(0)

boy

apple

cat

(1)

boy

apple

cat

(2)

apple

boy

cat

(0)

cat

boy

apple

(1)

cat

boy

apple

(2)

boy

cat

apple

(3)

boy

apple

cat

(4)

apple

boy

cat

int main() {

??? return 0 ;

}

“int”, “ ”, “main”, “(”, “)”,

“”,“{”, “/n”, “/t”, “return”

“”,“0”,“”,“;”,“/n”,

“}”, “/n”, “”

KWINT, SPACE, ID, OPAR, CPAR,

SPACE, OBRACE, SPACE, SPACE, KWRETURN,

SPACE, OCTALCONST, SPACE, SEMICOLON, SPACE,

CBRACE, SPACE, EOF

?

/* adder.jj Adding up numbers */

options {

? STATIC = false ;

}

PARSER_BEGIN(Adder)

class Adder {

? static void main( String[] args ) throws ParseException, TokenMgrError {

??? Adder parser = new Adder( System.in ) ;

??? parser.Start() ;

? }

}

PARSER_END(Adder)

SKIP : { " " }

SKIP : { "/n" | "/r" | "/r/n" }

TOKEN : { < PLUS : "+" > }

TOKEN : { < NUMBER : (["0"-"9"])+ > }

void Start() :

{}

{

? <NUMBER>

? (

??? <PLUS>

??? <NUMBER>

? )*

? <EOF>

}

options?
{?
? static = false;?
}

PARSER_BEGIN(Adder)?
package org.apache.javacc;

public class Adder?
{?
? public static void main(String args []) throws ParseException?
? {?
??? Adder parser = new Adder(System.in);?
??? parser.start();?
? }?
}?
PARSER_END(Adder)

SKIP :?
{?
? " "?
| "/r"?
| "/t"?
| "/n"?
}

TOKEN : /* OPERATORS */?
{?
? < PLUS : "+" >?
}

TOKEN :?
{?
? < NUMBER : ([ "0"-"9" ])+ >?
}

void start() :?
{}?
{?
? <NUMBER>?
? (?
??? <PLUS>?
??? <NUMBER>?
? )*?
}

final public void start() throws ParseException {

??//從詞法分析器取得下一個Token，而且要求必須是NUMBER類型，否則拋出異常。

??//此步要求表達式第一個出現的字符必須是NUMBER。

? jj_consume_token(NUMBER);

? label_1:

? while (true) {

????//jj_ntk()是取得下一個Token的類型，如果是PLUS，則繼續進行，如果是EOF則退出循環。

??? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

??? case PLUS:

????? ;

????? break;

??? default:

????? jj_la1[0] = jj_gen;

????? break label_1;

??? }

???//要求下一個PLUS字符，再下一個是一個NUMBER，如此下去。

??? jj_consume_token(PLUS);

??? jj_consume_token(NUMBER);

? }

}

Exception in thread "main" org.apache.javacc.ParseException: Encountered " "+" "+ "" at line 1, column 5.?
Was expecting:?
??? <NUMBER> ...?
??? at org.apache.javacc.Adder.generateParseException(Adder.java:185)?
??? at org.apache.javacc.Adder.jj_consume_token(Adder.java:123)?
??? at org.apache.javacc.Adder.start(Adder.java:24)?
??? at org.apache.javacc.Adder.main(Adder.java:8)

Exception in thread "main" org.apache.javacc.TokenMgrError: Lexical error at line 1, column 4.? Encountered: "-" (45), after : ""?
??? at org.apache.javacc.AdderTokenManager.getNextToken(AdderTokenManager.java:262)?
??? at org.apache.javacc.Adder.jj_ntk(Adder.java:148)?
??? at org.apache.javacc.Adder.start(Adder.java:15)?
??? at org.apache.javacc.Adder.main(Adder.java:8)

int start() throws NumberFormatException :

{

??//start函數中有三個變量

? Token t ;

? int i ;

? int value ;

}

{

??//首先要求表達式的第一個一定是一個NUMBER，并把其值付給t

? t= <NUMBER>

??//將t的值取出來，解析為整型，放入變量i中

? { i = Integer.parseInt( t.image ) ; }

??//最后的結果value設為i

? { value = i ; }

??//緊接著應該是零個或者多個PLUS和NUMBER的組合

? (

??? <PLUS>

????//每出現一個NUMBER，都將其付給t，并將t的值解析為整型，付給i

??? t= <NUMBER>

??? { i = Integer.parseInt( t.image ) ; }

????//將i加到value上

??? { value += i ; }

? )*

??//最后的value就是表達式的和

? { return value ; }

}

final public int start() throws ParseException, NumberFormatException {

? Token t;

