| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
X_ROBOTS_HTTP_HEADER |
"X-Robots-Tag" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
TOOL_DESCRIPTION |
"A tool for extracting metadata from WARC, ARC, and WAT files" |
public static final String |
TOOL_NAME |
"extractor" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
ABSOLUTE_OFFSET_KEY |
"absolute-offset" |
public static final String |
CDX |
"cdx" |
public static final String |
CDX_FILE |
"cdxfile" |
public static final int |
CDX_LINE_BUFFER_SIZE |
1224 |
public static final String |
CRLF |
"\r\n" |
public static final String |
DATE_FIELD_KEY |
"creation-date" |
public static final String |
DEFAULT_DIGEST_METHOD |
"SHA-1" |
public static final String |
DOT_COMPRESSED_FILE_EXTENSION |
".gz" |
public static final String |
DUMP |
"dump" |
public static final String |
GZIP_DUMP |
"gzipdump" |
public static final String |
HEADER |
"header" |
public static final String |
INVALID_SUFFIX |
".invalid" |
public static final String |
LENGTH_FIELD_KEY |
"length" |
public static final String |
MIMETYPE_FIELD_KEY |
"content-type" |
public static final String |
NOHEAD |
"nohead" |
public static final String |
OCCUPIED_SUFFIX |
".open" |
public static final String |
READER_IDENTIFIER_FIELD_KEY |
"reader-identifier" |
public static final String |
RECORD_IDENTIFIER_FIELD_KEY |
"record-identifier" |
public static final char |
SINGLE_SPACE |
32 |
public static final String |
TYPE_FIELD_KEY |
"type" |
public static final String |
URL_FIELD_KEY |
"subject-uri" |
public static final String |
VERSION_FIELD_KEY |
"version" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
ACTUAL_LENGTH_KEY |
"Actual-Length" |
public static final String |
ALEXA_DAT_MIME |
"alexa/dat" |
public static final String |
ARC_FILE_EXTENSION |
"arc" |
public static final String |
ARC_MAGIC_NUMBER |
"filedesc://" |
public static final int |
CARRIAGE_RETURN_ORD |
13 |
public static final String |
CHECKSUM_FIELD_KEY |
"checksum" |
public static final String |
CHECKSUM_HEADER_FIELD_KEY |
"checksum" |
public static final String |
CODE_HEADER_FIELD_KEY |
"result-code" |
public static final String |
COMPRESSED_ARC_FILE_EXTENSION |
"arc.gz" |
public static final String |
DATE_STRING_KEY |
"Date" |
public static final String |
DECLARED_LENGTH_KEY |
"Content-Length" |
public static final String |
DEFAULT_ENCODING |
"ISO-8859-1" |
public static final int |
DEFAULT_GZIP_HEADER_LENGTH |
10 |
public static final long |
DEFAULT_MAX_ARC_FILE_SIZE |
100000000L |
public static final String |
DEFAULT_MIME |
"x-archive/unknown" |
public static final String |
DELIMITER |
" " |
public static final String |
DNS_MIME |
"text/dns" |
public static final String |
DOT_ARC_FILE_EXTENSION |
".arc" |
public static final String |
DOT_COMPRESSED_ARC_FILE_EXTENSION |
".arc.gz" |
public static final String |
DOT_COMPRESSED_FILE_EXTENSION |
".gz" |
public static final int |
FIELD_COUNT |
5 |
public static final String |
FILEDESC_SCHEME |
"filedesc:/" |
public static final String |
FILENAME_FIELD_KEY |
"filename" |
public static final String |
FILENAME_HEADER_FIELD_KEY |
"filename" |
public static final char |
HEADER_FIELD_SEPARATOR |
32 |
public static final String |
HEADER_LENGTH |
"Header-Length" |
public static final String |
IP_HEADER_FIELD_KEY |
"ip-address" |
public static final String |
IP_KEY |
"IP-Address" |
public static final String |
LEADING_NEWLINES_KEY |
"Leading-Newlines" |
public static final char |
LINE_SEPARATOR |
10 |
public static final String |
LOCATION_HEADER_FIELD_KEY |
"location" |
public static final int |
MAX_HEADER_LINE_LENGTH |
102400 |
public static final int |
MAX_META_LENGTH |
32768 |
public static final int |
MAX_METADATA_LINE_LENGTH |
4096 |
public static final String |
MIME_KEY |
"Content-Type" |
public static final int |
