We Keep Coding

How to create a cyclic iterator over the alphabet in Python?

Given the following scenario:
import string
UPPERCASE_ALPHABET = list(string.ascii_uppercase)
LOWERCASE_ALPHABET = list(string.ascii_lowercase)
How to create a cyclic loop over the alphabet jumping N positions?
Example 1:
letter = a, jump = 5
Result: f
Example 2:
letter = z, jump = 5
Result: e
So far, I got:
import string
UPPERCASE_ALPHABET = list(string.ascii_uppercase)
LOWERCASE_ALPHABET = list(string.ascii_lowercase)
def forward(letter, jump):
alphabet = LOWERCASE_ALPHABET if letter.islower() else UPPERCASE_ALPHABET
index = alphabet.index(letter)
count = 0
while True:
if count == jump:
return alphabet[index]
if index == len(alphabet):
index = 0
index += 1
count += 1
print forward('a', 5)
print forward('z', 5)
But it doesn't look Pythonic at all...
Is there a better and Pythonic way of doing this? Maybe using chr(ord('N') + position) ?

I think you had the right idea with ord and chr:
import string
def forward(letter, jump):
if letter.islower():
start_character = ord('a')
else:
start_character = ord('A')
start = ord(letter) - start_character
offset = ((start + jump) % 26) + start_character
result = chr(offset)
return result
print forward('a', 5)
print forward('z', 5)
print forward('z', 1)
print forward('a', 26)
print forward('A', 5)
print forward('Z', 5)
print forward('Z', 1)
print forward('A', 26)
Output
f
e
a
a
F
E
A
A

I'd write a custom iterator class to encapsulate itertools.cycle() and provide a skip() functionality, e.g.:
import itertools
class CyclicSkipIterator(object):
def __init__(self, iterable):
self._iterator = itertools.cycle(iterable)
def __iter__(self):
return self
def next(self): # use __next__ on Python 3.x
return next(self._iterator)
def skip(self, number=1):
for i in xrange(number): # use range() on Python 3.x
next(self._iterator)
Then you can do exactly what you wanted with it:
import string
LOWERCASE_ALPHABET = list(string.ascii_lowercase)
lower_iter = CyclicSkipIterator(LOWERCASE_ALPHABET)
print(next(lower_iter)) # a
lower_iter.skip(4) # skip next 4 letters: b, c, d, e
print(next(lower_iter)) # f
lower_iter.skip(19) # skip another 19 letters to arrive at z
print(next(lower_iter)) # z
lower_iter.skip(4) # skip next 4 letters: a, b, c, d
print(next(lower_iter)) # e
You can add even more functionality if you wanted to, like reversing, switching iterables mid-iteration etc.
UPDATE: If you want to jump to a specific element in the list, you can add a method for that to the CyclicSkipIterator:
class CyclicSkipIterator(object):
def __init__(self, iterable):
self._iterator = itertools.cycle(iterable)
def __iter__(self):
return self
def __next__(self): # use __next__ on Python 3.x
return next(self._iterator)
def skip(self, number=1):
for _ in range(number): # use range() on Python 3.x
next(self._iterator)
def skip_to(self, element, max_count=100): # max_count protects against endless cycling
max_count = max(1, max_count) # ensure at least one iteration
for _ in range(max_count): # use range() on Python 3.x
e = next(self._iterator)
if element == e:
break
Then you can skip_to whatever letter you want:
import string
LOWERCASE_ALPHABET = list(string.ascii_lowercase)
lower_iter = CyclicSkipIterator(LOWERCASE_ALPHABET)
print(next(lower_iter)) # a
lower_iter.skip(4) # skip 4 letters: b, c, d, e
print(next(lower_iter)) # f
lower_iter.skip_to("y") # skip all letters up to y
print(next(lower_iter)) # z
lower_iter.skip(4) # skip 4 letters: a, b, c, d
print(next(lower_iter)) # e

class CyclicIterator:
def __init__(self,lst):
self.lst=lst
self.i=0
def __iter__(self):
return self
def __next__(self):
result=self.lst[self.i % len(self.lst)]
self.i+=3 #increasing by 3
return result
class that has iter() and next() meets iterator protocol. creating an instance of this iterator class
iter_cycle=CyclicIterator('abcdefghiijklmnnoprstuvyz')
numbers=range(1,27,3) # 26 letters increases by 3
list(zip(list(numbers),iter_cycle))

Instances of class polynomial

How can I get coefficients to list from three different ways of creating new instances of class Polynomial?
class Polynomial(object)
def __init__(self,*args)
self.coeffs=[]
...
pol1 = Polynomial([1,-3,0,2])
pol2 = Polynomial(1,-3,0,2)
pol3 = Polynomial(x0=1,x3=2­,x1=-3)
I am expecting for example: pol2 = Polynomial(1,-3,0,2), output is 2x^3-3x+1. But I need to get coefficients to list to work with them.

