def iget_records(custom_headers=None, **keywords): """ Obtain a generator of a list of records from an excel source It is similiar to :meth:`pyexcel.get_records` but it has less memory footprint but requires the headers to be in the first row. And the data matrix should be of equal length. It should consume less memory and should work well with large files. """ sheet_stream = sources.get_sheet_stream(on_demand=True, **keywords) headers = None for row_index, row in enumerate(sheet_stream.payload): if row_index == 0: headers = row else: if custom_headers: # custom order tmp_dict = dict( zip_longest(headers, row, fillvalue=constants.DEFAULT_NA)) ordered_dict = OrderedDict() for name in custom_headers: ordered_dict[name] = tmp_dict[name] yield ordered_dict else: # default order yield OrderedDict( zip_longest(headers, row, fillvalue=constants.DEFAULT_NA))
def iget_array(**keywords): """Obtain a generator of an two dimensional array from an excel source It is similiar to :meth:`pyexcel.get_array` but it has less memory footprint. """ sheet_stream = sources.get_sheet_stream(**keywords) return sheet_stream.payload
def iget_array(**keywords): """ Obtain a generator of an two dimensional array from an excel source It is similiar to :meth:`pyexcel.get_array` but it has less memory footprint. """ sheet_stream = sources.get_sheet_stream(on_demand=True, **keywords) return sheet_stream.payload
def get_sheet(**keywords): """ Get an instance of :class:`Sheet` from an excel source """ sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in keywords: sheet_params[field] = keywords.pop(field) named_content = sources.get_sheet_stream(**keywords) sheet = Sheet(named_content.payload, named_content.name, **sheet_params) return sheet
def save_as(**keywords): """ Save a sheet from a data source to another one """ dest_keywords, source_keywords = _split_keywords(**keywords) sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in source_keywords: sheet_params[field] = source_keywords.pop(field) sheet_stream = sources.get_sheet_stream(**source_keywords) sheet = Sheet(sheet_stream.payload, sheet_stream.name, **sheet_params) return sources.save_sheet(sheet, **dest_keywords)
def custom_importer1(self, content, **keywords): sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in keywords: sheet_params[field] = keywords.pop(field) keyword = source.get_keyword_for_parameter(attribute) if keyword == "file_type": keywords[keyword] = attribute keywords["file_content"] = content else: keywords[keyword] = content named_content = get_sheet_stream(**keywords) self.init(named_content.payload, named_content.name, **sheet_params)
def isave_as(**keywords): """ Save a sheet from a data source to another one with less memory It is simliar to :meth:`pyexcel.save_as` except that it does not accept parameters for :class:`pyexcel.Sheet`. And it read when it writes. """ dest_keywords, source_keywords = _split_keywords(**keywords) for field in constants.VALID_SHEET_PARAMETERS: if field in source_keywords: raise Exception(SAVE_AS_EXCEPTION) sheet = sources.get_sheet_stream(on_demand=True, **source_keywords) return sources.save_sheet(sheet, **dest_keywords)
def custom_importer1(self, content, **keywords): """docstring is assigned a few lines down the line""" sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in keywords: sheet_params[field] = keywords.pop(field) keyword = SOURCE.get_keyword_for_parameter(attribute) if keyword == "file_type": keywords[keyword] = attribute keywords["file_content"] = content else: keywords[keyword] = content named_content = get_sheet_stream(**keywords) self.init(named_content.payload, named_content.name, **sheet_params)
def iget_records(**keywords): """Obtain a generator of a list of records from an excel source It is similiar to :meth:`pyexcel.get_records` but it has less memory footprint but requires the headers to be in the first row. And the data matrix should be of equal length. It should consume less memory and should work well with large files. """ sheet_stream = sources.get_sheet_stream(**keywords) headers = None for row_index, row in enumerate(sheet_stream.payload): if row_index == 0: headers = row else: yield dict( zip_longest(headers, row, fillvalue=constants.DEFAULT_NA))
def iget_records(**keywords): """ Obtain a generator of a list of records from an excel source It is similiar to :meth:`pyexcel.get_records` but it has less memory footprint but requires the headers to be in the first row. And the data matrix should be of equal length. It should consume less memory and should work well with large files. """ sheet_stream = sources.get_sheet_stream(on_demand=True, **keywords) headers = None for row_index, row in enumerate(sheet_stream.payload): if row_index == 0: headers = row else: yield dict(zip_longest(headers, row, fillvalue=constants.DEFAULT_NA))
def get_sheet(**keywords): """Get an instance of :class:`Sheet` from an excel source :param file_name: a file with supported file extension :param file_content: the file content :param file_stream: the file stream :param file_type: the file type in *content* :param session: database session :param table: database table :param model: a django model :param adict: a dictionary of one dimensional arrays :param url: a download http url for your excel file :param with_keys: load with previous dictionary's keys, default is True :param records: a list of dictionaries that have the same keys :param array: a two dimensional array, a list of lists :param keywords: additional parameters, see :meth:`Sheet.__init__` :param sheet_name: sheet name. if sheet_name is not given, the default sheet at index 0 is loaded Not all parameters are needed. Here is a table ========================== ========================================= source parameters ========================== ========================================= loading from file file_name, sheet_name, keywords loading from string file_content, file_type, sheet_name, keywords loading from stream file_stream, file_type, sheet_name, keywords loading from sql session, table loading from sql in django model loading from query sets any query sets(sqlalchemy or django) loading from dictionary adict, with_keys loading from records records loading from array array loading from an url url ========================== ========================================= see also :ref:`a-list-of-data-structures` """ sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in keywords: sheet_params[field] = keywords.pop(field) named_content = sources.get_sheet_stream(**keywords) sheet = Sheet(named_content.payload, named_content.name, **sheet_params) return sheet
