Changed version, added readme file, modified the tests and included a…

… fixture, date supports different formats

README.rst

@@ -0,0 +1,31 @@
+python-xlsx
+===========
+
+A small footprint xslx reader that understands shared strings and can process
+excel dates.
+
+Usage
++++++++
+
+::
+
+    book = Workbook('filename or filedescriptor') #Open xlsx file
+    for sheet in book:
+        print sheet.name
+        for row, cells in sheet.rows().iteritems(): # or sheet.cols()
+            print row # prints row number
+            for cell in cells:
+                print cell.id, cell.value, cell.formula
+
+    # or you can access the sheets by their name:
+
+    some_sheet = book['some sheet name']
+    ...
+
+Alternatives
+------------
+
+To my knowledge there are other python alternatives:
+
+ * https://bitbucket.org/ericgazoni/openpyxl/
+ * https://github.com/leegao/pyXLSX

setup.py

@@ -1,9 +1,10 @@
 from distutils.core import setup
 
 setup(
-    version="0.1",
+    version="0.2",
     name='python-xlsx',
-    description="Tiny python code for parsing data from Microsoft's Office Open XML Spreadsheet format",
+    description="""Tiny python code for parsing data from Microsoft's Office
+    Open XML Spreadsheet format""",
     long_description="",
     classifiers=[
         'Development Status :: 3 - Alpha',

xlsx/__init__.py

@@ -8,15 +8,16 @@
 from xml.dom import minidom
 
 class DomZip(object):
+
     def __init__(self, filename):
-        self.filename = filename
+        self.ziphandle = zipfile.ZipFile(filename, 'r')
 
     def __getitem__(self, key):
         # @type ziphandle ZipFile
-        ziphandle = zipfile.ZipFile(self.filename)
-        dom = minidom.parseString(ziphandle.read(key))
-        ziphandle.close()
-        return dom
+        return minidom.parseString(self.ziphandle.read(key))
+
+    def __del__(self):
+        self.ziphandle.close()
 
 class Workbook(object):
 
@@ -54,6 +55,7 @@ def __getitem__(self, key):
             return self.__sheetsByName[key]
 
 class SharedStrings(list):
+
     def __init__(self, sharedStringsDom):
         nodes = sharedStringsDom.firstChild.childNodes
         for text in [n.firstChild.firstChild for n in nodes]:
@@ -85,17 +87,17 @@ def __load(self):
         rows = {}
         columns = {}
         for rowNode in sheetData.childNodes:
-            rowNum = rowNode.getAttribute("r")
+            rowNum = int(rowNode.getAttribute("r"))
             for columnNode in rowNode.childNodes:
                 colType = columnNode.getAttribute("t")
                 cellId = columnNode.getAttribute("r")
                 cellS = columnNode.getAttribute("s")
-                colNum = cellId[:len(cellId)-len(rowNum)]
+                colNum = cellId[:len(cellId)-len(str(rowNum))]
                 formula = None
                 if colType == "s":
                     stringIndex = columnNode.firstChild.firstChild.nodeValue
                     data = self.workbook.sharedStrings[int(stringIndex)]
-                elif cellS == '1' and colType == "n": #Date field
+                elif cellS in ('1', '2', '3', '4') and colType == "n": #Date field
                     data = xldate_as_tuple(int(columnNode.firstChild.firstChild.nodeValue), datemode=0)
                 elif columnNode.firstChild:
                     data = getattr(columnNode.getElementsByTagName("v")[0].firstChild, "nodeValue", None)

xlsx/tests/test_basic.py

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+import os
+import unittest
+
+from xlsx import Workbook
+
+class WorkbookTestCase(unittest.TestCase):
+
+    def setUp(self):
+        """ Getting all file from fixtures dir """
+        self.workbooks = {}
+        fixtures_dir = os.path.abspath(os.path.join(os.path.dirname(__file__),
+                                                    'fixtures'))
+        xlsx_files = os.listdir(fixtures_dir)
+        for filename in xlsx_files:
+            self.workbooks[filename] = Workbook(
+                os.path.join(fixtures_dir, filename))
+
+    def test_basic(self):
+        """ These test will run for all test files """
+
+        for filename, workbook in self.workbooks.items():
+            for sheet in workbook:
+                assert hasattr(sheet, 'id')
+                assert isinstance(sheet.name, basestring)
+                assert isinstance(sheet.rows(), dict)
+                assert isinstance(sheet.cols(), dict)
+
+                for row_num, cells in sheet.rows().iteritems():
+                    assert isinstance(row_num, int)
+                    assert isinstance(cells, list)
+                    for cell in cells:
+                        assert hasattr(cell, 'id')
+                        assert hasattr(cell, 'column')
+                        assert hasattr(cell, 'row')
+                        assert hasattr(cell, 'value')
+                        assert cell.row == row_num
+
+    def test_test1(self):
+        """ Specific test for `testdata/test1.xslx` file including
+        unicode strings and different date formats
+        """
+        workbook = self.workbooks['test1.xlsx']
+
+        self.assertEqual(unicode(workbook[1].name), u'рускии')
+        self.assertEqual(unicode(workbook[2].name), u'性 文化交流 例如')
+        self.assertEqual(unicode(workbook[3].name), u'تعد. بحق طائ')
+
+        for row_num, cells in workbook[1].rows().iteritems():
+            if row_num == 1:
+                self.assertEqual(unicode(cells[0].value), u'лорем ипсум')
+                self.assertEqual(unicode(cells[1].value), u'2')
+            if row_num == 2: #Test date fields
+                self.assertEqual(cells[0].value, (2010, 11, 12, 0, 0, 0))
+                self.assertEqual(cells[1].value, (1987, 12, 20, 0, 0, 0))
+                self.assertEqual(cells[2].value, (1987, 12, 20, 0, 0, 0))
+                self.assertEqual(cells[3].value, (1987, 12, 20, 0, 0, 0))
+                break
+
+        # Cell A1 in u'性 文化交流 例如'
+        self.assertEqual(unicode(workbook[2].cols()['A'][0].value),
+                         u'性 文化交流 例如')
+        self.assertEqual(unicode(workbook[2].cols()['A'][1].value),
+                         u'エム セシビ め「こを バジョン')
+
+
+if __name__ == '__main__':
+    unittest.main()