com.abubusoft.kripton.escape.StringEscapeUtils Maven / Gradle / Ivy
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You 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.abubusoft.kripton.escape;
import com.abubusoft.kripton.escape.text.AggregateTranslator;
import com.abubusoft.kripton.escape.text.CharSequenceTranslator;
import com.abubusoft.kripton.escape.text.EntityArrays;
import com.abubusoft.kripton.escape.text.JavaUnicodeEscaper;
import com.abubusoft.kripton.escape.text.LookupTranslator;
import com.abubusoft.kripton.escape.text.NumericEntityEscaper;
import com.abubusoft.kripton.escape.text.NumericEntityUnescaper;
import com.abubusoft.kripton.escape.text.OctalUnescaper;
import com.abubusoft.kripton.escape.text.StringUtils;
import com.abubusoft.kripton.escape.text.UnicodeUnescaper;
import com.abubusoft.kripton.escape.text.UnicodeUnpairedSurrogateRemover;
// TODO: Auto-generated Javadoc
/**
* Escapes and unescapes {@code String}s for
* Java, Java Script, HTML and XML.
*
* #ThreadSafe#
* @since 2.0
*/
public abstract class StringEscapeUtils {
/* ESCAPE TRANSLATORS */
/**
* Translator object for escaping Java.
*
* While {@link #escapeJava(String)} is the expected method of use, this
* object allows the Java escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_JAVA =
new LookupTranslator(
new String[][] {
{"\"", "\\\""},
{"\\", "\\\\"},
}).with(
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE())
).with(
JavaUnicodeEscaper.outsideOf(32, 0x7f)
);
/**
* Translator object for escaping EcmaScript/JavaScript.
*
* While {@link #escapeEcmaScript(String)} is the expected method of use, this
* object allows the EcmaScript escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_ECMASCRIPT =
new AggregateTranslator(
new LookupTranslator(
new String[][] {
{"'", "\\'"},
{"\"", "\\\""},
{"\\", "\\\\"},
{"/", "\\/"}
}),
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
JavaUnicodeEscaper.outsideOf(32, 0x7f)
);
/**
* Translator object for escaping Json.
*
* While {@link #escapeJson(String)} is the expected method of use, this
* object allows the Json escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.2
*/
public static final CharSequenceTranslator ESCAPE_JSON =
new AggregateTranslator(
new LookupTranslator(
new String[][] {
{"\"", "\\\""},
{"\\", "\\\\"},
{"/", "\\/"}
}),
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
JavaUnicodeEscaper.outsideOf(32, 0x7f)
);
/**
* Translator object for escaping XML 1.0.
*
* While {@link #escapeXml10(String)} is the expected method of use, this
* object allows the XML escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.3
*/
public static final CharSequenceTranslator ESCAPE_XML10 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.APOS_ESCAPE()),
new LookupTranslator(
new String[][] {
{ "\u0000", StringUtils.EMPTY },
{ "\u0001", StringUtils.EMPTY },
{ "\u0002", StringUtils.EMPTY },
{ "\u0003", StringUtils.EMPTY },
{ "\u0004", StringUtils.EMPTY },
{ "\u0005", StringUtils.EMPTY },
{ "\u0006", StringUtils.EMPTY },
{ "\u0007", StringUtils.EMPTY },
{ "\u0008", StringUtils.EMPTY },
{ "\u000b", StringUtils.EMPTY },
{ "\u000c", StringUtils.EMPTY },
{ "\u000e", StringUtils.EMPTY },
{ "\u000f", StringUtils.EMPTY },
{ "\u0010", StringUtils.EMPTY },
{ "\u0011", StringUtils.EMPTY },
{ "\u0012", StringUtils.EMPTY },
{ "\u0013", StringUtils.EMPTY },
{ "\u0014", StringUtils.EMPTY },
{ "\u0015", StringUtils.EMPTY },
{ "\u0016", StringUtils.EMPTY },
{ "\u0017", StringUtils.EMPTY },
{ "\u0018", StringUtils.EMPTY },
{ "\u0019", StringUtils.EMPTY },
{ "\u001a", StringUtils.EMPTY },
{ "\u001b", StringUtils.EMPTY },
{ "\u001c", StringUtils.EMPTY },
{ "\u001d", StringUtils.EMPTY },
{ "\u001e", StringUtils.EMPTY },
{ "\u001f", StringUtils.EMPTY },
{ "\ufffe", StringUtils.EMPTY },
{ "\uffff", StringUtils.EMPTY }
}),
NumericEntityEscaper.between(0x7f, 0x84),
NumericEntityEscaper.between(0x86, 0x9f),
new UnicodeUnpairedSurrogateRemover()
);
/**
* Translator object for escaping XML 1.1.
