collective/mediawiki_dump_tools
18
0
Fork 0
Code Issues Pull Requests Activity

Compare commits

base: collective:regex_scanner
Branches Tags
collective:master collective:parquet_support collective:mako_changes-20230429 collective:redirects collective:regex_scanner collective:tests collective:advanced_persistence collective:user_level_wikiq collective:mediawiki-utils-migration collective:legacy
..
compare: collective:legacy
Branches Tags
collective:parquet_support collective:mako_changes-20230429 collective:redirects collective:regex_scanner collective:master collective:tests collective:advanced_persistence collective:user_level_wikiq collective:mediawiki-utils-migration collective:legacy

1 Commits
regex_scan ... legacy

Author SHA1 Message Date
groceryheist
d1f5e7b44c undoing my changes to master for now. see branch mediawiki-utils-migration 2018-07-05 01:40:17 -07:00
33 changed files with 363 additions and 85855 deletions
Expand all files Collapse all files

3
.gitmodules vendored
View File

@@ -0,0 +1,3 @@
[submodule "Mediawiki-Utilities"]
path = Mediawiki-Utilities
url = https://github.com/halfak/Mediawiki-Utilities.git

1
Mediawiki-Utilities Submodule

Submodule Mediawiki-Utilities added at f7329417eb

4
README.rst
View File

@@ -7,7 +7,3 @@ submodule like::
git submodule init git submodule init
git submodule update git submodule update
Wikimedia dumps are usually in a compressed format such as 7z (most common), gz, or bz2. Wikiq uses your computer's compression software to read these files. Therefore wikiq depends on
`7za`, `gzcat`, and `zcat`.

1
mw Symbolic link
View File

@@ -0,0 +1 @@
Mediawiki-Utilities/mw

400
test/Wikiq_Unit_Test.py
View File

@@ -1,400 +0,0 @@
import unittest
import os
import subprocess
from shutil import copyfile
import pandas as pd
from pandas.util.testing import assert_frame_equal
from io import StringIO
# with / without pwr DONE
# with / without url encode DONE
# with / without collapse user DONE
# with output to sdtout DONE
# note that the persistence radius is 7 by default
# reading various file formats including
# 7z, gz, bz2, xml DONE
# wikia and wikipedia data DONE
# malformed xmls DONE
class Test_Wikipedia(unittest.TestCase):
def setUp(self):
if not os.path.exists("test_output"):
os.mkdir("test_output")
self.wiki = 'ikwiki-20180301-pages-meta-history'
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.base_call = "../wikiq {0} -o {1}"
self.input_dir = "dumps"
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_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.wait()
copyfile(self.call_output, test_file)
baseline_file = os.path.join(".", 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)
baseline = pd.read_table(baseline_file)
assert_frame_equal(test,baseline)
def test_WP_namespaces(self):
print(os.path.abspath('.'))
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.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}))
self.assertEqual(num_wrong_ns, 0)
baseline = pd.read_table(baseline_file)
assert_frame_equal(test,baseline)
def test_WP_revert_radius(self):
print(os.path.abspath('.'))
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.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}))
self.assertEqual(num_wrong_ns, 0)
baseline = pd.read_table(baseline_file)
assert_frame_equal(test,baseline)
class Test_Basic(unittest.TestCase):
def setUp(self):
if not os.path.exists("test_output"):
os.mkdir("test_output")
self.wiki = 'sailormoon'
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.baseline_output_dir = "baseline_output"
def test_noargs(self):
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.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)
def test_collapse_user(self):
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.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)
def test_pwr_segment(self):
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.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)
def test_pwr_legacy(self):
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.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)
def test_pwr(self):
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)
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.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)
def test_url_encode(self):
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.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)
class Test_Malformed(unittest.TestCase):
def setUp(self):
if not os.path.exists("test_output"):
os.mkdir("test_output")
self.wiki = 'twinpeaks'
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)
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.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')
class Test_Stdout(unittest.TestCase):
def setUp(self):
self.wiki = 'sailormoon'
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.baseline_output_dir = "baseline_output"
def test_noargs(self):
call = self.base_call.format(self.input_file)
proc = subprocess.run(call,stdout=subprocess.PIPE,shell=True)
outs = proc.stdout.decode("utf8")
test_file = "noargs_" + self.wikiq_out_name
baseline_file = os.path.join(".", self.baseline_output_dir, test_file)
print(baseline_file)
test = pd.read_table(StringIO(outs))
baseline = pd.read_table(baseline_file)
assert_frame_equal(test,baseline)
class Test_Regex(unittest.TestCase):
def setUp(self):
self.wiki = 'emptytext'
self.wikiq_out_name = self.wiki + '.tsv'
self.infile = "{0}.xml.bz2".format(self.wiki)
self.input_dir = "dumps"
self.input_file = os.path.join(".", self.input_dir,self.infile)
if not os.path.exists("test_output"):
os.mkdir("test_output")
self.test_output_dir = os.path.join(".", "test_output")
self.call_output = os.path.join(self.test_output_dir, self.wikiq_out_name)
# we have two base calls, one for checking inputs and the other for checking outputs
self.base_call = "../wikiq {0}"
self.base_call_outs = "../wikiq {0} -o {1}"
self.baseline_output_dir = "baseline_output"
# 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
"-RP 'NPO V' -RP THE -RPl testlabel",
#cp but rp label
"-CP '(Tamil|Li)' -RPl testlabel",
#regex is missing
"-CPl testlabel",
"-RP '\\b\\w{3}\\b' -RPl threeletters -CP '\\b\\w{3}\\b'"
]
# sample inputs for checking the outcomes of good inputs / test_basic_regex
self.good_inputs_list = [
"-RP '\\b\\d{3}\\b' -RPl threedigits",
#"-RP 'TestCase' -RP 'page' -RPl testcases -RPl page_word",
"-RP '(\\b[a-zA-Z]{3}\\b)' -RPl 3LETTERS -RP '(\\b(1[\d+])|(2[\d+])\\b)' -RPl NUMBERS",
"-CP 'Chevalier' -CPl chev_com -RP 'welcome to Wikipedia' -RPl wiki_welcome -CP 'Warning' -CPl warning",
"-CP 'WP:EVADE' -CPl wp_evade"
]
self.cap_inputs_list = [
"-RP 'Li Chevalier' -RPl li_cheval -CP '(?P<letter>\\b[a-zA-Z]{3}\\b)|(?P<number>\\b\\d+\\b)|(?P<cat>\\bcat\\b)' -CPl three",
"-CP '(?P<a>\\bTestCaseA\\b)|(?P<b>\\bTestCaseB\\b)|(?P<c>\\bTestCaseC\\b)|(?P<d>\\bTestCaseD\\b)' -CPl testcase -RP '(?P<npov>npov|NPOV)|(?P<neutral>neutral 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)
# 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)
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)
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_outs.format(self.input_file, self.test_output_dir)
call = call + " " + input
#print(call)
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)
#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))
#print(test_filename)
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_outs.format(self.input_file, self.test_output_dir)
call = call + " " + input
#print(call)
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)
if __name__ == '__main__':
unittest.main()

27
test/baseline_output/basic_emptytext_0.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars threedigits title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 None "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 119, 978, 500, 292, 225, 199, 292 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 119, 978, 500, 292, 225, 199, 292 "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 798, 150, 150, 150, 621, 100, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 798, 150, 150, 150, 621, 100, 621 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 119, 157, 119, 157, 119, 157, 119, 157 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 126, 126, 126, 126 "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars threedigits title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 None User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 119, 978, 500, 292, 225, 199, 292 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 119, 978, 500, 292, 225, 199, 292 Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 798, 150, 150, 150, 621, 100, 621 User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 798, 150, 150, 150, 621, 100, 621 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 119, 157, 119, 157, 119, 157, 119, 157 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 126, 126, 126, 126 User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 User talk:106.207.126.114

27
test/baseline_output/basic_emptytext_1.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace page_word revert reverteds revid sha1 testcases text_chars title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 None FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None 0 "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None 663 "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 None FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv TestCase, TestCase 399 "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 page FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None 1260 "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 page FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 TestCase 2249 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 page FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None 2230 "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 page, page FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None 27840 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 page, page FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None 27787 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 page, page FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None 27784 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 page, page FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None 27783 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 page, page FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None 27782 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 page, page FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None 27757 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 page, page FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None 27667 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None 25 "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 page FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None 1274 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None 113 "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None 199 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 page, page, page, page FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None 1840 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 page, page, page, page, page, page FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None 2949 "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None 28 "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None 38 "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None 65 "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None 285 "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None 103 "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 page FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None 1330 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 page FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None 2355 "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id minor namespace page_word revert reverteds revid sha1 testcases text_chars title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 None FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None 0 User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None 663 User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 None FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv TestCase, TestCase 399 User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 page FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None 1260 User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 page FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 TestCase 2249 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 page FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None 2230 Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 page, page FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None 27840 User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 page, page FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None 27787 User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 page, page FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None 27784 User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 page, page FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None 27783 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 page, page FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None 27782 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 page, page FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None 27757 User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 page, page FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None 27667 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None 25 Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 page FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None 1274 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None 113 Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None 199 User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 page, page, page, page FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None 1840 User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 page, page, page, page, page, page FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None 2949 User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None 28 User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None 38 User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None 65 BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None 285 Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None 103 Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 page FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None 1330 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 page FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None 2355 User talk:106.207.126.114

