Fix typo in documentation of __str__ of Token

README.md

@@ -1,2 +1,4 @@
-# lsbasi
-Let's Build A Simple Interpreter
+Source code for the series **Let's Build A Simple Interpreter**
+
++ [Let's Build A Simple Interpreter. Part 1.](http://ruslanspivak.com/lsbasi-part1/)
++ [Let's Build A Simple Interpreter. Part 2.](http://ruslanspivak.com/lsbasi-part2/)

part1/calc1.py

@@ -0,0 +1,130 @@
+# Token types
+#
+# EOF (end-of-file) token is used to indicate that
+# there is no more input left for lexical analysis
+INTEGER, PLUS, EOF = 'INTEGER', 'PLUS', 'EOF'
+
+
+class Token(object):
+    def __init__(self, type, value):
+        # token type: INTEGER, PLUS, or EOF
+        self.type = type
+        # token value: 0, 1, 2. 3, 4, 5, 6, 7, 8, 9, '+', or None
+        self.value = value
+
+    def __str__(self):
+        """String representation of the class instance.
+
+        Examples:
+            Token(INTEGER, 3)
+            Token(PLUS, '+')
+        """
+        return 'Token({type}, {value})'.format(
+            type=self.type,
+            value=repr(self.value)
+        )
+
+    def __repr__(self):
+        return self.__str__()
+
+
+class Interpreter(object):
+    def __init__(self, text):
+        # client string input, e.g. "3+5"
+        self.text = text
+        # self.pos is an index into self.text
+        self.pos = 0
+        # current token instance
+        self.current_token = None
+
+    def error(self):
+        raise Exception('Error parsing input')
+
+    def get_next_token(self):
+        """Lexical analyzer (also known as scanner or tokenizer)
+
+        This method is responsible for breaking a sentence
+        apart into tokens. One token at a time.
+        """
+        text = self.text
+
+        # is self.pos index past the end of the self.text ?
+        # if so, then return EOF token because there is no more
+        # input left to convert into tokens
+        if self.pos > len(text) - 1:
+            return Token(EOF, None)
+
+        # get a character at the position self.pos and decide
+        # what token to create based on the single character
+        current_char = text[self.pos]
+
+        # if the character is a digit then convert it to
+        # integer, create an INTEGER token, increment self.pos
+        # index to point to the next character after the digit,
+        # and return the INTEGER token
+        if current_char.isdigit():
+            token = Token(INTEGER, int(current_char))
+            self.pos += 1
+            return token
+
+        if current_char == '+':
+            token = Token(PLUS, current_char)
+            self.pos += 1
+            return token
+
+        self.error()
+
+    def eat(self, token_type):
+        # compare the current token type with the passed token
+        # type and if they match then "eat" the current token
+        # and assign the next token to the self.current_token,
+        # otherwise raise an exception.
+        if self.current_token.type == token_type:
+            self.current_token = self.get_next_token()
+        else:
+            self.error()
+
+    def expr(self):
+        """expr -> INTEGER PLUS INTEGER"""
+        # set current token to the first token taken from the input
+        self.current_token = self.get_next_token()
+
+        # we expect the current token to be a single-digit integer
+        left = self.current_token
+        self.eat(INTEGER)
+
+        # we expect the current token to be a '+' token
+        op = self.current_token
+        self.eat(PLUS)
+
+        # we expect the current token to be a single-digit integer
+        right = self.current_token
+        self.eat(INTEGER)
+        # after the above call the self.current_token is set to
+        # EOF token
+
+        # at this point INTEGER PLUS INTEGER sequence of tokens
+        # has been successfully found and the method can just
+        # return the result of adding two integers, thus
+        # effectively interpreting client input
+        result = left.value + right.value
+        return result
+
+
+def main():
+    while True:
+        try:
+            # To run under Python3 replace 'raw_input' call
+            # with 'input'
+            text = raw_input('calc> ')
+        except EOFError:
+            break
+        if not text:
+            continue
+        interpreter = Interpreter(text)
+        result = interpreter.expr()
+        print(result)
+
+
+if __name__ == '__main__':
+    main()

part1/factorial.pas

@@ -0,0 +1,17 @@
+program factorial;
+
+function factorial(n: integer): longint;
+begin
+    if n = 0 then
+        factorial := 1
+    else
+        factorial := n * factorial(n - 1);
+end;
+
+var
+    n: integer;
+
+begin
+    for n := 0 to 16 do
+        writeln(n, '! = ', factorial(n));
+end.

