aboutsummaryrefslogtreecommitdiffstats
path: root/resources/tools/presentation/new/input_data_parser.py
blob: beec34c1067e2006327fec139597b4bfb70e0b0c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
# Copyright (c) 2018 Cisco and/or its affiliates.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at:
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Data pre-processing

- extract data from output.xml files generated by Jenkins jobs and store in
  pandas' Series,
- provide access to the data.
"""

import multiprocessing
import os
import re
import pandas as pd
import logging

from robot.api import ExecutionResult, ResultVisitor
from robot import errors
from collections import OrderedDict
from string import replace
from os import remove

from input_data_files import download_and_unzip_data_file
from utils import Worker


class ExecutionChecker(ResultVisitor):
    """Class to traverse through the test suite structure.

    The functionality implemented in this class generates a json structure:

    Performance tests:

    {
        "metadata": {  # Optional
            "version": "VPP version",
            "job": "Jenkins job name",
            "build": "Information about the build"
        },
        "suites": {
            "Suite name 1": {
                "doc": "Suite 1 documentation",
                "parent": "Suite 1 parent",
                "level": "Level of the suite in the suite hierarchy"
            }
            "Suite name N": {
                "doc": "Suite N documentation",
                "parent": "Suite 2 parent",
                "level": "Level of the suite in the suite hierarchy"
            }
        }
        "tests": {
            "ID": {
                "name": "Test name",
                "parent": "Name of the parent of the test",
                "doc": "Test documentation"
                "msg": "Test message"
                "tags": ["tag 1", "tag 2", "tag n"],
                "type": "PDR" | "NDR",
                "throughput": {
                    "value": int,
                    "unit": "pps" | "bps" | "percentage"
                },
                "latency": {
                    "direction1": {
                        "100": {
                            "min": int,
                            "avg": int,
                            "max": int
                        },
                        "50": {  # Only for NDR
                            "min": int,
                            "avg": int,
                            "max": int
                        },
                        "10": {  # Only for NDR
                            "min": int,
                            "avg": int,
                            "max": int
                        }
                    },
                    "direction2": {
                        "100": {
                            "min": int,
                            "avg": int,
                            "max": int
                        },
                        "50": {  # Only for NDR
                            "min": int,
                            "avg": int,
                            "max": int
                        },
                        "10": {  # Only for NDR
                            "min": int,
                            "avg": int,
                            "max": int
                        }
                    }
                },
                "lossTolerance": "lossTolerance",  # Only for PDR
                "vat-history": "DUT1 and DUT2 VAT History"
                },
                "show-run": "Show Run"
            },
            "ID" {
                # next test
            }
        }
    }

    Functional tests:


    {
        "metadata": {  # Optional
            "version": "VPP version",
            "job": "Jenkins job name",
            "build": "Information about the build"
        },
        "suites": {
            "Suite name 1": {
                "doc": "Suite 1 documentation",
                "parent": "Suite 1 parent",
                "level": "Level of the suite in the suite hierarchy"
            }
            "Suite name N": {
                "doc": "Suite N documentation",
                "parent": "Suite 2 parent",
                "level": "Level of the suite in the suite hierarchy"
            }
        }
        "tests": {
            "ID": {
                "name": "Test name",
                "parent": "Name of the parent of the test",
                "doc": "Test documentation"
                "msg": "Test message"
                "tags": ["tag 1", "tag 2", "tag n"],
                "vat-history": "DUT1 and DUT2 VAT History"
                "show-run": "Show Run"
                "status": "PASS" | "FAIL"
            },
            "ID" {
                # next test
            }
        }
    }

    .. note:: ID is the lowercase full path to the test.
    """

    REGEX_RATE = re.compile(r'^[\D\d]*FINAL_RATE:\s(\d+\.\d+)\s(\w+)')

    REGEX_LAT_NDR = re.compile(r'^[\D\d]*'
                               r'LAT_\d+%NDR:\s\[\'(-?\d+\/-?\d+/-?\d+)\','
                               r'\s\'(-?\d+/-?\d+/-?\d+)\'\]\s\n'
                               r'LAT_\d+%NDR:\s\[\'(-?\d+/-?\d+/-?\d+)\','
                               r'\s\'(-?\d+/-?\d+/-?\d+)\'\]\s\n'
                               r'LAT_\d+%NDR:\s\[\'(-?\d+/-?\d+/-?\d+)\','
                               r'\s\'(-?\d+/-?\d+/-?\d+)\'\]')

