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");
}
public void testArticleCountAndType() throws Exception {
int expCount = 28;
PluginTestUtil.crawlSimAu(sau);
String pat1 = "branch(\\d+)/(\\d+file\\.html)";
String rep1 = "aps/journal/v123/n$1/full/$2";
PluginTestUtil.copyAu(sau, nau, ".*[^.][^p][^d][^f]$", pat1, rep1);
String pat2 = "branch(\\d+)/(\\d+file\\.pdf)";
String rep2 = "aps/journal/v123/n$1/pdf/$2";
PluginTestUtil.copyAu(sau, nau, ".*\\.pdf$", pat2, rep2);
// Remove some URLs
int deleted = 0;
for (Iterator it = nau.getAuCachedUrlSet().contentHashIterator(); it.hasNext(); ) {
CachedUrlSetNode cusn = (CachedUrlSetNode) it.next();
if (cusn instanceof CachedUrl) {
CachedUrl cu = (CachedUrl) cusn;
String url = cu.getUrl();
if (url.contains("/journal/")
&& (url.endsWith("1file.html") || url.endsWith("2file.pdf"))) {
deleteBlock(cu);
++deleted;
}
}
}
assertEquals(8, deleted);
Iterator<ArticleFiles> it = nau.getArticleIterator();
int count = 0;
int countHtmlOnly = 0;
int countPdfOnly = 0;
while (it.hasNext()) {
ArticleFiles af = it.next();
log.info(af.toString());
CachedUrl cu = af.getFullTextCu();
String url = cu.getUrl();
assertNotNull(cu);
String contentType = cu.getContentType();
log.debug("count " + count + " url " + url + " " + contentType);
count++;
if (af.getRoleUrl(ArticleFiles.ROLE_FULL_TEXT_PDF) == null) {
++countHtmlOnly;
}
if (af.getRoleUrl(ArticleFiles.ROLE_FULL_TEXT_PDF) == url) {
++countPdfOnly;
}
}
log.debug("Article count is " + count);
assertEquals(expCount, count);
assertEquals(4, countHtmlOnly);
assertEquals(4, countPdfOnly);
}
/*
* 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));
}
protected void checkRoot(SimulatedArchivalUnit sau) {
log.debug("checkRoot()");
CachedUrlSet set = sau.getAuCachedUrlSet();
Iterator setIt = set.flatSetIterator();
ArrayList childL = new ArrayList(1);
CachedUrlSet cus = null;
while (setIt.hasNext()) {
cus = (CachedUrlSet) setIt.next();
childL.add(cus.getUrl());
}
String urlRoot = sau.getUrlRoot();
String[] expectedA = new String[1];
expectedA[0] = urlRoot;
assertIsomorphic(expectedA, childL);
setIt = cus.flatSetIterator();
childL = new ArrayList(7);
while (setIt.hasNext()) {
childL.add(((CachedUrlSetNode) setIt.next()).getUrl());
}
expectedA =
new String[] {
urlRoot + "/001file.html",
urlRoot + "/001file.txt",
urlRoot + "/002file.html",
urlRoot + "/002file.txt",
urlRoot + "/branch1",
urlRoot + "/branch2",
urlRoot + "/index.html"
};
assertIsomorphic(expectedA, childL);
}
public void testRunStepsWithOverrunDisallowed() {
StepTask t1 = task(100, 300, 100, null, new MyMockStepper(15, -10));
// t1.setOverrunAllowed(true);
StepTask t2 = task(150, 250, 100, null, new MyMockStepper(10, -10));
Schedule s = sched(ListUtil.list(t1, t2));
fact.setResults(s, s);
assertTrue(tr.addToSchedule(t1));
assertTrue(tr.addToSchedule(t2));
TimeBase.setSimulated(101);
Interrupter intr = null;
try {
intr = interruptMeIn(TIMEOUT_SHOULDNT, true);
while (tr.findTaskToRun()) {
tr.runSteps(new MutableBoolean(true), null);
}
intr.cancel();
} catch (Exception e) {
log.error("runSteps threw:", e);
} finally {
if (intr.did()) {
fail("runSteps looped");
}
}
assertEquals(SetUtil.set(t1, t2), SetUtil.theSet(removedTasks));
assertTrue(t1.e.toString(), t1.e instanceof SchedService.Overrun);
}
public void testRunStepsWithOverrunAllowed() {
