public interface WARCConstants extends ArchiveFileConstants
| Modifier and Type | Interface and Description |
|---|---|
static class |
WARCConstants.WARCRecordType
WARC Record Types.
|
| Modifier and Type | Field and Description |
|---|---|
static java.lang.String |
COLON_SPACE |
static java.lang.String |
COMPRESSED_WARC_FILE_EXTENSION
Compressed WARC file extension.
|
static java.lang.String |
CONTENT_DESCRIPTION |
static java.lang.String |
CONTENT_LENGTH |
static java.lang.String |
CONTENT_TYPE |
static java.lang.String |
DEFAULT_ENCODING
Encoding to use getting bytes from strings.
|
static int |
DEFAULT_MAX_WARC_FILE_SIZE
Default maximum WARC file size.
|
static java.lang.String |
DOT_COMPRESSED_WARC_FILE_EXTENSION
Compressed dot WARC file extension.
|
static java.lang.String |
DOT_WARC_FILE_EXTENSION
Dot WARC file extension.
|
static java.lang.String |
FTP_CONTROL_CONVERSATION_MIMETYPE |
static char |
HEADER_FIELD_SEPARATOR
Header field seperator character.
|
static java.lang.String |
HEADER_KEY_BLOCK_DIGEST |
static java.lang.String |
HEADER_KEY_CONCURRENT_TO |
static java.lang.String |
HEADER_KEY_DATE |
static java.lang.String |
HEADER_KEY_ETAG |
static java.lang.String |
HEADER_KEY_FILENAME |
static java.lang.String |
HEADER_KEY_ID |
static java.lang.String |
HEADER_KEY_IP |
static java.lang.String |
HEADER_KEY_LAST_MODIFIED |
static java.lang.String |
HEADER_KEY_PAYLOAD_DIGEST |
static java.lang.String |
HEADER_KEY_PROFILE |
static java.lang.String |
HEADER_KEY_REFERS_TO |
static java.lang.String |
HEADER_KEY_REFERS_TO_DATE |
static java.lang.String |
HEADER_KEY_REFERS_TO_FILE_OFFSET |
static java.lang.String |
HEADER_KEY_REFERS_TO_FILENAME |
static java.lang.String |
HEADER_KEY_REFERS_TO_TARGET_URI
These fields help a consumer of the warc to locate the warc record that
"WARC-Refers-To" refers to.
|
static java.lang.String |
HEADER_KEY_TRUNCATED |
static java.lang.String |
HEADER_KEY_TYPE |
static java.lang.String |
HEADER_KEY_URI |
static java.lang.String |
HEADER_LINE_ENCODING |
static java.lang.String |
HTTP_REQUEST_MIMETYPE
To be safe, lets use application type rather than message.
|
static java.lang.String |
HTTP_RESPONSE_MIMETYPE |
static java.lang.String |
HTTP_RESPONSE_MIMETYPE_NS |
static int |
MAX_LINE_LENGTH |
static int |
MAX_WARC_HEADER_LINE_LENGTH
Assumed maximum size of a Header Line.
|
static java.lang.String |
NAMED_FIELD_CHECKSUM_LABEL |
static java.lang.String |
NAMED_FIELD_DESCRIPTION |
static java.lang.String |
NAMED_FIELD_FILEDESC |
static java.lang.String |
NAMED_FIELD_IP_LABEL |
static java.lang.String |
NAMED_FIELD_RELATED_LABEL |
static java.lang.String |
NAMED_FIELD_TRUNCATED |
static java.lang.String |
NAMED_FIELD_TRUNCATED_VALUE_HEAD |
static java.lang.String |
NAMED_FIELD_TRUNCATED_VALUE_LENGTH |
static java.lang.String |
NAMED_FIELD_TRUNCATED_VALUE_TIME |
static java.lang.String |
NAMED_FIELD_TRUNCATED_VALUE_UNSPECIFIED |
static java.lang.String |
NAMED_FIELD_WARCFILENAME |
static java.lang.String |
PLACEHOLDER_RECORD_LENGTH_STRING
Placeholder for length in Header line.
|
static java.lang.String |
PROFILE_REVISIT_IDENTICAL_DIGEST |
static java.lang.String |
PROFILE_REVISIT_NOT_MODIFIED |
static java.lang.String |
TRUNCATED_VALUE_UNSPECIFIED |
static java.lang.String |
TYPE |
static java.lang.String |
WARC_FIELDS_TYPE |
static java.lang.String |
WARC_FILE_EXTENSION
WARC file extention.
