summaryrefslogtreecommitdiffstats
path: root/tools/checkdocs.sh
blob: 4a798b378c073b50beef634b1efa8b195197cb4e (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
#!/bin/bash
#set -x # uncomment for bash script debugging

### ============================================================================
### 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.
### ============LICENSE_END=====================================================

###
### checkdocs.sh
###
### AUTHOR(S):
### Thomas Kulik, Deutsche Telekom AG, 2020 - 2021
###
### DESCRIPTION:
### Retrieves a full list of ONAP repos from gerrit inluding their state.
### Clones all active repos of the ONAP master branch plus other requested ONAP
### branches. Then the script does some docs related analyses depending on the
### clone results. It creates logfiles containing filtered results. In addition
### a table.csv is created which can be used to import it in a spreadsheed.
### Also a zip-file is created which contains all the results.
###
### IMPORTANT:
### - in the output, repo names are shown in square brackets for readability
###   e.g [aai/aai-common]/docs/release-notes.rst
### - in the table.csv file you see data for the requested branch if available.
###   if not available, data is retrieved from the master branch. it will be
###   denoted in round brackets, e.g. (3) (tox.ini)
###
### REQUIREMENTS:
### curl
### jq
###

###
### SOME HELPING COMMANDS TO PROCESS LOG FILES:
### create repo list
### curl -s https://git.onap.org/ | grep "^<tr><td class='toplevel-repo'><a title='" | sed -r "s:^<tr><td class='toplevel-repo'><a title='::" | sed -r "s:'.*::"
###
### remove branchname from the line:
### cat frankfurt_repoclone.log | sed 's:frankfurt|::'
###
### list only image names
### cat master_dockerimagesfull.log | grep image | sed -r 's:image\:::' | sed -r 's:^ +::' | sed '/^[[:space:]]*$/d'
###
### more interesting stuff ...
### curl https://gerrit.onap.org/r/projects/?d
### LONG:  curl -s 'https://gerrit.onap.org/r/projects/?d' | awk '{if(NR>1)print}' | jq -c '.[] | {id, state}' | sed -r 's:%2F:/:g' | sed -r 's:["{}]::g' | sed -r 's:id\:::' | sed -r 's:,state\::|:' | sed '/All-Projects/d' | sed '/All-Users/d'
### SHORT: curl -s 'https://gerrit.onap.org/r/projects/?d' | awk '{if(NR>1)print}' | jq -c '.[] | {id, state}' | sed -r 's:%2F:/:g; s:["{}]::g; s:id\:::; s:,state\::|:; /All-Projects/d; /All-Users/d'
###

script_version="1.6 (2021/03/30)"

# save command for the restart with logging enabled
command=$0
arguments=$@
fullcommand="${command} ${arguments}"

###
### functions
###

# print usage
function usage() {
  echo "                                                           "
  echo " checkdocs.sh Version ${script_version}"
  echo "                                                           "
  echo " USAGE:                                                    "
  echo "  ./checkdocs.sh <arguments>                               "
  echo "                                                           "
  echo " ARGUMENTS:                                                "
  echo "  -u|--user username                                       "
  echo "  linux foundation username used to clone ONAP repositories"
  echo "                                                           "
  echo "  -b|--branches branch1,branch2,branch3                    "
  echo "  list of branches to be cloned. master is automatically   "
  echo "  added to the list. do not add manually!                  "
  echo "                                                           "
  echo "  -d|--dev                                                 "
  echo "  development-mode - limits number of repos to be cloned   "
  echo "                                                           "
}

# draw a simple line
function drawline {
  echo "*******************************************************************************"
}

# remove lockfile in case script is interrupted
trap InterruptedScript SIGINT SIGTERM SIGHUP SIGKILL SIGSTOP
function InterruptedScript {
  echo " "
  echo "Script was interrupted."
  if [ -f $lockfile ] ; then
    rm $lockfile
  fi
  exit 0
}

###
### arguments handling
###

PARAMS=""

while (( "$#" )); do
  case "$1" in
    -d|--dev)
      devmode="TRUE"
      shift
      ;;
    -b|--branches)
      if [ -n "$2" ] && [ ${2:0:1} != "-" ]; then
        branches_csv=$2
        shift 2
      else
        echo "Error: Argument for $1 is missing" >&2
        usage
        exit 1
      fi
      ;;
    -u|--user)
      if [ -n "$2" ] && [ ${2:0:1} != "-" ]; then
        lfusername=$2
        shift 2
      else
        echo "Error: Argument for $1 is missing" >&2
        usage
        exit 1
      fi
        ;;
    -*|--*=) # unsupported flags
      echo "Error: Unsupported argument $1" >&2
      usage
      exit 1
      ;;
    *) # preserve positional arguments
      PARAMS="$PARAMS $1"
      shift
      ;;
  esac
done

