def dict2links(d):
rs = []
for k in sorted(d.keys()):
if k.isupper() or k in ('name', 'authored', 'roles'):
continue
v = d[k]
if k == 'g':
rs.append(\
(makeimg('ico-g', 'Google'),\
'<a href="https://www.google.com/search?q={}">{}</a>'.format(escape(v), v)))
elif k.endswith('.wp'):
lang = k.split('.')[0]
# Using ISO 639-1 language names
ico = makeimg('ico-wp', 'Wikipedia') + makeimg('ico-'+lang, ISONames[lang])
lang = k.split('.')[0]
r = '<a href="https://{}.wikipedia.org/wiki/{}">{}</a>'.format(\
lang, \
escape(v).replace('%20', '_'), \
v)
rs.append((ico, r))
elif k == 'wd':
rs.append(\
(makeimg('ico-wd', 'Wikidata'),\
'<a href="https://www.wikidata.org/wiki/{0}">{0}</a>'.format(v)))
elif k == 'dblp':
# http://dblp.uni-trier.de/pers/hd/m/Major:Elaine
if not isinstance(v, str):
print('Strange DBLP: “{}”'.format(v))
rs.append(\
(makeimg('ico-dblp', 'DBLP'),\
'<a href="http://dblp.uni-trier.de/pers/hd/{}/{}">DBLP: {}</a>'.format(\
v[0].lower(),
escape(v).replace('-', '='),
v)))
elif k == 'www':
if not v.startswith('http'):
w = v
v = 'http://'+v
else:
w = v.replace('http://', '').replace('https://', '')
rs.append(('', '<a href="{0}">{1}</a>'.format(v, w)))
elif k == 'sex':
ico = ''
rs.append(('', 'Gender: ' + v))
elif k == 'roles':
for role in v:
ico = makeimg(role[0].lower(), role[0], 30)
# if os.path.exists(outputdir + '/stuff/' + role[0].lower() + '.png'):
# else:
# ico = ''
if os.path.exists(outputdir + '/' + role[0] + '-' + role[1] + '.html'):
r = '<a href="../{0}-{1}.html">{0}-{1}</a>'.format(role[0], role[1])
else:
r = '{0}-{1}'.format(role[0], role[1])
rs.append((ico, r + ' ' + role[2]))
else:
rs.append(('', '{}: {}'.format(k, v)))
# print(rs)
return '\n'.join(['<h3>{} {}</h3>'.format(r[0], r[1]) for r in rs])
def kv2link(k, v):
if k == 'g':
ico = makeimg('g', 'Google')
r = '<a href="https://www.google.com/search?q={}">{}</a>'.format(
escape(v), v)
elif k.endswith('.wp'):
lang = k.split('.')[0]
# Using ISO 639-1 language names
ico = makeimg('wp', 'Wikipedia') + makeimg(lang, ISONames[lang])
lang = k.split('.')[0]
r = '<a href="https://{}.wikipedia.org/wiki/{}">{}</a>'.format(\
lang, \
escape(v).replace('%20', '_'), \
v)
elif k.endswith('.wb'):
lang = k.split('.')[0]
# Using ISO 639-1 language names
ico = makeimg('wb', 'Wikibooks') + makeimg(lang, ISONames[lang])
lang = k.split('.')[0]
r = '<a href="https://{}.wikibooks.org/wiki/{}">{}</a>'.format(\
lang, \
escape(v).replace('%20', '_'), \
v)
elif k == 'wd':
ico = makeimg('wd', 'Wikidata')
r = '<a href="https://www.wikidata.org/wiki/{0}">{0}</a>'.format(v)
elif k == 'hwiki':
ico = makeimg('h', 'Haskell Wiki')
r = '<a href="https://wiki.haskell.org/{}">{}</a>'.format(escape(v), v)
elif k == 'so':
ico = makeimg('so', 'Stack Overflow')
r = '<a href="http://stackoverflow.com/questions/tagged?tagnames={0}">{0}</a>'.format(
v)
elif k == 'www':
ico = '' #makeimg('www', 'Homepage')
if not v.startswith('http'):
y = v
v = 'http://' + v
else:
y = v.replace('http://', '').replace('https://', '')
r = '<a href="{0}">{1}</a>'.format(v, y)
elif k == 'aka':
ico = ''
r = '<br/>'.join(['a.k.a.: “{}”'.format(z) for z in listify(v)])
else:
ico = ''
r = '?{}?{}?'.format(k, v)
return ico + ' ' + r + '<br/>'
def kv2link(k, v):
if k == 'g':
ico = makeimg('g', 'Google')
r = '<a href="https://www.google.com/search?q={}">{}</a>'.format(escape(v), v)