Assuming, that one of the three ways is always used, you can do the following (without any validation):
class Polynomial(object):
def __init__(self, *args, **kwargs):
if args and isinstance(args[0], list): # Polynomial([1,-3,0,2])
self.coeffs=args[0]
elif args: # Polynomial(1,-3,0,2)
self.coeffs=args
else: # Polynomial(x0=1,x3=2­,x1=-3)
self.coeffs=[kwargs.get(x, 0) for x in ('x0', 'x1', 'x2', 'x3')]
def __str__(self):
s = ''
for i, x in reversed(list(enumerate(self.coeffs))):
if x:
if x > 0:
s += '+'
s += str(x)
if i > 0:
s += 'x'
if i > 1:
s += '^' + str(i)
return '0' if not s else s.lstrip('+')
pol1 = Polynomial([1,-3,0,2])
pol2 = Polynomial(1,-3,0,2)
pol3 = Polynomial(x0=1, x1=-3, x3=2)
print(pol1) # 2x^3-3x+1
print(pol2) # 2x^3-3x+1
print(pol3) # 2x^3-3x+1

In addition to schwobaseggl's response, I'd add this kind of checking:
if type(args[0]) == list:
self.coeffs=args
# ...
else:
self.coeffs=[kwargs.get(x, 0) for x in ['x'+i for i in range(len(kwargs))]]

Why does this character ▯ appear?

So this character ▯ appears when I run my code which I think means there is a missing character therefor it can't be displayed. (Not sure correct me if I am wrong) And well basically I want to be able to get rid of that character. Here is what it looks like when I run my code:
However in the back-end in the idle when I click on one of the boxes for it to be displayed up top it doesn't register and looks like this in idle:
Why does it appear on screen if it isn't going to appear in idle?
Also how can I get rid of the ▯ character from the main screen?
Here is my full code.
Here are segments in which I think the problem lies. (However I have not been able to solve the problem)
My classes for Tree comparison to find the sentences and their frequent use:
class Branch():
def __init__(self, value):
self.left = None
self.right = None
self.value = value
self.frequency = 1
def incFreq(self):
self.frequency = self.frequency + 1
def freq(self):
return self.frequency
class Tree():
highest = []
def __init__(self):
self.root = None
self.found = False
def findHighest(self):
from operator import itemgetter, attrgetter
self.highest = []
self.inorder(self.root)
self.highest = sorted(self.highest, key=itemgetter(1), reverse=True)
return self.highest
#lessThan function needed to compare strings
def lessThan(self, a, b):
if len(a) < len(b):
loopCount = len(a)
else:
loopCount = len(b)
for pos in range(0, loopCount):
if a[pos] > b[pos]:
return False
return True
def outputTree(self):
self.inorder(self.root)
def insert(self, value):
#increment freq if already exists, else insert
if not self.exists(value):
self.root = self.insertAtBranch(self.root, value)
def exists(self, value):
#set the class variable found to False to assume it is not there
self.found = False
self.findAtBranch(self.root, value)
return self.found
#Used to fine a value in a tree
def findAtBranch(self, branch, value):
if branch == None:
pass
else:
#print ("[" + branch.value + "][" + value + "]") # Error checking
if branch.value == value:
self.found = True
#print("found " + value)
branch.incFreq()
#print(branch.freq())
else:
self.findAtBranch(branch.left, value)
self.findAtBranch(branch.right, value)
def insertAtBranch(self, branch, value):
if branch == None:
return Branch(value)
else:
if self.lessThan(branch.value, value):
branch.right = self.insertAtBranch(branch.right, value)
else:
branch.left = self.insertAtBranch(branch.left, value)
return branch
def inorder(self, branch):
if branch == None: return
self.highest.append((branch.value, branch.freq()))
#print (branch.value)
#print (branch.freq())
#print(self.highest[0])
self.inorder(branch.left)
self.inorder(branch.right)
This is where I use the tree and pass sentences to be used on a different function:
def getPhrases(self, numToReturn):
topPhrases = []
phrasesTree = Tree()
#load tree with phrases from phrase text file
file = open('setPhrases.txt', 'r')
for line in file:
phrasesTree.insert(line)
#create a list of the top n of phrases to return
val = 0
for phrase in phrasesTree.findHighest():
if val < numToReturn:
topPhrases.append(phrase)
val = val + 1
return topPhrases
This is where I use the sentences to be able to display them on the screen:
def createPhrases(self):
print("createPhrases")
self.deletePanes()
self.show_keyboard = False
self.show_words = False
self.show_phrases = True
self.show_terminal = True
words = self.getPhrases(10)
for word, count in words:
self.addPane("{}".format(word, count), WORDS)
self.addPane("Boxes", PHRASE)
self.addPane("Keyboard", PHRASE)
self.addPane("OK", PHRASE)
self.drawPanes()

