summaryrefslogtreecommitdiffstats
path: root/bin/reproducible_html_notes.py
blob: c710c8ed8b6738bf4e5b7cc941345f95fd5c2856 (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
#!/usr/bin/python3
# -*- coding: utf-8 -*-
#
# Copyright © 2015 Mattia Rizzolo <mattia@mapreri.org>
# Based on reproducible_html_notes.sh © 2014 Holger Levsen <holger@layer-acht.org>
# Licensed under GPL-2
#
# Depends: python3 python3-yaml
#
# Build html pages based on the content of the notes.git repository

import yaml
from reproducible_common import *
from reproducible_html_packages import gen_packages_html

NOTES = 'packages.yml'
ISSUES = 'issues.yml'

note_html = Template((tab*2).join("""
<table class="body">
  <tr>
    <td>Version annotated:</td>
    <td>$version</td>
  </tr>
  $infos
  <tr>
    <td colspan="2">&nbsp;</td>
  </tr>
  <tr>
    <td colspan="2" style="text-align:right; font-size:0.9em;">
      <p>
        Notes are stored in <a href="https://anonscm.debian.org/cgit/reproducible/notes.git" target="_parent">notes.git</a>.
      </p>
    </td>
  </tr>
</table>""".splitlines(True)))
note_issues_html = Template((tab*3).join("""
<tr>
  <td>
    Identified issues:
  </td>
  <td>
    $issues
  </td>
</tr>""".splitlines(True)))
note_bugs_html = Template((tab*4).join("""
<tr>
  <td>
    Bugs noted:
  </td>
  <td>
     $bugs
  </td>
</tr>""".splitlines(True)))
note_comments_html = Template((tab*3).join("""
<tr>
  <td>
    Comments:
  </td>
  <td>
    $comments
  </td>
</tr>""".splitlines(True)))

note_issue_html_url = Template((tab*6).join("""
<tr>
  <td>
    URL
  </td>
  <td>
    <a href="$url" target="_blank">$url</a>
  </td>
</tr>""".splitlines(True)))
note_issue_html_desc = Template((tab*6).join("""
<tr>
  <td>
    Description
  </td>
  <td>
     $description
  </td>
</tr>""".splitlines(True)))
note_issue_html = Template((tab*5).join(("""
<table class="body">
  <tr>
    <td>
      Identifier:
    </td>
    <td>
      <a href="%s/${issue}_issue.html" target="_parent">$issue</a>
    </td>
  </tr>
  $issue_info
</table>
""" % ISSUES_URI).splitlines(True)))

issue_html_url = Template((tab*4).join("""
<tr>
  <td>
    URL:
  </td>
  <td>
    <a href="$url">$url</a>
  </td>
</tr>""".splitlines(True)))
issue_html = Template((tab*3).join("""
<table class="body">
  <tr>
    <td>
      Identifier:
    </td>
    <th>
      $issue
    </th>
  </tr>
    $urls
  <tr>
    <td>
      Description:
    </td>
    <td>
      $description
    </td>
  </tr>
  <tr>
    <td>
      Packages known to be affected by this issue:
    </td>
    <td>
$affected_pkgs
    </td>
  </tr>
  <tr><td colspan="2">&nbsp;</td></tr>
  <tr>
    <td colspan="2" style="text-align:right; font-size:0.9em;">
      <p>Notes are stored in <a href="https://anonscm.debian.org/cgit/reproducible/notes.git" target="_parent">notes.git</a>.</p>
    </td>
  </tr>
</table>""".splitlines(True)))


def load_notes():
    """
    format:
    { 'package_name': {'version': '0.0', 'comments'<etc>}, 'package_name':{} }
    """
    with open(NOTES) as fd:
        notes = yaml.load(fd)
    log.debug("notes loaded. There are " + str(len(notes)) +
                  " package listed")
    for package in notes:   # check if every pacakge listed on the notes
        try:                # actually have been tested
            query = 'SELECT s.name ' + \
                    'FROM results AS r JOIN sources AS s ON r.package_id=s.id ' + \
                    'WHERE s.name="{pkg}" AND r.status != ""'
            query = query.format(pkg=package)
            result = query_db(query)[0]
        except IndexError:
            print_critical_message('This query produces no results: ' + query +
                    '\nThis means there is no tested package with the name ' +
                    package + '.')
            raise
    return notes