NEW_LINE_ORD |
10 |
public static final String |
OFFSET_FIELD_KEY |
"offset" |
public static final String |
OFFSET_HEADER_FIELD_KEY |
"offset" |
public static final String |
STATUSCODE_FIELD_KEY |
"statuscode" |
public static final String |
TOKENIZED_PREFIX |
"tokenized_" |
public static final String |
TRAILING_CRUFT_KEY |
"Trailing-Slop" |
public static final String |
TRAILING_NEWLINES_KEY |
"Trailing-Newlines" |
public static final String |
URL_KEY |
"Target-URI" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
digest |
"digest" |
public static final String |
filename |
"filename" |
public static final String |
length |
"length" |
public static final String |
mimetype |
"mimetype" |
public static final String |
offset |
"offset" |
public static final String |
original |
"original" |
public static final String |
redirect |
"redirect" |
public static final String |
robotflags |
"robotflags" |
public static final String |
statuscode |
"statuscode" |
public static final String |
timestamp |
"timestamp" |
public static final String |
urlkey |
"urlkey" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
EMPTY_VALUE |
"-" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
BYTES_IN_INT |
4 |
public static final int |
BYTES_IN_SHORT |
2 |
public static final int |
GZIP_COMPRESSION_METHOD_DEFLATE |
8 |
public static final int |
GZIP_COMPRESSION_METHOD_IDX |
2 |
public static final int |
GZIP_FEXTRA_LENGTH_BYTES |
2 |
public static final int |
GZIP_FEXTRA_LENGTH_IDX |
2 |
public static final int |
GZIP_FEXTRA_NAME_BYTES |
2 |
public static final int |
GZIP_FEXTRA_NAME_IDX |
0 |
public static final int |
GZIP_FEXTRA_VALUE_IDX |
4 |
public static final int |
GZIP_FEXTRA_VALUE_MAX_LENGTH |
65536 |
public static final int |
GZIP_FLAG_FCOMMENT |
16 |
public static final int |
GZIP_FLAG_FEXTRA |
4 |
public static final int |
GZIP_FLAG_FHCRC |
2 |
public static final int |
GZIP_FLAG_FNAME |
8 |
public static final int |
GZIP_FLAG_FTEXT |
1 |
public static final int |
GZIP_FLAG_IDX |
3 |
public static final int |
GZIP_FLAG_VALID_BITS |
31 |
public static final int |
GZIP_FOOTER_BYTES |
8 |
public static final int |
GZIP_MAGIC_ONE |
31 |
public static final int |
GZIP_MAGIC_ONE_IDX |
0 |
public static final int |
GZIP_MAGIC_TWO |
139 |
public static final int |
GZIP_MAGIC_TWO_IDX |
1 |
public static final int |
GZIP_MTIME_IDX |
4 |
public static final int |
GZIP_MTIME_LENGTH |
4 |
public static final int |
GZIP_OS_IDX |
9 |
public static final int |
GZIP_OS_UNIX |
3 |
public static final int |
GZIP_STATIC_FOOTER_SIZE |
8 |
public static final int |
GZIP_STATIC_HEADER_SIZE |
10 |
public static final int |
GZIP_XFL_IDX |
8 |
public static final String |
NO_BYTES_IN_STREAM |
"No bytes in stream" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final long |
SEARCH_EOF_AT_START |
-9223372036854775808L |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
EARLIEST_TIMESTAMP |
"_EARLIEST" |
public static final String |
LATEST_TIMESTAMP |
"_LATEST" |
public static final String |
OFF |
"OFF" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
protected static final boolean |
DEFAULT_USE_NIO |
true |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final byte |
COLON |
58 |
public static final byte |
CR |
13 |
public static final String |
CRLF |
"\r\n" |
public static final byte |
HTAB |
9 |
public static final byte |
LF |
10 |
public static final int |
METHOD_CONNECT |
7 |
public static final String |
METHOD_CONNECT_STRING |
"CONNECT" |
public static final int |
METHOD_DELETE |
6 |
public static final String |
METHOD_DELETE_STRING |
"DELETE" |
public static final int |
METHOD_GET |
1 |
public static final String |
METHOD_GET_STRING |
"GET" |
public static final int |
METHOD_HEAD |
2 |
public static final String |
METHOD_HEAD_STRING |
"HEAD" |
public static final int |
