release 0.5.3 🥚 🎡, skip hidden rows and columns

Author: chfw

.moban.d/README.rst

@@ -5,6 +5,9 @@
 
 {%block description%}
 **pyexcel-{{file_type}}** is a tiny wrapper library to read, manipulate and write data in {{file_type}} format and it can read xlsx and xlsm fromat. You are likely to use it with `pyexcel <https://github.com/pyexcel/pyexcel>`_.
+
+New flag: `skip_hidden_row_and_column=True` allow you to skip hidden rows and columns. It may slow down its reading performance.
+
 {%endblock%}
 
 {%block extras %}

CHANGELOG.rst

@@ -1,6 +1,15 @@
 Change log
 ================================================================================
 
+0.5.3 - 2.11.2017
+--------------------------------------------------------------------------------
+
+Added
+********************************************************************************
+
+#. `#21 <https://github.com/pyexcel/pyexcel-xls/issues/21>`_, skip hidden rows
+   and columns under 'skip_hidden_row_and_column' flag.
+
 0.5.2 - 23.10.2017
 --------------------------------------------------------------------------------
 
@@ -19,6 +28,8 @@ added
 
 #. `#103 <https://github.com/pyexcel/pyexcel/issues/103>`_, include LICENSE file
    in MANIFEST.in, meaning LICENSE file will appear in the released tar ball.
+=======
+
 
 0.5.0 - 30.08.2017
 --------------------------------------------------------------------------------

README.rst

@@ -17,6 +17,9 @@ pyexcel-xls - Let you focus on data, instead of xls format
 
 **pyexcel-xls** is a tiny wrapper library to read, manipulate and write data in xls format and it can read xlsx and xlsm fromat. You are likely to use it with `pyexcel <https://github.com/pyexcel/pyexcel>`_.
 
+New flag: `skip_hidden_row_and_column=True` allow you to skip hidden rows and columns. It may slow down its reading performance.
+
+
 Known constraints
 ==================
 

docs/source/conf.py

@@ -21,8 +21,8 @@
 
 project = u'pyexcel-xls'
 copyright = u'2015-2017 Onni Software Ltd.'
-version = '0.5.2'
-release = '0.5.2'
+version = '0.5.3'
+release = '0.5.3'
 exclude_patterns = []
 pygments_style = 'sphinx'
 html_theme = 'default'

pyexcel_xls.yaml

@@ -1,9 +1,9 @@
 overrides: "pyexcel.yaml"
 name: "pyexcel-xls"
 nick_name: xls
-version: 0.5.2
-current_version: 0.5.2
-release: 0.5.2
+version: 0.5.3
+current_version: 0.5.3
+release: 0.5.3
 file_type: xls
 dependencies:
   - pyexcel-io>=0.5.3

pyexcel_xls/xlsr.py

@@ -32,6 +32,15 @@ class XLSheet(SheetReader):
     def __init__(self, sheet, auto_detect_int=True, **keywords):
         SheetReader.__init__(self, sheet, **keywords)
         self.__auto_detect_int = auto_detect_int
+        self.__hidden_cols = []
+        self.__hidden_rows = []
+        if keywords.get('skip_hidden_row_and_column') is True:
+            for col_index, info in self._native_sheet.colinfo_map.items():
+                if info.hidden == 1:
+                    self.__hidden_cols.append(col_index)
+            for row_index, info in self._native_sheet.rowinfo_map.items():
+                if info.hidden == 1:
+                    self.__hidden_rows.append(row_index)
 
     @property
     def name(self):
@@ -41,18 +50,19 @@ def number_of_rows(self):
         """
         Number of rows in the xls sheet
         """
-        return self._native_sheet.nrows
+        return self._native_sheet.nrows - len(self.__hidden_rows)
 
     def number_of_columns(self):
         """
         Number of columns in the xls sheet
         """
-        return self._native_sheet.ncols
+        return self._native_sheet.ncols - len(self.__hidden_cols)
 
     def cell_value(self, row, column):
         """
         Random access to the xls cells
         """
+        row, column = self._offset_hidden_indices(row, column)
         cell_type = self._native_sheet.cell_type(row, column)
         value = self._native_sheet.cell_value(row, column)
         if cell_type == xlrd.XL_CELL_DATE:
@@ -62,6 +72,19 @@ def cell_value(self, row, column):
                 value = int(value)
         return value
 
