MATLAB: Retrieve binary data back

encryption

I have a binary data as

00 10 11 01 10 11 11 01

I need to replace this data as if

00 = 0
01 = 1
10 or 11 = *

if i get a new data as below

0 * * 1 * * * 1

can you suggest any way to get back the binary data

00 10 11 01 10 11 11 01

Best Answer

In case you wanted to accept my answer, I'll repost my code in an actual answer. However, I would suggest you use Madhan's solution. That one ignores the last bit if the length is odd (which might not be what you want), while my code throws an error.

data='0010110110111101';
replace_with={'00','0';'01','1';'10','*';'11','*'};
key_list=replace_with(:,1);
val_list=replace_with(:,2);
%check for even numbers:
if rem(numel(data),2)~=0
    error('bits are not paired')
end
%convert to 1 pair per cell
datacell=mat2cell(data,1,2*ones(numel(data)/2,1));
% %loop through the replacer elements
% for n=1:numel(key_list)
%     datacell(ismember(datacell,key_list{n}))=val_list(n);
% end
inds=cellfun(@(x) find_indices(x,key_list),datacell);
L= inds~=0;
datacell(L)=val_list(inds(L));
%convert back to a char array
result=cell2mat(datacell);
clc,disp(result)
%local function:
function inds=find_indices(element,key_list)
[~,inds]=ismember(element,key_list);
end

Related Solutions

MATLAB: Read specific data columns from a text file based on header name requested by user

Before I continue, I want to Thank @Bob Nbob and @Stephen Cobeldick for their work, suggestions and help.

I really appreciate everything you guys are doing for this community.

Whoever is interested in this post and was waiting for an answer.

It took me a while but, I have finally got it to work correctly. The code is a little long and I did not exactly choose good variable names or probably wrote comments detailed enough.

If I can write a more efficient code and anyone has suggestions I'll consider them.

I don't know if 0.027222 seconds (from beginning to end) is efficient enough for this kind of task: read 68 columns of info from a text file full of "pages" of columns with no delimiters between columns.

The output is a 1X68 column cell array called "storage" with 99X1 or 100X1 cell arrays inside each cell of 68 cells. The output can be changed to numeric value later after removing some of the "." at the very end of some numbers (look at the number "8713996." FOPT in first cell towards the last rows - there is no "0" after the decimal).

The output is also a cell array and can be converted to a different type of array by using cell2mat,etc. functions (which I have not used in this code).

%% Read txt file
% Reset all the variables
clear;
clc;
% Read the content of the text file into memory
content = fileread('Original_1.txt');
% Declare desired string occurences (columns) to create the storage cell
% (initially with an unknown size) and store specified columns
desired_string = ["FOPT", "FGPT", "FWPT", "WOPR", "WWPR", "WOPT", "WWPT", "WGPT", "WGPR", "WBHP", "WGOR" ];
% Create cell array to store the columns desired
count_string = count(content,desired_string );
storage = cell(1,count_string);
% Delete unnecessary strings and special characters for readibility (should
% be left with 130 characters "per line"-content variable in workspace is a 
% character vector of size 1*154485). Warning: New line and carriage return
% characters also need to be deleted to get 130 characters "per line".
new_content = regexprep(content, '"SUMMARY\s.*$|"-.*$|SUMMARY\s.*$|^\s+|\n|\r', '', 'lineanchors', 'dotexceptnewline');
% If first 13 characters containts the string 'DATE' insert '!' to beginning
% as a delimiter to separate into pages
search_string = {'"','DATE'};
first_13 = new_content(1:13);
if contains(first_13,search_string(1,1))
   new_str = insertBefore(new_content, '"DATE', '!');
   final_str = strsplit(new_str, '!');
elseif contains(first_13, search_string(1,2))
   new_str = insertBefore(new_content, 'DATE', '!');
   final_str = strsplit(new_str, '!');
end
% Search for a specific string and read all the columns
pages = length(final_str);
add = 13;
count = 0;
next_column = 0;
% For loop for reading each page of the content
for ii = 2:pages
    
    % Convert cell into character vector
    new_char_vec = char(final_str(1,ii));
    % Length of each character vector in each cell
    long = length(char(final_str(1,ii)));
    
    % Column number of each page!
    row_no = long/130;
    
    % Read first 130 characters, 13 characters at a time 10 times and 
    % match the desired string
    for i = 1:10
        
        row = 1 + count;
        column = 13 + count;
        testing = new_char_vec(1, (row:column));
        count = count + add;
        
        % if contains 'FOPT' %read all the columns related
        if contains(testing,desired_string)
            
            % Move to next column of storage cell when string is found
            next_column = next_column + 1;
            