METHOD_POST |
3 |
public static final String |
METHOD_POST_STRING |
"POST" |
public static final int |
METHOD_PUT |
4 |
public static final String |
METHOD_PUT_STRING |
"PUT" |
public static final int |
METHOD_TRACE |
5 |
public static final String |
METHOD_TRACE_STRING |
"TRACE" |
public static final int |
METHOD_UNK |
0 |
public static final String |
METHOD_UNK_STRING |
"UNK" |
public static final String |
REASON_UNK |
"UNK" |
public static final byte |
SP |
32 |
public static final int |
STATUS_UNK |
0 |
public static final int |
VERSION_0 |
0 |
public static final String |
VERSION_0_STATUS |
"HTTP/1.0" |
public static final int |
VERSION_1 |
1 |
public static final String |
VERSION_1_STATUS |
"HTTP/1.1" |
public static final String |
VERSION_1_UNK |
"UNK" |
public static final int |
VERSION_9 |
9 |
public static final String |
VERSION_9_STATUS |
"HTTP/0.9" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
EMPTY |
"" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
protected static final String |
CHARSET_TOKEN |
"charset=" |
public static final String |
DEFAULT_CHARSET |
"UTF-8" |
protected static final String |
HTTP_CONTENT_TYPE_HEADER |
"CONTENT-TYPE" |
protected static final int |
MAX_CHARSET_READAHEAD |
65536 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
GUESS_TYPES |
3 |
public static final int |
MODE_COUNT |
6 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
SCRIPT_TAG_NAME |
"SCRIPT" |
public static final String |
STYLE_TAG_NAME |
"STYLE" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
COLON_SPACE |
": " |
public static final String |
COMPRESSED_WARC_FILE_EXTENSION |
"warc.gz" |
public static final String |
CONTENT_DESCRIPTION |
"Content-Description" |
public static final String |
CONTENT_LENGTH |
"Content-Length" |
public static final String |
CONTENT_TYPE |
"Content-Type" |
public static final String |
DEFAULT_ENCODING |
"UTF-8" |
public static final int |
DEFAULT_MAX_WARC_FILE_SIZE |
1073741824 |
public static final String |
DOT_COMPRESSED_WARC_FILE_EXTENSION |
".warc.gz" |
public static final String |
DOT_WARC_FILE_EXTENSION |
".warc" |
public static final String |
FTP_CONTROL_CONVERSATION_MIMETYPE |
"text/x-ftp-control-conversation" |
public static final char |
HEADER_FIELD_SEPARATOR |
32 |
public static final String |
HEADER_KEY_BLOCK_DIGEST |
"WARC-Block-Digest" |
public static final String |
HEADER_KEY_CONCURRENT_TO |
"WARC-Concurrent-To" |
public static final String |
HEADER_KEY_DATE |
"WARC-Date" |
public static final String |
HEADER_KEY_ETAG |
"WARC-Etag" |
public static final String |
HEADER_KEY_FILENAME |
"WARC-Filename" |
public static final String |
HEADER_KEY_ID |
"WARC-Record-ID" |
public static final String |
HEADER_KEY_IP |
"WARC-IP-Address" |
public static final String |
HEADER_KEY_LAST_MODIFIED |
"WARC-Last-Modified" |
public static final String |
HEADER_KEY_PAYLOAD_DIGEST |
"WARC-Payload-Digest" |
public static final String |
HEADER_KEY_PROFILE |
"WARC-Profile" |
public static final String |
HEADER_KEY_REFERS_TO |
"WARC-Refers-To" |
public static final String |
HEADER_KEY_REFERS_TO_DATE |
"WARC-Refers-To-Date" |
public static final String |
HEADER_KEY_REFERS_TO_FILE_OFFSET |
"WARC-Refers-To-File-Offset" |
public static final String |
HEADER_KEY_REFERS_TO_FILENAME |
"WARC-Refers-To-Filename" |
public static final String |
HEADER_KEY_REFERS_TO_TARGET_URI |
"WARC-Refers-To-Target-URI" |
public static final String |
HEADER_KEY_TRUNCATED |
"WARC-Truncated" |
public static final String |
HEADER_KEY_TYPE |
"WARC-Type" |
public static final String |
HEADER_KEY_URI |
"WARC-Target-URI" |
public static final String |
HEADER_LINE_ENCODING |
"UTF-8" |
public static final String |
HTTP_REQUEST_MIMETYPE |
"application/http; msgtype=request" |
public static final String |
HTTP_RESPONSE_MIMETYPE |