    REGEX_LAT_PDR = re.compile(r'^[\D\d]*'
                               r'LAT_\d+%PDR:\s\[\'(-?\d+/-?\d+/-?\d+)\','
                               r'\s\'(-?\d+/-?\d+/-?\d+)\'\][\D\d]*')

    REGEX_TOLERANCE = re.compile(r'^[\D\d]*LOSS_ACCEPTANCE:\s(\d*\.\d*)\s'
                                 r'[\D\d]*')

    REGEX_VERSION = re.compile(r"(return STDOUT Version:\s*)(.*)")

    REGEX_TCP = re.compile(r'Total\s(rps|cps|throughput):\s([0-9]*).*$')

    REGEX_MRR = re.compile(r'MaxReceivedRate_Results\s\[pkts/(\d*)sec\]:\s'
                           r'tx\s(\d*),\srx\s(\d*)')

    def __init__(self, metadata):
        """Initialisation.

        :param metadata: Key-value pairs to be included in "metadata" part of
        JSON structure.
        :type metadata: dict
        """

        # Type of message to parse out from the test messages
        self._msg_type = None

        # VPP version
        self._version = None

        # Number of VAT History messages found:
        # 0 - no message
        # 1 - VAT History of DUT1
        # 2 - VAT History of DUT2
        self._lookup_kw_nr = 0
        self._vat_history_lookup_nr = 0

        # Number of Show Running messages found
        # 0 - no message
        # 1 - Show run message found
        self._show_run_lookup_nr = 0

        # Test ID of currently processed test- the lowercase full path to the
        # test
        self._test_ID = None

        # The main data structure
        self._data = {
            "metadata": OrderedDict(),
            "suites": OrderedDict(),
            "tests": OrderedDict()
        }

        # Save the provided metadata
        for key, val in metadata.items():
            self._data["metadata"][key] = val

        # Dictionary defining the methods used to parse different types of
        # messages
        self.parse_msg = {
            "setup-version": self._get_version,
            "teardown-vat-history": self._get_vat_history,
            "test-show-runtime": self._get_show_run
        }

    @property
    def data(self):
        """Getter - Data parsed from the XML file.

        :returns: Data parsed from the XML file.
        :rtype: dict
        """
        return self._data

    def _get_version(self, msg):
        """Called when extraction of VPP version is required.

        :param msg: Message to process.
        :type msg: Message
        :returns: Nothing.
        """

        if msg.message.count("return STDOUT Version:"):
            self._version = str(re.search(self.REGEX_VERSION, msg.message).
                                group(2))
            self._data["metadata"]["version"] = self._version
            self._data["metadata"]["generated"] = msg.timestamp
            self._msg_type = None

    def _get_vat_history(self, msg):
        """Called when extraction of VAT command history is required.

        :param msg: Message to process.
        :type msg: Message
        :returns: Nothing.
        """
        if msg.message.count("VAT command history:"):
            self._vat_history_lookup_nr += 1
            if self._vat_history_lookup_nr == 1:
                self._data["tests"][self._test_ID]["vat-history"] = str()
            else:
                self._msg_type = None
            text = re.sub("[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3} "
                          "VAT command history:", "", msg.message, count=1). \
                replace("\n\n", "\n").replace('\n', ' |br| ').\
                replace('\r', '').replace('"', "'")

            self._data["tests"][self._test_ID]["vat-history"] += " |br| "
            self._data["tests"][self._test_ID]["vat-history"] += \
                "**DUT" + str(self._vat_history_lookup_nr) + ":** " + text

    def _get_show_run(self, msg):
        """Called when extraction of VPP operational data (output of CLI command
        Show Runtime) is required.

        :param msg: Message to process.
        :type msg: Message
        :returns: Nothing.
        """
        if msg.message.count("return STDOUT Thread "):
            self._show_run_lookup_nr += 1
            if self._lookup_kw_nr == 1 and self._show_run_lookup_nr == 1:
                self._data["tests"][self._test_ID]["show-run"] = str()
            if self._lookup_kw_nr > 1:
                self._msg_type = None
            if self._show_run_lookup_nr == 1:
                text = msg.message.replace("vat# ", "").\
                    replace("return STDOUT ", "").replace("\n\n", "\n").\
                    replace('\n', ' |br| ').\
                    replace('\r', '').replace('"', "'")
                try:
                    self._data["tests"][self._test_ID]["show-run"] += " |br| "
                    self._data["tests"][self._test_ID]["show-run"] += \
                        "**DUT" + str(self._lookup_kw_nr) + ":** |br| " + text
                except KeyError:
                    pass

    def _get_latency(self, msg, test_type):
        """Get the latency data from the test message.