? int i;

? int value;

? t = jj_consume_token(NUMBER);

? i = Integer.parseInt(t.image);

? value = i;

? label_1: while (true) {

??? switch ((jj_ntk == -1) ? jj_ntk() : jj_ntk) {

??? case PLUS:

????? ;

????? break;

??? default:

????? jj_la1[0] = jj_gen;

????? break label_1;

??? }

??? jj_consume_token(PLUS);

??? t = jj_consume_token(NUMBER);

??? i = Integer.parseInt(t.image);

??? value += i;

? }

? {

??? if (true)

????? return value;

? }

? throw new Error("Missing return statement in function");

}

int start() throws NumberFormatException :

{

? int i;

? int value ;

}

{

? value = getNextNumberValue()

? (

??? <PLUS>

??? i = getNextNumberValue()

??? { value += i ; }

? )*

? { return value ; }

}

int getNextNumberValue() throws NumberFormatException :

{

? Token t ;

}

{

? t=<NUMBER>

? { return Integer.parseInt( t.image ) ; }

}

?

final public int start() throws ParseException, NumberFormatException {

? int i;

? int value;

? value = getNextNumberValue();

? label_1: while (true) {

??? switch ((jj_ntk == -1) ? jj_ntk() : jj_ntk) {

??? case PLUS:

????? ;

????? break;

??? default:

????? jj_la1[0] = jj_gen;

????? break label_1;

??? }

??? jj_consume_token(PLUS);

??? i = getNextNumberValue();

??? value += i;

? }

? {

??? if (true)

????? return value;

? }

? throw new Error("Missing return statement in function");

}

final public int getNextNumberValue() throws ParseException, NumberFormatException {

? Token t;

? t = jj_consume_token(NUMBER);

? {

??? if (true)

????? return Integer.parseInt(t.image);

? }

? throw new Error("Missing return statement in function");

}

options {

STATIC = false ;

}

PARSER_BEGIN(Calculator)

? import java.io.PrintStream ;

? class Calculator {

??? static void main( String[] args ) throws ParseException, TokenMgrError, NumberFormatException {

????? Calculator parser = new Calculator( System.in ) ;

????? parser.Start( System.out ) ;

??? }

??? double previousValue = 0.0 ;

? }

PARSER_END(Calculator)

SKIP : { " " }

TOKEN : { < EOL:"/n" | "/r" | "/r/n" > }

TOKEN : { < PLUS : "+" > }

TOKEN { < NUMBER : (["0"-"9"])+ | (["0"-"9"])+ "." (["0"-"9"])+ | (["0"-"9"])+ "." | "." (["0"-"9"])+ > }

TOKEN : { < NUMBER : <DIGITS> | <DIGITS> "." <DIGITS> | <DIGITS> "." | "." <DIGITS>> }

TOKEN : { < #DIGITS : (["0"-"9"])+ > }

Start -> (Expression EOL)* EOF

void Start(PrintStream printStream) throws NumberFormatException :

{}

{

? (

??? previousValue = Expression()

??? <EOL>

??? { printStream.println( previousValue ) ; }

? )*

? <EOF>

}

Expression -> Primary (PLUS Primary)*

double Expression() throws NumberFormatException :

{

? double i ;

? double value ;

}

{

? value = Primary()

? (

??? <PLUS>

??? i= Primary()

??? { value += i ; }

? )*

? { return value ; }

}

double Primary() throws NumberFormatException :

{

? Token t ;

}

{

? t= <NUMBER>

? { return Double.parseDouble( t.image ) ; }

}

TOKEN : { < MINUS : "-" > }

Expression -> Primary (PLUS Primary | MINUS Primary)*

double Expression() throws NumberFormatException :

{

? double i ;

? double value ;

}

{

? value = Primary()

? (

??? <PLUS>

??? i = Primary()

??? { value += i ; }

??? |

??? <MINUS>

??? i = Primary()

??? { value -= i ; }

? )*

? { return value ; }

}

TOKEN : { < TIMES : "*" > }

TOKEN : { < DIVIDE : "/" > }

Expression -> Term (PLUSTerm | MINUSTerm)*

Term -> Primary (TIMES Primary | DIVIDE Primary)*

double Expression() throws NumberFormatException :

{

? double i ;

? double value ;

}

{

? value = Term()