|
static java.lang.String |
WARC_HEADER_ENCODING |
static java.lang.String |
WARC_ID
WARC-ID
|
static java.lang.String |
WARC_MAGIC
WARC MAGIC
WARC files and records begin with this sequence.
|
static java.lang.String |
WARC_VERSION
Hard-coded version for WARC files made with this code.
|
static java.lang.Character[] |
WSP
WSP
One of a space or horizontal tab character.
|
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, ORIGIN_FIELD_KEY, 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 java.lang.String WARC_MAGIC
static final java.lang.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 java.lang.String WARC_FILE_EXTENSION
static final java.lang.String DOT_WARC_FILE_EXTENSION
static final java.lang.String COMPRESSED_WARC_FILE_EXTENSION
static final java.lang.String DOT_COMPRESSED_WARC_FILE_EXTENSION
static final java.lang.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 java.lang.String HEADER_LINE_ENCODING
static final java.lang.String WARC_HEADER_ENCODING
static final java.lang.String TYPE
static final java.lang.String WARC_ID
static final char HEADER_FIELD_SEPARATOR
static final java.lang.Character[] WSP
static final java.lang.String PLACEHOLDER_RECORD_LENGTH_STRING
static final java.lang.String NAMED_FIELD_IP_LABEL
static final java.lang.String NAMED_FIELD_CHECKSUM_LABEL
static final java.lang.String NAMED_FIELD_RELATED_LABEL
static final java.lang.String NAMED_FIELD_WARCFILENAME
static final java.lang.String NAMED_FIELD_DESCRIPTION
static final java.lang.String NAMED_FIELD_FILEDESC
static final java.lang.String NAMED_FIELD_TRUNCATED
static final java.lang.String NAMED_FIELD_TRUNCATED_VALUE_TIME
static final java.lang.String NAMED_FIELD_TRUNCATED_VALUE_LENGTH
static final java.lang.String NAMED_FIELD_TRUNCATED_VALUE_HEAD
static final java.lang.String NAMED_FIELD_TRUNCATED_VALUE_UNSPECIFIED
static final java.lang.String HEADER_KEY_URI
static final java.lang.String HEADER_KEY_DATE
static final java.lang.String HEADER_KEY_TYPE
static final java.lang.String HEADER_KEY_ID
static final java.lang.String HEADER_KEY_IP
static final java.lang.String HEADER_KEY_BLOCK_DIGEST
static final java.lang.String HEADER_KEY_PAYLOAD_DIGEST
static final java.lang.String HEADER_KEY_CONCURRENT_TO
static final java.lang.String HEADER_KEY_TRUNCATED
static final java.lang.String HEADER_KEY_PROFILE
static final java.lang.String HEADER_KEY_FILENAME
static final java.lang.String HEADER_KEY_ETAG
static final java.lang.String HEADER_KEY_LAST_MODIFIED
static final java.lang.String HEADER_KEY_REFERS_TO
static final java.lang.String HEADER_KEY_REFERS_TO_TARGET_URI
WARCWriterProcessor,
Constant Field Valuesstatic final java.lang.String HEADER_KEY_REFERS_TO_DATE
static final java.lang.String HEADER_KEY_REFERS_TO_FILENAME
static final java.lang.String HEADER_KEY_REFERS_TO_FILE_OFFSET
static final java.lang.String PROFILE_REVISIT_IDENTICAL_DIGEST
static final java.lang.String PROFILE_REVISIT_NOT_MODIFIED
static final java.lang.String CONTENT_LENGTH
static final java.lang.String CONTENT_TYPE
static final java.lang.String CONTENT_DESCRIPTION
static final java.lang.String COLON_SPACE
static final java.lang.String TRUNCATED_VALUE_UNSPECIFIED
static final java.lang.String HTTP_REQUEST_MIMETYPE
static final java.lang.String HTTP_RESPONSE_MIMETYPE
static final java.lang.String HTTP_RESPONSE_MIMETYPE_NS
static final java.lang.String FTP_CONTROL_CONVERSATION_MIMETYPE
static final java.lang.String WARC_FIELDS_TYPE
Copyright © 2019 The International Internet Preservation Consortium. All Rights Reserved.