        :param msg: Message to be parsed.
        :param test_type: Type of the test - NDR or PDR.
        :type msg: str
        :type test_type: str
        :returns: Latencies parsed from the message.
        :rtype: dict
        """

        if test_type == "NDR":
            groups = re.search(self.REGEX_LAT_NDR, msg)
            groups_range = range(1, 7)
        elif test_type == "PDR":
            groups = re.search(self.REGEX_LAT_PDR, msg)
            groups_range = range(1, 3)
        else:
            return {}

        latencies = list()
        for idx in groups_range:
            try:
                lat = [int(item) for item in str(groups.group(idx)).split('/')]
            except (AttributeError, ValueError):
                lat = [-1, -1, -1]
            latencies.append(lat)

        keys = ("min", "avg", "max")
        latency = {
            "direction1": {
            },
            "direction2": {
            }
        }

        latency["direction1"]["100"] = dict(zip(keys, latencies[0]))
        latency["direction2"]["100"] = dict(zip(keys, latencies[1]))
        if test_type == "NDR":
            latency["direction1"]["50"] = dict(zip(keys, latencies[2]))
            latency["direction2"]["50"] = dict(zip(keys, latencies[3]))
            latency["direction1"]["10"] = dict(zip(keys, latencies[4]))
            latency["direction2"]["10"] = dict(zip(keys, latencies[5]))

        return latency

    def visit_suite(self, suite):
        """Implements traversing through the suite and its direct children.

        :param suite: Suite to process.
        :type suite: Suite
        :returns: Nothing.
        """
        if self.start_suite(suite) is not False:
            suite.suites.visit(self)
            suite.tests.visit(self)
            self.end_suite(suite)

    def start_suite(self, suite):
        """Called when suite starts.

        :param suite: Suite to process.
        :type suite: Suite
        :returns: Nothing.
        """

        try:
            parent_name = suite.parent.name
        except AttributeError:
            return

        doc_str = suite.doc.replace('"', "'").replace('\n', ' ').\
            replace('\r', '').replace('*[', ' |br| *[').replace("*", "**")
        doc_str = replace(doc_str, ' |br| *[', '*[', maxreplace=1)

        self._data["suites"][suite.longname.lower().replace('"', "'").
            replace(" ", "_")] = {
                "name": suite.name.lower(),
                "doc": doc_str,
                "parent": parent_name,
                "level": len(suite.longname.split("."))
            }

        suite.keywords.visit(self)

    def end_suite(self, suite):
        """Called when suite ends.

        :param suite: Suite to process.
        :type suite: Suite
        :returns: Nothing.
        """
        pass

    def visit_test(self, test):
        """Implements traversing through the test.

        :param test: Test to process.
        :type test: Test
        :returns: Nothing.
        """
        if self.start_test(test) is not False:
            test.keywords.visit(self)
            self.end_test(test)

    def start_test(self, test):
        """Called when test starts.

        :param test: Test to process.
        :type test: Test
        :returns: Nothing.
        """

        tags = [str(tag) for tag in test.tags]
        test_result = dict()
        test_result["name"] = test.name.lower()
        test_result["parent"] = test.parent.name.lower()
        test_result["tags"] = tags
        doc_str = test.doc.replace('"', "'").replace('\n', ' '). \
            replace('\r', '').replace('[', ' |br| [')
        test_result["doc"] = replace(doc_str, ' |br| [', '[', maxreplace=1)
        test_result["msg"] = test.message.replace('\n', ' |br| '). \
            replace('\r', '').replace('"', "'")
        if test.status == "PASS" and ("NDRPDRDISC" in tags or
                                      "TCP" in tags or
                                      "MRR" in tags):
            if "NDRDISC" in tags:
                test_type = "NDR"
            elif "PDRDISC" in tags:
                test_type = "PDR"
            elif "TCP" in tags:
                test_type = "TCP"
            elif "MRR" in tags:
                test_type = "MRR"
            else:
                return

