分词的话,java类的split方法和StringTokenizer类可以进行简单的分词,如果不用NLP的API类时。下文的例子都属于apache的openNLP的方法,案例来源于java自然语言处理这本书
import opennlp.tools.tokenize.SimpleTokenizer;
/**
* Filename: NlpTokenizerDeal.java
* Description: 文本分词标准化处理 -1.字母准变小写;2.缩写词展开;3.去除停用词;4.词干化和词性还原
* Copyright: Copyright (c) 2019 All Rights Reserved.
* @author: wangk
* @version: 1.0
* Create at: 2019年5月6日 上午11:26:53
*
* Modification History:
* Date Author Version Description
* ------------------------------------------------------------------
* 2019年5月6日 wangk 1.0 1.0 Version
*
*/
public class NlpTokenizerDeal {
static String paragraph = "A simple approach to create a class to hold and remove stopwords Let's IBM";
static String chineseLanguage = "第一个括号子表达式捕获 Web 地址的协议部分。该子表达式匹配在冒号和两个正斜杠前面的任何单词。"; //中文可以进行正则匹配每隔字中间加一个空格,就可以进行分词了
static String words[] = {"bank","banking","banks","banker"};
public static void main(String[] args) {
NlpTokenizerDeal to = new NlpTokenizerDeal();
//to.stopWordC(chineseLanguage);
to.porterStemmer(words);
}
/**
* @Description: 转换为小写字母
* @author wangk
* @param text
* @date: 2019年5月6日 上午11:30:33
*/
public void toLowerCase(String text) {
String ret = text.toLowerCase();
System.out.println(ret);
}
/**
* @Description: 停用词
* @author wangk
* @param text
* @date: 2019年5月6日 下午2:02:59
*/
public void stopWordE(String text) {
StopWords stopWords = new StopWords();
//注意大写字母,停用词为小写此处应该住变为小写
text = text.toLowerCase();
SimpleTokenizer simpleTokenizer = SimpleTokenizer.INSTANCE;
String tokens[] = simpleTokenizer.tokenize(text);
String list[] = stopWords.removeEWords(tokens);
for(String word : list) {
System.out.println(word);
}
}
//结果:simple approach create class hold and remove stopwords let ' s ibm
/**
* @Description: 停用词 中文
* @author wangk
* @param text
* @date: 2019年5月6日 下午2:02:59
*/
public void stopWordC(String text) {
StopWords stopWords = new StopWords();
//由于分词工具类采用空格分词,故每隔中文添加空格 试试停用词
String regex = "(.{1})";
text = text.replaceAll (regex, "$1 ");
SimpleTokenizer simpleTokenizer = SimpleTokenizer.INSTANCE;
String tokens[] = simpleTokenizer.tokenize(text);
String list[] = stopWords.removeCWords(tokens);
for(String word : list) {
System.out.println(word);
}
}
//结果:第个括号子表达式捕获Web地址协议部分。子表达式匹配冒号两正斜杠前面任单词。
/**
* @Description: 词干化 得到句子词元 只适用于普通的词缀
* Porter Stemmer 词干分析器官网 https://tartarus.org/martin/PorterStemmer/
* @author wangk
* @param text
* @date: 2019年5月6日 下午3:00:41
* apache opennlp http://svn.apache.org/repos/asf/opennlp/trunk/opennlp-tools/src/main/java/opennlp/tools/stemmer/PorterStemmer
*/
public void porterStemmer(String words[] ) {
PorterStemmer ps = new PorterStemmer();
for(String word : words) {
String stem = ps.stem(word);
System.out.println("word:"+word+" stem:"+stem);
}
}
/*word:bank stem:bank
word:banking stem:bank
word:banks stem:bank
word:banker stem:banker*/
}
用到的两个类,停用词类,和词干性还原类
package com.npl.demo.utils;
/**
*
* Stemmer, implementing the Porter Stemming Algorithm
*
* The Stemmer class transforms a word into its root form. The input
* word can be provided a character at time (by calling add()), or at once
* by calling one of the various stem(something) methods.
*/
public class PorterStemmer {
private char[] b;
private int i, /* offset into b */
j, k, k0;
private boolean dirty = false;
private static final int INC = 50;
public PorterStemmer() {
b = new char[INC];
i = 0;
}
/**
* reset() resets the stemmer so it can stem another word. If you invoke
* the stemmer by calling add(char) and then stem(), you must call reset()
* before starting another word.