StepTask t1 = task(100, 500, 30, null, new MyMockStepper(15, -10));
t1.setOverrunAllowed(true);
StepTask t2 = task(150, 250, 100, null, new MyMockStepper(10, -10));
newTr(
new MyMockTaskRunner(
new TaskRunner.SchedulerFactory() {
public Scheduler createScheduler() {
return new SortScheduler();
}
}));
assertTrue(tr.addToSchedule(t1));
assertTrue(tr.addToSchedule(t2));
TimeBase.setSimulated(101);
assertTrue(tr.findTaskToRun());
Interrupter intr = null;
try {
intr = interruptMeIn(TIMEOUT_SHOULDNT, true);
while (tr.findTaskToRun()) {
tr.runSteps(new MutableBoolean(true), null);
}
intr.cancel();
} catch (Exception e) {
log.error("runSteps threw:", e);
} finally {
if (intr.did()) {
fail("runSteps looped");
}
}
assertNull(t1.e);
assertTrue(t1.hasOverrun());
}
protected void checkContent(SimulatedArchivalUnit sau) throws IOException {
log.debug("checkContent()");
checkRoot(sau);
checkLeaf(sau);
checkStoredContent(sau);
checkDepth(sau);
}
public void testStepperThrows() {
final List finished = new ArrayList();
TaskCallback cb =
new TaskCallback() {
public void taskEvent(SchedulableTask task, Schedule.EventType event) {
if (event == Schedule.EventType.FINISH) {
finished.add(task);
}
}
};
MyMockStepper stepper = new MyMockStepper(10, -10);
stepper.setWhenToThrow(5);
StepTask t1 = task(100, 200, 100, cb, stepper);
Schedule s = sched(ListUtil.list(t1));
fact.setResult(s);
assertTrue(tr.addToSchedule(t1));
TimeBase.setSimulated(101);
assertTrue(tr.findTaskToRun());
Interrupter intr = null;
try {
intr = interruptMeIn(TIMEOUT_SHOULDNT, true);
tr.runSteps(new MutableBoolean(true), null);
intr.cancel();
} catch (Exception e) {
log.error("runSteps threw:", e);
} finally {
if (intr.did()) {
fail("runSteps looped");
}
}
assertSame(t1, finished.get(0));
assertTrue(t1.e instanceof ExpectedRuntimeException);
assertEquals(5, stepper.nSteps);
}
/**
* 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));
}
protected void checkLeaf(SimulatedArchivalUnit sau) {
log.debug("checkLeaf()");
String parent = sau.getUrlRoot() + "/branch1";
CachedUrlSetSpec spec = new RangeCachedUrlSetSpec(parent);
CachedUrlSet set = sau.makeCachedUrlSet(spec);
Iterator setIt = set.contentHashIterator();
ArrayList childL = new ArrayList(16);
while (setIt.hasNext()) {
childL.add(((CachedUrlSetNode) setIt.next()).getUrl());
}
String[] expectedA =
new String[] {
parent,
parent + "/001file.html",
parent + "/001file.txt",
parent + "/002file.html",
parent + "/002file.txt",
parent + "/branch1",
parent + "/branch1/001file.html",
parent + "/branch1/001file.txt",
parent + "/branch1/002file.html",
parent + "/branch1/002file.txt",
parent + "/branch1/index.html",
parent + "/branch2",
parent + "/branch2/001file.html",
parent + "/branch2/001file.txt",
parent + "/branch2/002file.html",
parent + "/branch2/002file.txt",
parent + "/branch2/index.html",
parent + "/index.html",
};
assertIsomorphic(expectedA, childL);
}
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");
}
private void deleteBlock(CachedUrl cu) throws IOException {
log.info("deleting " + cu.getUrl());
CachedUrlSetSpec cuss = new SingleNodeCachedUrlSetSpec(cu.getUrl());
ArchivalUnit au = cu.getArchivalUnit();
CachedUrlSet cus = au.makeCachedUrlSet(cuss);
NodeManager nm = au.getPlugin().getDaemon().getNodeManager(au);
nm.deleteNode(cus);
}
/** Test class for <code>org.lockss.scheduler.StepperTask</code> */