*
* While {@link #escapeXml11(String)} is the expected method of use, this
* object allows the XML escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.3
*/
public static final CharSequenceTranslator ESCAPE_XML11 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.APOS_ESCAPE()),
new LookupTranslator(
new String[][] {
{ "\u0000", StringUtils.EMPTY },
{ "\u000b", " " },
{ "\u000c", "" },
{ "\ufffe", StringUtils.EMPTY },
{ "\uffff", StringUtils.EMPTY }
}),
NumericEntityEscaper.between(0x1, 0x8),
NumericEntityEscaper.between(0xe, 0x1f),
NumericEntityEscaper.between(0x7f, 0x84),
NumericEntityEscaper.between(0x86, 0x9f),
new UnicodeUnpairedSurrogateRemover()
);
/**
* Translator object for escaping HTML version 3.0.
*
* While {@link #escapeHtml3(String)} is the expected method of use, this
* object allows the HTML escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_HTML3 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE())
);
/**
* Translator object for escaping HTML version 4.0.
*
* While {@link #escapeHtml4(String)} is the expected method of use, this
* object allows the HTML escaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_HTML4 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE()),
new LookupTranslator(EntityArrays.HTML40_EXTENDED_ESCAPE())
);
/* UNESCAPE TRANSLATORS */
/**
* Translator object for unescaping escaped Java.
*
* While {@link #unescapeJava(String)} is the expected method of use, this
* object allows the Java unescaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
// TODO: throw "illegal character: \92" as an Exception if a \ on the end of the Java (as per the compiler)?
public static final CharSequenceTranslator UNESCAPE_JAVA =
new AggregateTranslator(
new OctalUnescaper(), // .between('\1', '\377'),
new UnicodeUnescaper(),
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_UNESCAPE()),
new LookupTranslator(
new String[][] {
{"\\\\", "\\"},
{"\\\"", "\""},
{"\\'", "'"},
{"\\", ""}
})
);
/**
* Translator object for unescaping escaped EcmaScript.
*
* While {@link #unescapeEcmaScript(String)} is the expected method of use, this
* object allows the EcmaScript unescaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_ECMASCRIPT = UNESCAPE_JAVA;
/**
* Translator object for unescaping escaped Json.
*
* While {@link #unescapeJson(String)} is the expected method of use, this
* object allows the Json unescaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.2
*/
public static final CharSequenceTranslator UNESCAPE_JSON = UNESCAPE_JAVA;
/**
* Translator object for unescaping escaped HTML 3.0.
*
* While {@link #unescapeHtml3(String)} is the expected method of use, this
* object allows the HTML unescaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_HTML3 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
new NumericEntityUnescaper()
);
/**
* Translator object for unescaping escaped HTML 4.0.
*
* While {@link #unescapeHtml4(String)} is the expected method of use, this
* object allows the HTML unescaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_HTML4 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
new LookupTranslator(EntityArrays.HTML40_EXTENDED_UNESCAPE()),
new NumericEntityUnescaper()
);
/**
* Translator object for unescaping escaped XML.
*
* While {@link #unescapeXml(String)} is the expected method of use, this
* object allows the XML unescaping functionality to be used
* as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_XML =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
new LookupTranslator(EntityArrays.APOS_UNESCAPE()),
new NumericEntityUnescaper()
);
/* Helper functions */
/**
* {@code StringEscapeUtils} instances should NOT be constructed in
* standard programming.
