use of org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException in project fess by codelibs.
the class CsvDataStoreImpl method processCsv.
protected void processCsv(final DataConfig dataConfig, final IndexUpdateCallback callback, final Map<String, String> paramMap, final Map<String, String> scriptMap, final Map<String, Object> defaultDataMap, final CsvConfig csvConfig, final File csvFile, final long readInterval, final String csvFileEncoding, final boolean hasHeaderLine) {
logger.info("Loading " + csvFile.getAbsolutePath());
CsvReader csvReader = null;
try {
csvReader = new CsvReader(new BufferedReader(new InputStreamReader(new FileInputStream(csvFile), csvFileEncoding)), csvConfig);
List<String> headerList = null;
if (hasHeaderLine) {
headerList = csvReader.readValues();
}
List<String> list;
boolean loop = true;
while ((list = csvReader.readValues()) != null && loop && alive) {
final Map<String, Object> dataMap = new HashMap<>();
dataMap.putAll(defaultDataMap);
final Map<String, Object> resultMap = new LinkedHashMap<>();
resultMap.putAll(paramMap);
resultMap.put("csvfile", csvFile.getAbsolutePath());
resultMap.put("csvfilename", csvFile.getName());
resultMap.put("crawlingConfig", dataConfig);
boolean foundValues = false;
for (int i = 0; i < list.size(); i++) {
String key = null;
String value = list.get(i);
if (value == null) {
value = StringUtil.EMPTY;
}
if (StringUtil.isNotBlank(value)) {
foundValues = true;
}
if (headerList != null && headerList.size() > i) {
key = headerList.get(i);
if (StringUtil.isNotBlank(key)) {
resultMap.put(key, value);
}
}
key = CELL_PREFIX + Integer.toString(i + 1);
resultMap.put(key, value);
}
if (!foundValues) {
logger.debug("No data in line: {}", resultMap);
continue;
}
if (logger.isDebugEnabled()) {
for (final Map.Entry<String, Object> entry : resultMap.entrySet()) {
logger.debug(entry.getKey() + "=" + entry.getValue());
}
}
final Map<String, Object> crawlingContext = new HashMap<>();
crawlingContext.put("doc", dataMap);
resultMap.put("crawlingContext", crawlingContext);
for (final Map.Entry<String, String> entry : scriptMap.entrySet()) {
final Object convertValue = convertValue(entry.getValue(), resultMap);
if (convertValue != null) {
dataMap.put(entry.getKey(), convertValue);
}
}
if (logger.isDebugEnabled()) {
for (final Map.Entry<String, Object> entry : dataMap.entrySet()) {
logger.debug(entry.getKey() + "=" + entry.getValue());
}
}
try {
callback.store(paramMap, dataMap);
} catch (final CrawlingAccessException e) {
logger.warn("Crawling Access Exception at : " + dataMap, e);
Throwable target = e;
if (target instanceof MultipleCrawlingAccessException) {
final Throwable[] causes = ((MultipleCrawlingAccessException) target).getCauses();
if (causes.length > 0) {
target = causes[causes.length - 1];
}
}
String errorName;
final Throwable cause = target.getCause();
if (cause != null) {
errorName = cause.getClass().getCanonicalName();
} else {
errorName = target.getClass().getCanonicalName();
}
String url;
if (target instanceof DataStoreCrawlingException) {
final DataStoreCrawlingException dce = (DataStoreCrawlingException) target;
url = dce.getUrl();
if (dce.aborted()) {
loop = false;
}
} else {
url = csvFile.getAbsolutePath() + ":" + csvReader.getLineNumber();
}
final FailureUrlService failureUrlService = ComponentUtil.getComponent(FailureUrlService.class);
failureUrlService.store(dataConfig, errorName, url, target);
} catch (final Throwable t) {
logger.warn("Crawling Access Exception at : " + dataMap, t);
final String url = csvFile.getAbsolutePath() + ":" + csvReader.getLineNumber();
final FailureUrlService failureUrlService = ComponentUtil.getComponent(FailureUrlService.class);
failureUrlService.store(dataConfig, t.getClass().getCanonicalName(), url, t);
}
if (readInterval > 0) {
sleep(readInterval);
}
}
} catch (final Exception e) {
throw new DataStoreException("Failed to crawl data when reading csv file.", e);
} finally {
IOUtils.closeQuietly(csvReader);
}
}
use of org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException in project fess by codelibs.
the class DatabaseDataStoreImpl method storeData.
