Skip to content

Commit ca360cd

Browse files
author
Gal Ben David
committed
Fixed empty strings as input
1 parent 27e73a7 commit ca360cd

File tree

4 files changed

+35
-4
lines changed

4 files changed

+35
-4
lines changed

Cargo.toml

Lines changed: 8 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,14 +1,19 @@
11
[package]
22
name = "pywordsegment"
3-
version = "0.2.0"
3+
version = "0.2.1"
44
authors = ["Gal Ben David <gal@intsights.com>"]
55
edition = "2021"
66
description = "Concatenated-word segmentation Python library written in Rust"
77
readme = "README.md"
88
repository = "https://github.com/intsights/pywordsegment"
99
homepage = "https://github.com/intsights/pywordsegment"
1010
license = "MIT"
11-
keywords = ["word", "segment", "rust", "pyo3"]
11+
keywords = [
12+
"word",
13+
"segment",
14+
"rust",
15+
"pyo3",
16+
]
1217

1318
[package.metadata.maturin]
1419
requires-python = ">=3.7"
@@ -33,7 +38,7 @@ ahash = "0.7"
3338
rmp-serde = "0.15"
3439

3540
[dependencies.pyo3]
36-
version = "0.14.5"
41+
version = "0.15.1"
3742
features = ["extension-module"]
3843

3944
[profile.release]

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@ sdist-include = [
1313

1414
[tool.poetry]
1515
name = "pywordsegment"
16-
version = "0.2.0"
16+
version = "0.2.1"
1717
authors = ["Gal Ben David <gal@intsights.com>"]
1818
description = "Concatenated-word segmentation Python library written in Rust"
1919
readme = "README.md"

src/lib.rs

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -107,6 +107,10 @@ impl WordSegmenter {
107107
let mut result = Vec::with_capacity(text.len());
108108
let mut candidates = Vec::with_capacity(text.len());
109109

110+
if text.is_empty() {
111+
return result;
112+
}
113+
110114
for end in 1..=text.len() {
111115
let start = end.saturating_sub(MAX_WORD_LEN);
112116
for split in start..end {

tests/test_pywordsegment.py

Lines changed: 22 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -182,6 +182,28 @@ def test_segment_11(
182182
],
183183
)
184184

185+
def test_segment_12(
186+
self,
187+
):
188+
self.assertEqual(
189+
first=pywordsegment.WordSegmenter.segment(
190+
text='',
191+
),
192+
second=[],
193+
)
194+
195+
def test_segment_13(
196+
self,
197+
):
198+
self.assertEqual(
199+
first=pywordsegment.WordSegmenter.segment(
200+
text='a',
201+
),
202+
second=[
203+
'a',
204+
],
205+
)
206+
185207
def test_exist_as_segment_1(
186208
self,
187209
):

0 commit comments

Comments
 (0)