private void initTestPolls() throws Exception {
testV1polls = new V1Poll[testV1msg.length];
for (int i = 0; i < testV1polls.length; i++) {
log.debug3("initTestPolls: V1 " + i);
BasePoll p = pollmanager.makePoll(testV1msg[i]);
assertNotNull(p);
assertNotNull(p.getMessage());
log.debug("initTestPolls: V1 " + i + " returns " + p);
assertTrue(p instanceof V1Poll);
switch (i) {
case 0:
assertTrue(p instanceof V1NamePoll);
break;
case 1:
assertTrue(p instanceof V1ContentPoll);
break;
case 2:
assertTrue(p instanceof V1VerifyPoll);
break;
}
testV1polls[i] = (V1Poll) p;
assertNotNull(testV1polls[i]);
log.debug3("initTestPolls: " + i + " " + p.toString());
}
}
public void emitMetadata(ArticleFiles af, ArticleMetadata md) {
if (log.isDebug3()) log.debug3("emit(" + af + ", " + md + ")");
if (md != null) {
log.debug3("add " + md + " to amlist");
amlst.add(md);
}
;
}
public void testFunctionalFromTarHierarchy() throws Exception {
log.debug3("in testFromTarHierarchy");
// load the tarballs
InputStream file_input = null;
try {
file_input = getResourceAsStream(realTARFile_A);
// UrlCacher uc = au.makeUrlCacher(TAR_A_BASE);
// uc.storeContent(file_input, tarHeader);
UrlCacher uc = tarAu.makeUrlCacher(new UrlData(file_input, tarHeader, TAR_A_BASE));
uc.storeContent();
IOUtil.safeClose(file_input);
file_input = getResourceAsStream(realTARFile_B);
// uc = au.makeUrlCacher(TAR_B_BASE);
// uc.storeContent(file_input, tarHeader);
uc = tarAu.makeUrlCacher(new UrlData(file_input, tarHeader, TAR_B_BASE));
uc.storeContent();
IOUtil.safeClose(file_input);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
IOUtil.safeClose(file_input);
}
CachedUrlSet cus = tarAu.getAuCachedUrlSet();
for (CachedUrl cu : cus.getCuIterable()) {
log.debug3("AU - cu is: " + cu.getUrl());
cu.release();
}
// We need to start from the level of the ArticleMetadataExtractor
MyListEmitter emitter = new MyListEmitter();
ArticleMetadataExtractor amEx =
new ElsevierDeferredArticleMetadataExtractor(ArticleFiles.ROLE_ARTICLE_METADATA);
Iterator<ArticleFiles> it = tarAu.getArticleIterator(MetadataTarget.Any());
while (it.hasNext()) {
ArticleFiles af = it.next();
log.debug3("Metadata test - articlefiles " + af.toString());
// CachedUrl cu = af.getFullTextCu();
CachedUrl cu = af.getRoleCu(ArticleFiles.ROLE_ARTICLE_METADATA);
log.debug3("metadata cu is " + cu.getUrl());
// List<ArticleMetadata> mdlist = mle.extract(MetadataTarget.Any(), cu);
amEx.extract(MetadataTarget.Any(), af, emitter);
List<ArticleMetadata> returnList = emitter.getAmList();
assertNotNull(returnList);
log.debug3("size of returnList is " + returnList.size());
Iterator<ArticleMetadata> mdIt = returnList.iterator();
ArticleMetadata mdRecord = null;
while (mdIt.hasNext()) {
mdRecord = (ArticleMetadata) mdIt.next();
validateCompleteMetadataRecord(mdRecord);
}
}
}
/** test for method scheduleVote(..) */
public void testScheduleVote() {
V1Poll p = testV1polls[1];
assertTrue(p instanceof V1ContentPoll);
log.debug3("testScheduleVote 1");
p.scheduleVote();
log.debug3("testScheduleVote 2");
assertNotNull(p.m_voteTime);
assertTrue(p.m_voteTime.getRemainingTime() < p.m_deadline.getRemainingTime());
log.debug3("at end of testScheduleVote");
}
/*
* When testing no-pdf-check basic XML parsing, you will get partial MD records
* depending on whether the info comes from dataset.xml or from main.xml
*/
private void validateDatasetMetadataRecord(ArticleMetadata am) {
log.debug3("valideDatasetMetadatRecord");
String doi_val = am.get(MetadataField.FIELD_DOI);
assertEquals(common_issn, am.get(MetadataField.FIELD_ISSN));
log.debug3("doi val is: " + doi_val);
// The dataset doesn't set this value, it'll fail over the main.xml value
if (doi_val.equals("10.1016/S0140-1111(14)61865-1")) {
assertEquals(null, am.get(MetadataField.FIELD_DATE));
} else {
assertEquals(dateMap.get(doi_val), am.get(MetadataField.FIELD_DATE));
}
assertEquals(pubTitleMap.get(doi_val), am.get(MetadataField.FIELD_PUBLICATION_TITLE));
}
/**
* Method that creates a simulated Cached URL from the source code provided by the goodContent
* String. It then asserts that the metadata extracted, by using the
* MetaPressRisMetadataExtractorFactory, match the metadata in the source code.