public class TestStepperTask extends LockssTestCase {
public static Class testedClasses[] = {
org.lockss.scheduler.StepTask.class, org.lockss.scheduler.StepperTask.class,
};
static Logger log = Logger.getLogger("TestStepperTask");
public void setUp() throws Exception {
super.setUp();
TimeBase.setSimulated();
}
public void tearDown() throws Exception {
TimeBase.setReal();
super.tearDown();
}
static StepperTask taskBetween(long minStart, long deadline, int duration, Stepper stepper) {
return new StepperTask(
Deadline.at(minStart), Deadline.at(deadline), duration, null, null, stepper);
}
Stepper newSt(final boolean isFinished) {
return new Stepper() {
public int computeStep(int metric) {
return 0;
}
public boolean isFinished() {
return isFinished;
}
};
}
public void testStepper() {
Stepper st = newSt(false);
StepperTask t = taskBetween(100, 200, 50, st);
assertEquals(st, t.getStepper());
assertFalse(t.isBackgroundTask());
assertFalse(t.isFinished());
t.e = new Exception();
assertTrue(t.isFinished());
Stepper st2 = newSt(true);
StepperTask t2 = taskBetween(100, 200, 50, st2);
assertTrue(t2.isFinished());
}
public void testToString() {
Stepper st = newSt(false);
StepperTask t = taskBetween(100, 200, 50, st);
t.toString();
t.cookie = "foo";
t.toString();
}
}
protected void checkDepth(SimulatedArchivalUnit sau) {
log.debug("checkDepth()");
String URL_ROOT = sau.getUrlRoot();
assertEquals(0, sau.getLinkDepth(URL_ROOT + "/index.html"));
assertEquals(0, sau.getLinkDepth(URL_ROOT + "/"));
assertEquals(1, sau.getLinkDepth(URL_ROOT + "/001file.html"));
assertEquals(1, sau.getLinkDepth(URL_ROOT + "/branch1/index.html"));
assertEquals(1, sau.getLinkDepth(URL_ROOT + "/branch1/"));
assertEquals(2, sau.getLinkDepth(URL_ROOT + "/branch1/001file.html"));
}
public class TestElsevierXmlLinkExtractorFactory extends LinkExtractorTestCase {
private static Logger logger = Logger.getLogger("TestElsevierXmlLinkExtractorFactory");
String srcUrl = "http://www.example.com/";
private static final String withLinks =
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+ "<!DOCTYPE dataset SYSTEM \"http://support.sciencedirect.com/xml/sdosftp10.dtd\">\n"
+ "<dataset identifier=\"OXM10160\" customer=\"OHL\""
+ " status=\"Announcement\""
+ " version=\"Network Dataset Announcement/Confirmation v1.0\">"
+ " <date year=\"2007\" month=\"May\" day=\"1\"/>\n"
+ "<file name=\"01407007.tar\" size=\"21780480\""
+ " md5=\"6c7266e0e246bf3e8cf1cd8b659a7a73\"/>\n"
+ "<file name=\"03064530.tar\" size=\"12748800\""
+ " md5=\"df9519d3075e164d22f5dd4988a693c3\"/>\n"
+ "<file name=\"dataset.toc\" size=\"2216587\""
+ " md5=\"cd21741eb91fa0fdfef2fa36485e21a0\"/>\n"
+ "</dataset>\n";
private static final String withoutLinks =
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+ "<!DOCTYPE dataset SYSTEM \"http://support.sciencedirect.com/xml/sdosftp10.dtd\">\n"
+ "<dataset identifier=\"OXM10160\" customer=\"OHL\""
+ " status=\"Announcement\""
+ " version=\"Network Dataset Announcement/Confirmation v1.0\">"
+ " <date year=\"2007\" month=\"May\" day=\"1\"/>\n"
+ "</dataset>\n";
private static final String[] links = {
"01407007.tar", "03064530.tar", "dataset.toc",
};
public String getMimeType() {
return "text/xml";
}
public LinkExtractorFactory getFactory() {
return new ElsevierXmlLinkExtractorFactory();
}
