Strip whitespace from a string/Top and tail: Difference between revisions

Content added Content deleted
(→‎{{header|Kotlin}}: Note about predicate)
(→‎{{header|Java}}: Iterating by code points)
Line 1,038: Line 1,038:
public static String ltrim(String s) {
public static String ltrim(String s) {
int i = 0;
int i = 0;
while (i < s.length() && Character.isWhitespace(s.charAt(i))){
while (i < s.length() && Character.isWhitespace(s.charAt(i))) {
i++;
i++;
}
}
Line 1,046: Line 1,046:
public static String rtrim(String s) {
public static String rtrim(String s) {
int i = s.length() - 1;
int i = s.length() - 1;
while (i > 0 && Character.isWhitespace(s.charAt(i))){
while (i > 0 && Character.isWhitespace(s.charAt(i))) {
i--;
i--;
}
}
Line 1,056: Line 1,056:
}
}


public static void main(String[] args){
public static void main(String[] args) {
String s = " \t \r \n String with spaces \u2009 \t \r \n ";
String s = " \t \r \n String with spaces \u2009 \t \r \n ";
System.out.printf("[%s]\n", ltrim(s));
System.out.printf("[%s]\n", ltrim(s));
Line 1,063: Line 1,063:
}
}
}</lang>
}</lang>

===Supplementary-correct version===
Unicode *happens* to not have any whitespace characters outside of Basic Multilingual Plane (aka, they all fit inside a <code>char</code>). However, this not something you should ''generally'' rely on, and should assume your strings contain characters in the Supplementary Planes. As such, instead of iterating using <code>String.charAt</code>, prefer instead using <code>String.codePointAt</code> and <code>String.codePointBefore</code>, iterating over actual Unicode Code Points:

<lang java> public static String ltrim(String s) {
int offset = 0;
while (offset < s.length()) {
int codePoint = s.codePointAt(offset);
if (!Character.isWhitespace(codePoint)) break;
offset += Character.charCount(codePoint);
}
return s.substring(offset);
}

public static String rtrim(String s) {
int offset = s.length();
while (offset > 0) {
int codePoint = s.codePointBefore(offset);
if (!Character.isWhitespace(codePoint)) break;
offset -= Character.charCount(codePoint);
}
return s.substring(0, offset);
}
</lang>


=={{header|Javascript}}==
=={{header|Javascript}}==
Retrieved from "https://rosettacode.org/wiki/Strip_whitespace_from_a_string/Top_and_tail"