FAOSTAT_data_primap/fao_total_specifications_2023.m

function specifications = fao_total_specifications_2023(sourcename)
% fao_specifications just creates a structure containing all informations
%   needed to parse the fao files...
%
% INPUT PARAMETERS: None
%
% RETURN PARAMETERS:
%   specifications: a structure with many constants needed to parse the
%   input xls files for the program read_bulkplus_sheet.
%   specifications contains two fields, 'keystruct', and 'mapstruct'.
%   - specifications.keystruct - is a structure of sheet fieldnames (e.g.
%     'sheet_category'), where the value is a cellstr of the labels that
%     should be used to assign the value. The list is taken in the order it
%     is listed.
%   - specifications.mapstruct - is a structure that maps column headers (or other
%     inputs, such as $filename or $sheetname for the filename or sheetname,
%     respectively) to the values to be assigned to sheet fields.
%     mapstruct.names contains the list of headers names, where the index of
%     each header corresponds to the field 'var[index]'. mapstruct.varX
%     contains the field 'value', as well as fields for each sheet
%     fieldname (e.g. sheet_category) that gets mappings from this
%     parameter source. the field 'value' can have three types of values:
%     - a cellstr of possible values in the input file. In this case,
%     cellstrs of the same length are given for the sheet fieldnames, which
%     provide the values to map too.
%     - the string 'echo'. In this case, the value in the input file is fed
%     to a function, the name of which is given in the sheet fieldname
%     fields. if the function is an empty string, then the value in the
%     input file is simply fed directly.
%     - the string 'split'. In this case, the value in the input file for
%     this column is a year, such that before this year the data is to have
%     one designation, and after and including this year, it is to have a
%     different designation. (this is used for the IMF WEO data). The
%     designations are provided in the sheet fieldname field.
%
%
% GLOBALS:
% CONSTANTS: A structure containing string and numeric constants, which are
%           used in the PRIMAP functions. These are configurations like
%           scaling factors, but also fieldnames for the database and
%           mapping vectors etc.
%
% NOTES:
%
% (c) Written by Kathleen Markmann and the PRIMAP - PIK team, June 2012.
% This file is shared under a "Attribution-NonCommercial-ShareAlike 3.0"
% licence, which means that you must give credit to the author, are not
% allowed to use it for commercial purposes and you may share your
% derivatives of this work only under a similar licence. Other than that,
% you are free to copy, display, use, modify the code. The details of this
% licence are given at: http://creativecommons.org/licenses/by-nc-sa/3.0/
%
% version: 150602 JG - based on fao_specifications
% version: 201001 JG - adpated for FAO 2020A

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

global CONSTANTS
if isempty(CONSTANTS)
    error('Empty global variable! Please initialise with the drive_set_paths_and_globals... function!')
end

%please insert the download date?!
date = 'Jan 2023'; % for FAO2019A
%sourcename='FAO2018';

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%% sheet management %%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

% INPUT NAMES OF EXCEL SHEETS TO READ IN. IF NOT SPECIFIED, ALL SHEETS ARE
% READ IN
%specifications.sheetsToRead = {...
%};

% INPUT NAMES OF EXCEL SHEETS TO NOT READ IN. IF SHEET IS ENCOUNTERED THAT
% IS NOT LISTED IN THE SHEETSTOREAD OR SHEETSTOIGNORE, A WARNING IS GIVEN
%specifications.sheetsToIgnore = {...
%};

% data in csv-format?
specifications.isCSV = true;
specifications.CSVdelimiter = ',';
specifications.CSVQuotesToRemove = '';