? (

??? <PLUS>

??? i= Term()

??? { value += i ; }

??? |

??? <MINUS>

??? i= Term()

??? { value -= i ; }

? )*

? { return value ; }

}

double Term() throws NumberFormatException :

{

? double i ;

? double value ;

}

{

? value = Primary()

? (

??? <TIMES>

??? i = Primary()

??? { value *= i ; }

??? |

??? <DIVIDE>

??? i = Primary()

??? { value /= i ; }

? )*

? { return value ; }

}

TOKEN : { < OPEN PAR : "(" > }

TOKEN : { < CLOSE PAR : ")" > }

TOKEN : { < PREVIOUS : "$" > }

Primary –> NUMBER | PREVIOUS | OPEN_PAR Expression CLOSE_PAR | MINUS Primary

double Primary() throws NumberFormatException :

{

? Token t ;

? double d ;

}

{

? t=<NUMBER>

? { return Double.parseDouble( t.image ) ; }

? |

? <PREVIOUS>

? { return previousValue ; }

? |

? <OPEN PAR> d=Expression() <CLOSE PAR>

? { return d ; }

? |

? <MINUS> d=Primary()

? { return -d ; }

}

options?
{?
? static = false;?
}

PARSER_BEGIN(Calculator)?
package org.apache.javacc.calculater;?
? import java.io.PrintStream ;?
? class Calculator {?
??? static void main( String[] args ) throws ParseException, TokenMgrError, NumberFormatException {?
????? Calculator parser = new Calculator( System.in ) ;?
????? parser.start( System.out ) ;?
??? }?
??? double previousValue = 0.0 ;?
? }?
PARSER_END(Calculator)

SKIP : { " " }?
TOKEN : { < EOL: "/n" | "/r" | "/r/n" > }?
TOKEN : { < PLUS : "+" > }?
TOKEN : { < MINUS : "-" > }?
TOKEN : { < TIMES : "*" > }?
TOKEN : { < DIVIDE : "/" > }?
TOKEN : { < NUMBER : <DIGITS> | <DIGITS> "." <DIGITS> | <DIGITS> "." | "." <DIGITS>> }?
TOKEN : { < #DIGITS : (["0"-"9"])+ > }?
TOKEN : { < OPEN_PAR : "(" > }?
TOKEN : { < CLOSE_PAR : ")" > }?
TOKEN : { < PREVIOUS : "$" > }

void start(PrintStream printStream) throws NumberFormatException :?
{}?
{?
? (?
??? previousValue = Expression()?
??? { printStream.println( previousValue ) ; }?
? )*?
}

double Expression() throws NumberFormatException :?
{?
? double i ;?
? double value ;?
}?
{?
? value = Term()?
? (?
??? <PLUS>?
??? i= Term()?
??? { value += i ; }?
??? |?
??? <MINUS>?
??? i= Term()?
??? { value -= i ; }?
? )*?
? { return value ; }?
}

double Term() throws NumberFormatException :?
{?
? double i ;?
? double value ;?
}?
{?
? value = Primary()?
? (?
??? <TIMES>?
??? i = Primary()?
??? { value *= i ; }?
??? |?
??? <DIVIDE>?
??? i = Primary()?
??? { value /= i ; }?
? )*?
? { return value ; }?
}

double Primary() throws NumberFormatException :?
{?
? Token t ;?
? double d ;?
}?
{?
? t=<NUMBER>?
? { return Double.parseDouble( t.image ) ; }?
? |?
? <PREVIOUS>?
? { return previousValue ; }?
? |?
? <OPEN_PAR> d=Expression() <CLOSE_PAR>?
? { return d ; }?
? |?
? <MINUS> d=Primary()?
? { return -d ; }?
}

final public void start(PrintStream printStream) throws ParseException, NumberFormatException {

? label_1:

? while (true) {

??? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

??? case MINUS:

??? case NUMBER:

??? case OPEN_PAR:

??? case PREVIOUS:

????? ;

????? break;

??? default:

????? jj_la1[0] = jj_gen;

????? break label_1;

??? }

??? previousValue = Expression();

??? printStream.println( previousValue ) ;

? }

}

final public double Expression() throws ParseException, NumberFormatException {

? double i ;

? double value ;

? value = Term();

? label_2:

? while (true) {

??? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

??? case PLUS:

??? case MINUS:

????? ;

????? break;

??? default:

????? jj_la1[1] = jj_gen;

????? break label_2;

??? }

??? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

??? case PLUS:

