1.2、分词的过程
1.2.1、分词器工作的过程
内置的分词器效果都不好,那怎么办?只能自己写了!在写之前当然是要先看看内置的分词器是怎么实现的了。从1.1分析分词效果,可以看出KeywordAnalyzer这个分词器最懒惰,基本什么事情也没做。并不是它不会做,而是我们没找到使用它的方法,就像手上拿着个盒子,不知道里面是什么,就不知道这个是干嘛的,有什么用。打开盒子,那就是要查看源代码了!
代码 1.2.1.1
![]()
Code
1
using System;
2
3
namespace Lucene.Net.Analysis
4

{
5
6
/**//// <summary> "Tokenizes" the entire stream as a single token. This is useful
7
/// for data like zip codes, ids, and some product names.
8
/// </summary>
9
public class KeywordAnalyzer : Analyzer
10
{
11
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
12
{
13
return new KeywordTokenizer(reader);
14
}
15
16
public override TokenStream ReusableTokenStream(System.String fieldName, System.IO.TextReader reader)
17
{
18
Tokenizer tokenizer = (Tokenizer)GetPreviousTokenStream();
19
if (tokenizer == null)
20
{
21
tokenizer = new KeywordTokenizer(reader);
22
SetPreviousTokenStream(tokenizer);
23
}
24
else
25
tokenizer.Reset(reader);
26
return tokenizer;
27
}
28
}
29
}
代码1.2.1.1 就是传说中的源码了。先看看注释,意思大体是“‘Tokenizes’整体的流变成一个个词。这个特别适用于邮编,ID,和商品名称。”Tokenizes应该是拆分的意思,字典上查不到这个词。
这段代码比较简单,只有两个方法,而第二个方法就是我们先前分析结果的时候用的(见段落1.1)。关键点就在于调用了KeywordTokenizer类。切到KeywordTokenizer类查看一下。
代码1.2.1.2
![]()
Code
1
using System;
2
3
namespace Lucene.Net.Analysis
4

{
5
6
/**//// <summary> Emits the entire input as a single token.</summary>
7
public class KeywordTokenizer : Tokenizer
8
{
9
10
private const int DEFAULT_BUFFER_SIZE = 256;
11
12
private bool done;
13
14
public KeywordTokenizer(System.IO.TextReader input) : this(input, DEFAULT_BUFFER_SIZE)
15
{
16
}
17
18
public KeywordTokenizer(System.IO.TextReader input, int bufferSize) : base(input)
19
{
20
this.done = false;
21
}
22
23
public override Token Next(Token result)
24
{
25
if (!done)
26
{
27
done = true;
28
int upto = 0;
29
result.Clear();
30
char[] buffer = result.TermBuffer();
31
while (true)
32
{
33
int length = input.Read(buffer, upto, buffer.Length - upto);
34
if (length <= 0)
35
break;
36
upto += length;
37
if (upto == buffer.Length)
38
buffer = result.ResizeTermBuffer(1 + buffer.Length);
39
}
40
result.termLength = upto;
41
return result;
42
}
43
return null;
44
}
45
46
public override void Reset(System.IO.TextReader input)
47
{
48
base.Reset(input);
49
this.done = false;
50
}
51
}
52
}
代码 1.2.1.2 就是KeywordTokenizer的源码。代码量很小,却没有完成全部工作,而是将部分工作交给了父类。关注Lucene的人都可以知道,新版本中,分词这里换掉了,现在多了一个重载的Next方法。这里不讨论为什么要加这个重载,这篇文章主要是讲应用的。因为取词是用Next方法走的,那么只需要关注Next方法就可以了。KeywordTokenizer的父类是Tokenizer,但是在Tokenizer里找不到我们想要的关系,但是Tokenizer又继承自TokenStream。查看TokenStream类。
代码 1.2.1.3
![]()
Code
1
2
using System;
3
4
using Payload = Lucene.Net.Index.Payload;
5
6
namespace Lucene.Net.Analysis
7

