Factor out logic to get columns into separate functions.

pandas_ods_reader/algo.py

@@ -5,16 +5,7 @@ import pandas as pd
 from .utils import sanitize_df
 
 
-def parse_data(backend, rows, headers=True, columns=None, skiprows=0):
+def get_columns_from_headers(backend, row):
-    df_dict = OrderedDict()
-    col_index = {}
-    for _ in range(skiprows):
-        next(rows)
-    for i, row in enumerate(rows):
-        # row is a list of cells
-        if i == 0:
-            if not columns:
-                if headers:
     repeat_until = -1
     repeat_value = None
     # columns as lists in a dictionary
@@ -39,14 +30,31 @@ def parse_data(backend, rows, headers=True, columns=None, skiprows=0):
             while f"{column_name}.{idx}" in columns:
                 idx += 1
             columns.append(f"{column_name}.{idx}")
-                else:
+    return columns
-                    # without headers, assign generic numbered column names
-                    columns = [f"column.{j}" for j in range(len(row))]
 
+
+def get_generic_columns(row):
+    return [f"column.{j}" for j in range(len(row))]
+
+
+def get_columns(backend, row, headers):
+    if headers:
+        return get_columns_from_headers(backend, row)
+    return get_generic_columns(row)
+
+
+def parse_data(backend, rows, headers=True, columns=None, skiprows=0):
+    df_dict = OrderedDict()
+    col_index = {}
+    for _ in range(skiprows):
+        next(rows)
+    for i, row in enumerate(rows):
+        # row is a list of cells
+        if i == 0:
+            columns = columns or get_columns(backend, row, headers)
             df_dict = OrderedDict((column, []) for column in columns)
             # create index for the column headers
             col_index = {j: column for j, column in enumerate(columns)}
-
             if headers:
                 continue
 
@@ -55,14 +63,15 @@ def parse_data(backend, rows, headers=True, columns=None, skiprows=0):
                 value, _ = backend.get_value(cell, parsed=True)
                 # use header instead of column index
                 df_dict[col_index[j]].append(value)
+
     # make sure all columns are of the same length
     max_col_length = max(len(df_dict[col]) for col in df_dict)
     for col in df_dict:
         col_length = len(df_dict[col])
         if col_length < max_col_length:
             df_dict[col] += [None] * (max_col_length - col_length)
-    df = pd.DataFrame(df_dict)
+
-    return df
+    return pd.DataFrame(df_dict)
 
 
 def read_data(backend, file_or_path, sheet_id, headers=True, columns=None, skiprows=0):