public void testGetUrls() {
HashSet stringCollection = new HashSet();
stringCollection.add("test");
AuState auState =
makeAuState(mau, -1, -1, -1, -1, 123, stringCollection, 1, -1.0, 1.0, historyRepo);
Collection col = auState.getCrawlUrls();
Iterator colIter = col.iterator();
assertTrue(colIter.hasNext());
assertEquals("test", colIter.next());
assertFalse(colIter.hasNext());
}
private void outputSummary(String baseUrl, Set fetched, Set toCrawl, long elapsedTime) {
int fetchCount = fetched.size();
outputMessage(
"\n\nSummary for starting Url: " + baseUrl + " and depth: " + m_crawlDepth,
TEST_SUMMARY_MESSAGE);
outputMessage(
"\nUrls fetched: " + fetchCount + " Urls extracted: " + m_extracted.size(),
PLAIN_MESSAGE);
outputMessage("\nDepth Fetched Parsed New URLs", PLAIN_MESSAGE);
for (int depth = 1; depth <= m_crawlDepth; depth++) {
PrintfFormat pf = new PrintfFormat("%5d %7d %6d %8d");
Integer[] args =
new Integer[] {
new Integer(depth),
new Integer(depth_fetched[depth - 1]),
new Integer(depth_parsed[depth - 1]),
new Integer(depth_incl[depth - 1]),
};
String s = pf.sprintf(args);
outputMessage(s, PLAIN_MESSAGE);
}
outputMessage("\nRemaining unfetched: " + toCrawl.size(), PLAIN_MESSAGE);
if (false) {
for (Iterator iter = toCrawl.iterator(); iter.hasNext(); ) {
String url = (String) iter.next();
outputMessage(url, PLAIN_MESSAGE);
}
}
long secs = elapsedTime / Constants.SECOND;
long fetchRate = 0;
if (secs > 0) {
fetchRate = fetchCount * 60 * Constants.SECOND / elapsedTime;
}
outputMessage(
"\nElapsed Time: " + secs + " secs." + " Fetch Rate: " + fetchRate + " p/m",
PLAIN_MESSAGE);
}
private Set outputUrlResults(String url, Set m_inclset, Set m_exclset) {
Set new_incls = new TreeSet(CollectionUtils.subtract(m_inclset, m_reported));
Set new_excls = new TreeSet(CollectionUtils.subtract(m_exclset, m_reported));
if (!m_inclset.isEmpty()) {
outputMessage(
"\nIncluded Urls: ("
+ new_incls.size()
+ " new, "
+ (m_inclset.size() - new_incls.size())
+ " old)",
URL_SUMMARY_MESSAGE);
depth_incl[m_curDepth - 1] += new_incls.size();
}
for (Iterator it = new_incls.iterator(); it.hasNext(); ) {
outputMessage(it.next().toString(), PLAIN_MESSAGE);
}
if (!m_exclset.isEmpty()) {
outputMessage(
"\nExcluded Urls: ("
+ new_excls.size()
+ " new, "
+ (m_exclset.size() - new_excls.size())
+ " old)",
URL_SUMMARY_MESSAGE);
}
for (Iterator it = new_excls.iterator(); it.hasNext(); ) {
outputMessage(it.next().toString(), PLAIN_MESSAGE);
}
m_reported.addAll(new_incls);
m_reported.addAll(new_excls);
if (m_outWriter != null) {
try {
m_outWriter.flush();
} catch (IOException ex) {
}
}
return new_incls;
}
protected void initMimeMap() throws PluginException.InvalidDefinition {
for (Iterator iter = definitionMap.entrySet().iterator(); iter.hasNext(); ) {
Map.Entry ent = (Map.Entry) iter.next();
String key = (String) ent.getKey();
Object val = ent.getValue();
if (key.endsWith(DefinableArchivalUnit.SUFFIX_LINK_EXTRACTOR_FACTORY)) {
String mime = stripSuffix(key, DefinableArchivalUnit.SUFFIX_LINK_EXTRACTOR_FACTORY);
