Java CSVParser.close方法代码示例

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
public static void main(String[] args) throws IOException {
	CSVParser parser = CSVParser.parse(new File("dev/twitter-hate-speech-processed.csv"), Charset.forName("Cp1252"), CSVFormat.DEFAULT);
	try (PrintWriter writer = new PrintWriter("training/bad/model_comments_bad_tweets.txt", "UTF-8")) {
		boolean skipFirst = true;
		for (CSVRecord r : parser) {
			if (skipFirst){
				skipFirst=false;
				continue;
			}
			String classif = r.get(0);
			if (classif.equalsIgnoreCase("The tweet is not offensive")) {
				continue;
			}
			writer.println(r.get(2));
			
		}
	}finally {
		parser.close();
	}
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * String Parsing 
 */

public static String[] splitStr(String val, Integer len) throws IOException {
    
    String[] input;
    
    try {
        CSVParser parser = new CSVParser(new StringReader(val), CSVFormat.DEFAULT);
        CSVRecord record = parser.getRecords().get(0);
        input = new String[len];
        Iterator<String> valuesIt = record.iterator();
        int i = 0;
        while (valuesIt.hasNext()) {
            input[i] = valuesIt.next().trim();
            i++;
        }
        parser.close();
    } catch (ArrayIndexOutOfBoundsException e) {
        input = val.split(",", len);
        for (int i = 0; i < input.length; i++)
            input[i] = input[i].trim();
    }
    
    return input;
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * Adds labels read in a CSV file to the Jena model.
 * 
 * @param filePath The path of the CSV file.
 * @param version The version of the CPC classification.
 * @param language The tag representing the language of the labels ("fr", "es", etc.). 
 */
private void addLabels(String filePath, String version, String language) {

	if (filePath == null) return;

	logger.debug("Preparing to create additional labels for version " + version + ", language is " + language);
	try {
		Reader reader = new InputStreamReader(new FileInputStream(filePath), "Cp1252");
		CSVParser parser = new CSVParser(reader, CSVFormat.DEFAULT.withHeader());
		for (CSVRecord record : parser) {
			String itemCode = record.get(0);
			Resource itemResource = cpcModel.createResource(Names.getItemURI(itemCode, "CPC", version));
			itemResource.addProperty(SKOS.prefLabel, cpcModel.createLiteral(record.get(1), language));
		}
		parser.close();
		reader.close();
	} catch (Exception e) {
		logger.error("Error adding labels from " + filePath, e);
	}
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * Adds labels read in a CSV file to the Jena model.
 * 
 * @param filePath The path of the CSV file.
 * @param version The version of the ISIC classification.
 * @param language The tag representing the language of the labels ("fr", "es", etc.). 
 */
private void addLabels(String filePath, String version, String language) {

	if (filePath == null) return;

	logger.debug("Preparing to create additional labels, language is " + language + ", source file is " + filePath);
	try {
		Reader reader = new InputStreamReader(new FileInputStream(filePath), "Cp1252");
		CSVParser parser = new CSVParser(reader, ISIC_LABELS_FILE_FORMAT.get(version));
		for (CSVRecord record : parser) {
			String itemCode = record.get(0);
			Resource itemResource = isicModel.createResource(Names.getItemURI(itemCode, "ISIC", version));
			itemResource.addProperty(SKOS.prefLabel, isicModel.createLiteral(record.get(1), language));
		}
		parser.close();
		reader.close();
	} catch (Exception e) {
		logger.error("Error adding labels from " + filePath, e);
	}
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
static void parseFile(final String fileStr, final PublishSubject<Map<String, String>> subject) throws Exception {

        final CSVParser parser = CSVParser.parse(
            new File(fileStr), StandardCharsets.UTF_8, CSVFormat.DEFAULT
        );

        try {
            parser.forEach(csvRecord -> subject.onNext(toMap(csvRecord)));
            subject.onComplete();
        } finally {
            parser.close();
        }
    }
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
public void importData(DBHelper db, InputStreamReader input) throws IOException, FormatException, InterruptedException
{
    final CSVParser parser = new CSVParser(input, CSVFormat.RFC4180.withHeader());