27
test/baseline_output/basic_emptytext_2.tsv
View File

@@ -1,27 +0,0 @@
anon articleid chev_com date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title warning wiki_welcome
FALSE 56237363 None 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 "User talk:86.139.142.254" None None
FALSE 56237364 None 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 "User talk:Kavin kavitha" None None
FALSE 56237365 None 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 "User talk:Dr.vivek163" None None
FALSE 56237366 None 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 "User talk:Twistorl" Warning welcome to Wikipedia
FALSE 56237368 None 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 "Kom Firin" None None
FALSE 56237368 None 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 "Kom Firin" None None
FALSE 56237369 Chevalier, Chevalier 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 Chevalier, Chevalier 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 "User:Editingaccount1994/sandbox" None None
FALSE 56237370 None 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 "Anita del Rey" None None
FALSE 56237371 None 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 "User talk:119.94.96.157" Warning welcome to Wikipedia
FALSE 56237372 None 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 "Category:Ohmi Railway" None None
FALSE 56237375 None 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 "User talk:92.226.219.222" None None
FALSE 56237375 None 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 "User talk:92.226.219.222" None None
FALSE 56237375 None 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 "User talk:92.226.219.222" None None
FALSE 56237376 None 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 "User:Dipayanacharya" None None
FALSE 56237376 None 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 "User:Dipayanacharya" None None
FALSE 56237378 None 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 "BSCIC" None None
FALSE 56237379 None 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 "Category:Women government ministers of Yemen" None None
FALSE 56237381 None 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 "Talk:List of Morning Glories Characters" None None
FALSE 56237382 None 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 "User talk:106.207.126.114" Warning welcome to Wikipedia
FALSE 56237382 None 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 "User talk:106.207.126.114" None welcome to Wikipedia
1 anon articleid chev_com date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title warning wiki_welcome
2 FALSE 56237363 None 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 User talk:86.139.142.254 None None
3 FALSE 56237364 None 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 User talk:Kavin kavitha None None
4 FALSE 56237365 None 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 User talk:Dr.vivek163 None None
5 FALSE 56237366 None 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 User talk:Twistorl Warning welcome to Wikipedia
6 FALSE 56237368 None 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 Kom Firin None None
7 FALSE 56237368 None 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 Kom Firin None None
8 FALSE 56237369 Chevalier, Chevalier 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 User:Editingaccount1994/sandbox None None
9 FALSE 56237369 None 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 User:Editingaccount1994/sandbox None None
10 FALSE 56237369 None 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 User:Editingaccount1994/sandbox None None
11 FALSE 56237369 None 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 User:Editingaccount1994/sandbox None None
12 FALSE 56237369 None 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 User:Editingaccount1994/sandbox None None
13 FALSE 56237369 None 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 User:Editingaccount1994/sandbox None None
14 FALSE 56237369 Chevalier, Chevalier 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 User:Editingaccount1994/sandbox None None
15 FALSE 56237370 None 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 Anita del Rey None None
16 FALSE 56237371 None 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 User talk:119.94.96.157 Warning welcome to Wikipedia
17 FALSE 56237372 None 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 Category:Ohmi Railway None None
18 FALSE 56237375 None 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 User talk:92.226.219.222 None None
19 FALSE 56237375 None 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 User talk:92.226.219.222 None None
20 FALSE 56237375 None 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 User talk:92.226.219.222 None None
21 FALSE 56237376 None 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 User:Dipayanacharya None None
22 FALSE 56237376 None 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 User:Dipayanacharya None None
23 FALSE 56237378 None 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 BSCIC None None
24 FALSE 56237379 None 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 Category:Women government ministers of Yemen None None
25 FALSE 56237381 None 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 Talk:List of Morning Glories Characters None None
26 FALSE 56237382 None 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 User talk:106.207.126.114 Warning welcome to Wikipedia
27 FALSE 56237382 None 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 User talk:106.207.126.114 None welcome to Wikipedia

27
test/baseline_output/basic_emptytext_3.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title wp_evade
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 "User talk:86.139.142.254" WP:EVADE
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 "User talk:Kavin kavitha" None
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 "User talk:Dr.vivek163" None
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 "User talk:Twistorl" None
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 "Kom Firin" None
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 "Kom Firin" None
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 "User:Editingaccount1994/sandbox" None
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 "Anita del Rey" None
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 "User talk:119.94.96.157" None
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 "Category:Ohmi Railway" None
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 "User talk:92.226.219.222" None
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 "User talk:92.226.219.222" None
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 "User talk:92.226.219.222" WP:EVADE
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 "User:Dipayanacharya" None
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 "User:Dipayanacharya" None
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 "BSCIC" None
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 "Category:Women government ministers of Yemen" None
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 "Talk:List of Morning Glories Characters" None
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 "User talk:106.207.126.114" None
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 "User talk:106.207.126.114" None
1 anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title wp_evade
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 User talk:86.139.142.254 WP:EVADE
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 User talk:Kavin kavitha None
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 User talk:Dr.vivek163 None
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 User talk:Twistorl None
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 Kom Firin None
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 Kom Firin None
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 User:Editingaccount1994/sandbox None
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 User:Editingaccount1994/sandbox None
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 User:Editingaccount1994/sandbox None
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 User:Editingaccount1994/sandbox None
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 User:Editingaccount1994/sandbox None
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 User:Editingaccount1994/sandbox None
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 User:Editingaccount1994/sandbox None
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 Anita del Rey None
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 User talk:119.94.96.157 None
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 Category:Ohmi Railway None
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 User talk:92.226.219.222 None
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 User talk:92.226.219.222 None
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 User talk:92.226.219.222 WP:EVADE
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 User:Dipayanacharya None
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 User:Dipayanacharya None
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 BSCIC None
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 Category:Women government ministers of Yemen None
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 Talk:List of Morning Glories Characters None
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 User talk:106.207.126.114 None
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 User talk:106.207.126.114 None

27
test/baseline_output/basic_regextest_0.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars threedigits title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 126, 126, 126, 126 "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 119, 978, 500, 292, 225, 199, 292 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 119, 978, 500, 292, 225, 199, 292 "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 798, 150, 150, 150, 621, 100, 621 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 798, 150, 150, 150, 621, 100, 621 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 119, 157, 119, 157, 119, 157, 119, 157 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 126, 126, 126, 126 "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars threedigits title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 126, 126, 126, 126 User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 119, 978, 500, 292, 225, 199, 292 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 119, 978, 500, 292, 225, 199, 292 Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 798, 150, 150, 150, 621, 137, 137, 150, 150, 350, 195, 350, 195, 180, 180, 350, 195, 300, 150, 150, 150, 180, 180, 621 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 798, 150, 150, 150, 621, 100, 621 User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 798, 150, 150, 150, 621, 100, 621 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 119, 157, 119, 157, 119, 157, 119, 157 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 126, 126, 126, 126 User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114, 106, 207, 126, 114 User talk:106.207.126.114

27
test/baseline_output/basic_regextest_1.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace page_word revert reverteds revid sha1 testcases text_chars title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 page, page FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None 1141 "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None 663 "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 None FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv TestCase, TestCase 399 "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 page FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None 1260 "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 page FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 TestCase 2249 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 page FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None 2230 "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 page, page FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None 27840 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 page, page FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None 27787 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 page, page FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None 27784 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 page, page FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None 27783 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 page, page FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None 27782 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 page, page FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None 27757 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 page, page FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None 27667 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None 25 "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 page FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None 1274 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None 113 "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None 199 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 page, page, page, page FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None 1840 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 page, page, page, page, page, page FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None 2949 "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None 28 "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None 38 "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None 65 "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None 285 "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None 103 "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 page FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None 1330 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 page FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None 2355 "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id minor namespace page_word revert reverteds revid sha1 testcases text_chars title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 page, page FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None 1141 User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None 663 User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 None FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv TestCase, TestCase 399 User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 page FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None 1260 User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 page FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 TestCase 2249 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 page FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None 2230 Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 page, page FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None 27840 User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 page, page FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None 27787 User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 page, page FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None 27784 User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 page, page FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None 27783 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 page, page FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None 27782 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 page, page FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None 27757 User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 page, page FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None 27667 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None 25 Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 page FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None 1274 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None 113 Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None 199 User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 page, page, page, page FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None 1840 User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 page, page, page, page, page, page FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None 2949 User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None 28 User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None 38 User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None 65 BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None 285 Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None 103 Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 page FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None 1330 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 page FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None 2355 User talk:106.207.126.114

