pyparsing example

Pyparsion.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:977a530fe07ef0f070bef944a04bc6a483233573b0bf17ae77e06a0d82e02e52"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Pyparsing - python parsing library\n",
      "\n",
      "Pavel Tysliatski\n",
      "\n",
      "Expansa Group"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Common\n",
      "\n",
      "Site: http://pyparsing.wikispaces.com/\n",
      "\n",
      "Common information: http://pyparsing.wikispaces.com/HowToUsePyparsing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from pyparsing import *\n",
      "from string import *"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## ParserElement subclasses"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Basic subclasses\n",
      "\n",
      "    Literal\n",
      "    Word\n",
      "    Regex\n",
      "    SkipTo\n",
      "\n",
      "and etc."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Expression subclasses\n",
      "\n",
      "    Or - |\n",
      "    And - ^\n",
      "    Optional\n",
      "    ZeroOrMore\n",
      "    OneOrMore\n",
      "\n",
      "and etc."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Positional subclasses\n",
      "\n",
      "    StringStart\n",
      "    StringEnd\n",
      "    LineStart\n",
      "    LineEnd"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Converter subclasses\n",
      "\n",
      "    Suppress\n",
      "\n",
      "and etc."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Parser actions\n",
      "\n",
      "    setParserAction\n",
      "    addParserAction"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Base example\n",
      "Make parser:\n",
      "\n",
      "    [0-9]"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def action(s, loc, toks):\n",
      "    print('s', type(s), s)\n",
      "    print('loc', type(loc), loc)\n",
      "    print('toks', type(toks), toks)\n",
      "    return ['<'] + list(toks) + ['>']\n",
      "\n",
      "\n",
      "pattern = Suppress('[') + Word(digits) + '-' + Word(digits).setParseAction(action) + Suppress(']')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Parsing methods"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### parseString"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.parseString('[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s <class 'str'> [0-9]\n",
        "loc <class 'int'> 3\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "(['0', '-', '<', '9', '>'], {})"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# >>> pattern.parseString('test[0-9]test')\n",
      "# ParseException: Expected \"[\" (at char 0), (line:1, col:1)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### searchString"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.searchString('test[0-9]test')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s <class 'str'> test[0-9]test\n",
        "loc <class 'int'> 7\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "([(['0', '-', '<', '9', '>'], {})], {})"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.searchString('test[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s <class 'str'> test[0-9]test[0-9]\n",
        "loc <class 'int'> 7\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n",
        "s <class 'str'> test[0-9]test[0-9]\n",
        "loc <class 'int'> 16\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 6,
       "text": [
        "([(['0', '-', '<', '9', '>'], {}), (['0', '-', '<', '9', '>'], {})], {})"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### scanString"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "list(pattern.scanString('test[0-9]test'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s <class 'str'> test[0-9]test\n",
        "loc <class 'int'> 7\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "[((['0', '-', '<', '9', '>'], {}), 4, 9)]"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "list(pattern.scanString('test[0-9]test[0-9]'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s <class 'str'> test[0-9]test[0-9]\n",
        "loc <class 'int'> 7\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n",
        "s <class 'str'> test[0-9]test[0-9]\n",
        "loc <class 'int'> 16\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "[((['0', '-', '<', '9', '>'], {}), 4, 9),\n",
        " ((['0', '-', '<', '9', '>'], {}), 13, 18)]"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### transformString"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.transformString('test[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "s <class 'str'> test[0-9]test[0-9]\n",
        "loc <class 'int'> 7\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n",
        "s <class 'str'> test[0-9]test[0-9]\n",
        "loc <class 'int'> 16\n",
