def print_venue(entry):
result = ''
if entry.end > time.localtime():
result += 'I shall attend '
else:
result += 'I attended '
result += 'the '
if 'url' in entry:
if 'abbreviation' in entry:
result += entry.text + ' (<a href="' + entry.url + '">' + entry.abbreviation + '</a>)'
else:
result += '<a href="' + entry.url + '">' + entry.text + '</a>'
else:
result += entry.text
if 'abbreviation' in entry:
result += ' (' + entry.abbreviation + ')'
result += ' in ' + placelink(entry.venue)
result += ' (' + timeperiod(entry.begin, entry.end) + ')'
if 'talkid' in entry:
# read data XML file
xml = XML2Dict()
data = xml.fromstring(open('../xml/presentations.xml', 'r').read())
# transform date types
for entry2 in data.presentations.conferences.talk:
entry2.date = time.strptime(entry2.date, '%d %b %Y')
for entry2 in data.presentations.workshops.talk:
entry2.date = time.strptime(entry2.date, '%d %b %Y')
# look for talk with given id
for entry2 in data.presentations.conferences.talk:
if entry2.id == entry.talkid:
t = entry2.title
d = entry2.date
for entry2 in data.presentations.workshops.talk:
if entry2.id == entry.talkid:
t = entry2.title
d = entry2.date
result += ' and '
if entry.end > time.localtime():
result += 'give '
else:
result += 'gave '
result += 'a talk on “<a href="presentations.html#' + entry.talkid + '">' + t + '</a>.”'
# only print presentation date if venue is longer than one day
if entry.begin != entry.end:
result += ' (' + timeperiod(d, d) + ')'
result += '.'
return result
def print_pc(entry):
result = 'I was nominated as '
if 'role' in entry:
result += entry.role
else:
result += 'member'
result += ' of the program committee of the '
if 'kind' in entry:
result += entry.kind + ' '
result += '“'
if 'abbreviation' in entry:
result += entry.title
if 'url' in entry:
result += ' (<a href="' + entry.url + '">' + entry.abbreviation.replace(" ", " ") + '</a>)'
else:
result += ' (' + entry.abbreviation.replace(" ", " ") + ')'
else:
if 'url' in entry:
result += '<a href="' + entry.url + '">' + entry.title + '</a>'
else:
result += entry.title
result += '”'
result += ' (' + timeperiod(entry.begin, entry.end) + ').'
return result
def print_visit(entry):
result = ''
if entry.end > time.localtime():
result += 'I shall visit '
else:
result += 'I visited '
result += entry.text
result += ' (' + timeperiod(entry.begin, entry.end) + ').'
return result
def print_free(entry):
result = ''
if 'url' in entry:
result += '<a href="' + entry.url + '">'
result += entry.text
if 'url' in entry:
result += '</a>'
result += ' (' + timeperiod(entry.begin, entry.end) + ').'
return result
def download_stats():
pool = multiprocessing.Pool(config.WIKIMEDIA_PARALLEL_DOWNLOADS)
dump_files = [
wikimedia_stats_dump_path(day.year, day.month, day.day, hour) for day
in timeperiod(config.STATS_PERIOD_START, config.STATS_PERIOD_END)
for hour in range(24)
]
for i, msg in enumerate(pool.imap(apply_download, dump_files)):
print('({}/{})'.format(i + 1, len(dump_files)), msg)
pool.close()
pool.join()
def tools():
# add header template
print("Generating tools.html...")
