You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@commons.apache.org by ba...@apache.org on 2009/11/17 09:45:55 UTC
svn commit: r881197 - in /commons/proper/lang/trunk/src:
java/org/apache/commons/lang/ java/org/apache/commons/lang/text/translate/
test/org/apache/commons/lang/ test/org/apache/commons/lang/text/translate/
Author: bayard
Date: Tue Nov 17 08:45:55 2009
New Revision: 881197
URL: http://svn.apache.org/viewvc?rev=881197&view=rev
Log:
Removing the EscapeUtils/UnescapeUtils classes, and making StringEscapeUtils the replacement. Writer variants of StringEscapeUtils are dropped - instead you hit those via the translator objects. Some javadoc/testing cleanup needed.
Removed:
commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/EscapeUtils.java
commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/UnescapeUtils.java
commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/EscapeUtilsTest.java
commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/UnescapeUtilsTest.java
Modified:
commons/proper/lang/trunk/src/java/org/apache/commons/lang/StringEscapeUtils.java
commons/proper/lang/trunk/src/test/org/apache/commons/lang/StringEscapeUtilsTest.java
Modified: commons/proper/lang/trunk/src/java/org/apache/commons/lang/StringEscapeUtils.java
URL: http://svn.apache.org/viewvc/commons/proper/lang/trunk/src/java/org/apache/commons/lang/StringEscapeUtils.java?rev=881197&r1=881196&r2=881197&view=diff
==============================================================================
--- commons/proper/lang/trunk/src/java/org/apache/commons/lang/StringEscapeUtils.java (original)
+++ commons/proper/lang/trunk/src/java/org/apache/commons/lang/StringEscapeUtils.java Tue Nov 17 08:45:55 2009
@@ -19,8 +19,11 @@
import java.io.IOException;
import java.io.Writer;
-import org.apache.commons.lang.text.translate.EscapeUtils;
-import org.apache.commons.lang.text.translate.UnescapeUtils;
+import org.apache.commons.lang.text.translate.*;
+
+// CsvTranslators
+import org.apache.commons.lang.StringUtils;
+import org.apache.commons.lang.CharUtils;
/**
* <p>Escapes and unescapes <code>String</code>s for
@@ -38,12 +41,162 @@
* @author Pete Gieser
* @since 2.0
* @version $Id$
- *
- * @deprecated Use text.translate.EscapeUtils and text.translate.UnescapeUtils instead
*/
-@Deprecated
public class StringEscapeUtils {
+ /* ESCAPE TRANSLATORS */
+
+ public static final CharSequenceTranslator ESCAPE_JAVA =
+ new LookupTranslator(
+ new String[][] {
+ {"\"", "\\\""},
+ {"\\", "\\\\"},
+ }).with(
+ new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE())
+ ).with(
+ UnicodeEscaper.outsideOf(32, 0x7f)
+ );
+
+ public static final CharSequenceTranslator ESCAPE_ECMASCRIPT =
+ new AggregateTranslator(
+ new LookupTranslator(
+ new String[][] {
+ {"'", "\\'"},
+ {"\"", "\\\""},
+ {"\\", "\\\\"},
+ {"/", "\\/"}
+ }),
+ new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
+ UnicodeEscaper.outsideOf(32, 0x7f)
+ );
+
+ public static final CharSequenceTranslator ESCAPE_XML =
+ new AggregateTranslator(
+ new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
+ new LookupTranslator(EntityArrays.APOS_ESCAPE())
+ );
+
+ public static final CharSequenceTranslator ESCAPE_HTML3 =
+ new AggregateTranslator(
+ new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
+ new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE())
+ );
+
+ 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())
+ );
+
+ public static final CharSequenceTranslator ESCAPE_CSV = new CsvEscaper();
+
+ // TODO: Create a parent class - 'SinglePassTranslator' ?
+ // TODO: It would handle the index checking, and length returning, and
+ // TODO: could also have an optimization check method.
+ static class CsvEscaper extends CharSequenceTranslator {
+
+ private static final char CSV_DELIMITER = ',';
+ private static final char CSV_QUOTE = '"';
+ private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
+ private static final char[] CSV_SEARCH_CHARS = new char[] {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};
+
+ // TODO: Replace with a RegexTranslator. That should consume the number of characters the regex uses up?
