you need to use ascii code too

function [Program_Pr11] = Program_Pr11(Program_Pr11)
    % 1 - Încarcă textul din fișierul RTF
    fileID = fopen('text.rtf','r'); % Înlocuiește 'text.rtf' cu numele fișierului tău
    text = fscanf(fileID,'%c');
    fclose(fileID);
    
    % 2 - Determină limba textului (acest exemplu folosește o librărie externă, apelând un serviciu online sau o bibliotecă MATLAB)
    detected_language = detectLanguage(text);
    
    % 3 - Numărul de cuvinte și apariția fiecărui cuvânt
    words = split(text, ' ');
    num_words = numel(words);
    word_counts = countOccurrences(words);
    
    % 4 - Numărul de litere și frecvența fiecărui caracter
    letters = replace(text, ' ', ''); % Elimină spațiile
    num_letters = numel(letters);
    letter_counts = countOccurrences(letters);
    unique_chars = unique(letters);
    
    % 5 - Verifică și completează dicționarul cu cuvintele din text
    dictionary = loadDictionary(); % Încarcă dicționarul existent
    missing_words = findMissingWords(words, dictionary);
    updated_dictionary = addToDictionary(missing_words, dictionary);
    
    % 6 - Verifică prezența anumitor cuvinte indicate în text
    specified_words = {'word1', 'word2', 'word3'}; % Cuvintele de verificat
    word_presence = checkWordPresence(specified_words, words);
    
    % 7 - Reprezintă grafic frecvențele de apariție ale caracterelor în text
    figure;
    bar(unique_chars, letter_counts);
    xlabel('Caractere');
    ylabel('Frecvență de apariție');
    title('Frecvențele de apariție ale caracterelor în text');
    
    % Funcțiile auxiliare
    function detected_language = detectLanguage(text)
        % Implementează funcția pentru a detecta limba textului
        % Returnează limba detectată
        % Poate fi necesară utilizarea unor servicii sau biblioteci specializate
        % Exemplu: detected_language = MyLanguageDetectionFunction(text);
        detected_language = 'Romanian'; % Exemplu: limba detectată este româna
    end

    function counts = countOccurrences(items)
        unique_items = unique(items);
        counts = zeros(size(unique_items));
        for i = 1:numel(unique_items)
            counts(i) = sum(ismember(items, unique_items(i)));
        end
    end
    
    function dictionary = loadDictionary()
        % Implementează funcția pentru a încărca dicționarul
        % Returnează dicționarul
        dictionary = {'word1', 'word2', 'word3'}; % Exemplu: dicționarul tău
    end
    
    function missing_words = findMissingWords(words, dictionary)
        missing_words = setdiff(unique(words), dictionary);
    end
    
    function updated_dictionary = addToDictionary(new_words, dictionary)
        updated_dictionary = [dictionary new_words];
    end
    
    function word_presence = checkWordPresence(specific_words, words)
        word_presence = ismember(specific_words, words);
    end
end

[Dyuman Joshi]

What's your question?

[DGM]

Besides not actually saying what you want, you haven't included the working text.rtf. Are you aware that text.rtf is not a plain text file? I have to ask, because you're processing it like it's plain text when it's not. Disregarding array orientation errors, you're trying to fill your dictionary with a bunch of markup garbage that's not body text.

Answer 1

[DGM]

I fixed the improper concatenation and bad inputs to bar()

Program_Pr11('text.rtf.fakeextension.txt')

Of course, the bar labels are unreadable at this figure scale. I can't change that on the forum.

So what are those unique characters?

unique_chars =

'

$*-./0123456789;ABCDFHILNOQRSTWXYZ\_abcdefghijklmnopqrstuvwxy{}'

Let's look at the RTF file. Note that there aren't any uppercase characters or punctuation.

Let's see what the dictionary looks like:

