normalisation snippets

Author: Mcbencrafter

snippets/java/string-manipulation/capitalize-words.md

@@ -0,0 +1,27 @@
+---
+title: Capitalize Words
+description: Capitalizes the first letter of each word in a string
+author: Mcbencrafter
+tags: string,capitalize,words
+---
+
+```java
+public static String capitalizeWords(String text) {
+    String[] words = text.split("(?<=\\S)(?=\\s+)|(?<=\\s+)(?=\\S)"); // this is needed to preserve spaces (text.split(" ") would remove multiple spaces)
+    StringBuilder capitalizedText = new StringBuilder();
+    
+    for (String word : words) {
+        if (word.trim().isEmpty()) {
+            capitalizedText.append(word);
+            continue;
+        }
+        capitalizedText.append(Character.toUpperCase(word.charAt(0)))
+                .append(word.substring(1));
+    }
+    
+    return capitalizedText.toString();
+}
+
+// Usage:
+System.out.println(capitalizeWords("hello  world")); // "Hello  World"
+```

snippets/java/string-manipulation/normalize-whitespace.md

@@ -0,0 +1,15 @@
+---
+title: Normalize Whitespace
+description: Replaces consecutive whitespaces with a single space
+author: Mcbencrafter
+tags: string,whitespace,normalize
+---
+
+```java
+public static String normalizeWhitespace(String text) {
+    return text.replaceAll(" {2,}", " ");
+}
+
+// Usage:
+System.out.println(normalizeWhitespace("hello   world")); // "hello world"
+```

snippets/java/string-manipulation/remove-punctuation.md

@@ -0,0 +1,15 @@
+---
+title: Remove Punctuation
+description: Removes punctuation (, . !) from a string
+author: Mcbencrafter
+tags: string,punctuation,clean,normalization
+---
+
+```java
+public static String removePunctuation(String text) {
+    return text.replaceAll("[,!.]", "");
+}
+
+// Usage:
+System.out.println(removePunctuation("hello, world!")); // "hello world"
+```

snippets/java/string-manipulation/remove-special-characters.md

@@ -0,0 +1,15 @@
+---
+title: Remove Special Characters
+description: Removes any character which is not alphabetic (A-Z, a-z) or numeric (0-9)
+author: Mcbencrafter
+tags: string,special-characters,clean,normalization
+---
+
+```java
+public static String removeSpecialCharacters(String text) {
+    return text.replaceAll("[^a-zA-Z0-9]", "");
+}
+
+// Usage:
+System.out.println(removeSpecialCharacters("hello, world!#%")); // "hello world"
+```