Add paragraphMatch.

helper/exercises.py

@@ -1,4 +1,6 @@
 import queue
+import string
+
 import nltk
 import random
 import re
@@ -309,6 +311,10 @@ def generate_reading_exercises(passage: str, req_exercises: list, number_of_exer
             question = gen_write_blanks_exercise(passage, number_of_exercises, start_id, difficulty)
             exercises.append(question)
             print("Added write blanks: " + str(question))
+        elif req_exercise == "paragraphMatch":
+            question = gen_paragraph_match_exercise(passage, number_of_exercises, start_id)
+            exercises.append(question)
+            print("Added paragraph match: " + str(question))
 
         start_id = start_id + number_of_exercises
 
@@ -483,6 +489,53 @@ def gen_write_blanks_exercise(text: str, quantity: int, start_id, difficulty):
     }
 
 
+def gen_paragraph_match_exercise(text: str, quantity: int, start_id):
+    paragraphs = assign_letters_to_paragraphs(text)
+    heading_prompt = (
+                'For every paragraph of the list generate a minimum 5 word heading for it. Provide your answer in this JSON format: '
+                '{"headings": [ {"heading": "first paragraph heading"}, {"heading": "second paragraph heading"}]}\n'
+                'The paragraphs are these: ' + str(paragraphs))
+
+    token_count = count_tokens(heading_prompt)["n_tokens"]
+    headings = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, heading_prompt, token_count,
+                                         ["headings"],
+                                         GEN_QUESTION_TEMPERATURE)["headings"]
+
+    options = []
+    for i, paragraph in enumerate(paragraphs, start=0):
+        paragraph["heading"] = headings[i]
+        options.append({
+            "id": paragraph["letter"],
+            "sentence": paragraph["paragraph"]
+        })
+
+    random.shuffle(paragraphs)
+    sentences = []
+    for i, paragraph in enumerate(paragraphs, start=start_id):
+        sentences.append({
+            "id": i,
+            "sentence": paragraph["heading"],
+            "solution": paragraph["letter"]
+        })
+
+    return {
+            "id": str(uuid.uuid4()),
+            "allowRepetition": False,
+            "options": options,
+            "prompt": "Choose the correct heading for paragraphs from the list of headings below.",
+            "sentences": sentences[:quantity],
+            "type": "matchSentences"
+        }
+
+
+def assign_letters_to_paragraphs(paragraphs):
+    result = []
+    letters = iter(string.ascii_uppercase)
+    for paragraph in paragraphs.split("\n"):
+        result.append({'paragraph': paragraph.strip(), 'letter': next(letters)})
+    return result
+
+
 def gen_multiple_choice_exercise_listening_conversation(text: str, quantity: int, start_id, difficulty):
     gen_multiple_choice_for_text = "Generate " + str(
         quantity) + " " + difficulty + " difficulty multiple choice questions of 4 options of for this conversation: " \