@Override
protected void storeData(final DataConfig config, final IndexUpdateCallback callback, final Map<String, String> paramMap, final Map<String, String> scriptMap, final Map<String, Object> defaultDataMap) {
final long readInterval = getReadInterval(paramMap);
Connection con = null;
Statement stmt = null;
ResultSet rs = null;
try {
Class.forName(getDriverClass(paramMap));
final String jdbcUrl = getUrl(paramMap);
final String username = getUsername(paramMap);
final String password = getPassword(paramMap);
if (StringUtil.isNotEmpty(username)) {
con = DriverManager.getConnection(jdbcUrl, username, password);
} else {
con = DriverManager.getConnection(jdbcUrl);
}
final String sql = getSql(paramMap);
stmt = con.createStatement();
// SQL generated by an administrator
rs = stmt.executeQuery(sql);
boolean loop = true;
while (rs.next() && loop && alive) {
final Map<String, Object> dataMap = new HashMap<>();
dataMap.putAll(defaultDataMap);
final Map<String, Object> crawlingContext = new HashMap<>();
crawlingContext.put("doc", dataMap);
for (final Map.Entry<String, String> entry : scriptMap.entrySet()) {
final Object convertValue = convertValue(entry.getValue(), new ResultSetParamMap(config, crawlingContext, rs, paramMap));
if (convertValue != null) {
dataMap.put(entry.getKey(), convertValue);
}
}
try {
callback.store(paramMap, dataMap);
} catch (final CrawlingAccessException e) {
logger.warn("Crawling Access Exception at : " + dataMap, e);
Throwable target = e;
if (target instanceof MultipleCrawlingAccessException) {
final Throwable[] causes = ((MultipleCrawlingAccessException) target).getCauses();
if (causes.length > 0) {
target = causes[causes.length - 1];
}
}
String errorName;
final Throwable cause = target.getCause();
if (cause != null) {
errorName = cause.getClass().getCanonicalName();
} else {
errorName = target.getClass().getCanonicalName();
}
String url;
if (target instanceof DataStoreCrawlingException) {
final DataStoreCrawlingException dce = (DataStoreCrawlingException) target;
url = dce.getUrl();
if (dce.aborted()) {
loop = false;
}
} else {
url = sql + ":" + rs.getRow();
}
final FailureUrlService failureUrlService = ComponentUtil.getComponent(FailureUrlService.class);
failureUrlService.store(config, errorName, url, target);
} catch (final Throwable t) {
logger.warn("Crawling Access Exception at : " + dataMap, t);
final String url = sql + ":" + rs.getRow();
final FailureUrlService failureUrlService = ComponentUtil.getComponent(FailureUrlService.class);
failureUrlService.store(config, t.getClass().getCanonicalName(), url, t);
}
if (readInterval > 0) {
sleep(readInterval);
}
}
} catch (final Exception e) {
throw new DataStoreException("Failed to crawl data in DB.", e);
} finally {
try {
if (rs != null) {
rs.close();
}
} catch (final SQLException e) {
logger.warn("Failed to close a result set.", e);
} finally {
try {
if (stmt != null) {
stmt.close();
}
} catch (final SQLException e) {
logger.warn("Failed to close a statement.", e);
} finally {
try {
if (con != null) {
con.close();
}
} catch (final SQLException e) {
logger.warn("Failed to close a db connection.", e);
}
}
}
}
}
use of org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException in project fess by codelibs.
the class EsDataStoreImpl method processData.
