1 | /** |
2 | * |
3 | * Copyright (C) 2011 Cloud Conscious, LLC. <info@cloudconscious.com> |
4 | * |
5 | * ==================================================================== |
6 | * Licensed under the Apache License, Version 2.0 (the "License"); |
7 | * you may not use this file except in compliance with the License. |
8 | * You may obtain a copy of the License at |
9 | * |
10 | * http://www.apache.org/licenses/LICENSE-2.0 |
11 | * |
12 | * Unless required by applicable law or agreed to in writing, software |
13 | * distributed under the License is distributed on an "AS IS" BASIS, |
14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
15 | * See the License for the specific language governing permissions and |
16 | * limitations under the License. |
17 | * ==================================================================== |
18 | */ |
19 | package org.jclouds.util; |
20 | |
21 | import static com.google.common.base.Preconditions.checkNotNull; |
22 | import static com.google.common.io.ByteStreams.toByteArray; |
23 | import static com.google.common.io.Closeables.closeQuietly; |
24 | import static org.jclouds.util.Patterns.CHAR_TO_ENCODED_PATTERN; |
25 | import static org.jclouds.util.Patterns.CHAR_TO_PATTERN; |
26 | import static org.jclouds.util.Patterns.PLUS_PATTERN; |
27 | import static org.jclouds.util.Patterns.STAR_PATTERN; |
28 | import static org.jclouds.util.Patterns.TOKEN_TO_PATTERN; |
29 | import static org.jclouds.util.Patterns.URL_ENCODED_PATTERN; |
30 | import static org.jclouds.util.Patterns._7E_PATTERN; |
31 | |
32 | import java.io.ByteArrayInputStream; |
33 | import java.io.IOException; |
34 | import java.io.InputStream; |
35 | import java.io.UnsupportedEncodingException; |
36 | import java.net.URLDecoder; |
37 | import java.net.URLEncoder; |
38 | import java.util.Map; |
39 | import java.util.Map.Entry; |
40 | import java.util.regex.Matcher; |
41 | import java.util.regex.Pattern; |
42 | |
43 | import javax.annotation.Resource; |
44 | |
45 | import org.jclouds.logging.Logger; |
46 | |
47 | import com.google.common.base.Charsets; |
48 | |
49 | /** |
50 | * |
51 | * |
52 | * @author Adrian Cole |
53 | */ |
54 | public class Strings2 { |
55 | |
56 | /** |
57 | * Web browsers do not always handle '+' characters well, use the well-supported '%20' instead. |
58 | */ |
59 | public static String urlEncode(String in, char... skipEncode) { |
60 | if (isUrlEncoded(in)) |
61 | return in; |
62 | try { |
63 | String returnVal = URLEncoder.encode(in, "UTF-8"); |
64 | returnVal = Strings2.replaceAll(returnVal, '+', PLUS_PATTERN, "%20"); |
65 | returnVal = Strings2.replaceAll(returnVal, '*', STAR_PATTERN, "%2A"); |
66 | returnVal = Strings2.replaceAll(returnVal, _7E_PATTERN, "~"); |
67 | for (char c : skipEncode) { |
68 | returnVal = Strings2.replaceAll(returnVal, CHAR_TO_ENCODED_PATTERN.get(c), c + ""); |
69 | } |
70 | return returnVal; |
71 | } catch (UnsupportedEncodingException e) { |
72 | throw new IllegalStateException("Bad encoding on input: " + in, e); |
73 | } |
74 | } |
75 | |
76 | public static boolean isUrlEncoded(String in) { |
77 | return URL_ENCODED_PATTERN.matcher(in).matches(); |
78 | } |
79 | |
80 | public static String urlDecode(String in) { |
81 | try { |
82 | return URLDecoder.decode(in, "UTF-8"); |
83 | } catch (UnsupportedEncodingException e) { |
84 | throw new IllegalStateException("Bad encoding on input: " + in, e); |
85 | } |
86 | } |
87 | |
88 | public static String replaceTokens(String value, Iterable<Entry<String, String>> tokenValues) { |
89 | for (Entry<String, String> tokenValue : tokenValues) { |
90 | value = Strings2.replaceAll(value, TOKEN_TO_PATTERN.get(tokenValue.getKey()), tokenValue.getValue()); |
91 | } |
92 | return value; |
93 | } |
94 | |
95 | public static String replaceAll(String returnVal, Pattern pattern, String replace) { |