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%% READING SHEETS %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% SPECIFY IF DATA IS EXTRA LONG AND NEEDS TO BE READ IN BLOCKS
% IF BlockSize and dataBottomRightCorner IS NOT FIELD, DEFAULT IS TO READ IN ALL DATA AT ONCE
specifications.blockSize = 10000;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% SPECIFY IF LABEL IS ONLY ONE COLUMN. DEFAULT IS FALSE. IF TRUE, THEN
% COLUMN NAMES DO NOT NEED TO BE SPECIFIED. LABELS ASSUMED TO BE IN FIRST
% COLUMN
specifications.singleLabel = false;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% SPECIFY COLUMN INDEX WHERE ANNUAL DATA STARTS
%%%% TEMP %%%%
specifications.colStartOfYear = 9;
%temporarily because index has been written in files by mistake
%%%% TEMP %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% SPECIFY ROW INDEX WHERE THE HEADER IS FOUND. IF NOT GIVEN, DEFAULT IS 1.
% CAN BE MULTIPLE ROWS. IN THIS CASE, ALL ROWS LISTED ARE CONCATENATED WITH
% NO SPACES BETWEEN EACH ROW.
specifications.rowOfHeader = 1;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% SPECIFY ROW INDEX WHERE DATA STARTS. DEFAULT IS ROW AFTER HEADER
specifications.rowOfData = 2;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% HEADER VALUE THAT INDICATES THE END OF DATA. DATA IS
% ASSUMED TO END BEFORE THIS. IF NOT GIVEN, DEFAULT IS NaN
%specifications.nonDataKeyword = '2014F';
%each of these specification columns has to be defined in the following...
%the way is the same for all of them: first you define the name for the
%column than you define the mapping
%always the bulk name and in the same order the according PRIMAPDB names


%specifications.yearColIgnore = '\d*F';
%specifications.yearColTransform = '\d*'; %this is used to match a string
% which is then taken as the year

% DEFINE KEYSTRUCT %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% FOR EVERY SHEET KEY THAT IS TO BE DEFINED FROM THE INPUT FILE, PROVIDE
% THE SHEET KEY NAME AS A FIELD, AND THEN LIST THE COLUMN HEADERS (OR
% $filename or $sheetname FOR THE FILENAME OR EXCEL SHEETNAME,
% RESPECTIVELY) IN THE SUBFIELD colName. IF SINGLE COLUMN MODE IS DEFINED,
% THEN USE $label.

specifications.keystruct.(CONSTANTS.nameOfSheetEntity).colName = {'Element'};
specifications.keystruct.(CONSTANTS.nameOfCountryVector).colName = {'Area Code'};
specifications.keystruct.(CONSTANTS.nameOfSheetCategory).colName = {'Item'};
specifications.keystruct.(CONSTANTS.nameOfSheetType).colName = {'Element'};
specifications.keystruct.(CONSTANTS.nameOfSheetUnit).colName = {'Unit', 'Element', 'Variable'}; % {'Unit'};

%% TODO
% we need an new FAO specification because the new emission data does not really fit into the old categories
% we now have the following
% * Emissions on agricultural land
% = Farm-gate emissions + Fires in humid tropical forests + Net Forest conversion + Fires in organic soils
% * Farm-gate emissions (1)
% = Enteric Fermentation (1A) + Manure Management (1B) + Rice Cultivation (1C) + Synthetic Fertilizers (1D)
% + Manure applied to Soils (1E) + Manure left on Pasture (1F) + Crop Residues (1G) + Burning - Crop residues (1J)
% + Drained organic soils (1H, CO2 and N2O) + On-farm energy use (1K)
% * FORESTLAND = Forestland + Forest fires
% * LAND USE CHANGE = Fires in humid tropical forests + Net Forest conversion + Fires in organic soils
% (FORESTLAND and LAND USE CHANGE are not available in the csv files, but named on the
% "FAOSTAT Domain Emissions Totals. Metadata" document)


% IPCC type categories
% AFOLU = IPCC Agriculture + LULUCF
% IPCC Agriculture = Farm-gate emissions - On-farm energy use - Drained organic soils (CO2)
% LULUCF = LAND USE CHANGE + FORESTLAND + Drained organic soils (CO2)
% or LULUCF = Fires in humid tropical forests + Net Forest conversion + Fires in organic soils
%           + Forestland + Forest fires

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% MAPPING %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