# set positional arguments in their proper place
eval set -- "$PARAMS"

# old: declare -a branches=("master" "frankfurt" "guilin")
if [[ $branches_csv == "" || $lfusername == "" ]]; then
  usage
  exit -1
fi

# master branch is automatically added and must not part of the user arguments
if [[ $branches_csv == *"master"* ]]; then
  usage
  exit -1
fi
# clone master first, then the other branches
branches_csv="master,${branches_csv}"

# create the branches array by readinging in the values from the variable
IFS=',' read -r -a branches <<< "${branches_csv}"

#echo "DBUG: devmode      = \"${devmode}\""
#echo "DBUG: branches_csv = \"${branches_csv}\""
#echo "DBUG: lfusername   = \"${lfusername}\""
#echo "DBUG: branches     = \"${branches[@]}\""

# restart script with logging enabled
lockfile="checkdocs-runtime-lockfile"
if [ ! -f $lockfile ] ; then
  touch $lockfile
  echo "Restarting script with logging enabled."
  ${fullcommand} 2>&1 | tee checkdocs.log
  rm $lockfile
  exit
fi

echo " "
echo "checkdocs.sh Version ${script_version}"
echo " "

# curl must be installed
if ! command -v curl &> /dev/null
then
  echo "ERROR: curl command could not be found"
  exit -1
fi

today=$(date '+%Y-%m-%d');
repolist="gerrit-repos-master-"$today".txt";
unique=$(date +%s)

echo "Retrieving a full list of ONAP repositories (master) from gerrit.onap.org."

# retrieve the full repolist from gerrit
# workaround because of the (wrong?) response of gerrit.onap.org which makes jq command fail
# "| awk '{if(NR>1)print}'" filters the first line of the response so that jq will work again (thx marek)
curl -s 'https://gerrit.onap.org/r/projects/?d' | awk '{if(NR>1)print}' | jq -c '.[] | {id, state}' | sed -r 's:%2F:/:g; s:["{}]::g; s:id\:::; s:,state\::|:; /All-Projects/d; /All-Users/d' >./$repolist

# process the created repolist and try to clone the projects from the mirror

source="git://cloud.onap.org/mirror"
echo "Using \"${source}\" as the source and username \"${lfusername}\" for cloning the repositories."
echo "Start cloning of repositories ..."

for branch in "${branches[@]}"
do

  echo " "
  echo "###"
  echo "### ${branch}"
  echo "###"
  echo " "

  branch_upper=$(echo "${branch}" | tr '[:lower:]' '[:upper:]')

  mkdir $branch
  cp $repolist $branch
  cd $branch

  devcounter=0

  # process repolist
  while read line
  do

  if [[ $devmode == "TRUE" ]]; then
    devcounter=$((devcounter+1))
  fi

  if [[ $devcounter -lt "50" ]]; then

      if [[ $devmode == "TRUE" ]]; then
        echo "INFO: devmode! counter=${devcounter}"
      fi

      drawline
      reponame=$(echo $line | awk -F "|" '{print $1}');
      repostate=$(echo $line | awk -F "|" '{print $2}');
      echo $reponame
      echo $repostate

      if [[ $repostate == "ACTIVE" ]] || [[ $repostate == "READ_ONLY" ]]; then
        echo "Cloning \"${branch}\" branch of \"${repostate}\" project ${reponame}..."

        # previously used:   git clone --branch ${branch} --recurse-submodules ssh://${lfusername}@gerrit.onap.org:29418/$reponame ./$reponame
        # clone script Jess: git clone "git://cloud.onap.org/mirror/${i}" "${LOCALNAME}"
        git clone --branch ${branch} --recurse-submodules ${source}/${reponame} ./${reponame}
        gitexitcode=$?

        if [[ ! ${gitexitcode} == "0" ]]; then
          errormsg=$(tail -1 ../checkdocs.log)
        else
          errormsg="cloned"
        fi

        # repoclone.log format:  $1=gitexitcode|$2=reponame|$3=repostate|$4=errormsg
        echo "${gitexitcode}|${reponame}|${repostate}|${errormsg}" | tee -a ${branch}_repoclone.log