            test_result["type"] = test_type

            if test_type in ("NDR", "PDR"):
                try:
                    rate_value = str(re.search(
                        self.REGEX_RATE, test.message).group(1))
                except AttributeError:
                    rate_value = "-1"
                try:
                    rate_unit = str(re.search(
                        self.REGEX_RATE, test.message).group(2))
                except AttributeError:
                    rate_unit = "-1"

                test_result["throughput"] = dict()
                test_result["throughput"]["value"] = \
                    int(rate_value.split('.')[0])
                test_result["throughput"]["unit"] = rate_unit
                test_result["latency"] = \
                    self._get_latency(test.message, test_type)
                if test_type == "PDR":
                    test_result["lossTolerance"] = str(re.search(
                        self.REGEX_TOLERANCE, test.message).group(1))

            elif test_type in ("TCP", ):
                groups = re.search(self.REGEX_TCP, test.message)
                test_result["result"] = dict()
                test_result["result"]["value"] = int(groups.group(2))
                test_result["result"]["unit"] = groups.group(1)
            elif test_type in ("MRR", ):
                groups = re.search(self.REGEX_MRR, test.message)
                test_result["result"] = dict()
                test_result["result"]["duration"] = int(groups.group(1))
                test_result["result"]["tx"] = int(groups.group(2))
                test_result["result"]["rx"] = int(groups.group(3))
                test_result["result"]["throughput"] = int(
                    test_result["result"]["rx"] /
                    test_result["result"]["duration"])
        else:
            test_result["status"] = test.status

        self._test_ID = test.longname.lower()
        self._data["tests"][self._test_ID] = test_result

    def end_test(self, test):
        """Called when test ends.

        :param test: Test to process.
        :type test: Test
        :returns: Nothing.
        """
        pass

    def visit_keyword(self, keyword):
        """Implements traversing through the keyword and its child keywords.

        :param keyword: Keyword to process.
        :type keyword: Keyword
        :returns: Nothing.
        """
        if self.start_keyword(keyword) is not False:
            self.end_keyword(keyword)

    def start_keyword(self, keyword):
        """Called when keyword starts. Default implementation does nothing.

        :param keyword: Keyword to process.
        :type keyword: Keyword
        :returns: Nothing.
        """
        try:
            if keyword.type == "setup":
                self.visit_setup_kw(keyword)
            elif keyword.type == "teardown":
                self._lookup_kw_nr = 0
                self.visit_teardown_kw(keyword)
            else:
                self._lookup_kw_nr = 0
                self.visit_test_kw(keyword)
        except AttributeError:
            pass

    def end_keyword(self, keyword):
        """Called when keyword ends. Default implementation does nothing.

        :param keyword: Keyword to process.
        :type keyword: Keyword
        :returns: Nothing.
        """
        pass

    def visit_test_kw(self, test_kw):
        """Implements traversing through the test keyword and its child
        keywords.

        :param test_kw: Keyword to process.
        :type test_kw: Keyword
        :returns: Nothing.
        """
        for keyword in test_kw.keywords:
            if self.start_test_kw(keyword) is not False:
                self.visit_test_kw(keyword)
                self.end_test_kw(keyword)

    def start_test_kw(self, test_kw):
        """Called when test keyword starts. Default implementation does
        nothing.

        :param test_kw: Keyword to process.
        :type test_kw: Keyword
        :returns: Nothing.
        """
        if test_kw.name.count("Show Runtime Counters On All Duts"):
            self._lookup_kw_nr += 1
            self._show_run_lookup_nr = 0
            self._msg_type = "test-show-runtime"
            test_kw.messages.visit(self)

    def end_test_kw(self, test_kw):
        """Called when keyword ends. Default implementation does nothing.

        :param test_kw: Keyword to process.
        :type test_kw: Keyword
        :returns: Nothing.
        """
        pass

    def visit_setup_kw(self, setup_kw):
        """Implements traversing through the teardown keyword and its child
        keywords.

        :param setup_kw: Keyword to process.
        :type setup_kw: Keyword
        :returns: Nothing.
        """
        for keyword in setup_kw.keywords:
            if self.start_setup_kw(keyword) is not False:
                self.visit_setup_kw(keyword)
                self.end_setup_kw(keyword)

    def start_setup_kw(self, setup_kw):
        """Called when teardown keyword starts. Default implementation does
        nothing.

