#!/usr/bin/env python3

# code generated by "translate.py.pss" a pep script
# bumble.sf.net/books/pars/
import sys, re    # for sys.read(), write() and regex
from unicodedata import category # for matching classes

class Machine: 
  # make a new machine 
  def __init__(self):
    self.size = 100      # how many elements in stack/tape/marks
    self.eof = False     # end of stream reached?
    self.charsRead = 0   # how many chars already read
    self.linesRead = 1   # how many lines already read
    self.escape = "\\"
    self.delimiter = "*" # push/pop delimiter (default "*")
    self.counter = 0     # a counter for anything
    self.work = ""       # the workspace
    self.stack = []      # stack for parse tokens 
    self.cell = 0                # current tape cell
    self.tape = [""]*self.size   # a list of attribute for tokens 
    self.marks = [""]*self.size  # marked tape cells
    # or dont initialse peep until "parse()" calls "setInput()"
    self.peep = sys.stdin.read(1)

  def printSizeError(self):
    print("tape max size exceeded!"); 
    print("tape maximum size = " + str(self.size)); 
    print("tape cell (current) = " + str(self.cell)); 
    print("You can increase the self.size value in the python script "); 
    print("but normally this error indicates an error in your parsing "); 
    print("script. The only exception would be massively nested structures"); 
    print("in the source data.");

  def setInput(self, newInput): 
    print("to be implemented")

  # read one character from the input stream and 
  #    update the machine.
  def read(self): 
    if self.eof: System.exit(0)
    self.charsRead += 1;
    # increment lines
    if self.peep == "\n": self.linesRead += 1
    self.work += self.peep
    self.peep = sys.stdin.read(1) 
    if not self.peep: self.eof = True

  # increment tape pointer by one: trivial method in python 
  def increment(self):
    self.cell += 1
  
  # test if all chars in workspace are in unicode category
  def isInCategory(self, cat): 
    for ch in self.work:
      if not category(ch).startswith(cat): return False
    return True

  # def  
  # remove escape character: trivial method ?
  def unescapeChar(self, c):
    if len(self.work) > 0:
      self.work = self.work.replace("\\"+c, c)

  # add escape character : trivial
  def escapeChar(self, c):
    if len(self.work) > 0:
      self.work = self.work.replace(c, "\\"+c)

  # a helper function for the multiple escape char bug
  def countEscaped(self, suffix): 
    count = 0
    if self.work.endswith(suffix):
      s = self.work.removesuffix(suffix)
    while s.endswith(self.escape):
      count += 1
      s = s.removesuffix(self.escape)
    return count

  # reads the input stream until the workspace end with text 
  def until(self, suffix): 
    # read at least one character
    if self.eof: return
    self.read()
    while True: 
      if self.eof: return
      # no. bug! count the trailing escape chars, odd=continue, even=stop
      if self.work.endswith(suffix):
        #and (not self.work.endswith(self.escape + suffix)): 
        if self.countEscaped(suffix) % 2 == 0: return
      self.read()
    
  # pop the first token from the stack into the workspace */
  def pop(self): 
    if len(self.stack) == 0: return False
    self.work = mm.stack.pop() + self.work
    if self.cell > 0: self.cell -= 1
    return True

  # push the first token from the workspace to the stack 
  def push(self): 
    # dont increment the tape pointer on an empty push
    if len(self.work) == 0: return False
    # need to get this from the delimiter.
    iFirst = self.work.find(self.delimiter);
    if iFirst == -1:
      self.stack.append(self.work)
      self.work = "" 
      return True
    self.stack.append(self.work[0:iFirst+1])
    self.work = self.work[iFirst+1:]
    if self.cell < self.size: 
      self.cell += 1
    else:
      self.printSizeError(self);
      exit()
    return True