    SQLiteDatabase database = db.getWritableDatabase();
    database.beginTransaction();

    try
    {
        for (CSVRecord record : parser)
        {
            importLoyaltyCard(database, db, record);

            if(Thread.currentThread().isInterrupted())
            {
                throw new InterruptedException();
            }
        }

        parser.close();
        database.setTransactionSuccessful();
    }
    catch(IllegalArgumentException|IllegalStateException e)
    {
        throw new FormatException("Issue parsing CSV data", e);
    }
    finally
    {
        database.endTransaction();
        database.close();
    }
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * test readCSV() function
 * @return
 */
public String readCSV(){
	StringBuffer sb = new StringBuffer();
	
	try{
		filePath = servletContext.getRealPath("WEB-INF/csv/pending.csv");
		
		File f = new File(filePath);
		
		System.out.println(f.exists());

		FileReader fr = new FileReader(f);
		CSVParser parser = new CSVParser(fr, CSVFormat.DEFAULT);
	   
	    List<CSVRecord> l = parser.getRecords();
		for (CSVRecord r:l){
			System.out.println(r);
			sb.append(r.get(0));
			//sb.append(r.get(1));
			sb.append(r.get(2));
			sb.append(r.get(3));
			sb.append(r.get(4));
			sb.append("| ");
		}
		fr.close();
		parser.close();
		
	}catch (Exception e){
		e.printStackTrace();
	}
	return sb.toString();
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
private Map<String, Pair<Integer, Integer>> parseLines(String instanceTypeCsv) throws IOException, URISyntaxException, ParseException {
    InputStreamReader inputStreamReader;
    if (instanceTypeCsv.equalsIgnoreCase("classpath")) {
        inputStreamReader = new InputStreamReader(getClass().getClassLoader().getResourceAsStream("instancetypes.csv"), Charset.forName("UTF-8"));
    } else {
        URI uri = new URI(instanceTypeCsv);
        inputStreamReader = new InputStreamReader(new FileInputStream(new File(uri)), Charset.forName("UTF-8"));
    }

    CSVParser parser = null;
    List<CSVRecord> lines = null;
    try {
        parser = CSVFormat.DEFAULT.parse(new BufferedReader(inputStreamReader));
        lines = parser.getRecords();
    } finally {
        inputStreamReader.close();

        if (parser != null) {
            parser.close();
        }
    }

    if (lines == null || lines.size() <= 0) {
        throw new ParseException("instance-type-csv data is empty");
    }

    Map<String, Pair<Integer, Integer>> linesMap = new HashMap<String, Pair<Integer, Integer>>();
    for (CSVRecord current : lines) {
        linesMap.put(current.get(1), new ImmutablePair<Integer, Integer>(Integer.parseInt(current.get(2)), Integer.parseInt(current.get(3))));
    }

    return linesMap;
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * Reads the csv file of the TagDownloader
 */
public static void readFile(File file) {
	try {
		logger.info("Starting to read file of TagDownloader ...");
		BufferedReader reader =
				new BufferedReader(
				new InputStreamReader(
				new BZip2CompressorInputStream(
				new BufferedInputStream(
				new FileInputStream(file))), "UTF-8"));
		
		CSVParser parser = new CSVParser(reader, CSVFormat.RFC4180);
		
		dataStore.connect();		
		
		
		for (CSVRecord csvRecord: parser) {
			parseRecord(csvRecord);
			if (csvRecord.getRecordNumber() % 1000000 == 0) {
				logger.info("Current Record: " + csvRecord.getRecordNumber());
			}
		}
		
		dataStore.disconnect();
		parser.close();
		logger.info("Tag Distribution:\n"
				+ FrequencyUtils.formatFrequency(tagDistribution));
		logger.info("Finished");
	} catch (Exception e) {
		logger.error("", e);
	}		
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * Reads the csv file of the TagDownloader
 */
public static void readFile(File file) {
	try {
		logger.info("Starting to read file of GeolocationDatabase ...");
		BufferedReader reader =
				new BufferedReader(
				new InputStreamReader(
				new BZip2CompressorInputStream(
				new BufferedInputStream(
				new FileInputStream(file))), "UTF-8"));
		