+ @Override
+ public int translate(CharSequence input, int index, Writer out) throws IOException {
+
+ if(index != 0) {
+ throw new IllegalStateException("CsvEscaper should never reach the [1] index");
+ }
+
+ if (StringUtils.containsNone(input.toString(), CSV_SEARCH_CHARS)) {
+ out.write(input.toString());
+ } else {
+ out.write(CSV_QUOTE);
+ out.write(StringUtils.replace(input.toString(), CSV_QUOTE_STR, CSV_QUOTE_STR + CSV_QUOTE_STR));
+ out.write(CSV_QUOTE);
+ }
+ return input.length();
+ }
+ }
+
+ /* UNESCAPE TRANSLATORS */
+
+ // 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 UnicodeUnescaper(),
+ new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_UNESCAPE()),
+ new LookupTranslator(
+ new String[][] {
+ {"\\\\", "\\"},
+ {"\\\"", "\""},
+ {"\\'", "'"},
+ {"\\", ""}
+ })
+ );
+
+ public static final CharSequenceTranslator UNESCAPE_ECMASCRIPT = UNESCAPE_JAVA;
+
+ public static final CharSequenceTranslator UNESCAPE_HTML3 =
+ new AggregateTranslator(
+ new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
+ new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
+ new NumericEntityUnescaper()
+ );
+
+ 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()
+ );
+
+ public static final CharSequenceTranslator UNESCAPE_XML =
+ new AggregateTranslator(
+ new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
+ new LookupTranslator(EntityArrays.APOS_UNESCAPE()),
+ new NumericEntityUnescaper()
+ );
+
+ public static final CharSequenceTranslator UNESCAPE_CSV = new CsvUnescaper();
+
+ static class CsvUnescaper extends CharSequenceTranslator {
+
+ private static final char CSV_DELIMITER = ',';
+ private static final char CSV_QUOTE = '"';
+ private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
+ private static final char[] CSV_SEARCH_CHARS = new char[] {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};
+
+ // TODO: Replace with a RegexTranslator. That should consume the number of characters the regex uses up?
+ @Override
+ public int translate(CharSequence input, int index, Writer out) throws IOException {
+
+ if(index != 0) {
+ throw new IllegalStateException("CsvUnescaper should never reach the [1] index");
+ }
+
+ if ( input.charAt(0) != CSV_QUOTE || input.charAt(input.length() - 1) != CSV_QUOTE ) {
+ out.write(input.toString());
+ return input.length();
+ }
+
+ // strip quotes
+ String quoteless = input.subSequence(1, input.length() - 1).toString();
+
+ if ( StringUtils.containsAny(quoteless, CSV_SEARCH_CHARS) ) {
+ // deal with escaped quotes; ie) ""
+ out.write(StringUtils.replace(quoteless, CSV_QUOTE_STR + CSV_QUOTE_STR, CSV_QUOTE_STR));
+ } else {
+ out.write(input.toString());
+ }
+ return input.length();
+ }
+ }
+
+ /* Helper functions */
+
/**
* <p><code>StringEscapeUtils</code> instances should NOT be constructed in
* standard programming.</p>
@@ -78,39 +231,25 @@
* </pre>
* </p>
*
- * @param str String to escape values in, may be null
+ * @param input String to escape values in, may be null
* @return String with escaped values, <code>null</code> if null string input
*/
- public static String escapeJava(String str) {
- return EscapeUtils.escapeJava(str);
- }
-
- /**
- * <p>Escapes the characters in a <code>String</code> using Java String rules to
- * a <code>Writer</code>.</p>
- *
- * <p>A <code>null</code> string input has no effect.</p>
- *
- * @see #escapeJava(java.lang.String)
- * @param out Writer to write escaped string into
- * @param str String to escape values in, may be null
- * @throws IllegalArgumentException if the Writer is <code>null</code>
- * @throws IOException if error occurs on underlying Writer
- */
- public static void escapeJava(Writer out, String str) throws IOException {
- EscapeUtils.ESCAPE_JAVA.translate(str, out);
+ public static final String escapeJava(String input) {
+ return ESCAPE_JAVA.translate(input);
}
/**
- * <p>Escapes the characters in a <code>String</code> using JavaScript String rules.</p>
- * <p>Escapes any values it finds into their JavaScript String form.
+ * <p>Escapes the characters in a <code>String</code> using EcmaScript String rules.</p>
+ * <p>Escapes any values it finds into their EcmaScript String form.
* Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.) </p>
*
* <p>So a tab becomes the characters <code>'\\'</code> and
* <code>'t'</code>.</p>
*
- * <p>The only difference between Java strings and JavaScript strings
- * is that in JavaScript, a single quote and forward-slash (/) are escaped.</p>
+ * <p>The only difference between Java strings and EcmaScript strings
+ * is that in EcmaScript, a single quote and forward-slash (/) are escaped.</p>
+ *
+ * <p>Note that EcmaScript is best known by the JavaScript and ActionScript dialects. </p>
*
* <p>Example:
* <pre>
@@ -119,27 +258,11 @@
* </pre>
* </p>
*
- * @param str String to escape values in, may be null
+ * @param input String to escape values in, may be null
* @return String with escaped values, <code>null</code> if null string input
*/
- public static String escapeJavaScript(String str) {
- return EscapeUtils.escapeEcmaScript(str);
- }
-
- /**
- * <p>Escapes the characters in a <code>String</code> using JavaScript String rules
- * to a <code>Writer</code>.</p>
- *
- * <p>A <code>null</code> string input has no effect.</p>
- *
- * @see #escapeJavaScript(java.lang.String)
- * @param out Writer to write escaped string into
- * @param str String to escape values in, may be null
- * @throws IllegalArgumentException if the Writer is <code>null</code>
- * @throws IOException if error occurs on underlying Writer
- **/
- public static void escapeJavaScript(Writer out, String str) throws IOException {
- EscapeUtils.ESCAPE_ECMASCRIPT.translate(str, out);
+ public static final String escapeEcmaScript(String input) {
+ return ESCAPE_ECMASCRIPT.translate(input);
}
/**
@@ -148,65 +271,26 @@
* <code>'n'</code> into a newline character, unless the <code>'\'</code>
* is preceded by another <code>'\'</code>.</p>
*
- * @param str the <code>String</code> to unescape, may be null
+ * @param input the <code>String</code> to unescape, may be null
* @return a new unescaped <code>String</code>, <code>null</code> if null string input
*/
- public static String unescapeJava(String str) {
- return UnescapeUtils.unescapeJava(str);
- }
-
- /**
- * <p>Unescapes any Java literals found in the <code>String</code> to a
- * <code>Writer</code>.</p>
- *
- * <p>For example, it will turn a sequence of <code>'\'</code> and
- * <code>'n'</code> into a newline character, unless the <code>'\'</code>
- * is preceded by another <code>'\'</code>.</p>
- *
- * <p>A <code>null</code> string input has no effect.</p>
- *
- * @param out the <code>Writer</code> used to output unescaped characters
- * @param str the <code>String</code> to unescape, may be null
- * @throws IllegalArgumentException if the Writer is <code>null</code>
- * @throws IOException if error occurs on underlying Writer
- */
- public static void unescapeJava(Writer out, String str) throws IOException {
- UnescapeUtils.UNESCAPE_JAVA.translate(str, out);
+ public static final String unescapeJava(String input) {
+ return UNESCAPE_JAVA.translate(input);
}
/**
- * <p>Unescapes any JavaScript literals found in the <code>String</code>.</p>
+ * <p>Unescapes any EcmaScript literals found in the <code>String</code>.</p>
*
* <p>For example, it will turn a sequence of <code>'\'</code> and <code>'n'</code>
* into a newline character, unless the <code>'\'</code> is preceded by another
* <code>'\'</code>.</p>
*
* @see #unescapeJava(String)
- * @param str the <code>String</code> to unescape, may be null
+ * @param input the <code>String</code> to unescape, may be null
* @return A new unescaped <code>String</code>, <code>null</code> if null string input
*/
- public static String unescapeJavaScript(String str) {
- return UnescapeUtils.unescapeEcmaScript(str);
- }
-
- /**
- * <p>Unescapes any JavaScript literals found in the <code>String</code> to a
- * <code>Writer</code>.</p>
- *
- * <p>For example, it will turn a sequence of <code>'\'</code> and <code>'n'</code>
- * into a newline character, unless the <code>'\'</code> is preceded by another
- * <code>'\'</code>.</p>
- *
- * <p>A <code>null</code> string input has no effect.</p>
- *
- * @see #unescapeJava(Writer,String)
- * @param out the <code>Writer</code> used to output unescaped characters
- * @param str the <code>String</code> to unescape, may be null
- * @throws IllegalArgumentException if the Writer is <code>null</code>
- * @throws IOException if error occurs on underlying Writer
- */
- public static void unescapeJavaScript(Writer out, String str) throws IOException {
- UnescapeUtils.UNESCAPE_ECMASCRIPT.translate(str, out);
+ public static final String unescapeEcmaScript(String input) {
+ return UNESCAPE_ECMASCRIPT.translate(input);
}
// HTML and XML
@@ -227,7 +311,7 @@
* Note that the commonly used apostrophe escape character (&apos;)
* is not a legal entity and so is not supported). </p>
*
- * @param str the <code>String</code> to escape, may be null
+ * @param input the <code>String</code> to escape, may be null
* @return a new escaped <code>String</code>, <code>null</code> if null string input
*
* @see #unescapeHtml(String)
@@ -237,43 +321,14 @@
* @see <a href="http://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character References</a>
* @see <a href="http://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code positions</a>
*/
- public static String escapeHtml(String str) {
- return EscapeUtils.escapeHtml4(str);
+ public static final String escapeHtml4(String input) {
+ return ESCAPE_HTML4.translate(input);
}
- /**
- * <p>Escapes the characters in a <code>String</code> using HTML entities and writes
- * them to a <code>Writer</code>.</p>
- *
- * <p>
- * For example:
- * </p>
- * <code>"bread" & "butter"</code>
- * <p>becomes:</p>
- * <code>&quot;bread&quot; &amp; &quot;butter&quot;</code>.
