Coverage Summary for Class: UrlEscapers (com.google.common.net)

Class Class, % Method, % Line, %
UrlEscapers 0% (0/1) 0% (0/5) 0% (0/7)


1 /* 2  * Copyright (C) 2009 The Guava Authors 3  * 4  * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except 5  * in compliance with the License. You may obtain a copy of the License at 6  * 7  * http://www.apache.org/licenses/LICENSE-2.0 8  * 9  * Unless required by applicable law or agreed to in writing, software distributed under the License 10  * is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express 11  * or implied. See the License for the specific language governing permissions and limitations under 12  * the License. 13  */ 14  15 package com.google.common.net; 16  17 import com.google.common.annotations.GwtCompatible; 18 import com.google.common.escape.Escaper; 19  20 /** 21  * {@code Escaper} instances suitable for strings to be included in particular sections of URLs. 22  * 23  * <p>If the resulting URLs are inserted into an HTML or XML document, they will require additional 24  * escaping with {@link com.google.common.html.HtmlEscapers} or {@link 25  * com.google.common.xml.XmlEscapers}. 26  * 27  * @author David Beaumont 28  * @author Chris Povirk 29  * @since 15.0 30  */ 31 @GwtCompatible 32 @ElementTypesAreNonnullByDefault 33 public final class UrlEscapers { 34  private UrlEscapers() {} 35  36  // For each xxxEscaper() method, please add links to external reference pages 37  // that are considered authoritative for the behavior of that escaper. 38  39  static final String URL_FORM_PARAMETER_OTHER_SAFE_CHARS = "-_.*"; 40  41  static final String URL_PATH_OTHER_SAFE_CHARS_LACKING_PLUS = 42  "-._~" // Unreserved characters. 43  + "!$'()*,;&=" // The subdelim characters (excluding '+'). 44  + "@:"; // The gendelim characters permitted in paths. 45  46  /** 47  * Returns an {@link Escaper} instance that escapes strings so they can be safely included in <a 48  * href="https://goo.gl/MplK6I">URL form parameter names and values</a>. Escaping is performed 49  * with the UTF-8 character encoding. The caller is responsible for <a 50  * href="https://goo.gl/9EfkM1">replacing any unpaired carriage return or line feed characters 51  * with a CR+LF pair</a> on any non-file inputs before escaping them with this escaper. 52  * 53  * <p>When escaping a String, the following rules apply: 54  * 55  * <ul> 56  * <li>The alphanumeric characters "a" through "z", "A" through "Z" and "0" through "9" remain 57  * the same. 58  * <li>The special characters ".", "-", "*", and "_" remain the same. 59  * <li>The space character " " is converted into a plus sign "+". 60  * <li>All other characters are converted into one or more bytes using UTF-8 encoding and each 61  * byte is then represented by the 3-character string "%XY", where "XY" is the two-digit, 62  * uppercase, hexadecimal representation of the byte value. 63  * </ul> 64  * 65  * <p>This escaper is suitable for escaping parameter names and values even when <a 66  * href="https://goo.gl/utn6M">using the non-standard semicolon</a>, rather than the ampersand, as 67  * a parameter delimiter. Nevertheless, we recommend using the ampersand unless you must 68  * interoperate with systems that require semicolons. 69  * 70  * <p><b>Note:</b> Unlike other escapers, URL escapers produce <a 71  * href="https://url.spec.whatwg.org/#percent-encode">uppercase</a> hexadecimal sequences. 72  * 73  */ 74  public static Escaper urlFormParameterEscaper() { 75  return URL_FORM_PARAMETER_ESCAPER; 76  } 77  78  private static final Escaper URL_FORM_PARAMETER_ESCAPER = 79  new PercentEscaper(URL_FORM_PARAMETER_OTHER_SAFE_CHARS, true); 80  81  /** 82  * Returns an {@link Escaper} instance that escapes strings so they can be safely included in <a 83  * href="https://goo.gl/m2MIf0">URL path segments</a>. The returned escaper escapes all non-ASCII 84  * characters, even though <a href="https://goo.gl/e7E0In">many of these are accepted in modern 85  * URLs</a>. (<a href="https://goo.gl/jfVxXW">If the escaper were to leave these characters 86  * unescaped, they would be escaped by the consumer at parse time, anyway.</a>) Additionally, the 87  * escaper escapes the slash character ("/"). While slashes are acceptable in URL paths, they are 88  * considered by the specification to be separators between "path segments." This implies that, if 89  * you wish for your path to contain slashes, you must escape each segment separately and then 90  * join them. 91  * 92  * <p>When escaping a String, the following rules apply: 93  * 94  * <ul> 95  * <li>The alphanumeric characters "a" through "z", "A" through "Z" and "0" through "9" remain 96  * the same. 97  * <li>The unreserved characters ".", "-", "~", and "_" remain the same. 98  * <li>The general delimiters "@" and ":" remain the same. 99  * <li>The subdelimiters "!", "$", "&amp;", "'", "(", ")", "*", "+", ",", ";", and "=" remain 100  * the same. 101  * <li>The space character " " is converted into %20. 102  * <li>All other characters are converted into one or more bytes using UTF-8 encoding and each 103  * byte is then represented by the 3-character string "%XY", where "XY" is the two-digit, 104  * uppercase, hexadecimal representation of the byte value. 105  * </ul> 106  * 107  * <p><b>Note:</b> Unlike other escapers, URL escapers produce <a 108  * href="https://url.spec.whatwg.org/#percent-encode">uppercase</a> hexadecimal sequences. 109  */ 110  public static Escaper urlPathSegmentEscaper() { 111  return URL_PATH_SEGMENT_ESCAPER; 112  } 113  114  private static final Escaper URL_PATH_SEGMENT_ESCAPER = 115  new PercentEscaper(URL_PATH_OTHER_SAFE_CHARS_LACKING_PLUS + "+", false); 116  117  /** 118  * Returns an {@link Escaper} instance that escapes strings so they can be safely included in a <a 119  * href="https://goo.gl/xXEq4p">URL fragment</a>. The returned escaper escapes all non-ASCII 120  * characters, even though <a href="https://goo.gl/e7E0In">many of these are accepted in modern 121  * URLs</a>. 122  * 123  * <p>When escaping a String, the following rules apply: 124  * 125  * <ul> 126  * <li>The alphanumeric characters "a" through "z", "A" through "Z" and "0" through "9" remain 127  * the same. 128  * <li>The unreserved characters ".", "-", "~", and "_" remain the same. 129  * <li>The general delimiters "@" and ":" remain the same. 130  * <li>The subdelimiters "!", "$", "&amp;", "'", "(", ")", "*", "+", ",", ";", and "=" remain 131  * the same. 132  * <li>The space character " " is converted into %20. 133  * <li>Fragments allow unescaped "/" and "?", so they remain the same. 134  * <li>All other characters are converted into one or more bytes using UTF-8 encoding and each 135  * byte is then represented by the 3-character string "%XY", where "XY" is the two-digit, 136  * uppercase, hexadecimal representation of the byte value. 137  * </ul> 138  * 139  * <p><b>Note:</b> Unlike other escapers, URL escapers produce <a 140  * href="https://url.spec.whatwg.org/#percent-encode">uppercase</a> hexadecimal sequences. 141  */ 142  public static Escaper urlFragmentEscaper() { 143  return URL_FRAGMENT_ESCAPER; 144  } 145  146  private static final Escaper URL_FRAGMENT_ESCAPER = 147  new PercentEscaper(URL_PATH_OTHER_SAFE_CHARS_LACKING_PLUS + "+/?", false); 148 }