      #elif [[ $repostate == "READ_ONLY" ]]; then
        #echo "-|${reponame}|${repostate}|ignored" | tee -a ${branch}_repoclone.log
      else
        echo "-|${reponame}|unknown repo state \"${repostate}\"|-" | tee -a ${branch}_repoclone.log
      fi

      # examine repo
      if [[ ${gitexitcode} == "0" ]]; then

        printf "\ndocs directories:\n"
        find ./$reponame -type d -name docs | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_docs.log

        printf "\nrst files:\n"
        find ./$reponame -type f -name *.rst | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_rstfiles.log

        printf "\nrelease notes rst:\n"
        find ./$reponame -type f | grep 'release.*note.*.rst' | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_releasenotes.log

        printf "\ntox.ini files:\n"
        find ./$reponame -type f -name tox.ini | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_toxini.log

        printf "\nconf.py files:\n"
        find ./$reponame -type f -name conf.py | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_confpy.log

        printf "\nindex.rst files:\n"
        find ./$reponame -type f -name index.rst | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_indexrst.log

        printf "\nINFO.yaml files:\n"
        find ./$reponame -type f -name INFO.yaml | sed -r 's:./::' | sed -r s:${reponame}:[${reponame}]: | tee -a ${branch}_infoyaml.log

      fi

    # end defcounter loop
    fi

    gitexitcode=""

  done <${repolist}

  # examine repos
  drawline
  find . -type f -name values.yaml -print -exec grep "image:" {} \; | sed -r 's:^ +::' | tee ${branch}_dockerimagesfull.log
  drawline
  ls --format single-column -d */ | sed 's:/$::' | tee ${branch}_directories.log
  drawline
  cat ${branch}_dockerimagesfull.log | grep image | sed -r 's:image\:::' | sed -r 's:^ +::' | sed '/^[[:space:]]*$/d' >${branch}_dockerimages.log
  drawline
  ls --format single-column -d oom/kubernetes/*/ | tee ${branch}_oomkubernetes.log
  drawline

  # examine docs
  readarray -t docs_array < ./${branch}_docs.log;

  for line in "${docs_array[@]}"
  do

    echo $line | tee -a ${branch}_docsconfig.log

    # remove [ and ] which are distinguish the project name in the output
    line=$(echo $line | sed -r 's:\[:: ; s:\]::')

    if [ -f ./${line}/conf.py ] ; then
      echo "  conf.py ..... found" | tee -a ${branch}_docsconfig.log
    else
      echo "  conf.py ..... NOT FOUND" | tee -a ${branch}_docsconfig.log
    fi

    if [ -f ./${line}/index.rst ] ; then
      echo "  index.rst ... found" | tee -a ${branch}_docsconfig.log
    else
      echo "  index.rst ... NOT FOUND" | tee -a ${branch}_docsconfig.log
    fi

    if [ -f ./${line}/tox.ini ] ; then
      echo "  tox.ini ..... found" | tee -a ${branch}_docsconfig.log
    else
      echo "  tox.ini ..... NOT FOUND" | tee -a ${branch}_docsconfig.log
    fi

    echo " " | tee -a ${branch}_docsconfig.log

  done
  unset docs_array

  drawline

  ###
  ### build a csv table that combines results
  ###

  #
  # csv column #1: project name
  #

  readarray -t array < ./${repolist};
  i=0
  csv[i]="project"
  ((i++))
  for line in "${array[@]}"
  do
    reponame=$(echo $line | awk -F "|" '{print $1}');
    project=$(echo $reponame | sed 's:/.*$::')
    #echo "DBUG: reponame=${reponame}"
    #echo "DBUG:  project=${project}"
    #echo "DBUG:        i=${i}"
    csv[i]=${project}
    ((i++))
  done
  unset array
  unset i
  unset reponame
  unset project

  #
  # csv column #2: repo name
  #

  readarray -t array < ./${repolist};
  i=0
  csv[i]="${csv[i]},MASTER repo name"
  ((i++))
  for line in "${array[@]}"
  do
    reponame=$(echo $line | awk -F "|" '{print $1}');
    csv[i]="${csv[i]},${reponame}"
    ((i++))
  done
  unset array
  unset i
  unset reponame

  #
  # csv column #3: repo state
  #

  readarray -t array < ./${repolist};
  i=0
  csv[i]="${csv[i]},MASTER repo state"
  ((i++))
  for line in "${array[@]}"
  do
    repostate=$(echo $line | awk -F "|" '{print $2}');
    csv[i]="${csv[i]},${repostate}"
    ((i++))
  done
  unset array
  unset i
  unset repostate

