[
https://issues.apache.org/jira/browse/NIFI-3497?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15896382#comment-15896382
]
ASF GitHub Bot commented on NIFI-3497:
--------------------------------------
Github user joewitt commented on a diff in the pull request:
https://github.com/apache/nifi/pull/1564#discussion_r104316866
--- 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);
}
}
}
-
- return true;
+ return dictionaryTermMatches;
}
- private boolean anyMatch(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 true;
+ private Map<String,String> matchAll(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 --
avoid assigning hitCounter from the return. Increment then call.
> ScanAttribute should support tagging a flowfile with metadata value from the
> supplied dictionary
> ------------------------------------------------------------------------------------------------
>
> Key: NIFI-3497
> URL: https://issues.apache.org/jira/browse/NIFI-3497
> Project: Apache NiFi
> Issue Type: Improvement
> Reporter: Joseph Witt
> Assignee: Joseph Witt
>
> Today ScanAttribute just looks through the supplied dictionary and given
> object for a string matching hit. If it hits then it is a match otherwise it
> is a 'not found'. However, when a hit occurs it can often be quite useful to
> gather additional metadata about that hit. This makes cases like
> enrichment/tagging much easier.
> So, plan is to have ScanAttribute support a dictionary value demarcator which
> would separate the dictionary term from some string response that will be
> added to the flowfile. For instance a dictionary might have
> apples:These are red or green
> bananas:These are yellow unless you should toss them or make bread
> Then if a hit occurs on 'apples' the flowfile that contained such an
> attribute would have a new attribute such as 'dictionary.hit.term' = 'apple'
> and 'dictionary.hit.metadata' = 'These are red or green'.
> This means downstream processors could extract that metadata and do
> interesting things with it.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
