/**
* Creates a combined list of Entries using the provided mapping files.
*
* @param mappings List of mapping files
* @return list of Entries
*/
private static List<Entry> readEntries(
String annotatorName,
Set<String> noDefaultOverwriteLabels,
boolean ignoreCase,
boolean verbose,
String... mappings) {
// Unlike RegexNERClassifier, we don't bother sorting the entries
// We leave it to TokensRegex NER to sort out the priorities and matches
// (typically after all the matches has been made since for some TokenRegex expression,
// we don't know how many tokens are matched until after the matching is done)
List<Entry> entries = new ArrayList<>();
TrieMap<String, Entry> seenRegexes = new TrieMap<>();
Arrays.sort(mappings);
for (String mapping : mappings) {
BufferedReader rd = null;
try {
rd = IOUtils.readerFromString(mapping);
readEntries(
annotatorName,
entries,
seenRegexes,
mapping,
rd,
noDefaultOverwriteLabels,
ignoreCase,
verbose);
} catch (IOException e) {
throw new RuntimeIOException("Couldn't read TokensRegexNER from " + mapping, e);
} finally {
IOUtils.closeIgnoringExceptions(rd);
}
}
if (mappings.length != 1) {
logger.log(
"TokensRegexNERAnnotator "
+ annotatorName
+ ": Read "
+ entries.size()
+ " unique entries from "
+ mappings.length
+ " files");
}
return entries;
}
