xlscsv.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

#  Redistribution and use in source and binary forms, with or without
#  modification, are permitted provided that the following conditions are
#  met:
#  
#  * Redistributions of source code must retain the above copyright
#    notice, this list of conditions and the following disclaimer.
#  * Redistributions in binary form must reproduce the above
#    copyright notice, this list of conditions and the following disclaimer
#    in the documentation and/or other materials provided with the
#    distribution.
#  * Neither the name of the  nor the names of its
#    contributors may be used to endorse or promote products derived from
#    this software without specific prior written permission.
#  
#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
#  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
#  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
#  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
#  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
#  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
#  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
#  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
#  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
#  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#  

import csv
import openpyxl

class XlsxReader:
    """
        Wrapper class that reads an xlsx file like a :py:class:`csv.reader`.
        
        It takes as argument the file path to the Excel file and the name of
        the worksheet to work on. The interface is the same as for
        :py:class:`csv.reader`, this is an iterator that yields a list of
        strings per line.
    """
    def __init__(self, filename, worksheet):
        self.filename = filename
        self.workbook = openpyxl.load_workbook(filename, use_iterators = True)
        self.worksheet = self.workbook.get_sheet_by_name(worksheet)
        if self.worksheet is None:
            raise RuntimeError("Worksheet {} not found".format(worksheet))
        self.line_num = 0
        self.iter_rows = self.worksheet.iter_rows()
    
    def __iter__(self):
        return self
    
    def __next__(self):
        row = next(self.iter_rows)
        self.line_num += 1
        return [ cell.internal_value for cell in row ]

class DictXlsxReader(csv.DictReader):
    """
        Wrapper class that reads an xlsx file like a :py:class:`csv.DictReader`.
        
        It takes as argument the file path to the Excel file and the name of
        the worksheet to work on. The interface is the same as for
        :py:class:`csv.DictReader`, this is an iterator that yields a dict of
        strings per line. See :py:class:`csv.DictReader` for the meaning of
        ``fieldnames``, ``restkey`` and ``restval``.
    """
    def __init__(
                self, filename, worksheet, fieldnames=None,
                restkey=None, restval=None
            ):
        self._fieldnames = fieldnames
        self.restkey = restkey
        self.restval = restval
        self.reader = XlsxReader(filename, worksheet)
        self.line_num = 0