        "toks <class 'pyparsing.ParseResults'> ['9']\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "'test0-<9>test0-<9>'"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## More complex example\n",
      "\n",
      "Make iterator:\n",
      "\n",
      "    text_block[numeric_block][numeric_block]text_block...\n",
      "    \n",
      "For example:\n",
      "\n",
      "    >>> te\\[\\]st\\\\\\\\[0-9]test[0-9]\n",
      "    te[]st\\\\0test0\n",
      "    te[]st\\\\0test1\n",
      "    te[]st\\\\0test2\n",
      "    ...\n",
      "    te[]st\\\\9test7\n",
      "    te[]st\\\\9test8\n",
      "    te[]st\\\\9test9"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Parser"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "text = SkipTo(StringEnd() | '[')\n",
      "numeric = Suppress('[') + Word(digits) + Suppress('-') + Word(digits) + Suppress(']')\n",
      "pattern = ZeroOrMore(text | numeric)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def skip_empty(toks):\n",
      "    if not toks[0]:\n",
      "        raise ParseException('must be not empty')\n",
      "        \n",
      "\n",
      "text.addParseAction(skip_empty)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "SkipTo:({StringEnd | \"[\"})"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.parseString('test[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "(['test', '0', '9', 'test', '0', '9'], {})"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.parseString('te\\[\\]st\\\\\\\\[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "(['te\\\\'], {})"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Escaping"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "escape = (Literal('\\\\\\\\').addParseAction(replaceWith('\\\\')) | \n",
      "          Literal('\\\\[').addParseAction(replaceWith('[')) |\n",
      "          Literal('\\\\]').addParseAction(replaceWith(']')))\n",
      "text = SkipTo(StringEnd() | '[', ignore=escape).setParseAction(skip_empty)\n",
      "pattern = ZeroOrMore(text | numeric)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.parseString('te\\[\\]st\\\\\\\\[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "(['te\\\\[\\\\]st\\\\\\\\', '0', '9', 'test', '0', '9'], {})"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def unescape(toks):\n",
      "    return [escape.transformString(item) for item in toks]\n",
      "\n",
      "\n",
      "text.addParseAction(unescape)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 16,
       "text": [
        "SkipTo:({StringEnd | \"[\"})"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.parseString('te\\[\\]st\\\\\\\\[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 17,
       "text": [
        "(['te[]st\\\\', '0', '9', 'test', '0', '9'], {})"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Iterator"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def text_block(toks):\n",
      "    return [iter(toks)]\n",
      "    \n",
      "    \n",
      "def numeric_block(toks):\n",
      "    from_value, to_value = toks\n",
      "    return [map(str, range(int(from_value), int(to_value) + 1))]\n",
      "\n",
      "\n",
      "text.addParseAction(text_block)\n",
      "numeric.addParseAction(numeric_block)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "{Suppress:(\"[\") W:(0123...) Suppress:(\"-\") W:(0123...) Suppress:(\"]\")}"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "pattern.parseString('te\\[\\]st\\\\\\\\[0-9]test[0-9]')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "([<list_iterator object at 0x7f35380c7fd0>, <map object at 0x7f35381252b0>, <list_iterator object at 0x7f3538125278>, <map object at 0x7f3538100668>], {})"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from itertools import product\n",
      "\n",
      "\n",
      "def iterator(string):\n",
      "    return (''.join(items) for items in product(*pattern.parseString(string)))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 20
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### Test"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "len(list(iterator('te\\[\\]st\\\\\\\\[0-9]test[0-9]')))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 21,
       "text": [
        "100"
       ]
      }
     ],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "list(iterator('te\\[\\]st\\\\\\\\[0-9]test[0-9]'))[:3]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "['te[]st\\\\0test0', 'te[]st\\\\0test1', 'te[]st\\\\0test2']"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "list(iterator('te\\[\\]st\\\\\\\\[0-9]test[0-9]'))[-3:]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 23,
       "text": [
        "['te[]st\\\\9test7', 'te[]st\\\\9test8', 'te[]st\\\\9test9']"
       ]
      }
     ],
     "prompt_number": 23
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Questions?\n",
      "\n",
      "[email protected]"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}