预览CSV文件

UnicodeReader工具类

package com.example.file.file;


/**
 version: 1.1 / 2007-01-25
 - changed BOM recognition ordering (longer boms first)

 Original pseudocode   : Thomas Weidenfeller
 Implementation tweaked: Aki Nieminen

 http://www.unicode.org/unicode/faq/utf_bom.html
 BOMs:
 00 00 FE FF    = UTF-32, big-endian
 FF FE 00 00    = UTF-32, little-endian
 EF BB BF       = UTF-8,
 FE FF          = UTF-16, big-endian
 FF FE          = UTF-16, little-endian

 Win2k Notepad:
 Unicode format = UTF-16LE
 ***/

import java.io.*;

/**
 * Generic unicode textreader, which will use BOM mark
 * to identify the encoding to be used. If BOM is not found
 * then use a given default or system encoding.
 */
public class UnicodeReader extends Reader {
    PushbackInputStream internalIn;
    InputStreamReader internalIn2 = null;
    String defaultEnc;

    private static final int BOM_SIZE = 4;

    /**
     * @param in         inputstream to be read
     * @param defaultEnc default encoding if stream does not have
     *                   BOM marker. Give NULL to use system-level default.
     */
    public UnicodeReader(InputStream in, String defaultEnc) {
        internalIn = new PushbackInputStream(in, BOM_SIZE);
        this.defaultEnc = defaultEnc;
    }

    public String getDefaultEncoding() {
        return defaultEnc;
    }

    /**
     * Get stream encoding or NULL if stream is uninitialized.
     * Call init() or read() method to initialize it.
     */
    public String getEncoding() {
        if (internalIn2 == null) return null;
        return internalIn2.getEncoding();
    }

    /**
     * Read-ahead four bytes and check for BOM marks. Extra bytes are
     * unread back to the stream, only BOM bytes are skipped.
     */
    protected void init() throws IOException {
        if (internalIn2 != null) return;

        String encoding;
        byte bom[] = new byte[BOM_SIZE];
        int n, unread;
        n = internalIn.read(bom, 0, bom.length);

        if ((bom[0] == (byte) 0x00) && (bom[1] == (byte) 0x00) &&
                (bom[2] == (byte) 0xFE) && (bom[3] == (byte) 0xFF)) {
            encoding = "UTF-32BE";
            unread = n - 4;
        } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE) &&
                (bom[2] == (byte) 0x00) && (bom[3] == (byte) 0x00)) {
            encoding = "UTF-32LE";
            unread = n - 4;
        } else if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB) &&
                (bom[2] == (byte) 0xBF)) {
            encoding = "UTF-8";
            unread = n - 3;
        } else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) {
            encoding = "UTF-16BE";
            unread = n - 2;
        } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) {
            encoding = "UTF-16LE";
            unread = n - 2;
        } else {
            // Unicode BOM mark not found, unread all bytes
            encoding = defaultEnc;
            unread = n;
        }
        //System.out.println("read=" + n + ", unread=" + unread);

        if (unread > 0) internalIn.unread(bom, (n - unread), unread);

        // Use given encoding
        if (encoding == null) {
            internalIn2 = new InputStreamReader(internalIn);
        } else {
            internalIn2 = new InputStreamReader(internalIn, encoding);
        }
    }

    public void close() throws IOException {
        init();
        internalIn2.close();
    }

    public int read(char[] cbuf, int off, int len) throws IOException {
        init();
        return internalIn2.read(cbuf, off, len);
    }

}

主程序类

package com.example.file.file;


import com.csvreader.CsvReader;
import java.io.*;
import java.util.ArrayList;

public class PreviewChunkCSV {

    public static void main(String[] args) throws IOException {
        // 文件的路径
        File file = new File("C:\\Users\\86130\\Desktop\\仙启产品工具包\\工作簿1.csv");
        // 用来保存数据
        ArrayList<String[]> csvFileList = new ArrayList<>();

