Parser Notebook from More Adventures in Python Talk

TestPyPeg2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/Users/paulmuston/anaconda/envs/ipython/bin/python'"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import sys\n",
    "sys.executable"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "reference https://fdik.org/pyPEG/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pypeg2 import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "example = \"\"\"int f(int a, long b)\n",
    "{\n",
    "    do_this;\n",
    "    do_that;\n",
    "}\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class Type(Keyword):\n",
    "  grammar = Enum( K(\"int\"), K(\"long\") )\n",
    "\n",
    "class Parameter:\n",
    "  grammar = attr(\"typing\", Type), name()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<__main__.Parameter at 0x107f79278>"
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a = parse(\"int a\", Parameter)\n",
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['__class__',\n",
       " '__delattr__',\n",
       " '__dict__',\n",
       " '__dir__',\n",
       " '__doc__',\n",
       " '__eq__',\n",
       " '__format__',\n",
       " '__ge__',\n",
       " '__getattribute__',\n",
       " '__gt__',\n",
       " '__hash__',\n",
       " '__init__',\n",
       " '__init_subclass__',\n",
       " '__le__',\n",
       " '__lt__',\n",
       " '__module__',\n",
       " '__ne__',\n",
       " '__new__',\n",
       " '__reduce__',\n",
       " '__reduce_ex__',\n",
       " '__repr__',\n",
       " '__setattr__',\n",
       " '__sizeof__',\n",
       " '__str__',\n",
       " '__subclasshook__',\n",
       " '__weakref__',\n",
       " 'grammar',\n",
       " 'name',\n",
       " 'position_in_text',\n",
       " 'typing']"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Symbol('a'), Type('int'))"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a.name, a.typing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'__add__,__class__,__contains__,__delattr__,__dict__,__dir__,__doc__,__eq__,__format__,__ge__,__getattribute__,__getitem__,__getnewargs__,__gt__,__hash__,__init__,__init_subclass__,__iter__,__le__,__len__,__lt__,__mod__,__module__,__mul__,__ne__,__new__,__reduce__,__reduce_ex__,__repr__,__rmod__,__rmul__,__setattr__,__sizeof__,__str__,__subclasshook__,__weakref__,capitalize,casefold,center,check_keywords,count,encode,endswith,expandtabs,find,format,format_map,index,isalnum,isalpha,isdecimal,isdigit,isidentifier,islower,isnumeric,isprintable,isspace,istitle,isupper,join,ljust,lower,lstrip,maketrans,name,namespace,partition,position_in_text,regex,replace,rfind,rindex,rjust,rpartition,rsplit,rstrip,split,splitlines,startswith,strip,swapcase,title,translate,upper,zfill'"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\",\".join(dir(a.name))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Symbol('b'), Type('long'))"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b = parse(\"long b\", Parameter)\n",
    "b.name, b.typing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Parameters(Namespace):\n",
    "    grammar = optional(csl(Parameter))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "odict_keys([Symbol('a'), Symbol('b')])"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parms = parse(\"int a, long b\", Parameters)\n",
    "parms.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['a isa int', 'b isa long']\n"
     ]
    }
   ],
   "source": [
    "print([\"{} isa {}\".format(x.name,x.typing) for x in parms.values()])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class Function(List):\n",
    "    grammar = attr(\"typing\", Type), name(), \\\n",
    "            \"(\", attr(\"parms\", Parameters), \")\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Symbol('f'),\n",
       " Type('int'),\n",
       " Parameters([(Symbol('a'), <__main__.Parameter object at 0x1087aafd0>), (Symbol('b'), <__main__.Parameter object at 0x1087b2128>), ]))"
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f = parse(\"int f(int a, long b)\", Function)\n",
    "f.name, f.typing, f.parms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'int f(int a, long b)\\n{\\n    do_this;\\n    do_that;\\n}'"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class Instruction(str):\n",
    "  grammar = word, \";\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "block = \"{\", maybe_some(Instruction), \"}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "b = parse(\"{\\n    do_this;\\n    do_that;\\n}\", block)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['do_this', 'do_that']"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Function(List):\n",
    "    grammar = attr(\"typing\", Type), name(), \\\n",
    "            \"(\", attr(\"parms\", Parameters), \")\", \\\n",
    "            block"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Function(['do_this', 'do_that'], name=Symbol('f'))"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f = parse(example,Function)\n",
    "f"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Symbol('f'), Type('int'), 'do_this', 'do_that')"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f.name, f.typing, f[0], f[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['a isa int', 'b isa long']\n"
     ]
    }
   ],
   "source": [
    "print([\"{} isa {}\".format(x.name,x.typing) for x in f.parms.values()])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}