  #
  # csv column #4: clone message
  #

  readarray -t array < ./${branch}_repoclone.log;
  i=0
  csv[i]="${csv[i]},${branch_upper} clone message"
  ((i++))
  for line in "${array[@]}"
  do
    # repoclone.log format:  $1=gitexitcode|$2=reponame|$3=repostate|$4=errormsg
    errormsg=$(echo $line | awk -F "|" '{print $4}');
    csv[i]="${csv[i]},${errormsg}"
    ((i++))
  done
  unset array
  unset i
  unset errormsg

  #
  # csv column #5: lifecycle state
  # extracted from the INFO.yaml
  #

  readarray -t array < ./${repolist};
  i=0
  csv[i]="${csv[i]},project lifecycle state"
  ((i++))
  for line in "${array[@]}"
  do
    reponame=$(echo $line | awk -F "|" '{print $1}');
    if [ -f ./${reponame}/INFO.yaml ] ; then
      # check if repo/branch has a INFO.yaml
      lifecycleproject=$(grep '^project: ' ./${reponame}/INFO.yaml | awk -F ":" '{print $2}' | sed 's:^ ::' | sed "s:'::g" | tr '[:upper:]' '[:lower:]' | sed 's/\r$//')
      lifecyclestate=$(grep '^lifecycle_state: ' ./${reponame}/INFO.yaml | awk -F ":" '{print $2}' | sed 's:^ ::' | sed "s:'::g" | tr '[:upper:]' '[:lower:]' | sed 's/\r$//')
    elif [ ${branch} != "master" ] && [ -f ../master/${reponame}/INFO.yaml ] ; then
      # if current branch is not master AND if info.yaml not found in the current repo/branch THAN use INFO.yaml of repo/master if available
      #echo "DBUG: branch=${branch} - checking master for INFO.yaml"
      lifecycleproject=$(grep '^project: ' ../master/${reponame}/INFO.yaml | awk -F ":" '{print $2}' | sed 's:^ ::' | sed "s:'::g" | tr '[:upper:]' '[:lower:]' | sed 's/\r$//')
      lifecyclestate=$(grep '^lifecycle_state: ' ../master/${reponame}/INFO.yaml | awk -F ":" '{print $2}' | sed 's:^ ::' | sed "s:'::g" | tr '[:upper:]' '[:lower:]' | sed 's/\r$//')
      lifecyclestate="(${lifecyclestate})"
    else
      lifecyclestate="INFO.yaml not found"
    fi
    #echo "DBUG: working dir is ...";pwd
    #echo "DBUG: lifecycleproject=${lifecycleproject}"
    #echo "DBUG:   lifecyclestate=${lifecyclestate}"
    csv[i]="${csv[i]},${lifecyclestate}"
    ((i++))
  done
  unset array
  unset i
  unset lifecycleproject
  unset lifecyclestate

  #
  # csv column #6: RELEASE component (yes|maybe|unknown)
  # to be filled with values of the planned release config file maintained by
  # the onap release manager
  #

  # repoclone.log format:  $1=gitexitcode|$2=reponame|$3=repostate|$4=errormsg
  readarray -t array < ./${branch}_repoclone.log;
  i=0
  csv[i]="${csv[i]},${branch_upper} component"
  ((i++))
  for line in "${array[@]}"
  do

    # repoclone.log format:  $1=gitexitcode|$2=reponame|$3=repostate|$4=errormsg
    gitexitcode=$(echo $line | awk -F "|" '{print $1}');
       reponame=$(echo $line | awk -F "|" '{print $2}');
      repostate=$(echo $line | awk -F "|" '{print $3}');
       errormsg=$(echo $line | awk -F "|" '{print $4}');

    if [[ ${repostate} == "ACTIVE" && ${gitexitcode} == "0" ]]; then
      releasecomponent="yes"
    elif [ ${repostate} == "ACTIVE" ]; then
    #elif [[ ${repostate} == "ACTIVE" && ${gitexitcode} == "128" ]]; then
      releasecomponent="maybe"
    elif [[ ${repostate} == "READ_ONLY" && ${gitexitcode} == "0" ]]; then
      releasecomponent="yes"
    elif [ ${repostate} == "READ_ONLY" ]; then
      releasecomponent="maybe"
    else
      releasecomponent="unknown"
    fi

    csv[i]="${csv[i]},${releasecomponent}"
    ((i++))
  done
  unset array
  unset i
  unset gitexitcode
  unset reponame
  unset repostate
  unset errormsg
  unset releasecomponent