public void testFindCorrectEntries() throws Exception {
Set expected = new HashSet();
for (String link : links) {
expected.add(srcUrl + link);
}
assertEquals(expected, extractUrls(withLinks));
}
public void testFindNoEntries() throws Exception {
assertEmpty(extractUrls(withoutLinks));
}
}
// test null value in rows doesn't throw
public void testTextNull() throws Exception {
MockStatusAccessor statusAccessor =
MockStatusAccessor.generateStatusAccessor(colArray1, rowArrayWithNulls);
statSvc.registerStatusAccessor("testtbl", statusAccessor);
WebResponse resp = getTable("testtbl", true);
log.debug(resp.getText());
List lines = getLines(resp);
assertEqualTables(tableWithNulls, lines);
}
public void setUp() throws Exception {
super.setUp();
log.setLevel(Logger.LEVEL_DEBUG);
if (dig == null) {
dig = MessageDigest.getInstance(hashAlgorithm);
}
mau = new MockArchivalUnit(new MockPlugin());
cus = new MockCachedUrlSet(mau, null);
cus.setHashItSource(Collections.EMPTY_LIST);
TimeBase.setSimulated();
}
protected void hashContent(SimulatedArchivalUnit sau) throws Exception {
log.debug("hashContent()");
measureHashSpeed(sau);
// If any changes are made to the contents or shape of the simulated
// content tree, these hash values will have to be changed
checkHashSet(sau, true, false, fromHex("6AB258B4E1FFD9F9B45316B4F54111FF5E5948D2"));
checkHashSet(sau, true, true, fromHex("6AB258B4E1FFD9F9B45316B4F54111FF5E5948D2"));
checkHashSet(sau, false, false, fromHex("409893F1A603F4C276632694DB1621B639BD5164"));
checkHashSet(sau, false, true, fromHex("85E6213C3771BEAC5A4602CAF7982C6C222800D5"));
}
// test special (non-string) key in row doesn't throw
public void testTextNonStringKey() throws Exception {
MockStatusAccessor statusAccessor = new MockStatusAccessor();
List cols = ListUtil.list("foo", StatusTable.ROW_SEPARATOR);
statusAccessor.setRows(MockStatusAccessor.makeRowsFrom(cols, rowArray1), null);
statusAccessor.setColumnDescriptors(
MockStatusAccessor.makeColumnDescriptorsFrom(colArray1), null);
statSvc.registerStatusAccessor("testtbl", statusAccessor);
WebResponse resp = getTable("testtbl", true);
log.debug(resp.getText());
}
protected void createContent(SimulatedArchivalUnit sau) {
log.debug("createContent()");
scgen = sau.getContentGenerator();
scgen.setFileTypes(
SimulatedContentGenerator.FILE_TYPE_HTML + SimulatedContentGenerator.FILE_TYPE_TXT);
scgen.setAbnormalFile("1,1", 1);
scgen.setOddBranchesHaveContent(true);
sau.deleteContentTree();
sau.generateContentTree();
assertTrue(scgen.isContentTree());
}
/** 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);
}
}
private void initTestMsg() throws Exception {
testV1msg = new V1LcapMessage[3];
int[] pollType = {
Poll.V1_NAME_POLL, Poll.V1_CONTENT_POLL, Poll.V1_VERIFY_POLL,
};
PollFactory ppf = pollmanager.getPollFactory(1);
assertNotNull("PollFactory should not be null", ppf);
// XXX V1 support mandatory
assertTrue(ppf instanceof V1PollFactory);
V1PollFactory pf = (V1PollFactory) ppf;
for (int i = 0; i < testV1msg.length; i++) {
PollSpec spec = new MockPollSpec(testau, rootV1urls[i], lwrbnd, uprbnd, pollType[i]);
log.debug("Created poll spec: " + spec);
((MockCachedUrlSet) spec.getCachedUrlSet()).setHasContent(false);
int opcode = V1LcapMessage.NAME_POLL_REQ + (i * 2);
long duration = -1;
// NB calcDuration is not applied to Verify polls.