def load_issues():
    """
    format:
    { 'issue_name': {'description': 'blabla', 'url': 'blabla'} }
    """
    with open(ISSUES) as fd:
        issues = yaml.load(fd)
    log.debug("issues loaded. There are " + str(len(issues)) +
                  " issues listed")
    return issues


def fill_issue_in_note(issue):
    details = issues[issue]
    html = ''
    if 'url' in details:
        html += note_issue_html_url.substitute(url=details['url'])
    if 'description' in details:
        desc = details['description'].replace('\n', '<br />')
        html += note_issue_html_desc.substitute(description=desc)
    else:
        log.warning("The issue " + issue + " misses a description")
    return note_issue_html.substitute(issue=issue, issue_info=html)


def gen_html_note(note):
    """
    Given a note as input (as a dict:
    {"package_name": {"version": "0.0.0", "comments": "blablabla",
     "bugs": [111, 222], "issues": ["issue1", "issue2"]}}
    ) it returns the html body
    """
    infos = ''
    # check for issues:
    if 'issues' in note:
        tmp = ''
        for issue in note['issues']:
            tmp += fill_issue_in_note(issue)
            try:
                issues_count[issue].append(note['package'])
            except KeyError:
                issues_count[issue] = [note['package']]
        infos += note_issues_html.substitute(issues=tmp)
    # check for bugs:
    if 'bugs' in note:
        bugurls = ''
        for bug in note['bugs']:
            bugurls += '<a href="https://bugs.debian.org/' + str(bug) + \
                       '" target="_parent">' + str(bug) + '</a><br />'
        infos += note_bugs_html.substitute(bugs=bugurls)
    # check for comments:
    if 'comments' in note:
        comment = note['comments']
        comment = url2html.sub(r'<a href="\1">\1</a>', comment)
        comment = comment.replace('\n', '<br />')
        infos += note_comments_html.substitute(comments=comment)
    try:
        return note_html.substitute(version=str(note['version']), infos=infos)
    except KeyError:
        log.warning('You should really include a version in the ' +
              str(note['package']) + ' note')
        return note_html.substitute(version='N/A', infos=infos)

def gen_html_issue(issue):
    """
    Given a issue as input (as a dict:
    {"issue_identifier": {"description": "blablabla", "url": "blabla"}}
    ) it returns the html body
    """
    # check for url:
    if 'url' in issues[issue]:
        url = issue_html_url.substitute(url=issues[issue]['url'])
    else:
        url = ''
    # add affected packages:
    affected = ''
    try:
        affected += tab*4 + '<b>' + str(len(issues_count[issue])) + '</b>:\n'
        for pkg in sorted(issues_count[issue]):
            # FIXME we currently consider notes only for sid/amd64
            affected += (tab*7 + '<a href="%s/sid/amd64/%s.html" ' +
                         'class="noted">%s</a>\n') % (RB_PKG_URI, pkg, pkg)
    except KeyError:    # The note is not listed in any package, that is
        affected = '<i>None</i>'
    # check for description:
    try:
        desc = issues[issue]['description']
    except KeyError:
        log.warning('You should really include a description in the ' +
              issue + ' issue')
        desc = 'N/A'
    desc = url2html.sub(r'<a href="\1">\1</a>', desc)
    desc = desc.replace('\n', '<br />')
    return issue_html.substitute(issue=issue, urls=url, description=desc,
                                   affected_pkgs=affected)

