| 1 |
/******************************************************************************* |
| 2 |
* Copyright (c) 2009, 2017 IBM Corporation and others. |
| 3 |
* All rights reserved. |
| 4 |
* This program and the accompanying materials are made available under the |
| 5 |
* terms of the Eclipse Public License 2.0 which accompanies this distribution, |
| 6 |
t https://www.eclipse.org/legal/epl-2.0/ |
| 7 |
t |
| 8 |
t SPDX-License-Identifier: EPL-2.0 |
| 9 |
* |
| 10 |
* Contributors: IBM Corporation - initial API and implementation |
| 11 |
******************************************************************************/ |
| 12 |
|
| 13 |
package org.eclipse.equinox.internal.p2.publisher; |
| 14 |
|
| 15 |
import java.io.*; |
| 16 |
import java.util.Enumeration; |
| 17 |
import java.util.NoSuchElementException; |
| 18 |
|
| 19 |
/** |
| 20 |
* Tokenzier which supports quoting using '"' |
| 21 |
* The resulting tokens will not contain the quote character '"' unless it was escaped '\"' |
| 22 |
*/ |
| 23 |
public class QuotedTokenizer implements Enumeration<String> { |
| 24 |
private StreamTokenizer tokenizer = null; |
| 25 |
|
| 26 |
/** |
| 27 |
* Default delimiter is whitespace characters |
| 28 |
* @param str - String to be tokenized |
| 29 |
*/ |
| 30 |
public QuotedTokenizer(String str) { |
| 31 |
this(str, null); |
| 32 |
} |
| 33 |
|
| 34 |
/** |
| 35 |
* Tokenize based on the given delimiters. The quote character '"' can not be |
| 36 |
* used as a delimiter. |
| 37 |
* @param str - String to be tokenized |
| 38 |
* @param delim - delimiter characters |
| 39 |
* @throws IllegalArgumentException if delim contains the quote character '"' |
| 40 |
*/ |
| 41 |
public QuotedTokenizer(String str, String delim) { |
| 42 |
if (delim != null && delim.indexOf('"') > -1) |
| 43 |
throw new IllegalArgumentException(); |
| 44 |
|
| 45 |
StringReader reader = new StringReader(str); |
| 46 |
tokenizer = new StreamTokenizer(reader); |
| 47 |
|
| 48 |
tokenizer.resetSyntax(); |
| 49 |
if (delim == null) |
| 50 |
tokenizer.ordinaryChars(0, 0x20); |
| 51 |
else |
| 52 |
tokenizer.wordChars(0, 0x20); |
| 53 |
tokenizer.wordChars(0x21, 0xFF); //characters > 0xFF are also word chars |
| 54 |
tokenizer.quoteChar('"'); |
| 55 |
|
| 56 |
if (delim != null) { |
| 57 |
for (int i = 0; i < delim.length(); i++) { |
| 58 |
tokenizer.ordinaryChar(delim.charAt(i)); |
| 59 |
} |
| 60 |
} |
| 61 |
} |
| 62 |
|
| 63 |
/** |
| 64 |
* Test to see if more tokens are available |
| 65 |
* @return true if there is another token |
| 66 |
*/ |
| 67 |
public boolean hasMoreTokens() { |
| 68 |
return (token(null) != StreamTokenizer.TT_EOF); |
| 69 |
} |
| 70 |
|
| 71 |
/** |
| 72 |
* Return the next token, |
| 73 |
* @return the next token |
| 74 |
* @throws NoSuchElementException if there are no more tokens |
| 75 |
*/ |
| 76 |
public String nextToken() { |
| 77 |
StringBuffer buffer = new StringBuffer(10); |
| 78 |
int tokenType = token(buffer); |
| 79 |
|
| 80 |
if (tokenType == StreamTokenizer.TT_EOF) |
| 81 |
throw new NoSuchElementException(); |
| 82 |
|
| 83 |
return buffer.toString(); |
| 84 |
} |
| 85 |
|
| 86 |
/** |
| 87 |
* Get the next token, or check that there is a next token |
| 88 |
* @param buffer to hold the token, or null if we just want to know if there is one |
| 89 |
*/ |
| 90 |
private int token(StringBuffer buffer) { |
| 91 |
int tokenType = 0; |
| 92 |
int next = 0; |
| 93 |
|
| 94 |
get_token: while (true) { |
| 95 |
try { |
| 96 |
tokenType = tokenizer.nextToken(); |
| 97 |
} catch (IOException e) { |
| 98 |
tokenType = StreamTokenizer.TT_EOF; |
| 99 |
} |
| 100 |
switch (tokenType) { |
| 101 |
case StreamTokenizer.TT_WORD : |
| 102 |
case '"' : |
| 103 |
if (buffer == null) { |
| 104 |
//we just wanted to know if there was something coming |
| 105 |
tokenizer.pushBack(); |
| 106 |
return tokenType; |
| 107 |
} |
| 108 |
buffer.append(tokenizer.sval); |
| 109 |
|
| 110 |
// peek at the next token, |
| 111 |
try { |
| 112 |
next = tokenizer.nextToken(); |
| 113 |
tokenizer.pushBack(); |
| 114 |
} catch (IOException e) { |
| 115 |
next = StreamTokenizer.TT_EOF; |
| 116 |
} |
| 117 |
|
| 118 |
//if the next token is a quote, it is still this token, otherwise we are done |
| 119 |
if (next == '"') |
| 120 |
continue; |
| 121 |
break get_token; |
| 122 |
case StreamTokenizer.TT_EOF : |
| 123 |
break get_token; |
| 124 |
default : |
| 125 |
//ordinary char from delim, if we have something we are done, otherwise keep looking for a token |
| 126 |
if (buffer != null && buffer.length() > 0) |
| 127 |
break get_token; |
| 128 |
continue; |
| 129 |
} |
| 130 |
} |
| 131 |
return tokenType; |
| 132 |
} |
| 133 |
|
| 134 |
@Override |
| 135 |
public boolean hasMoreElements() { |
| 136 |
return hasMoreTokens(); |
| 137 |
} |
| 138 |
|
| 139 |
@Override |
| 140 |
public String nextElement() { |
| 141 |
return nextToken(); |
| 142 |
} |
| 143 |
} |