elif k.endswith('.wp'):
lang = k.split('.')[0]
# Using ISO 639-1 language names
ico = makeimg('wp', 'Wikipedia') + makeimg(lang, ISONames[lang])
lang = k.split('.')[0]
r = '<a href="https://{}.wikipedia.org/wiki/{}">{}</a>'.format(\
lang, \
escape(v).replace('%20', '_'), \
v)
elif k.endswith('.wb'):
lang = k.split('.')[0]
# Using ISO 639-1 language names
ico = makeimg('wb', 'Wikibooks') + makeimg(lang, ISONames[lang])
lang = k.split('.')[0]
r = '<a href="https://{}.wikibooks.org/wiki/{}">{}</a>'.format(\
lang, \
escape(v).replace('%20', '_'), \
v)
elif k == 'wd':
ico = makeimg('wd', 'Wikidata')
r = '<a href="https://www.wikidata.org/wiki/{0}">{0}</a>'.format(v)
elif k == 'hwiki':
ico = makeimg('h', 'Haskell Wiki')
r = '<a href="https://wiki.haskell.org/{}">{}</a>'.format(escape(v), v)
elif k == 'so':
ico = makeimg('so', 'Stack Overflow')
r = '<a href="http://stackoverflow.com/questions/tagged?tagnames={0}">{0}</a>'.format(v)
elif k == 'www':
ico = ''#makeimg('www', 'Homepage')
if not v.startswith('http'):
y = v
v = 'http://'+v
else:
y = v.replace('http://', '').replace('https://', '')
r = '<a href="{0}">{1}</a>'.format(v, y)
elif k == 'aka':
ico = ''
r = '<br/>'.join(['a.k.a.: “{}”'.format(z) for z in listify(v)])
else:
ico = ''
r = '?{}?{}?'.format(k, v)
return ico + ' ' + r + '<br/>'
siblings.update([s for s in x.getBareStems() if s != k and ifApproved(s)])
box = '<code>Used together with:</code><hr/>' + \
'\n<br/>'.join(['<span class="tag"><a href="{0}.html">{0}</a></span> ({1})'.format(\
*sn) for sn in siblings.most_common(5)])
f.write(wordHTML.format(\
stem=k,
inthebox=box,
listname='{} papers'.format(len(lst)),
dl='<dl class="toc">' + '\n'.join(lst).replace('href="', 'href="../') + '</dl>'))
f.close()
print('Word pages:', C.yellow('{}'.format(len(stems))), C.blue('generated'))
# stem index
f = open(outputdir+'/words.html', 'w', encoding='utf-8')
keyz = [k for k in stems.keys() if len(stems[k]) > 100 and ifApproved(k)]
keyz.sort(key=lambda t: -len(t), reverse=True)
lst = ['<li><a href="word/{}.html">{}</a>$ ({})</li>'.format(\
escape(t), t, len(stems[t])) for t in keyz]
ul = '<ul class="tri">' + '\n'.join(lst) + '</ul>'
CX = sum([len(stems[t]) for t in stems.keys()])
f.write(wordlistHTML.format(\
title='All known stems',
listname='{} stems known and {} shown from {} notable words'.format(len(stems), len(keyz), CX),
ul=ul))
f.close()
print('Stem index:', C.blue('created'))
print('{}\nDone with {} venues, {} papers, {} tags.'.format(\
C.purple('='*42),
C.red(len(sleigh.venues)),
C.red(sleigh.numOfPapers()),
C.red(sleigh.numOfTags())))
def dict2links(d):
rs = []
for k in sorted(d.keys()):
if k.isupper() or k in ('name', 'authored', 'roles'):
continue
v = d[k]
if k == 'g':
rs.append(\
(makeimg('ico-g', 'Google'),\
'<a href="https://www.google.com/search?q={}">{}</a>'.format(escape(v), v)))
elif k.endswith('.wp'):
lang = k.split('.')[0]
# Using ISO 639-1 language names
ico = makeimg('ico-wp', 'Wikipedia') + makeimg(
'ico-' + lang, ISONames[lang])
lang = k.split('.')[0]
r = '<a href="https://{}.wikipedia.org/wiki/{}">{}</a>'.format(\
lang, \
escape(v).replace('%20', '_'), \
v)
rs.append((ico, r))
elif k == 'wd':
rs.append(\
(makeimg('ico-wd', 'Wikidata'),\
'<a href="https://www.wikidata.org/wiki/{0}">{0}</a>'.format(v)))
elif k == 'dblp':
