upstreaming the fix from v0.3.3

Author: chfw

.travis.yml

@@ -3,13 +3,13 @@ language: python
 notifications:
   email: false
 python:
+  - pypy
   - 3.6
   - 3.5
   - 3.4
   - 3.3
   - 2.7
   - 2.6
-  - pypy
 matrix:
   include:
     - python: 2.7

CHANGELOG.rst

@@ -7,11 +7,29 @@ Change log
 Updated
 ********************************************************************************
 
-#. `#15 <https://github.com/pyexcel/pyexcel-xlsx/issues/15>`_, close file
-   handle
+#. `#15 <https://github.com/pyexcel/pyexcel-xlsx/issues/15>`_, close file handle
 #. pyexcel-io plugin interface now updated to use
    `lml <https://github.com/chfw/lml>`_.
 
+0.3.3 - 30/05/2017
+--------------------------------------------------------------------------------
+
+Updated
+********************************************************************************
+
+#. `#18 <https://github.com/pyexcel/pyexcel-xls/issues/18>`_, pass on
+   encoding_override and others to xlrd.
+
+0.3.2 - 18.05.2017
+--------------------------------------------------------------------------------
+
+Updated
+********************************************************************************
+
+#. `#16 <https://github.com/pyexcel/pyexcel-xls/issues/16>`_, allow mmap to
+   be passed as file content
+
+
 0.3.1 - 16.01.2017
 --------------------------------------------------------------------------------
 

docs/source/conf.py

@@ -12,7 +12,7 @@
 ]
 
 intersphinx_mapping = {
-    'pyexcel': ('http://pyexcel.readthedocs.org/en/latest/', None)
+    'pyexcel': ('http://pyexcel.readthedocs.org/en/latest/', None),
 }
 spelling_word_list_filename = 'spelling_wordlist.txt'
 templates_path = ['_templates']
@@ -21,7 +21,7 @@
 
 project = u'pyexcel-xls'
 copyright = u'2015-2017 Onni Software Ltd.'
-version = '0.3.1'
+version = '0.3.3'
 release = '0.4.0'
 exclude_patterns = []
 pygments_style = 'sphinx'

pyexcel_xls.yaml

@@ -2,7 +2,7 @@ overrides: "pyexcel.yaml"
 name: "pyexcel-xls"
 nick_name: xls
 version: 0.4.0
-release: 0.3.1
+release: 0.3.3
 file_type: xls
 dependencies:
   - pyexcel-io>=0.3.0

pyexcel_xls/xlsr.py

@@ -22,6 +22,13 @@
     from collections import OrderedDict
 
 
+XLS_KEYWORDS = [
+    'filename', 'logfile', 'verbosity', 'use_mmap',
+    'file_contents', 'encoding_override', 'formatting_info',
+    'on_demand', 'ragged_rows'
+]
+
+
 class XLSheet(SheetReader):
     """
     xls, xlsx, xlsm sheet reader
@@ -118,30 +125,34 @@ def read_sheet(self, native_sheet):
         return {sheet.name: sheet.to_array()}
 
     def _get_book(self, on_demand=False):
+        xlrd_params = self._extract_xlrd_params()
+        xlrd_params['on_demand'] = on_demand
+
         if self._file_name:
-            xls_book = xlrd.open_workbook(self._file_name, on_demand=on_demand)
+            xlrd_params['filename'] = self._file_name
         elif self._file_stream:
             self._file_stream.seek(0)
             file_content = self._file_stream.read()
-            xls_book = xlrd.open_workbook(
-                None,
-                file_contents=file_content,
-                on_demand=on_demand
-            )
+            xlrd_params['file_contents'] = file_content
         elif self._file_content is not None:
-            xls_book = xlrd.open_workbook(
-                None,
-                file_contents=self._file_content,
-                on_demand=on_demand
-            )
+            xlrd_params['file_contents'] = self._file_content
         else:
             raise IOError("No valid file name or file content found.")
+        xls_book = xlrd.open_workbook(**xlrd_params)
         return xls_book
 
     def _get_params(self):
         self.skip_hidden_sheets = self._keywords.get(
             'skip_hidden_sheets', True)
 
+    def _extract_xlrd_params(self):
+        params = {}
+        if self._keywords is not None:
+            for key in list(self._keywords.keys()):
+                if key in XLS_KEYWORDS:
+                    params[key] = self._keywords.pop(key)
+        return params
+
 
 def is_integer_ok_for_xl_float(value):
     """check if a float value had zero value in digits"""

tests/requirements.txt

@@ -1,4 +1,5 @@
 nose
+mock;python_version<"3"
 codecov
 coverage
 flake8

tests/test_bug_fixes.py

@@ -10,6 +10,7 @@
 from _compact import OrderedDict
 from nose.tools import eq_, raises
 import datetime
+from mock import patch
 
 
 def test_pyexcel_issue_5():
@@ -68,5 +69,17 @@ def test_issue_16_file_stream_has_no_getvalue():
         pe.get_sheet(file_stream=f, file_type='xls')
 
 
+@patch('xlrd.open_workbook')
+def test_issue_18_encoding_override_isnt_passed(fake_open):
+    fake_open.return_value = None
+    test_encoding = 'utf-32'
+    from pyexcel_xls.xlsr import XLSBook
+    book = XLSBook()
+    book.open('fake_file.xls', encoding_override=test_encoding)
+    book._get_book()
+    keywords = fake_open.call_args[1]
+    assert keywords['encoding_override'] == test_encoding
+
+
 def get_fixture(file_name):
     return os.path.join("tests", "fixtures", file_name)

tests/test_writer.py

@@ -19,10 +19,10 @@ def test_write_book(self):
         reader = Reader()
         reader.open(self.testfile)
         content = reader.read_all()
-        reader.close()
         for key in content.keys():
             content[key] = list(content[key])
         assert content == self.content
+        reader.close()
 
     def tearDown(self):
         if os.path.exists(self.testfile):