分类:
2008-06-22 13:15:19
关于FieldInfos类和FieldInfo类。
FieldInfo类与一个Document中的一个Field相对应,而FieldInfos类又是多个FieldInfo的容器,对每个Document的所有Field对应的FieldInfo进行管理。
FieldInfos类和FieldInfo类之间的关系,恰似SegmentInfos类(可以参考文章 Lucene-2.2.0 源代码阅读学习(18))和SegmentInfo类(可以参考文章 Lucene-2.2.0 源代码阅读学习(19))之间的关系。
FieldInfo类的实现比较简单,该类的定义如下所示:
package org.apache.lucene.index;
final class FieldInfo {
String name; // 一个Field的名称
boolean isIndexed; // 该Field是否被索引
int number; // 该Field的编号
// 是否存储该Field的词条向量
boolean storeTermVector;
boolean storeOffsetWithTermVector;
boolean storePositionWithTermVector;
boolean omitNorms; // 是否忽略与被索引的该Field相关的norm文件信息
boolean storePayloads; // 是否该Field存储与词条位置相关的Payload
// 构造一个FieldInfo对象
FieldInfo(String na, boolean tk, int nu, boolean storeTermVector,
boolean storePositionWithTermVector, boolean storeOffsetWithTermVector,
boolean omitNorms, boolean storePayloads) {
name = na;
isIndexed = tk;
number = nu;
this.storeTermVector = storeTermVector;
this.storeOffsetWithTermVector = storeOffsetWithTermVector;
this.storePositionWithTermVector = storePositionWithTermVector;
this.omitNorms = omitNorms;
this.storePayloads = storePayloads;
}
}
上面就是2.2.0版本中FieldInfo类的全部定义。
下面是FieldInfos了的定义了,该类主要是通过FieldInfo来管理一个Document中的全部Field,源代码如下所示:
package org.apache.lucene.index;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Fieldable;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.store.IndexOutput;
import java.io.IOException;
import java.util.*;
// FieldInfo描述的是Document中的Field的信息,而FieldInfos类是用来管理一个个的FieldInfo的。
final class FieldInfos {
// 下面一组byte成员,使用十六进制数初始化,用来管理FieldInfo的属性
static final byte IS_INDEXED = 0x1; // 是否索引
static final byte STORE_TERMVECTOR = 0x2; // 是否存储词条向量
static final byte STORE_POSITIONS_WITH_TERMVECTOR = 0x4; // 是否存储与词条向量相关的位置
static final byte STORE_OFFSET_WITH_TERMVECTOR = 0x8; // 是否存储与词条向量相关的offset
static final byte OMIT_NORMS = 0x10; // 是否存储被忽略的norms
static final byte STORE_PAYLOADS = 0x20; // 是否存储Payload
private ArrayList byNumber = new ArrayList(); // byNumber是通过编号,用来存放FieldInfo的列表
private HashMap byName = new HashMap(); // byNname是通过名称,用来存放FieldInfo的列表
FieldInfos() { } // 没有参数的FieldInfos的构造函数
// 通过索引目录d和一个索引输入流name构造一个FieldInfos对象
FieldInfos(Directory d, String name) throws IOException {
IndexInput input = d.openInput(name);
try {
read(input); // input输入流已打开,从索引目录中读取
} finally {
input.close();
}
}
// 为一个Document添加Field的信息(这种添加和直接向Document中添加Field不一样,这次添加的不是一些固有信息,是一些更详细的补充信息)
public void add(Document doc) {
List fields = doc.getFields(); // 先获取到该Document中已经添加进去的所有Field
Iterator fieldIterator = fields.iterator();
while (fieldIterator.hasNext()) {
Fieldable field = (Fieldable) fieldIterator.next();
add(field.name(), field.isIndexed(), field.isTermVectorStored(), field.isStorePositionWithTermVector(),
field.isStoreOffsetWithTermVector(), field.getOmitNorms()); // 传参,调用核心的add方法执行添加
}
}
/**
* 添加被索引的Field,需要指定是否具有词条向量
*/
public void addIndexed(Collection names, boolean storeTermVectors, boolean storePositionWithTermVector,boolean storeOffsetWithTermVector) {
Iterator i = names.iterator();
while (i.hasNext()) {
add((String)i.next(), true, storeTermVectors, storePositionWithTermVector, storeOffsetWithTermVector);
}
}
/**
* 当Field没有存储词条向量,添加Field
*
* @param names The names of the fields
* @param isIndexed Whether the fields are indexed or not
*
* @see #add(String, boolean)
*/
public void add(Collection names, boolean isIndexed) {
Iterator i = names.iterator();
while (i.hasNext()) {
add((String)i.next(), isIndexed);
}
}
/**
* Calls 5 parameter add with false for all TermVector parameters.