*
* @throws Exception
*/
public void testExtractGoodRisContent() throws Exception {
String goodContent = createGoodRisContent();
log.debug3(goodContent);
List<ArticleMetadata> mdlist = setupContentForAU(bau1, RIS_URL, goodContent, false);
assertNotEmpty(mdlist);
ArticleMetadata md = mdlist.get(0);
assertNotNull(md);
assertEquals(goodVolume, md.get(MetadataField.FIELD_VOLUME));
assertEquals(goodIssue, md.get(MetadataField.FIELD_ISSUE));
assertEquals(goodStartPage, md.get(MetadataField.FIELD_START_PAGE));
assertEquals(goodEndPage, md.get(MetadataField.FIELD_END_PAGE));
assertEquals(goodIssn, md.get(MetadataField.FIELD_ISSN));
Iterator<String> actAuthIter = md.getList(MetadataField.FIELD_AUTHOR).iterator();
for (String expAuth : goodAuthors) {
assertEquals(expAuth, actAuthIter.next());
}
assertEquals(goodTitle, md.get(MetadataField.FIELD_ARTICLE_TITLE));
assertEquals(goodJournal, md.get(MetadataField.FIELD_PUBLICATION_TITLE));
assertEquals(goodDate, md.get(MetadataField.FIELD_DATE));
assertEquals(goodPublisher, md.get(MetadataField.FIELD_PUBLISHER));
assertEquals(goodDOI, md.get(MetadataField.FIELD_DOI));
// This shouldn't get set. It will default later to fuill_text_cu
assertNotEquals(doiURL, md.get(MetadataField.FIELD_ACCESS_URL));
}
/*
* You will have to tell it the DOI and the schema because those normally come from dataset
*/
private void validateSingleMainMetadataRecord(ArticleMetadata am, String doi_val, String schema) {
log.debug3("valideSingleMainMetadatRecord");
if ("simple-article".equals(schema)) {
assertEquals(common_simple_article_title, am.get(MetadataField.FIELD_ARTICLE_TITLE));
} else {
assertEquals(common_article_title, am.get(MetadataField.FIELD_ARTICLE_TITLE));
}
log.debug3("doi val is: " + doi_val);
assertEquals(authorMap.get(doi_val), am.getList(MetadataField.FIELD_AUTHOR));
assertEquals(volMap.get(doi_val), am.get(MetadataField.FIELD_VOLUME));
assertEquals(issueMap.get(doi_val), am.get(MetadataField.FIELD_ISSUE));
assertEquals("Comment", am.getRaw(ElsevierMainDTD5XmlSchemaHelper.common_dochead));
assertEquals(doi_val, am.getRaw(ElsevierMainDTD5XmlSchemaHelper.common_doi));
assertEquals("2014", am.getRaw(ElsevierMainDTD5XmlSchemaHelper.common_copyright));
}
public void testSimpleMainXML() throws Exception {
log.debug3("testSimpleMainXML");
String xml_url = TAR_A_BASE + SUBDIR + "01420615/v64sC/S0142061514004608/main.xml";
List<ArticleMetadata> mdList =
extractFromContent(xml_url, "text/xml", simpleMain, nocheck_mle, null);
assertEquals(1, mdList.size());
validateSingleMainMetadataRecord(mdList.get(0), "10.1016/j.jidx.2014.07.028", "article");
}
/** test for method checkVote(..) */
public void testCheckVote() throws Exception {
V1LcapMessage msg = null;
log.debug3("starting testCheeckVote");
msg =
V1LcapMessage.makeReplyMsg(
testV1polls[0].getMessage(),
ByteArray.makeRandomBytes(20),
ByteArray.makeRandomBytes(20),
null,
V1LcapMessage.NAME_POLL_REP,
testduration,
testID);
log.debug3("testCheeckVote 2");
