|
|||||||||||||||||||
| Source file | Conditionals | Statements | Methods | TOTAL | |||||||||||||||
| ArgumentTokenizer.java | 84.2% | 85.5% | 100% | 85.5% |
|
||||||||||||||
| 1 | /*BEGIN_COPYRIGHT_BLOCK | |
| 2 | * | |
| 3 | * Copyright (c) 2001-2010, JavaPLT group at Rice University (drjava@rice.edu) | |
| 4 | * All rights reserved. | |
| 5 | * | |
| 6 | * Redistribution and use in source and binary forms, with or without | |
| 7 | * modification, are permitted provided that the following conditions are met: | |
| 8 | * * Redistributions of source code must retain the above copyright | |
| 9 | * notice, this list of conditions and the following disclaimer. | |
| 10 | * * Redistributions in binary form must reproduce the above copyright | |
| 11 | * notice, this list of conditions and the following disclaimer in the | |
| 12 | * documentation and/or other materials provided with the distribution. | |
| 13 | * * Neither the names of DrJava, the JavaPLT group, Rice University, nor the | |
| 14 | * names of its contributors may be used to endorse or promote products | |
| 15 | * derived from this software without specific prior written permission. | |
| 16 | * | |
| 17 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
| 18 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
| 19 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR | |
| 20 | * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR | |
| 21 | * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, | |
| 22 | * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, | |
| 23 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | |
| 24 | * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF | |
| 25 | * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING | |
| 26 | * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS | |
| 27 | * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
| 28 | * | |
| 29 | * This software is Open Source Initiative approved Open Source Software. | |
| 30 | * Open Source Initative Approved is a trademark of the Open Source Initiative. | |
| 31 | * | |
| 32 | * This file is part of DrJava. Download the current version of this project | |
| 33 | * from http://www.drjava.org/ or http://sourceforge.net/projects/drjava/ | |
| 34 | * | |
| 35 | * END_COPYRIGHT_BLOCK*/ | |
| 36 | ||
| 37 | package edu.rice.cs.util; | |
| 38 | ||
| 39 | import java.util.List; | |
| 40 | import java.util.LinkedList; | |
| 41 | ||
| 42 | /** | |
| 43 | * Utility class which can tokenize a String into a list of String arguments, | |
| 44 | * with behavior similar to parsing command line arguments to a program. | |
| 45 | * Quoted Strings are treated as single arguments, and escaped characters | |
| 46 | * are translated so that the tokenized arguments have the same meaning. | |
| 47 | * Since all methods are static, the class is declared abstract to prevent | |
| 48 | * instantiation. | |
| 49 | * @version $Id: ArgumentTokenizer.java 5175 2010-01-20 08:46:32Z mgricken $ | |
| 50 | */ | |
| 51 | public abstract class ArgumentTokenizer { | |
| 52 | private static final int NO_TOKEN_STATE = 0; | |
| 53 | private static final int NORMAL_TOKEN_STATE = 1; | |
| 54 | private static final int SINGLE_QUOTE_STATE = 2; | |
| 55 | private static final int DOUBLE_QUOTE_STATE = 3; | |
