Java处理文本文件：根据首个字段删除重复行并存储

123456,greenwitch street,near dominos store,Opp sandwitch company,Neyork,US,876890
123480,Postwitch street,near KFC store,Opp masala company,Newyork,US,876891
123456,Newyork street,near 100th avenue,King master company,Texas,US,10005

import java.util.List;
import java.util.function.Function;
import java.util.stream.Collectors;

public class DeduplicateTextFile {

    public static void main(String[] args) {
        List<String> sourceList = List.of(
            "123456,greenwitch street,near dominos store,Opp sandwitch company,Neyork,US,876890",
            "123480,Postwitch street,near KFC store,Opp masala company,Newyork,US,876891",
            "123456,Newyork street,near 100th avenue,King master company,Texas,US,10005"
        );

        List<String> uniqueList = sourceList.stream()
            .collect(Collectors.toMap(
                str -> str.substring(0, str.indexOf(',')), // keyMapper: 提取第一个逗号前的子字符串作为键
                Function.identity(),                       // valueMapper: 将整个字符串作为值
                (existing, replacement) -> existing        // mergeFunction: 如果键重复，保留已存在的（即第一次遇到的）值
            ))
            .values()                                      // 获取Map中所有的值（即唯一的行字符串）
            .stream()
            .toList();                                     // 将结果收集到List中

        System.out.println("去重后的列表 (字符串):");
        uniqueList.forEach(System.out::println);
    }
}

import lombok.Builder;
import lombok.Getter;

@Builder
@Getter
public class Company {
    private long id;
    private String street;
    private String locationDescription;
    private String companyName;
    private String state;
    private String country;
    private String zipCode;

    /**
     * 将一行字符串解析为Company对象
     * @param line 待解析的字符串
     * @return 解析后的Company对象
     */
    public static Company parse(String line) {
        String[] arr = line.split(",");
        if (arr.length < 7) {
            throw new IllegalArgumentException("Invalid line format: " + line);
        }
        return Company.builder()
            .id(Long.parseLong(arr[0]))
            .street(arr[1]) // 补充street字段
            .locationDescription(arr[2])
            .companyName(arr[3])
            .state(arr[4])
            .country(arr[5])
            .zipCode(arr[6])
            .build();
    }

    @Override
    public String toString() {
        return id + "," + street + "," + locationDescription + "," + companyName + "," + state + "," + country + "," + zipCode;
    }
}

import java.util.List;
import java.util.function.Function;
import java.util.stream.Collectors;

// 假设Company类已定义如上

public class DeduplicateWithDomainObject {

    public static void main(String[] args) {
        List<String> sourceList = List.of(
            "123456,greenwitch street,near dominos store,Opp sandwitch company,Neyork,US,876890",
            "123480,Postwitch street,near KFC store,Opp masala company,Newyork,US,876891",
            "123456,Newyork street,near 100th avenue,King master company,Texas,US,10005"
        );

        List<Company> uniqueCompanies = sourceList.stream()
            .map(Company::parse)                           // 将每行字符串解析为Company对象
            .collect(Collectors.toMap(
                Company::getId,                            // keyMapper: 使用Company对象的id作为键
                Function.identity(),                       // valueMapper: 将Company对象本身作为值
                (existing, replacement) -> existing        // mergeFunction: 如果id重复，保留已存在的Company对象
            ))
            .values()
            .stream()
            .toList();

        System.out.println("\n去重后的列表 (Company对象):");
        uniqueCompanies.forEach(System.out::println);
    }
}

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.List;
import java.util.stream.Collectors;

public class FileReaderExample {

    public static List<String> readLinesFromFile(String filePath) throws IOException {
        return Files.lines(Paths.get(filePath))
                    .collect(Collectors.toList());
    }

    public static void main(String[] args) {
        String filePath = "data.txt"; // 替换为你的文件路径
        // 假设data.txt文件内容如示例所示

        try {
            List<String> allLines = readLinesFromFile(filePath);
            // 接下来可以将allLines传递给上述的去重方法
            System.out.println("从文件读取的行数: " + allLines.size());
            // ... 进行去重操作
        } catch (IOException e) {
            System.err.println("读取文件时发生错误: " + e.getMessage());
        }
    }
}