findFilesWithStrings.m

function matchingFiles = findFilesWithStrings(folderPath, searchStrings, extension, exactMatchStrings)
%FINDFILESWITHSTRINGS Finds files whose names contain all specified strings (case-insensitive),
% with optional exact token matching (e.g., 'WhiteNoise' not matching 'FrozenWhiteNoise').
%
% Inputs:
%   folderPath        - Folder to search in
%   searchStrings     - Substrings to match (case-insensitive)
%   extension         - (Optional) File extension filter (e.g., '.csv')
%   exactMatchStrings - (Optional) Strings to match exactly as tokens
%
% Output:
%   matchingFiles     - Struct array of matching files (like dir)

    if nargin < 3 || isempty(extension)
        filePattern = fullfile(folderPath, '*');
    else
        if ~startsWith(extension, '.')
            extension = ['.', extension];
        end
        filePattern = fullfile(folderPath, ['*', extension]);
    end

    if nargin < 4
        exactMatchStrings = {};
    end

    allFiles = dir(filePattern);
    matchingFiles = [];

    for k = 1:length(allFiles)
        file = allFiles(k);
        if file.isdir
            continue;
        end

        % Separate base filename (no extension)
        [~, baseName, ~] = fileparts(file.name);
        baseNameLower = lower(baseName);

        % Case-insensitive substring match
        hasSubstrings = all(cellfun(@(s) contains(baseNameLower, lower(s)), searchStrings));

        % Tokenize base name using common separators
        tokens = regexp(baseNameLower, '[^_\-\.]+', 'match');

        % Case-insensitive exact match of tokens
        hasExact = all(ismember(lower(exactMatchStrings), tokens));

        if hasSubstrings && hasExact
            matchingFiles = [matchingFiles; file];
        end
    end
end