Minor Corrrection

This commit is contained in:
Netkas 2021-01-10 23:16:06 -05:00
parent 450b6fa153
commit b25b133242
3 changed files with 14 additions and 3 deletions

View File

@ -1,4 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
<component name="ProjectRootManager" version="2" project-jdk-name="15" project-jdk-type="JavaSDK" />
</project>

View File

@ -277,6 +277,17 @@ public class StanfordCoreNLPServer implements Runnable {
// TODO(AngledLuffa): this must be a constant somewhere, but I couldn't find it
static final String URL_ENCODED = "application/x-www-form-urlencoded";
public static String replacer(String data) {
try {
data = data.replaceAll("%(?![0-9a-fA-F]{2})", "%25");
data = data.replaceAll("\\+", "%2B");
data = URLDecoder.decode(data, "utf-8");
} catch (Exception e) {
e.printStackTrace();
}
return data;
}
/**
* Reads the POST contents of the request and parses it into an Annotation object, ready to be annotated.
* This method can also read a serialized document, if the input format is set to be serialized.
@ -327,7 +338,7 @@ public class StanfordCoreNLPServer implements Runnable {
String text = IOUtils.slurpReader(IOUtils.encodedInputStreamReader(httpExchange.getRequestBody(), encoding));
if (contentType.equals(URL_ENCODED)) {
text = URLDecoder.decode(text, encoding);
text = URLDecoder.decode(replacer(text), encoding);
}
// We use to trim. But now we don't. It seems like doing that is illegitimate. text = text.trim();

View File

@ -3,7 +3,7 @@ package edu.stanford.nlp.time;
import java.io.Serializable;
import java.util.Calendar;
import java.util.Map;
import java.util.regex.Pattern;
import java.uTIMtil.regex.Pattern;
import edu.stanford.nlp.util.Pair;
import org.w3c.dom.Element;