Я не уверен, насколько это легко, поскольку в нем используются некоторые более продвинутые концепции, такие как генераторы, но, по крайней мере, они надежны и хорошо документированы. Фактический код находится внизу и довольно лаконичен.
Основная идея заключается в том, что функция iter_delim_sets возвращает итератор для (или последовательность) кортежей, содержащих номер строки, набор индексов в «ожидаемой» строке, где был найден разделитель, и аналогичный набор для «фактическая» строка. Существует один такой кортеж, сгенерированный для каждой пары (ожидаемых, результирующих) строк. Эти кортежи кратко формализованы в тип collections.namedtuple, называемый DelimLocations.
Тогда функция analyze просто возвращает информацию более высокого уровня, основанную на таком наборе данных, сохраненную в DelimAnalysis namedtuple. Это делается с использованием алгебры базовых множеств.
"""Compare two sequences of strings.
Test data:
>>> from pprint import pprint
>>> delimiter = '||'
>>> expected = (
... delimiter.join(("one", "fish", "two", "fish")),
... delimiter.join(("red", "fish", "blue", "fish")),
... delimiter.join(("I do not like them", "Sam I am")),
... delimiter.join(("I do not like green eggs and ham.",)))
>>> actual = (
... delimiter.join(("red", "fish", "blue", "fish")),
... delimiter.join(("one", "fish", "two", "fish")),
... delimiter.join(("I do not like spam", "Sam I am")),
... delimiter.join(("I do not like", "green eggs and ham.")))
The results:
>>> pprint([analyze(v) for v in iter_delim_sets(delimiter, expected, actual)])
[DelimAnalysis(index=0, correct=2, incorrect=1, count_diff=0),
DelimAnalysis(index=1, correct=2, incorrect=1, count_diff=0),
DelimAnalysis(index=2, correct=1, incorrect=0, count_diff=0),
DelimAnalysis(index=3, correct=0, incorrect=1, count_diff=1)]
What they mean:
>>> pprint(delim_analysis_doc)
(('index',
('The number of the lines from expected and actual',
'used to perform this analysis.')),
('correct',
('The number of delimiter placements in ``actual``',
'which were correctly placed.')),
('incorrect', ('The number of incorrect delimiters in ``actual``.',)),
('count_diff',
('The difference between the number of delimiters',
'in ``expected`` and ``actual`` for this line.')))
And a trace of the processing stages:
>>> def dump_it(it):
... '''Wraps an iterator in code that dumps its values to stdout.'''
... for v in it:
... print v
... yield v
>>> for v in iter_delim_sets(delimiter,
... dump_it(expected), dump_it(actual)):
... print v
... print analyze(v)
... print '======'
one||fish||two||fish
red||fish||blue||fish
DelimLocations(index=0, expected=set([9, 3, 14]), actual=set([9, 3, 15]))
DelimAnalysis(index=0, correct=2, incorrect=1, count_diff=0)
======
red||fish||blue||fish
one||fish||two||fish
DelimLocations(index=1, expected=set([9, 3, 15]), actual=set([9, 3, 14]))
DelimAnalysis(index=1, correct=2, incorrect=1, count_diff=0)
======
I do not like them||Sam I am
I do not like spam||Sam I am
DelimLocations(index=2, expected=set([18]), actual=set([18]))
DelimAnalysis(index=2, correct=1, incorrect=0, count_diff=0)
======
I do not like green eggs and ham.
I do not like||green eggs and ham.
DelimLocations(index=3, expected=set([]), actual=set([13]))
DelimAnalysis(index=3, correct=0, incorrect=1, count_diff=1)
======
"""
from collections import namedtuple
# Data types
## Here ``expected`` and ``actual`` are sets
DelimLocations = namedtuple('DelimLocations', 'index expected actual')
DelimAnalysis = namedtuple('DelimAnalysis',
'index correct incorrect count_diff')
## Explanation of the elements of DelimAnalysis.
## There's no real convenient way to add a docstring to a variable.
delim_analysis_doc = (
('index', ("The number of the lines from expected and actual",
"used to perform this analysis.")),
('correct', ("The number of delimiter placements in ``actual``",
"which were correctly placed.")),
('incorrect', ("The number of incorrect delimiters in ``actual``.",)),
('count_diff', ("The difference between the number of delimiters",
"in ``expected`` and ``actual`` for this line.")))
# Actual functionality
def iter_delim_sets(delimiter, expected, actual):
"""Yields a DelimLocations tuple for each pair of strings.
``expected`` and ``actual`` are sequences of strings.
"""
from re import escape, compile as compile_
from itertools import count, izip
index = count()
re = compile_(escape(delimiter))
def delimiter_locations(string):
"""Set of the locations of matches of ``re`` in ``string``."""
return set(match.start() for match in re.finditer(string))
string_pairs = izip(expected, actual)
return (DelimLocations(index=index.next(),
expected=delimiter_locations(e),
actual=delimiter_locations(a))
for e, a in string_pairs)
def analyze(locations):
"""Returns an analysis of a DelimLocations tuple.
``locations.expected`` and ``locations.actual`` are sets.
"""
return DelimAnalysis(
index=locations.index,
correct=len(locations.expected & locations.actual),
incorrect=len(locations.actual - locations.expected),
count_diff=(len(locations.actual) - len(locations.expected)))