27
test/baseline_output/basic_regextest_2.tsv
View File

@@ -1,27 +0,0 @@
anon articleid chev_com date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title warning wiki_welcome
FALSE 56237363 None 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 "User talk:86.139.142.254" None None
FALSE 56237364 None 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 "User talk:Kavin kavitha" None None
FALSE 56237365 None 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 "User talk:Dr.vivek163" None None
FALSE 56237366 None 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 "User talk:Twistorl" Warning welcome to Wikipedia
FALSE 56237368 None 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 "Kom Firin" None None
FALSE 56237368 None 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 "Kom Firin" None None
FALSE 56237369 Chevalier, Chevalier 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 Chevalier, Chevalier 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 "User:Editingaccount1994/sandbox" None None
FALSE 56237370 None 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 "Anita del Rey" None None
FALSE 56237371 None 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 "User talk:119.94.96.157" Warning welcome to Wikipedia
FALSE 56237372 None 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 "Category:Ohmi Railway" None None
FALSE 56237375 None 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 "User talk:92.226.219.222" None None
FALSE 56237375 None 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 "User talk:92.226.219.222" None None
FALSE 56237375 None 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 "User talk:92.226.219.222" None None
FALSE 56237376 None 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 "User:Dipayanacharya" None None
FALSE 56237376 None 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 "User:Dipayanacharya" None None
FALSE 56237378 None 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 "BSCIC" None None
FALSE 56237379 None 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 "Category:Women government ministers of Yemen" None None
FALSE 56237381 None 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 "Talk:List of Morning Glories Characters" None None
FALSE 56237382 None 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 "User talk:106.207.126.114" Warning welcome to Wikipedia
FALSE 56237382 None 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 "User talk:106.207.126.114" None welcome to Wikipedia
1 anon articleid chev_com date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title warning wiki_welcome
2 FALSE 56237363 None 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 User talk:86.139.142.254 None None
3 FALSE 56237364 None 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 User talk:Kavin kavitha None None
4 FALSE 56237365 None 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 User talk:Dr.vivek163 None None
5 FALSE 56237366 None 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 User talk:Twistorl Warning welcome to Wikipedia
6 FALSE 56237368 None 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 Kom Firin None None
7 FALSE 56237368 None 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 Kom Firin None None
8 FALSE 56237369 Chevalier, Chevalier 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 User:Editingaccount1994/sandbox None None
9 FALSE 56237369 None 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 User:Editingaccount1994/sandbox None None
10 FALSE 56237369 None 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 User:Editingaccount1994/sandbox None None
11 FALSE 56237369 None 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 User:Editingaccount1994/sandbox None None
12 FALSE 56237369 None 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 User:Editingaccount1994/sandbox None None
13 FALSE 56237369 None 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 User:Editingaccount1994/sandbox None None
14 FALSE 56237369 Chevalier, Chevalier 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 User:Editingaccount1994/sandbox None None
15 FALSE 56237370 None 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 Anita del Rey None None
16 FALSE 56237371 None 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 User talk:119.94.96.157 Warning welcome to Wikipedia
17 FALSE 56237372 None 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 Category:Ohmi Railway None None
18 FALSE 56237375 None 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 User talk:92.226.219.222 None None
19 FALSE 56237375 None 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 User talk:92.226.219.222 None None
20 FALSE 56237375 None 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 User talk:92.226.219.222 None None
21 FALSE 56237376 None 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 User:Dipayanacharya None None
22 FALSE 56237376 None 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 User:Dipayanacharya None None
23 FALSE 56237378 None 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 BSCIC None None
24 FALSE 56237379 None 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 Category:Women government ministers of Yemen None None
25 FALSE 56237381 None 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 Talk:List of Morning Glories Characters None None
26 FALSE 56237382 None 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 User talk:106.207.126.114 Warning welcome to Wikipedia
27 FALSE 56237382 None 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 User talk:106.207.126.114 None welcome to Wikipedia

27
test/baseline_output/basic_regextest_3.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title wp_evade
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 "User talk:86.139.142.254" WP:EVADE
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 "User talk:Kavin kavitha" None
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 "User talk:Dr.vivek163" None
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 "User talk:Twistorl" None
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 "Kom Firin" None
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 "Kom Firin" None
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 "User:Editingaccount1994/sandbox" None
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 "User:Editingaccount1994/sandbox" None
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 "Anita del Rey" None
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 "User talk:119.94.96.157" None
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 "Category:Ohmi Railway" None
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 "User talk:92.226.219.222" None
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 "User talk:92.226.219.222" None
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 "User talk:92.226.219.222" WP:EVADE
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 "User:Dipayanacharya" None
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 "User:Dipayanacharya" None
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 "BSCIC" None
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 "Category:Women government ministers of Yemen" None
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 "Talk:List of Morning Glories Characters" None
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 "User talk:106.207.126.114" None
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 "User talk:106.207.126.114" None
1 anon articleid date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title wp_evade
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 User talk:86.139.142.254 WP:EVADE
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 User talk:Kavin kavitha None
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 User talk:Dr.vivek163 None
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 User talk:Twistorl None
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 Kom Firin None
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 Kom Firin None
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 User:Editingaccount1994/sandbox None
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 User:Editingaccount1994/sandbox None
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 User:Editingaccount1994/sandbox None
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 User:Editingaccount1994/sandbox None
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 User:Editingaccount1994/sandbox None
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 User:Editingaccount1994/sandbox None
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 User:Editingaccount1994/sandbox None
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 Anita del Rey None
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 User talk:119.94.96.157 None
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 Category:Ohmi Railway None
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 User talk:92.226.219.222 None
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 User talk:92.226.219.222 None
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 User talk:92.226.219.222 WP:EVADE
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 User:Dipayanacharya None
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 User:Dipayanacharya None
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 BSCIC None
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 Category:Women government ministers of Yemen None
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 Talk:List of Morning Glories Characters None
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 User talk:106.207.126.114 None
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 User talk:106.207.126.114 None

27
test/baseline_output/capturegroup_emptytext_0.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id li_cheval minor namespace revert reverteds revid sha1 text_chars three_cat three_letter three_number title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 None FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 None has, has None "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 None FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None AES, for 01, 12, 2001 "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 None FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None new None "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 None FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None None 1 "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 None FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 None AES, jpg, the, the, the, the, and, you, Tor 67, 119 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 None TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 None None None "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 None AES, nom None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 None web, See, for None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 None per, TFD, TFD None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 None per, for, Log, TFD 2010, 13 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 None per, for, Log, TFD 2011, 17 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 None you, are, tor, you None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 None jpg, jpg, has, COM 16, 2018 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 None FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None alt None "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 None FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 None None 119, 94, 96, 157, 119, 94, 96, 157, 1 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 None FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None AES None "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 None FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None AES None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 None TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None See, for None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 None FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 None has, has None "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 None FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None None None "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 None FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None None None "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 None FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None AES, and None "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 None FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None AES, Non None "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 None FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None AES, low, low None "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 None FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 None None 106, 207, 126, 114, 106, 207, 126, 114, 1 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 None FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 None None None "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id li_cheval minor namespace revert reverteds revid sha1 text_chars three_cat three_letter three_number title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 None FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 0 None has, has None User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 None FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None AES, for 01, 12, 2001 User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 None FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None new None User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 None FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None None 1 User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 None FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 None AES, jpg, the, the, the, the, and, you, Tor 67, 119 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 None TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 None None None Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 None AES, nom None User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 None web, See, for None User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 None per, TFD, TFD None User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 None per, for, Log, TFD 2010, 13 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 None per, for, Log, TFD 2011, 17 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 None you, are, tor, you None User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 None jpg, jpg, has, COM 16, 2018 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 None FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None alt None Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 None FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 None None 119, 94, 96, 157, 119, 94, 96, 157, 1 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 None FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None AES None Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 None FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None AES None User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 None TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None See, for None User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 None FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 None has, has None User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 None FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None None None User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 None FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None None None User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 None FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None AES, and None BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 None FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None AES, Non None Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 None FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None AES, low, low None Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 None FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 None None 106, 207, 126, 114, 106, 207, 126, 114, 1 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 None FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 None None None User talk:106.207.126.114

27
test/baseline_output/capturegroup_emptytext_1.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace npov_neutral npov_npov revert reverteds revid sha1 testcase_a testcase_b testcase_c testcase_d text_chars title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 None None FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None None None None 0 "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 None None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None None None None 663 "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 None NPOV, NPOV FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv None None None None 399 "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 None None FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None None None None 1260 "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 None NPOV FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 None TestCaseB None None 2249 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 None None FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None None None None 2230 "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 None None FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None None None None 27840 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 None None FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None None None None 27787 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 None None FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None None None None 27784 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 None None FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None None None None 27783 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 None None FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None None None None 27782 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 None None FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None None None TestCaseD 27757 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 None None FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None None None None 27667 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 None None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None None None None 25 "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 None None FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None None None None 1274 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 None None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None None None None 113 "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 None None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None None None None 199 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 None None FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None None None None 1840 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 None None FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None None None None 2949 "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 None None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None None None None 28 "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 None None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None None None None 38 "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 None None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None None None None 65 "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 None None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None None None None 285 "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 None None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None None None None 103 "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 None None FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None None None None 1330 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 None None FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None None None None 2355 "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id minor namespace npov_neutral npov_npov revert reverteds revid sha1 testcase_a testcase_b testcase_c testcase_d text_chars title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 None None FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None None None None 0 User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 None None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None None None None 663 User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 None NPOV, NPOV FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv None None None None 399 User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 None None FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None None None None 1260 User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 None NPOV FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 None TestCaseB None None 2249 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 None None FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None None None None 2230 Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 None None FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None None None None 27840 User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 None None FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None None None None 27787 User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 None None FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None None None None 27784 User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 None None FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None None None None 27783 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 None None FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None None None None 27782 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 None None FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None None None TestCaseD 27757 User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 None None FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None None None None 27667 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 None None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None None None None 25 Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 None None FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None None None None 1274 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 None None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None None None None 113 Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 None None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None None None None 199 User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 None None FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None None None None 1840 User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 None None FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None None None None 2949 User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 None None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None None None None 28 User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 None None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None None None None 38 User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 None None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None None None None 65 BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 None None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None None None None 285 Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 None None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None None None None 103 Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 None None FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None None None None 1330 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 None None FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None None None None 2355 User talk:106.207.126.114