When you read lines from file, newline characters are at the end. pygame's documentation states that:
The text can only be a single line: newline characters are not rendered.
So, you should change this fragment:
file = open('setPhrases.txt', 'r')
for line in file:
phrasesTree.insert(line)
to this:
file = open('setPhrases.txt', 'r')
for line in file:
phrasesTree.insert(line.strip())

Python compiler for simple language to java vm code algorithm

I have a simple language that I am trying to write a compiler for (yes it is homework) to compile a simple language I shall describe if necessary to java vm code.
It currently works pretty well I've just hit a bump with logical AND's and OR's.
Each work fine in a single if/while condition, but if I try and chain them things go wrong, correct me if I am wrong but I believe that AND has precedence, but I was wondering if there are logical ways of arranging them? I think is what I'm trying to ask, the java vm code output just has the compare and jump statements one after the other (which seems wrong). I realise it's quite abstract so maybe what I'm after is a pseudo code/algorithm for how to structure chained AND's and OR's.
EDIT: Currently just treats any combination of AND and OR as AND's. Comparing the factor/term/expression connection (compared to booleanfactor etc) I believe that AND has precedence? Just a thought.
Apologies if this is poorly understood :/
So i figure ill include relevant info just incase.
compiler
import re
import sys
# Restrictions:
# Integer constants must be short.
# Stack size must not exceed 1024.
# Integer is the only type.
# Logical operators cannot be nested.
class Scanner:
'''The interface comprises the methods lookahead and consume.
Other methods should not be called from outside of this class.'''
def __init__(self, input_file):
'''Reads the whole input_file to input_string.'''
# source code of the program to be compiled
self.input_string = input_file.read()
# index where the unprocessed part of input_string starts
self.current_char_index = 0
# a pair (most recently read token, matched substring of input_string)
self.current_token = self.get_token()
def skip_white_space(self):
'''Consumes all characters in input_string up to the next
non-white-space character.'''
if (self.current_char_index >= len(self.input_string) - 1):
# bad fix for it over-running the end of the file
return
while self.input_string[self.current_char_index].isspace():
self.current_char_index += 1
return
def get_token(self):
'''Returns the next token and the part of input_string it matched.
Returns None if there is no next token.
The characters up to the end of the token are consumed.'''
self.skip_white_space()
# find the longest prefix of input_string that matches a token
token, longest = None, ''
for (t, r) in Token.token_regexp:
match = re.match(r, self.input_string[self.current_char_index:])
if match and match.end() > len(longest):
token, longest = t, match.group()
# consume the token by moving the index to the end of the matched part
self.current_char_index += len(longest)
return (token, longest)
def lookahead(self):
'''Returns the next token without consuming it.
Returns None if there is no next token.'''
return self.current_token[0]
def consume(self, *tokens):
'''Returns the next token and consumes it, if it is in tokens.
Raises an exception otherwise.
If the token is a number or an identifier, its value is returned.'''
if self.current_token[0] not in tokens:
print('Token ' + self.current_token[0] + ' isn\'t in the tokens: ')
for token in tokens:
print(token)
raise Exception('Token is not in tokens this shouldn\'t happen much')
if self.current_token[0] == 'ID':
symbol_table.location(self.current_token[1])
value = self.current_token[1]
elif (self.current_token[0] == 'NUM'):
value = self.current_token[1]
else:
value = self.current_token[0]
self.current_token = self.get_token()
return value
