com.google.api.client.util.escape.CharEscapers Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of google-http-client Show documentation
Show all versions of google-http-client Show documentation
Google HTTP Client Library for Java. Functionality that works on all supported Java platforms,
including Java 5 (or higher) desktop (SE) and web (EE), Android, and Google App Engine.
/*
* Copyright (c) 2010 Google Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
* in compliance with the License. You may obtain a copy of the License at
*
* http://www.apache.org/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.google.api.client.util.escape;
import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
/**
* Utility functions for dealing with {@code CharEscaper}s, and some commonly used
* {@code CharEscaper} instances.
*
* @since 1.0
*/
public final class CharEscapers {
private static final Escaper URI_ESCAPER =
new PercentEscaper(PercentEscaper.SAFECHARS_URLENCODER, true);
private static final Escaper URI_PATH_ESCAPER =
new PercentEscaper(PercentEscaper.SAFEPATHCHARS_URLENCODER, false);
private static final Escaper URI_RESERVED_ESCAPER =
new PercentEscaper(PercentEscaper.SAFE_PLUS_RESERVED_CHARS_URLENCODER, false);
private static final Escaper URI_USERINFO_ESCAPER =
new PercentEscaper(PercentEscaper.SAFEUSERINFOCHARS_URLENCODER, false);
private static final Escaper URI_QUERY_STRING_ESCAPER =
new PercentEscaper(PercentEscaper.SAFEQUERYSTRINGCHARS_URLENCODER, false);
/**
* Escapes the string value so it can be safely included in URIs. For details on escaping URIs,
* see RFC 3986 - section 2.4.
*
*
* When encoding 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.
*
*
*
*
* Note: Unlike other escapers, URI escapers produce uppercase hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits for all
* percent-encodings."
*
*
*
* This escaper has identical behavior to (but is potentially much faster than):
*
* - {@link java.net.URLEncoder#encode(String, String)} with the encoding name "UTF-8"
*
*
*/
public static String escapeUri(String value) {
return URI_ESCAPER.escape(value);
}
/**
* Percent-decodes a US-ASCII string into a Unicode string. UTF-8 encoding is used to determine
* what characters are represented by any consecutive sequences of the form "%XX".
*
*
* This replaces each occurrence of '+' with a space, ' '. So this method should not be used for
* non application/x-www-form-urlencoded strings such as host and path.
*
*
* @param uri a percent-encoded US-ASCII string
* @return a Unicode string
*/
public static String decodeUri(String uri) {
try {
return URLDecoder.decode(uri, "UTF-8");
} catch (UnsupportedEncodingException e) {
// UTF-8 encoding guaranteed to be supported by JVM
throw new RuntimeException(e);
}
}
/**
* Escapes the string value so it can be safely included in URI path segments. For details on
* escaping URIs, see RFC 3986 - section
* 2.4.
*
*
* When encoding 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 delimiters "@" and ":" remain the same.
*
- The subdelimiters "!", "$", "&", "'", "(", ")", "*", ",", ";", and "=" remain the same.
*
- The space character " " is converted into %20.
*
- All other characters are converted into one or more bytes using UTF-8 encoding and each
* byte is then represented by the 3-character string "%XY", where "XY" is the two-digit,
* uppercase, hexadecimal representation of the byte value.
*
*
*
*
* Note: Unlike other escapers, URI escapers produce uppercase hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits for all
* percent-encodings."
*
*/
public static String escapeUriPath(String value) {
return URI_PATH_ESCAPER.escape(value);
}
/**
* Escapes a URI path but retains all reserved characters, including all general delimiters.
* That is the same as {@link #escapeUriPath(String)} except that it keeps '?', '+', and '/'
* unescaped.
*/
public static String escapeUriPathWithoutReserved(String value) {
return URI_RESERVED_ESCAPER.escape(value);
}
/**
* Escapes the string value so it can be safely included in URI user info part. For details on
* escaping URIs, see RFC 3986 - section
* 2.4.
*
*
* When encoding a String, the following rules apply:
*
* - The alphanumeric characters "a" through "z", "A" through "Z" and "0" through "9" remain the
* same.
*
- The unreserved characters ".", "-", "~", and "_" remain the same.
*
- The general delimiter ":" remains the same.
*
- The subdelimiters "!", "$", "&", "'", "(", ")", "*", ",", ";", 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, URI escapers produce uppercase hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits for all
* percent-encodings."
*
*
* @since 1.15
*/
public static String escapeUriUserInfo(String value) {
return URI_USERINFO_ESCAPER.escape(value);
}
/**
* Escapes the string value so it can be safely included in URI query string segments. When the
* query string consists of a sequence of name=value pairs separated by &, the names and
* values should be individually encoded. If you escape an entire query string in one pass with
* this escaper, then the "=" and "&" characters used as separators will also be escaped.
*
*
* This escaper is also suitable for escaping fragment identifiers.
*
*
*
* For details on escaping URIs, see RFC
* 3986 - section 2.4.
*
*
*
* When encoding 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 delimiters "@" and ":" remain the same.
*
- The path delimiters "/" and "?" remain the same.
*
- The subdelimiters "!", "$", "'", "(", ")", "*", ",", and ";", remain the same.
*
- The space character " " is converted into %20.
*
- The equals sign "=" is converted into %3D.
*
- The ampersand "&" is converted into %26.
*
- 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, URI escapers produce uppercase hexadecimal sequences. From
* RFC 3986:
* "URI producers and normalizers should use uppercase hexadecimal digits for all
* percent-encodings."
*
*/
public static String escapeUriQuery(String value) {
return URI_QUERY_STRING_ESCAPER.escape(value);
}
private CharEscapers() {
}
}