# http://dblp.uni-trier.de/pers/hd/m/Major:Elaine
if not isinstance(v, str):
print('Strange DBLP: “{}”'.format(v))
rs.append(\
(makeimg('ico-dblp', 'DBLP'),\
'<a href="http://dblp.uni-trier.de/pers/hd/{}/{}">DBLP: {}</a>'.format(\
v[0].lower(),
escape(v).replace('-', '='),
v)))
elif k == 'www':
if not v.startswith('http'):
w = v
v = 'http://' + v
else:
w = v.replace('http://', '').replace('https://', '')
rs.append(('', '<a href="{0}">{1}</a>'.format(v, w)))
elif k == 'sex':
ico = ''
rs.append(('', 'Gender: ' + v))
elif k == 'roles':
for role in v:
ico = makeimg(role[0].lower(), role[0], 30)
# if os.path.exists(outputdir + '/stuff/' + role[0].lower() + '.png'):
# else:
# ico = ''
if os.path.exists(outputdir + '/' + role[0] + '-' + role[1] +
'.html'):
r = '<a href="../{0}-{1}.html">{0}-{1}</a>'.format(
role[0], role[1])
else:
r = '{0}-{1}'.format(role[0], role[1])
rs.append((ico, r + ' ' + role[2]))
else:
rs.append(('', '{}: {}'.format(k, v)))
# print(rs)
return '\n'.join(['<h3>{} {}</h3>'.format(r[0], r[1]) for r in rs])
}
stemkeys = sorted(stems.keys(),
key=lambda Z: pad(stems[Z]) + pad(len(Z)) + Z,
reverse=True)
adds = '<hr/><code>Talks about:</code><hr/>' \
+ ' \n'.join(['<span class="tag"><a href="../word/{0}.html">{0}</a></span> ({1})'.format(S, stems[S]) \
for S in stemkeys[:10]])
boxlinks += adds
# combine boxlinks
if boxlinks:
boxlinks = '<div class="tbox">' + boxlinks + '</div>'
f.write(personHTML.format(\
title=k,
gender=gender,
boxlinks=boxlinks,
eperson=escape(k),
person=persondef['name'],
# boxlinks=links
namedlists=dls))
f.close()
print('Person pages:', C.yellow('{}'.format(len(ps))), C.blue('generated'))
# person index
# keyz = [k for k in ps.keys() if len(ts[k]) > 2]
# keyz = sorted(keyz, key=lambda t:len(ts[t]), reverse=True)
keyz = ps #sorted(ps.keys())
letters = [chr(x) for x in range(ord('a'), ord('z') + 1)]
indices = {x: [] for x in letters}
for t in keyz:
ws = t.split('_')
i = -1
if ws[i] == 'Jr':
print('{}: {} venues, {} papers\n{}'.format(\
C.purple('BibSLEIGH'),
C.red(len(sleigh.venues)),
C.red(sleigh.numOfPapers()),
C.purple('='*42)))
bundles = {}
for b in glob.glob(ienputdir + '/bundles/*.json'):
purename = b.split('/')[-1][:-5]
bun = json.load(open(b, 'r'))
prevcx = pcx
uberlist = '<h2>{1} papers</h2>{0}'.format(processSortedRel(bun['contents']), pcx-prevcx)
f = open(outputdir + '/bundle/' + purename + '.html', 'w')
f.write(bunHTML.format(\
title=purename+' bundle',
bundle=bun['name'],
ebundle=escape(purename),
dl=uberlist.replace('href="', 'href="../').replace('../mailto', 'mailto')))
f.close()
bundles[purename] = pcx-prevcx
print('Bundle pages:', C.yellow('{}'.format(len(bundles))), C.blue('generated'))
# now for the index
f = open(outputdir+'/bundle/index.html', 'w')
lst = ['<li><a href="{}.html">{}</a> ({})</li>'.format(\
escape(b),
b,
bundles[b]) for b in sorted(bundles.keys())]
ul = '<ul class="tri">' + '\n'.join(lst) + '</ul>'
f.write(bunListHTML.format(\
title='All specified bundles',
listname='{} bundles known with {} papers'.format(len(bundles), sum(bundles.values())),
ul='<ul class="tri">' + '\n'.join(lst) + '</ul>'))
for pk in persondef['authored']:
allstems += bykey[pk].getBareStems()
stems = {stem:allstems.count(stem) for stem in allstems if not ifIgnored(stem)}
stemkeys = sorted(stems.keys(), key=lambda Z: pad(stems[Z])+pad(len(Z))+Z, reverse=True)