????? jj_consume_token(PLUS);

????? i = Term();

????? value += i ;

????? break;

??? case MINUS:

????? jj_consume_token(MINUS);

????? i = Term();

????? value -= i ;

????? break;

??? default:

????? jj_la1[2] = jj_gen;

????? jj_consume_token(-1);

????? throw new ParseException();

??? }

? }

? {if (true) return value ;}

? throw new Error("Missing return statement in function");

}

final public double Term() throws ParseException, NumberFormatException {

? double i ;

? double value ;

? value = Primary();

? label_3:

? while (true) {

??? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

??? case TIMES:

??? case DIVIDE:

????? ;

????? break;

??? default:

????? jj_la1[3] = jj_gen;

????? break label_3;

??? }

??? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

??? case TIMES:

????? jj_consume_token(TIMES);

????? i = Primary();

????? value *= i ;

????? break;

??? case DIVIDE:

????? jj_consume_token(DIVIDE);

????? i = Primary();

????? value /= i ;

????? break;

??? default:

????? jj_la1[4] = jj_gen;

????? jj_consume_token(-1);

????? throw new ParseException();

??? }

? }

? {if (true) return value ;}

? throw new Error("Missing return statement in function");

}

final public double Primary() throws ParseException, NumberFormatException {

? Token t ;

? double d ;

? switch ((jj_ntk==-1)?jj_ntk():jj_ntk) {

? case NUMBER:

??? t = jj_consume_token(NUMBER);

??? {if (true) return Double.parseDouble( t.image ) ;}

??? break;

? case PREVIOUS:

??? jj_consume_token(PREVIOUS);

??? {if (true) return previousValue ;}

??? break;

? case OPEN_PAR:

??? jj_consume_token(OPEN_PAR);

??? d = Expression();

??? jj_consume_token(CLOSE_PAR);

??? {if (true) return d ;}

??? break;

? case MINUS:

??? jj_consume_token(MINUS);

??? d = Primary();

??? {if (true) return -d ;}

??? break;

? default:

??? jj_la1[5] = jj_gen;

??? jj_consume_token(-1);

??? throw new ParseException();

? }

? throw new Error("Missing return statement in function");

}

//默認處于DEFAULT狀態，當遇到/**的時候，轉換為IN_JAVADOC_COMMENT狀態

<DEFAULT> TOKEN : {<STARTDOC : “/**” > : IN_JAVADOC_COMMENT }

//在IN_JAVADOC_COMMENT狀態下，需要識別@param變量

<IN_JAVADOC_COMMENT> TOKEN : {<PARAM : "@param" >}

//在IN_JAVADOC_COMMENT狀態下，遇到*/的時候，裝換為DEFAULT狀態

<IN_JAVADOC_COMMENT> TOKEN : {<ENDDOC: "*/">: DEFAULT }

<*> TOKEN : {

? <#_NUM_CHAR:?? ["0"-"9"] >?//數字

| <#_ESCAPED_CHAR: "//" ~[] >?//"/"后的任何一個字符都是被轉義的

| <#_TERM_START_CHAR: ( ~[ " ", "/t", "/n", "/r", "/u3000", "+", "-", "!", "(", ")", ":", "^", "[", "]", "/"", "{", "}", "~", "*", "?", "//" ] | <_ESCAPED_CHAR> ) >?//表達式中任何一個term，都不能以[]括起來的列表中的lucene查詢語法關鍵字開頭，當然被轉義的除外。

| <#_TERM_CHAR: ( <_TERM_START_CHAR> | <_ESCAPED_CHAR> | "-" | "+" ) >?//表達式中的term非起始字符，可以包含任何非語法關鍵字字符，轉義過的字符，也可以包含+, -(但包含+,-的符合詞法，不合語法)。

| <#_WHITESPACE: ( " " | "/t" | "/n" | "/r" | "/u3000") >?//被認為是空格的字符

| <#_QUOTED_CHAR: ( ~[ "/"", "//" ] | <_ESCAPED_CHAR> ) >?//被引號括起來的字符不應再包括"和/，當然轉義過的除外。

