ユニコードテキストを分割するためのテストケースがありますが、その方法はわかりません。ここでユニコードと句読点付きのJavascript regexp
describe("garden: utils",() => {
it("should split correctly",() => {
assert.deepEqual(segmentation('Hockey is a popular sport in Canada.'), [
'Hockey', 'is', 'a', 'popular', 'sport', 'in', 'Canada', '.'
]);
assert.deepEqual(segmentation('How many provinces are there in Canada?'), [
'How', 'many', 'provinces', 'are', 'there', 'in', 'Canada', '?'
]);
assert.deepEqual(segmentation('The forest is on fire!'), [
'The', 'forest', 'is', 'on', 'fire', '!'
]);
assert.deepEqual(segmentation('Emily Carr, who was born in 1871, was a great painter.'), [
'Emily', 'Carr', ',', 'who', 'was', 'born', 'in', '1871', ',', 'was', 'a', 'great', 'painter', '.'
]);
assert.deepEqual(segmentation('This is David\'s computer.'), [
'This', 'is', 'David', '\'', 's', 'computer', '.'
]);
assert.deepEqual(segmentation('The prime minister said, "We will win the election."'), [
'The', 'prime', 'minister', 'said', ',', '"', 'We', 'will', 'win', 'the', 'election', '.', '"'
]);
assert.deepEqual(segmentation('There are three positions in hockey: goalie, defence, and forward.'), [
'There', 'are', 'three', 'positions', 'in', 'hockey', ':', 'goalie', ',', 'defence', ',', 'and', 'forward', '.'
]);
assert.deepEqual(segmentation('The festival is very popular; people from all over the world visit each year.'), [
'The', 'festival', 'is', 'very', 'popular', ';', 'people', 'from', 'all', 'over', 'the', 'world',
'visit', 'each', 'year', '.'
]);
assert.deepEqual(segmentation('Mild, wet, and cloudy - these are the characteristics of weather in Vancouver.'), [
'Mild', ',', 'wet', ',', 'and', 'cloudy', '-', 'these', 'are', 'the', 'characteristics', 'of', 'weather',
'in', 'Vancouver', '.'
]);
assert.deepEqual(segmentation('sweet-smelling'), [
'sweet', '-', 'smelling'
]);
});
it("should not split unicoded words",() => {
assert.deepEqual(segmentation('hacer a propósito'), [
'hacer', 'a', 'propósito'
]);
assert.deepEqual(segmentation('nhà em có con mèo'), [
'nhà', 'em', 'có', 'con', 'mèo'
]);
});
it("should group periods",() => {
assert.deepEqual(segmentation('So are ... the fishes.'), [
'So', 'are', '...', 'the', 'fishes', '.'
]);
assert.deepEqual(segmentation('So are ...... the fishes.'), [
'So', 'are', '......', 'the', 'fishes', '.'
]);
assert.deepEqual(segmentation('arriba arriba ja....'), [
'arriba', 'arriba', 'ja', '....'
]);
});
});
Pythonで同等の式である:
class Segmentation(BaseNLPProcessor):
pattern = re.compile('((?u)\w+|\.{2,}|[%s])' % string.punctuation)
@classmethod
def ignore_value(cls, value):
# type: (str) -> bool
return negate(compose(is_empty, string.strip))(value)
def split(self):
# type:() -> List[str]
return filter(self.ignore_value, self.pattern.split(self.value()))
私は、ユニコードに変換された単語や句読点によって複数のドットでグループを分割するjavascriptのためのPythonで同等の機能を書きたい...
Segmentation("Hockey is a popular sport in Canada.").split()
https://jsfiddle.net/hungphan/9u0javhg/ –
@HungPhanそこに行く人のために別の単純な答えを持っています。それは厳しいものです。 – TylerY86
ありがとう@ TylerY86。 –