/**
* Guess the encoding with the previously specified list of clues.
*
* @param content Content instance
* @param defaultValue Default encoding to return if no encoding can be detected with enough
* confidence. Note that this will <b>not</b> be normalized with {@link
* EncodingDetector#resolveEncodingAlias}
* @return Guessed encoding or defaultValue
*/
public String guessEncoding(Content content, String defaultValue) {
/*
* This algorithm could be replaced by something more sophisticated;
* ideally we would gather a bunch of data on where various clues
* (autodetect, HTTP headers, HTML meta tags, etc.) disagree, tag each with
* the correct answer, and use machine learning/some statistical method
* to generate a better heuristic.
*/
String base = content.getBaseUrl();
if (LOG.isTraceEnabled()) {
findDisagreements(base, clues);
}
/*
* Go down the list of encoding "clues". Use a clue if:
* 1. Has a confidence value which meets our confidence threshold, OR
* 2. Doesn't meet the threshold, but is the best try,
* since nothing else is available.
*/
EncodingClue defaultClue = new EncodingClue(defaultValue, "default");
EncodingClue bestClue = defaultClue;
for (EncodingClue clue : clues) {
if (LOG.isTraceEnabled()) {
LOG.trace(base + ": charset " + clue);
}
String charset = clue.value;
if (minConfidence >= 0 && clue.confidence >= minConfidence) {
if (LOG.isTraceEnabled()) {
LOG.trace(
base + ": Choosing encoding: " + charset + " with confidence " + clue.confidence);
}
return resolveEncodingAlias(charset).toLowerCase();
} else if (clue.confidence == NO_THRESHOLD && bestClue == defaultClue) {
bestClue = clue;
}
}
if (LOG.isTraceEnabled()) {
LOG.trace(base + ": Choosing encoding: " + bestClue);
}
return bestClue.value.toLowerCase();
}