}

<DEFAULT> TOKEN : {

? <AND:?????? ("AND" | "&&") >

| <OR:??????? ("OR" | "||") >

| <NOT:?????? ("NOT" | "!") >

| <PLUS:????? "+" >

| <MINUS:???? "-" >

| <LPAREN:??? "(" >

| <RPAREN:??? ")" >

| <COLON:???? ":" >

| <STAR:????? "*" >

| <CARAT:???? "^" > : Boost?//當遇到^的時候，后面跟隨的是boost表達式，進入Boost狀態

| <QUOTED:???? "/"" (<_QUOTED_CHAR>)* "/"">

| <TERM:????? <_TERM_START_CHAR> (<_TERM_CHAR>)*? >

| <FUZZY_SLOP:???? "~" ( (<_NUM_CHAR>)+ ( "." (<_NUM_CHAR>)+ )? )? >?//Fuzzy查詢，~后面跟小數。

| <PREFIXTERM:? ("*") | ( <_TERM_START_CHAR> (<_TERM_CHAR>)* "*" ) >?//使用*進行Prefix查詢，可以盡包含*，或者末尾包含*，然而只包含*符合詞法，不合語法。

| <WILDTERM:? (<_TERM_START_CHAR> | [ "*", "?" ]) (<_TERM_CHAR> | ( [ "*", "?" ] ))* >?//使用*和?進行wildcard查詢

| <RANGEIN_START: "[" > : RangeIn?//遇到[]的時候，是包含邊界的Range查詢

| <RANGEEX_START: "{" > : RangeEx?//遇到{}的時候，是不包含邊界的Range查詢

}

<Boost> TOKEN : {

<NUMBER:??? (<_NUM_CHAR>)+ ( "." (<_NUM_CHAR>)+ )? > : DEFAULT?//boost是一個小數

}

//包含邊界的Range查詢是[A TO B]的形式。

<RangeIn> TOKEN : {

<RANGEIN_TO: "TO">

| <RANGEIN_END: "]"> : DEFAULT

| <RANGEIN_QUOTED: "/"" (~["/""] | "///"")+ "/"">

| <RANGEIN_GOOP: (~[ " ", "]" ])+ >

}

//不包含邊界的Range查詢是{A TO B}的形式

<RangeEx> TOKEN : {

<RANGEEX_TO: "TO">

| <RANGEEX_END: "}"> : DEFAULT

| <RANGEEX_QUOTED: "/"" (~["/""] | "///"")+ "/"">

| <RANGEEX_GOOP: (~[ " ", "}" ])+ >

}

Query? ::= ( Clause )*

Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )

Query TopLevelQuery(String field) :

{

??? Query q;

}

{

??? q=Query(field) <EOF>

??? {

??????? return q;

??? }

}

Query Query(String field) :

{

? List<BooleanClause> clauses = new ArrayList<BooleanClause>();

? Query q, firstQuery=null;

? int conj, mods;

}

{

??//查詢語句開頭是一個Modifier，可以為空

? //Modifier后面便是子語句clause，可以生成子查詢語句q

? mods=Modifiers() q=Clause(field)

? {

????//如果第一個語句的Modifier是空，則將子查詢q付給firstQuery，從后面我們可以看到，當只有一個查詢語句的時候，如果其Modifier為空，則不返回BooleanQuery，而是返回子查詢對象firstQuery。從這里我們可以看出，如果查詢語句為"A"，則生成TermQuery，其term為"A"，如果查詢語句為"+A"，則生成BooleanQuery，其子查詢只有一個，就是TermQuery，其term為"A"。

??? addClause(clauses, CONJ_NONE, mods, q);

??? if (mods == MOD_NONE)

??????? firstQuery=q;

? }

? (

????//除了第一個語句外，其他的前面可以有連接符，或為AND，或為OR。

??? //如果在第一個語句之前出現連接符，則報錯，如"OR a"，會報Encountered " <OR> "OR "" at line 1, column 0.

??? //除了連接符，也會有Modifier，后面是子語句clause，生成子查詢q，并加入BooleanQuery中。

??? conj=Conjunction() mods=Modifiers() q=Clause(field)

??? { addClause(clauses, conj, mods, q); }

? )*

? {

????//如果只有一個查詢語句，且其modifier為空，則返回firstQuery，否則由所有的子語句clause，生成BooleanQuery。

??? if (clauses.size() == 1 && firstQuery != null)

????? return firstQuery;

??? else {

????? return getBooleanQuery(clauses);

??? }

? }

}

int Modifiers() : {

??//默認modifier為空，如果遇到+，就是required，如果遇到-或者NOT，就是prohibited。

? int ret = MOD_NONE;

}

{

? [

???? <PLUS> { ret = MOD_REQ; }

???? | <MINUS> { ret = MOD_NOT; }

???? | <NOT> { ret = MOD_NOT; }

? ]

? { return ret; }

}

//連接符

int Conjunction() : {

? int ret = CONJ_NONE;

}

{

? [

??? <AND> { ret = CONJ_AND; }

??? | <OR>? { ret = CONJ_OR; }

? ]

? { return ret; }

}

?