*
* Instead, the class should be used as:
* StringEscapeUtils.escapeJava("foo");
*
* This constructor is public to permit tools that require a JavaBean
* instance to operate.
*/
public StringEscapeUtils() {
super();
}
// Java and JavaScript
//--------------------------------------------------------------------------
/**
* Escapes the characters in a {@code String} using Java String rules.
*
* Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.)
*
* So a tab becomes the characters {@code '\\'} and
* {@code 't'}.
*
* The only difference between Java strings and JavaScript strings
* is that in JavaScript, a single quote and forward-slash (/) are escaped.
*
* Example:
*
* input string: He didn't say, "Stop!"
* output string: He didn't say, \"Stop!\"
*
*
* @param input String to escape values in, may be null
* @return String with escaped values, {@code null} if null string input
*/
public static final String escapeJava(final String input) {
return ESCAPE_JAVA.translate(input);
}
/**
* Escapes the characters in a {@code String} using EcmaScript String rules.
* Escapes any values it finds into their EcmaScript String form.
* Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.)
*
* So a tab becomes the characters {@code '\\'} and
* {@code 't'}.
*
* The only difference between Java strings and EcmaScript strings
* is that in EcmaScript, a single quote and forward-slash (/) are escaped.
*
* Note that EcmaScript is best known by the JavaScript and ActionScript dialects.
*
* Example:
*
* input string: He didn't say, "Stop!"
* output string: He didn\'t say, \"Stop!\"
*
*
* @param input String to escape values in, may be null
* @return String with escaped values, {@code null} if null string input
*
* @since 3.0
*/
public static final String escapeEcmaScript(final String input) {
return ESCAPE_ECMASCRIPT.translate(input);
}
/**
* Escapes the characters in a {@code String} using Json String rules.
* Escapes any values it finds into their Json String form.
* Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.)
*
* So a tab becomes the characters {@code '\\'} and
* {@code 't'}.
*
* The only difference between Java strings and Json strings
* is that in Json, forward-slash (/) is escaped.
*
* See http://www.ietf.org/rfc/rfc4627.txt for further details.
*
* Example:
*
* input string: He didn't say, "Stop!"
* output string: He didn't say, \"Stop!\"
*
*
* @param input String to escape values in, may be null
* @return String with escaped values, {@code null} if null string input
*
* @since 3.2
*/
public static final String escapeJson(final String input) {
return ESCAPE_JSON.translate(input);
}
/**
* Unescapes any Java literals found in the {@code String}.
* For example, it will turn a sequence of {@code '\'} and
* {@code 'n'} into a newline character, unless the {@code '\'}
* is preceded by another {@code '\'}.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
*/
public static final String unescapeJava(final String input) {
return UNESCAPE_JAVA.translate(input);
}
/**
* Unescapes any EcmaScript literals found in the {@code String}.
*
* For example, it will turn a sequence of {@code '\'} and {@code 'n'}
* into a newline character, unless the {@code '\'} is preceded by another
* {@code '\'}.
*
* @param input the {@code String} to unescape, may be null
* @return A new unescaped {@code String}, {@code null} if null string input
* @see #unescapeJava(String)
* @since 3.0
*/
public static final String unescapeEcmaScript(final String input) {
return UNESCAPE_ECMASCRIPT.translate(input);
}
/**
* Unescapes any Json literals found in the {@code String}.
*
* For example, it will turn a sequence of {@code '\'} and {@code 'n'}
* into a newline character, unless the {@code '\'} is preceded by another
* {@code '\'}.
*
* @param input the {@code String} to unescape, may be null
* @return A new unescaped {@code String}, {@code null} if null string input
* @see #unescapeJava(String)
* @since 3.2
*/
public static final String unescapeJson(final String input) {
return UNESCAPE_JSON.translate(input);
}
// HTML and XML
//--------------------------------------------------------------------------
/**
* Escapes the characters in a {@code String} using HTML entities.