% LISTS MAPPING BETWEEN VALUES IN THE INPUT FILE AND VALUES FOR THE
% DATATABLES. THE COLUMN HEADERS (OR $filename or $sheetname FOR THE
% FILENAME OR EXCEL SHEETNAME, RESPECTIVELY) ARE LISTED IN FIELD name.
% STANDARD INPUT FOR var[i].value IS TO PROVIDE A CELLSTR OF ALL VALUES
% FROM THE COLUMN LISTED IN name{i} THAT ARE TO BE ASSIGNED. VALUES TO BE
% IGNORED CAN BE LISTED IN FIELD var[i].valuesToIgnore, TO REDUCE WARNING
% MESSAGES. THE SHEET KEYS TO MAP TO ARE LISTED AS FIELDS UNDER var[i],
% WITH THE VALUE IN THE STANDARD CASE BEING A CELLSTR WITH THE SAME LENGTH
% AS THE FIELD value, THAT PROVIDES THE VALUES TO BE USED IN THE
% DATATABLES.
% ALTERNATE INPUTS FOR FIELD value ARE THE STRINGS 'echo' OR
% 'split'. 'echo' PASSES THE INPUT VALUE TO THE FUNCTION LISTED UNDER THE
% SHEET KEY FIELD, AND ASSIGNS THE OUTPUT TO THE SHEET KEY. 'split' ASSUMES
% THAT THE INPUT VALUES IS A YEAR. THE DATA WILL BE SPLIT INTO TWO
% DATATABLES AT THAT YEAR, WITH THAT YEAR BEING A PART OF THE SECOND
% DATATABLE. THE FIRST TABLE WILL GET THE FIRST ELEMENT ASSIGNED TO SHEET
% KEY FIELD, AND THE SECOND TABLE WILL GET THE SECOND ELEMENT.

%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% entity, category and unit %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
i = 1;
specifications.mapstruct.name{i} = 'Element';
specifications.mapstruct.(['var' num2str(i)]).value = { ...
    'Emissions (CH4)', 'Emissions (N2O)', 'Emissions (CO2)', ...
    'Emissions (CO2eq) (AR5)', 'Direct emissions (N2O)', 'Indirect emissions (N2O)', ...
    'Emissions (CO2eq) from F-gases (AR5)',
    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfSheetEntity) = { ...
    'CH4', 'N2O', 'CO2', ...
    'KYOTOGHGAR5', 'N2O', 'N2O', ...
    'FGASESAR5', ...
    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfSheetUnit) = { ...
    '', '', '', ...
    'CO2eq', '', '', ...
    'CO2eq', ...
    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfSheetType) = { ...
    'NET', 'NET', 'NET', ...
    'NET', 'DIR', 'IND', ...
    'NET', ...
    };
specifications.mapstruct.(['var' num2str(i)]).valueToIgnore = { ...
    'Emissions (CO2eq) from N2O (AR5)', ...
    'Emissions (CO2eq) from CH4 (AR5)', ...
    };


%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% region %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
i = 2;
specifications.mapstruct.name{i} = 'Area Code';
specifications.mapstruct.(['var' num2str(i)]).value = { ...
    '1', '2', '3', '4', '5', ...
    '6', '7', '8', '9', '10', ...
    '11', '12', '13', '14', '15', ...
    '16', '17', '18', '19', '20', ...
    '21', '22', '23', '24', '25', ... % 5
    '26', '27', '28', '29', '30', ...
    '31', '32', '33', '35', '36', ...
    '37', '38', '39', '40', '41', ...
    '42', '43', '44', '45', '46', ...
    '47', '48', '49', '50', '51', ... % 10
    '52', '53', '54', '55', '56', ...
    '57', '58', '59', '60', '61', ...
    '62', '63', '64', '65', '66', ...
    '67', '68', '69', '70', '71', ...
    '72', '73', '74', '75', '77', ... % 15
    '78', '79', '80', '81', '82', ...
    '83', '84', '85', '86', '87', ...
    '88', '89', '90', '91', '92', ...
    '93', '94', '95', '96', '97', ...
    '98', '99', '100', '101', '102', ... % 20
    '103', '104', '105', '106', '107', ...
    '108', '109', '110', '111', '112', ...
    '113', '114', '115', '116', '117', ...
    '118', '119', '120', '121', '122', ...
    '123', '124', '125', '126', '127', ... % 25
    '128', '129', '130', '131', '132', ...
    '133', '134', '135', '136', '137', ...
    '138', '139', '140', '141', '142', ...
    '143', '144', '145', '146', '147', ...
    '148', '149', '150', '151', '153', ... %30
    '154', '155', '156', '157', '158', ...
    '159', '160', '161', '162', '163', ...
    '164', '165', '166', '167', '168', ...
    '169', '170', '171', '172', '173', ...
    '174', '175', '176', '177', '178', ... %35
    '179', '180', '181', '182', '183', ...
    '184', '185', '186', '187', '188', ...
    '189', '190', '191', '192', '193', ...
    '194', '195', '196', '197', '198', ...
    '199', '200', '201', '202', '203', ... % 40
    '205', '206', '207', '208', '209', ...
    '210', '211', '212', '213', '214', ...
    '215', '216', '217', '218', '219', ...
    '220', '221', '222', '223', '224', ...
    '225', '226', '227', '228', '229', ... % 45
    '230', '231', '232', '233', '234', ...
    '235', '236', '237', '238', '239', ...
    '240', '242', '243', '244', '248', ...
    '249', '250', '251', '255', '256', ...
    '258', '259', '260', '264', '270', ... % 50
    '271', '272', '273', '274', '275', ...
    '276', '277', '278', '279', '280', ...
    '281', '282', '283', '284', '299', ...