Query Clause(String field) : {

? Query q;

? Token fieldToken=null, boost=null;

}

{

??//此處之所以向前看兩個符號，就是當看到<TERM>的時候，不知道它是一個field，還是一個term，當<TERM><COLON>在一起的時候，說明<TERM>代表一個field, 否則代表一個term

? [

??? LOOKAHEAD(2)

??? (

??? fieldToken=<TERM> <COLON> {field=discardEscapeChar(fieldToken.image);}

??? | <STAR> <COLON> {field="*";}

??? )

? ]

? (

??//或者是一個term，則由此term生成一個查詢對象

?? //或者是一個由括號括起來的子查詢

?? //()?表示可能存在一個boost，格式為^加一個數字

?? q=Term(field)

?? | <LPAREN> q=Query(field) <RPAREN> (<CARAT> boost=<NUMBER>)?

? )

? {

????//如果存在boost，則設定查詢對象的boost

??? if (boost != null) {

????? float f = (float)1.0;

????? try {

??????? f = Float.valueOf(boost.image).floatValue();

??????? q.setBoost(f);

????? } catch (Exception ignored) { }

??? }

??? return q;

? }

}

?

Query Term(String field) : {

? Token term, boost=null, fuzzySlop=null, goop1, goop2;

? boolean prefix = false;

? boolean wildcard = false;

? boolean fuzzy = false;

? Query q;

}

{

? (

???? (

??????//如果term僅結尾包含*則是prefix查詢。

?????? //如果以*開頭，或者中間包含*，或者結尾包含*(如果僅結尾包含，則prefix優先)則為wildcard查詢。

?????? term=<TERM>

?????? | term=<STAR> { wildcard=true; }

?????? | term=<PREFIXTERM> { prefix=true; }

?????? | term=<WILDTERM> { wildcard=true; }

?????? | term=<NUMBER>

???? )

?????//如果term后面是~，則是fuzzy查詢

???? [ fuzzySlop=<FUZZY_SLOP> { fuzzy=true; } ]

???? [ <CARAT> boost=<NUMBER> [ fuzzySlop=<FUZZY_SLOP> { fuzzy=true; } ] ]

???? {

????????//如果是wildcard查詢，則調用getWildcardQuery，

??????? //??? *:*得到MatchAllDocsQuery，將返回所有的文檔

??????? //??? 目前不支持最前面帶通配符的查詢(雖然詞法分析和語法分析都能通過)，否則報ParseException

??????? //??? 最后生成WildcardQuery

??????? //如果是prefix查詢，則調用getPrefixQuery，生成PrefixQuery

??????? //如果是fuzzy查詢，則調用getFuzzyQuery,生成FuzzyQuery

??????? //如果是普通查詢，則調用getFieldQuery

?????? String termImage=discardEscapeChar(term.image);

?????? if (wildcard) {

???????? q = getWildcardQuery(field, termImage);

?????? } else if (prefix) {

???????? q = getPrefixQuery(field, discardEscapeChar(term.image.substring(0, term.image.length()-1)));

?????? } else if (fuzzy) {

???????? float fms = fuzzyMinSim;

???????? try {

?????????? fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue();

???????? } catch (Exception ignored) { }

???????? if(fms < 0.0f || fms > 1.0f){

?????????? throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");

???????? }

???????? q = getFuzzyQuery(field, termImage,fms);

?????? } else {

???????? q = getFieldQuery(field, termImage);

?????? }

???? }

?????//包含邊界的range查詢，取得[goop1 TO goop2]，調用getRangeQuery，生成TermRangeQuery

???? | ( <RANGEIN_START> ( goop1=<RANGEIN_GOOP>|goop1=<RANGEIN_QUOTED> )

???????? [ <RANGEIN_TO> ] ( goop2=<RANGEIN_GOOP>|goop2=<RANGEIN_QUOTED> )

???????? <RANGEIN_END> )

?????? [ <CARAT> boost=<NUMBER> ]

??????? {

????????? if (goop1.kind == RANGEIN_QUOTED) {

??????????? goop1.image = goop1.image.substring(1, goop1.image.length()-1);

????????? }

????????? if (goop2.kind == RANGEIN_QUOTED) {

??????????? goop2.image = goop2.image.substring(1, goop2.image.length()-1);