- *
- * <p>Supports all known HTML 4.0 entities, including funky accents.
- * Note that the commonly used apostrophe escape character (&apos;)
- * is not a legal entity and so is not supported). </p>
- *
- * @param writer the writer receiving the escaped string, not null
- * @param string the <code>String</code> to escape, may be null
- * @throws IllegalArgumentException if the writer is null
- * @throws IOException when <code>Writer</code> passed throws the exception from
- * calls to the {@link Writer#write(int)} methods.
- *
- * @see #escapeHtml(String)
- * @see #unescapeHtml(String)
- * @see <a href="http://hotwired.lycos.com/webmonkey/reference/special_characters/">ISO Entities</a>
- * @see <a href="http://www.w3.org/TR/REC-html32#latin1">HTML 3.2 Character Entities for ISO Latin-1</a>
- * @see <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">HTML 4.0 Character entity references</a>
- * @see <a href="http://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character References</a>
- * @see <a href="http://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code positions</a>
- */
- public static void escapeHtml(Writer writer, String string) throws IOException {
- EscapeUtils.ESCAPE_HTML4.translate(string, writer);
+ public static final String escapeHtml3(String input) {
+ return ESCAPE_HTML3.translate(input);
}
-
+
//-----------------------------------------------------------------------
/**
* <p>Unescapes a string containing entity escapes to a string
@@ -287,34 +342,15 @@
* verbatim into the result string. e.g. "&gt;&zzzz;x" will
* become ">&zzzz;x".</p>
*
- * @param str the <code>String</code> to unescape, may be null
+ * @param input the <code>String</code> to unescape, may be null
* @return a new unescaped <code>String</code>, <code>null</code> if null string input
- * @see #escapeHtml(Writer, String)
*/
- public static String unescapeHtml(String str) {
- return UnescapeUtils.unescapeHtml4(str);
+ public static final String unescapeHtml4(String input) {
+ return UNESCAPE_HTML4.translate(input);
}
- /**
- * <p>Unescapes a string containing entity escapes to a string
- * containing the actual Unicode characters corresponding to the
- * escapes. Supports HTML 4.0 entities.</p>
- *
- * <p>For example, the string "&lt;Fran&ccedil;ais&gt;"
- * will become "<Français>"</p>
- *
- * <p>If an entity is unrecognized, it is left alone, and inserted
- * verbatim into the result string. e.g. "&gt;&zzzz;x" will
- * become ">&zzzz;x".</p>
- *
- * @param writer the writer receiving the unescaped string, not null
- * @param string the <code>String</code> to unescape, may be null
- * @throws IllegalArgumentException if the writer is null
- * @throws IOException if an IOException occurs
- * @see #escapeHtml(String)
- */
- public static void unescapeHtml(Writer writer, String string) throws IOException {
- UnescapeUtils.UNESCAPE_HTML4.translate(string, writer);
+ public static final String unescapeHtml3(String input) {
+ return UNESCAPE_HTML3.translate(input);
}
//-----------------------------------------------------------------------
@@ -331,36 +367,14 @@
* <p>Note that unicode characters greater than 0x7f are as of 3.0, no longer
* escaped. </p>
*
- * @param writer the writer receiving the unescaped string, not null
- * @param str the <code>String</code> to escape, may be null
- * @throws IllegalArgumentException if the writer is null
- * @throws IOException if there is a problem writing
- * @see #unescapeXml(java.lang.String)
- */
- public static void escapeXml(Writer writer, String str) throws IOException {
- EscapeUtils.ESCAPE_XML.translate(str, writer);
- }
-
- /**
- * <p>Escapes the characters in a <code>String</code> using XML entities.</p>
- *
- * <p>For example: <tt>"bread" & "butter"</tt> =>
- * <tt>&quot;bread&quot; &amp; &quot;butter&quot;</tt>.
