Merge pull request #234 from PyThaiNLP/issue224_refactor_tests

Issue #224: Refactor the test file

tests/test_corpus.py

@@ -0,0 +1,76 @@
+# -*- coding: utf-8 -*-
+
+import datetime
+import os
+import sys
+import unittest
+
+from nltk.corpus import wordnet as wn
+
+from pythainlp.corpus import (
+    _CORPUS_PATH,
+    conceptnet,
+    countries,
+    download,
+    provinces,
+    remove,
+    thai_negations,
+    thai_stopwords,
+    thai_syllables,
+    thai_words,
+    tnc,
+    ttc,
+    wordnet,
+)
+from pythainlp.corpus.common import _THAI_WORDS_FILENAME
+
+
+class TestCorpusPackage(unittest.TestCase):
+
+    def test_conceptnet(self):
+        self.assertIsNotNone(conceptnet.edges("รัก"))
+
+    def test_corpus(self):
+        self.assertIsNotNone(countries())
+        self.assertIsNotNone(provinces())
+        self.assertIsNotNone(thai_negations())
+        self.assertIsNotNone(thai_stopwords())
+        self.assertIsNotNone(thai_syllables())
+        self.assertIsNotNone(thai_words())
+        download("test")
+        self.assertIsNotNone(remove("test"))
+        self.assertIsNotNone(remove("tnc_freq"))
+
+    def test_tnc(self):
+        self.assertIsNotNone(tnc.word_freqs())
+        self.assertIsNotNone(tnc.word_freq("นก"))
+
+    def test_ttc(self):
+        self.assertIsNotNone(ttc.word_freqs())
+
+    def test_wordnet(self):
+        self.assertIsNotNone(wordnet.langs())
+
+        self.assertEqual(
+            wordnet.synset("spy.n.01").lemma_names("tha"), ["สปาย", "สายลับ"]
+        )
+        self.assertIsNotNone(wordnet.synsets("นก"))
+        self.assertIsNotNone(wordnet.all_synsets(pos=wn.ADJ))
+
+        self.assertIsNotNone(wordnet.lemmas("นก"))
+        self.assertIsNotNone(wordnet.all_lemma_names(pos=wn.ADV))
+        self.assertIsNotNone(wordnet.lemma("cat.n.01.cat"))
+
+        self.assertEqual(wordnet.morphy("dogs"), "dog")
+
+        bird = wordnet.synset("bird.n.01")
+        mouse = wordnet.synset("mouse.n.01")
+        self.assertEqual(
+            wordnet.path_similarity(bird, mouse), bird.path_similarity(mouse)
+        )
+        self.assertEqual(
+            wordnet.wup_similarity(bird, mouse), bird.wup_similarity(mouse)
+        )
+
+        cat_key = wordnet.synsets("แมว")[0].lemmas()[0].key()
+        self.assertIsNotNone(wordnet.lemma_from_key(cat_key))

tests/test_soundex.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+import datetime
+import os
+import sys
+import unittest
+
+from pythainlp.soundex import lk82, metasound, soundex, udom83
+
+
+class TestSoundexPackage(unittest.TestCase):
+
+    def test_soundex(self):
+        self.assertIsNotNone(soundex("a", engine="lk82"))
+        self.assertIsNotNone(soundex("a", engine="udom83"))
+        self.assertIsNotNone(soundex("a", engine="metasound"))
+        self.assertIsNotNone(soundex("a", engine="XXX"))
+
+        self.assertEqual(lk82(None), "")
+        self.assertEqual(lk82(""), "")
+        self.assertEqual(lk82("เหตุ"), lk82("เหด"))
+        self.assertEqual(lk82("รถ"), "ร3000")
+        self.assertIsNotNone(lk82("เกาะ"))
+        self.assertIsNotNone(lk82("อุยกูร์"))
+        self.assertIsNotNone(lk82("หยากไย่"))
+        self.assertIsNotNone(lk82("หอ"))
+        self.assertEqual(lk82("น์"), "")
+
+        self.assertEqual(udom83(None), "")
+        self.assertEqual(udom83(""), "")
+        self.assertEqual(udom83("เหตุ"), udom83("เหด"))
+        self.assertEqual(udom83("รถ"), "ร800000")
+
+        self.assertEqual(metasound(None), "")
+        self.assertEqual(metasound(""), "")
+        self.assertEqual(metasound("เหตุ"), metasound("เหด"))
+        self.assertEqual(metasound("รักษ์"), metasound("รัก"))
+        self.assertEqual(metasound("บูรณะ"), "บ550")
+        self.assertEqual(metasound("คน"), "ค500")
+        self.assertEqual(metasound("คนA"), "ค500")
+        self.assertEqual(metasound("ดา"), "ด000")
+        self.assertIsNotNone(metasound("จะ"))
+        self.assertIsNotNone(metasound("ปา"))
+        self.assertIsNotNone(metasound("งง"))
+        self.assertIsNotNone(metasound("ลา"))
+        self.assertIsNotNone(metasound("มา"))
+        self.assertIsNotNone(metasound("ยา"))
+        self.assertIsNotNone(metasound("วา"))
+        self.assertIsNotNone(metasound("บูชา"))
+        self.assertIsNotNone(metasound("กมลา"))
+        self.assertIsNotNone(metasound("กาโวกาโว"))
+        self.assertIsNotNone(metasound("สุวรรณา"))
+        self.assertIsNotNone(metasound("ดอยบอย"))

