From 12ac1c9a6bd57daae1a0f0bff1c6ddfe0c3ec68d Mon Sep 17 00:00:00 2001
From: wyy <wuyanyi09@gmail.com>
Date: Sun, 23 Jun 2013 23:58:25 +0800
Subject: [PATCH] init

---
 .gitignore |  2 ++
 Makefile   | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 Trie.cpp   | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 Trie.h     | 23 +++++++++++++++++++++++
 globals.h  |  6 ++++++
 main.cpp   | 29 +++++++++++++++++++++++++++++
 6 files changed, 155 insertions(+)
 create mode 100644 Makefile
 create mode 100644 Trie.cpp
 create mode 100644 Trie.h
 create mode 100644 globals.h
 create mode 100644 main.cpp

diff --git a/.gitignore b/.gitignore
index 887a366..5a49d7d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -6,3 +6,5 @@ tags
 *.d
 *.ut
 log
+main
+cppcommon/cmlib.a
diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..f49d634
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,46 @@
+CC = g++
+CCOPT = -Wall -c
+LINK = g++
+LINKOPT =
+PACKA = ar
+PARCAOPT = rc
+DOLINK = $(LINK) $(LINKOPT) -o $@ $^
+SOURCES := $(wildcard *.cpp)
+OBJS := $(patsubst %.cpp,%.o,$(SOURCES))
+
+CMDIR = ./cppcommon/
+CMLIB = $(CMDIR)cmlib.a
+
+
+# remove the objs after compilation
+.INTERMEDIATE: 
+.PHONY: clean
+
+# This is a suffix rule 
+#.c.o: 
+%.o: %.cpp
+	$(CC) $(CCOPT) $<
+
+# Main Targets
+all: main
+
+
+main: $(OBJS) $(CMLIB)
+	$(DOLINK)
+
+$(CMLIB): $(CMDIR)
+	cd $(CMDIR) && $(MAKE)
+
+#unit test
+Trie.ut: Trie.cpp Trie.h $(CMLIB)
+	g++ -o $@ $< -DTRIE_UT $(CMLIB) 
+
+clean:
+	rm -f *.o *.ut $(CMLIB) main
+
+sinclude $(SOURCES:.cpp=.d)
+%.d:%.cpp
+	@set -e; rm -f $@; \
+	$(CC) -MM $< > $@.$$$$; \
+	sed 's,\($*\).o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+	rm -f $@.$$$$
diff --git a/Trie.cpp b/Trie.cpp
new file mode 100644
index 0000000..1fcbb13
--- /dev/null
+++ b/Trie.cpp
@@ -0,0 +1,49 @@
+#include "Trie.h"
+
+namespace CppJieba
+{
+    Trie::Trie()
+    {
+    }
+    
+    Trie::~Trie()
+    {
+    }
+    
+    bool Trie::init(const char* const filepath)
+    {
+        ifstream ifile(filepath);
+        string line;
+        vector<string> vecBuf;
+        while(getline(ifile, line))
+        {
+            vecBuf.clear();
+            splitStr(line, vecBuf, " ");
+            PRINT_VECTOR(vecBuf);
+            getchar();
+            uint16_t strbuf[1024];
+
+            size_t unilen = utf8ToUnicode(line.c_str(), line.size(), strbuf);
+            for(int i = 0; i < unilen; i++)
+            {
+                // printf("%x\n", strbuf[i]);
+            }
+            char utf8str[512]={0};
+            unicodeToUtf8(strbuf, unilen, utf8str);
+            //cout<<strlen(utf8str);
+            cout<<utf8str<<endl;
+            
+        }
+    }
+    
+}
+
+#ifdef TRIE_UT
+using namespace CppJieba;
+int main()
+{
+    Trie trie;
+    trie.init();
+    return 0;
+}
+#endif
diff --git a/Trie.h b/Trie.h
new file mode 100644
index 0000000..b03e4a7
--- /dev/null
+++ b/Trie.h
@@ -0,0 +1,23 @@
+#ifndef TRIE_H
+#define TRIE_H
+#include <iostream>
+#include <fstream>
+#include "cppcommon/str_functs.h"
+#include "cppcommon/vec_functs.h"
+#include "globals.h"
+
+namespace CppJieba
+{
+    using namespace CPPCOMMON;
+    using namespace std;
+    class Trie
+    {
+        public:
+            Trie();
+            ~Trie();
+        public:
+            bool init(const char* const filepath = DICT_FILE_PATH);
+    };
+}
+
+#endif
diff --git a/globals.h b/globals.h
new file mode 100644
index 0000000..70863d7
--- /dev/null
+++ b/globals.h
@@ -0,0 +1,6 @@
+#ifndef GLOBALS_H
+#define GLOBALS_H
+
+const char * const DICT_FILE_PATH = "dict.txt";
+
+#endif
diff --git a/main.cpp b/main.cpp
new file mode 100644
index 0000000..6141e56
--- /dev/null
+++ b/main.cpp
@@ -0,0 +1,29 @@
+#include <iostream>
+#include <iconv.h>
+#include <stdint.h>
+#include <fstream>
+#include <memory.h>
+#include "cppcommon/str_functs.h"
+using namespace std;
+using namespace CPPCOMMON;
+
+int main()
+{
+    ifstream ifile("dict.txt");
+    string line;
+    while(getline(ifile, line))
+    {
+        uint16_t strbuf[1024];
+
+        size_t unilen = utf8ToUnicode(line.c_str(), line.size(), strbuf);
+        for(int i = 0; i < unilen; i++)
+        {
+            // printf("%x\n", strbuf[i]);
+        }
+        char utf8str[512]={0};
+        unicodeToUtf8(strbuf, unilen, utf8str);
+        //cout<<strlen(utf8str);
+        cout<<utf8str<<endl;
+    }
+    return 0;
+}