V1Poll p = null;
p = createCompletedPoll(theDaemon, testau, msg, 8, 2, pollmanager);
assertTrue(p instanceof V1NamePoll);
log.debug3("testCheeckVote 3");
assertNotNull(p);
PeerIdentity id = msg.getOriginatorId();
assertNotNull(id);
assertNotNull(p.m_tally);
int rep = p.m_tally.wtAgree + idmgr.getReputation(id);
// good vote check
p.checkVote(msg.getHashed(), new Vote(msg, false));
assertEquals(9, p.m_tally.numAgree);
assertEquals(2, p.m_tally.numDisagree);
assertEquals(rep, p.m_tally.wtAgree);
rep = p.m_tally.wtDisagree + idmgr.getReputation(id);
// bad vote check
p.checkVote(ByteArray.makeRandomBytes(20), new Vote(msg, false));
assertEquals(9, p.m_tally.numAgree);
assertEquals(3, p.m_tally.numDisagree);
assertEquals(rep, p.m_tally.wtDisagree);
}
/*
* When testing a complete extraction out of the tarset, the MD record will be completely filled in
* and pdf-existence will get established
*/
private void validateCompleteMetadataRecord(ArticleMetadata am) {
log.debug3("valideCompleteMetadatRecord");
String doi_val = am.get(MetadataField.FIELD_DOI);
/* make sure we can pick up both types of xml article data */
log.debug3("doi val is: " + doi_val);
if ("JA 5.2.0 SIMPLE-ARTICLE"
.equals(am.getRaw(ElsevierDatasetXmlSchemaHelper.dataset_dtd_metadata))) {
log.debug3("simple-article");
assertEquals(common_simple_article_title, am.get(MetadataField.FIELD_ARTICLE_TITLE));
} else {
assertEquals(common_article_title, am.get(MetadataField.FIELD_ARTICLE_TITLE));
}
assertEquals(common_issn, am.get(MetadataField.FIELD_ISSN));
assertEquals(authorMap.get(doi_val), am.getList(MetadataField.FIELD_AUTHOR));
assertEquals(dateMap.get(doi_val), am.get(MetadataField.FIELD_DATE));
assertEquals(accessUrlMap.get(doi_val), am.get(MetadataField.FIELD_ACCESS_URL));
assertEquals(volMap.get(doi_val), am.get(MetadataField.FIELD_VOLUME));
assertEquals(issueMap.get(doi_val), am.get(MetadataField.FIELD_ISSUE));
assertEquals(pubTitleMap.get(doi_val), am.get(MetadataField.FIELD_PUBLICATION_TITLE));
assertEquals("Elsevier", am.get(MetadataField.FIELD_PROVIDER));
assertEquals("Elsevier", am.get(MetadataField.FIELD_PUBLISHER));
log.debug3(am.ppString(2));
}
public void testSimpleDatasetXML() throws Exception {
log.debug3("testSimpleDatasetXML");
String file_input = StringUtil.fromInputStream(getResourceAsStream(testDatasetFile));
String xml_url = TAR_A_BASE + SUBDIR + "dataset.xml";
List<ArticleMetadata> mdList =
extractFromContent(xml_url, "text/xml", file_input, nocheck_mle, null);
assertEquals(6, mdList.size());
Iterator<ArticleMetadata> mdIt = mdList.iterator();
ArticleMetadata mdRecord = null;
while (mdIt.hasNext()) {
mdRecord = (ArticleMetadata) mdIt.next();
validateDatasetMetadataRecord(mdRecord);
}
}
/**
* Method that creates a simulated Cached URL from the source code provided by the goodContent
* String. It then asserts that the metadata extracted, by using the
* MetaPressRisMetadataExtractorFactory, match the metadata in the source code.
