Merge branch 'excel_parse_utils' of https://github.com/cancan101/pandas…

… into cancan101-excel_parse_utils Conflicts: doc/source/release.rst
pandas-dev · Aug 26, 2013 · 516f802 · 516f802
2 parents f2a7b9c + 9fcd30b
commit 516f802
Show file tree

Hide file tree

Showing 4 changed files with 47 additions and 14 deletions.
diff --git a/doc/source/release.rst b/doc/source/release.rst
@@ -121,6 +121,7 @@ pandas 0.13
       now returns a ``MultiIndex`` rather than an ``Index``. (:issue:`4039`)
 
   - Infer and downcast dtype if ``downcast='infer'`` is passed to ``fillna/ffill/bfill`` (:issue:`4604`)
+  - Factored out excel_value_to_python_value from ExcelFile::_parse_excel (:issue:`4589`)
 
 **Internal Refactoring**
 

diff --git a/pandas/io/excel.py b/pandas/io/excel.py
@@ -53,6 +53,23 @@ def read_excel(path_or_buf, sheetname, kind=None, **kwds):
     return ExcelFile(path_or_buf, kind=kind).parse(sheetname=sheetname,
                                                    kind=kind, **kwds)
 
+def excel_value_to_python_value(value, typ, datemode):
+    from xlrd import (xldate_as_tuple, XL_CELL_DATE,
+                      XL_CELL_ERROR, XL_CELL_BOOLEAN)
+
+    if typ == XL_CELL_DATE:
+        dt = xldate_as_tuple(value, datemode)
+        # how to produce this first case?
+        if dt[0] < datetime.MINYEAR:  # pragma: no cover
+            value = datetime.time(*dt[3:])
+        else:
+            value = datetime.datetime(*dt)
+    elif typ == XL_CELL_ERROR:
+        value = np.nan
+    elif typ == XL_CELL_BOOLEAN:
+        value = bool(value)
+
+    return value
 
 class ExcelFile(object):
     """
@@ -174,8 +191,6 @@ def _parse_excel(self, sheetname, header=0, skiprows=None, skip_footer=0,
                      index_col=None, has_index_names=None, parse_cols=None,
                      parse_dates=False, date_parser=None, na_values=None,
                      thousands=None, chunksize=None, **kwds):
-        from xlrd import (xldate_as_tuple, XL_CELL_DATE,
-                          XL_CELL_ERROR, XL_CELL_BOOLEAN)
 
         datemode = self.book.datemode
         if isinstance(sheetname, compat.string_types):
@@ -193,17 +208,7 @@ def _parse_excel(self, sheetname, header=0, skiprows=None, skip_footer=0,
                     should_parse[j] = self._should_parse(j, parse_cols)
 
                 if parse_cols is None or should_parse[j]:
-                    if typ == XL_CELL_DATE:
-                        dt = xldate_as_tuple(value, datemode)
-                        # how to produce this first case?
-                        if dt[0] < datetime.MINYEAR:  # pragma: no cover
-                            value = datetime.time(*dt[3:])
-                        else:
-                            value = datetime.datetime(*dt)
-                    elif typ == XL_CELL_ERROR:
-                        value = np.nan
-                    elif typ == XL_CELL_BOOLEAN:
-                        value = bool(value)
+                    value = excel_value_to_python_value(value=value, typ=typ, datemode=datemode)
                     row.append(value)
 
             data.append(row)

diff --git a/pandas/io/tests/data/types.xls b/pandas/io/tests/data/types.xls
diff --git a/pandas/io/tests/test_excel.py b/pandas/io/tests/test_excel.py
@@ -18,7 +18,8 @@
 import pandas.io.parsers as parsers
 from pandas.io.parsers import (read_csv, read_table, read_fwf,
                                 TextParser, TextFileReader)
-from pandas.io.excel import ExcelFile, ExcelWriter, read_excel
+from pandas.io.excel import (ExcelFile, ExcelWriter, read_excel,
+                             excel_value_to_python_value)
 from pandas.util.testing import (assert_almost_equal,
                                  assert_series_equal,
                                  network,
@@ -260,6 +261,32 @@ def test_excel_table(self):
         tm.assert_frame_equal(df4, df.ix[:-1])
         tm.assert_frame_equal(df4, df5)
 
+    def test_excel_value_to_python_value(self):
+        _skip_if_no_xlrd()
+
+        pth = os.path.join(self.dirpath, 'types.xls')
+        xls = ExcelFile(pth)
+        book = xls.book
+        sheet = book.sheet_by_index(0)
+
+        cell = sheet.cell(0, 0)
+        self.assertEquals(excel_value_to_python_value(value=cell.value, typ=cell.ctype, datemode=book.datemode), 'date')
+
+        cell = sheet.cell(0, 1)
+        self.assertEquals(excel_value_to_python_value(value=cell.value, typ=cell.ctype, datemode=book.datemode), datetime(year=2013, month=4, day=1))
+
+        cell = sheet.cell(1, 1)
+        self.assertEquals(excel_value_to_python_value(value=cell.value, typ=cell.ctype, datemode=book.datemode), True)
+
+        cell = sheet.cell(2, 1)
+        self.assertEquals(excel_value_to_python_value(value=cell.value, typ=cell.ctype, datemode=book.datemode), 1)
+
+        cell = sheet.cell(3, 1)
+        self.assertEquals(excel_value_to_python_value(value=cell.value, typ=cell.ctype, datemode=book.datemode), 1.1)
+
+        cell = sheet.cell(4, 1)
+        self.assertIs(excel_value_to_python_value(value=cell.value, typ=cell.ctype, datemode=book.datemode), np.nan) #We need to use is here because value is NaN
+
     def test_excel_read_buffer(self):
         _skip_if_no_xlrd()
         _skip_if_no_openpyxl()