if (val instanceof String) {
String factName = (String) val;
log.debug(mime + " link extractor: " + factName);
MimeTypeInfo.Mutable mti = mimeMap.modifyMimeTypeInfo(mime);
LinkExtractorFactory fact =
(LinkExtractorFactory) newAuxClass(factName, LinkExtractorFactory.class);
mti.setLinkExtractorFactory(fact);
}
} else if (key.endsWith(DefinableArchivalUnit.SUFFIX_CRAWL_FILTER_FACTORY)) {
// XXX This clause must precede the one for SUFFIX_HASH_FILTER_FACTORY
// XXX unless/until that key is changed to not be a terminal substring
// XXX of this one
String mime = stripSuffix(key, DefinableArchivalUnit.SUFFIX_CRAWL_FILTER_FACTORY);
if (val instanceof String) {
String factName = (String) val;
log.debug(mime + " crawl filter: " + factName);
MimeTypeInfo.Mutable mti = mimeMap.modifyMimeTypeInfo(mime);
FilterFactory fact = (FilterFactory) newAuxClass(factName, FilterFactory.class);
mti.setCrawlFilterFactory(fact);
}
} else if (key.endsWith(DefinableArchivalUnit.SUFFIX_HASH_FILTER_FACTORY)) {
String mime = stripSuffix(key, DefinableArchivalUnit.SUFFIX_HASH_FILTER_FACTORY);
if (val instanceof String) {
String factName = (String) val;
log.debug(mime + " filter: " + factName);
MimeTypeInfo.Mutable mti = mimeMap.modifyMimeTypeInfo(mime);
FilterFactory fact = (FilterFactory) newAuxClass(factName, FilterFactory.class);
mti.setHashFilterFactory(fact);
}
} else if (key.endsWith(DefinableArchivalUnit.SUFFIX_FETCH_RATE_LIMIT)) {
String mime = stripSuffix(key, DefinableArchivalUnit.SUFFIX_FETCH_RATE_LIMIT);
if (val instanceof String) {
String rate = (String) val;
log.debug(mime + " fetch rate: " + rate);
MimeTypeInfo.Mutable mti = mimeMap.modifyMimeTypeInfo(mime);
RateLimiter limit = mti.getFetchRateLimiter();
if (limit != null) {
limit.setRate(rate);
} else {
mti.setFetchRateLimiter(new RateLimiter(rate));
}
}
} else if (key.endsWith(DefinableArchivalUnit.SUFFIX_LINK_REWRITER_FACTORY)) {
String mime = stripSuffix(key, DefinableArchivalUnit.SUFFIX_LINK_REWRITER_FACTORY);
String factName = (String) val;
log.debug(mime + " link rewriter: " + factName);
MimeTypeInfo.Mutable mti = mimeMap.modifyMimeTypeInfo(mime);
LinkRewriterFactory fact =
(LinkRewriterFactory) newAuxClass(factName, LinkRewriterFactory.class);
mti.setLinkRewriterFactory(fact);
} else if (key.endsWith(DefinableArchivalUnit.SUFFIX_METADATA_EXTRACTOR_FACTORY_MAP)) {
String mime = stripSuffix(key, DefinableArchivalUnit.SUFFIX_METADATA_EXTRACTOR_FACTORY_MAP);
Map factNameMap = (Map) val;
Map factClassMap = new HashMap();
MimeTypeInfo.Mutable mti = mimeMap.modifyMimeTypeInfo(mime);
for (Iterator it = factNameMap.keySet().iterator(); it.hasNext(); ) {
String mdTypes = (String) it.next();
String factName = (String) factNameMap.get(mdTypes);
log.debug(mime + " (" + mdTypes + ") metadata extractor: " + factName);
for (String mdType : (List<String>) StringUtil.breakAt(mdTypes, ";")) {
setMdTypeFact(factClassMap, mdType, factName);
}
}
mti.setFileMetadataExtractorFactoryMap(factClassMap);
}
}
}