output = open('../html/tools.html', 'r').read()
# read data XML file
xml = XML2Dict()
data = xml.fromstring(open('../xml/tools.xml', 'r').read())
# fetch papers
paperdata = generate_publications.init()
first = True
for entry in data.tooling.tools.tool:
release = time.strptime(entry.release, '%d %b %Y')
if first:
output += '<h2 class="first">' + entry.name + '</h2>'
first = False
else:
output += '<h2>' + entry.name + '</h2>'
output += '<ul class="talks">\n'
output += '<li>' + entry.description.replace(entry.name, '<strong>' + entry.name + '</strong>') + '</li>\n'
if 'paper' in entry:
output += generate_publications.formatentry(generate_publications.entrybyname(entry.paper, paperdata)) + '\n'
if 'codevelopers' in entry:
if entry.codevelopers.find('and') != -1:
output += '<li>co-developers: ' + entry.codevelopers + '</li>\n'
else:
output += '<li>co-developer: ' + entry.codevelopers + '</li>\n'
output += '<li>development status: ' + entry.status + '</li>\n'
output += '<li>latest release: ' + timeperiod(release, release) + '</li>\n'
output += '</ul>\n'
# footer
output += '</div></div>'
output += footer()
output += '</body></html>'
print("Writing tools.html...")
f = open('../../tools.html', 'w')
f.write(output.replace(" & ", " & ").replace(" - ", " — "))
f.close()
def print_paper_accepted(entry, paperdata):
paper = generate_publications.formatentry(generate_publications.entrybyname(entry.paper, paperdata))
foo = generate_publications.entrybyname(entry.paper, paperdata)
if 'inproceedings' in foo:
title = foo['inproceedings']['title']['value']
venue = 'for the ' + foo['inproceedings']['booktitle']['value']
if 'article' in foo:
title = foo['article']['title']['value']
venue = 'for ' + foo['article']['journal']['value']
result = 'The paper “<a href="publications.html#' + foo.id + '">' + title + '</a>”'
result += ' has been accepted ' + venue + '.'
result += ' (' + timeperiod(entry.begin, entry.end) + ').'
return result
def print_lecture(entry):
result = ''
if entry.end > time.localtime():
result += 'I shall give a talk '
else:
result += 'I gave a talk '
if 'talkid' in entry:
result += 'on “<a href="presentations.html#' + entry.talkid + '">' + entry.title + '</a>” at the '
else:
result += 'on “' + entry.title + '” at the '
if 'url' in entry:
result += '<a href="' + entry.url + '">' + entry.text + '</a>'
else:
result += entry.text
result += ' in ' + placelink(entry.venue)
result += ' (' + timeperiod(entry.begin, entry.end) + ')'
return result
def load_stats():
files = [
os.path.join(
config.STATS_DUMP_DIR,
wikimedia_stats_dump_path(day.year, day.month, day.day, hour),
)
for day in timeperiod(
config.STATS_PERIOD_START, config.STATS_PERIOD_END
)
for hour in range(24)
]
stats = {site: defaultdict(int) for site in config.STATS_SITES}
# Keep one free CPU core to help the main process keeping up with the
# collection step.
#
# NOTE: If this becomes a real issue a fine way to fix this would be to
# distribute the collection step into the loading tasks by using a
# global lock on the computed structure.
pool = multiprocessing.Pool(max(1, multiprocessing.cpu_count() - 1))
for i_file, file_stats in enumerate(pool.imap(load_file, files)):
print(
"({}/{}) {}: updating {} items".format(
i_file + 1,
len(files),
files[i_file],
sum(len(lang) for lang in file_stats.values()),
)
)
for lang, pages in file_stats.items():
for page, views in pages.items():
stats[lang][page] += views
pool.close()
pool.join()
return stats
def presentations():
# add header template
print("Generating presentations.html...")
