mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +03:00
2ea9b58006
* Ignore prefix in suffix matches
Ignore the currently matched prefix when looking for suffix matches in
the tokenizer. Otherwise a lookbehind in the suffix pattern may match
incorrectly due the presence of the prefix in the token string.
* Move °[cfkCFK]. to a tokenizer exception
* Adjust exceptions for same tokenization as v3.1
* Also update test accordingly
* Continue to split . after °CFK if ° is not a prefix
* Exclude new ° exceptions for pl
* Switch back to default tokenization of "° C ."
* Revert "Exclude new ° exceptions for pl"
This reverts commit 952013a5b4.
* Add exceptions for °C for hu
54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
import sys
|
|
import pytest
|
|
|
|
|
|
def test_tokenizer_handles_emoticons(tokenizer):
|
|
# Tweebo challenge (CMU)
|
|
text = (
|
|
""":o :/ :'( >:o (: :) >.< XD -__- o.O ;D :-) @_@ :P 8D :1 >:( :D =| :> ...."""
|
|
)
|
|
tokens = tokenizer(text)
|
|
assert tokens[0].text == ":o"
|
|
assert tokens[1].text == ":/"
|
|
assert tokens[2].text == ":'("
|
|
assert tokens[3].text == ">:o"
|
|
assert tokens[4].text == "(:"
|
|
assert tokens[5].text == ":)"
|
|
assert tokens[6].text == ">.<"
|
|
assert tokens[7].text == "XD"
|
|
assert tokens[8].text == "-__-"
|
|
assert tokens[9].text == "o.O"
|
|
assert tokens[10].text == ";D"
|
|
assert tokens[11].text == ":-)"
|
|
assert tokens[12].text == "@_@"
|
|
assert tokens[13].text == ":P"
|
|
assert tokens[14].text == "8D"
|
|
assert tokens[15].text == ":1"
|
|
assert tokens[16].text == ">:("
|
|
assert tokens[17].text == ":D"
|
|
assert tokens[18].text == "=|"
|
|
assert tokens[19].text == ":>"
|
|
assert tokens[20].text == "...."
|
|
|
|
|
|
@pytest.mark.parametrize("text,length", [("108)", 2), ("XDN", 1)])
|
|
def test_tokenizer_excludes_false_pos_emoticons(tokenizer, text, length):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length", [("can you still dunk?🍕🍔😵LOL", 8), ("i💙you", 3), ("🤘🤘yay!", 4)]
|
|
)
|
|
def test_tokenizer_handles_emoji(tokenizer, text, length):
|
|
# These break on narrow unicode builds, e.g. Windows
|
|
if sys.maxunicode >= 1114111:
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
def test_tokenizer_degree(tokenizer):
|
|
for u in "cfkCFK":
|
|
assert [t.text for t in tokenizer(f"°{u}.")] == ["°", f"{u}", "."]
|
|
assert [t[1] for t in tokenizer.explain(f"°{u}.")] == ["°", f"{u}", "."]
|