Add skip_lines like Table.from_csv, closes #7

Author: James McKinney

agateexcel/table_xls.py

@@ -10,7 +10,7 @@
 import six
 import xlrd
 
-def from_xls(cls, path, sheet=None, **kwargs):
+def from_xls(cls, path, sheet=None, skip_lines=0, **kwargs):
     """
     Parse an XLS file.
 
@@ -19,6 +19,8 @@ def from_xls(cls, path, sheet=None, **kwargs):
     :param sheet:
         The name of a worksheet to load. If not specified then the first
         sheet will be used.
+    :param skip_lines:
+        The number of rows to skip from the top of the sheet.
     """
     if hasattr(path, 'read'):
         book = xlrd.open_workbook(file_contents=path.read())
@@ -36,11 +38,14 @@ def from_xls(cls, path, sheet=None, **kwargs):
     column_names = []
     columns = []
 
+    if not isinstance(skip_lines, int):
+        raise ValueError('skip_lines argument must be an int')
+
     for i in range(sheet.ncols):
         data = sheet.col_values(i)
-        name = six.text_type(data[0]) or None
-        values = data[1:]
-        types = sheet.col_types(i)[1:]
+        name = six.text_type(data[skip_lines]) or None
+        values = data[skip_lines + 1:]
+        types = sheet.col_types(i)[skip_lines + 1:]
 
         excel_type = determine_excel_type(types)
 

agateexcel/table_xlsx.py

@@ -12,7 +12,7 @@
 
 NULL_TIME = datetime.time(0, 0, 0)
 
-def from_xlsx(cls, path, sheet=None, **kwargs):
+def from_xlsx(cls, path, sheet=None, skip_lines=0, **kwargs):
     """
     Parse an XLSX file.
 
@@ -21,6 +21,8 @@ def from_xlsx(cls, path, sheet=None, **kwargs):
     :param sheet:
         The name or integer index of a worksheet to load. If not specified
         then the "active" sheet will be used.
+    :param skip_lines:
+        The number of rows to skip from the top of the sheet.
     """
     if hasattr(path, 'read'):
         f = path
@@ -39,7 +41,10 @@ def from_xlsx(cls, path, sheet=None, **kwargs):
     column_names = []
     rows = []
 
-    for i, row in enumerate(sheet.rows):
+    if not isinstance(skip_lines, int):
+        raise ValueError('skip_lines argument must be an int')
+
+    for i, row in enumerate(sheet.iter_rows(row_offset=skip_lines)):
         if i == 0:
             column_names = [None if c.value is None else six.text_type(c.value) for c in row]
             continue

examples/test_skip_lines.xls

@@ -59,6 +59,13 @@ def test_sheet_index(self):
         self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
         self.assertRows(table, [r.values() for r in self.table.rows])
 
+    def test_skip_lines(self):
+        table = agate.Table.from_xls('examples/test_skip_lines.xls', skip_lines=3)
+
+        self.assertColumnNames(table, self.column_names)
+        self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
+        self.assertRows(table, [r.values() for r in self.table.rows])
+
     def test_zeros(self):
         table = agate.Table.from_xls('examples/test_zeros.xls')
 

examples/test_skip_lines.xlsx

@@ -59,6 +59,13 @@ def test_sheet_index(self):
         self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
         self.assertRows(table, [r.values() for r in self.table.rows])
 
+    def test_skip_lines(self):
+        table = agate.Table.from_xlsx('examples/test_skip_lines.xlsx', skip_lines=3)
+
+        self.assertColumnNames(table, self.column_names)
+        self.assertColumnTypes(table, [agate.Number, agate.Text, agate.Boolean, agate.Date, agate.DateTime])
+        self.assertRows(table, [r.values() for r in self.table.rows])
+
     def test_ambiguous_date(self):
         table = agate.Table.from_xlsx('examples/test_ambiguous_date.xlsx')