public class JWATResource extends Resource implements org.archive.format.warc.WARCConstants
JWATFlexResourceStore
Modifier and Type | Field and Description |
---|---|
protected org.jwat.arc.ArcReader |
arcReader |
protected org.jwat.arc.ArcRecordBase |
arcRecord |
protected org.jwat.gzip.GzipEntry |
gzipEntry |
protected org.jwat.gzip.GzipReader |
gzipReader |
protected Map<String,String> |
headers |
protected long |
length |
protected InputStream |
payloadStream |
protected org.jwat.common.ByteCountingPushBackInputStream |
pbin |
protected int |
status |
protected org.jwat.warc.WarcReader |
warcReader |
protected org.jwat.warc.WarcRecord |
warcRecord |
COLON_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, PROFILE_REVISIT_URI_AGNOSTIC_IDENTICAL_DIGEST, TRUNCATED_VALUE_UNSPECIFIED, TYPE, WARC_FIELDS_TYPE, WARC_FILE_EXTENSION, WARC_HEADER_ENCODING, WARC_ID, WARC_MAGIC, WARC_VERSION, WSP
ABSOLUTE_OFFSET_KEY, CDX, CDX_FILE, CDX_LINE_BUFFER_SIZE, CRLF, 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, READER_IDENTIFIER_FIELD_KEY, RECORD_IDENTIFIER_FIELD_KEY, SINGLE_SPACE, TYPE_FIELD_KEY, URL_FIELD_KEY, VERSION_FIELD_KEY
Constructor and Description |
---|
JWATResource() |
Modifier and Type | Method and Description |
---|---|
void |
close() |
Map<String,String> |
getHttpHeaders()
Assumes an HTTP response - return the HTTP headers, not including the
HTTP Message header
|
long |
getRecordLength() |
String |
getRefersToDate()
return
WARC-Refers-To-Date WARC record header value or
equivalent. |
String |
getRefersToTargetURI()
return
WARC-Refer-To-Target-URI WARC record header value or
equivalent. |
static Resource |
getResource(InputStream rin,
long offset) |
int |
getStatusCode()
Assumes an HTTP resource - return the HTTP response code
|
available, getHeader, mark, markSupported, parseHeaders, read, read, read, reset, setChunkedEncoding, setInputStream, skip
protected org.jwat.common.ByteCountingPushBackInputStream pbin
protected org.jwat.gzip.GzipReader gzipReader
protected org.jwat.gzip.GzipEntry gzipEntry
protected org.jwat.arc.ArcReader arcReader
protected org.jwat.arc.ArcRecordBase arcRecord
protected org.jwat.warc.WarcReader warcReader
protected org.jwat.warc.WarcRecord warcRecord
protected InputStream payloadStream
protected long length
protected int status
public static Resource getResource(InputStream rin, long offset) throws IOException, ResourceNotAvailableException
public Map<String,String> getHttpHeaders()
Resource
getHttpHeaders
in class Resource
public long getRecordLength()
getRecordLength
in class Resource
public int getStatusCode()
Resource
getStatusCode
in class Resource
public String getRefersToTargetURI()
Resource
WARC-Refer-To-Target-URI
WARC record header value or
equivalent.
Default implementation returns null
.getRefersToTargetURI
in class Resource
public String getRefersToDate()
Resource
WARC-Refers-To-Date
WARC record header value or
equivalent.
Default implementation returns null
getRefersToDate
in class Resource
yyyyMMddHHmmss
)public void close() throws IOException
close
in interface Closeable
close
in interface AutoCloseable
close
in class Resource
IOException
Copyright © 2005–2015 IIPC. All rights reserved.