How to use extract_tags method in localstack

Best Python code snippet using localstack_python

testExtration.py

Source:testExtration.py

...11#ä»£ç æä»¶å¤¹åå«æä»¶chinesenews.txtï¼åå®¹ä¸ºä¸ç¯ä¸ææ°é»#12'''13input_file = open('chinesenews.txt',encoding= 'utf8')14fileContent = input_file.read()15tags = ChineseDealing.extract_tags(fileContent, topK=5)16print ('1'+",".join(tags))17'''18str1 = 'è®°è10æ¥ä»å¬å®é¨è·æï¼å¨å½å¬å®äº¤éç®¡çé¨é¨å°ä»10æ11æ¥è³12æ31æ¥å¼å±å¬è·¯éç¹äº¤éè¿æ³è¡ä¸ºä¸é¡¹æ´æ²»å·¥ä½ï¼å¯¹é«éå¬è·¯åéç¹å½ãçéä¸çè¶éè¡é©¶ãå®¢è½¦è¶åãç²å³é©¾é©¶3ç§ä¸¥éè¿æ³è¡ä¸ºè¿è¡éä¸æ´æ²»ã'19keystr1 = 'æ´æ²»äº¤éè¿æ³'20print(keystr1)21print(str1)22print(ChineseDealing.extractNewsTag(str1))2324str2 = '10æ¥10æ¶50åå·¦å³ï¼éåºç¶¦æ±å¿å¢ååçä¸èµ·éå¤§äº¤éäºæï¼ä¸è¾ä¸åå®¢è½¦ç±äºæ¹åççªç¶å¤±çµï¼å®¢è½¦ä»å±±é´å¬è·¯ä¸ä¾§ç¿»æå¥æ²³ä¸ï¼ç®åå·²ç¡®å®7äººæ»äº¡ã15äººåä¼¤ã'25keystr2 = 'éåºéå¤§è½¦ç¥¸'26print(keystr2)27print(str2)28print(ChineseDealing.extractForumTag(str2))2930str3 = 'ä¸ä½ç³æ²¹ä¸åä¸å®¶è®¤ä¸ºï¼å½åæåæ²¹ä»·æ ¼å¯è½åºç°âè±¡å¾æ§âçä¸è°ã'31keystr3 = 'æ²¹ä»·'32print(keystr3)33print(str3)34print(ChineseDealing.extractNewsTag(str3))3536str4 = 'ééé¨å¬å®å±æ¿å§å¼ åºåæ¨æ¥è¡¨ç¤ºï¼é¢è®¡æå¹´4ææå½åè½¦å°å®ç°ç¬¬åæ¬¡å¤§æéï¼å¨ä¸äºåºæ®µå®¢è½¦è¿è¡æ¶éå¯è¾¾200å¬éã'37keystr4 = 'åè½¦æé'38print(keystr4)39print(str4)40print(ChineseDealing.extract_tags(str4, topK=2))4142str5 = 'è®°è10æ¥ä»éè¥¿çæ¸åå¸æ¿åºäºè§£å°ï¼å½å°å¤§é¢ç§¯æ»å¡ç¾å®³æåä¸åéé¾èéä½å·²è¢«åç°ï¼æ¤æ¬¡ç¾å®³è¢«å13ä½ææ°ä¸æ1äººè·æã12äººæ»äº¡ã'43keystr5 = 'éè¥¿æ»å¡'44print(keystr5)45print(str5)46print(ChineseDealing.extract_tags(str5, topK=2))4748str6 = 'ç»æ¶æå®³åèå¤èªæ²»åºç¥åæ°è¥ä¼ä¸å®¶äºå¨æ°çä¸¤åå¶ææ½æ°¸å¿ ååå¿å¼ºï¼å¨10æ¥çä¸å®¡å®£å¤ä¸è¢«å¼åæµ©ç¹å¸ä¸çº§äººæ°æ³é¢å¤å¤æ»åï¼å¥å¤ºæ¿æ²»æå©ç»èº«ã'49keystr6 = 'åèå¤ç»æ¶æäººæ¡'50print(keystr6)51print(str6)52print(ChineseDealing.extract_tags(str6, topK=2))5354str7 = 'æ¨æ¥ï¼åæ¹å§ãæè²é¨çä¸é¨å§èåååºéç¥ï¼å³å®ä»10æä¸æ¬å¼å§è³11æåºï¼å¨å¨å½èå´åå¼å±æè²æ¶è´¹ä¸é¡¹æ£æ¥ãæ®è®°èäºè§£ï¼æå½55ä¸æä¸å°å¦ä¸ï¼æ¯å¹´æ©æ ¡è´¹æ¶å¥è³å°ç¾äº¿åä»¥ä¸ã'55keystr7 = 'æ©æ ¡è´¹'56print(keystr7)57print(str7)58print(ChineseDealing.extract_tags(str7, topK=2))5960str8 = 'å»å¹´åçå¨äºåæå±±â10Â·18âçæ ¡åæ¨æ¡ä¸ï¼ä¸åæªæ»¡18å¨å²çä¸å¦çå ææ¨åæåå¦ï¼æ·±å¤æææ½å¥å®¿èï¼ææ»çç¡çåå¦ãå°±å¨ä»èµ°åºå¶æ¡ç°åºæ¶ï¼éè§äºå¦å¤ä¸¤ä¸ªåå¦ï¼ç¬¬äºå¤©æä¸ï¼å¶æåæ¬¡è¿å¥å®¿èæäººçå£ãæ¤æ¡éæå¨å½ãè®°èæ¨æ¥è·æï¼äºåçé«é¢å¯¹è¿èµ·å¶ææ¡ä½åºç»å®¡å¤å³ï¼ç»´æä¸å®¡æ³é¢å¤å¤å¶ææ æå¾åï¼å¹¶ç±è¢«åäººå®¶å±åå¶æå¨å¦æ ¡å±åèµå¿æ»èå®¶å±15ä¸åã'61keystr8 = 'äºåæ ¡åæ¨æ¡è¿½è¸ª'62print(keystr8)63print(str8)64print(ChineseDealing.extract_tags(str8, topK=2))6566str9 = 'è¿æ¥ï¼ä¸ä½é³ååçåæªå©å¦å¦å´ç¨å¥¹çåå¼ºåä¹è§ææäºèº«è¾¹çæååè®¸å¤ç½æ°ãå°ççª(blog)ââåäº¬ææ¥ä¸åæåè®°èï¼å¨å ä¸ªæåçªéææåæï¼å´æ¯ç¶å³å®çä¸èéçå©åï¼äº²åå°ç§°è¿ä¸ªå©åä¸ºâçªå¨âï¼å¹¶å¨åå®¢ä¸ç¨è½»æ¾ãè°ä¾çè¯è¨è®°å½ä¸æåæé´çç¹ç¹æ»´æ»´ï¼è¯¥åå®¢çç¹å»çå¨ä¸å¨åçªç ´30ä¸ã'67keystr9 = 'æªå©å¦å¦å¼åå®¢'68print(keystr9)69print(str9)
...

