Merge pull request #18 from dhmit/create_corpus_model

Create corpus model

backend/app/admin.py

@@ -9,6 +9,7 @@
     models.Document,
     models.PronounSeries,
     models.Gender,
+    models.Corpus
 ]
 
 for model in models_to_register:

backend/app/migrations/0007_corpus.py

@@ -0,0 +1,25 @@
+# Generated by Django 3.1.5 on 2021-07-10 21:17
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('app', '0006_initial_data'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Corpus',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('title', models.CharField(max_length=30)),
+                ('description', models.CharField(blank=True, max_length=500)),
+                ('documents', models.ManyToManyField(to='app.Document')),
+            ],
+            options={
+                'verbose_name_plural': 'Corpora',
+            },
+        ),
+    ]

backend/app/models.py

@@ -489,3 +489,42 @@ def update_metadata(self, new_metadata):
             self.text = new_metadata['text']
             self.get_tokenized_text_wc_and_pos()
         self.save()
+
+
+class Corpus(models.Model):
+    """
+    This model will hold associations to other Documents and their
+    metadata (author, title, publication date, etc.)
+    """
+    title = models.CharField(max_length=30)
+    description = models.CharField(max_length=500, blank=True)
+    documents = models.ManyToManyField(Document)
+
+    class Meta:
+        verbose_name_plural = "Corpora"
+
+    def __str__(self):
+        """Returns the title of the corpus"""
+        return self.title
+
+    def __len__(self):
+        """Returns the number of documents associated with this corpus"""
+        return len(self.document_set.all())
+
+    def __iter__(self):
+        """Yields each document associated with the corpus"""
+        for this_document in self.document_set.all():
+            yield this_document
+
+    def __eq__(self, other):
+        """Returns true if both of the corpora are associated with the same documents"""
+        if not isinstance(other, Corpus):
+            raise NotImplementedError("Only a Corpus can be compared to another Corpus.")
+
+        if len(self) != len(other):
+            return False
+
+        if set(self.document_set.all()) == set(other.document_set.all()):
+            return True
+        else:
+            return False

backend/app/serializers.py

@@ -9,6 +9,7 @@
     PronounSeries,
     Gender,
     Document,
+    Corpus
 )
 
 
@@ -47,6 +48,16 @@ class SimpleDocumentSerializer(serializers.ModelSerializer):
     """
     Serializes a Document object (does not include the text itself)
     """
+
     class Meta:
         model = Document
         fields = ['id', 'author', 'title', 'year', 'word_count']
+
+class CorpusSerializer(serializers.ModelSerializer):
+    """
+    Serializes a Corpus object
+    """
+
+    class Meta:
+        model = Corpus
+        fields = ['id', 'title', 'description']

backend/app/tests.py

@@ -7,6 +7,7 @@
 from .models import (
     PronounSeries,
     Document,
+    Corpus
 )
 
 
@@ -186,19 +187,24 @@ def test_update_metadata(self):
         self.assertEqual(doc.word_count, 9)
 
 
-class MainTests(TestCase):
+class CorpusTestCase(TestCase):
     """
-    Backend TestCase
+    Test Cases for the Corpus Model
     """
 
-    # def setUp(self):
-    #     super().setUp()
-    #     do any setup here
+    def setUp(self):
+        Corpus.objects.create(title='corpus1', description='testing corpus save')
+        Document.objects.create_document(title='doc1', year=2021, text='The quick brown fox jumped over the lazy dog.')
+        Document.objects.create_document(title='doc2', text='She really likes to eat chocolate!')
+        Document.objects.create_document(title='doc3', text='Do you like ice cream as much as I do?')
+
+    def test_add_document_to_corpus(self):
+        corpus1 = Corpus.objects.get(title='corpus1')
+        doc1 = Document.objects.get(title='doc1')
+        doc2 = Document.objects.get(title='doc2')
+        doc3 = Document.objects.get(title='doc3')
+        doc1.corpus_set.add(corpus1)
+        self.assertEqual(list(corpus1.documents.all()), [doc1])
+        corpus1.documents.add(doc2, doc3)
+        self.assertEqual(list(corpus1.documents.all()), [doc1, doc2, doc3])
 
-    def test_sample(self):
-        """
-        Remove me once we have real tests here.
-        """
-        two = 2
-        another_two = 2
-        self.assertEqual(two + another_two, 4)