WordSegmenter is now a static class with static methods

Author: Gal Ben David

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pywordsegment"
-version = "0.1.2"
+version = "0.1.3"
 authors = ["Gal Ben David <gal@intsights.com>"]
 edition = "2018"
 description = "Concatenated-word segmentation Python library written in Rust"

README.md

@@ -50,24 +50,23 @@ import pywordsegment
 # The internal UNIGRAMS & BIGRAMS corpuses are lazy initialized
 # once per the whole module. Multiple WordSegmenter instances would
 # not create new dictionaries.
-word_segmenter = pywordsegment.WordSegmenter()
 
 # Segments a word to its parts
-word_segmenter.segment(
+pywordsegment.WordSegmenter.segment(
     text="theusashops",
 )
 # ["the", "usa", "shops"]
 
 
 # This function checks whether the substring exists as a whole segment
 # inside text.
-word_segmenter.exist_as_segment(
+pywordsegment.WordSegmenter.exist_as_segment(
     substring="inter",
     text="internationalairport",
 )
 # False
 
-word_segmenter.exist_as_segment(
+pywordsegment.WordSegmenter.exist_as_segment(
     substring="inter",
     text="intermilan",
 )

pyproject.toml

@@ -15,7 +15,7 @@ strip = true
 
 [tool.poetry]
 name = "pywordsegment"
-version = "0.1.2"
+version = "0.1.3"
 authors = ["Gal Ben David <gal@intsights.com>"]
 description = "Concatenated-word segmentation Python library written in Rust"
 readme = "README.md"

pywordsegment/__init__.py

@@ -9,9 +9,8 @@
 class WordSegmenter:
     word_segmenter: pywordsegment.WordSegmenter = None
 
-    def __init__(
-        self,
-    ) -> None:
+    @staticmethod
+    def load() -> None:
         if WordSegmenter.word_segmenter is None:
             current_file_dir = pathlib.Path(__file__).parent.absolute()
 
@@ -35,20 +34,26 @@ def __init__(
                 total_words_frequency=1024908267229.0,
             )
 
+    @staticmethod
     def segment(
-        self,
         text: str,
     ) -> typing.List[str]:
-        return self.word_segmenter.segment(
+        if WordSegmenter.word_segmenter is None:
+            WordSegmenter.load()
+
+        return WordSegmenter.word_segmenter.segment(
             text=text,
         )
 
+    @staticmethod
     def exist_as_segment(
-        self,
         substring: str,
         text: str,
     ) -> bool:
-        return self.word_segmenter.exist_as_segment(
+        if WordSegmenter.word_segmenter is None:
+            WordSegmenter.load()
+
+        return WordSegmenter.word_segmenter.exist_as_segment(
             substring=substring,
             text=text,
         )

pywordsegment/pywordsegment.pyi

@@ -2,17 +2,16 @@ import typing
 
 
 class WordSegmenter:
-    def __init__(
-        self,
-    ) -> None: ...
+    @staticmethod
+    def load() -> None: ...
 
+    @staticmethod
     def segment(
-        self,
         text: str,
-    ) -> typing.List[str, str]: ...
+    ) -> typing.List[str]: ...
 
+    @staticmethod
     def exist_as_segment(
-        self,
         substring: str,
         text: str,
     ) -> bool: ...

tests/test_pywordsegment.py

@@ -9,9 +9,8 @@ class WordSegmentTestCase(
     def test_segment_1(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='theusashops',
             ),
             second=[
@@ -24,9 +23,8 @@ def test_segment_1(
     def test_segment_2(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='choosespain',
             ),
             second=[
@@ -38,9 +36,8 @@ def test_segment_2(
     def test_segment_3(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='thisisatest',
             ),
             second=[
@@ -54,9 +51,8 @@ def test_segment_3(
     def test_segment_4(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='wheninthecourseofhumaneventsitbecomesnecessary',
             ),
             second=[
@@ -76,9 +72,8 @@ def test_segment_4(
     def test_segment_5(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='whorepresents',
             ),
             second=[
@@ -90,9 +85,8 @@ def test_segment_5(
     def test_segment_6(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='expertsexchange',
             ),
             second=[
@@ -104,9 +98,8 @@ def test_segment_6(
     def test_segment_7(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='speedofart',
             ),
             second=[
@@ -119,9 +112,8 @@ def test_segment_7(
     def test_segment_8(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='nowisthetimeforallgood',
             ),
             second=[
@@ -138,9 +130,8 @@ def test_segment_8(
     def test_segment_9(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='itisatruthuniversallyacknowledged',
             ),
             second=[
@@ -156,9 +147,8 @@ def test_segment_9(
     def test_segment_10(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='itwasabrightcolddayinaprilandtheclockswerestrikingthirteen',
             ),
             second=[
@@ -182,13 +172,28 @@ def test_segment_10(
     def test_segment_11(
         self,
     ):
-        word_segmenter = pywordsegment.WordSegmenter()
         self.assertEqual(
-            first=word_segmenter.segment(
+            first=pywordsegment.WordSegmenter.segment(
                 text='CaseTest',
             ),
             second=[
                 'case',
                 'test',
             ],
         )
+
+    def test_exist_as_segment_1(
+        self,
+    ):
+        self.assertFalse(
+            expr=pywordsegment.WordSegmenter.exist_as_segment(
+                substring='man',
+                text='manual',
+            ),
+        )
+        self.assertTrue(
+            expr=pywordsegment.WordSegmenter.exist_as_segment(
+                substring='man',
+                text='oneman',
+            ),
+        )