public class WARCFileWriter
extends org.springframework.data.hadoop.store.output.AbstractDataStreamWriter
implements org.springframework.data.hadoop.store.DataStoreWriter<org.archive.io.warc.WARCRecordInfo>, org.archive.format.warc.WARCConstants
DEFAULT_MAX_OPEN_ATTEMPTSCOLON_SPACE, COMPRESSED_WARC_FILE_EXTENSION, CONTENT_DESCRIPTION, CONTENT_LENGTH, CONTENT_TYPE, DEFAULT_ENCODING, DEFAULT_MAX_WARC_FILE_SIZE, DOT_COMPRESSED_WARC_FILE_EXTENSION, DOT_WARC_FILE_EXTENSION, FTP_CONTROL_CONVERSATION_MIMETYPE, HEADER_FIELD_SEPARATOR, HEADER_KEY_BLOCK_DIGEST, HEADER_KEY_CONCURRENT_TO, HEADER_KEY_DATE, HEADER_KEY_ETAG, HEADER_KEY_FILENAME, HEADER_KEY_ID, HEADER_KEY_IP, HEADER_KEY_LAST_MODIFIED, HEADER_KEY_PAYLOAD_DIGEST, HEADER_KEY_PROFILE, HEADER_KEY_REFERS_TO, HEADER_KEY_REFERS_TO_DATE, HEADER_KEY_REFERS_TO_FILE_OFFSET, HEADER_KEY_REFERS_TO_FILENAME, HEADER_KEY_REFERS_TO_TARGET_URI, HEADER_KEY_TRUNCATED, HEADER_KEY_TYPE, HEADER_KEY_URI, HEADER_LINE_ENCODING, HTTP_REQUEST_MIMETYPE, HTTP_RESPONSE_MIMETYPE, MAX_LINE_LENGTH, MAX_WARC_HEADER_LINE_LENGTH, NAMED_FIELD_CHECKSUM_LABEL, NAMED_FIELD_DESCRIPTION, NAMED_FIELD_FILEDESC, NAMED_FIELD_IP_LABEL, NAMED_FIELD_RELATED_LABEL, NAMED_FIELD_TRUNCATED, NAMED_FIELD_TRUNCATED_VALUE_HEAD, NAMED_FIELD_TRUNCATED_VALUE_LENGTH, NAMED_FIELD_TRUNCATED_VALUE_TIME, NAMED_FIELD_TRUNCATED_VALUE_UNSPECIFIED, NAMED_FIELD_WARCFILENAME, PLACEHOLDER_RECORD_LENGTH_STRING, PROFILE_REVISIT_IDENTICAL_DIGEST, PROFILE_REVISIT_NOT_MODIFIED, TRUNCATED_VALUE_UNSPECIFIED, TYPE, WARC_FIELDS_TYPE, WARC_FILE_EXTENSION, WARC_HEADER_ENCODING, WARC_ID, WARC_MAGIC, WARC_VERSION, WSPABSOLUTE_OFFSET_KEY, CDX, CDX_FILE, CDX_LINE_BUFFER_SIZE, DATE_FIELD_KEY, DEFAULT_DIGEST_METHOD, DOT_COMPRESSED_FILE_EXTENSION, DUMP, GZIP_DUMP, HEADER, INVALID_SUFFIX, LENGTH_FIELD_KEY, MIMETYPE_FIELD_KEY, NOHEAD, OCCUPIED_SUFFIX, ORIGIN_FIELD_KEY, READER_IDENTIFIER_FIELD_KEY, RECORD_IDENTIFIER_FIELD_KEY, SINGLE_SPACE, TYPE_FIELD_KEY, URL_FIELD_KEY, VERSION_FIELD_KEY| Constructor and Description |
|---|
WARCFileWriter(org.apache.hadoop.conf.Configuration configuration,
org.apache.hadoop.fs.Path basePath,
org.springframework.data.hadoop.store.codec.CodecInfo codec) |
| Modifier and Type | Method and Description |
|---|---|
void |
close() |
protected static String |
createRecordHeader(org.archive.io.warc.WARCRecordInfo record) |
org.archive.io.warc.WARCRecordInfo |
createWARCInfoRecord() |
void |
flush() |
org.springframework.data.hadoop.store.support.StreamsHolder<OutputStream> |
getOutput() |
long |
getPosition() |
protected void |
handleTimeout() |
void |
hflush() |
void |
write(org.archive.io.warc.WARCRecordInfo record) |
static void |
write(org.archive.io.warc.WARCRecordInfo record,
OutputStream out) |
getPosition, setMaxOpenAttemptsfindInitFiles, getOutputContext, getResolvedPath, initOutputContext, isAppendable, isFileWriteable, isOverwrite, isSyncable, onInit, renameFile, setAppendable, setFileNamingStrategy, setInWritingPrefix, setInWritingSuffix, setOverwrite, setRolloverStrategy, setSyncable, setWritePositiondoStart, doStop, flushTimeout, getCodec, getConfiguration, getPath, isCompressed, resetIdleTimeout, setCloseTimeout, setFlushTimeout, setIdleTimeoutafterPropertiesSet, getBeanFactory, getPhase, getStoreEventPublisher, getTaskExecutor, getTaskScheduler, isAutoStartup, isRunning, setAutoStartup, setBeanFactory, setPhase, setStoreEventPublisher, setTaskExecutor, setTaskScheduler, start, stop, stoppublic WARCFileWriter(org.apache.hadoop.conf.Configuration configuration,
org.apache.hadoop.fs.Path basePath,
org.springframework.data.hadoop.store.codec.CodecInfo codec)
public void close()
throws IOException
close in interface Closeableclose in interface AutoCloseableIOExceptionpublic void flush()
throws IOException
flush in interface FlushableIOExceptionpublic void hflush()
throws IOException
IOExceptionprotected void handleTimeout()
handleTimeout in class org.springframework.data.hadoop.store.support.StoreObjectSupportpublic org.springframework.data.hadoop.store.support.StreamsHolder<OutputStream> getOutput() throws IOException
getOutput in class org.springframework.data.hadoop.store.output.AbstractDataStreamWriterIOExceptionpublic org.archive.io.warc.WARCRecordInfo createWARCInfoRecord()
throws IOException
IOExceptionpublic void write(org.archive.io.warc.WARCRecordInfo record)
throws IOException
write in interface org.springframework.data.hadoop.store.DataWriter<org.archive.io.warc.WARCRecordInfo>IOExceptionpublic long getPosition()
throws IOException
IOExceptionpublic static void write(org.archive.io.warc.WARCRecordInfo record,
OutputStream out)
throws IOException
IOExceptionprotected static String createRecordHeader(org.archive.io.warc.WARCRecordInfo record)
Copyright © 2000–2018 LOCKSS Program. All rights reserved.