Github user joewitt commented on a diff in the pull request: https://github.com/apache/nifi/pull/1564#discussion_r104316845 --- Diff: nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/ScanAttribute.java --- @@ -207,36 +253,62 @@ public void onTrigger(final ProcessContext context, final ProcessSession session final boolean matchAll = context.getProperty(MATCHING_CRITERIA).getValue().equals(MATCH_CRITERIA_ALL); - for (final FlowFile flowFile : flowFiles) { - final boolean matched = matchAll ? allMatch(flowFile, attributePattern, dictionaryTerms) : anyMatch(flowFile, attributePattern, dictionaryTerms); - final Relationship relationship = matched ? REL_MATCHED : REL_UNMATCHED; + for (FlowFile flowFile : flowFiles) { + final Map<String,String> matched = (matchAll ? matchAll(flowFile, attributePattern, dictionaryTerms) : matchAny(flowFile, attributePattern, dictionaryTerms)); + flowFile = session.putAllAttributes(flowFile, matched); + + final Relationship relationship = (((matched.size() == (attributeNameMatches.size() * 3) && matchAll) || (matched.size() > 0 && !matchAll))) ? REL_MATCHED : REL_UNMATCHED; session.getProvenanceReporter().route(flowFile, relationship); session.transfer(flowFile, relationship); logger.info("Transferred {} to {}", new Object[]{flowFile, relationship}); } } - private boolean allMatch(final FlowFile flowFile, final Pattern attributePattern, final Set<String> dictionary) { - for (final Map.Entry<String, String> entry : flowFile.getAttributes().entrySet()) { - if (attributePattern == null || attributePattern.matcher(entry.getKey()).matches()) { - if (!dictionary.contains(entry.getValue())) { - return false; + private Map<String,String> matchAny(final FlowFile flowFile, final Pattern attributePattern, final Map<String,String> dictionary) { + Map<String,String> dictionaryTermMatches = new HashMap<String,String>(); + attributeNameMatches = new HashSet<String>(); + + int hitCounter = 0; + + for (final Map.Entry<String, String> attribute : flowFile.getAttributes().entrySet()) { + if (attributePattern == null || attributePattern.matcher(attribute.getKey()).matches()) { + attributeNameMatches.add(attribute.getKey()); + + if (dictionary.containsKey(attribute.getValue())) { + hitCounter = setDictionaryTermMatch(dictionary, dictionaryTermMatches, hitCounter, attribute); --- End diff -- hitCounter should not be assigned from the return of setDictionaryTermMatch. It should simply be incremented prior to the call.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---