    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfCountryVector) = { ...
    'ARM', 'AFG', 'ALB', 'DZA', 'ASM', ...
    'AND', 'AGO', 'ATG', 'ARG', 'AUS', ...
    'AUT', 'BHS', 'BHR', 'BRB', 'BELLUX', ...
    'BGD', 'BMU', 'BTN', 'BOL', 'BWA', ...
    'BRA', 'ABW', 'BLZ', 'IOT', 'SLB', ... % 5
    'BRN', 'BGR', 'MMR', 'BDI', 'ATA', ...
    'BVT', 'CMR', 'CAN', 'CPV', 'CYM', ...
    'CAF', 'LKA', 'TCD', 'CHL', 'CHN', ...
    'CXR', 'CCK', 'COL', 'COM', 'COG', ...
    'COK', 'CRI', 'CUB', 'CYP', 'CZESVK', ... % 10
    'AZE', 'BEN', 'DNK', 'DMA', 'DOM', ...
    'BLR', 'ECU', 'EGY', 'SLV', 'GNQ', ...
    'ETHERI', 'EST', 'FRO', 'FLK', 'FJI', ...
    'FIN', 'FRA', 'GUF', 'PYF', 'ATF', ...
    'DJI', 'GEO', 'GAB', 'GMB', 'F77', ... % 15
    'F78', 'DEU', 'BIH', 'GHA', 'GIB', ... %F77,78 is GDR and BRD but no data in FAOSTAT
    'KIR', 'GRC', 'GRL', 'GRD', 'GLP', ...
    'GUM', 'GTM', 'GIN', 'GUY', 'HMD', ...
    'HTI', 'VAT', 'HND', 'HKG', 'HUN', ...
    'HRV', 'ISL', 'IND', 'IDN', 'IRN', ... % 20
    'IRQ', 'IRL', 'ISR', 'ITA', 'CIV', ...
    'KAZ', 'JAM', 'JPN', 'JTN', 'JOR', ... % not sure what JTN is
    'KGZ', 'KEN', 'KHM', 'PRK', 'KOR', ...
    'KWT', 'LVA', 'LAO', 'LBN', 'LSO', ...
    'LBR', 'LBY', 'LIE', 'LTU', 'MHL', ... % 25
    'MAC', 'MDG', 'MWI', 'MYS', 'MDV', ...
    'MLI', 'MLT', 'MTQ', 'MRT', 'MUS', ...
    'MEX', 'MID', 'MCO', 'MNG', 'MSR', ... % MID unknown
    'MAR', 'MOZ', 'FSM', 'MDA', 'NAM', ...
    'NRU', 'NPL', 'NLD', 'ANT', 'NCL', ... % 30
    'MKD', 'VUT', 'NZL', 'NIC', 'NER', ...
    'NGA', 'NIU', 'NFK', 'NOR', 'MNP', ...
    'TTPI', 'PAK', 'PAN', 'CZE', 'PNG', ...
    'PRY', 'PER', 'PHL', 'PCN', 'POL', ...
    'PRT', 'GNB', 'TLS', 'PRI', 'ERI', ... % 35
    'QAT', 'PLW', 'ZWE', 'REU', 'ROU', ...
    'RWA', 'RUS', 'SRBMNE', 'SHN', 'KNA', ...
    'LCA', 'SPM', 'VCT', 'SMR', 'STP', ...
    'SAU', 'SEN', 'SYC', 'SLE', 'SVN', ...
    'SVK', 'SGP', 'SOM', 'ZAF', 'ESP', ... % 40
    'ESH', 'SDNSSD', 'SUR', 'TJK', 'SWZ', ...
    'SWE', 'CHE', 'SYR', 'TKM', 'TWN', ...
    'TZA', 'THA', 'TGO', 'TKL', 'TON', ...
    'TTO', 'OMN', 'TUN', 'TUR', 'TCA', ...
    'ARE', 'UGA', 'TUV', 'FSU', 'GBR', ... % 45
    'UKR', 'USA', 'UMI', 'BFA', 'URY', ...
    'UZB', 'VEN', 'VNM', 'ETH', 'VGB', ...
    'VIR', 'WAK', 'WLF', 'WSM', 'YUG', ... % WAK unknown
    'YEM', 'COD', 'ZMB', 'BEL', 'LUX', ...
    'AIA', 'CHI', 'SJM', 'IMN', 'MYT', ... % 50
    'SGS', 'SRB', 'MNE', 'GGY', 'UVK', ... % UVK unknown
    'SDN', 'SSD', 'BES', 'CUW', 'SXM', ...
    'MAF', 'BLM', 'JEY', 'ALA', 'PSE', ...