switch (opcode) {
case V1LcapMessage.NAME_POLL_REQ:
case V1LcapMessage.CONTENT_POLL_REQ:
// this will attempt to schedule and can return -1
duration = Math.max(pf.calcDuration(spec, pollmanager), 1000);
break;
case V1LcapMessage.VERIFY_POLL_REQ:
case V1LcapMessage.VERIFY_POLL_REP:
duration = 100000; // Arbitrary
break;
default:
fail("Bad opcode " + opcode);
break;
}
testV1msg[i] =
V1LcapMessage.makeRequestMsg(
spec,
agree_entries,
pf.makeVerifier(100000),
pf.makeVerifier(100000),
opcode,
duration,
testID);
assertNotNull(testV1msg[i]);
}
}
/**
* 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));
}
// one task to drop, succeeds after dropping it
public void testAddToScheduleOkAfterDrops() {
log.debug("testAddToScheduleOkAfterDrops()");
ConfigurationUtil.addFromArgs(
TaskRunner.PARAM_DROP_TASK_MAX, "10", TaskRunner.PARAM_MIN_CLEANUP_INTERVAL, "0");
StepTask t1 = task(100, 200, 50);
StepTask t2 = task(100, 200, 100);
Schedule sched1 = sched(ListUtil.list(t1));
Schedule sched2 = sched(ListUtil.list(t2));
fact.setResults(ListUtil.list(sched1, null, null, sched2, sched2));
TimeBase.step(101);
assertTrue(tr.addToSchedule(t1));
assertIsomorphic(ListUtil.list(t1), fact.scheduler.tasks);
assertEquals(SetUtil.set(t1), SetUtil.theSet(tr.getAcceptedTasks()));
assertForegroundStat(1, TaskRunner.STAT_ACCEPTED);
assertForegroundStat(0, TaskRunner.STAT_REFUSED);
assertForegroundStat(1, TaskRunner.STAT_WAITING);
assertForegroundStat(0, TaskRunner.STAT_DROPPED);
assertTrue(tr.addToSchedule(t2));
assertEquals(
ListUtil.list(
ListUtil.list(t1),
ListUtil.list(t1, t2),
ListUtil.list(t1),
Collections.EMPTY_SET,
ListUtil.list(t1, t2)),
fact.createArgs);
assertEquals(SetUtil.set(t1, t2), SetUtil.theSet(fact.scheduler.tasks));
assertTrue(t1.isDropped());
assertEquals(sched2, tr.getCurrentSchedule());
assertEquals(SetUtil.set(t1, t2), SetUtil.theSet(tr.getAcceptedTasks()));
assertEquals(SetUtil.set(t1), SetUtil.theSet(tr.getOverrunTasks()));
assertForegroundStat(2, TaskRunner.STAT_ACCEPTED);
assertForegroundStat(0, TaskRunner.STAT_REFUSED);
assertForegroundStat(1, TaskRunner.STAT_WAITING);
assertForegroundStat(1, TaskRunner.STAT_DROPPED);
t2.cancel();
assertForegroundStat(2, TaskRunner.STAT_ACCEPTED);
assertForegroundStat(0, TaskRunner.STAT_REFUSED);
assertForegroundStat(0, TaskRunner.STAT_WAITING);
assertForegroundStat(1, TaskRunner.STAT_DROPPED);
assertForegroundStat(1, TaskRunner.STAT_CANCELLED);
}