*
* @throws Exception
*/
public void testExtractAlternateRisContent() throws Exception {
String goodContent = createAlternateRisContent();
log.debug3(goodContent);
List<ArticleMetadata> mdlist = setupContentForAU(bau1, RIS_URL, goodContent, false);
assertNotEmpty(mdlist);
ArticleMetadata md = mdlist.get(0);
assertNotNull(md);
Iterator<String> actAuthIter = md.getList(MetadataField.FIELD_AUTHOR).iterator();
for (String expAuth : goodAuthors) {
assertEquals(expAuth, actAuthIter.next());
}
assertEquals(goodTitle, md.get(MetadataField.FIELD_ARTICLE_TITLE));
assertEquals(goodJournal, md.get(MetadataField.FIELD_PUBLICATION_TITLE));
assertEquals(goodDate, md.get(MetadataField.FIELD_DATE));
assertEquals(goodPublisher, md.get(MetadataField.FIELD_PUBLISHER));
}
public static V1Poll createCompletedPoll(
LockssDaemon daemon,
ArchivalUnit au,
V1LcapMessage testmsg,
int numAgree,
int numDisagree,
PollManager pollmanager)
throws Exception {
log.debug(
"createCompletedPoll: au: "
+ au.toString()
+ " peer "
+ testmsg.getOriginatorId()
+ " votes "
+ numAgree
+ "/"
+ numDisagree);
CachedUrlSetSpec cusSpec = null;
if ((testmsg.getLwrBound() != null)
&& (testmsg.getLwrBound().equals(PollSpec.SINGLE_NODE_LWRBOUND))) {
cusSpec = new SingleNodeCachedUrlSetSpec(testmsg.getTargetUrl());
} else {
cusSpec =
new RangeCachedUrlSetSpec(
testmsg.getTargetUrl(), testmsg.getLwrBound(), testmsg.getUprBound());
}
CachedUrlSet cus = au.makeCachedUrlSet(cusSpec);
PollSpec spec = new PollSpec(cus, Poll.V1_CONTENT_POLL);
((MockCachedUrlSet) spec.getCachedUrlSet()).setHasContent(false);
V1Poll p = null;
if (testmsg.isContentPoll()) {
p =
new V1ContentPoll(
spec,
pollmanager,
testmsg.getOriginatorId(),
testmsg.getChallenge(),
testmsg.getDuration(),
testmsg.getHashAlgorithm());
} else if (testmsg.isNamePoll()) {
p =
new V1NamePoll(
spec,
pollmanager,
testmsg.getOriginatorId(),
testmsg.getChallenge(),
testmsg.getDuration(),
testmsg.getHashAlgorithm());
} else if (testmsg.isVerifyPoll()) {
p =
new V1VerifyPoll(
spec,
pollmanager,
testmsg.getOriginatorId(),
testmsg.getChallenge(),
testmsg.getDuration(),
testmsg.getHashAlgorithm(),
testmsg.getVerifier());
}
assertNotNull(p);
p.setMessage(testmsg);
p.m_tally.quorum = numAgree + numDisagree;
p.m_tally.numAgree = numAgree;
p.m_tally.numDisagree = numDisagree;
p.m_tally.wtAgree = 2000;
p.m_tally.wtDisagree = 200;
p.m_tally.localEntries = makeEntries(1, 3);
p.m_tally.votedEntries = makeEntries(1, 5);
p.m_tally.votedEntries.remove(1);
p.m_pollstate = V1Poll.PS_COMPLETE;
p.m_callerID = testmsg.getOriginatorId();
log.debug3("poll " + p.toString());
p.m_tally.tallyVotes();
return p;
}
/*
* The supporting methods
*/
private void setUpExpectedTarContent() {
/* maps the DOIs in the metadata to the expected values */
log.debug3("setUpExpectedTarContent");
pubTitleMap = new HashMap<String, String>();
{
pubTitleMap.put("10.1016/j.jidx.2014.07.028", "International Journal of XXX");
pubTitleMap.put("10.1016/j.jidx2.2014.05.013", "Revista");