????????? }

????????? q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), true);

??????? }

?????//不包含邊界的range查詢，取得{goop1 TO goop2}，調用getRangeQuery，生成TermRangeQuery

???? | ( <RANGEEX_START> ( goop1=<RANGEEX_GOOP>|goop1=<RANGEEX_QUOTED> )

???????? [ <RANGEEX_TO> ] ( goop2=<RANGEEX_GOOP>|goop2=<RANGEEX_QUOTED> )

???????? <RANGEEX_END> )

?????? [ <CARAT> boost=<NUMBER> ]

??????? {

????????? if (goop1.kind == RANGEEX_QUOTED) {

??????????? goop1.image = goop1.image.substring(1, goop1.image.length()-1);

????????? }

????????? if (goop2.kind == RANGEEX_QUOTED) {

??????????? goop2.image = goop2.image.substring(1, goop2.image.length()-1);

????????? }

????????? q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), false);

??????? }

?????//被""括起來的term，得到phrase查詢，調用getFieldQuery

???? | term=<QUOTED>

?????? [ fuzzySlop=<FUZZY_SLOP> ]

?????? [ <CARAT> boost=<NUMBER> ]

?????? {

???????? int s = phraseSlop;

???????? if (fuzzySlop != null) {

?????????? try {

???????????? s = Float.valueOf(fuzzySlop.image.substring(1)).intValue();

?????????? }

?????????? catch (Exception ignored) { }

???????? }

???????? q = getFieldQuery(field, discardEscapeChar(term.image.substring(1, term.image.length()-1)), s);

?????? }

? )

? {

??? if (boost != null) {

????? float f = (float) 1.0;

????? try {

??????? f = Float.valueOf(boost.image).floatValue();

????? }

????? catch (Exception ignored) {

????? }

????? // avoid boosting null queries, such as those caused by stop words

????? if (q != null) {

??????? q.setBoost(f);

????? }

??? }

??? return q;

? }

}

protected Query getFieldQuery(String field, String queryText)? throws ParseException {

??//需要用analyzer對文本進行分詞

? TokenStream source;

? try {

??? source = analyzer.reusableTokenStream(field, new StringReader(queryText));

??? source.reset();

? } catch (IOException e) {

??? source = analyzer.tokenStream(field, new StringReader(queryText));

? }

? CachingTokenFilter buffer = new CachingTokenFilter(source);

? TermAttribute termAtt = null;

? PositionIncrementAttribute posIncrAtt = null;

? int numTokens = 0;

? boolean success = false;

? try {

??? buffer.reset();

??? success = true;

? } catch (IOException e) {

? }

??//得到TermAttribute和PositionIncrementAttribute，此兩項將決定到底產生什么樣的Query對象

? if (success) {

??? if (buffer.hasAttribute(TermAttribute.class)) {

????? termAtt = buffer.getAttribute(TermAttribute.class);

??? }

??? if (buffer.hasAttribute(PositionIncrementAttribute.class)) {

????? posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class);

??? }

? }

? int positionCount = 0;

? boolean severalTokensAtSamePosition = false;

? boolean hasMoreTokens = false;

? if (termAtt != null) {

??? try {

??????//遍歷分詞后的所有Token，統計Tokens的個數numTokens，以及positionIncrement的總數，即positionCount。

????? //當有一次positionIncrement為0的時候，severalTokensAtSamePosition設為true，表示有多個Token處在同一個位置。

????? hasMoreTokens = buffer.incrementToken();

????? while (hasMoreTokens) {

??????? numTokens++;

??????? int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1;

??????? if (positionIncrement != 0) {

????????? positionCount += positionIncrement;

??????? } else {

????????? severalTokensAtSamePosition = true;

??????? }

??????? hasMoreTokens = buffer.incrementToken();

????? }

??? } catch (IOException e) {

??? }

? }

? try {

????//重設buffer，以便生成phrase查詢的時候，term和position可以重新遍歷。

??? buffer.reset();

??? source.close();

? }

? catch (IOException e) {

? }

? if (numTokens == 0)

??? return null;

? else if (numTokens == 1) {

????//如果分詞后只有一個Token，則生成TermQuery

??? String term = null;

??? try {

????? boolean hasNext = buffer.incrementToken();

????? term = termAtt.term();

??? } catch (IOException e) {

??? }

??? return newTermQuery(new Term(field, term));