        // 文件编码格式
        String filecharset = getFilecharset(new FileInputStream(file));

        // 定义一个CSV路径
        UnicodeReader breader = new UnicodeReader(new FileInputStream(file), filecharset);

        CsvReader csvReader = new CsvReader(breader);

// 若只获得 数据的BODY(字节码文件)
// InputStream inputStream = new //ByteArrayInputStream(fileDescriptor.getBody().toByteArray());
 // BufferedReader breader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"), 8192);
        // 跳过表头  需要表头 忽略这一句
        csvReader.readHeaders();

        // 获取 表头
        String[] headers = csvReader.getHeaders();
        ArrayList<String> mRowList = new ArrayList<>();

        // 获取 最多40列表头、200行数据
        int headCount = 40;
        int rowCount = 200;
        if (headers.length < headCount){
            headCount = headers.length;
        }
        // 全部表头
        String[] mHeadArray = new String[headers.length];
        // 展示的表头
        String[] showHeadArray = new String[headCount];

        for(int i = 0; i < headers.length; i++){
            mHeadArray[i] = headers[i];
        }
        for (int i = 0; i < headCount; i++){
            showHeadArray[i] = headers[i];
        }

        // 逐行读取除表头的数据
        while (csvReader.readRecord()){
            csvFileList.add(csvReader.getValues());
        }
        csvReader.close();

        if (csvFileList.size() < 200){
            rowCount = csvFileList.size();
        }
        // 遍历读取CSV文件
        for (int row = 0; row < rowCount; row++){
            String rowItem = "";
            for (int i = 0; i < headCount; i++){
                // 获取第 row 行 第0列的数据
                String cell = "";
                if (i < headCount-1){
                    cell = csvFileList.get(row)[i] + ",";
                }else {
                    cell = csvFileList.get(row)[i];
                }
                rowItem = rowItem + cell;
            }
            mRowList.add(rowItem);
        }
        System.out.println("==================表头===========================");
        System.out.println(mHeadArray);
        System.out.println("==================展示的表头======================");
        System.out.println(showHeadArray);
        System.out.println("==================mRowList======================");
        System.out.println(mRowList);
        System.out.println("==================展示的行数======================");
        System.out.println(mRowList.size());
    }
    private static String getFilecharset(InputStream inputStream) {
        //默认GBK
        String charset = "GBK";
        byte[] first3Bytes = new byte[3];
        try (BufferedInputStream bis = new BufferedInputStream(inputStream)) {
            bis.mark(0);
            int read = bis.read(first3Bytes, 0, 3);
            // 文件编码为 ANSI
            if (read == -1) {
                return charset;
            }
            // 文件编码为 Unicode
            if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
                return "UTF-16LE";
            }
            // 文件编码为 Unicode big endian
            if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1] == (byte) 0xFF) {
                return "UTF-16BE";
            }
            // 文件编码为 UTF-8
            if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1] == (byte) 0xBB && first3Bytes[2] == (byte) 0xBF) {
                return "UTF-8";
            }
            bis.reset();

            int loc = 0;
            while ((read = bis.read()) != -1) {
                loc++;
                if (read >= 0xF0) {
                    break;
                }
                // 单独出现BF以下的，也算是GBK
                if (0x80 <= read && read <= 0xBF) {
                    break;
                }
                if (0xC0 <= read && read <= 0xDF) {
                    read = bis.read();
                    // 双字节 (0xC0 - 0xDF)
                    if (0x80 <= read && read <= 0xBF) {
                        // (0x80
                        // - 0xBF),也可能在GB编码内
                        continue;
                    }
                    break;
                }
                // 也有可能出错，但是几率较小
                if (0xE0 <= read && read <= 0xEF) {
                    read = bis.read();
                    if (0x80 <= read && read <= 0xBF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) {
                            charset = "UTF-8";
                        }
                    }
                    break;
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return charset;
    }
}