output = open('../html/presentations.html', 'r').read()
# read data XML file
xml = XML2Dict()
data = xml.fromstring(open('../xml/presentations.xml', 'r').read())
#########################
# part 1: Invited Talks #
#########################
# transform date types
for entry in data.presentations.invited.talk:
entry.date = time.strptime(entry.date, '%d %b %Y')
# sort by begin date
data.presentations.invited.talk = sorted(data.presentations.invited.talk, key=lambda k: k.date, reverse=True)
output += '<h2 class="first">Invited Presentations</h2>'
output += '<ul class="talks">\n'
for entry in data.presentations.invited.talk:
output += '<li id="' + entry.id + '">'
if 'slideshare' in entry:
output += '<a href="' + entry.slideshare + '" title="slides of the talk at Slideshare"></a>'
if 'vimeo' in entry:
output += '<a href="' + entry.vimeo + '" title="video of the talk at Vimeo"></a>'
output += '<strong>' + entry.title + '</strong><br/>'
output += entry.detail + '<br/>'
if entry.date > time.localtime():
output += 'to be held on '
output += timeperiod(entry.date, entry.date) + ' in ' + placelink(entry.venue)
output += '</li>\n'
# output for Slideshare.net
stdoutput = '\nInvited presentation given by Niels Lohmann on ' + timeperiod(entry.date, entry.date)
stdoutput += ' in ' + entry.venue + ' as ' + entry.detail
if stdoutput[-1] != '.':
stdoutput += '.\n'
sys.stderr.write(stdoutput)
output += '</ul>\n'
############################
# part 2: Conference Talks #
############################
# transform date types
for entry in data.presentations.conferences.talk:
entry.date = time.strptime(entry.date, '%d %b %Y')
# sort by begin date
data.presentations.conferences.talk = sorted(data.presentations.conferences.talk, key=lambda k: k.date, reverse=True)
output += '<h2>Conference Presentations</h2>'
output += '<ul class="talks">\n'
for entry in data.presentations.conferences.talk:
output += '<li id="' + entry.id + '">'
if 'slideshare' in entry:
output += '<a href="' + entry.slideshare + '" title="slides of the talk at Slideshare"></a>'
if 'vimeo' in entry:
output += '<a href="' + entry.vimeo + '" title="video of the talk at Vimeo"></a>'
output += '<strong>' + entry.title + '</strong><br/>'
if 'abbreviation' in entry:
output += '<em>' + entry.conference + ' (<a href="' + entry.url + '">' + entry.abbreviation.replace(" ", " ") + '</a>)</em><br/>'
else:
output += '<em><a href="' + entry.url + '">' + entry.conference + ' </a></em><br/>'
if entry.date > time.localtime():
output += 'to be held on '
output += timeperiod(entry.date, entry.date) + ' in ' + placelink(entry.venue)
output += '</li>\n'
# output for Slideshare.net
stdoutput = '\nConference presentation given by Niels Lohmann on ' + timeperiod(entry.date, entry.date)
stdoutput += ' in ' + entry.venue + ' at the ' + entry.conference
if 'abbreviation' in entry:
stdoutput += ' (' + entry.abbreviation + ')'
stdoutput += '.\n'
sys.stderr.write(stdoutput)
output += '</ul>\n'
##########################
# part 3: Workshop Talks #
##########################
# transform date types
for entry in data.presentations.workshops.talk:
entry.date = time.strptime(entry.date, '%d %b %Y')
# sort by begin date
data.presentations.workshops.talk = sorted(data.presentations.workshops.talk, key=lambda k: k.date, reverse=True)
output += '<h2>Workshop Presentations</h2>'
output += '<ul class="talks">\n'
for entry in data.presentations.workshops.talk:
output += '<li id="' + entry.id + '">'
if 'slideshare' in entry:
output += '<a href="' + entry.slideshare + '" title="slides of the talk at Slideshare"></a>'
if 'vimeo' in entry:
output += '<a href="' + entry.vimeo + '" title="video of the talk at Vimeo"></a>'
output += '<strong>' + entry.title + '</strong><br/>'
if 'abbreviation' in entry:
if 'url' in entry:
output += '<em>' + entry.conference + ' (<a href="' + entry.url + '">' + entry.abbreviation.replace(" ", " ") + '</a>)'
else:
output += '<em>' + entry.conference + ' (' + entry.abbreviation.replace(" ", " ") + ')'
else:
if 'url' in entry:
output += '<em><a href="' + entry.url + '">' + entry.conference + '</a>'
