Java字符串从基础到KMP算法实战指南

String str1 = "Hello";

String str2 = new String("World");

char[] charArray = {'J', 'a', 'v', 'a'};
String str3 = new String(charArray);

int length = str1.length();

String combined = str1.concat(str2);

boolean isEqual = str1.equals(str2);
boolean ignoreCase = str1.equalsIgnoreCase("hello");

String sub = str1.substring(1, 3);

int index = str1.indexOf('e');
boolean contains = str1.contains("ell");

String numStr = String.valueOf(123);

int num = Integer.parseInt("456");
double d = Double.parseDouble("3.14");

StringBuilder sb = new StringBuilder();
sb.append("Hello");
sb.append(" ");
sb.append("World");
String result = sb.toString();

String formatted = String.format("Name: %s, Age: %d", "Alice", 25);

System.out.printf("Value: %.2f%n", 3.14159);

boolean matches = "123-45-6789".matches("\\d{3}-\\d{2}-\\d{4}");

String[] parts = "apple,orange,banana".split(",");

byte[] utf8Bytes = str1.getBytes(StandardCharsets.UTF_8);
String decoded = new String(utf8Bytes, StandardCharsets.UTF_8);

public class KMP {
    // 构建部分匹配表（next数组）
    private static int[] buildNext(String pattern) {
        int[] next = new int[pattern.length()];
        next[0] = -1; // 初始化
        int i = 0, j = -1;
        while (i < pattern.length() - 1) {
            if (j == -1 || pattern.charAt(i) == pattern.charAt(j)) {
                i++;
                j++;
                next[i] = j;
            } else {
                j = next[j];
            }
        }
        return next;
    }
    // KMP匹配算法
    public static int kmpSearch(String text, String pattern) {
        int[] next = buildNext(pattern);
        int i = 0, j = 0;
        while (i < text.length() && j < pattern.length()) {
            if (j == -1 || text.charAt(i) == pattern.charAt(j)) {
                i++;
                j++;
            } else {
                j = next[j];
            }
        }
        return j == pattern.length() ? i - j : -1;
    }
    public static void main(String[] args) {
        String text = "ABABDABACDABABCABAB";
        String pattern = "ABABCABAB";
        int index = kmpSearch(text, pattern);
        System.out.println("匹配起始位置: " + index); // 输出: 10
    }
}

public class KMP {
    private int[] computeLPS(String pattern) {
        int[] lps = new int[pattern.length()];
        int len = 0;
        for (int i = 1; i < pattern.length(); ) {
            if (pattern.charAt(i) == pattern.charAt(len)) {
                lps[i++] = ++len;
            } else {
                if (len != 0) len = lps[len - 1];
                else lps[i++] = 0;
            }
        }
        return lps;
    }
    public List<Integer> search(String text, String pattern) {
        List<Integer> matches = new ArrayList<>();
        int[] lps = computeLPS(pattern);
        int i = 0, j = 0;
        while (i < text.length()) {
            if (text.charAt(i) == pattern.charAt(j)) {
                i++;
                j++;
            }
            if (j == pattern.length()) {
                matches.add(i - j);
                j = lps[j - 1];
            } else if (i < text.length() && text.charAt(i) != pattern.charAt(j)) {
                if (j != 0) j = lps[j - 1];
                else i++;
            }
        }
        return matches;
    }
}

Pattern dnaPattern = Pattern.compile("[ATCG]+");
Matcher matcher = dnaPattern.matcher(inputSequence);

Pattern lazyPattern = Pattern.compile("A+?C+?G+?"); // 懒惰匹配

Pattern boundaryPattern = Pattern.compile("^ATG[ATCG]{3,}TAA$");

List<DNASequence> sequences = ...; // 待匹配序列集合
sequences.parallelStream()
         .filter(s -> dnaPattern.matcher(s).find())
         .collect(Collectors.toList());