gnodet commented on code in PR #2071:
URL: https://github.com/apache/maven/pull/2071#discussion_r1935325435
##########
compat/maven-artifact/src/main/java/org/apache/maven/artifact/versioning/ComparableVersion.java:
##########
@@ -687,7 +700,8 @@ public final void parseVersion(String version) {
stack.push(list);
}
isCombination = false;
- } else if (Character.isDigit(c)) {
+ // TODO we might not want to use isDigit here; just check for
ASCII digits only
+ } else if (c >= '0' && c <= '9') {
Review Comment:
Something like the following maybe ?
```java
@SuppressWarnings("checkstyle:innerassignment")
public final void parseVersion(String version) {
this.value = version;
items = new ListItem();
version = version.toLowerCase(Locale.ENGLISH);
ListItem list = items;
Deque<Item> stack = new ArrayDeque<>();
stack.push(list);
boolean isDigit = false;
boolean isCombination = false;
int startIndex = 0;
StringBuilder normalizedBuffer = new StringBuilder();
for (int i = 0; i < version.length(); i++) {
char character = version.charAt(i);
int c = character;
// Handle high surrogate
if (Character.isHighSurrogate(character)) {
try {
char low = version.charAt(i + 1);
char[] both = {character, low};
c = Character.codePointAt(both, 0);
i++;
} catch (IndexOutOfBoundsException ex) {
// Treat high surrogate without low surrogate as a regular
character
}
}
// Normalize the Unicode digits (including supplemental plane
characters) using Character.digit()
if (Character.isDigit(c)) {
// Normalize Unicode digits to ASCII digits
int normalizedDigit = Character.digit(c, 10);
if (normalizedDigit != -1) {
c = normalizedDigit + '0'; // Convert digit to its ASCII
equivalent
}
}
// Build the normalized substring on the fly
if (c == '.' || c == '-' || i == version.length() - 1) {
// If we've reached a separator or the end of the string,
process the current segment
if (i == startIndex && c != '-') {
list.add(IntItem.ZERO); // Handle empty sections
} else {
// Add the current segment to the list after normalizing it
list.add(parseItem(isCombination, isDigit,
normalizedBuffer.toString()));
}
isCombination = false;
normalizedBuffer.setLength(0); // Reset the buffer for the next
segment
startIndex = i + 1;
// Handle separators
if (c == '-' && !list.isEmpty()) {
list.add(list = new ListItem());
stack.push(list);
}
} else if (c >= '0' && c <= '9') {
if (!isDigit && i > startIndex) {
// Handle combination of a letter and number, like "X1"
isCombination = true;
if (!list.isEmpty()) {
list.add(list = new ListItem());
stack.push(list);
}
}
isDigit = true;
} else {
if (isDigit && i > startIndex) {
list.add(parseItem(isCombination, true,
normalizedBuffer.toString()));
normalizedBuffer.setLength(0); // Reset buffer
startIndex = i;
list.add(list = new ListItem());
stack.push(list);
isCombination = false;
}
isDigit = false;
}
// Append the current character to the normalized buffer
normalizedBuffer.append((char) c);
}
if (version.length() > startIndex) {
// Final segment (if any)
if (!isDigit && !list.isEmpty()) {
list.add(list = new ListItem());
stack.push(list);
}
list.add(parseItem(isCombination, isDigit,
normalizedBuffer.toString()));
}
while (!stack.isEmpty()) {
list = (ListItem) stack.pop();
list.normalize();
}
}
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@maven.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