else:
output += '<em>' + entry.conference
if 'colocation' in entry:
if 'courl' in entry:
output += '; part of <a href="' + entry.courl + '">' + entry.colocation.replace(" ", " ") + '</a>'
else:
output += '; part of ' + entry.colocation.replace(" ", " ")
output += '</em><br/>'
if entry.date > time.localtime():
output += 'to be held on '
output += timeperiod(entry.date, entry.date) + ' in ' + placelink(entry.venue)
output += '</li>\n'
# output for Slideshare.net
stdoutput = '\nWorkshop presentation given by Niels Lohmann on ' + timeperiod(entry.date, entry.date)
stdoutput += ' in ' + entry.venue + ' at the ' + entry.conference
if 'abbreviation' in entry:
stdoutput += ' (' + entry.abbreviation + ')'
if 'colocation' in entry:
stdoutput += '; part of ' + entry.colocation
stdoutput += '.\n'
sys.stderr.write(stdoutput)
output += '</ul>\n'
##########################
# part 4: Demonstrations #
##########################
# transform date types
for entry in data.presentations.demonstrations.talk:
entry.date = time.strptime(entry.date, '%d %b %Y')
# sort by begin date
data.presentations.demonstrations.talk = sorted(data.presentations.demonstrations.talk, key=lambda k: k.date, reverse=True)
output += '<h2>Tool Demonstrations</h2>'
output += '<ul class="talks">\n'
for entry in data.presentations.demonstrations.talk:
output += '<li id="' + entry.id + '">'
if 'slideshare' in entry:
output += '<a href="' + entry.slideshare + '" title="slides of the talk at Slideshare"></a>'
if 'vimeo' in entry:
output += '<a href="' + entry.vimeo + '" title="video of the talk at Vimeo"></a>'
output += '<strong>' + entry.title + '</strong><br/>'
if 'abbreviation' in entry:
if 'url' in entry:
output += '<em>' + entry.conference + ' (<a href="' + entry.url + '">' + entry.abbreviation.replace(" ", " ") + '</a>)'
else:
output += '<em>' + entry.conference + ' (' + entry.abbreviation.replace(" ", " ") + ')'
else:
if 'url' in entry:
output += '<em><a href="' + entry.url + '">' + entry.conference + '</a>'
else:
output += '<em>' + entry.conference
if 'colocation' in entry:
if 'courl' in entry:
output += '; part of <a href="' + entry.courl + '">' + entry.colocation.replace(" ", " ") + '</a>'
else:
output += '; part of ' + entry.colocation.replace(" ", " ")
output += '</em><br/>'
output += timeperiod(entry.date, entry.date) + ' in ' + placelink(entry.venue)
output += '</li>\n'
# output for Slideshare.net
stdoutput = '\nTool demonstration given by Niels Lohmann on ' + timeperiod(entry.date, entry.date)
stdoutput += ' in ' + entry.venue + ' at the ' + entry.conference
if 'abbreviation' in entry:
stdoutput += ' (' + entry.abbreviation + ')'
if 'colocation' in entry:
stdoutput += '; part of ' + entry.colocation
stdoutput += '.\n'
sys.stderr.write(stdoutput)
output += '</ul>\n'
#########################
# part 5: Miscellaneous #
#########################
# transform date types
for entry in data.presentations.miscellaneous.talk:
entry.date = time.strptime(entry.date, '%d %b %Y')
# sort by begin date
data.presentations.miscellaneous.talk = sorted(data.presentations.miscellaneous.talk, key=lambda k: k.date, reverse=True)
output += '<h2>Miscellaneous</h2>'
output += '<ul class="talks">\n'
for entry in data.presentations.miscellaneous.talk:
output += '<li id="' + entry.id + '">'
output += '<a href="' + entry.slideshare + '" title="slides of the talk at Slideshare"></a>'
if 'vimeo' in entry:
output += '<a href="' + entry.vimeo + '" title="video of the talk at Vimeo"></a>'
output += '<strong>' + entry.title + '</strong><br/>'
output += entry.detail + '<br/>'
output += timeperiod(entry.date, entry.date) + ' in ' + placelink(entry.venue)
output += '</li>\n'
# output for Slideshare.net
stdoutput = '\nPresentation given by Niels Lohmann on ' + timeperiod(entry.date, entry.date)
stdoutput += ' in ' + entry.venue + '; ' + entry.detail
stdoutput += '.\n'
sys.stderr.write(stdoutput)
output += '</ul>\n'
# footer
output += '</div></div>'
output += footer()
output += '</body></html>'
print("Writing presentations.html...")
