public class WARCReaderFactory.UncompressedWARCReader extends WARCReader
ArchiveReader.ArchiveRecordIteratorWARCConstants.WARCRecordTypein, MAX_ALLOWED_RECOVERABLESCOLON_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, WSPABSOLUTE_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 |
|---|
WARCReaderFactory.UncompressedWARCReader(File f)
Constructor.
|
WARCReaderFactory.UncompressedWARCReader(File f,
long offset)
Constructor.
|
WARCReaderFactory.UncompressedWARCReader(String f,
InputStream is)
Constructor.
|
createArchiveRecord, createCDXIndexFile, dump, getDeleteFileOnCloseReader, getDotFileExtension, getFileExtension, gotoEOR, initialize, main, output, readExpectedCharcdxOutput, cleanupCurrentRecord, close, currentRecord, get, get, getCurrentRecord, getFileName, getIn, getInputStream, getLogger, getOptions, getReaderIdentifier, getStrippedFileName, getStrippedFileName, getTrueOrFalse, getVersion, isCompressed, isDigest, isStrict, isValid, iterator, logStdErr, output, outputRecord, outputRecord, positionForRecord, setCompressed, setDigest, setIn, setReaderIdentifier, setStrict, setVersion, stripExtension, validate, validatepublic WARCReaderFactory.UncompressedWARCReader(File f) throws IOException
f - Uncompressed arcfile to read.IOExceptionpublic WARCReaderFactory.UncompressedWARCReader(File f, long offset) throws IOException
f - Uncompressed file to read.offset - Offset at which to position Reader.IOExceptionpublic WARCReaderFactory.UncompressedWARCReader(String f, InputStream is)
f - Uncompressed file to read.is - InputStream.Copyright © 2015 The International Internet Preservation Consortium. All Rights Reserved.