- * </p>
- *
- * <p>Supports only the five basic XML entities (gt, lt, quot, amp, apos).
- * Does not support DTDs or external entities.</p>
- *
- * <p>Note that unicode characters greater than 0x7f are as of 3.0, no longer
- * escaped. </p>
- *
- * @param str the <code>String</code> to escape, may be null
+ * @param input the <code>String</code> to escape, may be null
* @return a new escaped <code>String</code>, <code>null</code> if null string input
* @see #unescapeXml(java.lang.String)
*/
- public static String escapeXml(String str) {
- return EscapeUtils.escapeXml(str);
+ public static final String escapeXml(String input) {
+ return ESCAPE_XML.translate(input);
}
+
//-----------------------------------------------------------------------
/**
@@ -374,34 +388,14 @@
* <p>Note that numerical \\u unicode codes are unescaped to their respective
* unicode characters. This may change in future releases. </p>
*
- * @param writer the writer receiving the unescaped string, not null
- * @param str the <code>String</code> to unescape, may be null
- * @throws IllegalArgumentException if the writer is null
- * @throws IOException if there is a problem writing
- * @see #escapeXml(String)
- */
- public static void unescapeXml(Writer writer, String str) throws IOException {
- UnescapeUtils.UNESCAPE_XML.translate(str, writer);
- }
-
- /**
- * <p>Unescapes a string containing XML entity escapes to a string
- * containing the actual Unicode characters corresponding to the
- * escapes.</p>
- *
- * <p>Supports only the five basic XML entities (gt, lt, quot, amp, apos).
- * Does not support DTDs or external entities.</p>
- *
- * <p>Note that numerical \\u unicode codes are unescaped to their respective
- * unicode characters. This may change in future releases. </p>
- *
- * @param str the <code>String</code> to unescape, may be null
+ * @param input the <code>String</code> to unescape, may be null
* @return a new unescaped <code>String</code>, <code>null</code> if null string input
* @see #escapeXml(String)
*/
- public static String unescapeXml(String str) {
- return UnescapeUtils.unescapeXml(str);
+ public static final String unescapeXml(String input) {
+ return UNESCAPE_XML.translate(input);
}
+
//-----------------------------------------------------------------------
@@ -422,40 +416,13 @@
* see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and
* <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
*
- * @param str the input CSV column String, may be null
+ * @param input the input CSV column String, may be null
* @return the input String, enclosed in double quotes if the value contains a comma,
* newline or double quote, <code>null</code> if null string input
* @since 2.4
*/
- public static String escapeCsv(String str) {
- return EscapeUtils.escapeCsv(str);
- }
-
- /**
- * <p>Writes a <code>String</code> value for a CSV column enclosed in double quotes,
- * if required.</p>
- *
- * <p>If the value contains a comma, newline or double quote, then the
- * String value is written enclosed in double quotes.</p>
- * </p>
- *
- * <p>Any double quote characters in the value are escaped with another double quote.</p>
- *
- * <p>If the value does not contain a comma, newline or double quote, then the
- * String value is written unchanged (null values are ignored).</p>
- * </p>
- *
- * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and
- * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
- *
- * @param str the input CSV column String, may be null
- * @param out Writer to write input string to, enclosed in double quotes if it contains
- * a comma, newline or double quote
- * @throws IOException if error occurs on underlying Writer
- * @since 2.4
- */
- public static void escapeCsv(Writer out, String str) throws IOException {
- EscapeUtils.ESCAPE_CSV.translate(str, out);
+ public static final String escapeCsv(String input) {
+ return ESCAPE_CSV.translate(input);
}
/**
@@ -475,40 +442,13 @@
* see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and
* <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
*
- * @param str the input CSV column String, may be null
+ * @param input the input CSV column String, may be null
* @return the input String, with enclosing double quotes removed and embedded double
* quotes unescaped, <code>null</code> if null string input
* @since 2.4
*/
- public static String unescapeCsv(String str) {
- return UnescapeUtils.unescapeCsv(str);
- }
-
- /**
- * <p>Returns a <code>String</code> value for an unescaped CSV column. </p>
- *
- * <p>If the value is enclosed in double quotes, and contains a comma, newline
- * or double quote, then quotes are removed.