part2/calc2.py

@@ -0,0 +1,154 @@
+# Token types
+# EOF (end-of-file) token is used to indicate that
+# there is no more input left for lexical analysis
+INTEGER, PLUS, MINUS, EOF = 'INTEGER', 'PLUS', 'MINUS', 'EOF'
+
+
+class Token(object):
+    def __init__(self, type, value):
+        # token type: INTEGER, PLUS, MINUS, or EOF
+        self.type = type
+        # token value: non-negative integer value, '+', '-', or None
+        self.value = value
+
+    def __str__(self):
+        """String representation of the class instance.
+
+        Examples:
+            Token(INTEGER, 3)
+            Token(PLUS '+')
+        """
+        return 'Token({type}, {value})'.format(
+            type=self.type,
+            value=repr(self.value)
+        )
+
+    def __repr__(self):
+        return self.__str__()
+
+
+class Interpreter(object):
+    def __init__(self, text):
+        # client string input, e.g. "3 + 5", "12 - 5", etc
+        self.text = text
+        # self.pos is an index into self.text
+        self.pos = 0
+        # current token instance
+        self.current_token = None
+        self.current_char = self.text[self.pos]
+
+    def error(self):
+        raise Exception('Error parsing input')
+
+    def advance(self):
+        """Advance the 'pos' pointer and set the 'current_char' variable."""
+        self.pos += 1
+        if self.pos > len(self.text) - 1:
+            self.current_char = None  # Indicates end of input
+        else:
+            self.current_char = self.text[self.pos]
+
+    def skip_whitespace(self):
+        while self.current_char is not None and self.current_char.isspace():
+            self.advance()
+
+    def integer(self):
+        """Return a (multidigit) integer consumed from the input."""
+        result = ''
+        while self.current_char is not None and self.current_char.isdigit():
+            result += self.current_char
+            self.advance()
+        return int(result)
+
+    def get_next_token(self):
+        """Lexical analyzer (also known as scanner or tokenizer)
+
+        This method is responsible for breaking a sentence
+        apart into tokens.
+        """
+        while self.current_char is not None:
+
+            if self.current_char.isspace():
+                self.skip_whitespace()
+                continue
+
+            if self.current_char.isdigit():
+                return Token(INTEGER, self.integer())
+
+            if self.current_char == '+':
+                self.advance()
+                return Token(PLUS, '+')
+
+            if self.current_char == '-':
+                self.advance()
+                return Token(MINUS, '-')
+
+            self.error()
+
+        return Token(EOF, None)
+
+    def eat(self, token_type):
+        # compare the current token type with the passed token
+        # type and if they match then "eat" the current token
+        # and assign the next token to the self.current_token,
+        # otherwise raise an exception.
+        if self.current_token.type == token_type:
+            self.current_token = self.get_next_token()
+        else:
+            self.error()
+
+    def expr(self):
+        """Parser / Interpreter
+
+        expr -> INTEGER PLUS INTEGER
+        expr -> INTEGER MINUS INTEGER
+        """
+        # set current token to the first token taken from the input
+        self.current_token = self.get_next_token()
+
+        # we expect the current token to be an integer
+        left = self.current_token
+        self.eat(INTEGER)
+
+        # we expect the current token to be either a '+' or '-'
+        op = self.current_token
+        if op.type == PLUS:
+            self.eat(PLUS)
+        else:
+            self.eat(MINUS)
+
+        # we expect the current token to be an integer
+        right = self.current_token
+        self.eat(INTEGER)
+        # after the above call the self.current_token is set to
+        # EOF token
+
+        # at this point either the INTEGER PLUS INTEGER or
+        # the INTEGER MINUS INTEGER sequence of tokens
+        # has been successfully found and the method can just
+        # return the result of adding or subtracting two integers,
+        # thus effectively interpreting client input
+        if op.type == PLUS:
+            result = left.value + right.value
+        else:
+            result = left.value - right.value
+        return result
+
+
+def main():
+    while True:
+        try:
+            # To run under Python3 replace 'raw_input' call
+            # with 'input'
+            text = raw_input('calc> ')
+        except EOFError:
+            break
+        if not text:
+            continue
+        interpreter = Interpreter(text)
+        result = interpreter.expr()
+        print(result)
+
+
+if __name__ == '__main__':
+    main()