		CSVParser parser = new CSVParser(reader, CSVFormat.RFC4180);
		
		
		for (CSVRecord csvRecord: parser) {
			parseRecord(csvRecord);
			if (csvRecord.getRecordNumber() % 1000000 == 0) {
				logger.info("Current Record: " + csvRecord.getRecordNumber());
			}
		}
		
		parser.close();
		logger.info("Finished");
	} catch (Exception e) {
		logger.error("", e);
	}		
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
public DBpediaResource getResourceById(String resourceId) {
    Map<String, List<String>> properties = new HashMap<>();
    try {
        CSVParser parser = execute(PROPERTIES_FOR_ENTITY.replace(":resourceId", resourceId));
        for (CSVRecord record : parser) {
            List<String> propertyContainer = properties.getOrDefault(record.get("relation"), new LinkedList<>());
            propertyContainer.add(record.get("property"));
            properties.put(record.get("relation"), propertyContainer);
        }
        parser.close();
    } catch (URISyntaxException | IOException e) {
        logger.error(e);
    }
    return new DBpediaResource(resourceId, properties);
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * Load the data table file (in CSV format) to memory.
 * 
 * @param in
 *            the {@link InputStream} contains the content of data table
 *            file
 * @return the data table
 * @throws IOException
 */
public DataTable load(InputStream in) throws IOException {
	List<List<Object>> rows = new LinkedList<>();
	BufferedReader reader = new BufferedReader(new InputStreamReader(in));
	CSVParser csvParser = new CSVParser(reader, CSVFormat.DEFAULT);
	// don't use csvParser.getRecords() for iteration, may cause huge memory usage and lead to out-of-memory error
	for (CSVRecord csvRecord : csvParser)
		rows.add(getFields(csvRecord));
	csvParser.close();
	/*String line;
	while ((line = reader.readLine()) != null) {
		rows.add(getFields(line));
	}*/
	return new DataTable(rows);
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
public static ReadResult readFromCsv(InputStream input, Consumer<? super CSVRecord> action) throws IOException {
	BufferedReader reader = new BufferedReader(new InputStreamReader(input, CHARSET), READ_BUFFER_SIZE);
	CSVParser parser = new CSVParser(reader, CSVFormat.EXCEL
		.withDelimiter(';')
		.withRecordSeparator('\n')
	);
	RecordReaderWrapper wrapper = new RecordReaderWrapper(action);
	parser.forEach(wrapper);
	parser.close();
	reader.close();
	return new ReadResult(wrapper.readedReacords, wrapper.successfulReadedRecors);
}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * Takes a CSV File and parses into a List of CSVRecords objects. Also verifies
 * that the SYMBOL variable exists in the csv since that is the critical piece
 * @param csvFile the file to input
 * @return List of CSVRecords
 * @throws IOException
 */
private static List<CSVRecord> getInputFromCSV(File csvFile)
		throws IOException {
	FileReader fr = new FileReader(csvFile);
	// For Testing
	try {
		printFile(csvFile);
	} catch (Exception e1) {
		// TODO Auto-generated catch block
		e1.printStackTrace();
	}

	CSVParser csvp = new CSVParser(fr, CSVFormat.EXCEL.withHeader());
	List<CSVRecord> list = csvp.getRecords();
	Map<String, Integer> headers = csvp.getHeaderMap();

	// Get Header map and index of SYMBOL
	try {
		// Sole purpose of i is to check to see if Symbol exists
		@SuppressWarnings("unused")
		int i = headers.get(SYMBOL).intValue();
		csvp.close();
		return list;
	} catch (NullPointerException e) {
		System.err.println("No " + SYMBOL + " Column Found");
		csvp.close();
		throw new IOException("Invalid File Format");
	}

}
 

import org.apache.commons.csv.CSVParser; //导入方法依赖的package包/类
/**
 * {@inheritDoc}
 */
@Override
public Collection<CsvLine> getLines() throws RtException {
    Check.notNull(format, "format");
    Check.notEmpty(fileContent, "fileContent");

     // withSkipHeaderRecord(true) only works with a header definition,
     // but our columns are dynamic (no fixed number)
     // => hence we need to exclude the header anyway, without relying
     // on the commons CSV parser behaviour
    boolean skipFirstLine = getFormat().getSkipHeaderRecord();
    log.debug("Parsing CSV lines with format {} ", getFormat());

    CSVParser parser = null;
    List<CSVRecord> records = null;
    try {
        parser = CSVParser.parse(getFileContent(), getFormat());

        records = parser.getRecords();
    } catch (IOException ioe) {
        log.error("Unable to parse CSV content ", ioe);
        throw new RtException(ioe.getMessage(), ioe);
    } finally {
        if (null != parser) {
            try {
                parser.close();
            } catch (IOException ignore) { }
        }
    }

    return toCsvLines(records, skipFirstLine);
}