fix #4: ignore potentially trailing none valued cells

pyexcel · Oct 9, 2015 · 00973b4 · 00973b4
1 parent fb8ba36
commit 00973b4
Show file tree

Hide file tree

Showing 4 changed files with 38 additions and 20 deletions.
diff --git a/doc/source/index.rst b/doc/source/index.rst
@@ -57,15 +57,20 @@ For individual excel file formats, please install them as you wish:
 .. _a-map-of-plugins-and-file-formats:
 .. table:: a map of plugins and supported excel file formats
 
-   ============== ======================================= ============= ========================   
-   Package name   Supported file formats                  Dependencies  Python versions           
-   ============== ======================================= ============= ========================   
-   `pyexcel-io`_  csv, csvz [#f1]_, tsv, tsvz [#f2]_                    2.6, 2.7, 3.3, 3.4, pypy  
-   `xls`_         xls, xlsx(read only), xlsm(read only)   xlrd, xlwt    2.6, 2.7, 3.3, 3.4, pypy
-   `xlsx`_        xlsx                                    openpyxl      2.6, 2.7, 3.3, 3.4, pypy   
-   `ods3`_        ods                                     ezodf, lxml   2.6, 2.7, 3.3, 3.4                 
-   `ods`_         ods (python 2.6, 2.7)                   odfpy         2.6, 2.7                
-   ============== ======================================= ============= ========================
+   ============== ======================= ============= ==================   
+   Package name   Supported file formats  Dependencies  Python versions     
+   ============== ======================= ============= ==================   
+   `pyexcel-io`_  csv, csvz [#f1]_, tsv,                2.6, 2.7, 3.3, 
+                                                        3.4, pypy  
+                  tsvz [#f2]_
+   `xls`_         xls, xlsx(read only),   xlrd, xlwt    2.6, 2.7, 3.3,
+                                                        3.4, pypy
+                  xlsm(read only)
+   `xlsx`_        xlsx                    openpyxl      2.6, 2.7, 3.3,
+                                                        3.4, pypy   
+   `ods3`_        ods                     ezodf, lxml   2.6, 2.7, 3.3, 3.4
+   `ods`_         ods (python 2.6, 2.7)   odfpy         2.6, 2.7          
+   ============== ======================= ============= ==================
 
 Please import them before you start to access the desired file formats::
 
@@ -78,6 +83,8 @@ After that, you can start get and save data in the loaded format.
     ============= =========== ============ ============ ============
     `pyexcel-io`_ `xls`_      `xlsx`_      `ods`_       `ods3`_        
     ============= =========== ============ ============ ============
+    0.0.7         0.0.7       0.0.6        0.0.6+       0.0.8       
+    0.0.6         0.0.7       0.0.6        0.0.6+       0.0.8       
     0.0.5         0.0.7       0.0.6        0.0.6+       0.0.8       
     0.0.4         0.0.7       0.0.6        0.0.6        0.0.8       
     0.0.3         0.0.6       0.0.5        0.0.5        0.0.7       

diff --git a/doc/source/plaincsv.rst b/doc/source/plaincsv.rst
@@ -1,6 +1,19 @@
 Working with CSV format
 ================================================================================
 
+Please note that csv reader load data in a lazy manner. It ignores excessive
+trailing cells that has None value. For example, the following csv content::
+
+    1,2,,,,,
+    3,4,,,,,
+    5,,,,,,,
+
+would end up as::
+
+    1,2
+    3,4
+    5,
+
 Write to a csv file
 --------------------------------------------------------------------------------
 

diff --git a/pyexcel_io/csvbook.py b/pyexcel_io/csvbook.py
@@ -61,19 +61,17 @@ def get_file_handle(self):
 
     def to_array(self):
         reader = csv.reader(self.get_file_handle(), **self.keywords)
-        longest_row_length = -1
         array = []
         for row in reader:
             myrow = []
+            tmp_row = []
             for element in row:
                 if PY2:
-                    myrow.append(element.decode(self.encoding))
-                else:
-                    myrow.append(element)
-            if longest_row_length == -1:
-                longest_row_length = len(myrow)
-            elif longest_row_length < len(myrow):
-                longest_row_length = len(myrow)
+                    element = element.decode(self.encoding)
+                tmp_row.append(element)
+                if element is not None and element != '':
+                    myrow += tmp_row
+                    tmp_row = []
             array.append(myrow)
         return array
 

diff --git a/tests/test_csv_book.py b/tests/test_csv_book.py
@@ -284,8 +284,8 @@ def setUp(self):
         self.test_file = "csv_book." + self.file_type
         self.data = [
             ["1"],
-            ["4", "5", "6"],
-            ["7"]
+            ["4", "5", "6", "", ""],
+            ["", "7"]
         ]
         with open(self.test_file, 'w') as f:
             for row in self.data:
@@ -297,7 +297,7 @@ def test_sheet_file_reader(self):
         assert result == [
             ["1"],
             ["4", "5", "6"],
-            ["7"]
+            ["", "7"]
         ]
 
     def tearDown(self):