  #
  # csv column #7:  docs (at repo root directory only; no recursive search!)
  # csv column #8:  conf.py
  # csv column #9:  tox.ini
  # csv column #10: index.rst
  #
  # columns are filled with values from requested branch.
  # if data is not available values from master branch are used.
  # to identify master branch values, data is put into round brackets "(...)"
  #

  readarray -t array < ./${repolist};
  i=0
  csv[$i]="${csv[i]},docs,conf.py,tox.ini,index.rst"
  ((i++))
  for line in "${array[@]}"
  do
    line=$(echo $line | sed 's:|.*$::')
    #echo "DBUG: line=${line}"
    #echo "DBUG: i=${i}"

    # docs
    if [ -d ./${line}/docs ] ; then
      docs="docs"
    elif [ -d ../master/${line}/docs ] ; then
      docs="(docs)"
    else
      docs="-"
    fi

    # conf.py
    if [ -f ./${line}/docs/conf.py ] ; then
      docs="${docs},conf.py"
    elif [ -f ../master/${line}/docs/conf.py ] ; then
      docs="${docs},(conf.py)"
    else
      docs="${docs},-"
    fi

    # tox.ini (check docs dir and also check project root dir)
    if [ -f ./${line}/docs/tox.ini ] || [ -f ./${line}/tox.ini ]; then
      docs="${docs},tox.ini"
      # tox.ini @ branch/docs dir
      if [ -f ./${line}/docs/tox.ini ] ; then
        docs="${docs} @docs"
      fi
      # tox.ini @ branch/project root dir
      if [ -f ./${line}/tox.ini ] ; then
        docs="${docs} @root"
      fi
    elif [ -f ../master/${line}/docs/tox.ini ] || [ -f ../master/${line}/tox.ini ]; then
      docs="${docs},(tox.ini"
      # tox.ini @ master/docs dir
      if [ -f ../master/${line}/docs/tox.ini ] ; then
        docs="${docs} @docs"
      fi
      # tox.ini @ master/project root dir
      if [ -f ../master/${line}/tox.ini ] ; then
        docs="${docs} @root"
      fi   
      # just add a round bracket at the end of the value
      docs="${docs})"
    else
      # no tox.ini found in docs or root dir
      docs="${docs},-"
    fi

    # index.rst
    if [ -f ./${line}/docs/index.rst ] ; then
      docs="${docs},index.rst"
    elif [ -f ../master/${line}/docs/index.rst ] ; then
      docs="${docs},(index.rst)"
    else
      docs="${docs},-"
    fi

    #echo "DBUG: docs=${docs}"
    line="${csv[i]},${docs}"
    csv[$i]=${line}
    ((i++))
  done
  unset array
  unset i
  unset docs

  #
  # csv column #11: index.html@RTD accessibility check
  # csv column #12: index.html url
  #

  readarray -t array < ./${branch}_repoclone.log;
  i=0
  csv[i]="${csv[i]},index.html@RTD,index.html url"
  ((i++))
  for line in "${array[@]}"
  do
    # repoclone.log format:  $1=gitexitcode|$2=reponame|$3=repostate|$4=errormsg
    gitexitcode=$(echo $line | awk -F "|" '{print $1}');
       reponame=$(echo $line | awk -F "|" '{print $2}');
      repostate=$(echo $line | awk -F "|" '{print $3}');
       errormsg=$(echo $line | awk -F "|" '{print $4}');

            url=""
    curl_result=""

    # this script works only with release "frankfurt" and later because
    # earlier releases are using submodule structure for documentation files
    if echo "$branch" | grep -q '^[abcde]'; then
      curl_result="unsupported release"
      url="-"
    else

      # we are working on "frankfurt" branch or later ...
      if [[ ${repostate} == "ACTIVE" ]] || [[ ${repostate} == "READ_ONLY" ]]; then

        # OPTIONAL: USE ALSO GITEXITCODE AS A FILTER CRITERIA ???

        # url base
        # important! only doc project needs a different url base
        if [[ ${reponame} == "doc" ]]; then
          url_start="https://docs.onap.org"
        else
          url_start="https://docs.onap.org/projects/onap"
        fi
        url_lang="en"
        url_branch=${branch}

        # "master" branch documentation is available as "latest" in RTD
        if [[ ${url_branch} == "master" ]]; then
          url_branch="latest"
        fi