27
test/baseline_output/capturegroup_regextest_0.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id li_cheval minor namespace revert reverteds revid sha1 text_chars three_cat three_letter three_number title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 None FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 None has, has None "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 None FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None AES, for 01, 12, 2001 "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 None FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None new None "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 None FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None None 1 "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 None FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 None AES, jpg, the, the, the, the, and, you, Tor 67, 119 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 None TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 None None None "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 None AES, nom None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 None web, See, for None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 None per, TFD, TFD None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 None per, for, Log, TFD 2010, 13 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 None per, for, Log, TFD 2011, 17 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 None you, are, tor, you None "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 None jpg, jpg, has, COM 16, 2018 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 None FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None alt None "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 None FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 None None 119, 94, 96, 157, 119, 94, 96, 157, 1 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 None FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None AES None "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 None FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None AES None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 None TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None See, for None "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 None FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 None has, has None "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 None FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None None None "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 None FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None None None "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 None FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None AES, and None "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 None FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None AES, Non None "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 None FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None AES, low, low None "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 None FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 None None 106, 207, 126, 114, 106, 207, 126, 114, 1 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 None FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 None None None "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id li_cheval minor namespace revert reverteds revid sha1 text_chars three_cat three_letter three_number title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 None FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 None has, has None User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 None FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 None AES, for 01, 12, 2001 User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 None FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 None new None User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 None FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 None None 1 User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 None FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 None AES, jpg, the, the, the, the, and, you, Tor 67, 119 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 None TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 None None None Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 None AES, nom None User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 None web, See, for None User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 None per, TFD, TFD None User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 None per, for, Log, TFD 2010, 13 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 None per, for, Log, TFD 2011, 17 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 None you, are, tor, you None User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier, Li Chevalier FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 None jpg, jpg, has, COM 16, 2018 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 None FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 None alt None Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 None FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 None None 119, 94, 96, 157, 119, 94, 96, 157, 1 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 None FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 None AES None Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 None FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 None AES None User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 None TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 None See, for None User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 None FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 None has, has None User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 None FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 None None None User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 None FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 None None None User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 None FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 None AES, and None BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 None FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 None AES, Non None Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 None FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 None AES, low, low None Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 None FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 None None 106, 207, 126, 114, 106, 207, 126, 114, 1 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 None FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 None None None User talk:106.207.126.114

27
test/baseline_output/capturegroup_regextest_1.tsv
View File

@@ -1,27 +0,0 @@
anon articleid date_time deleted editor editor_id minor namespace npov_neutral npov_npov revert reverteds revid sha1 testcase_a testcase_b testcase_c testcase_d text_chars title
FALSE 56237363 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 None None FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None None None None 1141 "User talk:86.139.142.254"
FALSE 56237364 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 None None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None None None None 663 "User talk:Kavin kavitha"
FALSE 56237365 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 None NPOV, NPOV FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv None None None None 399 "User talk:Dr.vivek163"
FALSE 56237366 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 None None FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None None None None 1260 "User talk:Twistorl"
FALSE 56237368 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 None NPOV FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 None TestCaseB None None 2249 "Kom Firin"
FALSE 56237368 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 None None FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None None None None 2230 "Kom Firin"
FALSE 56237369 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 None None FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None None None None 27840 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 None None FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None None None None 27787 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 None None FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None None None None 27784 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 None None FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None None None None 27783 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 None None FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None None None None 27782 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 None None FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None None None TestCaseD 27757 "User:Editingaccount1994/sandbox"
FALSE 56237369 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 None None FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None None None None 27667 "User:Editingaccount1994/sandbox"
FALSE 56237370 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 None None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None None None None 25 "Anita del Rey"
FALSE 56237371 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 None None FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None None None None 1274 "User talk:119.94.96.157"
FALSE 56237372 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 None None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None None None None 113 "Category:Ohmi Railway"
FALSE 56237375 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 None None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None None None None 199 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 None None FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None None None None 1840 "User talk:92.226.219.222"
FALSE 56237375 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 None None FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None None None None 2949 "User talk:92.226.219.222"
FALSE 56237376 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 None None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None None None None 28 "User:Dipayanacharya"
FALSE 56237376 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 None None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None None None None 38 "User:Dipayanacharya"
FALSE 56237378 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 None None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None None None None 65 "BSCIC"
FALSE 56237379 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 None None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None None None None 285 "Category:Women government ministers of Yemen"
FALSE 56237381 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 None None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None None None None 103 "Talk:List of Morning Glories Characters"
FALSE 56237382 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 None None FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None None None None 1330 "User talk:106.207.126.114"
FALSE 56237382 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 None None FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None None None None 2355 "User talk:106.207.126.114"
1 anon articleid date_time deleted editor editor_id minor namespace npov_neutral npov_npov revert reverteds revid sha1 testcase_a testcase_b testcase_c testcase_d text_chars title
2 FALSE 56237363 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 None None FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 None None None None 1141 User talk:86.139.142.254
3 FALSE 56237364 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 None None FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo None None None None 663 User talk:Kavin kavitha
4 FALSE 56237365 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 None NPOV, NPOV FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv None None None None 399 User talk:Dr.vivek163
5 FALSE 56237366 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 None None FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf None None None None 1260 User talk:Twistorl
6 FALSE 56237368 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 None NPOV FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 None TestCaseB None None 2249 Kom Firin
7 FALSE 56237368 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 None None FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh None None None None 2230 Kom Firin
8 FALSE 56237369 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 None None FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 None None None None 27840 User:Editingaccount1994/sandbox
9 FALSE 56237369 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 None None FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 None None None None 27787 User:Editingaccount1994/sandbox
10 FALSE 56237369 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 None None FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj None None None None 27784 User:Editingaccount1994/sandbox
11 FALSE 56237369 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 None None FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h None None None None 27783 User:Editingaccount1994/sandbox
12 FALSE 56237369 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 None None FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg None None None None 27782 User:Editingaccount1994/sandbox
13 FALSE 56237369 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 None None FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 None None None TestCaseD 27757 User:Editingaccount1994/sandbox
14 FALSE 56237369 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 None None FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 None None None None 27667 User:Editingaccount1994/sandbox
15 FALSE 56237370 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 None None FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 None None None None 25 Anita del Rey
16 FALSE 56237371 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 None None FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 None None None None 1274 User talk:119.94.96.157
17 FALSE 56237372 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 None None FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr None None None None 113 Category:Ohmi Railway
18 FALSE 56237375 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 None None FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq None None None None 199 User talk:92.226.219.222
19 FALSE 56237375 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 None None FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg None None None None 1840 User talk:92.226.219.222
20 FALSE 56237375 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 None None FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 None None None None 2949 User talk:92.226.219.222
21 FALSE 56237376 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 None None FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk None None None None 28 User:Dipayanacharya
22 FALSE 56237376 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 None None FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw None None None None 38 User:Dipayanacharya
23 FALSE 56237378 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 None None FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd None None None None 65 BSCIC
24 FALSE 56237379 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 None None FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n None None None None 285 Category:Women government ministers of Yemen
25 FALSE 56237381 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 None None FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 None None None None 103 Talk:List of Morning Glories Characters
26 FALSE 56237382 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 None None FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi None None None None 1330 User talk:106.207.126.114
27 FALSE 56237382 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 None None FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe None None None None 2355 User talk:106.207.126.114

2616
test/baseline_output/collapse-user_sailormoon.tsv
View File

File diff suppressed because it is too large Load Diff

15421
test/baseline_output/namespaces_ikwiki-20180301-pages-meta-history.tsv
View File

