in core/src/main/java/org/apache/stormcrawler/filtering/regex/RegexURLNormalizer.java [121:146]
private List<Rule> readRules(ArrayNode rulesList) {
List<Rule> rules = new ArrayList<>();
for (JsonNode regexNode : rulesList) {
if (regexNode == null || regexNode.isNull()) {
LOG.warn("bad config: 'regex' element is null");
continue;
}
JsonNode patternNode = regexNode.get("pattern");
JsonNode substitutionNode = regexNode.get("substitution");
String substitutionValue = "";
if (substitutionNode != null) {
substitutionValue = substitutionNode.asText();
}
if (patternNode != null && StringUtils.isNotBlank(patternNode.asText())) {
Rule rule = createRule(patternNode.asText(), substitutionValue);
if (rule != null) {
rules.add(rule);
}
}
}
if (rules.size() == 0) {
rules = EMPTY_RULES;
}
return rules;
}