From 09a84e7d11b4de51b6824ef65236a262a26aa055 Mon Sep 17 00:00:00 2001 From: Will Beason Date: Mon, 26 May 2025 15:07:39 -0500 Subject: [PATCH] Reformat Wikiq_Unit_Test.py Separate out reformatting from editing. Signed-off-by: Will Beason --- test/Wikiq_Unit_Test.py | 160 +++++++++++++++++++--------------------- 1 file changed, 75 insertions(+), 85 deletions(-) diff --git a/test/Wikiq_Unit_Test.py b/test/Wikiq_Unit_Test.py index 7f4df39..0cb78dc 100644 --- a/test/Wikiq_Unit_Test.py +++ b/test/Wikiq_Unit_Test.py @@ -9,6 +9,7 @@ import tracemalloc tracemalloc.start() + # with / without pwr DONE # with / without url encode DONE # with / without collapse user DONE @@ -25,25 +26,25 @@ class Test_Wikipedia(unittest.TestCase): os.mkdir("test_output") self.wiki = 'ikwiki-20180301-pages-meta-history' - self.wikiq_out_name = self.wiki + ".tsv" + self.wikiq_out_name = self.wiki + ".tsv" self.test_output_dir = os.path.join(".", "test_output") self.call_output = os.path.join(self.test_output_dir, self.wikiq_out_name) - self.infile = "{0}.xml.bz2".format(self.wiki) + self.infile = "{0}.xml.bz2".format(self.wiki) self.base_call = "../wikiq {0} -o {1}" self.input_dir = "dumps" - self.input_file = os.path.join(".", self.input_dir,self.infile) + self.input_file = os.path.join(".", self.input_dir, self.infile) self.baseline_output_dir = "baseline_output" def test_WP_url_encode(self): - test_filename = "url-encode_" + self.wikiq_out_name + test_filename = "url-encode_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " --url-encode" - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) @@ -52,52 +53,51 @@ class Test_Wikipedia(unittest.TestCase): # as a test let's make sure that we get equal data frames test = pd.read_table(test_file) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) def test_WP_namespaces(self): print(os.path.abspath('.')) - test_filename = "namespaces_" + self.wikiq_out_name + test_filename = "namespaces_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " -n 0 -n 1" print(call) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) baseline_file = os.path.join(os.path.abspath("."), self.baseline_output_dir, test_filename) # as a test let's make sure that we get equal data frames test = pd.read_table(test_file) - num_wrong_ns = sum(~ test.namespace.isin({0,1})) + num_wrong_ns = sum(~ test.namespace.isin({0, 1})) self.assertEqual(num_wrong_ns, 0) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) def test_WP_revert_radius(self): print(os.path.abspath('.')) - test_filename = "revert_radius_" + self.wikiq_out_name + test_filename = "revert_radius_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " -n 0 -n 1 -rr 1" print(call) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) baseline_file = os.path.join(os.path.abspath("."), self.baseline_output_dir, test_filename) # as a test let's make sure that we get equal data frames test = pd.read_table(test_file) - num_wrong_ns = sum(~ test.namespace.isin({0,1})) + num_wrong_ns = sum(~ test.namespace.isin({0, 1})) self.assertEqual(num_wrong_ns, 0) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) - + assert_frame_equal(test, baseline, check_like=True) class Test_Basic(unittest.TestCase): @@ -107,25 +107,25 @@ class Test_Basic(unittest.TestCase): os.mkdir("test_output") self.wiki = 'sailormoon' - self.wikiq_out_name = self.wiki + ".tsv" + self.wikiq_out_name = self.wiki + ".tsv" self.test_output_dir = os.path.join(".", "test_output") self.call_output = os.path.join(self.test_output_dir, self.wikiq_out_name) self.infile = "{0}.xml.7z".format(self.wiki) self.base_call = "../wikiq {0} -o {1}" self.input_dir = "dumps" - self.input_file = os.path.join(".", self.input_dir,self.infile) + self.input_file = os.path.join(".", self.input_dir, self.infile) self.baseline_output_dir = "baseline_output" def test_noargs(self): - test_filename = "noargs_" + self.wikiq_out_name + test_filename = "noargs_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) @@ -134,19 +134,18 @@ class Test_Basic(unittest.TestCase): test = pd.read_table(test_file) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) - + assert_frame_equal(test, baseline, check_like=True) def test_collapse_user(self): - test_filename = "collapse-user_" + self.wikiq_out_name + test_filename = "collapse-user_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " --collapse-user" - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) @@ -154,60 +153,57 @@ class Test_Basic(unittest.TestCase): baseline_file = os.path.join(".", self.baseline_output_dir, test_filename) test = pd.read_table(test_file) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) def test_pwr_segment(self): - test_filename = "persistence_segment_" + self.wikiq_out_name + test_filename = "persistence_segment_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " --persistence segment" - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() - copyfile(self.call_output, test_file) baseline_file = os.path.join(".", self.baseline_output_dir, test_filename) test = pd.read_table(test_file) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) def test_pwr_legacy(self): - test_filename = "persistence_legacy_" + self.wikiq_out_name + test_filename = "persistence_legacy_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " --persistence legacy" - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() - copyfile(self.call_output, test_file) baseline_file = os.path.join(".", self.baseline_output_dir, test_filename) test = pd.read_table(test_file) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) def test_pwr(self): - test_filename = "persistence_" + self.wikiq_out_name + test_filename = "persistence_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) - if os.path.exists(test_file): - os.remove(test_file) - + if os.path.exists(test_file): + os.remove(test_file) + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " --persistence" - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() - copyfile(self.call_output, test_file) baseline_file = os.path.join(".", self.baseline_output_dir, test_filename) @@ -216,19 +212,18 @@ class Test_Basic(unittest.TestCase): baseline = pd.read_table(baseline_file) test = test.reindex(columns=sorted(test.columns)) - assert_frame_equal(test,baseline, check_like=True) - + assert_frame_equal(test, baseline, check_like=True) def test_url_encode(self): - test_filename = "url-encode_" + self.wikiq_out_name + test_filename = "url-encode_" + self.wikiq_out_name test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) - + call = self.base_call.format(self.input_file, self.test_output_dir) call = call + " --url-encode" - proc = subprocess.Popen(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) @@ -237,7 +232,7 @@ class Test_Basic(unittest.TestCase): baseline = pd.read_table(baseline_file) test = test.reindex(columns=sorted(test.columns)) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) class Test_Malformed(unittest.TestCase): @@ -246,42 +241,40 @@ class Test_Malformed(unittest.TestCase): os.mkdir("test_output") self.wiki = 'twinpeaks' - self.wikiq_out_name = self.wiki + ".tsv" + self.wikiq_out_name = self.wiki + ".tsv" self.test_output_dir = os.path.join(".", "test_output") - self.call_output = os.path.join(self.test_output_dir, self.wikiq_out_name) + self.call_output = os.path.join(self.test_output_dir, self.wikiq_out_name) self.infile = "{0}.xml.7z".format(self.wiki) self.base_call = "../wikiq {0} -o {1}" self.input_dir = "dumps" - self.input_file = os.path.join(".", self.input_dir,self.infile) - + self.input_file = os.path.join(".", self.input_dir, self.infile) def test_malformed_noargs(self): - call = self.base_call.format(self.input_file, self.test_output_dir) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,stderr=subprocess.PIPE, shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) proc.wait() outs, errs = proc.communicate() errlines = str(errs).split("\\n") - self.assertEqual(errlines[-2],'xml.etree.ElementTree.ParseError: no element found: line 1369, column 0') + self.assertEqual(errlines[-2], 'xml.etree.ElementTree.ParseError: no element found: line 1369, column 0') + class Test_Stdout(unittest.TestCase): def setUp(self): self.wiki = 'sailormoon' - self.wikiq_out_name = self.wiki + ".tsv" + self.wikiq_out_name = self.wiki + ".tsv" self.infile = "{0}.xml.7z".format(self.wiki) self.base_call = "../wikiq {0} --stdout" self.input_dir = "dumps" - self.input_file = os.path.join(".", self.input_dir,self.infile) + self.input_file = os.path.join(".", self.input_dir, self.infile) self.baseline_output_dir = "baseline_output" def test_noargs(self): - call = self.base_call.format(self.input_file) print(call) - proc = subprocess.run(call,stdout=subprocess.PIPE,shell=True) + proc = subprocess.run(call, stdout=subprocess.PIPE, shell=True) outs = proc.stdout.decode("utf8") test_file = "noargs_" + self.wikiq_out_name @@ -289,7 +282,8 @@ class Test_Stdout(unittest.TestCase): print(baseline_file) test = pd.read_table(StringIO(outs)) baseline = pd.read_table(baseline_file) - assert_frame_equal(test,baseline, check_like=True) + assert_frame_equal(test, baseline, check_like=True) + class Test_Regex(unittest.TestCase): @@ -299,7 +293,7 @@ class Test_Regex(unittest.TestCase): self.infile = "{0}.xml.bz2".format(self.wiki) self.input_dir = "dumps" - self.input_file = os.path.join(".", self.input_dir,self.infile) + self.input_file = os.path.join(".", self.input_dir, self.infile) if not os.path.exists("test_output"): os.mkdir("test_output") @@ -314,13 +308,13 @@ class Test_Regex(unittest.TestCase): # sample inputs for checking that bad inputs get terminated / test_regex_inputs self.bad_inputs_list = [ - #label is missing - "-RP '\\b\\d+\\b'", - #number of reg and number of labels do not match + # label is missing + "-RP '\\b\\d+\\b'", + # number of reg and number of labels do not match "-RP 'NPO V' -RP THE -RPl testlabel", - #cp but rp label + # cp but rp label "-CP '(Tamil|Li)' -RPl testlabel", - #regex is missing + # regex is missing "-CPl testlabel", "-RP '\\b\\w{3}\\b' -RPl threeletters -CP '\\b\\w{3}\\b'" ] @@ -330,35 +324,32 @@ class Test_Regex(unittest.TestCase): "-RP '\\b\\d{3}\\b' -RPl threedigits", "-RP 'TestCase' -RP 'page' -RPl testcases -RPl page_word", "-CP 'Chevalier' -CPl chev_com -RP 'welcome to Wikipedia' -RPl wiki_welcome -CP 'Warning' -CPl warning", - "-CP 'WP:EVADE' -CPl wp_evade" + "-CP 'WP:EVADE' -CPl wp_evade" ] - self.cap_inputs_list = [ "-RP 'Li Chevalier' -RPl li_cheval -CP '(?P\\b[a-zA-Z]{3}\\b)|(?P\\b\\d+\\b)|(?P\\bcat\\b)' -CPl three", "-CP '(?P\\bTestCaseA\\b)|(?P\\bTestCaseB\\b)|(?P\\bTestCaseC\\b)|(?P\\bTestCaseD\\b)' -CPl testcase -RP '(?Pnpov|NPOV)|(?Pneutral point of view)' -RPl npov" ] - - def test_regex_inputs(self): for input in self.bad_inputs_list: call = self.base_call.format(self.input_file) call = call + " --stdout " + input print(call) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,stderr=subprocess.PIPE,shell=True) - stdout,stderr = proc.communicate() - #print(proc.returncode) - + proc = subprocess.Popen(call, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) + stdout, stderr = proc.communicate() + # print(proc.returncode) + # we want to check that the bad inputs were caught and sys.exit is stopping the code print(stderr.decode("utf-8")) - self.assertNotEqual(proc.returncode,0) + self.assertNotEqual(proc.returncode, 0) def test_basic_regex(self): for i, input in enumerate(self.good_inputs_list): test_filename = "basic_{0}_{1}.tsv".format(self.wikiq_out_name[:-4], str(i)) - #print(test_filename) + # print(test_filename) test_file = os.path.join(self.test_output_dir, test_filename) if os.path.exists(test_file): os.remove(test_file) @@ -367,18 +358,17 @@ class Test_Regex(unittest.TestCase): call = call + " " + input print(call) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,stderr=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) test = pd.read_table(test_file) - + baseline_file = os.path.join(".", self.baseline_output_dir, test_filename) baseline = pd.read_table(baseline_file) assert_frame_equal(test, baseline, check_like=True) print(i) - def test_capturegroup_regex(self): for i, input in enumerate(self.cap_inputs_list): test_filename = "capturegroup_{0}_{1}.tsv".format(self.wikiq_out_name[:-4], str(i)) @@ -391,13 +381,13 @@ class Test_Regex(unittest.TestCase): call = call + " " + input print(call) - proc = subprocess.Popen(call,stdout=subprocess.PIPE,stderr=subprocess.PIPE,shell=True) + proc = subprocess.Popen(call, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) proc.wait() copyfile(self.call_output, test_file) - + test = pd.read_table(test_file) - + baseline_file = os.path.join(".", self.baseline_output_dir, test_filename) baseline = pd.read_table(baseline_file) assert_frame_equal(test, baseline, check_like=True)