Github user myui commented on a diff in the pull request:
https://github.com/apache/incubator-hivemall/pull/97#discussion_r126858366
--- Diff: nlp/src/main/java/hivemall/nlp/tokenizer/KuromojiUDF.java ---
@@ -170,6 +192,100 @@ private static CharArraySet stopWords(@Nonnull final
String[] array)
return results;
}
+ @Nullable
+ private static UserDictionary userDictionary(@Nonnull final
ObjectInspector oi)
+ throws UDFArgumentException {
+ if (HiveUtils.isConstListOI(oi)) {
+ return userDictionary(HiveUtils.getConstStringArray(oi));
+ } else if (HiveUtils.isConstString(oi)) {
+ return userDictionary(HiveUtils.getConstString(oi));
+ } else {
+ throw new UDFArgumentException(
+ "User dictionary MUST be given as an array of constant
string or constant string (URL)");
+ }
+ }
+
+ @Nullable
+ private static UserDictionary userDictionary(@Nullable final String[]
userDictArray)
+ throws UDFArgumentException {
+ if (userDictArray == null) {
+ return null;
+ }
+
+ StringBuilder builder = new StringBuilder();
+ for (String row : userDictArray) {
+ builder.append(row);
+ builder.append("\r\n");
+ }
+ InputStream is = new
ByteArrayInputStream(builder.toString().getBytes());
+ final Reader reader = new InputStreamReader(is);
+ try {
+ return UserDictionary.open(reader); // return null if empty
+ } catch (Throwable e) {
+ throw new UDFArgumentException(
+ "Failed to create user dictionary based on the given
array<string>: " + e);
+ }
+ }
+
+ @Nullable
+ private static UserDictionary userDictionary(@Nullable final String
userDictURL)
+ throws UDFArgumentException {
+ if (userDictURL == null) {
+ return null;
+ }
+
+ final HttpURLConnection conn;
+ try {
+ conn = HttpUtils.getHttpURLConnection(userDictURL);
+ } catch (Throwable e) {
+ throw new UDFArgumentException("Failed to create HTTP
connection to the URL: " + e);
+ }
+
+ // allow to read as a compressed GZIP file for efficiency
+ conn.setRequestProperty("Accept-Encoding", "gzip");
+
+ conn.setConnectTimeout(CONNECT_TIMEOUT_MS); // throw exception
from connect()
+ conn.setReadTimeout(READ_TIMEOUT_MS); // throw exception from
getXXX() methods
+
+ final int responseCode;
+ try {
+ responseCode = conn.getResponseCode();
+ } catch (Throwable e) {
+ throw new UDFArgumentException("Failed to get response code: "
+ e);
+ }
+ if (responseCode != 200) {
+ throw new UDFArgumentException("God invalid response code: " +
responseCode);
+ }
+
+ final String contentType = conn.getContentType();
+ boolean textContent = contentType.startsWith("text/plain");
+ boolean binaryContent =
contentType.startsWith("application/octet-stream");
+ if (!textContent && !binaryContent) {
+ throw new UDFArgumentException(
+ "User dictionary URL indicates unexpected content type: "
+ contentType);
+ }
+
+ InputStream is;
+ try {
+ is = HttpUtils.getBoundedInputStream(conn,
MAX_INPUT_STREAM_SIZE);
+ if ((textContent && "gzip".equals(conn.getContentEncoding()))
|| binaryContent) {
+ is = new GZIPInputStream(is);
--- End diff --
simple as follows:
```java
if(urlString.endWith(".gz")) {
InputStream is = conn.getInputStream();
is = new LimitedInputStream(is, MAX_SIZE);
is = new GzipInputStream(is);
} else {
conn.setRequestProperty("Accept-Encoding", "gzip");
// conn.connect();
InputStream is = conn.getInputStream();
is = new LimitedInputStream(is, MAX_SIZE);
if ("gzip".equals(con.getContentEncoding())) {
is = new GzipInputStream(is);
}
}
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