    };
specifications.mapstruct.(['var' num2str(i)]).valueToIgnore = { ...
    '5000', '5100', '5101', '5102', '5103', ...
    '5104', '5105', '5200', '5203', '5204', ...
    '5206', '5207', '5300', '5301', '5302', ...
    '5303', '5304', '5305', '5400', '5401', ...
    '5402', '5403', '5404', '5500', '5501', ...
    '5502', '5503', '5504', '5707', '5801', ...
    '5802', '5803', '5815', '5817', '5848', ...
    '5849', '5873', 'F246', 'F247', 'F609', 'F614', ...
    'F616', 'F617', 'F618', 'F619', 'F620', ...
    'F621', 'F622',  '351',  ... %351 is China but we have it split up here
};


%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
i = 3;
specifications.mapstruct.name{i} = 'Item';
specifications.mapstruct.(['var' num2str(i)]).value = { ...
    'LULUCF', 'IPCC Agriculture', ...
    'Enteric Fermentation', 'Manure Management', 'Synthetic Fertilizers', ...
    'Manure applied to Soils', 'Manure left on Pasture', 'Crop Residues', ...
    'Burning - Crop residues', 'Net Forest conversion', 'Forestland', ...
    'Savanna fires', 'AFOLU', ...
    'Rice Cultivation', 'Agricultural Soils', ...
    'All sectors with LULUCF', 'All sectors without LULUCF', 'Energy', ...
    'IPPU', 'Other', 'Waste', ...
    'Drained organic soils', 'Drained organic soils (N2O)', 'Drained organic soils (CO2)', ...
    %'Forest fires', ... %5
    %'Fires in organic soils', 'On-farm energy use', 'Emissions on agricultural land', ...
    %'Farm-gate emissions', 'Fires in humid tropical forests',
        %'Agri-food systems',
    %'Farm gate', 'Fertilizers Manufacturing',
    %'Food Household Consumption', 'Food Packaging',
    %'Food Processing', 'Food Retail',
    %'Food Transport', 'Food systems waste disposal',
    % 'Land Use change', 'On-farm electricity use',
    % 'Pre- and post- production',
    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfSheetCategory) = { ...
    'IPCMLULUCF', 'IPCMAG', ...
    'IPC3A1', 'IPC3A2', 'IPC3C4A', ...
    'IPC3C4B', 'IPC3C4C', 'IPC3C4D', ...
    'IPC3C1B', 'IPCMNFC', 'IPC3B1', ...
    'IPC3C1C', 'IPC3', ...
    'IPC3C7', 'IPCM3C45AG', ...
    'IPC0', 'IPCM0EL', 'IPC1', ...
    'IPC2', 'IPC5', 'IPC4', ...
    'IPCM3C45DOS', 'IPCM3C45DOSN2O', 'IPCM3C45DOSCO2', ...
    %'MFF', ... %5
    %'2D3', '1K', 'MAL', ...
    %'MFG', '2D1',
    %'1H', 'M1HAG', 'M1HLU', ...
    };
specifications.mapstruct.(['var' num2str(i)]).valueToIgnore = { ...
    'Forest fires', ... %5
    'Fires in organic soils', 'On-farm energy use', 'Emissions on agricultural land', ...
    'Farm-gate emissions', 'Fires in humid tropical forests',  ...
    'Agri-food systems', 'Farm gate', 'Fertilizers Manufacturing', ...
    'Food Household Consumption', 'Food Packaging', ...
    'Food Processing', 'Food Retail', ...
    'Food Transport', 'Food systems waste disposal', ...
    'Land Use change', 'On-farm electricity use', ...
    'Pre- and post- production', ...
    'Agrifood Systems Waste Disposal', 'Agrifood systems', ... % below new in 2024A
    'Pesticides Manufacturing', 'Pre- and Post- Production', ...
    'Emissions from crops', 'Emissions from livestock', ... don't fit IPCC categories
    };