protected void processData(final DataConfig dataConfig, final IndexUpdateCallback callback, final Map<String, String> paramMap, final Map<String, String> scriptMap, final Map<String, Object> defaultDataMap, final long readInterval, final Client client) {
final boolean deleteProcessedDoc = paramMap.getOrDefault("delete.processed.doc", Constants.FALSE).equalsIgnoreCase(Constants.TRUE);
final String[] indices;
if (paramMap.containsKey(INDEX)) {
indices = paramMap.get(INDEX).trim().split(",");
} else {
indices = new String[] { "_all" };
}
final String scroll = paramMap.containsKey(SCROLL) ? paramMap.get(SCROLL).trim() : "1m";
final String timeout = paramMap.containsKey(TIMEOUT) ? paramMap.get(TIMEOUT).trim() : "1m";
final SearchRequestBuilder builder = client.prepareSearch(indices);
if (paramMap.containsKey(TYPE)) {
builder.setTypes(paramMap.get(TYPE).trim().split(","));
}
if (paramMap.containsKey(SIZE)) {
builder.setSize(Integer.parseInt(paramMap.get(SIZE)));
}
if (paramMap.containsKey(FIELDS)) {
builder.setFetchSource(paramMap.get(FIELDS).trim().split(","), null);
}
builder.setQuery(QueryBuilders.wrapperQuery(paramMap.containsKey(QUERY) ? paramMap.get(QUERY).trim() : "{\"match_all\":{}}"));
builder.setScroll(scroll);
builder.setPreference(paramMap.containsKey(PREFERENCE) ? paramMap.get(PREFERENCE).trim() : Constants.SEARCH_PREFERENCE_PRIMARY);
try {
SearchResponse response = builder.execute().actionGet(timeout);
String scrollId = response.getScrollId();
while (scrollId != null) {
final SearchHits searchHits = response.getHits();
final SearchHit[] hits = searchHits.getHits();
if (hits.length == 0) {
scrollId = null;
break;
}
boolean loop = true;
final BulkRequestBuilder bulkRequest = deleteProcessedDoc ? client.prepareBulk() : null;
for (final SearchHit hit : hits) {
if (!alive || !loop) {
break;
}
final Map<String, Object> dataMap = new HashMap<>();
dataMap.putAll(defaultDataMap);
final Map<String, Object> resultMap = new LinkedHashMap<>();
resultMap.putAll(paramMap);
resultMap.put("index", hit.getIndex());
resultMap.put("type", hit.getType());
resultMap.put("id", hit.getId());
resultMap.put("version", Long.valueOf(hit.getVersion()));
resultMap.put("hit", hit);
resultMap.put("source", hit.getSource());
resultMap.put("crawlingConfig", dataConfig);
if (logger.isDebugEnabled()) {
for (final Map.Entry<String, Object> entry : resultMap.entrySet()) {
logger.debug(entry.getKey() + "=" + entry.getValue());
}
}
final Map<String, Object> crawlingContext = new HashMap<>();
crawlingContext.put("doc", dataMap);
resultMap.put("crawlingContext", crawlingContext);
for (final Map.Entry<String, String> entry : scriptMap.entrySet()) {
final Object convertValue = convertValue(entry.getValue(), resultMap);
if (convertValue != null) {
dataMap.put(entry.getKey(), convertValue);
}
}
if (logger.isDebugEnabled()) {
for (final Map.Entry<String, Object> entry : dataMap.entrySet()) {
logger.debug(entry.getKey() + "=" + entry.getValue());
}
}
try {
callback.store(paramMap, dataMap);
} catch (final CrawlingAccessException e) {
logger.warn("Crawling Access Exception at : " + dataMap, e);
Throwable target = e;
if (target instanceof MultipleCrawlingAccessException) {
final Throwable[] causes = ((MultipleCrawlingAccessException) target).getCauses();
if (causes.length > 0) {
target = causes[causes.length - 1];
}
}
String errorName;
final Throwable cause = target.getCause();
if (cause != null) {
errorName = cause.getClass().getCanonicalName();
} else {
errorName = target.getClass().getCanonicalName();
}
String url;
if (target instanceof DataStoreCrawlingException) {
final DataStoreCrawlingException dce = (DataStoreCrawlingException) target;
url = dce.getUrl();
if (dce.aborted()) {
loop = false;
}
} else {
url = hit.getIndex() + "/" + hit.getType() + "/" + hit.getId();
}
final FailureUrlService failureUrlService = ComponentUtil.getComponent(FailureUrlService.class);
failureUrlService.store(dataConfig, errorName, url, target);
} catch (final Throwable t) {
logger.warn("Crawling Access Exception at : " + dataMap, t);
final String url = hit.getIndex() + "/" + hit.getType() + "/" + hit.getId();
final FailureUrlService failureUrlService = ComponentUtil.getComponent(FailureUrlService.class);
failureUrlService.store(dataConfig, t.getClass().getCanonicalName(), url, t);
}
if (bulkRequest != null) {
bulkRequest.add(client.prepareDelete(hit.getIndex(), hit.getType(), hit.getId()));
}
if (readInterval > 0) {
sleep(readInterval);
}
}
if (bulkRequest != null && bulkRequest.numberOfActions() > 0) {
final BulkResponse bulkResponse = bulkRequest.execute().actionGet(timeout);
if (bulkResponse.hasFailures()) {
logger.warn(bulkResponse.buildFailureMessage());
}
}
if (!alive) {
break;
}
response = client.prepareSearchScroll(scrollId).setScroll(scroll).execute().actionGet(timeout);
scrollId = response.getScrollId();
}
} catch (final Exception e) {
throw new DataStoreException("Failed to crawl data when acessing elasticsearch.", e);
}
}
Aggregations