tests/test_spell.py

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+
+import datetime
+import os
+import sys
+import unittest
+
+from pythainlp.spell import NorvigSpellChecker, correct, spell
+
+
+class TestSpellPackage(unittest.TestCase):
+
+    def test_spell(self):
+        self.assertEqual(spell(None), "")
+        self.assertEqual(spell(""), "")
+        self.assertIsNotNone(spell("เน้ร"))
+        self.assertIsNotNone(spell("เกสมร์"))
+
+        self.assertEqual(correct(None), "")
+        self.assertEqual(correct(""), "")
+        self.assertIsNotNone(correct("ทดสอง"))
+
+        checker = NorvigSpellChecker(dict_filter="")
+        self.assertIsNotNone(checker.dictionary())
+        self.assertGreaterEqual(checker.prob("มี"), 0)

tests/test_summarize.py

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+
+import datetime
+import os
+import sys
+import unittest
+
+from pythainlp.summarize import summarize
+
+
+class TestSummarizePackage(unittest.TestCase):
+
+    def test_summarize(self):
+        text = "อาหาร หมายถึง ของแข็งหรือของเหลว "
+        text += "ที่กินหรือดื่มเข้าสู่ร่างกายแล้ว "
+        text += "จะทำให้เกิดพลังงานและความร้อนแก่ร่างกาย "
+        text += "ทำให้ร่างกายเจริญเติบโต "
+        text += "ซ่อมแซมส่วนที่สึกหรอ ควบคุมการเปลี่ยนแปลงต่างๆ ในร่างกาย "
+        text += "ช่วยทำให้อวัยวะต่างๆ ทำงานได้อย่างปกติ "
+        text += "อาหารจะต้องไม่มีพิษและไม่เกิดโทษต่อร่างกาย"
+        self.assertEqual(
+            summarize(text=text, n=1, engine="frequency"),
+            ["อาหารจะต้องไม่มีพิษและไม่เกิดโทษต่อร่างกาย"],
+        )
+        self.assertIsNotNone(summarize(text, 1, engine="XX"))