class Token:
DO = 'DO';
ELSE = 'ELSE';
END = 'END';
IF = 'IF';
THEN = 'THEN';
WHILE = 'WHILE';
SEM = 'SEM';
BEC = 'BEC';
LESS = 'LESS';
EQ = 'EQ';
GRTR = 'GRTR';
LEQ = 'LEQ';
NEQ = 'NEQ';
GEQ = 'GEQ';
ADD = 'ADD';
SUB = 'SUB';
MUL = 'MUL';
DIV = 'DIV';
LPAR = 'LPAR';
RPAR = 'RPAR';
NUM = 'NUM';
ID = 'ID';
READ = 'READ';
WRITE = 'WRITE';
OR = 'OR';
AND = 'AND';
NOT = 'NOT';
# The following list gives the regular expression to match a token.
# The order in the list matters for mimicking Flex behaviour.
# Longer matches are preferred over shorter ones.
# For same-length matches, the first in the list is preferred.
token_regexp = [
(DO, 'do'),
(ELSE, 'else'),
(END, 'end'),
(IF, 'if'),
(THEN, 'then'),
(WHILE, 'while'),
(READ, 'read'),
(WRITE, 'write'),
(OR, 'or'),
(AND, 'and'),
(NOT, 'not'),
(SEM, ';'),
(BEC, ':='),
(LESS, '<'),
(EQ, '='),
(NEQ, '!='),
(GRTR, '>'),
(LEQ, '<='),
(GEQ, '>='),
(ADD, '[+]'), # + is special in regular expressions
(SUB, '-'),
(MUL, '[*]'),
(DIV, '/'),
(LPAR, '[(]'), # ( is special in regular expressions
(RPAR, '[)]'), # ) is special in regular expressions
(ID, '[a-z]+'),
(NUM, '[0-9]+'),
]
class Symbol_Table:
'''A symbol table maps identifiers to locations.'''
def __init__(self):
self.symbol_table = {}
def size(self):
'''Returns the number of entries in the symbol table.'''
return len(self.symbol_table)
def location(self, identifier):
'''Returns the location of an identifier. If the identifier is not in
the symbol table, it is entered with a new location. Locations are
numbered sequentially starting with 0.'''
if identifier in self.symbol_table:
return self.symbol_table[identifier]
index = len(self.symbol_table)
self.symbol_table[identifier] = index
return index
class Label:
def __init__(self):
self.current_label = 0
def next(self):
'''Returns a new, unique label.'''
self.current_label += 1
return 'l' + str(self.current_label)
def indent(s, level):
return ' '*level + s + '\n'
# Each of the following classes is a kind of node in the abstract syntax tree.
# indented(level) returns a string that shows the tree levels by indentation.
# code() returns a string with JVM bytecode implementing the tree fragment.
# true_code/false_code(label) jumps to label if the condition is/is not true.
# Execution of the generated code leaves the value of expressions on the stack.
class Program_AST:
def __init__(self, program):
self.program = program
def __repr__(self):
return repr(self.program)
def indented(self, level):
return self.program.indented(level)
def code(self):
program = self.program.code()
local = symbol_table.size()
java_scanner = symbol_table.location('Java Scanner')
return '.class public Program\n' + \
'.super java/lang/Object\n' + \
'.method public <init>()V\n' + \
'aload_0\n' + \
'invokenonvirtual java/lang/Object/<init>()V\n' + \
'return\n' + \
'.end method\n' + \
'.method public static main([Ljava/lang/String;)V\n' + \
'.limit locals ' + str(local) + '\n' + \
'.limit stack 1024\n' + \
'new java/util/Scanner\n' + \
'dup\n' + \
'getstatic java/lang/System.in Ljava/io/InputStream;\n' + \
'invokespecial java/util/Scanner.<init>(Ljava/io/InputStream;)V\n' + \
'astore ' + str(java_scanner) + '\n' + \
program + \
'return\n' + \
'.end method\n'
class Statements_AST:
def __init__(self, statements):
self.statements = statements
def __repr__(self):
result = repr(self.statements[0])
for st in self.statements[1:]:
result += '; ' + repr(st)
return result
def indented(self, level):
result = indent('Statement(s)', level)
for st in self.statements:
result += st.indented(level+1)
return result
def code(self):
result = ''
for st in self.statements:
result += st.code()
return result
class If_AST:
def __init__(self, boolean_expression, then):
self.boolean_expression = boolean_expression
self.then = then
def __repr__(self):
return 'if ' + repr(self.boolean_expression) + ' then ' + \
repr(self.then) + ' end'
def indented(self, level):