        :param setup_kw: Keyword to process.
        :type setup_kw: Keyword
        :returns: Nothing.
        """
        if setup_kw.name.count("Show Vpp Version On All Duts") \
                and not self._version:
            self._msg_type = "setup-version"
            setup_kw.messages.visit(self)

    def end_setup_kw(self, setup_kw):
        """Called when keyword ends. Default implementation does nothing.

        :param setup_kw: Keyword to process.
        :type setup_kw: Keyword
        :returns: Nothing.
        """
        pass

    def visit_teardown_kw(self, teardown_kw):
        """Implements traversing through the teardown keyword and its child
        keywords.

        :param teardown_kw: Keyword to process.
        :type teardown_kw: Keyword
        :returns: Nothing.
        """
        for keyword in teardown_kw.keywords:
            if self.start_teardown_kw(keyword) is not False:
                self.visit_teardown_kw(keyword)
                self.end_teardown_kw(keyword)

    def start_teardown_kw(self, teardown_kw):
        """Called when teardown keyword starts. Default implementation does
        nothing.

        :param teardown_kw: Keyword to process.
        :type teardown_kw: Keyword
        :returns: Nothing.
        """

        if teardown_kw.name.count("Show Vat History On All Duts"):
            self._vat_history_lookup_nr = 0
            self._msg_type = "teardown-vat-history"
            teardown_kw.messages.visit(self)

    def end_teardown_kw(self, teardown_kw):
        """Called when keyword ends. Default implementation does nothing.

        :param teardown_kw: Keyword to process.
        :type teardown_kw: Keyword
        :returns: Nothing.
        """
        pass

    def visit_message(self, msg):
        """Implements visiting the message.

        :param msg: Message to process.
        :type msg: Message
        :returns: Nothing.
        """
        if self.start_message(msg) is not False:
            self.end_message(msg)

    def start_message(self, msg):
        """Called when message starts. Get required information from messages:
        - VPP version.

        :param msg: Message to process.
        :type msg: Message
        :returns: Nothing.
        """

        if self._msg_type:
            self.parse_msg[self._msg_type](msg)

    def end_message(self, msg):
        """Called when message ends. Default implementation does nothing.

        :param msg: Message to process.
        :type msg: Message
        :returns: Nothing.
        """
        pass


class InputData(object):
    """Input data

    The data is extracted from output.xml files generated by Jenkins jobs and
    stored in pandas' DataFrames.

    The data structure:
    - job name
      - build number
        - metadata
          - job
          - build
          - vpp version
        - suites
        - tests
          - ID: test data (as described in ExecutionChecker documentation)
    """

    def __init__(self, spec):
        """Initialization.

        :param spec: Specification.
        :type spec: Specification
        """

        # Specification:
        self._cfg = spec

        # Data store:
        self._input_data = pd.Series()

    @property
    def data(self):
        """Getter - Input data.

        :returns: Input data
        :rtype: pandas.Series
        """
        return self._input_data

    def metadata(self, job, build):
        """Getter - metadata

        :param job: Job which metadata we want.
        :param build: Build which metadata we want.
        :type job: str
        :type build: str
        :returns: Metadata
        :rtype: pandas.Series
        """

        return self.data[job][build]["metadata"]

    def suites(self, job, build):
        """Getter - suites

        :param job: Job which suites we want.
        :param build: Build which suites we want.
        :type job: str
        :type build: str
        :returns: Suites.
        :rtype: pandas.Series
        """

        return self.data[job][str(build)]["suites"]

    def tests(self, job, build):
        """Getter - tests

        :param job: Job which tests we want.
        :param build: Build which tests we want.
        :type job: str
        :type build: str
        :returns: Tests.
        :rtype: pandas.Series
        """

        return self.data[job][build]["tests"]

    @staticmethod
    def _parse_tests(job, build, log):
        """Process data from robot output.xml file and return JSON structured
        data.

