def get_splits(run_on_word, num_splits, lexicon):
"""Return all possible valid splits for run_on_word.
TODO: Check for validity of each word.
TODO: Use DP and memoize valid word splits for substrings.
"""
# List of all valid indices that a string can be partitioned at.
all_indices = range(1, len(run_on_word))
valid_split_indices = itertools.combinations(all_indices, num_splits)
valid_split_indices = [list(tuple_) for tuple_ in valid_split_indices]
crude_splits_list = [partition(run_on_word, index_list)
for index_list in valid_split_indices]
return [str_tuple for str_tuple in crude_splits_list
if all(lexicon.is_known_word(word) for word in str_tuple)]
def get_splits(run_on_word, num_splits, lexicon):
"""Return all possible valid splits for run_on_word.
TODO: Check for validity of each word.
TODO: Use DP and memoize valid word splits for substrings.
"""
# List of all valid indices that a string can be partitioned at.
all_indices = range(1, len(run_on_word))
valid_split_indices = itertools.combinations(all_indices, num_splits)
valid_split_indices = [list(tuple_) for tuple_ in valid_split_indices]
crude_splits_list = [
partition(run_on_word, index_list)
for index_list in valid_split_indices
]
return [
str_tuple for str_tuple in crude_splits_list if all(
lexicon.is_known_word(word) for word in str_tuple)
]
def get_corrected_split_queries(query, lexicon):
"""Correct split query by joining words.
Return list of word/phrase/sentence queries with the split words joined.
Assumption: a word has been split only once.
Note: The original query is NOT part of the returned list.
Arguments:
- `query`: Suggestion object
- `lexicon`: lexicon of the spell checker
"""
# TODO: Should probably check to see if the resultant suggestion
# is a word/phrase/suggestion and then set its suggestion_type.
# eg. 'No w.' (sentence) -> 'Now.' (word)
joined_up_suggestion_list = [
Suggestion(query[:i] + [query[i] + query[i + 1]] + query[i+2:],
suggestion_type = query.suggestion_type)
for i in range(len(query) - 1)
if lexicon.is_known_word(query[i] + query[i + 1])]
return joined_up_suggestion_list
def get_corrected_split_queries(query, lexicon):
"""Correct split query by joining words.
Return list of word/phrase/sentence queries with the split words joined.
Assumption: a word has been split only once.
Note: The original query is NOT part of the returned list.
Arguments:
- `query`: Suggestion object
- `lexicon`: lexicon of the spell checker
"""
# TODO: Should probably check to see if the resultant suggestion
# is a word/phrase/suggestion and then set its suggestion_type.
# eg. 'No w.' (sentence) -> 'Now.' (word)
joined_up_suggestion_list = [
Suggestion(query[:i] + [query[i] + query[i + 1]] + query[i + 2:],
suggestion_type=query.suggestion_type)
for i in range(len(query) - 1)
if lexicon.is_known_word(query[i] + query[i + 1])
]
return joined_up_suggestion_list