"application/http; msgtype=response" |
public static final int |
MAX_LINE_LENGTH |
102400 |
public static final int |
MAX_WARC_HEADER_LINE_LENGTH |
102400 |
public static final String |
NAMED_FIELD_CHECKSUM_LABEL |
"Checksum" |
public static final String |
NAMED_FIELD_DESCRIPTION |
"Description" |
public static final String |
NAMED_FIELD_FILEDESC |
"ARC-FileDesc" |
public static final String |
NAMED_FIELD_IP_LABEL |
"IP-Address" |
public static final String |
NAMED_FIELD_RELATED_LABEL |
"References" |
public static final String |
NAMED_FIELD_TRUNCATED |
"Truncated" |
public static final String |
NAMED_FIELD_TRUNCATED_VALUE_HEAD |
"long-headers" |
public static final String |
NAMED_FIELD_TRUNCATED_VALUE_LENGTH |
"length" |
public static final String |
NAMED_FIELD_TRUNCATED_VALUE_TIME |
"time" |
public static final String |
NAMED_FIELD_WARCFILENAME |
"Filename" |
public static final String |
PLACEHOLDER_RECORD_LENGTH_STRING |
"000000000000" |
public static final String |
PROFILE_REVISIT_IDENTICAL_DIGEST |
"http://netpreserve.org/warc/1.0/revisit/identical-payload-digest" |
public static final String |
PROFILE_REVISIT_NOT_MODIFIED |
"http://netpreserve.org/warc/1.0/revisit/server-not-modified" |
public static final String |
PROFILE_REVISIT_URI_AGNOSTIC_IDENTICAL_DIGEST |
"http://netpreserve.org/warc/1.0/revisit/uri-agnostic-identical-payload-digest" |
public static final String |
TRUNCATED_VALUE_UNSPECIFIED |
"unspecified" |
public static final String |
TYPE |
"type" |
public static final String |
WARC_FIELDS_TYPE |
"application/warc-fields" |
public static final String |
WARC_FILE_EXTENSION |
"warc" |
public static final String |
WARC_HEADER_ENCODING |
"UTF-8" |
public static final String |
WARC_ID |
"WARC/1.0" |
public static final String |
WARC_MAGIC |
"WARC/" |
public static final String |
WARC_VERSION |
"1.0" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
MAX_ALLOWED_RECOVERABLES |
10 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
protected static final long |
MAX_HEADER_MATERIAL |
1048576L |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
UTF8 |
"UTF-8" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
DEFAULT_MAX_ACTIVE |
1 |
public static final int |
DEFAULT_MAX_WAIT_FOR_IDLE |
500 |
protected static final int |
LARGEST_MAX_ACTIVE |
255 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
DEFAULT_PREFIX |
"WEB" |
public static final String |
DEFAULT_TEMPLATE |
"${prefix}-${timestamp17}-${serialno}-${heritrix.pid}~${heritrix.hostname}~${heritrix.port}" |
public static final String |
UTF8 |
"UTF-8" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
WCDX_VERSION |
"0.1" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
CONTENT_BYTES |
"contentBytes" |
public static final String |
NUM_RECORDS |
"numRecords" |
public static final String |
SIZE_ON_DISK |
"sizeOnDisk" |
public static final String |
TOTAL_BYTES |
"totalBytes" |
public static final String |
TOTALS |
"totals" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
ARC_HEADER_LENGTH |
"ARC-Header-Length" |
public static final String |
ARC_HEADER_METADATA |
"ARC-Header-Metadata" |
public static final String |
CONTAINER |
"Container" |
public static final String |
CONTAINER_COMPRESSED |
"Compressed" |
public static final String |
CONTAINER_FILENAME |
"Filename" |
public static final String |
CONTAINER_OFFSET |
"Offset" |
public static final String |
DAT_METADATA |
"DAT-Metadata" |
public static final String |
DNS_DATE |
"Date" |
public static final String |
DNS_ENTRIES |
"Entries" |
public static final String |
DNS_METADATA |
"DNS-Metadata" |
public static final String |
DNS_NAME |
"Name" |
public static final String |
DNS_NETCLASS |
"Net-Class" |
public static final String |
DNS_TTL |
"TTL" |
public static final String |
DNS_TYPE |
"Type" |