*
* @param name The name of the Fieldable
* @param isIndexed true if the field is indexed
* @see #add(String, boolean, boolean, boolean, boolean)
*/
public void add(String name, boolean isIndexed) {
add(name, isIndexed, false, false, false, false);
}
/**
* Calls 5 parameter add with false for term vector positions and offsets.
*
* @param name The name of the field
* @param isIndexed true if the field is indexed
* @param storeTermVector true if the term vector should be stored
*/
public void add(String name, boolean isIndexed, boolean storeTermVector){
add(name, isIndexed, storeTermVector, false, false, false);
}
/** If the field is not yet known, adds it. If it is known, checks to make
* sure that the isIndexed flag is the same as was given previously for this
* field. If not - marks it as being indexed. Same goes for the TermVector
* parameters.
*
* @param name The name of the field
* @param isIndexed true if the field is indexed
* @param storeTermVector true if the term vector should be stored
* @param storePositionWithTermVector true if the term vector with positions should be stored
* @param storeOffsetWithTermVector true if the term vector with offsets should be stored
*/
public void add(String name, boolean isIndexed, boolean storeTermVector,
boolean storePositionWithTermVector, boolean storeOffsetWithTermVector) {
add(name, isIndexed, storeTermVector, storePositionWithTermVector, storeOffsetWithTermVector, false);
}
/** If the field is not yet known, adds it. If it is known, checks to make
* sure that the isIndexed flag is the same as was given previously for this
* field. If not - marks it as being indexed. Same goes for the TermVector
* parameters.
*
* @param name The name of the field
* @param isIndexed true if the field is indexed
* @param storeTermVector true if the term vector should be stored
* @param storePositionWithTermVector true if the term vector with positions should be stored
* @param storeOffsetWithTermVector true if the term vector with offsets should be stored
* @param omitNorms true if the norms for the indexed field should be omitted
*/
public void add(String name, boolean isIndexed, boolean storeTermVector,
boolean storePositionWithTermVector, boolean storeOffsetWithTermVector, boolean omitNorms) {
add(name, isIndexed, storeTermVector, storePositionWithTermVector,
storeOffsetWithTermVector, omitNorms, false);
}
/** 如果该Field没有被添加过,则添加它。如果已经添加过,核查后确保它的是否被索引标志位与已经存在的一致,如果是“不索引”标志,则修改标志位为true.
*该add添加方法才是最核心的实现方法。
* @param name The name of the field
* @param isIndexed true if the field is indexed
* @param storeTermVector true if the term vector should be stored
* @param storePositionWithTermVector true if the term vector with positions should be stored
* @param storeOffsetWithTermVector true if the term vector with offsets should be stored
* @param omitNorms true if the norms for the indexed field should be omitted
* @param storePayloads true if payloads should be stored for this field
*/
public FieldInfo add(String name, boolean isIndexed, boolean storeTermVector,
boolean storePositionWithTermVector, boolean storeOffsetWithTermVector,
boolean omitNorms, boolean storePayloads) {
FieldInfo fi = fieldInfo(name); // 根据指定的name构造一个FieldInfo对象
if (fi == null) { // 如果构造的FieldInfo为null,则调用addInternal()方法,重新构造一个
return addInternal(name, isIndexed, storeTermVector, storePositionWithTermVector, storeOffsetWithTermVector, omitNorms, storePayloads);
} else { // 如果构造的FieldInfo不为null(即已经存在一个相同name的FieldInfo)
if (fi.isIndexed != isIndexed) { // 如果存在的FieldInfo被索引
fi.isIndexed = true; // 一旦被索引了,总是索引
}
if (fi.storeTermVector != storeTermVector) {
fi.storeTermVector = true; // 一旦存储词条向量,总是存储
}
if (fi.storePositionWithTermVector != storePositionWithTermVector) {
fi.storePositionWithTermVector = true; // once vector, always vector
}
if (fi.storeOffsetWithTermVector != storeOffsetWithTermVector) {
fi.storeOffsetWithTermVector = true; // once vector, always vector
}
if (fi.omitNorms != omitNorms) {
fi.omitNorms = false; // 一旦存储norms,则总是存储norms