*/
public void reset() { i = 0; dirty = false; }
/**
* Add a character to the word being stemmed. When you are finished
* adding characters, you can call stem(void) to process the word.
*/
public void add(char ch) {
if (b.length == i) {
char[] new_b = new char[i+INC];
for (int c = 0; c < i; c++) new_b[c] = b[c]; {
b = new_b;
}
}
b[i++] = ch;
}
/**
* After a word has been stemmed, it can be retrieved by toString(),
* or a reference to the internal buffer can be retrieved by getResultBuffer
* and getResultLength (which is generally more efficient.)
*/
@Override
public String toString() { return new String(b,0,i); }
/**
* Returns the length of the word resulting from the stemming process.
*/
public int getResultLength() { return i; }
/**
* Returns a reference to a character buffer containing the results of
* the stemming process. You also need to consult getResultLength()
* to determine the length of the result.
*/
public char[] getResultBuffer() { return b; }
/* cons(i) is true <=> b[i] is a consonant. */
private final boolean cons(int i) {
switch (b[i]) {
case 'a': case 'e': case 'i': case 'o': case 'u':
return false;
case 'y':
return (i==k0) ? true : !cons(i-1);
default:
return true;
}
}
/* m() measures the number of consonant sequences between k0 and j. if c is
a consonant sequence and v a vowel sequence, and <..> indicates arbitrary
presence,
<c><v> gives 0
<c>vc<v> gives 1
<c>vcvc<v> gives 2
<c>vcvcvc<v> gives 3
....
*/
private final int m() {
int n = 0;
int i = k0;
while(true) {
if (i > j)
return n;
if (! cons(i))
break;
i++;
}
i++;
while(true) {
while(true) {
if (i > j)
return n;
if (cons(i))
break;
i++;
}
i++;
n++;
while(true) {
if (i > j)
return n;
if (! cons(i))
break;
i++;
}
i++;
}
}
/* vowelinstem() is true <=> k0,...j contains a vowel */
private final boolean vowelinstem() {
int i;
for (i = k0; i <= j; i++)
if (! cons(i))
return true;
return false;
}
/* doublec(j) is true <=> j,(j-1) contain a double consonant. */
private final boolean doublec(int j) {
if (j < k0+1)
return false;
if (b[j] != b[j-1])
return false;
return cons(j);
}
/* cvc(i) is true <=> i-2,i-1,i has the form consonant - vowel - consonant
and also if the second c is not w,x or y. this is used when trying to
restore an e at the end of a short word. e.g.
cav(e), lov(e), hop(e), crim(e), but
snow, box, tray.
*/
private final boolean cvc(int i) {
if (i < k0+2 || !cons(i) || cons(i-1) || !cons(i-2))
return false;
else {
int ch = b[i];
if (ch == 'w' || ch == 'x' || ch == 'y') return false;
}
return true;
}
private final boolean ends(String s) {
int l = s.length();
int o = k-l+1;
if (o < k0)
return false;
for (int i = 0; i < l; i++)
if (b[o+i] != s.charAt(i))
return false;
j = k-l;
return true;
}
/* setto(s) sets (j+1),...k to the characters in the string s, readjusting
k. */
void setto(String s) {
int l = s.length();
int o = j+1;
for (int i = 0; i < l; i++)
b[o+i] = s.charAt(i);
k = j+l;
dirty = true;
}
/* r(s) is used further down. */
void r(String s) { if (m() > 0) setto(s); }
/* step1() gets rid of plurals and -ed or -ing. e.g.
caresses -> caress
ponies -> poni
ties -> ti
caress -> caress
cats -> cat
feed -> feed
agreed -> agree
disabled -> disable
matting -> mat
mating -> mate
meeting -> meet
milling -> mill
messing -> mess
meetings -> meet
*/
private final void step1() {
if (b[k] == 's') {
if (ends("sses")) k -= 2;
else if (ends("ies")) setto("i");
else if (b[k-1] != 's') k--;
}
if (ends("eed")) {
if (m() > 0)
k--;
}
else if ((ends("ed") || ends("ing")) && vowelinstem()) {
k = j;
if (ends("at")) setto("ate");
else if (ends("bl")) setto("ble");
else if (ends("iz")) setto("ize");
else if (doublec(k)) {
int ch = b[k--];
if (ch == 'l' || ch == 's' || ch == 'z')
k++;
}
else if (m() == 1 && cvc(k))
setto("e");
}
}
/* step2() turns terminal y to i when there is another vowel in the stem. */
private final void step2() {
if (ends("y") && vowelinstem()) {
b[k] = 'i';
dirty = true;
}
}
/* step3() maps double suffices to single ones. so -ization ( = -ize plus
-ation) maps to -ize etc. note that the string before the suffix must give
m() > 0. */
private final void step3() {
if (k == k0) return; /* For Bug 1 */
switch (b[k-1]) {
case 'a':
if (ends("ational")) { r("ate"); break; }
if (ends("tional")) { r("tion"); break; }
break;
case 'c':
if (ends("enci")) { r("ence"); break; }
if (ends("anci")) { r("ance"); break; }
break;
case 'e':
if (ends("izer")) { r("ize"); break; }
break;
case 'l':
if (ends("bli")) { r("ble"); break; }
if (ends("alli")) { r("al"); break; }
if (ends("entli")) { r("ent"); break; }
if (ends("eli")) { r("e"); break; }
if (ends("ousli")) { r("ous"); break; }
break;
case 'o':
if (ends("ization")) { r("ize"); break; }
if (ends("ation")) { r("ate"); break; }
if (ends("ator")) { r("ate"); break; }
break;
case 's':
if (ends("alism")) { r("al"); break; }
if (ends("iveness")) { r("ive"); break; }
if (ends("fulness")) { r("ful"); break; }
if (ends("ousness")) { r("ous"); break; }
break;
case 't':
if (ends("aliti")) { r("al"); break; }
if (ends("iviti")) { r("ive"); break; }
if (ends("biliti")) { r("ble"); break; }
break;
case 'g':
if (ends("logi")) { r("log"); break; }
}
}
/* step4() deals with -ic-, -full, -ness etc. similar strategy to step3. */
private final void step4() {
switch (b[k]) {
case 'e':
if (ends("icate")) { r("ic"); break; }
if (ends("ative")) { r(""); break; }
if (ends("alize")) { r("al"); break; }
break;
case 'i':
if (ends("iciti")) { r("ic"); break; }
break;
case 'l':
if (ends("ical")) { r("ic"); break; }
if (ends("ful")) { r(""); break; }
break;
case 's':
if (ends("ness")) { r(""); break; }
break;
}
}
/* step5() takes off -ant, -ence etc., in context <c>vcvc<v>. */
private final void step5() {
if (k == k0) return; /* for Bug 1 */
switch (b[k-1]) {
case 'a':
if (ends("al")) break;
return;
case 'c':
if (ends("ance")) break;
if (ends("ence")) break;
return;
case 'e':
if (ends("er")) break; return;
case 'i':
if (ends("ic")) break; return;
case 'l':
if (ends("able")) break;
if (ends("ible")) break; return;
case 'n':
if (ends("ant")) break;
if (ends("ement")) break;
if (ends("ment")) break;
/* element etc. not stripped before the m */
if (ends("ent")) break;
return;
case 'o':
if (ends("ion") && j >= 0 && (b[j] == 's' || b[j] == 't')) break;
/* j >= 0 fixes Bug 2 */
if (ends("ou")) break;
return;
/* takes care of -ous */
case 's':
if (ends("ism")) break;
return;
case 't':
if (ends("ate")) break;
if (ends("iti")) break;
return;
case 'u':
if (ends("ous")) break;
return;
case 'v':
if (ends("ive")) break;
return;
case 'z':
if (ends("ize")) break;
return;
default:
return;
}
if (m() > 1)
k = j;
}
/* step6() removes a final -e if m() > 1. */
private final void step6() {
j = k;
if (b[k] == 'e') {
int a = m();
if (a > 1 || a == 1 && !cvc(k-1))
k--;
}
if (b[k] == 'l' && doublec(k) && m() > 1)
k--;
}
/**
* Stem a word provided as a String. Returns the result as a String.
*/
public String stem(String s) {
if (stem(s.toCharArray(), s.length()))
return toString();
else
return s;
}
/**
* Stem a word provided as a CharSequence.
* Returns the result as a CharSequence.
*/
public CharSequence stem(CharSequence word) {
return stem(word.toString());
}
/** Stem a word contained in a char[]. Returns true if the stemming process
* resulted in a word different from the input. You can retrieve the
* result with getResultLength()/getResultBuffer() or toString().
*/
public boolean stem(char[] word) {
return stem(word, word.length);
}
/** Stem a word contained in a portion of a char[] array. Returns
* true if the stemming process resulted in a word different from
* the input. You can retrieve the result with
* getResultLength()/getResultBuffer() or toString().
*/
public boolean stem(char[] wordBuffer, int offset, int wordLen) {
reset();
if (b.length < wordLen) {
b = new char[wordLen - offset];
}
System.arraycopy(wordBuffer, offset, b, 0, wordLen);
i = wordLen;
return stem(0);
}
/** Stem a word contained in a leading portion of a char[] array.
* Returns true if the stemming process resulted in a word different
* from the input. You can retrieve the result with
* getResultLength()/getResultBuffer() or toString().
*/
public boolean stem(char[] word, int wordLen) {
return stem(word, 0, wordLen);
}
/** Stem the word placed into the Stemmer buffer through calls to add().
* Returns true if the stemming process resulted in a word different
* from the input. You can retrieve the result with
* getResultLength()/getResultBuffer() or toString().
*/
public boolean stem() {
return stem(0);
}
public boolean stem(int i0) {
k = i - 1;
k0 = i0;
if (k > k0+1) {
step1(); step2(); step3(); step4(); step5(); step6();
}
// Also, a word is considered dirty if we lopped off letters
// Thanks to Ifigenia Vairelles for pointing this out.
if (i != k+1)
dirty = true;
i = k+1;
return dirty;
}
}
package com.npl.demo.utils;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashSet;
public class StopWords {
static String paragraph = "Let's The first sentence. The second sentence. Let's IBM";
static String chineseLanguage = "时代的碰撞|中国古典民乐与流行的相遇"; //中文可以进行正则匹配每隔字中间加一个空格,就可以进行分词了
private String[] englishStopWords = {"a","off","on","once","only","or","other","ought","our","ours ","ourselves","out","over","own","same","shan't","she",
"she'd","she'll","she's","should","shouldn't","so","some","such","than","that","that's","the","their","theirs","them","themselves","then",
"there","there's","these","they","they'd","they'll","they're","they've","this","those","through","to","too","under","until","up","very",
"was","wasn't","we","we'd","we'll","we're","we've","were","weren't","what","what's","when","when's","where","where's","which","while","who",
"who's","whom","why","why's","with","won't","would","wouldn't","you","you'd","you'll","you're","you've","your","yours","yourself","yourselves"};
private String[] chineseStopWords = {"的","一","不","在","人","有","是","为","以","于","上","他","而","后","之","来","及","了","因","下","可","到","由",
"这","与","也","此","但","并","个","其","已","无","小","我","们","起","最","再","今","去","好","只","又","或","很","亦","某","把","那","你","乃",
"它","吧","被","比","别","趁","当","从","到","得","打","凡","儿","尔","该","各","给","跟","和","何","还","即","几","既","看","据","距","靠","啦",
"了","另","么","每","们","嘛","拿","哪","那","您","凭","且","却","让","仍","啥","如","若","使","谁","虽","随","同","所","她","哇","嗡","往","哪",
"些","向","沿","哟","用","于","咱","则","怎","曾","至","致","着","诸","自"};
private static HashSet eStopWords = new HashSet();
private static HashSet cStopWords = new HashSet();
public StopWords() {
eStopWords.addAll(Arrays.asList(englishStopWords));
cStopWords.addAll(Arrays.asList(chineseStopWords));
}
public StopWords(String fileName) {
try {
BufferedReader br = new BufferedReader(new FileReader(fileName));
while(br.ready()) {
eStopWords.add(br.readLine());
}
} catch (IOException e) {
e.printStackTrace();
}
}
public void addEStopWords(String word) {
eStopWords.add(word);
}
public void addCStopWords(String word) {
cStopWords.add(word);
}
/**
* @Description: 将提交来的词列表处理,去除停用词,返回非停用词列表 英文
* @author wangk
* @param words
* @return
* @date: 2019年5月6日 下午2:29:39
*/
public String[] removeEWords(String[] words) {
ArrayList<String> tokens = new ArrayList(Arrays.asList(words));
for(int i=0;i<tokens.size();i++) {
if(eStopWords.contains(tokens.get(i))) {
tokens.remove(i);
}
}
return (String[])tokens.toArray(new String[tokens.size()]);
}
/**
* @Description: 将提交来的词列表处理,去除停用词,返回非停用词列表 中文
* @author wangk
* @param words
* @return
* @date: 2019年5月6日 下午2:36:25
*/
public String[] removeCWords(String[] words) {
ArrayList<String> tokens = new ArrayList(Arrays.asList(words));
for(int i=0;i<tokens.size();i++) {
if(cStopWords.contains(tokens.get(i))) {
tokens.remove(i);
}
}
return (String[])tokens.toArray(new String[tokens.size()]);
}
}