{
8
9
/**//// <summary>A TokenStream enumerates the sequence of tokens, either from
10
/// fields of a document or from query text.
11
/// <p>
12
/// This is an abstract class. Concrete subclasses are:
13
/// <ul>
14
/// <li>{@link Tokenizer}, a TokenStream
15
/// whose input is a Reader; and
16
/// <li>{@link TokenFilter}, a TokenStream
17
/// whose input is another TokenStream.
18
/// </ul>
19
/// NOTE: subclasses must override at least one of {@link
20
/// #Next()} or {@link #Next(Token)}.
21
/// </summary>
22
23
public abstract class TokenStream
24
{
25
26
/**//// <summary>Returns the next token in the stream, or null at EOS.
27
/// The returned Token is a "full private copy" (not
28
/// re-used across calls to next()) but will be slower
29
/// than calling {@link #Next(Token)} instead..
30
/// </summary>
31
public virtual Token Next()
32
{
33
Token result = Next(new Token());
34
35
if (result != null)
36
{
37
Payload p = result.GetPayload();
38
if (p != null)
39
{
40
result.SetPayload((Payload) p.Clone());
41
}
42
}
43
44
return result;
45
}
46
47
/**//// <summary>Returns the next token in the stream, or null at EOS.
48
/// When possible, the input Token should be used as the
49
/// returned Token (this gives fastest tokenization
50
/// performance), but this is not required and a new Token
51
/// may be returned. Callers may re-use a single Token
52
/// instance for successive calls to this method.
53
/// <p>
54
/// This implicitly defines a "contract" between
55
/// consumers (callers of this method) and
56
/// producers (implementations of this method
57
/// that are the source for tokens):
58
/// <ul>
59
/// <li>A consumer must fully consume the previously
60
/// returned Token before calling this method again.</li>
61
/// <li>A producer must call {@link Token#Clear()}
62
/// before setting the fields in it & returning it</li>
63
/// </ul>
64
/// Note that a {@link TokenFilter} is considered a consumer.
65
/// </summary>
66
/// <param name="result">a Token that may or may not be used to return
67
/// </param>
68
/// <returns> next token in the stream or null if end-of-stream was hit
69
/// </returns>
70
public virtual Token Next(Token result)
71
{
72
return Next();
73
}
74
75
/**//// <summary>Resets this stream to the beginning. This is an
76
/// optional operation, so subclasses may or may not
77
/// implement this method. Reset() is not needed for
78
/// the standard indexing process. However, if the Tokens
79
/// of a TokenStream are intended to be consumed more than
80
/// once, it is necessary to implement reset().
81
/// </summary>
82
public virtual void Reset()
83
{
84
}
85
86
/**//// <summary>Releases resources associated with this stream. </summary>
87
public virtual void Close()
88
{
89
}
90
}
91
}
代码 1.2.1.3 就是TokenStream类的源码。Next(Token)方法和Next()是相互调用的关系。但是因为Next(Token)方法在KeywordTokenizer里被重写掉了,因此,这里就可以忽略TokenStream的Next(Token)方法了。
从上面代码可以看出,调用Next()方法,实际上是传递给Next(Token)方法一个新Token实例。即使直接调用Next(Token),传递一个带有数据的Token,也会先被清除。在循环中,会把构造函数传入的流缓冲进Token类的缓冲区。ResizeTermBuffer方法是自动扩容用的,就像.Net Framework里的一些类能够自然扩容一样。比如List<T>,Hashtable或StringBuilder等。这个过程看不到分词的过程。不过这样就大致明白了分词器工作的流程。
1.2.2 如何让分词器分词
知道分词器如何工作了,但是现在还不明白分词如何分词。再回到1.1.2节,看到WhitespaceAnalyzer分词器似乎是学习的好选择。因为这个分词器只有遇到空格才会进行分词操作。
根据1.2.1的经验,直接查看WhitespaceTokenizer类。
代码1.2.2.1
![]()
Code
1
using System;
2
3
namespace Lucene.Net.Analysis
4