        # replace all / characters in repo name with - charachter
        url_repo=$(echo ${reponame} | sed -r 's/\//-/g')
        url_file="index.html"

        # build the full url
        if [[ ${reponame} == "doc" ]]; then
          # build the full url for the doc project
          url="${url_start}/${url_lang}/${url_branch}/${url_file}"
        else
          # build the full url for the other projects
          url="${url_start}-${url_repo}/${url_lang}/${url_branch}/${url_file}"
        fi
        #echo "DBUG: url=$url"

        # test accessibility of url
        curl --head --silent --fail "${url}?${unique}" >/dev/null
        curl_result=$?

        # convert numeric results to text
        if [ "${curl_result}" = "0" ]; then
          curl_result="accessible"
        elif [ "${curl_result}" = "22" ]; then
          curl_result="does not exist"
        else
          curl_result="ERROR:${curl_result}"
        fi

        # url does not exist for this branch.
        # in case the requested url is not already for "master" branch,
        # we try to access the url of the master branch and denote the
        # result by using round brackets (result)
        if [[ ${curl_result} == "does not exist" && ! $branch == "master" ]]; then

          # build the full (master/latest) url
          url="${url_start}-${url_repo}/${url_lang}/latest/${url_file}"
          #echo "DBUG: url=$url"

          # test accessibility of url in "master branch" (latest)
          curl --head --silent --fail "${url}?${unique}" >/dev/null
          curl_result=$?
          # denote result as a value from "master" branch (latest)
          url="(${url})"

          # convert numeric results to text
          if [ "${curl_result}" = "0" ]; then
            curl_result="(accessible)"
          elif [ "${curl_result}" = "22" ]; then
            curl_result="(does not exist)"
          else
            curl_result="(ERROR:${curl_result})"
          fi

        fi
      else
        # repostate IS NOT ACTIVE OR READ_ONLY - no curl test required
        curl_result="-"
        url="-"
      fi
    fi

    echo "$url ... $curl_result"
    csv[i]="${csv[i]},${curl_result},${url}"
    #echo "DBUG: csv line=${csv[i]}"

    ((i++))
  done

  #
  # csv column #13: release notes
  #

  readarray -t array < ../${repolist};
  i=0
  csv[i]="${csv[i]},release notes"
  ((i++))
  for line in "${array[@]}"
  do
    line=$(echo $line | sed 's:|.*$::')
    #echo "DBUG: line=\"${line}\""
    #echo "DBUG: i=${i}"
    relnote=""

    # put repo name in square brackets for increased grep hit rate
    # escape minus and bracket characters to avoid problems with the grep command
    #repo_grepable=$(echo ${line} | sed -r s:${line}:[${line}]: | sed -r 's/-/\\-/g' | sed -r 's/\[/\\[/g' | sed -r 's/\]/\\]/g')
    #echo "DBUG: repo_grepable=\"${repo_grepable}\""

    # check if repo dir exists in this branch
    if [ -d ./${line} ] ; then
      # if yes, check if repo name appears in the branch releasenotes.log
      relnote=$(find "./${line}" -type f | grep 'release.*note.*.rst' | wc -l);
      #echo "DBUG: relnote=${relnote}"
      # repo dir DOES NOT exist in this branch - so check if repo dir exists in MASTER branch
    elif [ -d ../master/${line} ] ; then
      # if yes, check if repo name appears in the MASTER releasenotes.log
      # count release notes files in MASTER branch (in repo root and its subdirectories)
      relnote=$(find "../master/${line}" -type f | grep 'release.*note.*.rst' | wc -l);
      #echo "DBUG: relnote=${relnote}"
      # put results in round brackets to show that this is MASTER data
      relnote=$(echo ${relnote} | sed -r s:${relnote}:\(${relnote}\):)
    else
      relnote="-"
    fi
    #echo "DBUG: relnote=${relnote}"

    line="${csv[i]},${relnote}"
    csv[i]=${line}
    ((i++))

  done
  unset array
  unset i
  unset relnote
  unset repo_grepable

  #
  # build the table.csv file
  #

  for i in "${csv[@]}"
  do
    echo "$i" | tee -a ./${branch}_table.csv
  done

  #
  # create data package for this branch and zip it
  #

  datadir=${branch}_data
  mkdir $datadir
  cp $repolist $datadir
  cp ${branch}_table.csv $datadir
  cp ${branch}_*.log $datadir
  zip -r ${datadir}.zip $datadir

  # return from the branch directory
  cd ..

# return and work on the next requested branch ... or exit
done