pubTitleMap.put("10.1016/S1473-1111(14)70840-0", "The Journal");
pubTitleMap.put("10.1016/S0140-1111(14)61865-1", "The Other Journal");
pubTitleMap.put("10.1016/j.foo.2014.08.001", "Foo");
pubTitleMap.put("10.1016/j.foo.2014.08.123", "Foo");
}
;
dateMap = new HashMap<String, String>();
{
dateMap.put("10.1016/j.jidx.2014.07.028", "2014-07-30");
dateMap.put("10.1016/j.jidx2.2014.05.013", "2014-07-09");
dateMap.put("10.1016/S1473-1111(14)70840-0", "2014-09-01");
dateMap.put("10.1016/S0140-1111(14)61865-1", "2014"); // will get from main.xml as backup
dateMap.put("10.1016/j.foo.2014.08.001", "2014-08-20");
dateMap.put("10.1016/j.foo.2014.08.123", "2014-08-20");
}
;
accessUrlMap = new HashMap<String, String>();
{
accessUrlMap.put(
"10.1016/j.jidx.2014.07.028",
TAR_A_BASE + SUBDIR + "01420615/v64sC/S0142061514004608/main.pdf");
accessUrlMap.put(
"10.1016/j.jidx2.2014.05.013",
TAR_A_BASE + SUBDIR + "00349356/v61i9/S0034935614001819/main.pdf");
accessUrlMap.put(
"10.1016/S1473-1111(14)70840-0",
TAR_A_BASE + SUBDIR + "14733099/v14i10/S1473309914708400/main.pdf");
accessUrlMap.put(
"10.1016/S0140-1111(14)61865-1",
TAR_B_BASE + SUBDIR + "01406736/v384sS1/S0140673614618651/main.pdf");
accessUrlMap.put(
"10.1016/j.foo.2014.08.001",
TAR_B_BASE + SUBDIR + "00191035/v242sC/S0019103514004151/main.pdf");
accessUrlMap.put(
"10.1016/j.foo.2014.08.123",
TAR_B_BASE + SUBDIR + "00191035/v242sC/S0019103514003856/main.pdf");
}
;
ArrayList<String> goodAuthors = new ArrayList<String>();
{
goodAuthors.add("Writer, Bob");
goodAuthors.add("Q. Text, Samantha");
}
ArrayList<String> simpleAuthors = new ArrayList<String>();
{
simpleAuthors.add("Simple, Josh");
}
ArrayList<String> extendedAuthors = new ArrayList<String>();
{
extendedAuthors.add("Writer, Bob");
extendedAuthors.add("Q. Text, Samantha");
extendedAuthors.add("The COLLABORATIVE Investigators");
}
authorMap = new HashMap<String, List<String>>();
{
authorMap.put("10.1016/j.jidx.2014.07.028", goodAuthors);
authorMap.put("10.1016/j.jidx2.2014.05.013", goodAuthors);
authorMap.put("10.1016/S1473-1111(14)70840-0", extendedAuthors);
authorMap.put("10.1016/S0140-1111(14)61865-1", simpleAuthors);
authorMap.put("10.1016/j.foo.2014.08.001", goodAuthors);
authorMap.put("10.1016/j.foo.2014.08.123", goodAuthors);
}
;
volMap = new HashMap<String, String>();
{
volMap.put("10.1016/j.jidx.2014.07.028", "64");
volMap.put("10.1016/j.jidx2.2014.05.013", "61");
volMap.put("10.1016/S1473-1111(14)70840-0", "14");
volMap.put("10.1016/S0140-1111(14)61865-1", "384");
volMap.put("10.1016/j.foo.2014.08.001", "242");
volMap.put("10.1016/j.foo.2014.08.123", "242");
}
;
issueMap = new HashMap<String, String>();
{
issueMap.put("10.1016/j.jidx.2014.07.028", "C");
issueMap.put("10.1016/j.jidx2.2014.05.013", "9");
issueMap.put("10.1016/S1473-1111(14)70840-0", "10");
issueMap.put("10.1016/S0140-1111(14)61865-1", "S1");
issueMap.put("10.1016/j.foo.2014.08.001", "C");
issueMap.put("10.1016/j.foo.2014.08.123", "C");
}
;
}
