com.fitbur.google.common.net.UrlEscapers Maven / Gradle / Ivy
/*
* Copyright (C) 2009 The Guava Authors
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in com.fitburpliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.com.fitbur/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.fitbur.google.com.fitburmon.net;
import com.fitbur.google.com.fitburmon.annotations.Beta;
import com.fitbur.google.com.fitburmon.annotations.GwtCompatible;
import com.fitbur.google.com.fitburmon.escape.Escaper;
/**
* {@code Escaper} instances suitable for strings to be included in particular
* sections of URLs.
*
* If the resulting URLs are inserted into an HTML or XML document, they will
* require additional escaping with {@link com.fitbur.google.com.fitburmon.html.HtmlEscapers}
* or {@link com.fitbur.google.com.fitburmon.xml.XmlEscapers}.
*
*
* @author David Beaumont
* @author Chris Povirk
* @since 15.0
*/
@Beta
@GwtCompatible
public final class UrlEscapers {
private UrlEscapers() {}
// For each xxxEscaper() method, please add links to external reference pages
// that are considered authoritative for the behavior of that escaper.
static final String URL_FORM_PARAMETER_OTHER_SAFE_CHARS = "-_.*";
static final String URL_PATH_OTHER_SAFE_CHARS_LACKING_PLUS =
"-._~" + // Unreserved characters.
"!$'()*,;&=" + // The subdelim characters (excluding '+').
"@:"; // The gendelim characters permitted in paths.
/**
* Returns an {@link Escaper} instance that escapes strings so they can be
* safely included in URL form parameter names
* and values. Escaping is performed with the UTF-8 character encoding.
* The caller is responsible for replacing any
* unpaired carriage return or line feed characters with a CR+LF pair on
* any non-file inputs before escaping them with this escaper.
*
*
When escaping a String, the following rules apply:
*
* - The alphanumeric characters "a" through "z", "A" through "Z" and "0"
* through "9" remain the same.
*
- The special characters ".", "-", "*", and "_" remain the same.
*
- The space character " " is converted into a plus sign "+".
*
- All other characters are converted into one or more bytes using UTF-8
* encoding and each byte is then represented by the 3-character string
* "%XY", where "XY" is the two-digit, uppercase, hexadecimal
* representation of the byte value.
*
*
* This escaper is suitable for escaping parameter names and values even
* when using the non-standard semicolon,
* rather than the ampersand, as a parameter com.fitburlimiter. Nevertheless, we
* recommend using the ampersand unless you must interoperate with systems
* that require semicolons.
*
*
Note: Unlike other escapers, URL escapers produce uppercase
* hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits
* for all percent-encodings."
*
*/
public static Escaper urlFormParameterEscaper() {
return URL_FORM_PARAMETER_ESCAPER;
}
private static final Escaper URL_FORM_PARAMETER_ESCAPER =
new PercentEscaper(URL_FORM_PARAMETER_OTHER_SAFE_CHARS, true);
/**
* Returns an {@link Escaper} instance that escapes strings so they can be
* safely included in URL path segments. The
* returned escaper escapes all non-ASCII characters, even though many of these are accepted in modern URLs.
* (If the escaper were to leave these
* characters unescaped, they would be escaped by the consumer at parse time,
* anyway.) Additionally, the escaper escapes the slash character ("/").
* While slashes are acceptable in URL paths, they are considered by the
* specification to be separators between "path segments." This implies that,
* if you wish for your path to contain slashes, you must escape each segment
* separately and then join them.
*
*
When escaping a String, the following rules apply:
*
* - The alphanumeric characters "a" through "z", "A" through "Z" and "0"
* through "9" remain the same.
*
- The unreserved characters ".", "-", "~", and "_" remain the same.
*
- The general com.fitburlimiters "@" and ":" remain the same.
*
- The subdelimiters "!", "$", "&", "'", "(", ")", "*", "+", ",", ";",
* and "=" remain the same.
*
- The space character " " is converted into %20.
*
- All other characters are converted into one or more bytes using UTF-8
* encoding and each byte is then represented by the 3-character string
* "%XY", where "XY" is the two-digit, uppercase, hexadecimal
* representation of the byte value.
*
*
* Note: Unlike other escapers, URL escapers produce uppercase
* hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits
* for all percent-encodings."
*/
public static Escaper urlPathSegmentEscaper() {
return URL_PATH_SEGMENT_ESCAPER;
}
private static final Escaper URL_PATH_SEGMENT_ESCAPER =
new PercentEscaper(URL_PATH_OTHER_SAFE_CHARS_LACKING_PLUS + "+", false);
/**
* Returns an {@link Escaper} instance that escapes strings so they can be
* safely included in a URL fragment. The
* returned escaper escapes all non-ASCII characters, even though many of these are accepted in modern URLs.
* (If the escaper were to leave these
* characters unescaped, they would be escaped by the consumer at parse time,
* anyway.)
*
*
When escaping a String, the following rules apply:
*
* - The alphanumeric characters "a" through "z", "A" through "Z" and "0"
* through "9" remain the same.
*
- The unreserved characters ".", "-", "~", and "_" remain the same.
*
- The general com.fitburlimiters "@" and ":" remain the same.
*
- The subdelimiters "!", "$", "&", "'", "(", ")", "*", "+", ",", ";",
* and "=" remain the same.
*
- The space character " " is converted into %20.
*
- Fragments allow unescaped "/" and "?", so they remain the same.
*
- All other characters are converted into one or more bytes using UTF-8
* encoding and each byte is then represented by the 3-character string
* "%XY", where "XY" is the two-digit, uppercase, hexadecimal
* representation of the byte value.
*
*
* Note: Unlike other escapers, URL escapers produce uppercase
* hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits
* for all percent-encodings."
*/
public static Escaper urlFragmentEscaper() {
return URL_FRAGMENT_ESCAPER;
}
private static final Escaper URL_FRAGMENT_ESCAPER =
new PercentEscaper(URL_PATH_OTHER_SAFE_CHARS_LACKING_PLUS + "+/?", false);
}