File diff suppressed because it is too large Load Diff

4652
test/baseline_output/noargs_sailormoon.tsv
View File

File diff suppressed because it is too large Load Diff

4652
test/baseline_output/persistence_legacy_sailormoon.tsv
View File

File diff suppressed because it is too large Load Diff

4652
test/baseline_output/persistence_sailormoon.tsv
View File

File diff suppressed because it is too large Load Diff

4652
test/baseline_output/persistence_segment_sailormoon.tsv
View File

File diff suppressed because it is too large Load Diff

27
test/baseline_output/regextest.tsv
View File

@@ -1,27 +0,0 @@
anon articleid chev_com date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title warning wiki_welcome
FALSE 56237363 None 2018-01-07 10:40:58 FALSE "NinjaRobotPirate" 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 "User talk:86.139.142.254" None None
FALSE 56237364 None 2018-01-07 10:41:10 FALSE "Kavin kavitha" 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 "User talk:Kavin kavitha" None None
FALSE 56237365 None 2018-01-07 10:41:26 FALSE "Amicable always" 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 "User talk:Dr.vivek163" None None
FALSE 56237366 None 2018-01-07 10:41:31 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 "User talk:Twistorl" Warning welcome to Wikipedia
FALSE 56237368 None 2018-01-07 10:41:51 FALSE "Khruner" 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 "Kom Firin" None None
FALSE 56237368 None 2018-01-27 12:16:02 FALSE "Khruner" 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 "Kom Firin" None None
FALSE 56237369 Chevalier, Chevalier 2018-01-07 10:42:05 FALSE "Editingaccount1994" 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-07 11:09:52 FALSE "AnomieBOT" 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 21:45:50 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 23:28:11 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-12 23:28:39 FALSE "SporkBot" 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 None 2018-01-13 13:45:33 FALSE "Frietjes" 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 "User:Editingaccount1994/sandbox" None None
FALSE 56237369 Chevalier, Chevalier 2018-01-24 01:35:22 FALSE "CommonsDelinker" 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 "User:Editingaccount1994/sandbox" None None
FALSE 56237370 None 2018-01-07 10:42:20 FALSE "PamD" 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 "Anita del Rey" None None
FALSE 56237371 None 2018-01-07 10:42:27 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 "User talk:119.94.96.157" Warning welcome to Wikipedia
FALSE 56237372 None 2018-01-07 10:42:50 FALSE "Underbar dk" 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 "Category:Ohmi Railway" None None
FALSE 56237375 None 2018-01-07 10:43:32 FALSE "TastyPoutine" 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 "User talk:92.226.219.222" None None
FALSE 56237375 None 2018-01-07 11:10:24 FALSE "AnomieBOT" 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 "User talk:92.226.219.222" None None
FALSE 56237375 None 2018-01-07 14:33:36 FALSE "Only" 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 "User talk:92.226.219.222" None None
FALSE 56237376 None 2018-01-07 10:44:01 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 "User:Dipayanacharya" None None
FALSE 56237376 None 2018-01-07 10:49:08 FALSE "Dipayanacharya" 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 "User:Dipayanacharya" None None
FALSE 56237378 None 2018-01-07 10:44:56 FALSE "Vinegarymass911" 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 "BSCIC" None None
FALSE 56237379 None 2018-01-07 10:45:21 FALSE "BrownHairedGirl" 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 "Category:Women government ministers of Yemen" None None
FALSE 56237381 None 2018-01-07 10:45:54 FALSE "PRehse" 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 "Talk:List of Morning Glories Characters" None None
FALSE 56237382 None 2018-01-07 10:45:56 FALSE "ClueBot NG" 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 "User talk:106.207.126.114" Warning welcome to Wikipedia
FALSE 56237382 None 2018-01-07 10:50:22 FALSE "HindWIKI" 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 "User talk:106.207.126.114" None welcome to Wikipedia
1 anon articleid chev_com date_time deleted editor editor_id minor namespace revert reverteds revid sha1 text_chars title warning wiki_welcome
2 FALSE 56237363 None 2018-01-07 10:40:58 FALSE NinjaRobotPirate 3742946 FALSE 3 FALSE 819091731 135nz8q6lfam6cojla7azb7k5alx3t3 1141 User talk:86.139.142.254 None None
3 FALSE 56237364 None 2018-01-07 10:41:10 FALSE Kavin kavitha 32792125 FALSE 3 FALSE 819091755 0pwezjc6yopz0smc8al6ogc4fax5bwo 663 User talk:Kavin kavitha None None
4 FALSE 56237365 None 2018-01-07 10:41:26 FALSE Amicable always 32621254 FALSE 3 FALSE 819091788 sz3t2ap7z8bpkdvdvi195f3i35949bv 399 User talk:Dr.vivek163 None None
5 FALSE 56237366 None 2018-01-07 10:41:31 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091796 r6s5j8j3iykenrhuhpnkpsmmd71vubf 1260 User talk:Twistorl Warning welcome to Wikipedia
6 FALSE 56237368 None 2018-01-07 10:41:51 FALSE Khruner 8409334 FALSE 0 FALSE 819091825 tf5qz2yaswx61zrlm9ovxzuhl7r2dc4 2249 Kom Firin None None
7 FALSE 56237368 None 2018-01-27 12:16:02 FALSE Khruner 8409334 TRUE 0 FALSE 822610647 e6oa4g0qv64icdaq26uu1zzbyr5hcbh 2230 Kom Firin None None
8 FALSE 56237369 Chevalier, Chevalier 2018-01-07 10:42:05 FALSE Editingaccount1994 32794215 FALSE 2 FALSE 819091844 0fyvyh2a8xu41gt8obr34oba0bfixj6 27840 User:Editingaccount1994/sandbox None None
9 FALSE 56237369 None 2018-01-07 11:09:52 FALSE AnomieBOT 7611264 TRUE 2 FALSE 819093984 8gy52aolt5rg3eaketwj5v7eiw0apv2 27787 User:Editingaccount1994/sandbox None None
10 FALSE 56237369 None 2018-01-12 21:45:50 FALSE SporkBot 12406635 TRUE 2 FALSE 820064189 he8ydemaanxlrpftqxkez8jfpge1fsj 27784 User:Editingaccount1994/sandbox None None
11 FALSE 56237369 None 2018-01-12 23:28:11 FALSE SporkBot 12406635 TRUE 2 FALSE 820078679 0to17w9rth3url8n7gvucdtobybdq5h 27783 User:Editingaccount1994/sandbox None None
12 FALSE 56237369 None 2018-01-12 23:28:39 FALSE SporkBot 12406635 TRUE 2 FALSE 820078733 531dizmmloyxffbkdr5vph7owh921eg 27782 User:Editingaccount1994/sandbox None None
13 FALSE 56237369 None 2018-01-13 13:45:33 FALSE Frietjes 13791031 FALSE 2 FALSE 820177382 nik9p2u2fuk4yazjxt8ymbicxv5qid9 27757 User:Editingaccount1994/sandbox None None
14 FALSE 56237369 Chevalier, Chevalier 2018-01-24 01:35:22 FALSE CommonsDelinker 2304267 FALSE 2 FALSE 822038928 gwk6pampl8si1v5pv3kwgteg710sfw3 27667 User:Editingaccount1994/sandbox None None
15 FALSE 56237370 None 2018-01-07 10:42:20 FALSE PamD 1368779 FALSE 0 FALSE 819091874 n4ozbsgle13p9yywtfrz982ccj8woc9 25 Anita del Rey None None
16 FALSE 56237371 None 2018-01-07 10:42:27 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819091883 ksohnvsbeuzwpl5vb8a3v8m18hva0a7 1274 User talk:119.94.96.157 Warning welcome to Wikipedia
17 FALSE 56237372 None 2018-01-07 10:42:50 FALSE Underbar dk 677153 FALSE 14 FALSE 819091914 je7aw21fedbwyqsyofpisdrynsu7olr 113 Category:Ohmi Railway None None
18 FALSE 56237375 None 2018-01-07 10:43:32 FALSE TastyPoutine 882433 FALSE 3 FALSE 819091968 cpm4tkzcx4hc6irr9ukbi06ogud8dtq 199 User talk:92.226.219.222 None None
19 FALSE 56237375 None 2018-01-07 11:10:24 FALSE AnomieBOT 7611264 TRUE 3 FALSE 819094036 artmfz8b2gxhb3pp8a5p4ksplxqfkpg 1840 User talk:92.226.219.222 None None
20 FALSE 56237375 None 2018-01-07 14:33:36 FALSE Only 702940 FALSE 3 FALSE 819112363 dn9wj0n8d8pdd5lqe56uw5xamupowr1 2949 User talk:92.226.219.222 None None
21 FALSE 56237376 None 2018-01-07 10:44:01 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092004 ofueugwatmmn7u73isw732neuza57gk 28 User:Dipayanacharya None None
22 FALSE 56237376 None 2018-01-07 10:49:08 FALSE Dipayanacharya 32794237 FALSE 2 FALSE 819092390 dsz55xv96ec2uv6w9c1z7c52ipfovbw 38 User:Dipayanacharya None None
23 FALSE 56237378 None 2018-01-07 10:44:56 FALSE Vinegarymass911 21516552 FALSE 0 FALSE 819092066 9ma38hak0ef1ew4fpiutxpnzd8oz1wd 65 BSCIC None None
24 FALSE 56237379 None 2018-01-07 10:45:21 FALSE BrownHairedGirl 754619 FALSE 14 FALSE 819092102 4dvakoat58bzyf5hmtthxukt29hip6n 285 Category:Women government ministers of Yemen None None
25 FALSE 56237381 None 2018-01-07 10:45:54 FALSE PRehse 410898 FALSE 1 FALSE 819092135 2sjrxsc7os9k9pg4su2t4rk2j8nn0h7 103 Talk:List of Morning Glories Characters None None
26 FALSE 56237382 None 2018-01-07 10:45:56 FALSE ClueBot NG 13286072 FALSE 3 FALSE 819092138 3y9t5wpk6ur5jhone75rhm4wjf01fgi 1330 User talk:106.207.126.114 Warning welcome to Wikipedia
27 FALSE 56237382 None 2018-01-07 10:50:22 FALSE HindWIKI 31190506 FALSE 3 FALSE 819092495 8wvn6vh3isyt0dorpe89lztrburgupe 2355 User talk:106.207.126.114 None welcome to Wikipedia

15421
test/baseline_output/revert_radius_ikwiki-20180301-pages-meta-history.tsv
View File

File diff suppressed because it is too large Load Diff

27780
test/baseline_output/url-encode_ikwiki-20180301-pages-meta-history.tsv
View File

File diff suppressed because it is too large Load Diff

4652
test/baseline_output/url-encode_sailormoon.tsv
View File

File diff suppressed because it is too large Load Diff

BIN
test/dumps/emptytext.xml.bz2
View File

Binary file not shown.

BIN
test/dumps/ikwiki-20180301-pages-meta-history.xml.bz2
View File

Binary file not shown.

BIN
test/dumps/regextest.xml.bz2
View File

Binary file not shown.

BIN
test/dumps/sailormoon.xml.7z
View File

Binary file not shown.

BIN
test/dumps/twinpeaks.xml.7z
View File

Binary file not shown.