return indent('If-Then', level) + \
self.boolean_expression.indented(level+1) + \
self.then.indented(level+1)
def code(self):
l1 = label_generator.next()
return self.boolean_expression.code(l1) + \
self.then.code() + \
l1 + ':\n'
class If_Else_AST:
def __init__(self, boolean_expression, then, _else):
self.boolean_expression = boolean_expression;
self.then = then;
self._else = _else;
def __repr__(self):
return 'if ' + repr(self.boolean_expression) + ' then ' + \
repr(self.then) + ' else ' + \
repr(self._else) + ' end'
def indented(self, level):
return indent('If-Then-Else', level) + \
self.boolean_expression.indented(level+1) + \
self.then.indented(level+1) + \
indent('Else', level+1) + \
self._else.indented(level+1)
def code(self):
l1 = label_generator.next()
l2 = label_generator.next()
return self.boolean_expression.code(l1) + \
self.then.code() + \
'goto ' + l2 + '\n' + \
l1 + ':\n' + \
self._else.code() + \
l2 + ':\n'
class While_AST:
def __init__(self, boolean_term, body):
self.boolean_term = boolean_term
self.body = body
def __repr__(self):
return 'while ' + repr(self.boolean_term) + ' do ' + \
repr(self.body) + ' end'
def indented(self, level):
return indent('While-Do', level) + \
self.boolean_term.indented(level+1) + \
self.body.indented(level+2)
def code(self):
l1 = label_generator.next()
l2 = label_generator.next()
return l1 + ':\n' + \
self.boolean_term.code(l2) + \
self.body.code() + \
'goto ' + l1 + '\n' + \
l2 + ':\n'
class Assign_AST:
def __init__(self, identifier, expression):
self.identifier = identifier
self.expression = expression
def __repr__(self):
return repr(self.identifier) + ':=' + repr(self.expression)
def indented(self, level):
return indent('Assign', level) + \
self.identifier.indented(level+1) + \
self.expression.indented(level+1)
def code(self):
loc = symbol_table.location(self.identifier.identifier)
return self.expression.code() + \
'istore ' + str(loc) + '\n'
class Write_AST:
def __init__(self, expression):
self.expression = expression
def __repr__(self):
return 'write ' + repr(self.expression)
def indented(self, level):
return indent('Write', level) + self.expression.indented(level+1)
def code(self):
return 'getstatic java/lang/System/out Ljava/io/PrintStream;\n' + \
self.expression.code() + \
'invokestatic java/lang/String/valueOf(I)Ljava/lang/String;\n' + \
'invokevirtual java/io/PrintStream/println(Ljava/lang/String;)V\n'
class Read_AST:
def __init__(self, identifier):
self.identifier = identifier
def __repr__(self):
return 'read ' + repr(self.identifier)
def indented(self, level):
return indent('Read', level) + self.identifier.indented(level+1)
def code(self):
java_scanner = symbol_table.location('Java Scanner')
loc = symbol_table.location(self.identifier.identifier)
return 'aload ' + str(java_scanner) + '\n' + \
'invokevirtual java/util/Scanner.nextInt()I\n' + \
'istore ' + str(loc) + '\n'
class Comparison_AST:
def __init__(self, left, op, right):
self.left = left
self.op = op
self.right = right
def __repr__(self):
op = { Token.LESS:'<', Token.EQ:'=', Token.GRTR:'>',
Token.LEQ:'<=', Token.NEQ:'!=', Token.GEQ:'>=' }
return repr(self.left) + op[self.op] + repr(self.right)
def indented(self, level):
return indent(self.op, level) + \
self.left.indented(level+1) + \
self.right.indented(level+1)
def true_code(self, label):
op = { Token.LESS:'if_icmplt', Token.EQ:'if_icmpeq',
Token.GRTR:'if_icmpgt', Token.LEQ:'if_icmple',
Token.NEQ:'if_icmpne', Token.GEQ:'if_icmpge' }
return self.left.code() + \
self.right.code() + \
op[self.op] + ' ' + label + '\n'
def false_code(self, label):
# Negate each comparison because of jump to "false" label.
op = { Token.LESS:'if_icmpge', Token.EQ:'if_icmpne',
Token.GRTR:'if_icmple', Token.LEQ:'if_icmpgt',
Token.NEQ:'if_icmpeq', Token.GEQ:'if_icmplt' }
return self.left.code() + \
self.right.code() + \
op[self.op] + ' ' + label + '\n'
class Expression_AST:
def __init__(self, left, op, right):
