From 6bcd5075c479ae674a0b11ad7f7d752e436ed5b7 Mon Sep 17 00:00:00 2001
From: Thomas Edwards <tomedwards@sirma.com>
Date: Tue, 11 Jun 2024 14:45:43 +0100
Subject: [PATCH] Implements NER  - to use send http get request to
 {domain}/ner with form data key = page / value = document/s sends back json
 success with output containing ner results

---
 .idea/cogniStance.iml |  1 +
 api/api_functions.py  |  8 +++++++-
 func/ner/ner.py       | 22 +++++++++++++---------
 3 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/.idea/cogniStance.iml b/.idea/cogniStance.iml
index 2f0a841..1058f41 100644
--- a/.idea/cogniStance.iml
+++ b/.idea/cogniStance.iml
@@ -3,6 +3,7 @@
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$">
       <excludeFolder url="file://$MODULE_DIR$/.venv" />
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
     </content>
     <orderEntry type="jdk" jdkName="Python 3.9 (cognistance)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
diff --git a/api/api_functions.py b/api/api_functions.py
index 5aace62..92ab989 100644
--- a/api/api_functions.py
+++ b/api/api_functions.py
@@ -1,3 +1,5 @@
+from flask import make_response, jsonify
+
 from func.ner.ner import *
 from func.usas.usas import *
 
@@ -7,7 +9,11 @@ from func.usas.usas import *
 # Returns NER results
 def get_ner_for_data(page):
     result = run_ner_on_text(page)
-    return result
+
+    if result["code"] == "SUCCESS":
+        return make_response(jsonify(result), 201)
+
+    return make_response(jsonify(result), 400)
 
 
 def get_usas_for_data():
diff --git a/func/ner/ner.py b/func/ner/ner.py
index b17f5b8..0001999 100644
--- a/func/ner/ner.py
+++ b/func/ner/ner.py
@@ -5,14 +5,18 @@ from transformers import pipeline
 # Perform NER on Text
 def run_ner_on_text(page):
     ner_driver = CkipNerChunker(model="bert-base")
-    ws_driver = CkipWordSegmenter(device=-1)
 
-    txt = [
-        "傅達仁今將執行安樂死，卻突然爆出自己20年前遭緯來體育台封殺，他不懂自己哪裡得罪到電視台。",
-        "美國參議院針對今天總統布什所提名的勞工部長趙小蘭展開認可聽證會，預料她將會很順利通過參議院支持，成為該國有史以來第一位的華裔女性內閣成員。",
-        "空白 也是可以的～",
-    ]
+    data = []
+    ner = ner_driver([page])
 
-    ner = ner_driver(txt)
-    print(ner)
-    return "hello ner"
+    for item in ner[0]:
+        word = item.word
+        ner = item.ner
+        idx = item.idx
+        obj = {"word":word, "translation": "" , "ner":ner, "idx":idx}
+
+        data.append(obj)
+
+    result = {'output': data,'message': 'Done', 'code': 'SUCCESS'}
+
+    return result
-- 
GitLab