public class CDXServer extends BaseCDXServer
Modifier and Type | Field and Description |
---|---|
protected String |
cdxFormat |
protected org.archive.format.cdx.CDXLineFactory |
cdxLineFactory |
protected org.archive.format.cdx.CDXInputSource |
cdxSource |
protected boolean |
collapseToLast |
protected org.archive.format.gzip.zipnum.ZipNumParams |
defaultParams |
protected int |
maxPageSize |
protected String[] |
noCollapsePrefix |
protected int |
queryMaxLimit |
protected org.archive.format.gzip.zipnum.ZipNumCluster |
zipnumSource |
ajaxAccessControl, authChecker, canonicalizer, CDX_AUTH_TOKEN, cookieAuthToken, surtMode, urlSurtRangeComputer
Constructor and Description |
---|
CDXServer() |
Modifier and Type | Method and Description |
---|---|
void |
afterPropertiesSet() |
protected org.archive.util.iterator.CloseableIterator<String> |
createBoundedCdxIterator(String[] startEndUrl,
CDXQuery query,
org.archive.format.gzip.zipnum.ZipNumIndex.PageResult pageResult,
org.archive.util.iterator.CloseableIterator<String> idx) |
protected org.archive.util.iterator.CloseableIterator<String> |
createPagedCdxIterator(String[] startEndUrl,
CDXQuery query,
AuthToken authToken,
CDXWriter responseWriter) |
protected boolean |
determineGzip(javax.servlet.http.HttpServletRequest request,
CDXQuery query) |
org.archive.format.cdx.CDXLine |
findLastCapture(String url,
String digest,
boolean ignoreRobots)
Look up the latest (non-revisit) capture of
url in the
CDX database. |
void |
getCdx(CDXQuery query,
AuthToken authToken,
CDXWriter responseWriter) |
void |
getCdx(javax.servlet.http.HttpServletRequest request,
javax.servlet.http.HttpServletResponse response,
CDXQuery query) |
String |
getCdxFormat() |
org.archive.format.cdx.CDXInputSource |
getCdxSource() |
org.archive.format.gzip.zipnum.ZipNumParams |
getDefaultParams() |
String[] |
getNoCollapsePrefix() |
int |
getPageSize() |
int |
getQueryMaxLimit() |
org.archive.format.gzip.zipnum.ZipNumCluster |
getZipnumSource() |
boolean |
isCollapseToLast() |
void |
setCdxFormat(String cdxFormat) |
void |
setCdxSource(org.archive.format.cdx.CDXInputSource cdxSource) |
void |
setCollapseToLast(boolean collapseToLast)
If set to
true , timestamp-collapsing writes out the last best
capture in the collapse group, instead of the first. |
void |
setDefaultParams(org.archive.format.gzip.zipnum.ZipNumParams defaultParams) |
void |
setNoCollapsePrefix(String[] noCollapsePrefix) |
void |
setPageSize(int pageSize) |
void |
setQueryMaxLimit(int queryMaxLimit) |
void |
setZipnumSource(org.archive.format.gzip.zipnum.ZipNumCluster zipnumSource) |
protected void |
writeCdxResponse(CDXWriter responseWriter,
org.archive.util.iterator.CloseableIterator<String> cdx,
int readLimit,
CDXQuery query,
AuthToken authToken,
CDXAccessFilter accessChecker) |
protected void |
writeIdxResponse(CDXWriter responseWriter,
org.archive.util.iterator.CloseableIterator<String> iter) |
canonicalize, createAuthToken, extractAuthToken, getAjaxAccessControl, getAuthChecker, getCookieAuthToken, handleAjax, isSurtMode, prepareResponse, setAjaxAccessControl, setAuthChecker, setCookieAuthToken, setSurtMode
protected org.archive.format.gzip.zipnum.ZipNumCluster zipnumSource
protected org.archive.format.cdx.CDXInputSource cdxSource
protected String cdxFormat
protected org.archive.format.cdx.CDXLineFactory cdxLineFactory
protected int maxPageSize
protected int queryMaxLimit
protected String[] noCollapsePrefix
protected boolean collapseToLast
protected org.archive.format.gzip.zipnum.ZipNumParams defaultParams
public void afterPropertiesSet() throws Exception
afterPropertiesSet
in interface org.springframework.beans.factory.InitializingBean
afterPropertiesSet
in class BaseCDXServer
Exception
public org.archive.format.gzip.zipnum.ZipNumCluster getZipnumSource()
public void setZipnumSource(org.archive.format.gzip.zipnum.ZipNumCluster zipnumSource)
public int getPageSize()
public void setPageSize(int pageSize)
public org.archive.format.gzip.zipnum.ZipNumParams getDefaultParams()
public void setDefaultParams(org.archive.format.gzip.zipnum.ZipNumParams defaultParams)
public String getCdxFormat()
public void setCdxFormat(String cdxFormat)
public int getQueryMaxLimit()
public void setQueryMaxLimit(int queryMaxLimit)
public String[] getNoCollapsePrefix()
public void setNoCollapsePrefix(String[] noCollapsePrefix)
public boolean isCollapseToLast()
public void setCollapseToLast(boolean collapseToLast)
true
, timestamp-collapsing writes out the last best
capture in the collapse group, instead of the first.
Initial value is false.
collapseToLast
- the collapseToLast to setDupeTimestampLastBestStatusFilter
public org.archive.format.cdx.CDXInputSource getCdxSource()
public void setCdxSource(org.archive.format.cdx.CDXInputSource cdxSource)
protected boolean determineGzip(javax.servlet.http.HttpServletRequest request, CDXQuery query)
@RequestMapping(value="/cdx") public void getCdx(javax.servlet.http.HttpServletRequest request, javax.servlet.http.HttpServletResponse response, CDXQuery query)
public void getCdx(CDXQuery query, AuthToken authToken, CDXWriter responseWriter) throws IOException
IOException
protected org.archive.util.iterator.CloseableIterator<String> createPagedCdxIterator(String[] startEndUrl, CDXQuery query, AuthToken authToken, CDXWriter responseWriter) throws IOException
IOException
protected org.archive.util.iterator.CloseableIterator<String> createBoundedCdxIterator(String[] startEndUrl, CDXQuery query, org.archive.format.gzip.zipnum.ZipNumIndex.PageResult pageResult, org.archive.util.iterator.CloseableIterator<String> idx) throws IOException
IOException
protected void writeIdxResponse(CDXWriter responseWriter, org.archive.util.iterator.CloseableIterator<String> iter)
protected void writeCdxResponse(CDXWriter responseWriter, org.archive.util.iterator.CloseableIterator<String> cdx, int readLimit, CDXQuery query, AuthToken authToken, CDXAccessFilter accessChecker)
public org.archive.format.cdx.CDXLine findLastCapture(String url, String digest, boolean ignoreRobots)
url
in the
CDX database.
If digest
is non-null
, return only a capture with
identical digest.url
- URL (in regular form) to look fordigest
- content digest in the same format as CDX database,
or null
if any version qualifies.ignoreRobots
- whether robots.txt-excluded captures qualifyCopyright © 2005–2015 IIPC. All rights reserved.