✨ support skip_hidden_row_and_column

Author: chfw

.moban.d/README.rst

@@ -3,5 +3,10 @@
 {%block description%}
 **pyexcel-xlsx** is a tiny wrapper library to read, manipulate and write data in xlsx and xlsm fromat using openpyxl. You are likely to use it with `pyexcel <https://github.com/pyexcel/pyexcel>`__.
 
-Please note that `auto_detect_int` flag will not take effect because openpyxl detect integer in python 3 by default.
+Please note:
+
+1. `auto_detect_int` flag will not take effect because openpyxl detect integer in python 3 by default.
+2. `skip_hidden_row_and_column` will slow down the read operation.
+
+
 {%endblock%}

pyexcel_xlsx/xlsxr.py

@@ -29,7 +29,8 @@ def row_iterator(self):
 
         http://openpyxl.readthedocs.io/en/default/optimized.html
         """
-        return self._native_sheet.rows
+        for row in self._native_sheet.rows:
+            yield row
 
     def column_iterator(self, row):
         """
@@ -39,6 +40,28 @@ def column_iterator(self, row):
             yield cell.value
 
 
+class SlowSheet(XLSXSheet):
+    """
+    This sheet will be slower because it does not use readonly sheet
+    """
+    def row_iterator(self):
+        """
+        skip hidden rows
+        """
+        for row_index, row in enumerate(self._native_sheet.rows, 1):
+            if self._native_sheet.row_dimensions[row_index].hidden is False:
+                yield row
+
+    def column_iterator(self, row):
+        """
+        skip hidden columns
+        """
+        for column_index, cell in enumerate(row, 1):
+            letter = openpyxl.utils.get_column_letter(column_index)
+            if self._native_sheet.column_dimensions[letter].hidden is False:
+                yield cell.value
+
+
 class XLSXBook(BookReader):
     """
     Open xlsx as read only mode
@@ -80,13 +103,20 @@ def read_all(self):
         return result
 
     def read_sheet(self, native_sheet):
-        sheet = XLSXSheet(native_sheet, **self._keywords)
+        if self._keywords.get('skip_hidden_row_and_column', False) is True:
+            sheet = SlowSheet(native_sheet, **self._keywords)
+        else:
+            sheet = XLSXSheet(native_sheet, **self._keywords)
         return {sheet.name: sheet.to_array()}
 
     def close(self):
         self._native_book.close()
         self._native_book = None
 
     def _load_the_excel_file(self, file_alike_object):
+        read_only_flag = True
+        if self._keywords.get('skip_hidden_row_and_column', False) is True:
+            read_only_flag = False
         self._native_book = openpyxl.load_workbook(
-            filename=file_alike_object, data_only=True, read_only=True)
+            filename=file_alike_object, data_only=True,
+            read_only=read_only_flag)

tests/fixtures/hidden.xlsx

@@ -0,0 +1,10 @@
+import os
+from nose.tools import eq_
+from pyexcel_xls import get_data
+
+
+def test_hidden_row():
+    data = get_data(os.path.join("tests", "fixtures", "hidden.xlsx"),
+                    skip_hidden_row_and_column=True)
+    expected = [[1, 2], [7, 9]]
+    eq_(data['Sheet1'], expected)