- * </p>
- *
- * <p>Any double quote escaped characters (a pair of double quotes) are unescaped
- * to just one double quote. </p>
- *
- * <p>If the value is not enclosed in double quotes, or is and does not contain a
- * comma, newline or double quote, then the String value is returned unchanged.</p>
- * </p>
- *
- * see <a href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and
- * <a href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
- *
- * @param str the input CSV column String, may be null
- * @param out Writer to write the input String to, with enclosing double quotes
- * removed and embedded double quotes unescaped, <code>null</code> if null string input
- * @throws IOException if error occurs on underlying Writer
- * @since 2.4
- */
- public static void unescapeCsv(Writer out, String str) throws IOException {
- UnescapeUtils.UNESCAPE_CSV.translate(str, out);
+ public static final String unescapeCsv(String input) {
+ return UNESCAPE_CSV.translate(input);
}
}
Modified: commons/proper/lang/trunk/src/test/org/apache/commons/lang/StringEscapeUtilsTest.java
URL: http://svn.apache.org/viewvc/commons/proper/lang/trunk/src/test/org/apache/commons/lang/StringEscapeUtilsTest.java?rev=881197&r1=881196&r2=881197&view=diff
==============================================================================
--- commons/proper/lang/trunk/src/test/org/apache/commons/lang/StringEscapeUtilsTest.java (original)
+++ commons/proper/lang/trunk/src/test/org/apache/commons/lang/StringEscapeUtilsTest.java Tue Nov 17 08:45:55 2009
@@ -63,14 +63,14 @@
public void testEscapeJava() throws IOException {
assertEquals(null, StringEscapeUtils.escapeJava(null));
try {
- StringEscapeUtils.escapeJava(null, null);
+ StringEscapeUtils.ESCAPE_JAVA.translate(null, null);
fail();
} catch (IOException ex) {
fail();
} catch (IllegalArgumentException ex) {
}
try {
- StringEscapeUtils.escapeJava(null, "");
+ StringEscapeUtils.ESCAPE_JAVA.translate("", null);
fail();
} catch (IOException ex) {
fail();
@@ -123,21 +123,21 @@
assertEquals(message, expected, converted);
StringWriter writer = new StringWriter();
- StringEscapeUtils.escapeJava(writer, original);
+ StringEscapeUtils.ESCAPE_JAVA.translate(original, writer);
assertEquals(expected, writer.toString());
}
public void testUnescapeJava() throws IOException {
assertEquals(null, StringEscapeUtils.unescapeJava(null));
try {
- StringEscapeUtils.unescapeJava(null, null);
+ StringEscapeUtils.UNESCAPE_JAVA.translate(null, null);
fail();
} catch (IOException ex) {
fail();
} catch (IllegalArgumentException ex) {
}
try {
- StringEscapeUtils.unescapeJava(null, "");
+ StringEscapeUtils.UNESCAPE_JAVA.translate("", null);
fail();
} catch (IOException ex) {
fail();
@@ -177,31 +177,31 @@
expected, actual);
StringWriter writer = new StringWriter();
- StringEscapeUtils.unescapeJava(writer, original);
+ StringEscapeUtils.UNESCAPE_JAVA.translate(original, writer);
assertEquals(unescaped, writer.toString());
}
- public void testEscapeJavaScript() {
- assertEquals(null, StringEscapeUtils.escapeJavaScript(null));
+ public void testEscapeEcmaScript() {
+ assertEquals(null, StringEscapeUtils.escapeEcmaScript(null));
try {
- StringEscapeUtils.escapeJavaScript(null, null);
+ StringEscapeUtils.ESCAPE_ECMASCRIPT.translate(null, null);
fail();
} catch (IOException ex) {
fail();
} catch (IllegalArgumentException ex) {
}
try {
- StringEscapeUtils.escapeJavaScript(null, "");
+ StringEscapeUtils.ESCAPE_ECMASCRIPT.translate("", null);
fail();
} catch (IOException ex) {
fail();
} catch (IllegalArgumentException ex) {
}
- assertEquals("He didn\\'t say, \\\"stop!\\\"", StringEscapeUtils.escapeJavaScript("He didn't say, \"stop!\""));
+ assertEquals("He didn\\'t say, \\\"stop!\\\"", StringEscapeUtils.escapeEcmaScript("He didn't say, \"stop!\""));
