AppletTalk.com

giugy · Guest

Hi,sorry for my english but I don't speak it very well....

Someone knows where I can find the Keyword Extractor source code
written in java? A software that analyzes a text and extract the
keyword of the text (the most present words in the text....for example
the word "hello" is present forty times,the word "thanks" is present
thirty times....).

I need to see the software's source code written in java in order to
understand as it works....

Thaks,bye

glen herrmannsfeldt · Guest

giugy wrote:

giugy · Guest

Yes, I have found a code like this....

import java.io.*;
import java.util.*;

class Counter implements Comparable {
private String word;
private int count;
public Counter(String word) {
this.word = word;
count = 1;
}
public void increment() { count++; }
public String toString() {
return "\n" + word + " [" + count + "]";
}
public boolean equals(Object obj) {
return obj instanceof Counter &&
((Counter)obj).word.equals(word);
}
public int hashCode() {
return word.hashCode();
}
public int compareTo(Object o) {
return word.compareTo(((Counter)o).word);
}
}

class CounterSet extends AbstractSet {
private Map set = new TreeMap();
public void addOrIncrement(String s) {
Counter c = new Counter(s);
if (set.containsKey(c))
((Counter)set.get(c)).increment();
else
set.put(c, c);
}
public Iterator iterator() {
return set.keySet().iterator();
}
public int size() {
return set.size();
}
public String toString() {
return set.keySet().toString();
}
}

class WordCount {
private FileReader file;
private StreamTokenizer st;

private CounterSet counts = new CounterSet();
WordCount(String filename)
throws FileNotFoundException {
try {
file = new FileReader(filename);
st = new StreamTokenizer(
new BufferedReader(file));
st.ordinaryChar('.');
st.ordinaryChar('-');
st.lowerCaseMode(true);

} catch(FileNotFoundException e) {
System.err.println(
"Could not open " + filename);
throw e;
}
}
void cleanup() {
try {
file.close();
} catch(IOException e) {
System.err.println(
"file.close() unsuccessful");
}
}
void countWords() {
try {
while(st.nextToken() !=
StreamTokenizer.TT_EOF) {
String s = "a";
switch(st.ttype) {
case StreamTokenizer.TT_EOL:
s = new String("EOL");
break;

case StreamTokenizer.TT_NUMBER:
// s = Double.toString(st.nval);
break;

case StreamTokenizer.TT_WORD:
s = st.sval;
break;
default: // single character in ttype
s = String.valueOf((char)st.ttype);
}

if(s.length() > 3)
counts.addOrIncrement(s);
}
} catch(IOException e) {
System.err.println(
"st.nextToken() unsuccessful");
}
}
public Iterator iterator() {
return counts.iterator();
}
public String toString() {
return counts.toString();
}
}

public class KeyWordExtractor {
public static void main(String[] args)
throws FileNotFoundException {
for(int i = 0; i < args.length; i++){
WordCount wc = new WordCount(args[i]);
wc.countWords();
System.out.println("WORD = " + wc);
wc.cleanup();
}
}
}

and it give me to occurrency of every world in the text...in example if
i give in input a text like (a stupid example) "java function java
library function java" in output I obtain WORD = [function[2] ,
java[3] , library[1]] ....that are the occurrences of the word in the
text,but my problem is that I need in output not all the word of the
text...but only the the word that appears many times in the text...in
this case java that is the keyword of the text....WORD = [java]

I know that there is still little code to write,but I do not know well
java and so I don't succeed to write it!!!
Please Help me....THANKS!!!

glen herrmannsfeldt ha scritto:

giugy · Guest

Yes, I have found a code like this....

