public class ResourceExtractor extends java.lang.Object implements ResourceConstants, org.apache.hadoop.util.Tool
| Modifier and Type | Field and Description |
|---|---|
static java.lang.String |
TOOL_DESCRIPTION |
static java.lang.String |
TOOL_NAME |
ARC_HEADER_LENGTH, ARC_HEADER_METADATA, CONTAINER, CONTAINER_COMPRESSED, CONTAINER_FILENAME, CONTAINER_OFFSET, CR_NL_CHARS, DAT_METADATA, DNS_DATE, DNS_ENTRIES, DNS_METADATA, DNS_NAME, DNS_NETCLASS, DNS_TTL, DNS_TYPE, DNS_VALUE, ENVELOPE, ENVELOPE_FORMAT, ENVELOPE_FORMAT_ARC, ENVELOPE_FORMAT_WARC, ENVELOPE_FORMAT_WARC_1_0, FILEDESC_DATA, FILEDESC_FORMAT, FILEDESC_MAJOR, FILEDESC_METADATA, FILEDESC_MINOR, FILEDESC_ORGANIZATION, GZIP, GZIP_COMMENT_LENGTH, GZIP_DEFLATE_LENGTH, GZIP_FEXTRA, GZIP_FEXTRA_NAME, GZIP_FEXTRA_VALUE, GZIP_FILENAME, GZIP_FOOTER_LENGTH, GZIP_HEADER_CRC, GZIP_HEADER_LENGTH, GZIP_INFLATED_CRC, GZIP_INFLATED_LENGTH, HTML_BASE, HTML_HEAD, HTML_LINK_TAGS, HTML_LINKS, HTML_META_TAGS, HTML_METADATA, HTML_SCRIPT_TAGS, HTML_TITLE, HTTP_ENTITY_DIGEST, HTTP_ENTITY_LENGTH, HTTP_ENTITY_TRAILING_SLOP, HTTP_HEADERS_CORRUPT, HTTP_HEADERS_LENGTH, HTTP_HEADERS_LIST, HTTP_MESSAGE_METHOD, HTTP_MESSAGE_PATH, HTTP_MESSAGE_REASON, HTTP_MESSAGE_STATUS, HTTP_MESSAGE_VERSION, HTTP_REQUEST_MESSAGE, HTTP_REQUEST_METADATA, HTTP_RESPONSE_MESSAGE, HTTP_RESPONSE_METADATA, METADATA_KV_NAME, METADATA_KV_VALUE, PAYLOAD_CONTENT_TYPE, PAYLOAD_DIGEST, PAYLOAD_LEADING_SLOP_BYTES, PAYLOAD_LENGTH, PAYLOAD_METADATA, PAYLOAD_SLOP_BYTES, PAYLOAD_TYPE_DAT, PAYLOAD_TYPE_DNS, PAYLOAD_TYPE_FILEDESC, PAYLOAD_TYPE_HTTP_REQUEST, PAYLOAD_TYPE_HTTP_RESPONSE, PAYLOAD_TYPE_WARC_META_FIELDS, PAYLOAD_TYPE_WARCINFO, WARC_HEADER_LENGTH, WARC_HEADER_METADATA, WARC_META_FIELDS_CORRUPT, WARC_META_FIELDS_LIST, WARC_META_FIELDS_METADATA, WARCINFO_METADATA| Constructor and Description |
|---|
ResourceExtractor() |
| Modifier and Type | Method and Description |
|---|---|
org.apache.hadoop.conf.Configuration |
getConf() |
java.io.OutputStream |
getOut() |
static void |
main(java.lang.String[] args) |
int |
run(java.lang.String[] args) |
void |
setConf(org.apache.hadoop.conf.Configuration conf) |
void |
setOut(java.io.OutputStream out) |
public static final java.lang.String TOOL_NAME
public static final java.lang.String TOOL_DESCRIPTION
public void setConf(org.apache.hadoop.conf.Configuration conf)
setConf in interface org.apache.hadoop.conf.Configurablepublic org.apache.hadoop.conf.Configuration getConf()
getConf in interface org.apache.hadoop.conf.Configurablepublic static void main(java.lang.String[] args)
throws java.lang.Exception
java.lang.Exceptionpublic int run(java.lang.String[] args)
throws java.lang.IndexOutOfBoundsException,
java.io.FileNotFoundException,
java.io.IOException,
ResourceParseException,
java.net.URISyntaxException
run in interface org.apache.hadoop.util.Tooljava.lang.IndexOutOfBoundsExceptionjava.io.FileNotFoundExceptionjava.io.IOExceptionResourceParseExceptionjava.net.URISyntaxExceptionpublic java.io.OutputStream getOut()
public void setOut(java.io.OutputStream out)
out - the out to setCopyright © 2019 The International Internet Preservation Consortium. All Rights Reserved.