*
*
* For example:
*
* "bread" & "butter"
* becomes:
*
* "bread" & "butter".
*
*
* Supports all known HTML 4.0 entities, including funky accents.
* Note that the commonly used apostrophe escape character (')
* is not a legal entity and so is not supported).
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
*
* @see ISO Entities
* @see HTML 3.2 Character Entities for ISO Latin-1
* @see HTML 4.0 Character entity references
* @see HTML 4.01 Character References
* @see HTML 4.01 Code positions
*
* @since 3.0
*/
public static final String escapeHtml4(final String input) {
return ESCAPE_HTML4.translate(input);
}
/**
* Escapes the characters in a {@code String} using HTML entities.
* Supports only the HTML 3.0 entities.
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
*
* @since 3.0
*/
public static final String escapeHtml3(final String input) {
return ESCAPE_HTML3.translate(input);
}
//-----------------------------------------------------------------------
/**
* Unescapes a string containing entity escapes to a string
* containing the actual Unicode characters corresponding to the
* escapes. Supports HTML 4.0 entities.
*
* For example, the string {@code "<Français>"}
* will become {@code ""}
*
* If an entity is unrecognized, it is left alone, and inserted
* verbatim into the result string. e.g. {@code ">&zzzz;x"} will
* become {@code ">&zzzz;x"}.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
*
* @since 3.0
*/
public static final String unescapeHtml4(final String input) {
return UNESCAPE_HTML4.translate(input);
}
/**
* Unescapes a string containing entity escapes to a string
* containing the actual Unicode characters corresponding to the
* escapes. Supports only HTML 3.0 entities.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
*
* @since 3.0
*/
public static final String unescapeHtml3(final String input) {
return UNESCAPE_HTML3.translate(input);
}
/**
* Escapes the characters in a {@code String} using XML entities.
*
* For example: {@code "bread" & "butter"} =>
* {@code "bread" & "butter"}.
*
*
* Note that XML 1.0 is a text-only format: it cannot represent control
* characters or unpaired Unicode surrogate codepoints, even after escaping.
* {@code escapeXml10} will remove characters that do not fit in the
* following ranges:
*
* {@code #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]}
*
* Though not strictly necessary, {@code escapeXml10} will escape
* characters in the following ranges:
*
* {@code [#x7F-#x84] | [#x86-#x9F]}
*
* The returned string can be inserted into a valid XML 1.0 or XML 1.1
* document. If you want to allow more non-text characters in an XML 1.1
* document, use {@link #escapeXml11(String)}.
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
* @see #unescapeXml(java.lang.String)
* @since 3.3
*/
public static String escapeXml10(final String input) {
return ESCAPE_XML10.translate(input);
}
/**
* Escapes the characters in a {@code String} using XML entities.
*
* For example: {@code "bread" & "butter"} =>
* {@code "bread" & "butter"}.
*
*
* XML 1.1 can represent certain control characters, but it cannot represent
* the null byte or unpaired Unicode surrogate codepoints, even after escaping.
* {@code escapeXml11} will remove characters that do not fit in the following
* ranges:
*
* {@code [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]}
*
* {@code escapeXml11} will escape characters in the following ranges:
*
* {@code [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]}
*
* The returned string can be inserted into a valid XML 1.1 document. Do not
* use it for XML 1.0 documents.
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
* @see #unescapeXml(java.lang.String)
* @since 3.3
*/
public static String escapeXml11(final String input) {
return ESCAPE_XML11.translate(input);
}
//-----------------------------------------------------------------------
/**
* Unescapes a string containing XML entity escapes to a string
* containing the actual Unicode characters corresponding to the
* escapes.
*
* Supports only the five basic XML entities (gt, lt, quot, amp, apos).
* Does not support DTDs or external entities.
*
* Note that numerical \\u Unicode codes are unescaped to their respective
* Unicode characters. This may change in future releases.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
* @see #escapeXml10(String)
* @see #escapeXml11(String)
*/
public static final String unescapeXml(final String input) {
return UNESCAPE_XML.translate(input);
}
//-----------------------------------------------------------------------
}