words =

66×1 cell array

{'{\rtf1\ansi\deff3\adeflang1025↵{\fonttbl{\f0\froman\fprq2\fcharset0' }

{'Times' }

{'New' }

{'Roman;}{\f1\froman\fprq2\fcharset2' }

{'Symbol;}{\f2\fswiss\fprq2\fcharset0' }

{'Arial;}{\f3\froman\fprq2\fcharset0' }

{'Liberation' }

{'Serif{\*\falt' }

{'Times' }

{'New' }

{'Roman};}{\f4\fswiss\fprq2\fcharset0' }

{'Liberation' }

{'Sans{\*\falt' }

{'Arial};}{\f5\fnil\fprq2\fcharset0' }

{'WenQuanYi' }

{'Zen' }

{'Hei;}{\f6\fnil\fprq2\fcharset0' }

{'FreeSans;}{\f7\fswiss\fprq0\fcharset128' }

{'FreeSans;}}↵{\colortbl;\red0\green0\blue0;\red0\green0\blue255;\red0\green255\blue255;\red0\green255\blue0;\red255\green0\blue255;\red255\green0\blue0;\red255\green255\blue0;\red255\green255\blue255;\red0\green0\blue128;\red0\green128\blue128;\red0\green128\blue0;\red128\green0\blue128;\red128\green0\blue0;\red128\green128\blue0;\red128\green128\blue128;\red192\green192\blue192;\red255\green143\blue31;\red239\green0\blue0;}↵{\stylesheet{\s0\snext0\nowidctlpar\hyphpar0\cf0\kerning1\dbch\af5\langfe2052\dbch\af6\afs24\alang1081\loch\f3\fs24\lang1033'}

{'Normal;}↵{\s15\sbasedon0\snext16\sb240\sa120\keepn\dbch\af5\dbch\af6\afs28\loch\f4\fs28' }

{'Heading;}↵{\s16\sbasedon0\snext16\sl288\slmult1\sb0\sa140' }

{'Text' }

{'Body;}↵{\s17\sbasedon16\snext17\sl288\slmult1\sb0\sa140\dbch\af7' }

{'List;}↵{\s18\sbasedon0\snext18\sb120\sa120\noline\i\dbch\af7\afs24\ai\fs24' }

{'Caption;}↵{\s19\sbasedon0\snext19\noline\dbch\af7' }

{'Index;}↵}{\*\generator' }

{'LibreOffice/5.0.3.2$Linux_X86_64' }

{'LibreOffice_project/00m0$Build-2}{\info{\author' }

{'fahrekin' }

{'}{\creatim\yr2023\mo12\dy8\hr6\min39}{\author' }

{'fahrekin' }

{'}{\revtim\yr2023\mo12\dy8\hr6\min42}{\printim\yr0\mo0\dy0\hr0\min0}}\deftab709↵\viewscale100↵{\*\pgdsctbl↵{\pgdsc0\pgdscuse451\pgwsxn12240\pghsxn15840\marglsxn1134\margrsxn1134\margtsxn1134\margbsxn1134\pgdscnxt0' }

{'Default' }

{'Style;}}↵\formshade\paperh15840\paperw12240\margl1134\margr1134\margt1134\margb1134\sectd\sbknone\sectunlocked1\pgndec\pgwsxn12240\pghsxn15840\marglsxn1134\margrsxn1134\margtsxn1134\margbsxn1134\ftnbj\ftnstart1\ftnrstcont\ftnnar\aenddoc\aftnrstcont\aftnstart1\aftnnrlc↵{\*\ftnsep\chftnsep}\pgndec\pard\plain' }

{'\s0\nowidctlpar\hyphpar0\cf0\kerning1\dbch\af5\langfe2052\dbch\af6\afs24\alang1081\loch\f3\fs24\lang1033{\rtlch' }

{'\ltrch\loch↵blah' }

{'blah' }

{'blah' }

{'}↵\par' }

{'\pard\plain' }

{'\s0\nowidctlpar\hyphpar0\cf0\kerning1\dbch\af5\langfe2052\dbch\af6\afs24\alang1081\loch\f3\fs24\lang1033{\cf18\rtlch' }

{'\ltrch\loch↵apple}{\rtlch' }

{'\ltrch\loch↵' }

{'}{\cf7\rtlch' }

{'\ltrch\loch↵banana}{\rtlch' }

{'\ltrch\loch↵' }

{'}{\cf17\rtlch' }

{'\ltrch\loch↵orange}↵\par' }

{'\pard\plain' }

{'\s0\nowidctlpar\hyphpar0\cf0\kerning1\dbch\af5\langfe2052\dbch\af6\afs24\alang1081\loch\f3\fs24\lang1033{\b\ab\rtlch' }

{'\ltrch\loch↵cat' }

{'dog' }

{'hamster}↵\par' }

{'\pard\plain' }

{'\s0\nowidctlpar\hyphpar0\cf0\kerning1\dbch\af5\langfe2052\dbch\af6\afs24\alang1081\loch\f3\fs24\lang1033{\rtlch' }

{'\ltrch\loch↵word1' }

{'}{\i\ai\rtlch' }

{'\ltrch\loch↵word1}{\rtlch' }

{'\ltrch\loch↵' }

{'word2' }

{'}{\ul\ulc0\rtlch' }

{'\ltrch\loch↵word3}{\rtlch' }

{'\ltrch\loch↵' }

{'word3' }

{'word3}↵\par' }

{'}'