| 56 | ||
| 57 | /** Tokenizes the given String into String tokens | |
| 58 | * @param arguments A String containing one or more command-line style arguments to be tokenized. | |
| 59 | * @return A list of parsed and properly escaped arguments. | |
| 60 | */ | |
| 61 | 180 | public static List<String> tokenize(String arguments) { |
| 62 | 180 | return tokenize(arguments, false); |
| 63 | } | |
| 64 | ||
| 65 | /** Tokenizes the given String into String tokens. | |
| 66 | * @param arguments A String containing one or more command-line style arguments to be tokenized. | |
| 67 | * @param stringify whether or not to include escape special characters | |
| 68 | * @return A list of parsed and properly escaped arguments. | |
| 69 | */ | |
| 70 | 243 | public static List<String> tokenize(String arguments, boolean stringify) { |
| 71 | ||
| 72 | 243 | LinkedList<String> argList = new LinkedList<String>(); |
| 73 | 243 | StringBuilder currArg = new StringBuilder(); |
| 74 | 243 | boolean escaped = false; |
| 75 | 243 | int state = NO_TOKEN_STATE; // start in the NO_TOKEN_STATE |
| 76 | 243 | int len = arguments.length(); |
| 77 | ||
| 78 | // Loop over each character in the string | |
| 79 | 243 | for (int i = 0; i < len; i++) { |
| 80 | 686 | char c = arguments.charAt(i); |
| 81 | 686 | if (escaped) { |
| 82 | // Escaped state: just append the next character to the current arg. | |
| 83 | 17 | escaped = false; |
| 84 | 17 | currArg.append(c); |
| 85 | } | |
| 86 | else { | |
| 87 | 669 | switch(state) { |
| 88 | 55 | case SINGLE_QUOTE_STATE: |
| 89 | 55 | if (c == '\'') { |
| 90 | // Seen the close quote; continue this arg until whitespace is seen | |
| 91 | 12 | state = NORMAL_TOKEN_STATE; |
| 92 | } | |
| 93 | else { | |
| 94 | 43 | currArg.append(c); |
| 95 | } | |
| 96 | 55 | break; |
| 97 | 98 | case DOUBLE_QUOTE_STATE: |
| 98 | 98 | if (c == '"') { |
| 99 | // Seen the close quote; continue this arg until whitespace is seen | |
| 100 | 26 | state = NORMAL_TOKEN_STATE; |
| 101 | } | |
| 102 | 72 | else if (c == '\\') { |
| 103 | // Look ahead, and only escape quotes or backslashes | |
| 104 | 19 | i++; |
| 105 | 19 | char next = arguments.charAt(i); |
| 106 | 19 | if (next == '"' || next == '\\') { |
| 107 | 8 | currArg.append(next); |
| 108 | } | |
| 109 | else { | |
| 110 | 11 | currArg.append(c); |
| 111 | 11 | currArg.append(next); |
| 112 | } | |
| 113 | } | |
| 114 | else { | |
| 115 | 53 | currArg.append(c); |
| 116 | } | |
| 117 | 98 | break; |
| 118 | // case NORMAL_TOKEN_STATE: | |
| 119 | // if (Character.isWhitespace(c)) { | |
| 120 | // // Whitespace ends the token; start a new one | |
| 121 | // argList.add(currArg.toString()); | |
| 122 | // currArg = new StringBuffer(); | |
| 123 | // state = NO_TOKEN_STATE; | |
| 124 | // } | |
| 125 | // else if (c == '\\') { | |
| 126 | // // Backslash in a normal token: escape the next character | |
| 127 | // escaped = true; | |
| 128 | // } | |
| 129 | // else if (c == '\'') { | |
| 130 | // state = SINGLE_QUOTE_STATE; | |
| 131 | // } | |
| 132 | // else if (c == '"') { | |
| 133 | // state = DOUBLE_QUOTE_STATE; | |
| 134 | // } | |
| 135 | // else { | |
| 136 | // currArg.append(c); | |
| 137 | // } | |
| 138 | // break; | |
| 139 | 145 | case NO_TOKEN_STATE: |