960
wikiq
View File

@@ -1,602 +1,358 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
# original wikiq headers are: title articleid revid date_time anon # original wikiq headers are: title articleid revid date_time anon
# editor editor_id minor text_size text_entropy text_md5 reversion # editor editor_id minor text_size text_entropy text_md5 reversion
# additions_size deletions_size # additions_size deletions_size
import argparse import argparse
import sys import sys
import os, os.path import os, os.path
import re import re
from subprocess import Popen, PIPE from subprocess import Popen, PIPE
from collections import deque from collections import deque
from hashlib import sha1 from hashlib import sha1
from mwxml import Dump from mw.xml_dump import Iterator
from mw.lib import persistence
from deltas.tokenizers import wikitext_split from mw.lib import reverts
import mwpersistence from urllib.parse import quote
import mwreverts TO_ENCODE = ('title', 'editor')
from urllib.parse import quote PERSISTENCE_RADIUS=7
TO_ENCODE = ('title', 'editor')
PERSISTENCE_RADIUS=7 def calculate_persistence(tokens_added):
from deltas import SequenceMatcher return(sum([(len(x.revisions)-1) for x in tokens_added]),
from deltas import SegmentMatcher len(tokens_added))
class PersistMethod: class WikiqIterator():
none = 0 def __init__(self, fh, collapse_user=False):
sequence = 1 self.fh = fh
segment = 2 self.collapse_user = collapse_user
legacy = 3 self.mwiterator = Iterator.from_file(self.fh)
self.__pages = self.load_pages()
def calculate_persistence(tokens_added):
return(sum([(len(x.revisions)-1) for x in tokens_added]), def load_pages(self):
len(tokens_added)) for page in self.mwiterator:
yield WikiqPage(page, collapse_user=self.collapse_user)
class WikiqIterator(): def __iter__(self):
def __init__(self, fh, collapse_user=False): return self.__pages
self.fh = fh
self.collapse_user = collapse_user def __next__(self):
self.mwiterator = Dump.from_file(self.fh) return next(self._pages)
self.namespace_map = { ns.id : ns.name for ns in
self.mwiterator.site_info.namespaces } class WikiqPage():
self.__pages = self.load_pages() __slots__ = ('id', 'title', 'namespace', 'redirect',
'restrictions', 'mwpage', '__revisions',
def load_pages(self): 'collapse_user')
for page in self.mwiterator:
yield WikiqPage(page, def __init__(self, page, collapse_user=False):
namespace_map = self.namespace_map, self.id = page.id
collapse_user=self.collapse_user) self.title = page.title
self.namespace = page.namespace
def __iter__(self): self.redirect = page.redirect
return self.__pages self.restrictions = page.restrictions
def __next__(self): self.collapse_user = collapse_user
return next(self._pages) self.mwpage = page
self.__revisions = self.rev_list()
class WikiqPage():
__slots__ = ('id', 'title', 'namespace', 'redirect', def rev_list(self):
'restrictions', 'mwpage', '__revisions', # Outline for how we want to handle collapse_user=True
'collapse_user') # iteration rev.user prev_rev.user add prev_rev?
# 0 A None Never
def __init__(self, page, namespace_map, collapse_user=False): # 1 A A False
self.id = page.id # 2 B A True
self.namespace = page.namespace # 3 A B True
# following mwxml, we assume namespace 0 in cases where # 4 A A False
# page.namespace is inconsistent with namespace_map # Post-loop A Always
if page.namespace not in namespace_map: for i, rev in enumerate(self.mwpage):
self.title = page.title # never yield the first time
page.namespace = 0 if i == 0:
if page.namespace != 0: if self.collapse_user:
self.title = ':'.join([namespace_map[page.namespace], page.title]) collapsed_revs = 1
else: rev.collapsed_revs = collapsed_revs
self.title = page.title
self.restrictions = page.restrictions else:
self.collapse_user = collapse_user if self.collapse_user:
self.mwpage = page # yield if this is the last edit in a seq by a user and reset
self.__revisions = self.rev_list() if not rev.contributor.user_text == prev_rev.contributor.user_text:
yield prev_rev
def rev_list(self): collapsed_revs = 1
# Outline for how we want to handle collapse_user=True rev.collapsed_revs = collapsed_revs
# iteration rev.user prev_rev.user add prev_rev? # otherwise, add one to the counter
# 0 A None Never else:
# 1 A A False collapsed_revs += 1
# 2 B A True rev.collapsed_revs = collapsed_revs
# 3 A B True # if collapse_user is false, we always yield
# 4 A A False else:
# Post-loop A Always yield prev_rev
for i, rev in enumerate(self.mwpage):
# never yield the first time prev_rev = rev
if i == 0: # also yield the final time
if self.collapse_user: yield prev_rev
collapsed_revs = 1
rev.collapsed_revs = collapsed_revs def __iter__(self):
return self.__revisions
else:
if self.collapse_user: def __next__(self):
# yield if this is the last edit in a seq by a user and reset return next(self.__revisions)
# also yield if we do know who the user is
class WikiqParser():
if rev.deleted.user or prev_rev.deleted.user:
yield prev_rev
collapsed_revs = 1 def __init__(self, input_file, output_file, collapse_user=False, persist=False, urlencode=False):
rev.collapsed_revs = collapsed_revs
self.input_file = input_file
elif not rev.user.text == prev_rev.user.text: self.output_file = output_file
yield prev_rev self.collapse_user = collapse_user
collapsed_revs = 1 self.persist = persist
rev.collapsed_revs = collapsed_revs self.printed_header = False
# otherwise, add one to the counter self.namespaces = []
else: self.urlencode = urlencode
collapsed_revs += 1
rev.collapsed_revs = collapsed_revs def __get_namespace_from_title(self, title):
# if collapse_user is false, we always yield default_ns = None
else:
yield prev_rev for ns in self.namespaces:
# skip if the namespace is not defined
prev_rev = rev if ns == None:
default_ns = self.namespaces[ns]
# also yield the final time continue
yield prev_rev
if title.startswith(ns + ":"):
def __iter__(self): return self.namespaces[ns]
return self.__revisions
# if we've made it this far with no matches, we return the default namespace
def __next__(self): return default_ns
return next(self.__revisions)
def process(self):
class RegexPair(object): # create a regex that creates the output filename
def __init__(self, pattern, label): # output_filename = re.sub(r'^.*/(enwiki\-\d+)\-.*p(\d+)p.*$',
self.pattern = re.compile(pattern) # r'output/wikiq-\1-\2.tsv',
self.label = label # input_filename)
self.has_groups = bool(self.pattern.groupindex)
if self.has_groups: # Construct dump file iterator
self.capture_groups = list(self.pattern.groupindex.keys()) dump = WikiqIterator(self.input_file, collapse_user=self.collapse_user)
def _make_key(self, cap_group): # extract list of namspaces
return ("{}_{}".format(self.label, cap_group)) self.namespaces = {ns.name : ns.id for ns in dump.mwiterator.namespaces}
def matchmake(self, content, rev_data): page_count = 0
rev_count = 0
temp_dict = {} # Iterate through pages
for page in dump:
# the searched text (content, which is rev.comment or rev.text) is empty if self.persist:
if (content==""): state = persistence.State()
# if there are capture groups, we go through and put in a value for each group window = deque(maxlen=PERSISTENCE_RADIUS)
if self.has_groups:
for cap_group in self.capture_groups: rev_detector = reverts.Detector()
key = self._make_key(cap_group)
temp_dict[key] = None # Iterate through a page's revisions
# if no capture groups, just put the value in for the associated label for rev in page:
else:
temp_dict[self.label] = None rev_data = {'revid' : rev.id,
# searched text is not empty and we do the searches 'date_time' : rev.timestamp.strftime('%Y-%m-%d %H:%M:%S'),
else: 'articleid' : page.id,
# if there are named capture groups in the regex 'editor_id' : "" if rev.contributor.id == None else rev.contributor.id,
if self.has_groups: 'title' : '"' + page.title + '"',
'namespace' : page.namespace if page.namespace else self.__get_namespace_from_title(page.title),
# if there are matches of some sort in this revision content, fill the lists for each cap_group 'deleted' : "TRUE" if rev.text.deleted else "FALSE" }
if self.pattern.search(content) is not None:
m = self.pattern.finditer(content) # if revisions are deleted, /many/ things will be missing
matchobjects = list(m) if rev.text.deleted:
rev_data['text_chars'] = ""
for cap_group in self.capture_groups: rev_data['sha1'] = ""
key = self._make_key(cap_group) rev_data['revert'] = ""
temp_list = [] rev_data['reverteds'] = ""
for match in matchobjects:
# we only want to add the match for the capture group if the match is not None else:
if match.group(cap_group) != None: # if text exists, we'll check for a sha1 and generate one otherwise
temp_list.append(match.group(cap_group)) if rev.sha1:
text_sha1 = rev.sha1
# if temp_list of matches is empty just make that column None else:
if len(temp_list)==0: text_sha1 = sha1(bytes(rev.text, "utf8")).hexdigest()
temp_dict[key] = None
# else we put in the list we made in the for-loop above rev_data['sha1'] = text_sha1
else:
temp_dict[key] = ', '.join(temp_list) # TODO rev.bytes doesn't work.. looks like a bug
rev_data['text_chars'] = len(rev.text)
# there are no matches at all in this revision content, we default values to None
else: # generate revert data
for cap_group in self.capture_groups: revert = rev_detector.process(text_sha1, rev.id)
key = self._make_key(cap_group) if revert:
temp_dict[key] = None rev_data['revert'] = "TRUE"
rev_data['reverteds'] = '"' + ",".join([str(x) for x in revert.reverteds]) + '"'
# there are no capture groups, we just search for all the matches of the regex else:
else: rev_data['revert'] = "FALSE"
#given that there are matches to be made rev_data['reverteds'] = ""
if self.pattern.search(content) is not None:
m = self.pattern.findall(content) # if the fact that the edit was minor can be hidden, this might be an issue
m_fixed = [] rev_data['minor'] = "TRUE" if rev.minor else "FALSE"
for match in m:
if type(match) is tuple: if rev.contributor.user_text:
matchies = set() # wrap user-defined editors in quotes for fread
for sub_m in match: rev_data['editor'] = '"' + rev.contributor.user_text + '"'
matchies.add(sub_m) rev_data['anon'] = "TRUE" if rev.contributor.id == None else "FALSE"
m_fixed += matchies
else: else:
m_fixed.append(match) rev_data['anon'] = ""
rev_data['editor'] = ""
temp_dict[self.label] = ', '.join(m_fixed)
else: #if re.match(r'^#redirect \[\[.*\]\]', rev.text, re.I):
temp_dict[self.label] = None # redirect = True
#else:
# update rev_data with our new columns # redirect = False
rev_data.update(temp_dict)
return rev_data #TODO missing: additions_size deletions_size
# if collapse user was on, lets run that
class WikiqParser(): if self.collapse_user:
def __init__(self, input_file, output_file, regex_match_revision, regex_match_comment, regex_revision_label, regex_comment_label, collapse_user=False, persist=None, urlencode=False, namespaces = None, revert_radius=15): rev_data['collapsed_revs'] = rev.collapsed_revs
"""
Parameters: if self.persist:
persist : what persistence method to use. Takes a PersistMethod value if rev.text.deleted:
""" for k in ["token_revs", "tokens_added", "tokens_removed", "tokens_window"]:
self.input_file = input_file old_rev_data[k] = None
self.output_file = output_file else:
self.collapse_user = collapse_user _, tokens_added, tokens_removed = state.process(rev.text, rev.id, text_sha1)
self.persist = persist window.append((rev.id, rev_data, tokens_added, tokens_removed))
self.printed_header = False
self.namespaces = [] if len(window) == PERSISTENCE_RADIUS:
self.urlencode = urlencode old_rev_id, old_rev_data, old_tokens_added, old_tokens_removed = window[0]
self.revert_radius = revert_radius
num_token_revs, num_tokens = calculate_persistence(old_tokens_added)
if namespaces is not None:
self.namespace_filter = set(namespaces) old_rev_data["token_revs"] = num_token_revs
else: old_rev_data["tokens_added"] = num_tokens
self.namespace_filter = None old_rev_data["tokens_removed"] = len(old_tokens_removed)
old_rev_data["tokens_window"] = PERSISTENCE_RADIUS-1
self.regex_revision_pairs = self.make_matchmake_pairs(regex_match_revision, regex_revision_label)
self.regex_comment_pairs = self.make_matchmake_pairs(regex_match_comment, regex_comment_label) self.print_rev_data(old_rev_data)
else:
def make_matchmake_pairs(self, patterns, labels): self.print_rev_data(rev_data)
if (patterns is not None and labels is not None) and \
(len(patterns) == len(labels)): rev_count += 1
return [RegexPair(pattern, label) for pattern, label in zip(patterns, labels)]
elif (patterns is None and labels is None): if self.persist:
return [] # print out metadata for the last RADIUS revisions
else: for i, item in enumerate(window):
sys.exit('Each regular expression *must* come with a corresponding label and vice versa.') # if the window was full, we've already printed item 0
if len(window) == PERSISTENCE_RADIUS and i == 0:
def matchmake(self, rev, rev_data): continue
if not rev.text:
rev.text = "" rev_id, rev_data, tokens_added, tokens_removed = item
if not rev.comment: num_token_revs, num_tokens = calculate_persistence(tokens_added)
rev.comment = ""
rev_data["token_revs"] = num_token_revs
rev_data = self.matchmake_revision(rev.text, rev_data) rev_data["tokens_added"] = num_tokens
rev_data = self.matchmake_comment(rev.comment, rev_data) rev_data["tokens_removed"] = len(tokens_removed)
return rev_data rev_data["tokens_window"] = len(window)-(i+1)
def matchmake_revision(self, text, rev_data): self.print_rev_data(rev_data)
return self.matchmake_pairs(text, rev_data, self.regex_revision_pairs)
page_count += 1
def matchmake_comment(self, comment, rev_data):
return self.matchmake_pairs(comment, rev_data, self.regex_comment_pairs) print("Done: %s revisions and %s pages." % (rev_count, page_count),
file=sys.stderr)
def matchmake_pairs(self, content, rev_data, pairs):
for pair in pairs: def print_rev_data(self, rev_data):
rev_data = pair.matchmake(content, rev_data) # if it's the first time through, print the header
return rev_data if self.urlencode:
for field in TO_ENCODE:
def __get_namespace_from_title(self, title): rev_data[field] = quote(str(rev_data[field]))
default_ns = None
if not self.printed_header:
for ns in self.namespaces: print("\t".join([str(k) for k in sorted(rev_data.keys())]), file=self.output_file)
# skip if the namespace is not defined self.printed_header = True
if ns == None:
default_ns = self.namespaces[ns] print("\t".join([str(v) for k, v in sorted(rev_data.items())]), file=self.output_file)
continue
if title.startswith(ns + ":"): def open_input_file(input_filename):
return self.namespaces[ns] if re.match(r'.*\.7z$', input_filename):
cmd = ["7za", "x", "-so", input_filename, '*']
# if we've made it this far with no matches, we return the default namespace elif re.match(r'.*\.gz$', input_filename):
return default_ns cmd = ["zcat", input_filename]
elif re.match(r'.*\.bz2$', input_filename):
cmd = ["zcat", input_filename]
def process(self):
try:
# create a regex that creates the output filename input_file = Popen(cmd, stdout=PIPE).stdout
# output_filename = re.sub(r'^.*/(enwiki\-\d+)\-.*p(\d+)p.*$', except NameError:
# r'output/wikiq-\1-\2.tsv', input_file = open(input_filename, 'r')
# input_filename)
return input_file
# Construct dump file iterator
dump = WikiqIterator(self.input_file, collapse_user=self.collapse_user) def open_output_file(input_filename):
# create a regex that creates the output filename
# extract list of namspaces output_filename = re.sub(r'\.(7z|gz|bz2)?$', '', input_filename)
self.namespaces = {ns.name : ns.id for ns in dump.mwiterator.site_info.namespaces} output_filename = re.sub(r'\.xml', '', output_filename)
output_filename = output_filename + ".tsv"
page_count = 0 output_file = open(output_filename, "w")
rev_count = 0
return output_file
# Iterate through pages parser = argparse.ArgumentParser(description='Parse MediaWiki XML database dumps into tab delimitted data.')
for page in dump:
namespace = page.namespace if page.namespace is not None else self.__get_namespace_from_title(page.title) # arguments for the input direction
parser.add_argument('dumpfiles', metavar="DUMPFILE", nargs="*", type=str,
# skip namespaces not in the filter help="Filename of the compressed or uncompressed XML database dump. If absent, we'll look for content on stdin and output on stdout.")
if self.namespace_filter is not None:
if namespace not in self.namespace_filter: parser.add_argument('-o', '--output-dir', metavar='DIR', dest='output_dir', type=str, nargs=1,
continue help="Directory for output files.")
rev_detector = mwreverts.Detector(radius = self.revert_radius) parser.add_argument('-s', '--stdout', dest="stdout", action="store_true",
help="Write output to standard out (do not create dump file)")
if self.persist != PersistMethod.none:
window = deque(maxlen=PERSISTENCE_RADIUS) parser.add_argument('--collapse-user', dest="collapse_user", action="store_true",
help="Operate only on the final revision made by user a user within all sequences of consecutive edits made by a user. This can be useful for addressing issues with text persistence measures.")
if self.persist == PersistMethod.sequence:
state = mwpersistence.DiffState(SequenceMatcher(tokenizer = wikitext_split), parser.add_argument('-p', '--persistence', dest="persist", action="store_true",
revert_radius=PERSISTENCE_RADIUS) help="Compute and report measures of content persistent: (1) persistent token revisions, (2) tokens added, and (3) number of revision used in computing the first measure.")
elif self.persist == PersistMethod.segment: parser.add_argument('-u', '--url-encode', dest="urlencode", action="store_true",
state = mwpersistence.DiffState(SegmentMatcher(tokenizer = wikitext_split), help="Output url encoded text strings. This works around some data issues like newlines in editor names. In the future it may be used to output other text data.")
revert_radius=PERSISTENCE_RADIUS)
args = parser.parse_args()
# self.persist == PersistMethod.legacy
else: if len(args.dumpfiles) > 0:
from mw.lib import persistence for filename in args.dumpfiles:
state = persistence.State() input_file = open_input_file(filename)
# Iterate through a page's revisions # open directory for output
for rev in page: if args.output_dir:
output_dir = args.output_dir[0]
# initialize rev_data else:
rev_data = { output_dir = "."
'revid':rev.id,
'date_time' : rev.timestamp.strftime('%Y-%m-%d %H:%M:%S'), print("Processing file: %s" % filename, file=sys.stderr)
'articleid' : page.id,
'editor_id' : "" if rev.deleted.user == True or rev.user.id is None else rev.user.id, if args.stdout:
'title' : '"' + page.title + '"', output_file = sys.stdout
'namespace' : namespace, else:
'deleted' : "TRUE" if rev.deleted.text else "FALSE" filename = os.path.join(output_dir, os.path.basename(filename))
} output_file = open_output_file(filename)
rev_data = self.matchmake(rev, rev_data) wikiq = WikiqParser(input_file, output_file,
collapse_user=args.collapse_user,
# if revisions are deleted, /many/ things will be missing persist=args.persist,
if rev.deleted.text: urlencode=args.urlencode)
rev_data['text_chars'] = ""
rev_data['sha1'] = ""
rev_data['revert'] = "" wikiq.process()
rev_data['reverteds'] = ""
# close things
else: input_file.close()
# rev.text can be None if the page has no text output_file.close()
if not rev.text: else:
rev.text = "" wikiq = WikiqParser(sys.stdin, sys.stdout,
