|
|||||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | ||||||||
java.lang.Objectorg.jwat.warc.WarcHeader
public class WarcHeader
| Constructor Summary | |
|---|---|
protected |
WarcHeader()
Non public constructor to allow unit testing. |
| Method Summary | |
|---|---|
protected void |
addErrorDiagnosis(DiagnosisType type,
String entity,
String... information)
Add an error diagnosis of the given type on a specific entity with optional extra information. |
protected void |
addHeader(HeaderLine headerLine)
Identify a (WARC) header name, validate the value and set the header. |
HeaderLine |
addHeader(String fieldName,
ContentType contentTypeFieldValue,
String fieldValueStr)
|
HeaderLine |
addHeader(String fieldName,
Date dateFieldValue,
String fieldValueStr)
|
HeaderLine |
addHeader(String fieldName,
InetAddress inetAddrFieldValue,
String fieldValueStr)
|
HeaderLine |
addHeader(String fieldName,
Integer integerFieldValue,
String fieldValueStr)
|
HeaderLine |
addHeader(String fieldName,
Long longFieldValue,
String fieldValueStr)
|
HeaderLine |
addHeader(String fieldName,
String fieldValue)
|
HeaderLine |
addHeader(String fieldName,
String fieldValueStr,
int dt,
Integer integerFieldValue,
Long longFieldValue,
WarcDigest digestFieldValue,
ContentType contentTypeFieldValue,
Date dateFieldValue,
InetAddress inetAddrFieldValue,
URI uriFieldValue)
|
HeaderLine |
addHeader(String fieldName,
URI uriFieldValue,
String fieldValueStr)
|
HeaderLine |
addHeader(String fieldName,
WarcDigest digestFieldValue,
String fieldValueStr)
|
protected void |
addWarningDiagnosis(DiagnosisType type,
String entity,
String... information)
Add a warning diagnosis of the given type on a specific entity with optional extra information. |
protected void |
checkFieldPolicy(int rtype,
int ftype,
Object fieldObj,
String valueStr)
Given a WARC record type and a WARC field looks up the policy in a matrix build from the WARC ISO standard. |
protected void |
checkFields()
Validate the WARC header relative to the WARC-Type and according the WARC ISO standard. |
static WarcHeader |
initHeader(WarcReader reader,
long startOffset,
Diagnostics<Diagnosis> diagnostics)
|
static WarcHeader |
initHeader(WarcWriter writer,
Diagnostics<Diagnosis> diagnostics)
|
boolean |
parseHeader(ByteCountingPushBackInputStream in)
|
protected void |
parseHeaders(ByteCountingPushBackInputStream in)
Reads WARC header lines one line at a time until an empty line is encountered. |
protected boolean |
parseVersion(ByteCountingPushBackInputStream in)
Looks forward in the inputstream for a valid WARC version line. |
| Methods inherited from class java.lang.Object |
|---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
| Field Detail |
|---|
protected WarcReader reader
protected Diagnostics<Diagnosis> diagnostics
protected WarcFieldParsers fieldParser
protected DateFormat warcDateFormat
DateFormat as specified by the WARC ISO standard.
protected long startOffset
protected boolean[] seen
public String warcTypeStr
public Integer warcTypeIdx
public String warcFilename
public String warcRecordIdStr
public URI warcRecordIdUri
public String warcDateStr
public Date warcDate
public String contentLengthStr
public Long contentLength
public String contentTypeStr
public ContentType contentType
public String warcTruncatedStr
public Integer warcTruncatedIdx
public String warcIpAddress
public InetAddress warcInetAddress
public List<WarcConcurrentTo> warcConcurrentToList
public String warcRefersToStr
public URI warcRefersToUri
public String warcTargetUriStr
public URI warcTargetUriUri
public String warcWarcinfoIdStr
public URI warcWarcInfoIdUri
public String warcBlockDigestStr
public WarcDigest warcBlockDigest
public String warcPayloadDigestStr
public WarcDigest warcPayloadDigest
public String warcIdentifiedPayloadTypeStr
public ContentType warcIdentifiedPayloadType
public String warcProfileStr
public Integer warcProfileIdx
public String warcSegmentNumberStr
public Integer warcSegmentNumber
public String warcSegmentOriginIdStr
public URI warcSegmentOriginIdUrl
public String warcSegmentTotalLengthStr
public Long warcSegmentTotalLength
protected ByteArrayOutputStream headerBytesOut
public byte[] headerBytes
protected List<HeaderLine> headerList
protected Map<String,HeaderLine> headerMap
| Constructor Detail |
|---|
protected WarcHeader()
| Method Detail |
|---|
public static WarcHeader initHeader(WarcWriter writer,
Diagnostics<Diagnosis> diagnostics)
public static WarcHeader initHeader(WarcReader reader,
long startOffset,
Diagnostics<Diagnosis> diagnostics)
protected void addErrorDiagnosis(DiagnosisType type,
String entity,
String... information)
type - diagnosis typeentity - entity examinedinformation - optional extra information
protected void addWarningDiagnosis(DiagnosisType type,
String entity,
String... information)
type - diagnosis typeentity - entity examinedinformation - optional extra information
public boolean parseHeader(ByteCountingPushBackInputStream in)
throws IOException
IOException
protected boolean parseVersion(ByteCountingPushBackInputStream in)
throws IOException
in - data inputstream
IOException - if an error occurs while reading version data
protected void parseHeaders(ByteCountingPushBackInputStream in)
throws IOException
in - header input stream
IOException - if an error occurs while reading the WARC headerprotected void addHeader(HeaderLine headerLine)
fieldName - header namefieldValue - header valueseen - array of headers seen so far used for duplication check
public HeaderLine addHeader(String fieldName,
String fieldValue)
public HeaderLine addHeader(String fieldName,
Integer integerFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
Long longFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
WarcDigest digestFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
ContentType contentTypeFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
Date dateFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
InetAddress inetAddrFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
URI uriFieldValue,
String fieldValueStr)
public HeaderLine addHeader(String fieldName,
String fieldValueStr,
int dt,
Integer integerFieldValue,
Long longFieldValue,
WarcDigest digestFieldValue,
ContentType contentTypeFieldValue,
Date dateFieldValue,
InetAddress inetAddrFieldValue,
URI uriFieldValue)
protected void checkFields()
protected void checkFieldPolicy(int rtype,
int ftype,
Object fieldObj,
String valueStr)
rtype - WARC record type idftype - WARC field type idfieldObj - WARC fieldvalueStr - WARC raw field value
|
|||||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | ||||||||