self.left = left
self.op = op
self.right = right
def __repr__(self):
op = { Token.ADD:'+', Token.SUB:'-', Token.MUL:'*', Token.DIV:'/' }
return '(' + repr(self.left) + op[self.op] + repr(self.right) + ')'
def indented(self, level):
return indent(self.op, level) + \
self.left.indented(level+1) + \
self.right.indented(level+1)
def code(self):
op = { Token.ADD:'iadd', Token.SUB:'isub',
Token.MUL:'imul', Token.DIV:'idiv' }
return self.left.code() + \
self.right.code() + \
op[self.op] + '\n'
class Number_AST:
def __init__(self, number):
self.number = number
def __repr__(self):
return self.number
def indented(self, level):
return indent(self.number, level)
def code(self): # works only for short numbers
return 'sipush ' + self.number + '\n'
class Identifier_AST:
def __init__(self, identifier):
self.identifier = identifier
def __repr__(self):
return self.identifier
def indented(self, level):
return indent(self.identifier, level)
def code(self):
loc = symbol_table.location(self.identifier)
return 'iload ' + str(loc) + '\n'
class BooleanFactor_AST:
def __init__(self, condition, logic):
self.condition = condition
self.logic = logic
def __repr__(self):
if self.logic == False:
return 'NOT ' + repr(self.condition)
else:
return repr(self.condition)
def indented(self, level):
if self.logic == False:
return indent('NOT ', level) + self.condition.indented(level + 1)
else:
return self.condition.indented(level)
def false_code(self, label):
if self.logic == True:
return self.condition.false_code(label)
else:
return self.condition.true_code(label)
return
def true_code(self, label):
if self.logic == True:
return self.condition.true_code(label)
else:
return self.condition.false_code(label)
class BooleanTerm_AST:
def __init__(self, terms):
self.terms = terms
def __repr__(self):
result = repr(self.terms[0])
for term in self.terms[1:]:
result = result + ' AND ' + repr(term)
return result
def indented(self, level):
result = self.terms[0].indented(level)
for term in self.terms[1:]:
result = result + indent('AND', level)
result = result + term.indented(level)
return result
def code(self, label):
result = ''
for term in self.terms:
result = result + term.false_code(label)
return result
class BooleanExpression_AST:
def __init__(self, expressions):
self.expressions = expressions
def __repr__(self):
result = repr(self.expressions[0])
for expression in self.expressions[1:]:
result = result + ' OR ' + repr(expression)
return result
def indented(self, level):
result = self.expressions[0].indented(level)
indentation = 0
for expression in self.expressions[1:]:
indentation += 1
result = result + indent('OR', level + indentation)
result = result + expression.indented(level + indentation)
return result
def code(self, label):
result = ''
for expression in self.expressions:
result = result + expression.code(label)
return result
# The following methods comprise the recursive-descent parser.
def program():
sts = statements()
return Program_AST(sts)
def statements():
result = [statement()]
while scanner.lookahead() == Token.SEM:
scanner.consume(Token.SEM)
st = statement()
result.append(st)
return Statements_AST(result)
def statement():
if scanner.lookahead() == Token.IF:
return if_statement()
elif scanner.lookahead() == Token.WHILE:
return while_statement()
elif scanner.lookahead() == Token.ID:
return assignment()
elif scanner.lookahead() == Token.READ:
return read();
elif scanner.lookahead() == Token.WRITE:
return write();
else: # error
return scanner.consume(Token.IF, Token.WHILE, Token.ID)
def if_statement():
scanner.consume(Token.IF)
condition = boolean_expression()
scanner.consume(Token.THEN)
then = statements()
if scanner.lookahead() == Token.END:
scanner.consume(Token.END)
return If_AST(condition, then)
else:
scanner.consume(Token.ELSE)
_else = statements()
scanner.consume(Token.END)
return If_Else_AST(condition, then, _else)
def while_statement():
scanner.consume(Token.WHILE)