tests/test_tag.py

@@ -0,0 +1,113 @@
+# -*- coding: utf-8 -*-
+
+import datetime
+import os
+import sys
+import unittest
+
+from pythainlp.tag import perceptron, pos_tag, pos_tag_sents, unigram
+from pythainlp.tag.locations import tag_provinces
+from pythainlp.tag.named_entity import ThaiNameTagger
+from pythainlp.tokenize import (
+    word_tokenize,
+)
+
+
+class TestTagPackage(unittest.TestCase):
+
+    def test_pos_tag(self):
+        tokens = ["ผม", "รัก", "คุณ"]
+
+        self.assertEqual(pos_tag(None), [])
+        self.assertEqual(pos_tag([]), [])
+
+        self.assertEqual(unigram.tag(None, corpus="pud"), [])
+        self.assertEqual(unigram.tag([], corpus="pud"), [])
+        self.assertEqual(unigram.tag(None, corpus="orchid"), [])
+        self.assertEqual(unigram.tag([], corpus="orchid"), [])
+
+        self.assertIsNotNone(
+            pos_tag(tokens, engine="unigram", corpus="orchid")
+        )
+        self.assertIsNotNone(pos_tag(tokens, engine="unigram", corpus="pud"))
+        self.assertIsNotNone(pos_tag([""], engine="unigram", corpus="pud"))
+        self.assertEqual(
+            pos_tag(word_tokenize("คุณกำลังประชุม"), engine="unigram"),
+            [("คุณ", "PPRS"), ("กำลัง", "XVBM"), ("ประชุม", "VACT")],
+        )
+
+        self.assertIsNotNone(
+            pos_tag(tokens, engine="perceptron", corpus="orchid")
+        )
+        self.assertIsNotNone(
+            pos_tag(tokens, engine="perceptron", corpus="pud")
+        )
+        self.assertEqual(perceptron.tag(None, corpus="pud"), [])
+        self.assertEqual(perceptron.tag([], corpus="pud"), [])
+        self.assertEqual(perceptron.tag(None, corpus="orchid"), [])
+        self.assertEqual(perceptron.tag([], corpus="orchid"), [])
+
+        self.assertIsNotNone(pos_tag(None, engine="artagger"))
+        self.assertIsNotNone(pos_tag([], engine="artagger"))
+        self.assertIsNotNone(pos_tag(tokens, engine="artagger"))
+        self.assertEqual(
+            pos_tag(word_tokenize("คุณกำลังประชุม"), engine="artagger"),
+            [("คุณ", "PPRS"), ("กำลัง", "XVBM"), ("ประชุม", "VACT")],
+        )
+
+        self.assertEqual(pos_tag_sents(None), [])
+        self.assertEqual(pos_tag_sents([]), [])
+        self.assertEqual(
+            pos_tag_sents([["ผม", "กิน", "ข้าว"], ["แมว", "วิ่ง"]]),
+            [
+                [("ผม", "PPRS"), ("กิน", "VACT"), ("ข้าว", "NCMN")],
+                [("แมว", "NCMN"), ("วิ่ง", "VACT")],
+            ],
+        )
+
+    # ### pythainlp.tag.locations
+
+    def test_ner_locations(self):
+        self.assertEqual(
+            tag_provinces(["หนองคาย", "น่าอยู่"]),
+            [("หนองคาย", "B-LOCATION"), ("น่าอยู่", "O")],
+        )
+
+    # ### pythainlp.tag.named_entity
+
+    def test_ner(self):
+        ner = ThaiNameTagger()
+        self.assertEqual(ner.get_ner(""), [])
+        self.assertIsNotNone(ner.get_ner("แมวทำอะไรตอนห้าโมงเช้า"))
+        self.assertIsNotNone(ner.get_ner("แมวทำอะไรตอนห้าโมงเช้า", pos=False))
+        self.assertIsNotNone(
+            ner.get_ner(
+                """คณะวิทยาศาสตร์ประยุกต์และวิศวกรรมศาสตร์ มหาวิทยาลัยขอนแก่น
+                วิทยาเขตหนองคาย 112 หมู่ 7 บ้านหนองเดิ่น ตำบลหนองกอมเกาะ อำเภอเมือง
+                จังหวัดหนองคาย 43000"""
+            )
+        )
+        # self.assertEqual(
+        #     ner.get_ner("แมวทำอะไรตอนห้าโมงเช้า"),
+        #     [
+        #         ("แมว", "NCMN", "O"),
+        #         ("ทำ", "VACT", "O"),
+        #         ("อะไร", "PNTR", "O"),
+        #         ("ตอน", "NCMN", "O"),
+        #         ("ห้า", "VSTA", "B-TIME"),
+        #         ("โมง", "NCMN", "I-TIME"),
+        #         ("เช้า", "ADVN", "I-TIME"),
+        #     ],
+        # )
+        # self.assertEqual(
+        #     ner.get_ner("แมวทำอะไรตอนห้าโมงเช้า", pos=False),
+        #     [
+        #         ("แมว", "O"),
+        #         ("ทำ", "O"),
+        #         ("อะไร", "O"),
+        #         ("ตอน", "O"),
+        #         ("ห้า", "B-TIME"),
+        #         ("โมง", "I-TIME"),
+        #         ("เช้า", "I-TIME"),
+        #     ],
+        # )