implement overwriting headers

README.md

@@ -27,8 +27,20 @@ Usage
 from pandas_ods_reader import read_ods
 
 path = "path/to/file.ods"
+
+# load a sheet based on its index (1 based)
 sheet_idx = 1
-df1 = read_ods(path, sheet_idx)
+df = read_ods(path, sheet_idx)
+
+# load a sheet based on its name
 sheet_name = "sheet1"
-df2 = read_ods(path, sheet_name)
+df = read_ods(path, sheet_name)
+
+# load a file that does not contain a header row
+# if no columns are provided they will be numbered
+df = read_ods(path, 1, headers=False)
+
+# load a file and provide custom column names
+# if headers is True (the default), the header row will be overwritten
+df = read_ods(path, 1, columns=["A", "B", "C"])
 ```

pandas_ods_reader/parser.py

@@ -19,21 +19,22 @@ def load_ods(doc, sheet, headers=True, columns=None):
     col_index = {}
     for i, row in enumerate(sheet.rows()):
         # row is a list of cells
-        if headers and i == 0:
+        if headers and i == 0 and not columns:
             # columns as lists in a dictionary
             df_dict = {cell.value: [] for cell in row if cell.value}
             # create index for the column headers
             col_index = {
                 j: cell.value for j, cell in enumerate(row) if cell.value}
             continue
-        elif not headers and i == 0:
+        elif i == 0:
             columns = columns if columns else (
                 ["column_%s" % j for j in range(len(row))])
             # columns as lists in a dictionary
             df_dict = {column: [] for column in columns}
             # create index for the column headers
             col_index = {j: column for j, column in enumerate(columns)}
-            continue
+            if headers:
+                continue
         for j, cell in enumerate(row):
             if j < len(col_index):
                 # use header instead of column index

pandas_ods_reader/tests/test_read_ods.py

@@ -8,30 +8,40 @@ from pandas_ods_reader import read_ods
 root = os.path.dirname(os.path.abspath(__file__))
 rsc = os.path.join(root, "rsc")
 
+header_file = "example_headers.ods"
+no_header_file = "example_no_headers.ods"
+
 
 class TestOdsReader(object):
     def test_header_file_with_int(self):
-        example = "example_headers.ods"
+        path = os.path.join(rsc, header_file)
-        path = os.path.join(rsc, example)
         df = read_ods(path, 1)
         assert isinstance(df, pd.DataFrame)
+        assert len(df) == 10
 
     def test_header_file_with_str(self):
-        example = "example_headers.ods"
+        path = os.path.join(rsc, header_file)
-        path = os.path.join(rsc, example)
         df = read_ods(path, "Sheet1")
         assert isinstance(df, pd.DataFrame)
+        assert len(df) == 10
+
+    def test_header_file_with_cols(self):
+        path = os.path.join(rsc, header_file)
+        columns = ["One", "Two", "Three", "Four", "Five"]
+        df = read_ods(path, "Sheet1", columns=columns)
+        assert list(df.columns) == columns
+        assert len(df) == 10
 
     def test_no_header_file_no_cols(self):
-        example = "example_no_headers.ods"
+        path = os.path.join(rsc, no_header_file)
-        path = os.path.join(rsc, example)
         df = read_ods(path, 1, headers=False)
         assert list(df.columns) == [
             "column_%s" % i for i in range(len(df.columns))]
+        assert len(df) == 10
 
     def test_no_header_file_with_cols(self):
-        example = "example_headers.ods"
+        path = os.path.join(rsc, no_header_file)
-        path = os.path.join(rsc, example)
         columns = ["A", "B", "C", "D", "E"]
         df = read_ods(path, 1, headers=False, columns=columns)
         assert list(df.columns) == columns
+        assert len(df) == 10

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 
 
-VERSION = "0.0.5"
+VERSION = "0.0.6"
 
 with open("README.md", "r") as fh:
     long_description = fh.read()