}
if (fi.storePayloads != storePayloads) {
fi.storePayloads = true;
}
}
return fi; // 返回一个FieldInfo对象
}
private FieldInfo addInternal(String name, boolean isIndexed,
boolean storeTermVector, boolean storePositionWithTermVector,
boolean storeOffsetWithTermVector, boolean omitNorms, boolean storePayloads) {
FieldInfo fi =
new FieldInfo(name, isIndexed, byNumber.size(), storeTermVector, storePositionWithTermVector,
storeOffsetWithTermVector, omitNorms, storePayloads);
byNumber.add(fi); // byNumber是一个List,将构造的FieldInfo加入到列表中
byName.put(name, fi); // byName是一个HashMap,其中的键值对
return fi;
}
public int fieldNumber(String fieldName) { // 根据指定的Field的名称,获取该Field的编号
try {
FieldInfo fi = fieldInfo(fieldName);
if (fi != null)
return fi.number;
}
catch (IndexOutOfBoundsException ioobe) {
return -1;
}
return -1;
}
public FieldInfo fieldInfo(String fieldName) { // 根据指定的Field的名称,从byName列表中取出该Field
return (FieldInfo) byName.get(fieldName);
}
// 根据指定的编号,获取Field的名称name
public String fieldName(int fieldNumber) {
try {
return fieldInfo(fieldNumber).name;
}
catch (NullPointerException npe) {
return "";
}
}
// 根据指定的Field的编号,获取一个FieldInfo对象
public FieldInfo fieldInfo(int fieldNumber) {
try {
return (FieldInfo) byNumber.get(fieldNumber); // 从byNymber列表中取出索引为指定fieldNumber的FieldInfo对象
}
catch (IndexOutOfBoundsException ioobe) {
return null;
}
}
public int size() { // 计算byName这个HashMap的大小
return byNumber.size();
}
public boolean hasVectors() { // 返回byName这个HashMap中FieldInfo指定对应的Field不存储词条向量的标志值,即false
boolean hasVectors = false;
for (int i = 0; i < size(); i++) {
if (fieldInfo(i).storeTermVector) {
hasVectors = true;
break;
}
}
return hasVectors;
}
public void write(Directory d, String name) throws IOException { // 将FieldInfo的信息输出到索引目录中,name是索引目录中存在的索引段文件名segments.fnm(可以参考文章 Lucene-2.2.0 源代码阅读学习(21) 中,DocumentWriter的addDocument()方法)
IndexOutput output = d.createOutput(name);
try {
write(output); // 调用下面的write方法,对FieldInfo的信息进行格式化(输出)写入索引目录
} finally {
output.close();
}
}
public void write(IndexOutput output) throws IOException { // 对FieldInfo的信息进行格式化(输出)写入索引目录
output.writeVInt(size());
for (int i = 0; i < size(); i++) {
FieldInfo fi = fieldInfo(i);
byte bits = 0x0;
if (fi.isIndexed) bits |= IS_INDEXED;
if (fi.storeTermVector) bits |= STORE_TERMVECTOR;
if (fi.storePositionWithTermVector) bits |= STORE_POSITIONS_WITH_TERMVECTOR;
if (fi.storeOffsetWithTermVector) bits |= STORE_OFFSET_WITH_TERMVECTOR;
if (fi.omitNorms) bits |= OMIT_NORMS;
if (fi.storePayloads) bits |= STORE_PAYLOADS;
output.writeString(fi.name);
output.writeByte(bits);
}
}
private void read(IndexInput input) throws IOException { // 通过打开一个输入流,读取FieldInfo的信息
int size = input.readVInt();//read in the size
for (int i = 0; i < size; i++) {
String name = input.readString().intern();
byte bits = input.readByte();
boolean isIndexed = (bits & IS_INDEXED) != 0;
boolean storeTermVector = (bits & STORE_TERMVECTOR) != 0;
boolean storePositionsWithTermVector = (bits & STORE_POSITIONS_WITH_TERMVECTOR) != 0;
boolean storeOffsetWithTermVector = (bits & STORE_OFFSET_WITH_TERMVECTOR) != 0;
boolean omitNorms = (bits & OMIT_NORMS) != 0;
boolean storePayloads = (bits & STORE_PAYLOADS) != 0;
addInternal(name, isIndexed, storeTermVector, storePositionsWithTermVector, storeOffsetWithTermVector, omitNorms, storePayloads); // 调用addInternal()在内存中构造一个FieldInfo对象,对它进行管理
}
}
}
对FieldInfo类和FieldInfos类进行总结:
1、FieldInfo作为一个实体,保存了Field的一些主要的信息;
2、因为对Field的操作比较频繁,而每次管理都在内存中加载FieldInfo这个轻量级但信息很重要的对象,能够大大提高建立索引的速度;
3、FieldInfos包含的信息比较丰富,通过一个FieldInfo对象,调出Document中的Field到内存中,对每个Field进行详细的管理。
4、FieldInfos支持独立从索引目录中读取Document中的信息(主要根据Document参数,管理其中的Field),然后再写回到索引目录。
综合总结:
FieldInfos是对Document中的Field进行管理的,它主要是在内存中进行管理,然后写入到索引目录中。具体地,它所拥有的信息都被写入了一个与索引段文件相关的segments.fnm文件中(可以参考文章 Lucene-2.2.0 源代码阅读学习(21) ,在DocumentWriter类的addDocument()方法中可以看到)
DocumnetWriter类的实现,是在FieldInfos类的基础上。FieldInfos类对Document的所有的Field的静态信息进行管理,而DocumentWriter类表现出了更强大的管理Document的功能,主要是对Field进行了一些高级的操作,比如使用Analyzer分析器进行分词、对切分出来的词条进行排序(文档倒排)等等。
下一步,就要仔细研究DocumnetWriter类了。