public class ARCUtils extends java.lang.Object implements ARCConstants
ARCConstants.ArcRecordErrorsACTUAL_LENGTH_KEY, ALEXA_DAT_MIME, ARC_FILE_EXTENSION, ARC_GZIP_EXTRA_FIELD, ARC_MAGIC_NUMBER, ARC_META_CHARSET, CARRIAGE_RETURN_ORD, CHECKSUM_FIELD_KEY, CHECKSUM_HEADER_FIELD_KEY, CODE_HEADER_FIELD_KEY, COMPRESSED_ARC_FILE_EXTENSION, DATE_STRING_KEY, DECLARED_LENGTH_KEY, DEFAULT_ENCODING, DEFAULT_GZIP_HEADER_LENGTH, DEFAULT_MAX_ARC_FILE_SIZE, DEFAULT_MIME, DELIMITER, DNS_MIME, DOT_ARC_FILE_EXTENSION, DOT_COMPRESSED_ARC_FILE_EXTENSION, DOT_COMPRESSED_FILE_EXTENSION, FIELD_COUNT, FILEDESC_SCHEME, FILENAME_FIELD_KEY, FILENAME_HEADER_FIELD_KEY, GZIP_HEADER_BEGIN, HEADER_FIELD_SEPARATOR, HEADER_LENGTH, IP_HEADER_FIELD_KEY, IP_KEY, LEADING_NEWLINES_KEY, LINE_SEPARATOR, LOCATION_HEADER_FIELD_KEY, MAX_HEADER_LINE_LENGTH, MAX_META_LENGTH, MAX_METADATA_LINE_LENGTH, MIME_KEY, MINIMUM_RECORD_LENGTH, NEW_LINE_ORD, OFFSET_FIELD_KEY, OFFSET_HEADER_FIELD_KEY, REQUIRED_VERSION_1_HEADER_FIELDS, STATUSCODE_FIELD_KEY, TOKENIZED_PREFIX, TRAILING_CRUFT_KEY, TRAILING_NEWLINES_KEY, URL_KEYABSOLUTE_OFFSET_KEY, CDX, CDX_FILE, CDX_LINE_BUFFER_SIZE, CRLF, DATE_FIELD_KEY, DEFAULT_DIGEST_METHOD, 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| Constructor and Description |
|---|
ARCUtils() |
| Modifier and Type | Method and Description |
|---|---|
static boolean |
isCompressed(java.io.File arcFile) |
static java.lang.String |
parseArcFilename(java.lang.String pathOrUri) |
static boolean |
testCompressedARCFile(java.io.File arcFile)
Check file is compressed and in ARC GZIP format.
|
static boolean |
testCompressedARCFile(java.io.File arcFile,
boolean skipSuffixCheck)
Check file is compressed and in ARC GZIP format.
|
static boolean |
testCompressedARCStream(java.io.InputStream is)
Tests passed stream is gzip stream by reading in the HEAD.
|
static boolean |
testCompressedRepositionalStream(it.unimi.dsi.fastutil.io.RepositionableStream rs)
Tests passed stream is gzip stream by reading in the HEAD.
|
static boolean |
testCompressedStream(java.io.InputStream is)
Tests passed stream is gzip stream by reading in the HEAD.
|
static boolean |
testUncompressedARCFile(java.io.File arcFile)
Check file is uncompressed ARC file.
|
public static java.lang.String parseArcFilename(java.lang.String pathOrUri)
throws java.net.URISyntaxException
pathOrUri - Path or URI to extract arc filename from.java.net.URISyntaxExceptionpublic static boolean isCompressed(java.io.File arcFile)
throws java.io.IOException
arcFile - File to test.arcFile is compressed ARC.java.io.IOExceptionpublic static boolean testCompressedARCFile(java.io.File arcFile)
throws java.io.IOException
arcFile - File to test if its Internet Archive ARC file
GZIP compressed.java.io.IOException - If file does not exist or is not unreadable.public static boolean testCompressedARCFile(java.io.File arcFile,
boolean skipSuffixCheck)
throws java.io.IOException
arcFile - File to test if its Internet Archive ARC file
GZIP compressed.skipSuffixCheck - Set to true if we're not to test on the
'.arc.gz' suffix.java.io.IOException - If file does not exist or is not unreadable.public static boolean testCompressedARCStream(java.io.InputStream is)
throws java.io.IOException
is - An InputStream.java.io.IOExceptionpublic static boolean testCompressedRepositionalStream(it.unimi.dsi.fastutil.io.RepositionableStream rs)
throws java.io.IOException
rs - An InputStream that is Repositionable.java.io.IOExceptionpublic static boolean testCompressedStream(java.io.InputStream is)
throws java.io.IOException
is - An InputStream.java.io.IOExceptionpublic static boolean testUncompressedARCFile(java.io.File arcFile)
throws java.io.IOException
arcFile - File to test if its Internet Archive ARC file uncompressed.java.io.IOException - If file does not exist or is not unreadable.Copyright © 2019 The International Internet Preservation Consortium. All Rights Reserved.