interpreter_class.py

Go to the documentation of this file.

 
 
from io import StringIO
 
 
 
class Interpreter_Class:
    
    PERIOD = 100
    
    QUESTION = 101
 
    
    _commonwords = [
        "the",
        "be",
        "to",
        "of",
        "and",
        "a",
        "in",
        "that",
        "have",
        "I",
        "it",
        "for",
        "not",
        "on",
        "with",
        "he",
        "as",
        "you",
        "do",
        "at",
        "this",
        "but",
        "his",
        "by",
        "from",
        "they",
        "we",
        "say",
        "her",
        "she",
        "or",
        "an",
        "will",
        "my",
        "one",
        "all",
        "would",
        "there",
        "their",
        "what",
    ]
 
 
    
    def _InterpretToken(self, token : int) -> str:
        tokenAsString = ""
 
        # Rule 1: token is between 0 and the number of common words.
        if token >= 0 and token < len(Interpreter_Class._commonwords):
            tokenAsString = Interpreter_Class._commonwords[token]
        else:
            # Rule 1: token can also be a PERIOD
            if token == Interpreter_Class.PERIOD:
                tokenAsString = "."
            # Rule 1: or the token can also be a QUESTION
            elif token == Interpreter_Class.QUESTION:
                tokenAsString = "?"
            else:
                # Rule 1: Invalid tokens returned in a string.
                tokenAsString = "<UNKNOWN TOKEN {0}>".format(token)
 
        return tokenAsString;
 
 
    
    def Interpret(self, tokens : list[int]) -> str:
        output = StringIO()
 
        numTokens = len(tokens)
 
        for tokenIndex in range(0, numTokens):
            # Rule 1: Interpret token
            tokenAsString = self._InterpretToken(tokens[tokenIndex])
            if tokenIndex == 0:
                # Rule 2: First word in sentence gets capitalized according to local rules.
                tokenAsString = tokenAsString.title()
            output.write(tokenAsString)
 
            # Rule 4: No space between last two tokens (if the following expression is false)
            if tokenIndex + 2 < numTokens:
                # Rule 3: Separate all words by a single space.
                output.write(" ")
 
        return output.getvalue()