Atitit. camel分词器 分词引擎 camel拆分 的实现设计
1.2. 特殊处理 对于JSONObject 多个大写字母连写的处理1
2.1. public class CamelScannerQ1 extends Scanner {2
2.2. public class iniState extends State {3
2.3. public class BigCaseLetterState extends State {4
2.4. public class LowerLetterState extends State {5
2.5. public class NumState extends State {7
1. camel分词器
1.1. 实现的界定符号大写字母小写字母数字
1.2. 特殊处理 对于JSONObject 多个大写字母连写的处理
1.3. camel分词器code
作者:: 老哇的爪子 Attilax 艾龙， EMAIL:1466519819@qq.com
转载请注明来源： http://blog.csdn.net/attilax
2. 代码实现
package com.attilax.fsm.camelScanner;
import java.util.ArrayList;
import java.util.List;
import com.attilax.fsm.Context;
import com.attilax.fsm.FinishState;
import com.attilax.fsm.Scanner;
import com.attilax.fsm.Token;
import com.attilax.json.JSONArray;
import com.attilax.json.JSONObject;
2.1. public class CamelScannerQ1 extends Scanner {
public static void main(String[] args) {
String s = "fld1=1,fld2='at''t,lax',fld3='val3'";
s = "aaaaCamelJSONObject123forMac";
s="com.sun.jna.platform.win32.Variant$VARIANT$_VARIANT$__VARIANT$BRECORD$ByReference.class";
s="";
//s="a";
@SuppressWarnings("rawtypes")
List tokenList = new CamelScannerQ1().getTokenList(s);
System.out.println(JSONArray.fromObject(tokenList).toString(2));
}
public List<String> getTokenList_retStr(String s)
{
if(s.length()==0)
return new ArrayList<String>();
List<String> li_r=new ArrayList<String>();
List<Token> li=getTokenList(s);
for (Token token : li) {
li_r.add(token.value);
}
return li_r;
}
public List getTokenList(String s) {
// DslPaserContext context = new DslPaserContext();
Context context = new Context();
context.setState(new iniState());
int n = 0;
while (!(context.state instanceof FinishState)) {
// System.out.println(n);
// ����
context.request(s);
n++;
if (n > 200)
break;
}
for (Token tk : context.tokenList) {
// if(tk.value.trim().length()>0)
System.out.println(tk.value + "===");
}
return (List) context.tokenList;
}
}
package com.attilax.fsm.camelScanner;
import java.util.List;
import com.attilax.fsm.Context;
import com.attilax.fsm.State;
import com.attilax.lang.text.strUtil;
import com.attilax.util.numUtil;
2.2. public class iniState extends State {
@Override
public void handle(String sampleParameter, Context context) {
context.curcharIndex=0;
char curChar=context.sa[context.curcharIndex];
if(strUtil.isBigLetter(curChar))
{
newToken(context, curChar);
context.state=new BigCaseLetterState();
}
if(strUtil.isLowerLetter(curChar))
{
newToken(context, curChar);
context.state=new LowerLetterState();
}
if(numUtil.isNum(curChar))
{
newToken(context, curChar);
context.state=new NumState();
}
}
}
package com.attilax.fsm.camelScanner;
import com.attilax.fsm.Context;
import com.attilax.fsm.FinishState;
import com.attilax.fsm.State;
import com.attilax.fsm.Token;
import com.attilax.lang.text.strUtil;
import com.attilax.util.numUtil;
2.3. public class BigCaseLetterState extends State {
@Override
public void handle(String sampleParameter, Context context) {
if(MoveNextisEnd(context) ) //or next cur move
return;
char curChar=context.sa[context.curcharIndex];
if(strUtil.isBigLetter(curChar))
{
context.curToken.value=context.curToken.value+String.valueOf(curChar);
context.state=new BigCaseLetterState();
}
if(strUtil.isLowerLetter(curChar))
{
context.curToken.value=context.curToken.value+String.valueOf(curChar);
context.state=new LowerLetterState();
}
if(numUtil.isNum(curChar))
{
context.tokenList.add(context.curToken);
context.curToken=new Token();
context.curToken.value=context.curToken.value+String.valueOf(curChar);
context.state=new NumState();
}
}
}
package com.attilax.fsm.camelScanner;
import com.attilax.fsm.Context;
import com.attilax.fsm.FinishState;
import com.attilax.fsm.State;
import com.attilax.fsm.Token;
import com.attilax.lang.text.strUtil;
import com.attilax.util.numUtil;
2.4. public class LowerLetterState extends State {
@Override
public void handle(String sampleParameter, Context context) {
// TODO Auto-generated method stub
if(MoveNextisEnd(context) )
return;
String trim = context.curToken.value.trim();
String allUpperLetter =trim.substring(0,trim.length()-1);
if(allUpperLetter.startsWith("J"))
System.out.println("");
if(strUtil.isBigLetter(allUpperLetter) && allUpperLetter.length()>1) //multi upperLetter
{
final String word=allUpperLetter.substring(0,trim.length()-2);
Token t=new Token(){
{
this.value=word;
}
};
context.tokenList.add(t);
Token t2=new Token();
t2.value=trim.substring( trim.length()-2);
context.curToken=t2;
//context.tokenList.add(t2);
}
char curChar=context.sa[context.curcharIndex];
if(strUtil.isBigLetter(curChar))
{
addCurTokenNnewToken(context, curChar);
context.state=new BigCaseLetterState();
}
if(strUtil.isLowerLetter(curChar))
{
context.curToken.value=context.curToken.value+String.valueOf(curChar);
// context.state=new LowerLetterState(); //state not change
}
if(numUtil.isNum(curChar))
{
addCurTokenNnewToken(context, curChar);
context.state=new NumState();
}
}
package com.attilax.fsm.camelScanner;
import com.attilax.fsm.Context;
import com.attilax.fsm.FinishState;
import com.attilax.fsm.State;
import com.attilax.fsm.Token;
import com.attilax.lang.text.strUtil;
import com.attilax.util.numUtil;
2.5. public class NumState extends State {
@Override
public void handle(String sampleParameter, Context context) {
// TODO Auto-generated method stub
if(MoveNextisEnd(context) )
return;
char curChar=context.sa[context.curcharIndex];
if(strUtil.isBigLetter(curChar))
{
addCurTokenNnewToken(context, curChar);
context.state=new BigCaseLetterState();
}
if(strUtil.isLowerLetter(curChar))
{
addCurTokenNnewToken(context, curChar);
context.state=new LowerLetterState();
}
if(numUtil.isNum(curChar))
{
context.curToken.value=context.curToken.value+String.valueOf(curChar);
// context.state=new NumState();
}
}
}
}