public void indexFile(Document doc) throws IOException {
String data64 = org.elasticsearch.common.Base64.encodeFromFile(doc.getContentFilepath());
File file = new File(doc.getContentFilepath());
InputStream fileReader = new FileInputStream(file);
double bytes = file.length();
int indexedChars = 1000000;
Metadata metadata = new Metadata();
byte[] buffer = new byte[1024 * 8];
ByteArrayOutputStream bos = new ByteArrayOutputStream();
int i;
while (-1 != (i = fileReader.read(buffer))) {
bos.write(buffer, 0, i);
}
byte[] data = bos.toByteArray();
String parsedContent;
try {
// Set the maximum length of strings returned by the parseToString method, -1 sets no limit
parsedContent =
tika().parseToString(new BytesStreamInput(data, false), metadata, indexedChars);
} catch (IOException | TikaException e) {
e.printStackTrace();
parsedContent = "";
}
XContentBuilder source =
jsonBuilder()
.startObject()
.field("file", data64)
.field("filename", doc.getRootFileName())
.field("title", doc.getTitle())
.field("author", doc.getAuthor())
.field("created_date", doc.getDateCreated())
.field("content_type", FilenameUtils.getExtension(doc.getRootFileName()))
.field("content_length", bytes)
.field("content", parsedContent)
.endObject();
IndexResponse idxResp =
mClient
.prepareIndex()
.setIndex(idxName)
.setType(idxType)
.setId(doc.getHash())
.setSource(source)
.setRefresh(true)
.execute()
.actionGet();
}