% general caveats in mapping: does not distinguish between direct and
% indirect. All mapped to direct IPCC cats (3.C.4)
% it's unclear where drained organic soils should be mapped to. It's
% included in Agricultural soils and thus implicitly mapped to M.3.C.45AG

% TODO make new FAO terminology
% FAO sector hierarchy (total domain)
% IPCC Agriculture (CH4, N2O) X
% * Enteric fermentation (CH4 only) X
% * Manure Management X
% * Burning - crop residues X
% * Savanna fires X
% * Rice cultivation (CH4 only) X
% * Agricultural soils (N2O only) X
%   * Synthetic Fertilizers X
%   * Manure applied to soils X
%   * Manure left on Pasture X
%   * Crop Residues X
%   * Drained organic soils (N2O)

% not in IPCC Agriculture hierarchy
% Drained organic soils (CO2)
% Net Forest conversion
% Fires in humid tropical forests
% Fires in organic soils
% Forest fires
% Forestland
% On-farm energy use


% agg
% Agricultural Soils
% IPCC Agriculture
% LULUCF
% AFOLU
% Emissions on agricultural land
% Farm-gate emissions
% Land Use change


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
i = 4;
specifications.mapstruct.name{i} = 'Unit';
specifications.mapstruct.(['var' num2str(i)]).value = { ...
    'Gigagrams', 'gigagrams', 'tonnes', 'Kg', 'Head', ...
    'kilotonnes', 'kt', ...
    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfSheetUnit) = { ...
    'Gg', 'Gg', 't', 'Kg', 'Heads', ...
    'kt', 'kt', ...
    };
specifications.mapstruct.(['var' num2str(i)]).valueToIgnore = { ...
    'g N20/kg dry matter', 'g CH4/kg dry matter', 'Ha', ...
    'Kg of nutrients', 'kg N2O-N/kg N', 'million kWh', ...
    'Terajoule', 'Kg/TJ', 'Kg CH4/head', ...
    'kg N2O-N/kg N', ...
    };

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
i = 5;
specifications.mapstruct.name{i} = 'Variable';
specifications.mapstruct.(['var' num2str(i)]).value = { ...
    'Value', ...
    };
specifications.mapstruct.(['var' num2str(i)]).(CONSTANTS.nameOfSheetUnit) = { ...
    '', ...
    };
specifications.mapstruct.(['var' num2str(i)]).valueToIgnore = { ...
    'Flag', 'Note', 'FAO Source', 'Source Code', ...
    'Domain', 'Flag Description', 'Domain Code', ...
    'Source', 'Area Code (M49)', ...
    };

%%%%%%%%%%%%%%%%%%%%%%%%%%%% default table %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%since we want to build up datatables we need a default table which gets
%parametrised according to the row which we are parsing

%specify default datatable (all necessary fields...)
specifications.patternTable.(CONSTANTS.nameOfSheetCode) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetCategory) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetCategoryName) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetEntity) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetType) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetClass) = 'TOTAL';
specifications.patternTable.(CONSTANTS.nameOfSheetDescr) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetNote) = 'Read in by JG';
specifications.patternTable.(CONSTANTS.nameOfSheetSource) = sourcename;
specifications.patternTable.(CONSTANTS.nameOfSheetFirstdatarow) = 0;
specifications.patternTable.(CONSTANTS.nameOfSheetUnit) = '';
specifications.patternTable.(CONSTANTS.nameOfSheetScenario) = 'HISTORY';
specifications.patternTable.(CONSTANTS.nameOfSheetDatatype) = 'CountryYearMatrix';
specifications.patternTable.(CONSTANTS.nameOfCountryVector) = {};
specifications.patternTable.(CONSTANTS.nameOfDataField) = [];
specifications.patternTable.(CONSTANTS.nameOfYearVector) = [];
specifications.patternTable.(CONSTANTS.nameOfSheetSubsource) = {};
specifications.patternTable.(CONSTANTS.nameOfSheetTablekind) = CONSTANTS.defaultForSheetTablekind;

end %function bp_specifications