        :param job: The name of job which build output data will be processed.
        :param build: The build which output data will be processed.
        :param log: List of log messages.
        :type job: str
        :type build: dict
        :type log: list of tuples (severity, msg)
        :returns: JSON data structure.
        :rtype: dict
        """

        metadata = {
            "job": job,
            "build": build
        }

        with open(build["file-name"], 'r') as data_file:
            try:
                result = ExecutionResult(data_file)
            except errors.DataError as err:
                log.append(("ERROR", "Error occurred while parsing output.xml: "
                                     "{0}".format(err)))
                return None
        checker = ExecutionChecker(metadata)
        result.visit(checker)

        return checker.data

    def _download_and_parse_build(self, pid, data_queue, job, build, repeat):
        """Download and parse the input data file.

        :param pid: PID of the process executing this method.
        :param data_queue: Shared memory between processes. Queue which keeps
            the result data. This data is then read by the main process and used
            in further processing.
        :param job: Name of the Jenkins job which generated the processed input
            file.
        :param build: Information about the Jenkins build which generated the
            processed input file.
        :param repeat: Repeat the download specified number of times if not
            successful.
        :type pid: int
        :type data_queue: multiprocessing.Manager().Queue()
        :type job: str
        :type build: dict
        :type repeat: int
        """

        logs = list()

        logging.info("  Processing the job/build: {0}: {1}".
                     format(job, build["build"]))

        logs.append(("INFO", "  Processing the job/build: {0}: {1}".
                     format(job, build["build"])))

        state = "failed"
        success = False
        data = None
        do_repeat = repeat
        while do_repeat:
            success = download_and_unzip_data_file(self._cfg, job, build, pid,
                                                   logs)
            if success:
                break
            do_repeat -= 1
        if not success:
            logs.append(("ERROR", "It is not possible to download the input "
                                  "data file from the job '{job}', build "
                                  "'{build}', or it is damaged. Skipped.".
                         format(job=job, build=build["build"])))
        if success:
            logs.append(("INFO", "  Processing data from the build '{0}' ...".
                         format(build["build"])))
            data = InputData._parse_tests(job, build, logs)
            if data is None:
                logs.append(("ERROR", "Input data file from the job '{job}', "
                                      "build '{build}' is damaged. Skipped.".
                             format(job=job, build=build["build"])))
            else:
                state = "processed"

            try:
                remove(build["file-name"])
            except OSError as err:
                logs.append(("ERROR", "Cannot remove the file '{0}': {1}".
                             format(build["file-name"], err)))
        logs.append(("INFO", "  Done."))

        result = {
            "data": data,
            "state": state,
            "job": job,
            "build": build,
            "logs": logs
        }
        data_queue.put(result)

    def download_and_parse_data(self, repeat=1):
        """Download the input data files, parse input data from input files and
        store in pandas' Series.

        :param repeat: Repeat the download specified number of times if not
            successful.
        :type repeat: int
        """

        logging.info("Downloading and parsing input files ...")

        work_queue = multiprocessing.JoinableQueue()
        manager = multiprocessing.Manager()
        data_queue = manager.Queue()
        cpus = multiprocessing.cpu_count()

        workers = list()
        for cpu in range(cpus):
            worker = Worker(work_queue,
                            data_queue,
                            self._download_and_parse_build)
            worker.daemon = True
            worker.start()
            workers.append(worker)
            os.system("taskset -p -c {0} {1} > /dev/null 2>&1".
                      format(cpu, worker.pid))

        for job, builds in self._cfg.builds.items():
            for build in builds:
                work_queue.put((job, build, repeat))

        work_queue.join()

        logging.info("Done.")

        while not data_queue.empty():
            result = data_queue.get()

            job = result["job"]
            build_nr = result["build"]["build"]

            if result["data"]:
                data = result["data"]
                build_data = pd.Series({
                    "metadata": pd.Series(data["metadata"].values(),
                                          index=data["metadata"].keys()),
                    "suites": pd.Series(data["suites"].values(),
                                        index=data["suites"].keys()),
                    "tests": pd.Series(data["tests"].values(),
                                       index=data["tests"].keys())})

                if self._input_data.get(job, None) is None:
                    self._input_data[job] = pd.Series()
                self._input_data[job][str(build_nr)] = build_data

                self._cfg.set_input_file_name(job, build_nr,
                                              result["build"]["file-name"])

            self._cfg.set_input_state(job, build_nr, result["state"])

            for item in result["logs"]:
                if item[0] == "INFO":
                    logging.info(item[1])
                elif item[0] == "ERROR":
                    logging.error(item[1])
                elif item[0] == "DEBUG":
                    logging.debug(item[1])
                elif item[0] == "CRITICAL":
                    logging.critical(item[1])
                elif item[0] == "WARNING":
                    logging.warning(item[1])

        del data_queue

        # Terminate all workers
        for worker in workers:
            worker.terminate()
            worker.join()

        logging.info("Done.")

