implementation of pyexcel-io v0.2.2 paginantion support. the answer to big size csv

pyexcel_xls/xls.py

@@ -104,7 +104,16 @@ class XLSheet(SheetReader):
         for row in range(0, self.number_of_rows()):
             return_row = []
             tmp_row = []
+            if self.skip_row(row, self.start_row, self.row_limit):
+                continue
+
             for column in range(0, self.number_of_columns()):
+                skip_column = self.skip_column(column,
+                                               self.start_column,
+                                               self.column_limit)
+                if skip_column:
+                    continue
+
                 cell_value = self.cell_value(row, column)
                 tmp_row.append(cell_value)
                 if cell_value is not None and cell_value != '':

tests/base.py

@@ -107,7 +107,7 @@ class PyexcelMultipleSheetBase:
         for s in b:
             data = pyexcel.utils.to_array(s)
             assert self.content[s.name] == data
-        si = pyexcel.iterators.SheetIterator(b)
+        si = pyexcel.sheets.iterators.SheetIterator(b)
         for s in si:
             data = pyexcel.utils.to_array(s)
             assert self.content[s.name] == data

tests/test_filter.py

@@ -0,0 +1,63 @@
+import os
+
+from pyexcel_io import get_data, save_data
+from nose.tools import eq_
+
+
+class TestFilter:
+    def setUp(self):
+        self.test_file = "test_filter.xlsx"
+        sample = [
+            [1, 21, 31],
+            [2, 22, 32],
+            [3, 23, 33],
+            [4, 24, 34],
+            [5, 25, 35],
+            [6, 26, 36]
+        ]
+        save_data(self.test_file, sample)
+        self.sheet_name = "pyexcel_sheet1"
+
+    def test_filter_row(self):
+        filtered_data = get_data(self.test_file, start_row=3,
+                                 library="pyexcel-xls")
+        expected = [[4, 24, 34], [5, 25, 35], [6, 26, 36]]
+        eq_(filtered_data[self.sheet_name], expected)
+
+    def test_filter_row_2(self):
+        filtered_data = get_data(self.test_file, start_row=3, row_limit=1,
+                                 library="pyexcel-xls")
+        expected = [[4, 24, 34]]
+        eq_(filtered_data[self.sheet_name], expected)
+
+    def test_filter_column(self):
+        filtered_data = get_data(self.test_file, start_column=1,
+                                 library="pyexcel-xls")
+        expected = [[21, 31], [22, 32], [23, 33],
+                    [24, 34], [25, 35], [26, 36]]
+        eq_(filtered_data[self.sheet_name], expected)
+
+    def test_filter_column_2(self):
+        filtered_data = get_data(self.test_file,
+                                 start_column=1, column_limit=1,
+                                 library="pyexcel-xls")
+        expected = [[21], [22], [23], [24], [25], [26]]
+        eq_(filtered_data[self.sheet_name], expected)
+
+    def test_filter_both_ways(self):
+        filtered_data = get_data(self.test_file,
+                                 start_column=1, start_row=3,
+                                 library="pyexcel-xls")
+        expected = [[24, 34], [25, 35], [26, 36]]
+        eq_(filtered_data[self.sheet_name], expected)
+
+    def test_filter_both_ways_2(self):
+        filtered_data = get_data(self.test_file,
+                                 start_column=1, column_limit=1,
+                                 start_row=3, row_limit=1,
+                                 library="pyexcel-xls")
+        expected = [[24]]
+        eq_(filtered_data[self.sheet_name], expected)
+
+    def tearDown(self):
+        os.unlink(self.test_file)