            % Create cell array inside each column of storage cell array
            % row_no varies
            storage{1,next_column} = cell(row_no,1);
            % read_rows and read_columns are reset to row and column
            % everytime the desired_string is found
            read_rows = row;
            read_columns = column;
            
            % Store the the desired string column's first row
            storage{1,next_column}{1,1} = new_char_vec(1, (read_rows:read_columns));
            % Store each row of the desired string column (starting from 2nd row) in a for loop
                
                for jj = 2:(row_no)
                    read_rows = read_rows + 130;
                    read_columns = read_columns + 130;
                    storage{1,next_column}{jj,1} = new_char_vec(1, (read_rows:read_columns));
                end
            
        end
         
    end
    
    
% Reset count
count = 0;
end
% Clear all the unnecessary variables
clear add column content count count_string desired_string final_str first_13 i ii jj long new_char_vec new_content new_str next_column pages read_rows read_columns row row_no search_string testing

MATLAB: Converting unformatted text to formatted text

I have assumed that the size of the resulting arrays are known

fid = fopen( 'c:\m\cssm\test4.txt' );
rows = textscan( fid, '%s', 'Delimiter', '\n' );
fclose( fid );
rows = rows{:};
str = 'RainflowCycleCounterHistogram';  % avoid magic number

len = length( str );
is_counter   = strncmp( str, rows, len ); 
counter_rows = rows( is_counter );
%








str = 'RainflowCycleMeanBreakpoints';  
len = length( str );
is_mean   = strncmp( str, rows, len ); 
mean_rows = rows( is_mean );
%
str = 'RainflowCycleRangeBreakpoints';  
len = length( str );
is_range   = strncmp( str, rows, len ); 
range_rows = rows( is_range );
%
counter_matrix = nan( 10, 10 );
for jj = 1 : length( counter_rows )
%    


    cac = textscan( counter_rows{jj}, '%*s%d%d%f'   ...
                ,   'Delimiter'          , ' []:'   ...
                ,   'MultipleDelimsAsOne', true     ); 
%            





    counter_matrix( cac{1}+1, cac{2}+1 ) = cac{3};  % one based      



end
mean_vector = nan( 1, 10 );
for jj = 1 : length( mean_rows )
%    
    cac = textscan( mean_rows{jj}, '%*s%d%f'        ...
                ,   'Delimiter'          , ' []:'   ...
                ,   'MultipleDelimsAsOne', true     ); 
%            
    mean_vector( 1, cac{1}+1 ) = cac{2};  % one based      
end
range_vector = nan( 1, 10 );
for jj = 1 : length( range_rows )
%    
    cac = textscan( range_rows{jj}, '%*s%d%f'        ...
                ,   'Delimiter'          , ' []:'   ...
                ,   'MultipleDelimsAsOne', true     ); 
%            
    range_vector( 1, cac{1}+1 ) = cac{2};  % one based      
end

&nbsp

or maybe better - no assumptions regarding sizes

fid = fopen( 'c:\m\cssm\test4.txt' );
rows = textscan( fid, '%s', 'Delimiter', '\n' );
fclose( fid );
rows = rows{:};
str = 'RainflowCycleCounterHistogram';  % avoid magic number
len = length( str );
is_counter   = strncmp( str, rows, len ); 
counter_rows = rows( is_counter );
%
str = 'RainflowCycleMeanBreakpoints';  
len = length( str );
is_mean   = strncmp( str, rows, len ); 
mean_rows = rows( is_mean );
%
str = 'RainflowCycleRangeBreakpoints';  
len = length( str );
is_range   = strncmp( str, rows, len ); 
range_rows = rows( is_range );
%
CRS = permute( char( counter_rows ), [2,1] );
cac = textscan( CRS, '%*s%f%f%f'                ...
            ,   'Delimiter'             , '[]: '...
            ,   'MultipleDelimsAsOne'   , true  ...
            ,   'CollectOutput'         , true  ); 
num = cac{1};          
% 

sz1 = min( num(:,1:2), [], 1 );
sz2 = max( num(:,1:2), [], 1 );
sz  = sz2-sz1+[1,1];
ix_linear = sub2ind( sz, num(:,1)+1, num(:,2)+1  ); % one based 

counter_matrix( ix_linear ) = num(:,3); 
counter_matrix = reshape( counter_matrix, sz );
MRS = permute( char( mean_rows ), [2,1] );
cac = textscan( MRS, '%*s%f%f'                  ...
            ,   'Delimiter'             , '[]: '...
            ,   'MultipleDelimsAsOne'   , true  ...
            ,   'CollectOutput'         , true  ); 
num = cac{1};                  
%            
mean_vector( num(:,1)+1 ) = num(:,2);  % one based