def purge_old_notes(notes):
    removed_pages = []
    to_rebuild = []
    presents = sorted(os.listdir(NOTES_PATH))
    for page in presents:
        pkg = page.rsplit('_', 1)[0]
        log.debug('Checking if ' + page + ' (from ' + pkg + ') is still needed')
        if pkg not in notes:
            log.info('There are no notes for ' + pkg + '. Removing old page.')
            os.remove(NOTES_PATH + '/' + page)
            removed_pages.append(pkg)
    for pkg in removed_pages:
        try:
            query = 'SELECT s.name ' + \
                    'FROM results AS r JOIN sources AS s ON r.package_id=s.id ' + \
                    'WHERE s.name="{pkg}" AND r.status != "" AND s.suite="sid"'
            query = query.format(pkg=pkg)
            to_rebuild.append(query_db(query)[0][0])
        except IndexError:  # the package is not tested. this can happen if
            pass            # a package got removed from the archive
    if to_rebuild:
        gen_packages_html(to_rebuild)


def iterate_over_notes(notes):
    num_notes = str(len(notes))
    i = 0
    for package in sorted(notes):
        log.debug('iterating over notes... ' + str(i) + '/' + num_notes)
        note = notes[package]
        note['package'] = package
        log.debug('\t' + str(note))
        html = gen_html_note(note)

        title = 'Notes for ' + package + ' - reproducible builds result'
        destfile = NOTES_PATH + '/' + package + '_note.html'
        write_html_page(title=title, body=html, destfile=destfile,
                        noheader=True)

        desturl = REPRODUCIBLE_URL + NOTES_URI + '/' + package + '_note.html'
        log.info("you can now see your notes at " + desturl)
        i = i + 1

def iterate_over_issues(issues):
    num_issues = str(len(issues))
    i = 0
    for issue in sorted(issues):
        log.debug('iterating over issues... ' + str(i) + '/' + num_issues)
        log.debug('\t' + str(issue))
        html = gen_html_issue(issue)

        title = 'Notes about issue ' + issue
        destfile = ISSUES_PATH + '/' + issue + '_issue.html'
        write_html_page(title=title, body=html, destfile=destfile,
                        style_note=True)

        desturl = REPRODUCIBLE_URL + ISSUES_URI + '/' + issue + '_issue.html'
        log.info("you can now see the issue at " + desturl)
        i = i + 1

def sort_issues(issue):
    try:
        return (-len(issues_count[issue]), issue)
    except KeyError:    # there are no packages affected by this issue
        return (0, issue)

def index_issues(issues):
    templ = "\n<table class=\"body\">\n" + tab + "<tr>\n" + tab*2 + "<th>\n" \
          + tab*3 + "Identified issues\n" + tab*2 + "</th>\n" + tab*2 + "<th>\n" \
          + tab*3 + "Affected packages\n" + tab*2 + "</th>\n" + tab + "</tr>\n"
    html = (tab*2).join(templ.splitlines(True))
    for issue in sorted(issues, key=sort_issues):
        html += tab*3 + '<tr>\n'
        html += tab*4 + '<td><a href="' + ISSUES_URI + '/' + issue + \
                '_issue.html">' + issue + '</a></td>\n'
        html += tab*4 + '<td>\n'
        try:
            html += tab*5 + '<b>' + str(len(issues_count[issue])) + '</b>:\n'
            html += tab*5 + ', '.join(issues_count[issue]) + '\n'
        except KeyError:    # there are no packages affected by this issue
            html += tab*5 + '<b>0</b>\n'
        html += tab*4 + '</td>\n'
        html += tab*3 + '</tr>\n'
    html += tab*2 + '</table>\n'
    html += tab*2 + '<p>For a total of <b>' + \
            str(len([x for x in notes if notes[x].get('issues')])) + \
            '</b> packages categorized in <b>' + str(len(issues)) + \
            '</b> issues.</p>'
    html += tab*2 + '<p>Notes are stored in <a href="https://anonscm.debian.org/cgit/reproducible/notes.git" target="_parent">notes.git</a>.</p>'
    title = 'Overview of known issues related to reproducible builds'
    destfile = BASE + '/index_issues.html'
    desturl = REPRODUCIBLE_URL + '/index_issues.html'
    write_html_page(title=title, body=html, destfile=destfile)
    log.info('Issues index now available at ' + desturl)


