From 45d619ad3434607481de500bcec7bcb2419c88ff Mon Sep 17 00:00:00 2001
From: Hagen Peukert <hagen.peukert@uni-hamburg.de>
Date: Fri, 1 Apr 2022 10:28:30 +0200
Subject: [PATCH] Lemmatization implemented
---
Morphochron/src/Init.java | 5 ++++-
Morphochron/src/OED.java | 20 +++++++++++++++-----
Morphochron/src/SuffixEnum.java | 6 +++---
3 files changed, 22 insertions(+), 9 deletions(-)
diff --git a/Morphochron/src/Init.java b/Morphochron/src/Init.java
index f1a3941..226c6ab 100644
--- a/Morphochron/src/Init.java
+++ b/Morphochron/src/Init.java
@@ -92,7 +92,10 @@ public class Init
// normalizedWords.add("dignitary");
// normalizedWords.add("proposition");
// normalizedWords.add("daskommtnichtvor");
-//
+// normalizedWords.add("annoyaunce");
+// normalizedWords.add("assygnement");
+// normalizedWords.add("daskommtnichtvor");
+
frame.setMessage("All words of type " + wordclass + " selected\n");
//detect affixes in word list as a pre-processing and countercheck these with OED REST API
diff --git a/Morphochron/src/OED.java b/Morphochron/src/OED.java
index 7369afc..52ea05f 100644
--- a/Morphochron/src/OED.java
+++ b/Morphochron/src/OED.java
@@ -54,6 +54,14 @@ public class OED
this.resultPath = resultPath;
}
+ /*
+ * gets lemmatized word representation of OED REST API as JSON object
+ */
+ private String getRESTAPILemmatizedWord(String word)
+ {
+ return "https://oed-researcher-api.oxfordlanguages.com/oed/api/v0.2/lemmatize/?form=" + word;// + "&part_of_speech=" + wordclass;
+ }
+
/*
* gets word representation of OED REST API as JSON object
*/
@@ -80,11 +88,11 @@ public class OED
JSONArray arr = obj.getJSONArray("data");
for (int i = 0; i < arr.length(); i++)
{
- wordid = arr.getJSONObject(i).getString("id");
+ wordid = arr.getJSONObject(i).getJSONObject("word").getString("id");
//System.out.println("Wort-ID:" + wordid);
- if (wordid.equals(word + wordclass)) break; //words may be part of several word classes
+ if (wordid.endsWith(wordclass)) break; //words may be part of several word classes
}
-
+
return wordid;
}
@@ -181,7 +189,8 @@ public class OED
{
//Map<String, Integer> oedData = new HashMap<String,Integer>();
Boolean entryAvailable = false;
- String wordJSON = getRESTAPIWordRepresentation(word.toLowerCase());
+ //String wordJSON = getRESTAPIWordRepresentation(word.toLowerCase());
+ String wordJSON = getRESTAPILemmatizedWord(word.toLowerCase());
JSONObject jo = getJSonResponse(wordJSON);
String id = processJSonWordID(jo);
if (!id.isEmpty())
@@ -199,7 +208,8 @@ public class OED
public Set<String> getMorphemesOEDRequest()
{
- String wordJSON = getRESTAPIWordRepresentation(word.toLowerCase());
+ //String wordJSON = getRESTAPIWordRepresentation(word.toLowerCase());
+ String wordJSON = getRESTAPILemmatizedWord(word.toLowerCase());
JSONObject jo = getJSonResponse(wordJSON);
String id = processJSonWordID(jo);
Set<String> affixes = new HashSet<String>();
diff --git a/Morphochron/src/SuffixEnum.java b/Morphochron/src/SuffixEnum.java
index 2093588..8106fb2 100644
--- a/Morphochron/src/SuffixEnum.java
+++ b/Morphochron/src/SuffixEnum.java
@@ -88,9 +88,9 @@ public enum SuffixEnum {
ward("ward"), wards("wards"), ware("ware"), uaeras("ware"), uaras("ware"), uaro("ware"), waeras("ware"), wara("ware"), waran("ware"),
waras("ware"), waru("ware"), wearan("ware"), waeren("ware"), warae("ware"), wick("wick"), y("y"), ig("y"), ye("y"), igan("y"), izen("y"),
ezen("y"), yen("y"), ey("y"), yl("yl"), yne("yne");
- private final String morpheme;
-
- //constructor
+
+ private String morpheme;
+
SuffixEnum(String morpheme) {
this.morpheme = morpheme;
}
--
GitLab