✨ detect merged cells, resolve #25

.moban.d/README.rst

@@ -6,6 +6,8 @@
 {%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>`_.
 
+:fire: New flag: `detect_merged_cells` allows you to spread the same value among all merged cells. But be aware that this may slow down its reading performance.
+
 New flag: `skip_hidden_row_and_column` allows you to skip hidden rows and columns and is defaulted to **True**. It may slow down its reading performance. And it is only valid for 'xls' files. For 'xlsx' files, please use pyexcel-xlsx.
 
 {%endblock%}

CHANGELOG.rst

@@ -1,6 +1,15 @@
 Change log
 ================================================================================
 
+0.5.5 - unreleased
+--------------------------------------------------------------------------------
+
+Added
+********************************************************************************
+
+#. `#25 <https://github.com/pyexcel/pyexcel-xls/issues/25>`_, detect merged
+   cell in .xls
+
 0.5.4 - 2.11.2017
 --------------------------------------------------------------------------------
 

README.rst

@@ -17,6 +17,8 @@ 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>`_.
 
+:fire: New flag: `detect_merged_cells` allows you to spread the same value among all merged cells. But be aware that this may slow down its reading performance.
+
 New flag: `skip_hidden_row_and_column` allows you to skip hidden rows and columns and is defaulted to **True**. It may slow down its reading performance. And it is only valid for 'xls' files. For 'xlsx' files, please use pyexcel-xlsx.
 
 

pyexcel_xls.yaml

@@ -1,8 +1,8 @@
 overrides: "pyexcel.yaml"
 name: "pyexcel-xls"
 nick_name: xls
-version: 0.5.4
-current_version: 0.5.4
+version: 0.5.5
+current_version: 0.5.5
 release: 0.5.4
 file_type: xls
 dependencies:

pyexcel_xls/xlsr.py

@@ -12,7 +12,7 @@
 
 from pyexcel_io.book import BookReader
 from pyexcel_io.sheet import SheetReader
-from pyexcel_io._compact import OrderedDict
+from pyexcel_io._compact import OrderedDict, irange
 from pyexcel_io.service import has_no_digits_in_float
 
 
@@ -23,6 +23,21 @@
 ]
 
 
+class MergedCell(object):
+    def __init__(self, row_low, row_high, column_low, column_high):
+        self.__rl = row_low
+        self.__rh = row_high
+        self.__cl = column_low
+        self.__ch = column_high
+        self.value = None
+
+    def register_cells(self, registry):
+        for rowx in irange(self.__rl, self.__rh):
+            for colx in irange(self.__cl, self.__ch):
+                key = "%s-%s" % (rowx, colx)
+                registry[key] = self
+
+
 class XLSheet(SheetReader):
     """
     xls, xlsx, xlsm sheet reader
@@ -34,6 +49,11 @@ def __init__(self, sheet, auto_detect_int=True, **keywords):
         self.__auto_detect_int = auto_detect_int
         self.__hidden_cols = []
         self.__hidden_rows = []
+        self.__merged_cells = {}
+        if keywords.get('detect_merged_cells') is True:
+            for merged_cell_ranges in sheet.merged_cells:
+                merged_cells = MergedCell(*merged_cell_ranges)
+                merged_cells.register_cells(self.__merged_cells)
         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:
@@ -62,14 +82,23 @@ def cell_value(self, row, column):
         """
         Random access to the xls cells
         """
-        row, column = self._offset_hidden_indices(row, column)
+        if self._keywords.get('skip_hidden_row_and_column') is True:
+            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:
             value = xldate_to_python_date(value)
         elif cell_type == xlrd.XL_CELL_NUMBER and self.__auto_detect_int:
             if has_no_digits_in_float(value):
                 value = int(value)
+        if self.__merged_cells:
+            merged_cell = self.__merged_cells.get("%s-%s" % (row, column))
+            if merged_cell:
+                if merged_cell.value:
+                    value = merged_cell.value
+                else:
+                    merged_cell.value = value
         return value
 
     def _offset_hidden_indices(self, row, column):
@@ -97,6 +126,7 @@ def __init__(self):
         self._file_content = None
         self.__skip_hidden_sheets = True
         self.__skip_hidden_row_column = True
+        self.__detect_merged_cells = False
 
     def open(self, file_name, **keywords):
         self.__parse_keywords(**keywords)
@@ -115,6 +145,7 @@ 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)
+        self.__detect_merged_cells = keywords.get('detect_merged_cells', False)
 
     def close(self):
         if self._native_book:
@@ -163,6 +194,8 @@ def _get_book(self, on_demand=False):
             raise IOError("No valid file name or file content found.")
         if self.__skip_hidden_row_column and self._file_type == 'xls':
             xlrd_params['formatting_info'] = True
+        if self.__detect_merged_cells:
+            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 = '0.5.4'
+VERSION = '0.5.5'
 EMAIL = 'wangc_2011@hotmail.com'
 LICENSE = 'New BSD'
 DESCRIPTION = (

tests/test_merged_cells.py

@@ -0,0 +1,11 @@
+import os
+from pyexcel_xls import get_data
+from nose.tools import eq_
+
+
+def test_merged_cells():
+    data = get_data(os.path.join("tests", "fixtures", "merged-cell-sheet.xls"),
+                    detect_merged_cells=True,
+                    library="pyexcel-xls")
+    expected = [[1, 2, 3], [1, 5, 6], [1, 8, 9], [10, 11, 11]]
+    eq_(data['Sheet1'], expected)