assertEquals("document.getElementById(\\\"test\\\").value = \\'<script>alert(\\'aaa\\');<\\/script>\\';",
- StringEscapeUtils.escapeJavaScript("document.getElementById(\"test\").value = '<script>alert('aaa');</script>';"));
+ StringEscapeUtils.escapeEcmaScript("document.getElementById(\"test\").value = '<script>alert('aaa');</script>';"));
}
@@ -227,10 +227,10 @@
String message = htmlEscapes[i][0];
String expected = htmlEscapes[i][1];
String original = htmlEscapes[i][2];
- assertEquals(message, expected, StringEscapeUtils.escapeHtml(original));
+ assertEquals(message, expected, StringEscapeUtils.escapeHtml4(original));
StringWriter sw = new StringWriter();
try {
- StringEscapeUtils.escapeHtml(sw, original);
+ StringEscapeUtils.ESCAPE_HTML4.translate(original, sw);
} catch (IOException e) {
}
String actual = original == null ? null : sw.toString();
@@ -238,16 +238,16 @@
}
}
- public void testUnescapeHtml() {
+ public void testUnescapeHtml4() {
for (int i = 0; i < htmlEscapes.length; ++i) {
String message = htmlEscapes[i][0];
String expected = htmlEscapes[i][2];
String original = htmlEscapes[i][1];
- assertEquals(message, expected, StringEscapeUtils.unescapeHtml(original));
+ assertEquals(message, expected, StringEscapeUtils.unescapeHtml4(original));
StringWriter sw = new StringWriter();
try {
- StringEscapeUtils.unescapeHtml(sw, original);
+ StringEscapeUtils.UNESCAPE_HTML4.translate(original, sw);
} catch (IOException e) {
}
String actual = original == null ? null : sw.toString();
@@ -256,18 +256,18 @@
// \u00E7 is a cedilla (c with wiggle under)
// note that the test string must be 7-bit-clean (unicode escaped) or else it will compile incorrectly
// on some locales
- assertEquals("funny chars pass through OK", "Fran\u00E7ais", StringEscapeUtils.unescapeHtml("Fran\u00E7ais"));
+ assertEquals("funny chars pass through OK", "Fran\u00E7ais", StringEscapeUtils.unescapeHtml4("Fran\u00E7ais"));
- assertEquals("Hello&;World", StringEscapeUtils.unescapeHtml("Hello&;World"));
- assertEquals("Hello&#;World", StringEscapeUtils.unescapeHtml("Hello&#;World"));
- assertEquals("Hello&# ;World", StringEscapeUtils.unescapeHtml("Hello&# ;World"));
- assertEquals("Hello&##;World", StringEscapeUtils.unescapeHtml("Hello&##;World"));
+ assertEquals("Hello&;World", StringEscapeUtils.unescapeHtml4("Hello&;World"));
+ assertEquals("Hello&#;World", StringEscapeUtils.unescapeHtml4("Hello&#;World"));
+ assertEquals("Hello&# ;World", StringEscapeUtils.unescapeHtml4("Hello&# ;World"));
+ assertEquals("Hello&##;World", StringEscapeUtils.unescapeHtml4("Hello&##;World"));
}
public void testUnescapeHexCharsHtml() {
// Simple easy to grok test
- assertEquals("hex number unescape", "\u0080\u009F", StringEscapeUtils.unescapeHtml("€Ÿ"));
- assertEquals("hex number unescape", "\u0080\u009F", StringEscapeUtils.unescapeHtml("€Ÿ"));
+ assertEquals("hex number unescape", "\u0080\u009F", StringEscapeUtils.unescapeHtml4("€Ÿ"));
+ assertEquals("hex number unescape", "\u0080\u009F", StringEscapeUtils.unescapeHtml4("€Ÿ"));
// Test all Character values:
for (char i = Character.MIN_VALUE; i < Character.MAX_VALUE; i++) {
Character c1 = new Character(i);
@@ -275,19 +275,19 @@
String expected = c1.toString() + c2.toString();
String escapedC1 = "&#x" + Integer.toHexString((c1.charValue())) + ";";
String escapedC2 = "&#x" + Integer.toHexString((c2.charValue())) + ";";
- assertEquals("hex number unescape index " + (int)i, expected, StringEscapeUtils.unescapeHtml(escapedC1 + escapedC2));
+ assertEquals("hex number unescape index " + (int)i, expected, StringEscapeUtils.unescapeHtml4(escapedC1 + escapedC2));
}
}
public void testUnescapeUnknownEntity() throws Exception
{
- assertEquals("&zzzz;", StringEscapeUtils.unescapeHtml("&zzzz;"));
+ assertEquals("&zzzz;", StringEscapeUtils.unescapeHtml4("&zzzz;"));
}