def index_notes(notes, bugs):
    log.debug('Building the index_notes page...')
    all_pkgs = query_db('SELECT s.name, r.status ' +
                        'FROM results AS r JOIN sources AS s ON r.package_id=s.id ' +
                        'WHERE s.suite="sid" ORDER BY s.name')
    with_notes = [x for x in all_pkgs if x[0] in notes]
    html = '\n<p>There are ' + str(len(notes)) + ' packages with notes.</p>\n'
    for status in ['unreproducible', 'FTBFS', 'not for us', 'blacklisted', 'reproducible']:
        pkgs = [x[0] for x in with_notes if x[1] == status]
        if not pkgs:
            continue
        html += '<p>\n'
        html += tab + '<img src="/static/' + join_status_icon(status)[1] + '"'
        html += ' alt="' + status + ' icon" />\n'
        pkgs = [x[0] for x in with_notes if x[1] == status]
        html += tab + str(len(pkgs)) + ' ' + status + ' packages:\n'
        html += tab + '<code>\n'
        for pkg in pkgs:
            # FIXME we currently consider notes only for sid/amd64
            url = RB_PKG_URI + '/sid/amd64/' + pkg + '.html'
            html += tab*2 + '<a href="' + url + '" class="noted">' + pkg
            html += '</a>' + get_trailing_icon(pkg, bugs) + '\n'
        html += tab + '</code>\n'
        html += '</p>\n'
    html += '<p>Notes are stored in <a href="https://anonscm.debian.org/cgit/reproducible/notes.git" target="_parent">notes.git</a>.</p>'
    html = (tab*2).join(html.splitlines(True))
    title = 'Overview of packages with notes'
    destfile = BASE + '/index_notes.html'
    desturl = REPRODUCIBLE_URL + '/index_notes.html'
    write_html_page(title=title, body=html, destfile=destfile,
                    style_note=True)
    log.info('Notes index now available at ' + desturl)


def index_no_notes(notes, bugs):
    log.debug('Building the index_no_notes page...')
    all_pkgs = query_db('SELECT s.name, r.status ' +
                        'FROM results AS r JOIN sources AS s ON r.package_id=s.id ' +
                        'WHERE r.status = "unreproducible" OR r.status = "FTBFS"' +
                        'AND s.suite="sid" ' +
                        'ORDER BY r.build_date DESC')
    without_notes = [x for x in all_pkgs if x[0] not in notes]
    html = '\n<p>There are ' + str(len(without_notes)) + ' unreproducible ' \
           + 'packages without notes. These are the packages with failures ' \
           + 'that still need to be investigated.<br />\n'
    html += 'In particular:</p>\n'
    for status in ['unreproducible', 'FTBFS']:
        pkgs = [x[0] for x in without_notes if x[1] == status]
        if not pkgs:
            continue
        html += '<p>\n'
        html += tab + '<img src="/static/' + join_status_icon(status)[1] + '"'
        html += ' alt="' + status + ' icon" />\n'
        html += tab + str(len(pkgs)) + ' ' + status + ' packages:\n'
        html += tab + '<code>\n'
        for pkg in pkgs:
            # FIXME we currently consider notes only for sid/amd64
            url = RB_PKG_URI + '/sid/amd64/' + pkg + '.html'
            html += tab*2 + '<a href="' + url + '" class="package">' + pkg
            html += '</a>' + get_trailing_icon(pkg, bugs) + '\n'
        html += tab + '</code>\n'
        html += '</p>\n'
    html += '<p>Notes are stored in <a href="https://anonscm.debian.org/cgit/reproducible/notes.git" target="_parent">notes.git</a>.</p>'
    html = (tab*2).join(html.splitlines(True))
    title = 'Overview of packages without notes'
    destfile = BASE + '/index_no_notes.html'
    desturl = REPRODUCIBLE_URL + '/index_no_notes.html'
    write_html_page(title=title, body=html, destfile=destfile,
                    style_note=True)
    log.info('Packages without notes index now available at ' + desturl)


if __name__ == '__main__':
    issues_count = {}
    bugs = get_bugs()
    notes = load_notes()
    issues = load_issues()
    iterate_over_notes(notes)
    iterate_over_issues(issues)
    index_issues(issues)
    index_notes(notes, bugs)
    index_no_notes(notes, bugs)
    purge_old_notes(notes)
    gen_packages_html(notes) # regenerate all rb-pkg/ pages