public void testDecompressException() throws IOException {
// build 5k array
byte[] uncompressedData = new byte[5 * 1024];
for (int i = 0; i < uncompressedData.length; i++) {
uncompressedData[i] = 1;
}
byte[] compressedData = doCompress(uncompressedData);
Bucket inBucket = new ArrayBucket(compressedData);
NullBucket outBucket = new NullBucket();
InputStream decompressorInput = null;
OutputStream decompressorOutput = null;
try {
decompressorInput = inBucket.getInputStream();
decompressorOutput = outBucket.getOutputStream();
Compressor.COMPRESSOR_TYPE.GZIP.decompress(
decompressorInput, decompressorOutput, 4096 + 10, 4096 + 20);
decompressorInput.close();
decompressorOutput.close();
} catch (CompressionOutputSizeException e) {
// expect this
return;
} finally {
Closer.close(decompressorInput);
Closer.close(decompressorOutput);
inBucket.free();
outBucket.free();
}
fail("did not throw expected CompressionOutputSizeException");
}
private void getWordsFromPages()
throws URISyntaxException, UnsafeContentTypeException, IOException {
// Content-XXXXXXX.html pages only, because they contain all the contents
// and their respective URIs won't change over time
InputStream filterInput = null;
OutputStream filterOutput = null;
ArrayBucket input = null;
NullBucket output = null;
for (final Content content : new FlogFactory(flog).getContentsTreeMap(false).values()) {
NullFilterCallback nullFC = new NullFilterCallback();
input =
new ArrayBucket(
ContentSyntax.parseSomeString(content.getContent(), content.getContentSyntax())
.getBytes("UTF-8"));
output = new NullBucket();
filterInput = input.getInputStream();
filterOutput = output.getOutputStream();
ContentFilter.filter(
filterInput,
filterOutput,
"text/html",
new URI("http://whocares.co:12345/"),
nullFC,
null,
null);
filterInput.close();
filterOutput.close();
input.free();
output.free();
final String cURI = "Content-" + content.getID() + ".html";
this.pageIDs.add(cURI);
final int pageID = this.pageIDs.indexOf(cURI);
for (String w : nullFC.words.keySet()) {
if (!this.ourWords.containsKey(w)) {
this.ourWords.put(w, new HashMap<Integer, Vector<Long>>());
}
final HashMap<Integer, Vector<Long>> container = this.ourWords.get(w);
if (!container.containsKey(pageID)) {
container.put(pageID, new Vector<Long>());
}
final Vector<Long> subContainer = container.get(pageID);
for (Long position : nullFC.words.get(w)) {
if (!subContainer.contains(position)) {
subContainer.add(position);
}
}
final Byte firstMD5 = Byte.valueOf(DataFormatter.getMD5(w).substring(0, 1), 16);
final Vector<String> md5Container = this.wordsByMD5.get(firstMD5);
if (!md5Container.contains(w)) {
md5Container.add(w);
}
}
}
}