# if text exists, we'll check for a sha1 and generate one otherwise collapse_user=args.collapse_user,
persist=args.persist,
if rev.sha1: urlencode=args.urlencode)
text_sha1 = rev.sha1 wikiq.process()
else:
# stop_words = "a,able,about,across,after,all,almost,also,am,among,an,and,any,are,as,at,be,because,been,but,by,can,cannot,could,dear,did,do,does,either,else,ever,every,for,from,get,got,had,has,have,he,her,hers,him,his,how,however,i,if,in,into,is,it,its,just,least,let,like,likely,may,me,might,most,must,my,neither,no,nor,not,of,off,often,on,only,or,other,our,own,rather,said,say,says,she,should,since,so,some,than,that,the,their,them,then,there,these,they,this,tis,to,too,twas,us,wants,was,we,were,what,when,where,which,while,who,whom,why,will,with,would,yet,you,your"
text_sha1 = sha1(bytes(rev.text, "utf8")).hexdigest() # stop_words = stop_words.split(",")
rev_data['sha1'] = text_sha1
# TODO rev.bytes doesn't work.. looks like a bug
rev_data['text_chars'] = len(rev.text)
# generate revert data
revert = rev_detector.process(text_sha1, rev.id)
if revert:
rev_data['revert'] = "TRUE"
rev_data['reverteds'] = '"' + ",".join([str(x) for x in revert.reverteds]) + '"'
else:
rev_data['revert'] = "FALSE"
rev_data['reverteds'] = ""
# if the fact that the edit was minor can be hidden, this might be an issue
rev_data['minor'] = "TRUE" if rev.minor else "FALSE"
if not rev.deleted.user:
# wrap user-defined editors in quotes for fread
rev_data['editor'] = '"' + rev.user.text + '"'
rev_data['anon'] = "TRUE" if rev.user.id == None else "FALSE"
else:
rev_data['anon'] = ""
rev_data['editor'] = ""
#if re.match(r'^#redirect \[\[.*\]\]', rev.text, re.I):
# redirect = True
#else:
# redirect = False
#TODO missing: additions_size deletions_size
# if collapse user was on, lets run that
if self.collapse_user:
rev_data['collapsed_revs'] = rev.collapsed_revs
if self.persist != PersistMethod.none:
if rev.deleted.text:
for k in ["token_revs", "tokens_added", "tokens_removed", "tokens_window"]:
old_rev_data[k] = None
else:
if self.persist != PersistMethod.legacy:
_, tokens_added, tokens_removed = state.update(rev.text, rev.id)
else:
_, tokens_added, tokens_removed = state.process(rev.text, rev.id, text_sha1)
window.append((rev.id, rev_data, tokens_added, tokens_removed))
if len(window) == PERSISTENCE_RADIUS:
old_rev_id, old_rev_data, old_tokens_added, old_tokens_removed = window[0]
num_token_revs, num_tokens = calculate_persistence(old_tokens_added)
old_rev_data["token_revs"] = num_token_revs
old_rev_data["tokens_added"] = num_tokens
old_rev_data["tokens_removed"] = len(old_tokens_removed)
old_rev_data["tokens_window"] = PERSISTENCE_RADIUS-1
self.print_rev_data(old_rev_data)
else:
self.print_rev_data(rev_data)
rev_count += 1
if self.persist != PersistMethod.none:
# print out metadata for the last RADIUS revisions
for i, item in enumerate(window):
# if the window was full, we've already printed item 0
if len(window) == PERSISTENCE_RADIUS and i == 0:
continue
rev_id, rev_data, tokens_added, tokens_removed = item
num_token_revs, num_tokens = calculate_persistence(tokens_added)
rev_data["token_revs"] = num_token_revs
rev_data["tokens_added"] = num_tokens
rev_data["tokens_removed"] = len(tokens_removed)
rev_data["tokens_window"] = len(window)-(i+1)
self.print_rev_data(rev_data)
page_count += 1
print("Done: %s revisions and %s pages." % (rev_count, page_count),
file=sys.stderr)
def print_rev_data(self, rev_data):
# if it's the first time through, print the header
if self.urlencode:
for field in TO_ENCODE:
rev_data[field] = quote(str(rev_data[field]))
if not self.printed_header:
print("\t".join([str(k) for k in sorted(rev_data.keys())]), file=self.output_file)
self.printed_header = True
print("\t".join([str(v) for k, v in sorted(rev_data.items())]), file=self.output_file)
def open_input_file(input_filename):
if re.match(r'.*\.7z$', input_filename):
cmd = ["7za", "x", "-so", input_filename, '*']
elif re.match(r'.*\.gz$', input_filename):
cmd = ["zcat", input_filename]
elif re.match(r'.*\.bz2$', input_filename):
cmd = ["bzcat", "-dk", input_filename]
try:
input_file = Popen(cmd, stdout=PIPE).stdout
except NameError:
input_file = open(input_filename, 'r')
return input_file
def open_output_file(input_filename):
# create a regex that creates the output filename
output_filename = re.sub(r'\.(7z|gz|bz2)?$', '', input_filename)
output_filename = re.sub(r'\.xml', '', output_filename)
output_filename = output_filename + ".tsv"
output_file = open(output_filename, "w")
return output_file
parser = argparse.ArgumentParser(description='Parse MediaWiki XML database dumps into tab delimitted data.')
# arguments for the input direction
parser.add_argument('dumpfiles', metavar="DUMPFILE", nargs="*", type=str,
help="Filename of the compressed or uncompressed XML database dump. If absent, we'll look for content on stdin and output on stdout.")
parser.add_argument('-o', '--output-dir', metavar='DIR', dest='output_dir', type=str, nargs=1,
help="Directory for output files.")
parser.add_argument('-s', '--stdout', dest="stdout", action="store_true",
help="Write output to standard out (do not create dump file)")
parser.add_argument('--collapse-user', dest="collapse_user", action="store_true",
help="Operate only on the final revision made by user a user within all sequences of consecutive edits made by a user. This can be useful for addressing issues with text persistence measures.")
parser.add_argument('-p', '--persistence', dest="persist", default=None, const='', type=str, choices = ['','segment','sequence','legacy'], nargs='?',
help="Compute and report measures of content persistent: (1) persistent token revisions, (2) tokens added, and (3) number of revision used in computing the first measure. This may by slow. The defualt is -p=sequence, which uses the same algorithm as in the past, but with improvements to wikitext parsing. Use -p=legacy for old behavior used in older research projects. Use -p=segment for advanced persistence calculation method that is robust to content moves, but prone to bugs, and slower.")
parser.add_argument('-u', '--url-encode', dest="urlencode", action="store_true",
help="Output url encoded text strings. This works around some data issues like newlines in editor names. In the future it may be used to output other text data.")
parser.add_argument('-n', '--namespace-include', dest="namespace_filter", type=int, action='append',
help="Id number of namspace to include. Can be specified more than once.")
parser.add_argument('-rr',
'--revert-radius',
dest="revert_radius",
type=int,
action='store',
default=15,
help="Number of edits to check when looking for reverts (default: 15)")
parser.add_argument('-RP', '--revision-pattern', dest="regex_match_revision", default=None, type=str, action='append',
help="The regular expression to search for in revision text. The regex must be surrounded by quotes.")
parser.add_argument('-RPl', '--revision-pattern-label', dest="regex_revision_label", default=None, type=str, action='append',
help="The label for the outputted column based on matching the regex in revision text.")
parser.add_argument('-CP', '--comment-pattern', dest="regex_match_comment", default=None, type=str, action='append',
help="The regular expression to search for in comments of revisions.")
parser.add_argument('-CPl', '--comment-pattern-label', dest="regex_comment_label", default=None, type=str, action='append',
help="The label for the outputted column based on matching the regex in comments.")
args = parser.parse_args()
# set persistence method
if args.persist is None:
persist = PersistMethod.none
elif args.persist == "segment":
persist = PersistMethod.segment
elif args.persist == "legacy":
persist = PersistMethod.legacy
else:
persist = PersistMethod.sequence
if args.namespace_filter is not None:
namespaces = args.namespace_filter
else:
namespaces = None
if len(args.dumpfiles) > 0:
for filename in args.dumpfiles:
input_file = open_input_file(filename)
# open directory for output
if args.output_dir:
output_dir = args.output_dir[0]
else:
output_dir = "."
print("Processing file: %s" % filename, file=sys.stderr)
if args.stdout:
output_file = sys.stdout
else:
filename = os.path.join(output_dir, os.path.basename(filename))
output_file = open_output_file(filename)
wikiq = WikiqParser(input_file,
output_file,
collapse_user=args.collapse_user,
persist=persist,
urlencode=args.urlencode,
namespaces=namespaces,
revert_radius=args.revert_radius,
regex_match_revision = args.regex_match_revision,
regex_revision_label = args.regex_revision_label,
regex_match_comment = args.regex_match_comment,
regex_comment_label = args.regex_comment_label)
wikiq.process()
# close things
input_file.close()
output_file.close()
else:
wikiq = WikiqParser(sys.stdin,
sys.stdout,
collapse_user=args.collapse_user,
persist=persist,
#persist_legacy=args.persist_legacy,
urlencode=args.urlencode,
namespaces=namespaces,
revert_radius=args.revert_radius,
regex_match_revision = args.regex_match_revision,
regex_revision_label = args.regex_revision_label,
regex_match_comment = args.regex_match_comment,
regex_comment_label = args.regex_comment_label)
wikiq.process()
# stop_words = "a,able,about,across,after,all,almost,also,am,among,an,and,any,are,as,at,be,because,been,but,by,can,cannot,could,dear,did,do,does,either,else,ever,every,for,from,get,got,had,has,have,he,her,hers,him,his,how,however,i,if,in,into,is,it,its,just,least,let,like,likely,may,me,might,most,must,my,neither,no,nor,not,of,off,often,on,only,or,other,our,own,rather,said,say,says,she,should,since,so,some,than,that,the,their,them,then,there,these,they,this,tis,to,too,twas,us,wants,was,we,were,what,when,where,which,while,who,whom,why,will,with,would,yet,you,your"
# stop_words = stop_words.split(",")