| 140 | 371 | case NORMAL_TOKEN_STATE: |
| 141 | 516 | switch(c) { |
| 142 | 18 | case '\\': |
| 143 | 18 | escaped = true; |
| 144 | 18 | state = NORMAL_TOKEN_STATE; |
| 145 | 18 | break; |
| 146 | 12 | case '\'': |
| 147 | 12 | state = SINGLE_QUOTE_STATE; |
| 148 | 12 | break; |
| 149 | 27 | case '"': |
| 150 | 27 | state = DOUBLE_QUOTE_STATE; |
| 151 | 27 | break; |
| 152 | 459 | default: |
| 153 | 459 | if (!Character.isWhitespace(c)) { |
| 154 | 377 | currArg.append(c); |
| 155 | 377 | state = NORMAL_TOKEN_STATE; |
| 156 | } | |
| 157 | 82 | else if (state == NORMAL_TOKEN_STATE) { |
| 158 | // Whitespace ends the token; start a new one | |
| 159 | 82 | argList.add(currArg.toString()); |
| 160 | 82 | currArg = new StringBuilder(); |
| 161 | 82 | state = NO_TOKEN_STATE; |
| 162 | } | |
| 163 | } | |
| 164 | 516 | break; |
| 165 | 0 | default: |
| 166 | 0 | throw new IllegalStateException("ArgumentTokenizer state " + state + " is invalid!"); |
| 167 | } | |
| 168 | } | |
| 169 | } | |
| 170 | ||
| 171 | // If we're still escaped, put in the backslash | |
| 172 | 243 | if (escaped) { |
| 173 | 1 | currArg.append('\\'); |
| 174 | 1 | argList.add(currArg.toString()); |
| 175 | } | |
| 176 | // Close the last argument if we haven't yet | |
| 177 | 242 | else if (state != NO_TOKEN_STATE) { |
| 178 | 62 | argList.add(currArg.toString()); |
| 179 | } | |
| 180 | // Format each argument if we've been told to stringify them | |
| 181 | 243 | if (stringify) { |
| 182 | 37 | for (int i = 0; i < argList.size(); i++) { |
| 183 | 110 | argList.set(i, "\"" + _escapeQuotesAndBackslashes(argList.get(i)) + "\""); |
| 184 | } | |
| 185 | } | |
| 186 | 243 | return argList; |
| 187 | } | |
| 188 | ||
| 189 | /** Inserts backslashes before any occurrences of a backslash or | |
| 190 | * quote in the given string. Also converts any special characters | |
| 191 | * appropriately. | |
| 192 | */ | |
| 193 | 110 | protected static String _escapeQuotesAndBackslashes(String s) { |
| 194 | 110 | final StringBuilder buf = new StringBuilder(s); |
| 195 | ||
| 196 | // Walk backwards, looking for quotes or backslashes. | |
| 197 | // If we see any, insert an extra backslash into the buffer at | |
| 198 | // the same index. (By walking backwards, the index into the buffer | |
| 199 | // will remain correct as we change the buffer.) | |
| 200 | 110 | for (int i = s.length()-1; i >= 0; i--) { |
| 201 | 414 | char c = s.charAt(i); |
| 202 | 414 | if ((c == '\\') || (c == '"')) { |
| 203 | 19 | buf.insert(i, '\\'); |
| 204 | } | |
| 205 | // Replace any special characters with escaped versions | |
| 206 | 395 | else if (c == '\n') { |
| 207 | 0 | buf.deleteCharAt(i); |
| 208 | 0 | buf.insert(i, "\\n"); |
| 209 | } | |
| 210 | 395 | else if (c == '\t') { |
| 211 | 0 | buf.deleteCharAt(i); |
| 212 | 0 | buf.insert(i, "\\t"); |
| 213 | } | |
| 214 | 395 | else if (c == '\r') { |
| 215 | 0 | buf.deleteCharAt(i); |
| 216 | 0 | buf.insert(i, "\\r"); |
| 217 | } | |
| 218 | 395 | else if (c == '\b') { |
| 219 | 0 | buf.deleteCharAt(i); |
| 220 | 0 | buf.insert(i, "\\b"); |
| 221 | } | |
| 222 | 395 | else if (c == '\f') { |
| 223 | 0 | buf.deleteCharAt(i); |
| 224 | 0 | buf.insert(i, "\\f"); |
| 225 | } | |
| 226 | } | |
| 227 | 110 | return buf.toString(); |
| 228 | } | |
| 229 | } |
|
||||||||||