  # this function is not used (the code is "inlined") 
  def swap(self): 
    s = self.work
    self.work = self.tape[self.cell]
    self.tape[self.cell] = s

  def writeToFile(self): 
    f = open("sav.pp", "w")
    f.write(self.work) 
    f.close() 

  def printState(self): 
    print("Stack[" + ",".join(self.stack) + 
      "] Work[" + self.work + "] Peep[" + self.peep + "]");
    print("Acc:" + str(self.counter) + " Esc:" + self.escape +
          " Delim:" + self.delimiter + " Chars:" + str(self.charsRead) +
          " Lines:" + str(self.linesRead) + " Cell:" + str(self.cell));

  # this is where the actual parsing/compiling code should go
  # so that it can be used by other python classes/objects. Also
  # should have a stream argument.
  def parse(self, s): 
    # a reset or "setinput()" method would be useful to parse a 
    # different string/file/stream, without creating a new
    # machine object.
    # could use code like this to check if input is string or file
    if isinstance(s, file):
      print("")
      # self.reset(s)
      # self.reader = s
    elif isinstance(s, string):
      f = StringIO.StringIO("test")
      for line in f: print(line)
    else:
      f = sys.stdin
    sys.stdout.write("not implemented")


# end of Machine class definition

# will become:
# mm.parse(sys.stdin)  or 
# mm.parse("abcdef") or
# open f; mm.parse(f)

temp = ""    
mm = Machine() 
mm.work += ""
mm.work += "\n    An attempt at basic natural language parsing. "
mm.work += "\n    Use the following words in simple sentences: "
mm.work += "\n"
mm.work += "\n     articles: the, this, her, his, a, one, some, "
mm.work += "\n     preposition: up, in, at, on, with, under, to"
mm.work += "\n     adjectives: simple, big, small, blue, beautiful, small,"
mm.work += "\n     nouns: flower, tree, dog, house, horse, girl, fish, meat,"
mm.work += "\n     verbs: runs, eats, sleeps, is, grows, digs, sings"
mm.work += "\n"
mm.work += "\n    End the sentence with a full stop \".\""
mm.work += "\n      eg: the small dog eats fish."
mm.work += "\n      eg: the simple horse runs on the house ."
mm.work += "\n   .\n"
sys.stdout.write(mm.work) # print
mm.work = ''              # clear
while (not mm.eof): 
  
  # lex block 
  while True: 
    mm.read()           # read
    if (mm.work.isalpha()):
      # while  
      while mm.work.isalpha():
        if mm.eof:  break
        mm.read()
      mm.tape[mm.cell] = mm.work  # put 
      if (mm.work == "the" or mm.work == "this" or mm.work == "her" or mm.work == "his" or mm.work == "a" or mm.work == "one" or mm.work == "some"):
        mm.work = ''              # clear
        mm.work += "article*"
        mm.push();
        break
      if (mm.work == "up" or mm.work == "in" or mm.work == "at" or mm.work == "on" or mm.work == "with" or mm.work == "under" or mm.work == "to"):
        mm.work = ''              # clear
        mm.work += "preposition*"
        mm.push();
        break
      if (mm.work == "simple" or mm.work == "big" or mm.work == "small" or mm.work == "blue" or mm.work == "beautiful" or mm.work == "small"):
        mm.work = ''              # clear
        mm.work += "adjective*"
        mm.push();
        break
      if (mm.work == "flower" or mm.work == "tree" or mm.work == "dog" or mm.work == "house" or mm.work == "horse" or mm.work == "girl" or mm.work == "fish" or mm.work == "meat"):
        mm.work = ''              # clear
        mm.work += "noun*"
        mm.push();
        break
      if (mm.work == "runs" or mm.work == "eats" or mm.work == "sleeps" or mm.work == "is" or mm.work == "grows" or mm.work == "digs" or mm.work == "sings"):
        mm.work = ''              # clear
        mm.work += "verb*"
        mm.push();
        break
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "<"
      mm.work += mm.tape[mm.cell] # get
      mm.work += ">"
      mm.work += " Sorry, don't understand that word! \n"
      sys.stdout.write(mm.work) # print
      mm.work = ''              # clear
      exit()
    # use a full-stop to complete sentence
    if (mm.work == "."):
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "dot*"
      mm.push();
    # ignore every thing else
    mm.work = ''              # clear
    break 
  