f = open('../../presentations.html', 'w')
f.write(output.replace(" & ", " & ").replace(" - ", " — "))
f.close()
def teaching():
# add header template
print("Generating teaching.html...")
output = open('../html/teaching.html', 'r').read()
# read data XML file
xml = XML2Dict()
data = xml.fromstring(open('../xml/teaching.xml', 'r').read())
#################################
# part 1: Supervision of Theses #
#################################
output += '<h2 class="first">Supervision of Theses</h2>'
output += '<ul class="talks">\n'
for entry in data.teaching.supervisions.thesis:
output += '<li>' + entry.author + '. '
output += '<strong>' + entry.title + '</strong><br/>'
output += entry.type + ', ' + entry.institution
if 'date' in entry:
entry.date = time.strptime(entry.date, '%d %b %Y')
output += ', submitted ' + timeperiod(entry.date, entry.date)
else:
output += ', expected ' + entry.expected
output += '</li>\n'
output += '</ul>\n'
####################
# part 2: Lectures #
####################
output += '<h2>Lectures</h2>'
output += '<ul class="talks">\n'
for entry in data.teaching.lectures.lecture:
output += '<li>'
output += '<strong>' + entry.title
if 'byProxy' in entry:
output += ' — by proxy'
output += '</strong><br/>'
if 'detail' in entry:
output += entry.detail + ', '
output += entry.institution + ' (' + entry.term + ')'
output += '</li>\n'
output += '</ul>\n'
####################
# part 3: Seminars #
####################
output += '<h2>Seminars</h2>'
output += '<ul class="talks">\n'
for entry in data.teaching.seminars.seminar:
output += '<li>'
output += '<strong>' + entry.title
if 'byProxy' in entry:
output += ' — by proxy'
output += '</strong><br/>'
if 'detail' in entry:
output += entry.detail + ', '
output += entry.institution + ' (' + entry.term + ')'
output += '</li>\n'
output += '</ul>\n'
#####################
# part 4: Exercises #
#####################
output += '<h2>Exercises</h2>'
output += '<ul class="talks">\n'
for entry in data.teaching.exercises.exercise:
output += '<li>'
# if 'evaluation' in entry:
# output += '<a href="files/' + entry.evaluation + '" class="evaluation"></a>'
output += '<strong>'
if 'page' in entry:
output += '<a href="teaching/' + entry.page + '.html">' + entry.title + '</a>'
else:
output += entry.title
output += '</strong><br/>'
if 'detail' in entry:
output += entry.detail + ', '
output += entry.institution + ' (' + entry.term + ')'
output += '</li>\n'
output += '</ul>\n'
# footer
output += '</div></div>'
output += footer()
output += '</body></html>'
print("Writing teaching.html...")
f = open('../../teaching.html', 'w')
f.write(output.replace(" & ", " & ").replace(" - ", " — "))
f.close()
def academic():
# add header template
print("Generating academic.html...")
