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

Rewriting OctalUnescaper as a hand rolled parser (all of 4 characters), instead of trying to handle the conversion via repeated attempts to convert the numbers. This fixes bugs, see LANG-929, and also changes the behaviour for 'illegal' octals such as \999. Instead of throwing NumberFormatException, it will now ignore them. This seems the better behaviour. 

git-svn-id: https://svn.apache.org/repos/asf/commons/proper/lang/trunk@1535914 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Henri Yandell 2013-10-26 02:45:39 +00:00
parent 6ea7f2f7af
commit 2550d4cfa2
2 changed files with 29 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
src/main/java/org/apache/commons/lang3/text/translate/OctalUnescaper.java
View File

@ -40,25 +40,34 @@ public class OctalUnescaper extends CharSequenceTranslator {
*/
@Override
public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
if(input.charAt(index) == '\\' && index < (input.length() - 1) && Character.isDigit(input.charAt(index + 1)) ) {
final int start = index + 1;
int remaining = input.length() - index - 1; // how many characters left, ignoring the first \
StringBuilder builder = new StringBuilder();
if(input.charAt(index) == '\\' && remaining > 0 && isOctalDigit(input.charAt(index + 1)) ) {
int next = index + 1;
int next2 = index + 2;
int next3 = index + 3;
int end = index + 2;
while ( end < input.length() && Character.isDigit(input.charAt(end)) ) {
end++;
if ( Integer.parseInt(input.subSequence(start, end).toString(), 10) > OCTAL_MAX) {
end--; // rollback
break;
}
// only 3 characters applicable for Octal
if (end - start >= 3) {
break;
// we know this is good as we checked it in the if block above
builder.append(input.charAt(next));
if(remaining > 1 && isOctalDigit(input.charAt(next2))) {
builder.append(input.charAt(next2));
if(remaining > 2 && isZeroToThree(input.charAt(next)) && isOctalDigit(input.charAt(next3))) {
builder.append(input.charAt(next3));
}
}
out.write( Integer.parseInt(input.subSequence(start, end).toString(), 8) );
return 1 + end - start;
out.write( Integer.parseInt(builder.toString(), 8) );
return 1 + builder.length();
}
return 0;
}
private boolean isOctalDigit(char ch) {
return ch >= '0' && ch <= '7';
}
private boolean isZeroToThree(char ch) {
return ch >= '0' && ch <= '3';
}
}

17
src/test/java/org/apache/commons/lang3/text/translate/OctalUnescaperTest.java
View File

@ -69,19 +69,14 @@ public class OctalUnescaperTest {
input = "\\0003";
result = oue.translate(input);
assertEquals("Failed to unescape octal characters via the between method", "\000" + "3", result);
}
@Test
public void testOutOfRange() {
final OctalUnescaper oue = new OctalUnescaper();
input = "\\279";
result = oue.translate(input);
assertEquals("Failed to unescape octal characters via the between method", "\279", result);
String input = "\\999";
try {
String result = oue.translate(input);
fail("NumberFormatException was expected for input: " + input);
} catch(NumberFormatException nfe) {
// expected
}
input = "\\999";
result = oue.translate(input);
assertEquals("Failed to ignore an out of range octal character via the between method", "\\999", result);
}
}