condition = boolean_expression()
scanner.consume(Token.DO)
body = statements()
scanner.consume(Token.END)
return While_AST(condition, body)
def assignment():
ident = identifier()
scanner.consume(Token.BEC)
expr = expression()
return Assign_AST(ident, expr)
def read():
scanner.consume(Token.READ)
variable = identifier()
return Read_AST(variable)
def write():
scanner.consume(Token.WRITE)
expr = expression()
return Write_AST(expr)
def comparison():
left = expression()
op = scanner.consume(Token.LESS, Token.EQ, Token.GRTR,
Token.LEQ, Token.NEQ, Token.GEQ)
right = expression()
return Comparison_AST(left, op, right)
def expression():
result = term()
while scanner.lookahead() in [Token.ADD, Token.SUB]:
op = scanner.consume(Token.ADD, Token.SUB)
tree = term()
result = Expression_AST(result, op, tree)
return result
def term():
result = factor()
while scanner.lookahead() in [Token.MUL, Token.DIV]:
op = scanner.consume(Token.MUL, Token.DIV)
tree = factor()
result = Expression_AST(result, op, tree)
return result
def factor():
if scanner.lookahead() == Token.LPAR:
scanner.consume(Token.LPAR)
result = expression()
scanner.consume(Token.RPAR)
return result
elif scanner.lookahead() == Token.NUM:
value = scanner.consume(Token.NUM)
return Number_AST(value)
elif scanner.lookahead() == Token.ID:
return identifier()
else: # error
return scanner.consume(Token.LPAR, Token.NUM, Token.ID)
def identifier():
value = scanner.consume(Token.ID)
return Identifier_AST(value)
def boolean_factor():
if scanner.lookahead() == Token.NOT:
scanner.consume(Token.NOT)
logic = False
else:
logic = True
result = comparison()
return BooleanFactor_AST(result, logic)
def boolean_term():
result = [boolean_factor()]
while scanner.lookahead() in [Token.AND]:
scanner.consume(scanner.lookahead())
temp = boolean_factor()
result.append(temp)
return BooleanTerm_AST(result)
def boolean_expression():
result = [boolean_term()]
while scanner.lookahead() in [Token.OR]:
scanner.consume(scanner.lookahead())
temp = boolean_term()
result.append(temp)
return BooleanExpression_AST(result)
# Initialise scanner, symbol table and label generator.
#scanner = Scanner(open('test.txt'))
scanner = Scanner(sys.stdin)
symbol_table = Symbol_Table()
symbol_table.location('Java Scanner') # fix a location for the Java Scanner
label_generator = Label()
# Uncomment the following to test the scanner without the parser.
# This shows a list of all tokens in the input.
#
#token = scanner.lookahead()
#while token != None:
# print(token)
# scanner.consume(token)
# token = scanner.lookahead()
#exit()
# Call the parser.
ast = program()
assert scanner.lookahead() == None
# Uncomment the following to test the parser without the code generator.
# The first line gives back the program by calling __repr__ of the AST classes.
# The second line shows the syntax tree with levels indicated by indentation.
#
#print(ast)
#print(ast.indented(0))
#exit()
# Call the code generator.
# This translates the abstract syntax tree to JVM bytecode.
# It can be assembled to a class file by Jasmin: http://jasmin.sourceforge.net/
print(ast.code())
testing bat file
python compiler.py <test.txt> Program.j
java -Xmx100m -jar jasmin.jar Program.j
java -Xmx100m Program < testInput.txt > test_output.txt
and language (BNF)
Program = Statements
Statements = Statement (; Statement)
Statement = If | While | Assignment
If = if Comparison then Statements end
While = while Comparison do Statements end
Assignment = identifier := Expression
Comparison = Expression Relation Expression
Relation = = | != | < | <= | > | >=
Expression = Term ((+ | -) Term)
Term = Factor ((* | /) Factor)
Factor = (Expression) | number | identifier
BooleanExpression = BooleanTerm (or BooleanTerm)*
BooleanTerm = BooleanFactor (and BooleanFactor)*
BooleanFactor = not BooleanFactor | Comparison
I think thats all that is relevant, cheers if you take a go at helping me on this

