public interface WARCConstants extends ArchiveFileConstants
| Modifier and Type | Interface and Description |
|---|---|
static class |
WARCConstants.WARCRecordType
WARC Record Types.
|
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_KEYstatic final int DEFAULT_MAX_WARC_FILE_SIZE
static final String WARC_MAGIC
static final String WARC_VERSION
static final int MAX_WARC_HEADER_LINE_LENGTH
alexa/include/a_arcio.h:
#define LINE_LENGTH (100*1024)
static final int MAX_LINE_LENGTH
static final String WARC_FILE_EXTENSION
static final String DOT_WARC_FILE_EXTENSION
static final String COMPRESSED_WARC_FILE_EXTENSION
static final String DOT_COMPRESSED_WARC_FILE_EXTENSION
static final String DEFAULT_ENCODING
TODO: ARC uses ISO-8859-1. In general, we should use UTF-8 but we probably need a single byte encoding if we're out for preserving the binary data as received over the net (We probably don't want to transform the supra-ASCII characters to UTF-8 before storing in ARC). For now, till we figure it, DEFAULT_ENCODING is single-byte charset -- same as ARCs.
static final String HEADER_LINE_ENCODING
static final String WARC_HEADER_ENCODING
static final String TYPE
static final String WARC_ID
static final char HEADER_FIELD_SEPARATOR
static final Character[] WSP
static final String PLACEHOLDER_RECORD_LENGTH_STRING
static final String NAMED_FIELD_IP_LABEL
static final String NAMED_FIELD_CHECKSUM_LABEL
static final String NAMED_FIELD_RELATED_LABEL
static final String NAMED_FIELD_WARCFILENAME
static final String NAMED_FIELD_DESCRIPTION
static final String NAMED_FIELD_FILEDESC
static final String NAMED_FIELD_TRUNCATED
static final String NAMED_FIELD_TRUNCATED_VALUE_TIME
static final String NAMED_FIELD_TRUNCATED_VALUE_LENGTH
static final String NAMED_FIELD_TRUNCATED_VALUE_HEAD
static final String NAMED_FIELD_TRUNCATED_VALUE_UNSPECIFIED
static final String HEADER_KEY_URI
static final String HEADER_KEY_DATE
static final String HEADER_KEY_TYPE
static final String HEADER_KEY_ID
static final String HEADER_KEY_IP
static final String HEADER_KEY_BLOCK_DIGEST
static final String HEADER_KEY_PAYLOAD_DIGEST
static final String HEADER_KEY_CONCURRENT_TO
static final String HEADER_KEY_TRUNCATED
static final String HEADER_KEY_PROFILE
static final String HEADER_KEY_FILENAME
static final String HEADER_KEY_ETAG
static final String HEADER_KEY_LAST_MODIFIED
static final String HEADER_KEY_REFERS_TO
static final String HEADER_KEY_REFERS_TO_TARGET_URI
WARCWriterProcessor,
Constant Field Valuesstatic final String HEADER_KEY_REFERS_TO_DATE
static final String HEADER_KEY_REFERS_TO_FILENAME
static final String HEADER_KEY_REFERS_TO_FILE_OFFSET
static final String PROFILE_REVISIT_URI_AGNOSTIC_IDENTICAL_DIGEST
static final String PROFILE_REVISIT_IDENTICAL_DIGEST
static final String PROFILE_REVISIT_NOT_MODIFIED
static final String CONTENT_LENGTH
static final String CONTENT_TYPE
static final String CONTENT_DESCRIPTION
static final String COLON_SPACE
static final String TRUNCATED_VALUE_UNSPECIFIED
static final String HTTP_REQUEST_MIMETYPE
static final String HTTP_RESPONSE_MIMETYPE
static final String FTP_CONTROL_CONVERSATION_MIMETYPE
static final String WARC_FIELDS_TYPE
Copyright © 2015 The International Internet Preservation Consortium. All Rights Reserved.