/** Load synonyms with the given {@link SynonymMap.Parser} class. */
private SynonymMap loadSynonyms(
ResourceLoader loader, String cname, boolean dedup, Analyzer analyzer)
throws IOException, ParseException {
CharsetDecoder decoder =
Charset.forName("UTF-8")
.newDecoder()
.onMalformedInput(CodingErrorAction.REPORT)
.onUnmappableCharacter(CodingErrorAction.REPORT);
SynonymMap.Parser parser;
Class<? extends SynonymMap.Parser> clazz = loader.findClass(cname, SynonymMap.Parser.class);
try {
parser =
clazz
.getConstructor(boolean.class, boolean.class, Analyzer.class)
.newInstance(dedup, expand, analyzer);
} catch (Exception e) {
throw new RuntimeException(e);
}
File synonymFile = new File(synonyms);
if (synonymFile.exists()) {
decoder.reset();
parser.parse(new InputStreamReader(loader.openResource(synonyms), decoder));
} else {
List<String> files = splitFileNames(synonyms);
for (String file : files) {
decoder.reset();
parser.parse(new InputStreamReader(loader.openResource(file), decoder));
}
}
return parser.build();
}
/**
* Loads the hunspell dictionary and affix files defined in the configuration
*
* @param loader ResourceLoader used to load the files
*/
public void inform(ResourceLoader loader) throws IOException {
assureMatchVersion();
String dictionaryArg = args.get(PARAM_DICTIONARY);
if (dictionaryArg == null) {
throw new IllegalArgumentException("Parameter " + PARAM_DICTIONARY + " is mandatory.");
}
String dictionaryFiles[] = args.get(PARAM_DICTIONARY).split(",");
String affixFile = args.get(PARAM_AFFIX);
String pic = args.get(PARAM_IGNORE_CASE);
if (pic != null) {
if (pic.equalsIgnoreCase(TRUE)) ignoreCase = true;
else if (pic.equalsIgnoreCase(FALSE)) ignoreCase = false;
else
throw new IllegalArgumentException(
"Unknown value for " + PARAM_IGNORE_CASE + ": " + pic + ". Must be true or false");
}
String strictAffixParsingParam = args.get(PARAM_STRICT_AFFIX_PARSING);
boolean strictAffixParsing = true;
if (strictAffixParsingParam != null) {
if (strictAffixParsingParam.equalsIgnoreCase(FALSE)) strictAffixParsing = false;
else if (strictAffixParsingParam.equalsIgnoreCase(TRUE)) strictAffixParsing = true;
else
throw new IllegalArgumentException(
"Unknown value for "
+ PARAM_STRICT_AFFIX_PARSING
+ ": "
+ strictAffixParsingParam
+ ". Must be true or false");
}
InputStream affix = null;
List<InputStream> dictionaries = new ArrayList<InputStream>();
try {
dictionaries = new ArrayList<InputStream>();
for (String file : dictionaryFiles) {
dictionaries.add(loader.openResource(file));
}
affix = loader.openResource(affixFile);
this.dictionary =
new HunspellDictionary(
affix, dictionaries, luceneMatchVersion, ignoreCase, strictAffixParsing);
} catch (ParseException e) {
throw new IOException(
"Unable to load hunspell data! [dictionary="
+ args.get("dictionary")
+ ",affix="
+ affixFile
+ "]",
e);
} finally {
IOUtils.closeWhileHandlingException(affix);
IOUtils.closeWhileHandlingException(dictionaries);
}
}
private Properties canUpdate() {
try {
if (conf == null) return null;
Properties p = new Properties();
InputStream confStream = loader.openResource(conf);
p.load(confStream);
confStream.close();
String lastupdate = p.getProperty("lastupdate", "0");
Long t = new Long(lastupdate);
if (t > this.lastUpdateTime) {
this.lastUpdateTime = t.longValue();
String paths = p.getProperty("files");
if (paths == null || paths.trim().isEmpty()) return null;
System.out.println("loading conf");
return p;
} else {
this.lastUpdateTime = t.longValue();
return null;
}
} catch (Exception e) {
System.err.println("ansj parsing conf NullPointerException~~~~~" + e.getMessage());
return null;
}
}
public void update() throws IOException {
Properties p = canUpdate();
if (p != null) {
List<String> dicPaths = SplitFileNames(p.getProperty("files"));
List<InputStream> inputStreamList = new ArrayList<InputStream>();
for (String path : dicPaths) {
if ((path != null && !path.isEmpty())) {
InputStream is = loader.openResource(path);
if (is != null) {
inputStreamList.add(is);
}
}
}
if (!inputStreamList.isEmpty()) {
UserDefineLibrary.reloadMainAndAdd(inputStreamList); // load dic to MainDic
}
}
}
private List<String> getLines(ResourceLoader loader, String resource) throws IOException {
return WordlistLoader.getLines(loader.openResource(resource), StandardCharsets.UTF_8);
}