Coding dojo in Minsk session result for 2019-01-26

chemistry.py

"""
See the full table at http://www.hemi.nsu.ru/mends.htm
"""

MENDELEEV_TABLE = {
    'H': 1,
    'He': 4,
    'Li': 7,
    'Be': 9,
    'B': 11,
    'C': 12,
    'N': 14,
    'O': 16,
    'F': 19,
    'Ne': 20,
    'Na': 23,
    'Mg': 24,
    'Al': 27,
    'Si': 28,
    'P': 31,
    'S': 32,
    'Cl': 35,
    'Ar': 40,
    'K': 39,
    'Ca': 40,
    'Sc': 45,
    'Ti': 48,
    'V': 51,
    'Cr': 52,
    'Mn': 55,
    'Fe': 56,
    'Co': 59,
    'Ni': 59,
    'Cu': 64,
    'Zn': 65,
    'Ga': 70,
    'Ge': 73,
    'As': 75,
    'Se': 79,
    'Br': 80,
    'Kr': 84,
}


def molar_mass(text):
    """
    See https://en.wikipedia.org/wiki/Molar_mass

    >>> molar_mass('H2O')
    18
    >>> molar_mass('C2H5OH')
    46
    >>> molar_mass('H2SO4')
    98
    """
    return sum(
        MENDELEEV_TABLE[atom] * amount
        for atom, amount in parse_molekula(text)
    )


def parse_molekula(text):
    """
    >>> parse_molekula('C2H5')
    [['C', 2], ['H', 5]]
    >>> parse_molekula('OH')
    [['O', 1], ['H', 1]]
    >>> parse_molekula('NaCl')
    [['Na', 1], ['Cl', 1]]
    """

    tokens = tokenize(text)
    result = []
    for atom_group in tokens:
        atom = ''
        amount = ''
        for c in atom_group:
            if c.isalpha():
                atom += c
            elif c.isdigit():
                amount += c
        result.append([atom, int(amount if amount else 1)])

    return result




def tokenize(text):
    """
    >>> tokenize('NaCl')
    ['Na', 'Cl']
    >>> tokenize('H2O')
    ['H2', 'O']
    """
    result = []
    buffer = ''
    for c in text:
        if c.isupper() and buffer == '':
            buffer += c
        elif c.islower():
            buffer += c
        elif c.isdigit():
            buffer += c
        elif c.isupper():
            result.append(buffer)
            buffer = c
    if buffer != '':
        result.append(buffer)
    return result

compress.py

#! -*- coding: utf-8 -*-

import chemistry


def compress_string(text):
    """
    Написать фукнцию, которая будет "сжимать" переданную строку.
    Вместо повтора символов будет указывать сколько раз символ повторялся.

    >>> compress_string('aaabbbbcddd')
    'a3b4cd3'
    >>> compress_string('abcdefgh')
    'abcdefgh'
    >>> compress_string('aaaaabaaaaa')
    'a5ba5'
    >>> compress_string('')
    ''
    """
    if text == '':
        return ''

    result = []
    for char, count in split(text):
        result.append(char + str(count if count > 1 else ''))
    return ''.join(result)


def split(text):
    last, count = text[0], 1
    for char in text[1:]:
        if char == last:
            count += 1
        else:
            yield last, count
            last = char
            count = 1
    yield last, count


def decompress_string(text):
    """
    Написать функцию обратную compress_string
    
    >>> compress_string('a3b4cd3')
    'aaabbbbcddd'
    >>> compress_string('abcdefgh')
    'abcdefgh'
    >>> compress_string('a5ba5')
    'aaaaabaaaaa'
    >>> compress_string('')
    ''
    """
    if text == '':
        return ''

    result = []
    last = text[0]
    for char in text[1:]:
        if char.isdigit():
            count += char
        elif char != last:
            result.append(last * int(count or 1))
            count = ''
            last = char

    result.append(last * int(count or 1))
    return ''.join(result)


if __name__ == '__main__':
    import doctest
    doctest.testmod()