public void testEscapeHtmlVersions() throws Exception
{
- assertEquals("Β", StringEscapeUtils.escapeHtml("\u0392"));
- assertEquals("\u0392", StringEscapeUtils.unescapeHtml("Β"));
+ assertEquals("Β", StringEscapeUtils.escapeHtml4("\u0392"));
+ assertEquals("\u0392", StringEscapeUtils.unescapeHtml4("Β"));
//todo: refine API for escaping/unescaping specific HTML versions
@@ -310,14 +310,14 @@
StringWriter sw = new StringWriter();
try {
- StringEscapeUtils.escapeXml(sw, "<abc>");
+ StringEscapeUtils.ESCAPE_XML.translate("<abc>", sw);
} catch (IOException e) {
}
assertEquals("XML was escaped incorrectly", "<abc>", sw.toString() );
sw = new StringWriter();
try {
- StringEscapeUtils.unescapeXml(sw, "<abc>");
+ StringEscapeUtils.UNESCAPE_XML.translate("<abc>", sw);
} catch (IOException e) {
}
assertEquals("XML was unescaped incorrectly", "<abc>", sw.toString() );
@@ -326,14 +326,14 @@
// Tests issue #38569
// http://issues.apache.org/bugzilla/show_bug.cgi?id=38569
public void testStandaloneAmphersand() {
- assertEquals("<P&O>", StringEscapeUtils.unescapeHtml("<P&O>"));
- assertEquals("test & <", StringEscapeUtils.unescapeHtml("test & <"));
+ assertEquals("<P&O>", StringEscapeUtils.unescapeHtml4("<P&O>"));
+ assertEquals("test & <", StringEscapeUtils.unescapeHtml4("test & <"));
assertEquals("<P&O>", StringEscapeUtils.unescapeXml("<P&O>"));
assertEquals("test & <", StringEscapeUtils.unescapeXml("test & <"));
}
public void testLang313() {
- assertEquals("& &", StringEscapeUtils.unescapeHtml("& &"));
+ assertEquals("& &", StringEscapeUtils.unescapeHtml4("& &"));
}
public void testEscapeCsvString() throws Exception
@@ -361,7 +361,7 @@
private void checkCsvEscapeWriter(String expected, String value) {
try {
StringWriter writer = new StringWriter();
- StringEscapeUtils.escapeCsv(writer, value);
+ StringEscapeUtils.ESCAPE_CSV.translate(value, writer);
assertEquals(expected, writer.toString());
} catch (IOException e) {
fail("Threw: " + e);
@@ -397,7 +397,7 @@
private void checkCsvUnescapeWriter(String expected, String value) {
try {
StringWriter writer = new StringWriter();
- StringEscapeUtils.unescapeCsv(writer, value);
+ StringEscapeUtils.UNESCAPE_CSV.translate(value, writer);
assertEquals(expected, writer.toString());
} catch (IOException e) {
fail("Threw: " + e);
@@ -414,14 +414,14 @@
String original = new String(data, "UTF8");
- String escaped = StringEscapeUtils.escapeHtml( original );
+ String escaped = StringEscapeUtils.escapeHtml4( original );
assertEquals( "High unicode should not have been escaped", original, escaped);
- String unescaped = StringEscapeUtils.unescapeHtml( escaped );
+ String unescaped = StringEscapeUtils.unescapeHtml4( escaped );
assertEquals( "High unicode should have been unchanged", original, unescaped);
// TODO: I think this should hold, needs further investigation
-// String unescapedFromEntity = StringEscapeUtils.unescapeHtml( "𝍢" );
+// String unescapedFromEntity = StringEscapeUtils.unescapeHtml4( "𝍢" );
// assertEquals( "High unicode should have been unescaped", original, unescapedFromEntity);
}
@@ -429,11 +429,11 @@
public void testEscapeHiragana() throws java.io.UnsupportedEncodingException {
// Some random Japanese unicode characters
String original = "\u304B\u304C\u3068";
- String escaped = StringEscapeUtils.escapeHtml(original);
- assertEquals( "Hiragana character unicode behaviour should not be being escaped by escapeHtml",
+ String escaped = StringEscapeUtils.escapeHtml4(original);
+ assertEquals( "Hiragana character unicode behaviour should not be being escaped by escapeHtml4",
original, escaped);
- String unescaped = StringEscapeUtils.unescapeHtml( escaped );
+ String unescaped = StringEscapeUtils.unescapeHtml4( escaped );
assertEquals( "Hiragana character unicode behaviour has changed - expected no unescaping", escaped, unescaped);
}