如何读取一列中包含多个值的 .csv 文件

Question

我的文件在一列中包含多个值。我试图用这个代码使用java读取这个文件：

ArrayList<String> linesList1 = new ArrayList<>();
ArrayList<String> roadlinkid = new ArrayList<>();
ArrayList<String> road_name_orignal = new ArrayList<>();
ArrayList<String> road_name_copy = new ArrayList<>();
ArrayList<String[]> networkmember_href = new ArrayList<>();
ArrayList<String> road_fid = new ArrayList<>();
// Input of file which needs to be parsed
String csvFile1 = "RoadData.csv";
BufferedReader csvReader1;
// Data split by ',' in CSV file
String csvSplitBy = ",";

try {
    String line;
    csvReader1 = new BufferedReader(new FileReader(csvFile1));
    while ((line = csvReader1.readLine()) !=null) {
        linesList1.add(line);
    }
    csvReader1.close();


} 
catch (IOException e) { e.printStackTrace(); } 

for (int i = 0; i < linesList1.size(); i++) {
    String[] data = linesList1.get(i).split(csvSplitBy);
     road_fid.add( data[1]);
     road_name_orignal.add( data[9]);
     if (data[9].contains("{")) {
         String[] xy = data[9].replaceAll("\\{|\\}", "").split(",");
         int leng = xy.length;
         String[] networkmember = new String [leng];
         for ( int n = 0 ; n < leng ; n++) {

             networkmember[n] = xy [n];
         }
     networkmember_href.add(networkmember);
     }


}

此代码运行良好，但问题是该代码将列中的每个值作为单独的列处理。因此，它返回错误的数据。

文件： http://s000.tinyupload.com/?file_id=47090134488569683648

想法是通过比较 RoadData.csv 中的 road_fid 和 RoadLink.csv 中的 roadlink_fid，从 RoadData.csv 中找到道路名称并将其写入 RoadLink.csv。不幸的是，我可以找到一种方法来处理具有多值的列。任何建议，请。

提前致谢。

Answer 1

以下是解析文件的一些代码，您可以添加额外的处理来解析其中包含列表的字段，或将changedate 和reasonforchange 等列表组合成包含这两个数据的对象列表。例如List<ChangeInfo>，其中ChangeInfo 包含changedate 和reasonforchange。

我仍然建议使用 csv 解析器，但这段代码对于这个特定用例应该足够好。彻底测试..

---

主要：

public static void main(String[] args){
    List<RoadLinkRecord> records = parse("path\\to\\RoadLink.csv");

    // display all the records
    for (RoadLinkRecord record : records) {
        System.out.println(record);
    }
}

---

CSV 解析：

private static final Pattern csvFieldPattern =
        Pattern.compile("(?<=[$,])(\"(\"\"|[^\"])*\"|[^,]*)");

/** This parse method requires the CSV file to have a header row */
public static List<RoadLinkRecord> parse(String csvFilePath) {
    // TODO accept Reader or maybe InputStream rather than file path
    File f = new File(csvFilePath);

    List<RoadLinkRecord> records = new ArrayList<>();

    try (BufferedReader br = new BufferedReader(new FileReader(f));) {
        // get the header fields
        String line = br.readLine();
        List<String> headers = new ArrayList<>();
        {
            Matcher matcher = csvFieldPattern.matcher(line);
            while (matcher.find())
                headers.add(matcher.group());
        }

        // iterate through record fields
        int recordNum = 0;
        while ((line = br.readLine()) != null) {
            recordNum++;

            // allocate array to hold the fields
            String[] fields = new String[headers.size()];
            // use matcher to get each of the fields
            Matcher matcher = csvFieldPattern.matcher(line);
            for (int i = 0; i < headers.size(); i++) {
                if (!matcher.find()) {
                    throw new IllegalArgumentException(
                            "Couldn't find field '" + headers.get(i) + "' for record " + recordNum);
                }
                fields[i] = matcher.group();
            }
            if (matcher.find()) {
                throw new IllegalArgumentException("Found excess fields in record " + recordNum);
            }

