Add support to include an excel file (.xls or .xlsx) directly

pantable/pantable.py

@@ -183,6 +183,20 @@ def read_data(include, data):
     if include is None:
         with io.StringIO(data) as file:
             raw_table_list = list(csv.reader(file))
+    elif str(include).strip().endswith('.xls') or \
+            str(include).strip().endswith('.xlsx'):
+        try:
+            import pandas as pd
+            temp = pd.read_excel(include, index_col=0)
+            raw_table_list = read_data(None, temp.to_csv())
+        except ModuleNotFoundError:
+            raw_table_list = None
+            panflute.debug("pandas needs to be installed. You "
+                           "can find installation instruction at "
+                           "http://pandas.pydata.org/pandas-docs/stable/install.html")
+        except IOError:
+            raw_table_list = None
+            panflute.debug("pantable: file not found from the path", include)
     else:
         try:
             with io.open(str(include)) as file:

tests/pantable/test_read_data.py

@@ -7,10 +7,13 @@ def test_read_data():
     # check include
     # invalid include: file doesn't exist
     assert read_data('abc.xyz', '') is None
+    assert read_data('abc.xlsx', '') is None
     # invalid include: wrong type
     assert read_data(True, '') is None
     # valid include
     assert read_data('tests/csv_tables.csv', '') is not None
+    assert read_data('tests/csv_tables.xlsx', '') is not None
+    assert read_data('tests/csv_tables.xls', '') is not None
     # check type
     data = r"""1,2
 3,4
@@ -41,6 +44,26 @@ def test_read_data():
                                 '$2.10',
                                 '5^10^~units~',
                                 'Benefits of eating oranges:\n\n- **cures** scurvy\n- `tasty`']]
+    assert read_data('tests/csv_tables.xlsx', 
+                     data) == [['**_Fruit_**', '~~Price~~', '_Number_', '`Advantages`'],
+                               ['*Bananas~1~*',
+                                '1.34',
+                                '12~units~',
+                                'Benefits of eating bananas \r\n(**Note the appropriately\r\nrendered block markdown**):    \r\n\r\n- _built-in wrapper_        \r\n- ~~**bright color**~~\r\n\r\n'],
+                               ['*Oranges~2~*',
+                                '2.1',
+                                '5^10^~units~',
+                                'Benefits of eating oranges:\r\n\r\n- **cures** scurvy\r\n- `tasty`']]
+    assert read_data('tests/csv_tables.xls',
+                     data) == [['**_Fruit_**', '~~Price~~', '_Number_', '`Advantages`'],
+                               ['*Bananas~1~*',
+                                '1.34',
+                                '12~units~',
+                                'Benefits of eating bananas \r\n(**Note the appropriately\r\nrendered block markdown**):    \r\n\r\n- _built-in wrapper_        \r\n- ~~**bright color**~~\r\n\r\n'],
+                               ['*Oranges~2~*',
+                                '2.1',
+                                '5^10^~units~',
+                                'Benefits of eating oranges:\r\n\r\n- **cures** scurvy\r\n- `tasty`']]
     # check empty table
     assert read_data(None, '') == []
     return

tests/requirements.txt

@@ -5,3 +5,4 @@ pytest-cov
 coverage
 coveralls
 future
+pandas