output = open('../html/academic.html', 'r').read()
# read data XML file
xml = XML2Dict()
data = xml.fromstring(open('../xml/academic.xml', 'r').read())
output += '<h2 class="first">Steering Committee Membership</h2>\n'
output += '<ul class="talks">\n'
output += '<li><strong><a href="http://zeus-workshop.eu/">ZEUS Workshop Series</a></strong><br />Central European Workshop on Services and their Composition</li>'
output += '</ul>\n'
#####################################
# part 1: Organization of Workshops #
#####################################
# transform date types
for entry in data.scientific.organization.workshop:
entry.begin = time.strptime(entry.begin, '%d %b %Y')
entry.end = time.strptime(entry.end, '%d %b %Y')
# sort by begin date
data.scientific.organization.workshop = sorted(data.scientific.organization.workshop, key=lambda k: k.begin, reverse=True)
# output
output += '<h2>Organization of Workshops</h2>\n'
output += '<ul class="talks">\n'
for entry in data.scientific.organization.workshop:
# title
output += '<li><strong>'
if 'abbreviation' in entry:
output += entry.title
if 'url' in entry:
output += ' (<a href="' + entry.url + '">' + entry.abbreviation.replace(" ", " ") + '</a>)'
else:
output += ' (' + entry.abbreviation.replace(" ", " ") + ')'
else:
if 'url' in entry:
output += '<a href="' + entry.url + '">' + entry.title + '</a>'
else:
output += entry.title
output += '</strong><br/>\n'
# colocation
if 'kind' in entry:
output += entry.kind
if 'colocation' in entry:
output += ', '
if 'courl' in entry:
output += 'part of <a href="' + entry.courl + '">' + entry.colocation + '</a>'
else:
output += 'part of ' + entry.colocation
else:
if 'colocation' in entry:
if 'courl' in entry:
output += 'part of <a href="' + entry.courl + '">' + entry.colocation + '</a>'
else:
output += 'part of ' + entry.colocation
# date
output += '<br/>'
output += timeperiod(entry.begin, entry.end)
# venue
if 'venue' in entry:
output += ' in ' + entry.venue
output += '</li>\n'
output += '</ul>\n'
##########################
# part 2: PC memberships #
##########################
# transform date types
for entry in data.scientific.memberships.pc:
entry.date = time.strptime(entry.date, '%d %b %Y')
entry.begin = time.strptime(entry.begin, '%d %b %Y')
entry.end = time.strptime(entry.end, '%d %b %Y')
# sort by begin date
data.scientific.memberships.pc = sorted(data.scientific.memberships.pc, key=lambda k: k.begin, reverse=True)
# output
output += '<h2>Program Committee Memberships</h2>\n'
output += '<ul class="talks">\n'
for entry in data.scientific.memberships.pc:
# title
output += '<li><strong>'
if 'abbreviation' in entry:
output += entry.title
if 'url' in entry:
output += ' (<a href="' + entry.url + '">' + entry.abbreviation.replace(" ", " ") + '</a>)'
else:
output += ' (' + entry.abbreviation.replace(" ", " ") + ')'
else:
if 'url' in entry:
output += '<a href="' + entry.url + '">' + entry.title + '</a>'
else:
output += entry.title
if 'role' in entry:
output += ' — ' + entry.role
output += '</strong><br/>\n'
# colocation
if 'kind' in entry:
output += entry.kind
if 'colocation' in entry:
output += ', '
if 'courl' in entry:
output += 'part of <a href="' + entry.courl + '">' + entry.colocation + '</a>'
else:
output += 'part of ' + entry.colocation
else:
if 'colocation' in entry:
if 'courl' in entry:
output += 'part of <a href="' + entry.courl + '">' + entry.colocation + '</a>'
else:
output += 'part of ' + entry.colocation
# date
output += '<br/>'
output += timeperiod(entry.begin, entry.end)
# venue
if 'venue' in entry:
output += ' in ' + entry.venue
# call for paper
if 'cfp' in entry and entry.begin > time.localtime():
output += '<br/><a href="' + entry.cfp + '">Call for papers</a>'
output += '</li>\n'
output += '</ul>\n'
###########################
# part 3: Journal Reviews #
###########################
# sort by journal title
data.scientific.journalreviews.journal = sorted(data.scientific.journalreviews.journal, key=lambda k: k.title)
# output
output += '<h2>Journal Reviewing Activities</h2>\n'
output += '<ul class="talks">\n'
for entry in data.scientific.journalreviews.journal:
# title
output += '<li><strong>'
if 'url' in entry:
output += '<a href="' + entry.url + '">' + entry.title + '</a>'
else:
output += entry.title
output += '</strong></li>\n'
output += '</ul>\n'
# footer
output += '</div></div>'
output += footer()
output += '</body></html>'
print("Writing academic.html...")
f = open('../../academic.html', 'w')
f.write(output.replace(" & ", " & ").replace(" - ", " — "))
f.close()