96 | Matcher m = pattern.matcher(returnVal); |
97 | returnVal = m.replaceAll(replace); |
98 | return returnVal; |
99 | } |
100 | |
101 | public static String replaceAll(String input, char ifMatch, Pattern pattern, String replacement) { |
102 | if (input.indexOf(ifMatch) != -1) { |
103 | input = pattern.matcher(input).replaceAll(replacement); |
104 | } |
105 | return input; |
106 | } |
107 | |
108 | public static String replaceAll(String input, char match, String replacement) { |
109 | if (input.indexOf(match) != -1) { |
110 | input = CHAR_TO_PATTERN.get(match).matcher(input).replaceAll(replacement); |
111 | } |
112 | return input; |
113 | } |
114 | |
115 | public static final String UTF8_ENCODING = "UTF-8"; |
116 | |
117 | public static String toStringAndClose(InputStream input) throws IOException { |
118 | checkNotNull(input, "input"); |
119 | try { |
120 | return new String(toByteArray(input), Charsets.UTF_8); |
121 | } catch (IOException e) { |
122 | logger.warn(e, "Failed to read from stream"); |
123 | return null; |
124 | } catch (NullPointerException e) { |
125 | return null; |
126 | } finally { |
127 | closeQuietly(input); |
128 | } |
129 | } |
130 | |
131 | public static InputStream toInputStream(String in) { |
132 | return new ByteArrayInputStream(in.getBytes(Charsets.UTF_8)); |
133 | } |
134 | |
135 | /** |
136 | * Encode the given string with the given encoding, if possible. If the encoding fails with |
137 | * {@link UnsupportedEncodingException}, log a warning and fall back to the system's default |
138 | * encoding. |
139 | * |
140 | * @param str |
141 | * what to encode |
142 | * @param charsetName |
143 | * the name of a supported {@link java.nio.charset.Charset </code>charset<code>} |
144 | * @return properly encoded String. |
145 | */ |
146 | public static byte[] encodeString(String str, String charsetName) { |
147 | try { |
148 | return str.getBytes(charsetName); |
149 | } catch (UnsupportedEncodingException e) { |
150 | logger.warn(e, "Failed to encode string to bytes with encoding " + charsetName |
151 | + ". Falling back to system's default encoding"); |
152 | return str.getBytes(); |
153 | } |
154 | } |
155 | |
156 | @Resource |
157 | private static Logger logger = Logger.NULL; |
158 | |
159 | /** |
160 | * Encode the given string with the UTF-8 encoding, the sane default. In the very unlikely event |
161 | * the encoding fails with {@link UnsupportedEncodingException}, log a warning and fall back to |
162 | * the system's default encoding. |
163 | * |
164 | * @param str |
165 | * what to encode |
166 | * @return properly encoded String. |
167 | */ |
168 | public static byte[] encodeString(String str) { |
169 | return encodeString(str, UTF8_ENCODING); |
170 | } |
171 | |
172 | /** |
173 | * replaces tokens that are expressed as <code>{token}</code> |
174 | * |
175 | * <p/> |
176 | * ex. if input is "hello {where}"<br/> |
177 | * and replacements is "where" -> "world" <br/> |
178 | * then replaceTokens returns "hello world" |
179 | * |
180 | * @param input |
181 | * source to replace |
182 | * @param replacements |
183 | * token/value pairs |
184 | */ |
185 | public static String replaceTokens(String input, Map<String, String> replacements) { |
186 | Matcher matcher = Patterns.TOKEN_PATTERN.matcher(input); |
187 | StringBuilder builder = new StringBuilder(); |
188 | int i = 0; |
189 | while (matcher.find()) { |
190 | String replacement = replacements.get(matcher.group(1)); |
191 | builder.append(input.substring(i, matcher.start())); |
192 | if (replacement == null) |
193 | builder.append(matcher.group(0)); |
194 | else |
195 | builder.append(replacement); |
196 | i = matcher.end(); |
197 | } |
198 | builder.append(input.substring(i, input.length())); |
199 | return builder.toString(); |
200 | } |
201 | |
202 | } |