public static final String |
DNS_VALUE |
"Value" |
public static final String |
ENVELOPE |
"Envelope" |
public static final String |
ENVELOPE_FORMAT |
"Format" |
public static final String |
ENVELOPE_FORMAT_ARC |
"ARC" |
public static final String |
ENVELOPE_FORMAT_WARC |
"WARC" |
public static final String |
FILEDESC_DATA |
"Data" |
public static final String |
FILEDESC_FORMAT |
"Format" |
public static final String |
FILEDESC_MAJOR |
"Major-Version" |
public static final String |
FILEDESC_METADATA |
"Filedesc-Metadata" |
public static final String |
FILEDESC_MINOR |
"Minor-Version" |
public static final String |
FILEDESC_ORGANIZATION |
"Organization" |
public static final String |
GZIP |
"Gzip-Metadata" |
public static final String |
GZIP_COMMENT_LENGTH |
"Comment-Length" |
public static final String |
GZIP_DEFLATE_LENGTH |
"Deflate-Length" |
public static final String |
GZIP_FEXTRA |
"F-Extra" |
public static final String |
GZIP_FEXTRA_NAME |
"Name" |
public static final String |
GZIP_FEXTRA_VALUE |
"Value" |
public static final String |
GZIP_FILENAME |
"Filename" |
public static final String |
GZIP_FOOTER_LENGTH |
"Footer-Length" |
public static final String |
GZIP_HEADER_CRC |
"Header-CRC" |
public static final String |
GZIP_HEADER_LENGTH |
"Header-Length" |
public static final String |
GZIP_INFLATED_CRC |
"Inflated-CRC" |
public static final String |
GZIP_INFLATED_LENGTH |
"Inflated-Length" |
public static final String |
HTML_BASE |
"Base" |
public static final String |
HTML_HEAD |
"Head" |
public static final String |
HTML_LINK_TAGS |
"Link" |
public static final String |
HTML_LINKS |
"Links" |
public static final String |
HTML_META_TAGS |
"Metas" |
public static final String |
HTML_METADATA |
"HTML-Metadata" |
public static final String |
HTML_SCRIPT_TAGS |
"Scripts" |
public static final String |
HTML_TITLE |
"Title" |
public static final String |
HTTP_ENTITY_DIGEST |
"Entity-Digest" |
public static final String |
HTTP_ENTITY_LENGTH |
"Entity-Length" |
public static final String |
HTTP_ENTITY_TRAILING_SLOP |
"Entity-Trailing-Slop-Bytes" |
public static final String |
HTTP_HEADERS_CORRUPT |
"Headers-Corrupt" |
public static final String |
HTTP_HEADERS_LENGTH |
"Headers-Length" |
public static final String |
HTTP_HEADERS_LIST |
"Headers" |
public static final String |
HTTP_MESSAGE_METHOD |
"Method" |
public static final String |
HTTP_MESSAGE_PATH |
"Path" |
public static final String |
HTTP_MESSAGE_REASON |
"Reason" |
public static final String |
HTTP_MESSAGE_STATUS |
"Status" |
public static final String |
HTTP_MESSAGE_VERSION |
"Version" |
public static final String |
HTTP_REQUEST_MESSAGE |
"Request-Message" |
public static final String |
HTTP_REQUEST_METADATA |
"HTTP-Request-Metadata" |
public static final String |
HTTP_RESPONSE_MESSAGE |
"Response-Message" |
public static final String |
HTTP_RESPONSE_METADATA |
"HTTP-Response-Metadata" |
public static final String |
METADATA_KV_NAME |
"Name" |
public static final String |
METADATA_KV_VALUE |
"Value" |
public static final String |
PAYLOAD_CONTENT_TYPE |
"Actual-Content-Type" |
public static final String |
PAYLOAD_DIGEST |
"Block-Digest" |
public static final String |
PAYLOAD_LEADING_SLOP_BYTES |
"Leading-Slop-Length" |
public static final String |
PAYLOAD_LENGTH |
"Actual-Content-Length" |
public static final String |
PAYLOAD_METADATA |
"Payload-Metadata" |
public static final String |
PAYLOAD_SLOP_BYTES |
"Trailing-Slop-Length" |
public static final String |
PAYLOAD_TYPE_DAT |
"alexa/dat" |
public static final String |
PAYLOAD_TYPE_DNS |
"text/dns" |
public static final String |
PAYLOAD_TYPE_FILEDESC |
"alexa/filedesc" |
public static final String |
PAYLOAD_TYPE_HTTP_REQUEST |
"application/http; msgtype=request" |
public static final String |
PAYLOAD_TYPE_HTTP_RESPONSE |
"application/http; msgtype=response" |