def export_network(instance, request): # get the license from this animal license_object = instance.get_object().mouse.mouse_set.license # get the user from this animal user_object = license_object.owner # get all the mice from this license and user # first get the mouse_sets mouse_sets = MouseSet.objects.filter(owner=user_object, license=license_object) # now get the mice within this mouse set mice = [list(el.mouse.all()) for el in mouse_sets] # flatten the list mice = [el for sublist in mice for el in sublist] # get the corresponding scoresheets scoresheets = [list(el.score_sheet.all()) for el in mice] # get the fields # get the fields fields = ([f.name for f in ScoreSheet._meta.get_fields() if not f.is_relation] + ['mouse__mouse_name', 'owner__username']) # allocate a dictionary to store the scoresheets out_dict = {} # for all the mice for idx, animal in enumerate(scoresheets): # generate the name of the sheet sheet_name = str(mice[idx]) dest_keywords, source_keywords = _split_keywords(query_sets=animal, column_names=fields, dest_file_type='xls') sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in source_keywords: sheet_params[field] = source_keywords.pop(field) sheet_stream = sources.get_sheet_stream(**source_keywords) # turn it into a sheet sheet = Sheet(sheet_stream.payload, sheet_name, **sheet_params) # put in the dictionary out_dict[sheet_name] = sheet # turn the dictionary into a book out_book = pe.get_book(bookdict=out_dict) # get the file name for the book file_name = ' '.join(('Score Sheet', license_object.license_id.split('_')[1], 'Food Water', str(user_object))) \ + '.xls' # get the final path book_path = os.path.join(license_object.score_sheet_path, file_name) # save the book to file out_book.save_as(book_path) # the following code prompts the user to save the spreadsheet wherever, might be useful later # book_stream = sources.save_book(out_book, file_type='xls') # # get the response # response = excel._make_response(book_stream, 'xls', 200, file_name=file_name) # # get the content disposition from the response to add to the http response # content_disposition = {'Content-Disposition': response['Content-Disposition']} # # get the http response # hresponse = HttpResponse(response, content_type='application/vnd.ms-excel') # # edit the headers to include the content disposition, since for some reason httpresponse doesn't do it # hresponse._headers['content-disposition'] = list(content_disposition.items())[0] # return hresponse return HttpResponseRedirect('/loggers/score_sheet/')
def save_as(**keywords): """Save a sheet from a data source to another one It accepts two sets of keywords. Why two sets? one set is source, the other set is destination. In order to distinguish the two sets, source set will be exactly the same as the ones for :meth:`pyexcel.get_sheet`; destination set are exactly the same as the ones for :class:`pyexcel.Sheet.save_as` but require a 'dest' prefix. :param file_name: a file with supported file extension :param file_content: the file content :param file_stream: the file stream :param file_type: the file type in *content* :param session: database session :param table: database table :param model: a django model :param adict: a dictionary of one dimensional arrays :param url: a download http url for your excel file :param with_keys: load with previous dictionary's keys, default is True :param records: a list of dictionaries that have the same keys :param array: a two dimensional array, a list of lists :param keywords: additional parameters, see :meth:`Sheet.__init__` :param sheet_name: sheet name. if sheet_name is not given, the default sheet at index 0 is loaded :param dest_file_name: another file name. **out_file** is deprecated though is still accepted. :param dest_file_type: this is needed if you want to save to memory :param dest_session: the target database session :param dest_table: the target destination table :param dest_model: the target django model :param dest_mapdict: a mapping dictionary, see :meth:`pyexcel.Sheet.save_to_memory` :param dest_initializer: a custom initializer function for table or model :param dest_mapdict: nominate headers :param dest_batch_size: object creation batch size. it is Django specific :returns: IO stream if saving to memory. None otherwise if csv file is destination format, python csv `fmtparams <https://docs.python.org/release/3.1.5/ library/csv.html#dialects-and-formatting-parameters>`_ are accepted for example: dest_lineterminator will replace default '\r\n' to the one you specified ========================== ========================================= source parameters ========================== ========================================= loading from file file_name, sheet_name, keywords loading from string file_content, file_type, sheet_name, keywords loading from stream file_stream, file_type, sheet_name, keywords loading from sql session, table loading from sql in django model loading from query sets any query sets(sqlalchemy or django) loading from dictionary adict, with_keys loading from records records loading from array array loading from an url url ========================== ========================================= ================= ============================================= Saving to source parameters ================= ============================================= file dest_file_name, dest_sheet_name, keywords with prefix 'dest' memory dest_file_type, dest_content, dest_sheet_name, keywords with prefix 'dest' sql dest_session, dest_table, dest_initializer, dest_mapdict django model dest_model, dest_initializer, dest_mapdict, dest_batch_size ================= ============================================= In addition, this function use :class:`pyexcel.Sheet` to render the data which could have performance penalty. In exchange, parameters for :class:`pyexcel.Sheet` can be passed on, e.g. `name_columns_by_row`. """ dest_keywords, source_keywords = _split_keywords(**keywords) sheet_params = {} for field in constants.VALID_SHEET_PARAMETERS: if field in source_keywords: sheet_params[field] = source_keywords.pop(field) sheet_stream = sources.get_sheet_stream(**source_keywords) sheet = Sheet(sheet_stream.payload, sheet_stream.name, **sheet_params) return sources.save_sheet(sheet, **dest_keywords)