Add sheet_index param in datafile API to handle excel files with multiple sheets

mathesar/api/serializers/data_files.py

@@ -22,7 +22,7 @@ class Meta:
         model = DataFile
         fields = [
             'id', 'file', 'table_imported_to', 'user', 'header', 'delimiter',
-            'escapechar', 'quotechar', 'paste', 'url', 'created_from', 'max_level'
+            'escapechar', 'quotechar', 'paste', 'url', 'created_from', 'max_level', 'sheet_index'
         ]
         extra_kwargs = {
             'file': {'required': False},

mathesar/imports/excel.py

@@ -50,8 +50,9 @@ def remove_empty_rows_and_columns_from_dataframe(df):
 def create_db_table_from_excel_data_file(data_file, name, schema, comment=None):
     db_name = schema.database.name
     engine = create_mathesar_engine(db_name)
+    header_row = 0 if data_file.header else None
     dataframe = remove_empty_rows_and_columns_from_dataframe(
-        pandas.read_excel(data_file.file.path)
+        pandas.read_excel(data_file.file.path, data_file.sheet_index, header=header_row)
     )
     column_names = process_column_names(dataframe.columns)
     try:

mathesar/migrations/0005_datafile_sheet_name.py

@@ -0,0 +1,18 @@
+# Generated by Django 3.1.14 on 2023-09-01 04:53
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('mathesar', '0004_shares'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='datafile',
+            name='sheet_name',
+            field=models.CharField(default='0', max_length=100),
+        ),
+    ]

mathesar/migrations/0006_auto_20230906_0413.py

@@ -0,0 +1,22 @@
+# Generated by Django 3.1.14 on 2023-09-06 04:13
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('mathesar', '0005_datafile_sheet_name'),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name='datafile',
+            name='sheet_name',
+        ),
+        migrations.AddField(
+            model_name='datafile',
+            name='sheet_index',
+            field=models.IntegerField(default=0),
+        ),
+    ]

mathesar/models/base.py

@@ -871,6 +871,7 @@ class DataFile(BaseModel):
     base_name = models.CharField(max_length=100)
     header = models.BooleanField(default=True)
     max_level = models.IntegerField(default=0, blank=True)
+    sheet_index = models.IntegerField(default=0)
     delimiter = models.CharField(max_length=1, default=',', blank=True)
     escapechar = models.CharField(max_length=1, blank=True)
     quotechar = models.CharField(max_length=1, default='"', blank=True)

mathesar/tests/api/test_table_api.py

@@ -2092,3 +2092,35 @@ def test_create_table_using_null_id_excel_data_file(client, null_id_excel_data_f
         client, table_name, expt_name, null_id_excel_data_file, schema, first_row,
         column_names, import_target_table=None
     )
+
+
+def _create_excel_datafile_using_sheet_index_param(filepath, sheet_index):
+    with open(filepath, "rb") as file:
+        data_file = DataFile.objects.create(
+            file=File(file),
+            created_from='file',
+            base_name='multiple_sheets',
+            type='excel',
+            sheet_index=sheet_index
+        )
+    return data_file
+
+
+def test_create_table_with_multiple_sheets_excel_file(client, multiple_sheets_excel_filepath, schema):
+    column_names = ['Name', 'Age', 'Email']
+    test_datafile_objects_with_sheet_index = [
+        _create_excel_datafile_using_sheet_index_param(multiple_sheets_excel_filepath, sheet_index)
+        for sheet_index in range(3)
+    ]
+    expected_first_row_data = [
+        (1, 'Jim', '25', 'jim@example.com'),
+        (1, 'John', '25', 'john@example.com'),
+        (1, 'Jake', '25', 'jake@example.com'),
+    ]
+
+    for index, datafile in enumerate(test_datafile_objects_with_sheet_index):
+        table_name = f'Table {index}'
+        check_create_table_response(
+            client, table_name, table_name, datafile, schema, expected_first_row_data[index],
+            column_names, import_target_table=None
+        )

mathesar/tests/conftest.py

@@ -265,6 +265,11 @@ def null_id_table_excel_filepath():
     return 'mathesar/tests/data/excel_parsing/null_id_table.xlsx'
 
 
+@pytest.fixture(scope='session')
+def multiple_sheets_excel_filepath():
+    return 'mathesar/tests/data/excel_parsing/multiple_sheets.xlsx'
+
+
 @pytest.fixture
 def db_table_to_dj_table(engine, create_schema):
     """

mathesar/utils/datafiles.py

@@ -114,13 +114,17 @@ def create_datafile(data):
         )
     else:
         max_level = data.get('max_level', 0)
+        sheet_index = data.get('sheet_index', 1)
+        # Pandas indexes sheets from 0 and not 1.
+        sheet_index = sheet_index - 1
         datafile = DataFile(
             file=raw_file,
             base_name=base_name,
             type=type,
             created_from=created_from,
             header=header,
-            max_level=max_level
+            max_level=max_level,
+            sheet_index=sheet_index
         )
     datafile.save()
     raw_file.close()