public static final String |
PAYLOAD_TYPE_WARC_META_FIELDS |
"application/metadata-fields" |
public static final String |
PAYLOAD_TYPE_WARCINFO |
"application/warc-fields" |
public static final String |
WARC_HEADER_LENGTH |
"WARC-Header-Length" |
public static final String |
WARC_HEADER_METADATA |
"WARC-Header-Metadata" |
public static final String |
WARC_META_FIELDS_CORRUPT |
"FIELDS_CORRUPT" |
public static final String |
WARC_META_FIELDS_LIST |
"Metadata-Records" |
public static final String |
WARC_META_FIELDS_METADATA |
"WARC-Metadata-Metadata" |
public static final String |
WARCINFO_METADATA |
"WARC-Info-Metadata" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
AUTH_ORIGINAL |
0 |
public static final int |
AUTH_SETTINGS |
5 |
public static final int |
AUTH_STRIP_PASS |
2 |
public static final int |
AUTH_STRIP_USER |
1 |
public static final int |
HASH_ORIGINAL |
0 |
public static final int |
HASH_SETTINGS |
4 |
public static final int |
HASH_STRIP |
1 |
public static final int |
HOST_LOWERCASE |
1 |
public static final int |
HOST_MASSAGE |
2 |
public static final int |
HOST_ORIGINAL |
0 |
public static final int |
HOST_SETTINGS |
0 |
public static final int |
NUM_SETTINGS |
7 |
public static final int |
PATH_LOWERCASE |
1 |
public static final int |
PATH_ORIGINAL |
0 |
public static final int |
PATH_SETTINGS |
2 |
public static final int |
PATH_STRIP_EMPTY |
4 |
public static final int |
PATH_STRIP_SESSION_ID |
2 |
public static final int |
PATH_STRIP_TRAILING_SLASH_UNLESS_EMPTY |
8 |
public static final int |
PORT_ORIGINAL |
0 |
public static final int |
PORT_SETTINGS |
1 |
public static final int |
PORT_STRIP_DEFAULT |
1 |
public static final int |
QUERY_ALPHA_REORDER |
8 |
public static final int |
QUERY_LOWERCASE |
1 |
public static final int |
QUERY_ORIGINAL |
0 |
public static final int |
QUERY_SETTINGS |
3 |
public static final int |
QUERY_STRIP_EMPTY |
4 |
public static final int |
QUERY_STRIP_SESSION_ID |
2 |
public static final int |
SCHEME_LOWERCASE |
1 |
public static final int |
SCHEME_ORIGINAL |
0 |
public static final int |
SCHEME_SETTINGS |
6 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
DEFAULT_PORT |
-1 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final char |
COLON |
58 |
public static final String |
COMMERCIAL_AT |
"@" |
public static final String |
DEFAULT_SCHEME |
"http://" |
public static final String |
DNS_SCHEME |
"dns:" |
public static final String |
FILEDESC_SCHEME |
"filedesc:" |
public static final String |
FTP_SCHEME |
"ftp://" |
public static final String |
HTTP_SCHEME |
"http://" |
public static final String |
HTTPS_SCHEME |
"https://" |
public static final String |
MMS_SCHEME |
"mms://" |
public static final char |
PERCENT_SIGN |
37 |
public static final String |
RTSP_SCHEME |
"rtsp://" |
public static final String |
STRAY_SPACING |
"[\n\r\t\\p{Zl}\\p{Zp}\u0085]+" |
public static final String |
WAIS_SCHEME |
"wais://" |
public static final String |
WARCINFO_SCHEME |
"warcinfo:" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
MASSAGEHOST_PATTERN |
"^www\\d*\\." |
public static final int |
MAX_URL_LENGTH |
2083 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
protected static final String |
ACCEPTABLE_ASCII_DOMAIN |
"^(?:[a-zA-Z0-9_-]++(?:\\.)?)++$" |
public static final String |
APOSTROPH |
"`" |
public static final String |
BACKSLASH |
"\\" |
public static final String |
CIRCUMFLEX |
"^" |
public static final String |
CIRCUMFLEX_PATTERN |
"\\^" |
public static final char |
COLON |
58 |
public static final String |
COMMERCIAL_AT |
"@" |
public static final String |
DOT |
"." |
public static final String |
EMPTY_STRING |
"" |
public static final String |
ESCAPED_APOSTROPH |
"%60" |
public static final String |
ESCAPED_BACKSLASH |
"%5C" |
public static final String |