RRS = permute( char( range_rows ), [2,1] );
cac = textscan( RRS, '%*s%f%f'                  ...
            ,   'Delimiter'             , ' []:'...
            ,   'MultipleDelimsAsOne'   , true  ...
            ,   'CollectOutput'         , true  ); 
%            
range_vector( num(:,1)+1 ) = num(:,2);  % one based

hope they return identical results :-)

&nbsp

and another iteration

Comments:

A function is superior to a script. It doesn't mess with the base workspace. It's easier to debug and it's easier to call from a script or function.
This function is readable. It's fairly straightforward to add new keywords and row formats.
The switch case can be replaced by a feval construct. But why do that?
The subfunctions, f1, f2 and f3, have large parts of their code in common. That asks for further refactoring.
Allocating a separate sub-function to each type of row makes testing easier.
If speed becomes a problem analyze the code with the profiler.

>> S = cssm( 'c:\m\cssm\text4.txt' )
S = 
                   RainflowCycleCounterHistogram: [10x10 double]
                    RainflowCycleMeanBreakpoints: [-111 100 300 330 360 380 390 400 410 420]
                   RainflowCycleRangeBreakpoints: [0 35 70 100 135 170 200 230 260 300]
                  RainflowCycleReversalTolerance: 20
                        PowerCylinderTemperature: 0
               PowerCylinderTemperatureHistogram: [1x12 double]
    PowerCylinderTemperatureHistogramBreakpoints: [0 150 175 200 220 250 300 320 350 370 400]
>>

where

function    S = cssm( filespec )
    fid = fopen( filespec );
    rows = textscan( fid, '%s', 'Delimiter', '\n' );
    fclose( fid );
    rows = strtrim( rows{:} );
    type_list   = {
    ... format  keyword   
        'f1', 'RainflowCycleCounterHistogram'
        'f2', 'RainflowCycleMeanBreakpoints'
        'f2', 'RainflowCycleRangeBreakpoints'
        'f3', 'RainflowCycleReversalTolerance'
        'f3', 'PowerCylinderTemperature'
        'f2', 'PowerCylinderTemperatureHistogram'
        'f2', 'PowerCylinderTemperatureHistogramBreakpoints'    
        };
    for jj = 1 : size( type_list, 1 )
        switch type_list{jj,1}
            case 'f1'
                S.(type_list{jj,2}) = f1( type_list{jj,2}, rows );
            case 'f2'
                S.(type_list{jj,2}) = f2( type_list{jj,2}, rows );
            case 'f3'
                S.(type_list{jj,2}) = f3( type_list{jj,2}, rows );
            otherwise
                error( 'The format, "%s", is not yet implemented', type_list{jj,1} )
        end
    end
end
function    matrix = f1( keyword, rows )
    ism = is_member( keyword, rows );
    cur_rows = rows( ism );
    %
    str = permute( char( cur_rows ), [2,1] );
    cac = textscan( str, '%*s%f%f%f'                ...
                ,   'Delimiter'             , '[]: '...
                ,   'MultipleDelimsAsOne'   , true  ...
                ,   'CollectOutput'         , true  ); 
    num = cac{1};          
    % 
    sz1 = min( num(:,1:2), [], 1 );
    sz2 = max( num(:,1:2), [], 1 );
    sz  = sz2-sz1+[1,1];
    ix_linear = sub2ind( sz, num(:,1)+1, num(:,2)+1  ); % one based 
    matrix( ix_linear ) = num(:,3); 
    matrix = reshape( matrix, sz );
end
function    matrix = f2( keyword, rows )
    ism = is_member( keyword, rows );
    cur_rows = rows( ism );
    %
    str = permute( char( cur_rows ), [2,1] );
    cac = textscan( str, '%*s%f%f'                  ...
                ,   'Delimiter'             , '[]: '...
                ,   'MultipleDelimsAsOne'   , true  ...
                ,   'CollectOutput'         , true  ); 
    num = cac{1};                  
    %            
    matrix( num(:,1)+1 ) = num(:,2);  % one based      
end
function    matrix = f3( keyword, rows )
    ism = is_member( keyword, rows );
    cur_rows = rows( ism );
    %
    str = permute( char( cur_rows ), [2,1] );
    cac = textscan( str, '%*s%f', 'Delimiter',':' );
    matrix = cac{:};   
end
function    ism = is_member( keyword, rows )
    %   the keyword is followed by either ":" or "["
    cac = regexp( rows, ['^',keyword,'(?=(:|\[))'], 'once' );
    ism = not( cellfun( @isempty, cac ) );
end

Best Answer

Related Solutions

MATLAB: Read specific data columns from a text file based on header name requested by user

MATLAB: Converting unformatted text to formatted text

Related Question