    @staticmethod
    def _end_of_tag(tag_filter, start=0, closer="'"):
        """Return the index of character in the string which is the end of tag.

        :param tag_filter: The string where the end of tag is being searched.
        :param start: The index where the searching is stated.
        :param closer: The character which is the tag closer.
        :type tag_filter: str
        :type start: int
        :type closer: str
        :returns: The index of the tag closer.
        :rtype: int
        """

        try:
            idx_opener = tag_filter.index(closer, start)
            return tag_filter.index(closer, idx_opener + 1)
        except ValueError:
            return None

    @staticmethod
    def _condition(tag_filter):
        """Create a conditional statement from the given tag filter.

        :param tag_filter: Filter based on tags from the element specification.
        :type tag_filter: str
        :returns: Conditional statement which can be evaluated.
        :rtype: str
        """

        index = 0
        while True:
            index = InputData._end_of_tag(tag_filter, index)
            if index is None:
                return tag_filter
            index += 1
            tag_filter = tag_filter[:index] + " in tags" + tag_filter[index:]

    def filter_data(self, element, params=None, data_set="tests",
                    continue_on_error=False):
        """Filter required data from the given jobs and builds.

        The output data structure is:

        - job 1
          - build 1
            - test (suite) 1 ID:
              - param 1
              - param 2
              ...
              - param n
            ...
            - test (suite) n ID:
            ...
          ...
          - build n
        ...
        - job n

        :param element: Element which will use the filtered data.
        :param params: Parameters which will be included in the output. If None,
        all parameters are included.
        :param data_set: The set of data to be filtered: tests, suites,
        metadata.
        :param continue_on_error: Continue if there is error while reading the
        data. The Item will be empty then
        :type element: pandas.Series
        :type params: list
        :type data_set: str
        :type continue_on_error: bool
        :returns: Filtered data.
        :rtype pandas.Series
        """

        try:
            if element["filter"] in ("all", "template"):
                cond = "True"
            else:
                cond = InputData._condition(element["filter"])
            logging.debug("   Filter: {0}".format(cond))
        except KeyError:
            logging.error("  No filter defined.")
            return None

        if params is None:
            params = element.get("parameters", None)

        data = pd.Series()
        try:
            for job, builds in element["data"].items():
                data[job] = pd.Series()
                for build in builds:
                    data[job][str(build)] = pd.Series()
                    try:
                        data_iter = self.data[job][str(build)][data_set].\
                            iteritems()
                    except KeyError:
                        if continue_on_error:
                            continue
                        else:
                            return None
                    for test_ID, test_data in data_iter:
                        if eval(cond, {"tags": test_data.get("tags", "")}):
                            data[job][str(build)][test_ID] = pd.Series()
                            if params is None:
                                for param, val in test_data.items():
                                    data[job][str(build)][test_ID][param] = val
                            else:
                                for param in params:
                                    try:
                                        data[job][str(build)][test_ID][param] =\
                                            test_data[param]
                                    except KeyError:
                                        data[job][str(build)][test_ID][param] =\
                                            "No Data"
            return data

        except (KeyError, IndexError, ValueError) as err:
            logging.error("   Missing mandatory parameter in the element "
                          "specification: {0}".format(err))
            return None
        except AttributeError:
            return None
        except SyntaxError:
            logging.error("   The filter '{0}' is not correct. Check if all "
                          "tags are enclosed by apostrophes.".format(cond))
            return None

    @staticmethod
    def merge_data(data):
        """Merge data from more jobs and builds to a simple data structure.

        The output data structure is:

        - test (suite) 1 ID:
          - param 1
          - param 2
          ...
          - param n
        ...
        - test (suite) n ID:
        ...

        :param data: Data to merge.
        :type data: pandas.Series
        :returns: Merged data.
        :rtype: pandas.Series
        """

        logging.info("    Merging data ...")

        merged_data = pd.Series()
        for _, builds in data.iteritems():
            for _, item in builds.iteritems():
                for ID, item_data in item.iteritems():
                    merged_data[ID] = item_data

        return merged_data