Apache
/
commons-lang
mirror of https://github.com/apache/commons-lang.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LANG-877: Performance improvements for StringEscapeUtils. This fixes #49 from github. Thanks to Fabian Lange. 

git-svn-id: https://svn.apache.org/repos/asf/commons/proper/lang/trunk@1666535 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Benedikt Ritter 2015-03-13 18:18:59 +00:00
parent a234f033b6
commit 1f75a8f7cc
5 changed files with 30 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/changes/changes.xml
View File

@ -22,6 +22,7 @@
<body>
<release version="3.4" date="tba" description="tba">
<action issue="LANG-877" type="add" dev="britter" due-to="Fabian Lange">Performance improvements for StringEscapeUtils</action>
<action issue="LANG-1093" type="add" dev="britter" due-to="Fabian Lange">Add ClassUtils.getAbbreviatedName()</action>
<action issue="LANG-1090" type="fix" dev="sebb">FastDateParser does not set error indication in ParsePosition</action>
<action issue="LANG-1089" type="fix" dev="sebb">FastDateParser does not handle excess hours as per SimpleDateFormat</action>

17
src/main/java/org/apache/commons/lang3/CharUtils.java
View File

@ -31,6 +31,8 @@ public class CharUtils {
private static final String[] CHAR_STRING_ARRAY = new String[128];
private static final char[] HEX_DIGITS = new char[] {'0','1','2','3','4','5','6','7','8','9','a','b','c','d','e','f'};
/**
* {@code \u000a} linefeed LF ('\n').
*
@ -350,14 +352,13 @@ public class CharUtils {
* @return the escaped Unicode string
*/
public static String unicodeEscaped(final char ch) {
if (ch < 0x10) {
return "\\u000" + Integer.toHexString(ch);
} else if (ch < 0x100) {
return "\\u00" + Integer.toHexString(ch);
} else if (ch < 0x1000) {
return "\\u0" + Integer.toHexString(ch);
}
return "\\u" + Integer.toHexString(ch);
StringBuilder sb = new StringBuilder(6);
sb.append("\\u");
sb.append(HEX_DIGITS[(ch >> 12) & 15]);
sb.append(HEX_DIGITS[(ch >> 8) & 15]);
sb.append(HEX_DIGITS[(ch >> 4) & 15]);
sb.append(HEX_DIGITS[(ch) & 15]);
return sb.toString();
}
/**

17
src/main/java/org/apache/commons/lang3/text/translate/CharSequenceTranslator.java
View File

@ -31,6 +31,8 @@ import java.util.Locale;
*/
public abstract class CharSequenceTranslator {
static final char[] HEX_DIGITS = new char[] {'0','1','2','3','4','5','6','7','8','9','A','B','C','D','E','F'};
/**
* Translate a set of codepoints, represented by an int index into a CharSequence,
* into another set of codepoints. The number of codepoints consumed must be returned,
@ -84,9 +86,18 @@ public abstract class CharSequenceTranslator {
while (pos < len) {
final int consumed = translate(input, pos, out);
if (consumed == 0) {
final char[] c = Character.toChars(Character.codePointAt(input, pos));
out.write(c);
pos+= c.length;
// inlined implementation of Character.toChars(Character.codePointAt(input, pos))
// avoids allocating temp char arrays and duplicate checks
char c1 = input.charAt(pos);
out.write(c1);
pos++;
if (Character.isHighSurrogate(c1) && pos < len) {
char c2 = input.charAt(pos);
if (Character.isLowSurrogate(c2)) {
out.write(c2);
pos++;
}
}
continue;
}
// contract with translators is that they have to understand codepoints

12
src/main/java/org/apache/commons/lang3/text/translate/UnicodeEscaper.java
View File

@ -114,14 +114,12 @@ public class UnicodeEscaper extends CodePointTranslator {
// TODO: Handle potential + sign per various Unicode escape implementations
if (codepoint > 0xffff) {
out.write(toUtf16Escape(codepoint));
} else if (codepoint > 0xfff) {
out.write("\\u" + hex(codepoint));
} else if (codepoint > 0xff) {
out.write("\\u0" + hex(codepoint));
} else if (codepoint > 0xf) {
out.write("\\u00" + hex(codepoint));
} else {
out.write("\\u000" + hex(codepoint));
out.write("\\u");
out.write(HEX_DIGITS[(codepoint >> 12) & 15]);
out.write(HEX_DIGITS[(codepoint >> 8) & 15]);
out.write(HEX_DIGITS[(codepoint >> 4) & 15]);
out.write(HEX_DIGITS[(codepoint) & 15]);
}
return true;
}

1
src/test/java/org/apache/commons/lang3/CharUtilsTest.java
View File

@ -194,6 +194,7 @@ public class CharUtilsTest {
@Test
public void testToUnicodeEscaped_char() {
assertEquals("\\u0041", CharUtils.unicodeEscaped('A'));
assertEquals("\\u004c", CharUtils.unicodeEscaped('L'));
for (int i = 0; i < 196; i++) {
final String str = CharUtils.unicodeEscaped((char) i);