if you want a method to chain OR's and AND'syou can use this property:
p v q === ¬p ^ ¬q
Is equivalent, you can process all in the AND form. for example.
p v q ^ r v s === ¬p ^ ¬q ^ ¬r ^ ¬s
So evaluate the expression in AND form is simple with an algorithm.
I guess the expression doesn't have any parenthesis, in other way you need prioritize the grouping symbols (), [], {}.

python - how to replace all link tags in html with an <em> tag?

I have a routine that converts a long article string into a shorted summary in PHP but rather than do this at page render I'd like to store the summary in a database.
I have everything all sorted out except for replacing link tags with a <em>text</em>. I don't want to use beautiful soup for this, I'd rather some simple regex replace if possible, or perhaps another function of HTMLParser (I couldn't find anything after Googling for a while).
Here's what I have currently:
import HTMLParser, string, re
tag_end_re = re.compile(r'(\w+)[^>]*>')
entity_end_re = re.compile(r'(\w+;)')
class StrippingParser(HTMLParser.HTMLParser):
# These are the HTML tags that we will leave intact
valid_tags = ('a')
from htmlentitydefs import entitydefs # replace entitydefs from sgmllib
def __init__(self):
HTMLParser.HTMLParser.__init__(self)
self.result = ""
self.endTagList = []
def handle_data(self, data):
if data:
self.result = self.result + data
def handle_charref(self, name):
self.result = "%s&#%s;" % (self.result, name)
def handle_entityref(self, name):
if self.entitydefs.has_key(name):
x = ';'
else:
# this breaks unstandard entities that end with ';'
x = ''
self.result = "%s&%s%s" % (self.result, name, x)
def handle_starttag(self, tag, attrs):
""" Delete all tags except for legal ones """
if tag in self.valid_tags:
self.result = self.result + '<' + tag
for k, v in attrs:
if string.lower(k[0:2]) != 'on' and string.lower(v[0:10]) != 'javascript':
self.result = '%s %s="%s"' % (self.result, k, v)
endTag = '</%s>' % tag
self.endTagList.insert(0,endTag)
self.result = self.result + '>'
def handle_endtag(self, tag):
if tag in self.valid_tags:
self.result = "%s</%s>" % (self.result, tag)
remTag = '</%s>' % tag
self.endTagList.remove(remTag)
def cleanup(self):
""" Append missing closing tags """
for j in range(len(self.endTagList)):
self.result = self.result + self.endTagList[j]
def strip(s):
""" Strip illegal HTML tags from string s """
parser = StrippingParser()
parser.feed(s)
parser.close()
parser.cleanup()
return parser.result
def truncate_html(string, length, ellipsis='...'):
"""Truncate HTML string, preserving tag structure and character entities."""
length = int(length)
output_length = 0
i = 0
pending_close_tags = {}
while output_length < length and i < len(string):
c = string[i]
if c == '<':
# probably some kind of tag
if i in pending_close_tags:
# just pop and skip if it's closing tag we already knew about
i += len(pending_close_tags.pop(i))
else:
# else maybe add tag
i += 1
match = tag_end_re.match(string[i:])
if match:
tag = match.groups()[0]
i += match.end()
# save the end tag for possible later use if there is one
match = re.search(r'(</' + tag + '[^>]*>)', string[i:], re.IGNORECASE)
if match:
pending_close_tags[i + match.start()] = match.groups()[0]
else:
output_length += 1 # some kind of garbage, but count it in
elif c == '&':
# possible character entity, we need to skip it
i += 1
match = entity_end_re.match(string[i:])
if match:
i += match.end()
# this is either a weird character or just '&', both count as 1
output_length += 1
else:
# plain old characters
skip_to = string.find('<', i, i + length)
if skip_to == -1:
skip_to = string.find('&', i, i + length)
if skip_to == -1:
skip_to = i + length
# clamp
delta = min(skip_to - i,
length - output_length,
len(string) - i)
output_length += delta
i += delta
output = [string[:i]]
if output_length == length:
output.append(ellipsis)
for k in sorted(pending_close_tags.keys()):
output.append(pending_close_tags[k])
return "".join(output)
def summarize(contents,length):
summary = strip(contents)
summary = truncate_html(summary,length)
return summary
Calling summarize('my long text with links',400) currently returns a 400 character (excluding html tags) containing links. I need help replacing those links with tags.

You can use a simple regex for this:
import re
'<em>' + re.search(r'<a.+>(.+)</a>',r'my long text with links').group(1) + '</em>'