Skip to content

Count code points, not UTF-16 units, in XPath string functions #298

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SABITHSAHEB wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Count code points, not UTF-16 units, in XPath string functions #298

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 23 additions & 15 deletions src/main/java/org/apache/commons/jxpath/ri/compiler/CoreFunction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -650,7 +650,7 @@ protected Object functionStringLength(final EvalContext context) {
assertArgCount(1);
s = InfoSetUtil.stringValue(getArg1().computeValue(context));
}
return Double.valueOf(s.length());
return Double.valueOf(s.codePointCount(0, s.length()));
}

/**
Expand All @@ -665,19 +665,20 @@ protected Object functionSubstring(final EvalContext context) {
assertArgRange(minArgs, maxArgs);
final int ac = getArgumentCount();
final String s1 = InfoSetUtil.stringValue(getArg1().computeValue(context));
final int s1Length = s1.codePointCount(0, s1.length());
double from = InfoSetUtil.doubleValue(getArg2().computeValue(context));
if (Double.isNaN(from)) {
return "";
}
from = Math.round(from);
if (from > s1.length() + 1) {
if (from > s1Length + 1) {
return "";
}
if (ac == 2) {
if (from < 1) {
from = 1;
}
return s1.substring((int) from - 1);
return s1.substring(s1.offsetByCodePoints(0, (int) from - 1));
}
double length = InfoSetUtil.doubleValue(getArg3().computeValue(context));
length = Math.round(length);
Expand All @@ -688,16 +689,16 @@ protected Object functionSubstring(final EvalContext context) {
if (to < 1) {
return "";
}
if (to > s1.length() + 1) {
if (to > s1Length + 1) {
if (from < 1) {
from = 1;
}
return s1.substring((int) from - 1);
return s1.substring(s1.offsetByCodePoints(0, (int) from - 1));
}
if (from < 1) {
from = 1;
}
return s1.substring((int) from - 1, (int) (to - 1));
return s1.substring(s1.offsetByCodePoints(0, (int) from - 1), s1.offsetByCodePoints(0, (int) (to - 1)));
}

/**
Expand Down Expand Up @@ -770,20 +771,27 @@ protected Object functionTranslate(final EvalContext context) {
final String s1 = InfoSetUtil.stringValue(getArg1().computeValue(context));
final String s2 = InfoSetUtil.stringValue(getArg2().computeValue(context));
final String s3 = InfoSetUtil.stringValue(getArg3().computeValue(context));
final char[] chars = s1.toCharArray();
int out = 0;
for (int in = 0; in < chars.length; in++) {
final char c = chars[in];
final int inx = s2.indexOf(c);
final int[] codePoints = s1.codePoints().toArray();
final int[] fromCodePoints = s2.codePoints().toArray();
final int[] toCodePoints = s3.codePoints().toArray();
final StringBuilder buffer = new StringBuilder(s1.length());
for (final int c : codePoints) {
int inx = -1;
for (int i = 0; i < fromCodePoints.length; i++) {
if (fromCodePoints[i] == c) {
inx = i;
break;
}
}
if (inx != -1) {
if (inx < s3.length()) {
chars[out++] = s3.charAt(inx);
if (inx < toCodePoints.length) {
buffer.appendCodePoint(toCodePoints[inx]);
}
} else {
chars[out++] = c;
buffer.appendCodePoint(c);
}
}
return new String(chars, 0, out);
return buffer.toString();
}

/**
Expand Down
15 changes: 15 additions & 0 deletions src/test/java/org/apache/commons/jxpath/ri/compiler/CoreFunctionTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,6 +132,21 @@ void testNumberConversionIsXPathConformant() {
assertXPathValue(context, "'1e3' = 1000", Boolean.FALSE);
}

@Test
void testStringFunctionsCountCodePoints() {
// U+1D11E MUSICAL SYMBOL G CLEF is one XPath character but two UTF-16 chars.
context.getVariables().declareVariable("clef", "𝄞abc");
assertXPathValue(context, "string-length($clef)", Double.valueOf(4));
assertXPathValue(context, "substring($clef, 2)", "abc");
assertXPathValue(context, "substring($clef, 1, 1)", "𝄞");
assertXPathValue(context, "substring($clef, 2, 2)", "ab");
assertXPathValue(context, "substring($clef, 0, 2)", "𝄞");
assertXPathValue(context, "substring($clef, 5)", "");
assertXPathValue(context, "translate($clef, 'a', '-')", "𝄞-bc");
assertXPathValue(context, "translate($clef, substring($clef, 1, 1), 'x')", "xabc");
assertXPathValue(context, "translate('abc', 'b', $clef)", "a𝄞c");
}

@Test
void testExtendedKeyFunction() {
context.setKeyManager(new ExtendedKeyManager() {
Expand Down