编辑距离算法增加编辑信息返回

最新推荐文章于 2024-07-24 20:44:05 发布

天使手儿

最新推荐文章于 2024-07-24 20:44:05 发布

阅读量125

点赞数 3

文章标签：算法

本文链接：https://blog.csdn.net/qq_42893430/article/details/136719294

版权

本文介绍了Levenshtein距离类的实现，用于计算两个字符串之间的最小编辑距离，通过动态规划方法追踪并记录所需的编辑操作，包括插入、删除和替换。

摘要由CSDN通过智能技术生成

/**
     * 编辑距离类
     *
     */
    class EditOperation {
        private int index;
        private String originalChar;
        private String newChar;
        private String operation;

        public EditOperation(int index, String originalChar, String newChar, String operation) {
            this.index = index;
            this.originalChar = originalChar;
            this.newChar = newChar;
            this.operation = operation;
        }

        public int getIndex() {
            return index;
        }

        public void setIndex(int index) {
            this.index = index;
        }

        public String getOriginalChar() {
            return originalChar;
        }

        public void setOriginalChar(String originalChar) {
            this.originalChar = originalChar;
        }

        public String getNewChar() {
            return newChar;
        }

        public void setNewChar(String newChar) {
            this.newChar = newChar;
        }

        public String getOperation() {
            return operation;
        }

        public void setOperation(String operation) {
            this.operation = operation;
        }
    }

private List<EditOperation> levenshtein(String str1, String str2) {
        int[][] dp = new int[str1.length() + 1][str2.length() + 1];
        List<EditOperation> operations = new ArrayList<>();
        // 初始化边界情况
        for (int i = 0; i <= str1.length(); i++) {
            dp[i][0] = i;
        }
        for (int j = 0; j <= str2.length(); j++) {
            dp[0][j] = j;
        }
        // 计算Levenshtein距离
        for (int i = 1; i <= str1.length(); i++) {
            for (int j = 1; j <= str2.length(); j++) {
                int cost = str1.charAt(i - 1) == str2.charAt(j - 1) ? 0 : 1;
                dp[i][j] = Math.min(
                        Math.min(dp[i - 1][j] + 1, dp[i][j - 1] + 1), dp[i - 1][j - 1] + cost);
            }
        }
        // 回溯以确定编辑操作
        int i = str1.length();
        int j = str2.length();
        while (i > 0 && j > 0) {
            int cost = str1.charAt(i - 1) == str2.charAt(j - 1) ? 0 : 1;
            if (dp[i][j] == dp[i - 1][j] + 1) {
                // deletion
                operations.add(new EditOperation(i - 1, str1.substring(i - 1, i),
                        "DELETE", "DELETE"));
                i--;
            } else if (dp[i][j] == dp[i][j - 1] + 1) {
                // insertion
                operations.add(new EditOperation(i - 1, "INSERT",
                        str2.substring(j - 1, j), "INSERT"));
                j--;
            } else if (dp[i][j] == dp[i - 1][j - 1] + cost) {
                if (cost == 1) {
                    // substitution
                    operations.add(new EditOperation(i - 1, str1.substring(i - 1, i),
                            str2.substring(j - 1, j), "SUBSTITUTE"));
                }
                i--;
                j--;
            }
        }
        // 添加剩余的插入或删除操作
        while (i > 0) {
            operations.add(new EditOperation(i - 1, str1.substring(i - 1, i),
                    "DELETE", "DELETE"));
            i--;
        }
        while (j > 0) {
            operations.add(new EditOperation(str1.length() - 1, "INSERT",
                    str2.substring(j - 1, j), "INSERT"));
            j--;
        }
        // 反转操作列表以获取正确的顺序
        Collections.reverse(operations);
        return operations;
}