public class WARCReader extends ArchiveReader implements WARCConstants
WARCReaderFactory to get instance.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, HTTP_RESPONSE_MIMETYPE_NS, 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, 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, ORIGIN_FIELD_KEY, READER_IDENTIFIER_FIELD_KEY, RECORD_IDENTIFIER_FIELD_KEY, SINGLE_SPACE, TYPE_FIELD_KEY, URL_FIELD_KEY, VERSION_FIELD_KEY| Modifier | Constructor and Description |
|---|---|
protected |
WARCReader() |
| Modifier and Type | Method and Description |
|---|---|
protected WARCRecord |
createArchiveRecord(java.io.InputStream is,
long offset)
Create new WARC record.
|
static void |
createCDXIndexFile(java.lang.String urlOrPath)
Generate a CDX index file for an ARC file.
|
void |
dump(boolean compress)
Dump this file on STDOUT
|
ArchiveReader |
getDeleteFileOnCloseReader(java.io.File f) |
java.lang.String |
getDotFileExtension() |
java.lang.String |
getFileExtension() |
protected void |
gotoEOR(ArchiveRecord record)
Skip over any trailing new lines at end of the record so we're lined up
ready to read the next.
|
protected void |
initialize(java.lang.String i)
Convenience method used by subclass constructors.
|
static void |
main(java.lang.String[] args)
Command-line interface to WARCReader.
|
protected static void |
output(WARCReader reader,
java.lang.String format)
Write out the arcfile.
|
protected void |
readExpectedChar(java.io.InputStream is,
int expected) |
cdxOutput, 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, validateprotected void initialize(java.lang.String i)
ArchiveReaderinitialize in class ArchiveReaderi - Identifier for Archive file this reader goes against.protected void gotoEOR(ArchiveRecord record) throws java.io.IOException
gotoEOR in class ArchiveReaderrecord - java.io.IOExceptionprotected void readExpectedChar(java.io.InputStream is,
int expected)
throws java.io.IOException
java.io.IOExceptionprotected WARCRecord createArchiveRecord(java.io.InputStream is, long offset) throws java.io.IOException
createArchiveRecord in class ArchiveReaderis - InputStream to use.offset - Absolute offset into WARC file.java.io.IOExceptionpublic void dump(boolean compress)
throws java.io.IOException,
java.text.ParseException
ArchiveReaderdump in class ArchiveReaderjava.io.IOExceptionjava.text.ParseExceptionpublic ArchiveReader getDeleteFileOnCloseReader(java.io.File f)
getDeleteFileOnCloseReader in class ArchiveReaderpublic java.lang.String getDotFileExtension()
getDotFileExtension in class ArchiveReaderpublic java.lang.String getFileExtension()
getFileExtension in class ArchiveReaderprotected static void output(WARCReader reader, java.lang.String format) throws java.io.IOException, java.text.ParseException
reader - format - Format to use outputting.java.io.IOExceptionjava.text.ParseExceptionpublic static void createCDXIndexFile(java.lang.String urlOrPath)
throws java.io.IOException,
java.text.ParseException
urlOrPath - The ARC file to generate a CDX index forjava.io.IOExceptionjava.text.ParseExceptionpublic static void main(java.lang.String[] args)
throws org.apache.commons.cli.ParseException,
java.io.IOException,
java.text.ParseException
usage: java org.archive.io.arc.WARCReader [--offset=#] ARCFILE -h,--help Prints this message and exits. -o,--offset Outputs record at this offset into arc file.
Outputs using a pseudo-CDX format as described here: CDX Legent and here Example. Legend used in below is: 'CDX b e a m s c V (or v if uncompressed) n g'. Hash is hard-coded straight SHA-1 hash of content.
args - Command-line arguments.org.apache.commons.cli.ParseException - Failed parse of the command line.java.io.IOExceptionjava.text.ParseExceptionCopyright © 2019 The International Internet Preservation Consortium. All Rights Reserved.