Java CSVFormat.parse方法代码示例

import org.apache.commons.csv.CSVFormat; //导入方法依赖的package包/类
public static BeamRecord csvLine2BeamRecord(
    CSVFormat csvFormat,
    String line,
    BeamRecordSqlType beamRecordSqlType) {
  List<Object> fieldsValue = new ArrayList<>(beamRecordSqlType.getFieldCount());
  try (StringReader reader = new StringReader(line)) {
    CSVParser parser = csvFormat.parse(reader);
    CSVRecord rawRecord = parser.getRecords().get(0);

    if (rawRecord.size() != beamRecordSqlType.getFieldCount()) {
      throw new IllegalArgumentException(String.format(
          "Expect %d fields, but actually %d",
          beamRecordSqlType.getFieldCount(), rawRecord.size()
      ));
    } else {
      for (int idx = 0; idx < beamRecordSqlType.getFieldCount(); idx++) {
        String raw = rawRecord.get(idx);
        fieldsValue.add(autoCastField(beamRecordSqlType.getFieldTypeByIndex(idx), raw));
      }
    }
  } catch (IOException e) {
    throw new IllegalArgumentException("decodeRecord failed!", e);
  }
  return new BeamRecord(beamRecordSqlType, fieldsValue);
}
 

import org.apache.commons.csv.CSVFormat; //导入方法依赖的package包/类
/**
 * Decodes data from the provided stream and invoke the provided {@link Consumer} for each decoded record.
 *
 * @param in          the {@link InputStream} for the CSV file
 * @param headers     a list of the headers to keep from decoded records
 * @param mapToResult the function to invoke for reach decoded record
 * @throws IOException                      in the event of an I/O error.
 * @throws DecodingDataFromAdapterException if an error occurred while decoding the CSV file.
 */
public void decode(InputStream in, List<String> headers, Consumer<DataSample<T>> mapToResult) throws IOException, DecodingDataFromAdapterException {
    try (Profiler ignored = Profiler.start("Building time series from csv data", logger::trace)) {
        try (BufferedReader reader = new BufferedReader(new InputStreamReader(in, encoding))) {
            CSVFormat csvFormat = CSVFormat.DEFAULT
                    .withAllowMissingColumnNames(false)
                    .withFirstRecordAsHeader()
                    .withSkipHeaderRecord()
                    .withDelimiter(delimiter);
            Iterable<CSVRecord> records = csvFormat.parse(reader);

            for (CSVRecord csvRecord : records) {
                ZonedDateTime timeStamp = dateParser.apply(csvRecord.get(0));
                DataSample<T> tRecord = new DataSample<>(timeStamp);
                for (String h : headers) {
                    tRecord.getCells().put(h, numberParser.apply(csvRecord.get(h)));
                }
                mapToResult.accept(tRecord);
            }
        }
    }
}
 

import org.apache.commons.csv.CSVFormat; //导入方法依赖的package包/类
/**
 * Returns the columns headers of the CSV file.
 *
 * @param in an input stream for the CSV file.
 * @return the columns headers of the CSV file.
 * @throws IOException                      in the event of an I/O error.
 * @throws DecodingDataFromAdapterException if an error occurred while decoding the CSV file.
 */
public List<String> getDataColumnHeaders(InputStream in) throws IOException, DecodingDataFromAdapterException {
    try (BufferedReader reader = new BufferedReader(new InputStreamReader(in, encoding))) {
        CSVFormat csvFormat = CSVFormat.DEFAULT
                .withAllowMissingColumnNames(false)
                .withDelimiter(delimiter);
        Iterable<CSVRecord> records = csvFormat.parse(reader);
        return this.parseColumnHeaders(records.iterator().next());
    }
}
 

import org.apache.commons.csv.CSVFormat; //导入方法依赖的package包/类
void readEntityDictionary(String filename, String charset, String type) {
    String absoluteFilename = IOUtils.getAbsoluteFile(getBaseDir(),filename);
    CSVFormat format = CSVFormat.RFC4180;
    format = format.withHeader();
    try {
        InputStream in = IOUtils.getInputStream(absoluteFilename);
        java.io.Reader reader = new InputStreamReader(in,charset);

