10.6 StreamTokenizer
10.6 StreamTokenizer
尽管
//: SortedWordCount.java
// Counts words in a file, outputs
// results in sorted form.
import java.io.*;
import java.util.*;
import c08.*; // Contains StrSortVector
class Counter {
private int i = 1;
int read() { return i; }
void increment() { i++; }
}
public class SortedWordCount {
private FileInputStream file;
private StreamTokenizer st;
private Hashtable counts = new Hashtable();
SortedWordCount(String filename)
throws FileNotFoundException {
try {
file = new FileInputStream(filename);
st = new StreamTokenizer(file);
st.ordinaryChar('.');
st.ordinaryChar('-');
} catch(FileNotFoundException e) {
System.out.println(
"Could not open " + filename);
throw e;
}
}
void cleanup() {
try {
file.close();
} catch(IOException e) {
System.out.println(
"file.close() unsuccessful");
}
}
void countWords() {
try {
while(st.nextToken() !=
StreamTokenizer.TT_EOF) {
String s;
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; // Already a String
break;
default: // single character in ttype
s = String.valueOf((char)st.ttype);
}
if(counts.containsKey(s))
((Counter)counts.get(s)).increment();
else
counts.put(s, new Counter());
}
} catch(IOException e) {
System.out.println(
"st.nextToken() unsuccessful");
}
}
Enumeration values() {
return counts.elements();
}
Enumeration keys() { return counts.keys(); }
Counter getCounter(String s) {
return (Counter)counts.get(s);
}
Enumeration sortedKeys() {
Enumeration e = counts.keys();
StrSortVector sv = new StrSortVector();
while(e.hasMoreElements())
sv.addElement((String)e.nextElement());
// This call forces a sort:
return sv.elements();
}
public static void main(String[] args) {
try {
SortedWordCount wc =
new SortedWordCount(args[0]);
wc.countWords();
Enumeration keys = wc.sortedKeys();
while(keys.hasMoreElements()) {
String key = (String)keys.nextElement();
System.out.println(key + ": "
+ wc.getCounter(key).read());
}
wc.cleanup();
} catch(Exception e) {
e.printStackTrace();
}
}
} ///:~
最好将结果按排序格式输出,但由于
为打开文件,使用了一个
在
找到一个记号后,会查询
在
10.6.1 StringTokenizer
尽管并不必要
可用
作为一个例子,下述程序将执行一个有限的句法分析,查询键短语序列,了解句子暗示的是快乐亦或悲伤的含义。
//: AnalyzeSentence.java
// Look for particular sequences
// within sentences.
import java.util.*;
public class AnalyzeSentence {
public static void main(String[] args) {
analyze("I am happy about this");
analyze("I am not happy about this");
analyze("I am not! I am happy");
analyze("I am sad about this");
analyze("I am not sad about this");
analyze("I am not! I am sad");
analyze("Are you happy about this?");
analyze("Are you sad about this?");
analyze("It's you! I am happy");
analyze("It's you! I am sad");
}
static StringTokenizer st;
static void analyze(String s) {
prt("\nnew sentence >> " + s);
boolean sad = false;
st = new StringTokenizer(s);
while (st.hasMoreTokens()) {
String token = next();
// Look until you find one of the
// two starting tokens:
if(!token.equals("I") &&
!token.equals("Are"))
continue; // Top of while loop
if(token.equals("I")) {
String tk2 = next();
if(!tk2.equals("am")) // Must be after I
break; // Out of while loop
else {
String tk3 = next();
if(tk3.equals("sad")) {
sad = true;
break; // Out of while loop
}
if (tk3.equals("not")) {
String tk4 = next();
if(tk4.equals("sad"))
break; // Leave sad false
if(tk4.equals("happy")) {
sad = true;
break;
}
}
}
}
if(token.equals("Are")) {
String tk2 = next();
if(!tk2.equals("you"))
break; // Must be after Are
String tk3 = next();
if(tk3.equals("sad"))
sad = true;
break; // Out of while loop
}
}
if(sad) prt("Sad detected");
}
static String next() {
if(st.hasMoreTokens()) {
String s = st.nextToken();
prt(s);
return s;
}
else
return "";
}
static void prt(String s) {
System.out.println(s);
}
} ///:~
对于准备分析的每个字串,我们进入一个
无论如何,只应将