import java.io.*;
import java.util.*;

class Counter implements Comparable {
private String word;
private int count;
public Counter(String word) {
this.word = word;
count = 1;
}
public void increment() { count++; }
public String toString() {
return "\n" + word + " [" + count + "]";
}
public boolean equals(Object obj) {
return obj instanceof Counter &&
((Counter)obj).word.equals(word);
}
public int hashCode() {
return word.hashCode();
}
public int compareTo(Object o) {
return word.compareTo(((Counter)o).word);
}
}

class CounterSet extends AbstractSet {
private Map set = new TreeMap();
public void addOrIncrement(String s) {
Counter c = new Counter(s);
if (set.containsKey(c))
((Counter)set.get(c)).increment();
else
set.put(c, c);
}
public Iterator iterator() {
return set.keySet().iterator();
}
public int size() {
return set.size();
}
public String toString() {
return set.keySet().toString();
}
}

class WordCount {
private FileReader file;
private StreamTokenizer st;

private CounterSet counts = new CounterSet();
WordCount(String filename)
throws FileNotFoundException {
try {
file = new FileReader(filename);
st = new StreamTokenizer(
new BufferedReader(file));
st.ordinaryChar('.');
st.ordinaryChar('-');
st.lowerCaseMode(true);

} catch(FileNotFoundException e) {
System.err.println(
"Could not open " + filename);
throw e;
}
}
void cleanup() {
try {
file.close();
} catch(IOException e) {
System.err.println(
"file.close() unsuccessful");
}
}
void countWords() {
try {
while(st.nextToken() !=
StreamTokenizer.TT_EOF) {
String s = "a";
switch(st.ttype) {
case StreamTokenizer.TT_EOL:
s = new String("EOL");
break;

case StreamTokenizer.TT_NUMBER:
// s = Double.toString(st.nval);
break;

case StreamTokenizer.TT_WORD:
s = st.sval;
break;
default: // single character in ttype
s = String.valueOf((char)st.ttype);
}

if(s.length() > 3)
counts.addOrIncrement(s);
}
} catch(IOException e) {
System.err.println(
"st.nextToken() unsuccessful");
}
}
public Iterator iterator() {
return counts.iterator();
}
public String toString() {
return counts.toString();
}
}

public class KeyWordExtractor {
public static void main(String[] args)
throws FileNotFoundException {
for(int i = 0; i < args.length; i++){
WordCount wc = new WordCount(args[i]);
wc.countWords();
System.out.println("WORD = " + wc);
wc.cleanup();
}
}
}

and it give me to occurrency of every world in the text...in example if
i give in input a text like (a stupid example) "java function java
library function java" in output I obtain WORD = [function[2] ,
java[3] , library[1]] ....that are the occurrences of the word in the
text,but my problem is that I need in output not all the word of the
text...but only the the word that appears many times in the text...in
this case java that is the keyword of the text....WORD = [java]

I know that there is still little code to write,but I do not know well
java and so I don't succeed to write it!!!
Please Help me....THANKS!!!

glen herrmannsfeldt ha scritto:

glen herrmannsfeldt · Guest

giugy wrote:

giugy · Guest

Sorry but maybe I make a stupid errore....if I change
return "\n" + word + " [" + count + "]";
with
return count=" "+word;

I obtain an error like this "found: java.lang.String required: int" ,
because count is an it and word is a string and the function required
gives back a String....how can i do?

glen herrmannsfeldt ha scritto:

giugy · Guest

Sorry but maybe I make a stupid errore....if I change
return "\n" + word + " [" + count + "]";
with
return count=" "+word;

I obtain an error like this "found: java.lang.String required: int" ,
because count is an it and word is a string and the function required
gives back a String....how can i do?

glen herrmannsfeldt ha scritto:

giugy · Guest

Sorry but maybe I make a stupid errore....if I change
return "\n" + word + " [" + count + "]";
with
return count=" "+word;

I obtain an error like this "found: java.lang.String required: int" ,
because count is an it and word is a string and the function required
gives back a String....how can i do?

glen herrmannsfeldt ha scritto:

glen herrmannsfeldt · Guest

giugy wrote: