def test_tokenizer_initial_special_case_explain(en_vocab):
tokenizer = Tokenizer(
en_vocab,
token_match=re.compile("^id$").match,
rules={
"id": [{"ORTH": "i"}, {"ORTH": "d"}],
},
)
tokens = [t.text for t in tokenizer("id")]
explain_tokens = [t[1] for t in tokenizer.explain("id")]
assert tokens == explain_tokens
def test_tokenizer_explain_special_matcher(en_vocab):
suffix_re = re.compile(r"[\.]$")
infix_re = re.compile(r"[/]")
rules = {"a.": [{"ORTH": "a."}]}
tokenizer = Tokenizer(
en_vocab,
rules=rules,
suffix_search=suffix_re.search,
infix_finditer=infix_re.finditer,
)
tokens = [t.text for t in tokenizer("a/a.")]
explain_tokens = [t[1] for t in tokenizer.explain("a/a.")]
assert tokens == explain_tokens
def test_tokenizer_infix_prefix(en_vocab):
# the prefix and suffix matches overlap in the suffix lookbehind
infixes = ["±"]
suffixes = ["%"]
infix_re = compile_infix_regex(infixes)
suffix_re = compile_suffix_regex(suffixes)
tokenizer = Tokenizer(
en_vocab,
infix_finditer=infix_re.finditer,
suffix_search=suffix_re.search,
)
tokens = [t.text for t in tokenizer("±10%")]
assert tokens == ["±10", "%"]
explain_tokens = [t[1] for t in tokenizer.explain("±10%")]
assert tokens == explain_tokens
def test_tokenizer_prefix_suffix_overlap_lookbehind(en_vocab):
# the prefix and suffix matches overlap in the suffix lookbehind
prefixes = ["a(?=.)"]
suffixes = [r"(?<=\w)\.", r"(?<=a)\d+\."]
prefix_re = compile_prefix_regex(prefixes)
suffix_re = compile_suffix_regex(suffixes)
tokenizer = Tokenizer(
en_vocab,
prefix_search=prefix_re.search,
suffix_search=suffix_re.search,
)
tokens = [t.text for t in tokenizer("a10.")]
assert tokens == ["a", "10", "."]
explain_tokens = [t[1] for t in tokenizer.explain("a10.")]
assert tokens == explain_tokens