+    def _offset_hidden_indices(self, row, column):
+        row = calculate_offsets(row, self.__hidden_rows)
+        column = calculate_offsets(column, self.__hidden_cols)
+        return row, column
+
+
+def calculate_offsets(incoming_index, hidden_indices):
+    offset = 0
+    for index in hidden_indices:
+        if index <= (incoming_index + offset):
+            offset += 1
+    return incoming_index + offset
+
 
 class XLSBook(BookReader):
     """
@@ -72,19 +95,26 @@ class XLSBook(BookReader):
     def __init__(self):
         BookReader.__init__(self)
         self._file_content = None
+        self.__skip_hidden_sheets = True
+        self.__skip_hidden_row_column = True
 
-    def open(self, file_name, skip_hidden_sheets=True, **keywords):
+    def open(self, file_name, **keywords):
+        self.__parse_keywords(**keywords)
         BookReader.open(self, file_name, **keywords)
-        self.__skip_hidden_sheets = skip_hidden_sheets
 
-    def open_stream(self, file_stream, skip_hidden_sheets=True, **keywords):
+    def open_stream(self, file_stream, **keywords):
+        self.__parse_keywords(**keywords)
         BookReader.open_stream(self, file_stream, **keywords)
-        self.__skip_hidden_sheets = skip_hidden_sheets
 
-    def open_content(self, file_content, skip_hidden_sheets=True, **keywords):
+    def open_content(self, file_content, **keywords):
+        self.__parse_keywords(**keywords)
         self._keywords = keywords
         self._file_content = file_content
-        self.__skip_hidden_sheets = skip_hidden_sheets
+
+    def __parse_keywords(self, **keywords):
+        self.__skip_hidden_sheets = keywords.get('skip_hidden_sheets', True)
+        self.__skip_hidden_row_column = keywords.get(
+            'skip_hidden_row_and_column', True)
 
     def close(self):
         if self._native_book:
@@ -131,6 +161,8 @@ def _get_book(self, on_demand=False):
             xlrd_params['file_contents'] = self._file_content
         else:
             raise IOError("No valid file name or file content found.")
+        if self.__skip_hidden_row_column:
+            xlrd_params['formatting_info'] = True
         xls_book = xlrd.open_workbook(**xlrd_params)
         return xls_book
 

setup.py

@@ -9,7 +9,7 @@
 
 NAME = 'pyexcel-xls'
 AUTHOR = 'C.W.'
-VERSION = '0.5.2'
+VERSION = '0.5.3'
 EMAIL = 'wangc_2011@hotmail.com'
 LICENSE = 'New BSD'
 DESCRIPTION = (
@@ -18,7 +18,7 @@
     ''
 )
 URL = 'https://github.com/pyexcel/pyexcel-xls'
-DOWNLOAD_URL = '%s/archive/0.5.2.tar.gz' % URL
+DOWNLOAD_URL = '%s/archive/0.5.3.tar.gz' % URL
 FILES = ['README.rst',  'CHANGELOG.rst']
 KEYWORDS = [
     'xls',
@@ -55,11 +55,12 @@
 # You do not need to read beyond this line
 PUBLISH_COMMAND = '{0} setup.py sdist bdist_wheel upload -r pypi'.format(
     sys.executable)
-GS_COMMAND = ('gs pyexcel-xls v0.5.2 ' +
-              "Find 0.5.2 in changelog for more details")
+GS_COMMAND = ('gs pyexcel-xls v0.5.3 ' +
+              "Find 0.5.3 in changelog for more details")
 NO_GS_MESSAGE = ('Automatic github release is disabled. ' +
                  'Please install gease to enable it.')
-UPLOAD_FAILED_MSG = ('Upload failed. please run "%s" yourself.')
+UPLOAD_FAILED_MSG = (
+    'Upload failed. please run "%s" yourself.' % PUBLISH_COMMAND)
 HERE = os.path.abspath(os.path.dirname(__file__))
 
 

tests/fixtures/complex_hidden_sheets.xls

@@ -0,0 +1,18 @@
+import os
+from nose.tools import eq_
+from pyexcel_xls import get_data
+
+
+def test_simple_hidden_sheets():
+    data = get_data(os.path.join("tests", "fixtures", "hidden.xls"),
+                    skip_hidden_row_and_column=True)
+    expected = [[1, 3], [7, 9]]
+    eq_(data['Sheet1'], expected)
+
+
+def test_complex_hidden_sheets():
+    data = get_data(
+        os.path.join("tests", "fixtures", "complex_hidden_sheets.xls"),
+        skip_hidden_row_and_column=True)
+    expected = [[1, 3, 5, 7, 9], [31, 33, 35, 37, 39], [61, 63, 65, 67]]
+    eq_(data['Sheet1'], expected)