{
5
6
/**//// <summary>A WhitespaceTokenizer is a tokenizer that divides text at whitespace.
7
/// Adjacent sequences of non-Whitespace characters form tokens.
8
/// </summary>
9
10
public class WhitespaceTokenizer : CharTokenizer
11
{
12
/**//// <summary>Construct a new WhitespaceTokenizer. </summary>
13
public WhitespaceTokenizer(System.IO.TextReader in_Renamed) : base(in_Renamed)
14
{
15
}
16
17
/**//// <summary>Collects only characters which do not satisfy
18
/// {@link Character#isWhitespace(char)}.
19
/// </summary>
20
protected internal override bool IsTokenChar(char c)
21
{
22
return !System.Char.IsWhiteSpace(c);
23
}
24
}
25
}
很好,这段代码很短,可是没有看到我们想要的东西。继续看父类。
代码1.2.2.2
![]()
Code
1
using System;
2
3
namespace Lucene.Net.Analysis
4

{
5
6
/**//// <summary>An abstract base class for simple, character-oriented tokenizers.</summary>
7
public abstract class CharTokenizer : Tokenizer
8
{
9
public CharTokenizer(System.IO.TextReader input) : base(input)
10
{
11
}
12
13
private int offset = 0, bufferIndex = 0, dataLen = 0;
14
private const int MAX_WORD_LEN = 255;
15
private const int IO_BUFFER_SIZE = 1024;
16
private char[] ioBuffer = new char[IO_BUFFER_SIZE];
17
18
/**//// <summary>Returns true iff a character should be included in a token. This
19
/// tokenizer generates as tokens adjacent sequences of characters which
20
/// satisfy this predicate. Characters for which this is false are used to
21
/// define token boundaries and are not included in tokens.
22
/// </summary>
23
protected internal abstract bool IsTokenChar(char c);
24
25
/**//// <summary>Called on each token character to normalize it before it is added to the
26
/// token. The default implementation does nothing. Subclasses may use this
27
/// to, e.g., lowercase tokens.
28
/// </summary>
29
protected internal virtual char Normalize(char c)
30
{
31
return c;
32
}
33
34
public override Token Next(Token token)
35
{
36
token.Clear();
37
int length = 0;
38
int start = bufferIndex;
39
char[] buffer = token.TermBuffer();
40
while (true)
41
{
42
43
if (bufferIndex >= dataLen)
44
{
45
offset += dataLen;
46
dataLen = input is Lucene.Net.Index.DocumentsWriter.ReusableStringReader ? ((Lucene.Net.Index.DocumentsWriter.ReusableStringReader) input).Read(ioBuffer) : input.Read((System.Char[]) ioBuffer, 0, ioBuffer.Length);
47
if (dataLen <= 0)
48
{
49
if (length > 0)
50
break;
51
else
52
return null;
53
}
54
bufferIndex = 0;
55
}
56
57
char c = ioBuffer[bufferIndex++];
58
59
if (IsTokenChar(c))
60
{
61
// if it's a token char
62
63
if (length == 0)
64
// start of token
65
start = offset + bufferIndex - 1;
66
else if (length == buffer.Length)
67
buffer = token.ResizeTermBuffer(1 + length);
68
69
buffer[length++] = Normalize(c); // buffer it, normalized
70
71
if (length == MAX_WORD_LEN)
72
// buffer overflow!
73
break;
74
}
75
else if (length > 0)
76
// at non-Letter w/ chars
77
break; // return 'em
78
}
79
80
token.termLength = length;
81
token.startOffset = start;
82
token.endOffset = start + length;
83
return token;
84
}
85
86
public override void Reset(System.IO.TextReader input)
87
{
88
base.Reset(input);
89
bufferIndex = 0;
90
offset = 0;
91
dataLen = 0;
92
}
93
}
94
}
天公不作美,刚看到简单的,就来了个长的。无奈中。不过为什么要多一重继承呢?那就是有其他分词器也用到CharTokenizer了。而WhitespaceTokenizer中没有重写Next方法,而只是重写了IsTokenChar方法,几乎可以肯定。这个IsTokenChar才是重点。IsTokenChar故名思意,一看注释,果然!这个方法是判断是否遇到了分词的点的。这个其实和string类的Split方法相似。注意到Next方法关于IsTokenChar逻辑那一段,恩,果然是这样分词的。实际上就是拆分字符串嘛。