	rm multi_cws

examples/cws.cpp

@@ -0,0 +1,40 @@
+#include <iostream>
+#include <string>
+#include "segment_dll.h"
+
+int main(int argc, char * argv[]) {
+    if (argc < 2) {
+        std::cerr << "cws [model path] [lexicon_file]" << std::endl;
+        return 1;
+    }
+
+    void * engine = 0;
+    if (argc == 2) {
+        engine = segmentor_create_segmentor(argv[1]);
+    } else if (argc == 3) {
+        engine = segmentor_create_segmentor(argv[1], argv[2]);
+    }
+
+    if (!engine) {
+        return -1;
+    }
+    std::vector<std::string> words;
+
+    const char * suite[2] = {
+        "What's wrong with you? 别灰心! http://t.cn/zQz0Rn",
+        "台北真的是天子骄子吗？",};
+
+    for (int i = 0; i < 2; ++ i) {
+        words.clear();
+        int len = segmentor_segment(engine, suite[i], words);
+        for (int i = 0; i < len; ++ i) {
+            std::cout << words[i];
+            if (i+1 == len) std::cout <<std::endl;
+            else std::cout<< "|";
+        }
+    }
+
+    segmentor_release_segmentor(engine);
+    return 0;
+}
+

examples/ner.cpp

@@ -0,0 +1,43 @@
+#include <iostream>
+#include <vector>
+
+#include "ner_dll.h"
+
+int main(int argc, char * argv[]) {
+    if (argc < 2) {
+        std::cerr << "usage: ./ner [model_path]" << std::endl;
+        return -1;
+    }
+
+    void * engine = ner_create_recognizer(argv[1]);
+    if (!engine) {
+        std::cerr << "failed to load model" << std::endl;
+        return -1;
+    }
+
+    std::vector<std::string> words;
+    std::vector<std::string> postags;
+
+    words.push_back("中国");    postags.push_back("ns");
+    words.push_back("国际");    postags.push_back("n");
+    words.push_back("广播");    postags.push_back("n");
+    words.push_back("电台");    postags.push_back("n");
+    words.push_back("创办");    postags.push_back("v");
+    words.push_back("于");      postags.push_back("p");
+    words.push_back("1941年");  postags.push_back("m");
+    words.push_back("12月");    postags.push_back("m");
+    words.push_back("3日");     postags.push_back("m");
+    words.push_back("。");      postags.push_back("wp");
+
+    std::vector<std::string>    tags;
+
+    ner_recognize(engine, words, postags, tags);
+
+    for (int i = 0; i < tags.size(); ++ i) {
+        std::cout << words[i] << "\t" << postags[i] << "\t" << tags[i] << std::endl;
+    }
+
+    ner_release_recognizer(engine);
+    return 0;
+}
+

examples/par.cpp

@@ -0,0 +1,37 @@
+#include <iostream>
+#include <vector>
+
+#include "parser_dll.h"
+
+int main(int argc, char * argv[]) {
+    if (argc < 2) {
+        return -1;
+    }
+
+    void * engine = parser_create_parser(argv[1]);
+    if (!engine) {
+        return -1;
+    }
+
+    std::vector<std::string> words;
+    std::vector<std::string> postags;
+
+    words.push_back("一把手");      postags.push_back("n");
+    words.push_back("亲自");        postags.push_back("d");
+    words.push_back("过问");        postags.push_back("v");
+    words.push_back("。");          postags.push_back("wp");
+
+    std::vector<int>            heads;
+    std::vector<std::string>    deprels;
+
+    parser_parse(engine, words, postags, heads, deprels);
+
+    for (int i = 0; i < heads.size(); ++ i) {
+        std::cout << words[i] << "\t" << postags[i] << "\t" 
+            << heads[i] << "\t" << deprels[i] << std::endl;
+    }
+
+    parser_release_parser(engine);
+    return 0;
+}
+

examples/pos.cpp

@@ -0,0 +1,36 @@
+#include <iostream>
+#include <vector>
+
+#include "postag_dll.h"
+
+int main(int argc, char * argv[]) {
+    if (argc < 1) {
+        return -1;
+    }
+
+    void * engine = postagger_create_postagger(argv[1]);
+    if (!engine) {
+        return -1;
+    }
+
+    std::vector<std::string> words;
+
+    words.push_back("我");
+    words.push_back("是");
+    words.push_back("中国人");
+
+    std::vector<std::string> tags;
+
+    postagger_postag(engine, words, tags);
+
+    for (int i = 0; i < tags.size(); ++ i) {
+        std::cout << words[i] << "/" << tags[i];
+        if (i == tags.size() - 1) std::cout << std::endl;
+        else std::cout << " ";
+
+    }
+
+    postagger_release_postagger(engine);
+    return 0;
+}
+

src/parser/parser.cpp

@@ -939,6 +939,7 @@ void Parser::test() {
 
     ifstream f(test_file);
     if (!f) {
+        ERROR_LOG("Failed to load test file %s", test_file);
         return;
     }