  # parse block 
  while True:  
    # 2 tokens
    mm.pop();
    mm.pop();
    if (mm.work == "article*noun*"):
      mm.work = ''              # clear
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      if mm.cell > 0: mm.cell -= 1  # --
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "nounphrase*"
      mm.push();
      continue
    if (mm.work == "verb*preposition*"):
      mm.work = ''              # clear
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      if mm.cell > 0: mm.cell -= 1  # --
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "verbphrase*"
      mm.push();
      continue
    # 3 tokens
    mm.pop();
    if (mm.work == "noun*verb*dot*" or mm.work == "nounphrase*verb*dot*" or mm.work == "noun*verbphrase*dot*" or mm.work == "nounphrase*verbphrase*dot*"):
      mm.work = ''              # clear
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      if mm.cell > 0: mm.cell -= 1  # --
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "sentence*"
      mm.push();
      continue
    if (mm.work == "article*adjective*noun*"):
      mm.work = ''              # clear
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      if mm.cell > 0: mm.cell -= 1  # --
      if mm.cell > 0: mm.cell -= 1  # --
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "nounphrase*"
      mm.push();
      continue
    # 4 tokens
    mm.pop();
    if (mm.work == "nounphrase*verb*noun*dot*" or mm.work == "noun*verb*noun*dot*" or mm.work == "nounphrase*verb*nounphrase*dot*" or mm.work == "noun*verb*nounphrase*dot*" or mm.work == "nounphrase*verbphrase*nounphrase*dot*" or mm.work == "noun*verbphrase*nounphrase*dot*" or mm.work == "nounphrase*verbphrase*noun*dot*" or mm.work == "noun*verbphrase*noun*dot*"):
      mm.work = ''              # clear
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      mm.work += " "
      mm.cell += 1                  # ++
      mm.work += mm.tape[mm.cell] # get
      if mm.cell > 0: mm.cell -= 1  # --
      if mm.cell > 0: mm.cell -= 1  # --
      mm.tape[mm.cell] = mm.work  # put 
      mm.work = ''              # clear
      mm.work += "sentence*"
      mm.push();
      continue
    mm.push();
    mm.push();
    mm.push();
    mm.push();
    if (mm.eof):
      mm.pop();
      mm.pop();
      if (mm.work == "sentence*"):
        mm.work = ''              # clear
        mm.work += "It's an english sentence! \n("
        mm.work += mm.tape[mm.cell] # get
        mm.work += ") \n"
        mm.work += "But it may not make sense! \n"
        sys.stdout.write(mm.work) # print
        mm.work = ''              # clear
        exit()
      if (mm.work == "nounphrase*"):
        mm.work = ''              # clear
        mm.work += "its a noun-phrase! ("
        mm.work += mm.tape[mm.cell] # get
        mm.work += ") \n"
        sys.stdout.write(mm.work) # print
        mm.work = ''              # clear
        exit()
      if (mm.work == "verbphrase*"):
        mm.work = ''              # clear
        mm.work += "its a verb-phrase! ("
        mm.work += mm.tape[mm.cell] # get
        mm.work += ") \n"
        sys.stdout.write(mm.work) # print
        mm.work = ''              # clear
        exit()
      mm.push();
      mm.push();
      mm.work += "nope, not a sentence. \n"
      sys.stdout.write(mm.work) # print
      mm.work = ''              # clear
      mm.work += "The parse stack was: \n  "
      sys.stdout.write(mm.work) # print
      mm.work = ''              # clear
      while (mm.pop()):  continue    # unstack 
      mm.work += "\n"
      sys.stdout.write(mm.work) # print
      exit()
    break # parse
  

# end of generated code