? } else {

???//如果分詞后不只有一個Token

??? if (severalTokensAtSamePosition) {

???//如果有多個Token處于同一個位置

????? if (positionCount == 1) {

????????//并且處于同一位置的Token還全部處于第一個位置，則生成BooleanQuery，處于同一位置的Token之間是OR的關系

??????? BooleanQuery q = newBooleanQuery(true);

??????? for (int i = 0; i < numTokens; i++) {

????????? String term = null;

????????? try {

??????????? boolean hasNext = buffer.incrementToken();

??????????? term = termAtt.term();

????????? } catch (IOException e) {

????????? }

????????? Query currentQuery = newTermQuery(new Term(field, term));

????????? q.add(currentQuery, BooleanClause.Occur.SHOULD);

??????? }

??????? return q;

????? }

????? else {

????????//如果有多個Token處于同一位置，但不是第一個位置，則生成MultiPhraseQuery。

??????? //所謂MultiPhraseQuery即其可以包含多個phrase，其又一個ArrayList<Term[]> termArrays，每一項都是一個Term的數組，屬于同一個數組的Term表示在同一個位置。它有函數void add(Term[] terms)一次添加一個數組的Term。比如我們要搜索"microsoft app*"，其表示多個phrase，"microsoft apple"，"microsoft application"都算。此時用QueryParser.parse("/"microsoft app*/"")從而生成PhraseQuery是搜不出microsoft apple和microsoft application的，也不能搜出microsoft app，因為*一旦被引號所引，就不算通配符了。所以必須生成MultiPhraseQuery，首先用add(new Term[]{new Term("field", "microsoft")})將microsoft作為一個Term數組添加進去，然后用add(new Term[]{new Term("field", "app"), new Term("field", "apple"), new Term("field", "application")})作為一個Term數組添加進去(算作同一個位置的)，則三者都能搜的出來。

??????? MultiPhraseQuery mpq = newMultiPhraseQuery();

??????? mpq.setSlop(phraseSlop);

??????? List<Term> multiTerms = new ArrayList<Term>();

??????? int position = -1;

??????? for (int i = 0; i < numTokens; i++) {

????????? String term = null;

????????? int positionIncrement = 1;

????????? try {

??????????? boolean hasNext = buffer.incrementToken();

??????????? assert hasNext == true;

??????????? term = termAtt.term();

??????????? if (posIncrAtt != null) {

????????????? positionIncrement = posIncrAtt.getPositionIncrement();

??????????? }

????????? } catch (IOException e) {

????????? }

????????? if (positionIncrement > 0 && multiTerms.size() > 0) {

????????????//如果positionIncrement大于零，說明此Term和前一個Term已經不是同一個位置了，所以原來收集在multiTerms中的Term都算作同一個位置，添加到MultiPhraseQuery中作為一項。并清除multiTerms，以便重新收集相同位置的Term。

??????????? if (enablePositionIncrements) {

????????????? mpq.add(multiTerms.toArray(new Term[0]),position);

??????????? } else {

????????????? mpq.add(multiTerms.toArray(new Term[0]));

??????????? }

??????????? multiTerms.clear();

????????? }

??????????//將此Term收集到multiTerms中。

????????? position += positionIncrement;

????????? multiTerms.add(new Term(field, term));

??????? }

????????//當遍歷完所有的Token，同處于最后一個位置的Term已經收集到multiTerms中了，把他們加到MultiPhraseQuery中作為一項。

??????? if (enablePositionIncrements) {

????????? mpq.add(multiTerms.toArray(new Term[0]),position);

??????? } else {

????????? mpq.add(multiTerms.toArray(new Term[0]));

??????? }

??????? return mpq;

????? }

??? }

??? else {

??????//如果不存在多個Token處于同一個位置的情況，則直接生成PhraseQuery

????? PhraseQuery pq = newPhraseQuery();

????? pq.setSlop(phraseSlop);

????? int position = -1;

????? for (int i = 0; i < numTokens; i++) {

??????? String term = null;

??????? int positionIncrement = 1;

??????? try {

????????? boolean hasNext = buffer.incrementToken();

????????? assert hasNext == true;

????????? term = termAtt.term();

????????? if (posIncrAtt != null) {

??????????? positionIncrement = posIncrAtt.getPositionIncrement();

????????? }

??????? } catch (IOException e) {

??????? }

??????? if (enablePositionIncrements) {

????????? position += positionIncrement;

????????? pq.add(new Term(field, term),position);

??????? } else {

????????? pq.add(new Term(field, term));

??????? }

????? }

????? return pq;

??? }

? }

}