test.py

Source:test.py

...11class ExtractIpv4Test(unittest.TestCase):12    def do_extract(self, expected, text, tag='ipv4'):13        self.assertEqual(14                expected,15                extract_tags(text).get(tag, []))16    def test_all_zeroes(self):17        self.do_extract(['0.0.0.0'], '#0.0.0.0#')18    19    def test_multiple(self):20        self.do_extract(['0.0.0.0', '1.1.1.1'], '#0.0.0.0#1.1.1.1#')21    22    def test_all_ff(self):23        self.do_extract(['255.255.255.255'], '#255.255.255.255#')24    def test_out_of_range(self):25        self.do_extract([], '#256.256.256.256#')26   27    def test_short_formats(self):28        "Although these are valid IPs we only want to match full 4-octet IPs"29        self.do_extract([], '#192.168.1#')30        self.do_extract([], '#192.168#')31        self.do_extract([], '#192#')32class ExtractIpv6Test(unittest.TestCase):33    def do_extract(self, expected, text, tag='ipv6'):34        self.assertEqual(35                expected,36                extract_tags(text).get(tag, []))37    def test_full_address(self):38        self.maxDiff = None39        self.do_extract(40                ['fe80:0000:0000:0000:0204:61ff:fe9d:f156'], 41                '#fe80:0000:0000:0000:0204:61ff:fe9d:f156#')42    43    def test_drop_leading_zeroes(self):44        self.do_extract(45                ['fe80:0:0:0:204:61ff:fe9d:f156'], 46                '#fe80:0:0:0:204:61ff:fe9d:f156#')47    def test_collapse_multiple_zeroes(self):48        self.do_extract(49                ['fe80::204:61ff:fe9d:f156'], 50                '#fe80::204:61ff:fe9d:f156#')51    def test_localhost(self):52        self.do_extract(53                ['::1'], 54                '#::1#')55    56    def test_link_local_prefix(self):57        self.do_extract(58                ['fe80::'], 59                '#fe80::#')60    def test_global_unicast_prefix(self):61        self.do_extract(62                ['2001::'], 63                '#2001::#')64class ExtractEmailTest(unittest.TestCase):65    def do_extract(self, expected, text, tag='email'):66        self.assertEqual(67                expected,68                extract_tags(text).get(tag, []))69    def test_plain_email(self):70        self.do_extract(['test@test.com'], '#test@test.com#')71class ExtractMd5Test(unittest.TestCase):72    def do_extract(self, expected, text, tag='md5'):73        self.assertEqual(74                expected,75                extract_tags(text).get(tag, []))76    def test_plain_md5(self):77        self.do_extract(78                ['0123456789abcdef0123456789abcdef'],79                '#0123456789abcdef0123456789abcdef#')80    def test_uppercase(self):81        self.do_extract(82                ['0123456789ABCDEF0123456789ABCDEF'],83                '#0123456789ABCDEF0123456789ABCDEF#')84    85    def test_invalid_letters(self):86        self.do_extract(87                [],88                '#G123456789ABCDEF0123456789ABCDEF#')89    def test_md5_no_match_inside_longer(self):90        self.do_extract(91                [],92                '#0123456789abcdef0123456789abcdef00000000#')93class ExtractUrlTest(unittest.TestCase):94    def do_extract(self, expected, text, tag='url'):95        self.assertEqual(96                expected,97                extract_tags(text).get(tag, []))98    def test_http_url(self):99        self.do_extract(['http://www.example.com'], '#http://www.example.com  ')100    def test_ftp_url(self):101        self.do_extract(['ftp://www.example.com'], '#ftp://www.example.com  ')102class ExtractBaseDomainTest(unittest.TestCase):103    def do_extract(self, expected, text, tag='domain'):104        self.assertEqual(105                expected,106                extract_tags(text).get(tag, []))107    def test_dot_com(self):108        self.do_extract(['domain.com'], 'http://sub.domain.com/foo')109    def test_dot_co_dot_uk(self):110        self.do_extract(['domain.co.uk'], 'http://sub.domain.co.uk/foo')111    def test_multi_subdomains(self):112        self.do_extract(['domain.com'], 'http://sub1.sub2.domain.com/foo')113class ExtractHostnameTest(unittest.TestCase):114    def do_extract(self, expected, text, tag='hostname'):115        self.assertEqual(116                expected,117                extract_tags(text).get(tag, []))118    def test_dot_com(self):119        self.do_extract(['sub.domain.com'], 'http://sub.domain.com/foo')120    def test_dot_co_dot_uk(self):121        self.do_extract(['sub.domain.co.uk'], 'http://sub.domain.co.uk/foo')122    def test_multi_subdomains(self):123        self.do_extract(124                ['sub1.sub2.domain.com'],125                'http://sub1.sub2.domain.com/foo')126if __name__ == '__main__':...

__init__.py

Source:__init__.py

1from __future__ import absolute_import2from .tfidf import TFIDF3from .textrank import TextRank4try:5    from .analyzer import ChineseAnalyzer6except ImportError:7    pass8default_tfidf = TFIDF()9default_textrank = TextRank()10extract_tags = tfidf = default_tfidf.extract_tags11set_idf_path = default_tfidf.set_idf_path12textrank = default_textrank.extract_tags13def set_stop_words(stop_words_path):14    default_tfidf.set_stop_words(stop_words_path)...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.