ESCAPED_CIRCUMFLEX |
"%5E" |
public static final String |
ESCAPED_LCURBRACKET |
"%7B" |
public static final String |
ESCAPED_LSQRBRACKET |
"%5B" |
public static final String |
ESCAPED_PIPE |
"%7C" |
public static final String |
ESCAPED_QUOT |
"%22" |
public static final String |
ESCAPED_RCURBRACKET |
"%7D" |
public static final String |
ESCAPED_RSQRBRACKET |
"%5D" |
public static final String |
ESCAPED_SPACE |
"%20" |
public static final String |
ESCAPED_SQUOT |
"%27" |
public static final String |
HTTP |
"http" |
public static final String |
HTTP_PORT |
":80" |
public static final String |
HTTPS |
"https" |
public static final String |
HTTPS_PORT |
":443" |
public static final String |
IMPROPERESC |
"%((?:[^\\p{XDigit}])|(?:.[^\\p{XDigit}])|(?:\\z))" |
public static final String |
IMPROPERESC_REPLACE |
"%25$1" |
public static final String |
LCURBRACKET |
"{" |
public static final String |
LCURBRACKET_PATTERN |
"\\{" |
public static final String |
LSQRBRACKET |
"[" |
public static final String |
LSQRBRACKET_PATTERN |
"\\[" |
public static final String |
NBSP |
"\u00a0" |
public static final char |
PERCENT_SIGN |
37 |
public static final String |
PIPE |
"|" |
public static final String |
PIPE_PATTERN |
"\\|" |
public static final String |
QUOT |
"\"" |
public static final String |
RCURBRACKET |
"}" |
public static final String |
RCURBRACKET_PATTERN |
"\\}" |
public static final String |
RSQRBRACKET |
"]" |
public static final String |
RSQRBRACKET_PATTERN |
"\\]" |
public static final String |
SLASH |
"/" |
public static final String |
SLASHDOTDOTSLASH |
"^(/\\.\\./)+" |
public static final String |
SPACE |
" " |
public static final String |
SQUOT |
"\'" |
public static final String |
STRAY_SPACING |
"[\n\r\t]+" |
public static final String |
TRAILING_ESCAPED_SPACE |
"^(.*)(%20)+$" |
public static final String |
URI_HEX_ENCODING |
"^[^%]*%[\\p{XDigit}][\\p{XDigit}].*" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
GZIP_SUFFIX |
".gz" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
VERSION |
"0.1" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
NO_TYPE_MIMETYPE |
"no-type" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
TEST_TMP_SYSTEM_PROPERTY_NAME |
"testtmpdir" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
protected static final String |
CRLF |
"\r\n" |
protected static final String |
FOLD_PREFIX |
"\r\n " |
public static final long |
MAXIMUM_SIZE |
10240L |
public static final String |
MIMETYPE |
"application/warc-fields" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
TOOL_DESCRIPTION |
"A tool for performing binary searches through sorted text files, either local, or in HDFS" |
public static final String |
TOOL_NAME |
"bin-search" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
BINSEARCH_BLOCK_SIZE |
8192 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
CONTENT_LENGTH |
"Content-Length" |
public static final String |
LAST_MODIFIED |
"Last-Modified" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final String |
COMMENT_LINE |
"\\s*(#.*)?" |
public static final String |
ENTRY |
"$1" |
public static final String |
NONWHITESPACE_ENTRY_TRAILING_COMMENT |
"^[\\s\ufeff]*(\\S+)\\s*(#.*)?$" |
public static final String |
TRIMMED_ENTRY_TRAILING_COMMENT |
"^\\s*([^#]+?)\\s*(#.*)?$" |
| Modifier and Type | Constant Field | Value |
|---|---|---|
public static final int |
MINIMAL_GZIP_HEADER_LENGTH |
10 |
| Modifier and Type | Constant Field | Value |
|---|---|---|
protected static final int |
FCOMMENT |
16 |
protected static final int |
FEXTRA |
4 |
protected static final int |
FHCRC |
2 |
protected static final int |
FNAME |
8 |
protected static final int |
FTEXT |
1 |
public static final int |
GZIP_MAGIC |
35615 |
Copyright © 2015 The International Internet Preservation Consortium. All Rights Reserved.