        CSVParser parser = format.parse(reader);
        for(CSVRecord record :parser.getRecords()) {
            String entityName = record.get("name");
            String entityUrl = record.get("url");

            StringTokenizer tokenizer = new StringTokenizer(entityName);
            int tokenCount = 0;
            StringBuilder tokenPhrase = new StringBuilder();
            while(tokenizer.hasMoreTokens()) {

                String token = tokenizer.nextToken();
                if(dictionaryMap.size() < tokenCount+1) {
                    dictionaryMap.add(new HashMap<String, Entity>());
                }
                if(tokenCount > 0) {
                    tokenPhrase.append(" ");
                }
                tokenPhrase.append(token);

                Map<String,Entity> entityMap = dictionaryMap.get(tokenCount);
                Entity newEntity = new Entity(entityName, !tokenizer.hasMoreTokens());
                newEntity.setUrl(entityUrl);
                newEntity.setType(type);
                String key = normalize(tokenPhrase.toString());
                Entity entity = entityMap.get(key);
                if(entity == null) {
                    entityMap.put(key, newEntity);
                } else if(newEntity.getName().length() < entity.getName().length()) {
                    entityMap.put(key, newEntity);
                }

                tokenCount++;

            }

        }
        in.close();
    } catch (IOException e) {
        throw new RuntimeException(e);
    }


}
 

import org.apache.commons.csv.CSVFormat; //导入方法依赖的package包/类
@Override
public void init() {
    topicValues = new HashMap<String, HashSet<String>>();
    InputStream in = null;
    try {
        String filename = getProperty("filename", null);
        String absoluteFilename = IOUtils.getAbsoluteFile(getBaseDir(), filename);

        in = IOUtils.getInputStream(absoluteFilename);
        java.io.Reader reader = new InputStreamReader(in, StandardCharsets.UTF_8.name());

        CSVFormat format = CSVFormat.RFC4180
                                    .withHeader()
                                    .withDelimiter(',');

        CSVParser parser = format.parse(reader);
        Iterator<CSVRecord> csvIterator = parser.iterator();
        while(csvIterator.hasNext()) {
            CSVRecord record = csvIterator.next();
            String topic = record.get(0);
            String value = record.get(1);

            if(!topicValues.containsKey(topic)) {
                topicValues.put(topic, new HashSet<String>());
            }
            topicValues.get(topic).add(value);
        }
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
    finally {
        if(in != null){
            try {
                in.close();
            } catch (IOException ignored) {
            }
        }
    }

    fieldTopic = getProperty("fieldTopic", null);
    fieldValue = getProperty("fieldValue", null);

    super.init();
}
 

import org.apache.commons.csv.CSVFormat; //导入方法依赖的package包/类
@Override
public void init() {
    topicValues = new HashMap<String, HashSet<String>>();
    InputStream in = null;
    try {
        String filename = getProperty("filename", null);
        String absoluteFilename = IOUtils.getAbsoluteFile(getBaseDir(), filename);

        in = IOUtils.getInputStream(absoluteFilename);
        java.io.Reader reader = new InputStreamReader(in, StandardCharsets.UTF_8.name());

        CSVFormat format = CSVFormat.RFC4180
                                    .withHeader()
                                    .withDelimiter(',');

        CSVParser parser = format.parse(reader);
        Iterator<CSVRecord> csvIterator = parser.iterator();
        while(csvIterator.hasNext()) {
            CSVRecord record = csvIterator.next();
            String topic = record.get(0);
            String value = record.get(1).toLowerCase();

            if(!topicValues.containsKey(topic)) {
                topicValues.put(topic, new HashSet<String>());
            }
            topicValues.get(topic).add(value);
        }
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
    finally {
        if(in != null){
            try {
                in.close();
            } catch (IOException ignored) {
            }
        }
    }

    fieldTopic = getProperty("fieldTopic", null);
    fieldValue = getProperty("fieldValue", null);

    super.init();
}