            // add the record from this line
            records.add(new RoadLinkRecord(recordNum, fields));
        }
    } catch (IOException e) {
        // TODO trouble reading the file
    } catch (IllegalArgumentException e) {
        // TODO error while parsing the file
    }

    return records;
}

---

数据容器：

public class RoadLinkRecord {
    private final int recordNumber;
    private final String roadlink_fid;
    private final String version;
    private final String versiondate;
    private final String changedate;
    private final String reasonforchange;
    private final String descriptivegroup;
    private final String descriptiveterm;
    private final String natureofroad;
    private final String length;
    private final String directednode_href;
    private final String directednode_orientation;
    private final String directednode_gradeseparation;
    private final String referencetotopographicarea_href;
    private final String theme;
    private final String filename;
    private final String wkb_geometry;
    private final String roadnumber;
    private final String dftname;
    private final String fid;
    private final String roadname;

    public RoadLinkRecord(final int recordNumber, final String[] csvFields) {
        if (csvFields.length != 20) {
            throw new IllegalArgumentException(
                    "Wrong number of fields for a RoadLinkRecord! Expected 20, found "
                            + csvFields.length);
        }
        this.recordNumber = recordNumber;

        this.roadlink_fid = processStringField(csvFields[0]);
        this.version = processStringField(csvFields[1]);
        this.versiondate = processStringField(csvFields[2]);
        this.changedate = processStringField(csvFields[3]);
        this.reasonforchange = processStringField(csvFields[4]);
        this.descriptivegroup = processStringField(csvFields[5]);
        this.descriptiveterm = processStringField(csvFields[6]);
        this.natureofroad = processStringField(csvFields[7]);
        this.length = processStringField(csvFields[8]);
        this.directednode_href = processStringField(csvFields[9]);
        this.directednode_orientation = processStringField(csvFields[10]);
        this.directednode_gradeseparation = processStringField(csvFields[11]);
        this.referencetotopographicarea_href = processStringField(csvFields[12]);
        this.theme = processStringField(csvFields[13]);
        this.filename = processStringField(csvFields[14]);
        this.wkb_geometry = processStringField(csvFields[15]);
        this.roadnumber = processStringField(csvFields[16]);
        this.dftname = processStringField(csvFields[17]);
        this.fid = processStringField(csvFields[18]);
        this.roadname = processStringField(csvFields[19]);
    }

    private static String processStringField(String field) {
        // consider empty fields as null
        if (field.isEmpty()) {
            return null;
        }
        // strip double quotes and replace any escaped quotes
        final int endIndex = field.length() - 1;
        if (field.charAt(0) == '"' && field.charAt(endIndex) == '"') {
            return field.substring(1, endIndex).replace("\"\"", "\"");
        }
        return field;
    }

    public int getRecordNumber() { return recordNumber; }
    public String getRoadlink_fid() { return roadlink_fid; }
    public String getVersion() { return version; }
    public String getVersiondate() { return versiondate; }
    public String getChangedate() { return changedate; }
    public String getReasonforchange() { return reasonforchange; }
    public String getDescriptivegroup() { return descriptivegroup; }
    public String getDescriptiveterm() { return descriptiveterm; }
    public String getNatureofroad() { return natureofroad; }
    public String getLength() { return length; }
    public String getDirectednode_href() { return directednode_href; }
    public String getDirectednode_orientation() { return directednode_orientation; }
    public String getDirectednode_gradeseparation() { return directednode_gradeseparation; }
    public String getReferencetotopographicarea_href() { return referencetotopographicarea_href; }
    public String getTheme() { return theme; }
    public String getFilename() { return filename; }
    public String getWkb_geometry() {     return wkb_geometry; }
    public String getRoadnumber() { return roadnumber; }
    public String getDftname() { return dftname; }
    public String getFid() { return fid; }
    public String getRoadname() { return roadname; }

    @Override
    public String toString() {
        return "roadlink_fid= " + roadlink_fid + "; version= " + version + "; versiondate= "
                + versiondate + "; changedate= " + changedate + "; reasonforchange= "
                + reasonforchange + "; descriptivegroup= " + descriptivegroup + "; descriptiveterm= "
                + descriptiveterm + "; natureofroad= " + natureofroad + "; length= " + length
                + "; directednode_href= " + directednode_href + "; directednode_orientation= "
                + directednode_orientation + "; directednode_gradeseparation= "
                + directednode_gradeseparation + "; referencetotopographicarea_href= "
                + referencetotopographicarea_href + "; theme= " + theme + "; filename= " + filename
                + "; wkb_geometry= " + wkb_geometry + "; roadnumber= " + roadnumber + "; dftname= "
                + dftname + "; fid= " + fid + "; roadname= " + roadname + ";";
    }
}