adds = '<hr/><code>Talks about:</code><hr/>' \
+ ' \n'.join(['<span class="tag"><a href="../word/{0}.html">{0}</a></span> ({1})'.format(S, stems[S]) \
for S in stemkeys[:10]])
boxlinks += adds
# combine boxlinks
if boxlinks:
boxlinks = '<div class="tbox">' + boxlinks + '</div>'
f.write(personHTML.format(\
title=k,
gender=gender,
boxlinks=boxlinks,
eperson=escape(k),
person=persondef['name'],
# boxlinks=links
namedlists=dls))
f.close()
print('Person pages:', C.yellow('{}'.format(len(ps))), C.blue('generated'))
# person index
# keyz = [k for k in ps.keys() if len(ts[k]) > 2]
# keyz = sorted(keyz, key=lambda t:len(ts[t]), reverse=True)
keyz = ps#sorted(ps.keys())
letters = [chr(x) for x in range(ord('a'), ord('z')+1)]
indices = {x:[] for x in letters}
for t in keyz:
ws = t.split('_')
i = -1
if ws[i] == 'Jr':
if 'g' not in tagdef.keys():
links.append(kv2link('g', tagdef['namefull'] if 'namefull' in tagdef.keys() else key))
links.extend([kv2link(jk, tagdef[jk]) for jk in tagdef.keys()\
if not jk.isupper() \
and not jk.startswith('match') \
and not jk.startswith('name') \
and jk != 'relieves'])
title = tagdef['namefull'] if 'namefull' in tagdef.keys() else tagdef['name']
subt = ('<br/><em>'+tagdef['namelong']+'</em>') if 'namelong' in tagdef.keys() else ''
links = '<strong>{}</strong>{}<hr/>'.format(title, subt) + '\n'.join(sorted(links))
dl = '<dl class="toc">' + '\n'.join(lst) + '</dl>'
# hack to get from tags to papers
dl = dl.replace('href="', 'href="../')
f.write(tagHTML.format(\
title=key+' tag',
etag=escape(key),
tag=key,
above='',
boxlinks=links,
listname='{} papers'.format(len(lst)),
dl=dl))
f.close()
print('Tag pages:', C.yellow('{}'.format(len(ts))), C.blue('generated'))
# tag index
f = open(outputdir+'/tag/index.html', 'w')
keyz = [q for q in ts.keys() if len(ts[q]) > 2]
keyz.sort(key=lambda t: len(ts[t]), reverse=True)
lst = ['<li>#<a href="{}.html">{}</a> ({})</li>'.format(escape(t), t, len(ts[t])) for t in keyz]
ul = '<ul class="tri mul">' + '\n'.join(lst) + '</ul>'
CX = sum([len(ts[t]) for t in ts.keys()])
f.write(taglistHTML.format(\
siblings.update([s for s in x.getBareStems() if s != k and ifApproved(s)])
box = '<code>Used together with:</code><hr/>' + \
'\n<br/>'.join(['<span class="tag"><a href="{0}.html">{0}</a></span> ({1})'.format(\
*sn) for sn in siblings.most_common(5)])
f.write(wordHTML.format(\
stem=k,
inthebox=box,
listname='{} papers'.format(len(lst)),
dl='<dl class="toc">' + '\n'.join(lst).replace('href="', 'href="../') + '</dl>'))
f.close()
print('Word pages:', C.yellow('{}'.format(len(stems))), C.blue('generated'))
# stem index
f = open(outputdir+'/words.html', 'w')
keyz = [k for k in stems.keys() if len(stems[k]) > 100 and ifApproved(k)]
keyz.sort(key=lambda t: -len(t), reverse=True)
lst = ['<li><a href="word/{}.html">{}</a>$ ({})</li>'.format(\
escape(t), t, len(stems[t])) for t in keyz]
ul = '<ul class="tri">' + '\n'.join(lst) + '</ul>'
CX = sum([len(stems[t]) for t in stems.keys()])
f.write(wordlistHTML.format(\
title='All known stems',
listname='{} stems known and {} shown from {} notable words'.format(len(stems), len(keyz), CX),
ul=ul))
f.close()
print('Stem index:', C.blue('created'))
print('{}\nDone with {} venues, {} papers, {} tags.'.format(\
C.purple('='*42),
C.red(len(sleigh.venues)),
C.red(sleigh.numOfPapers()),
C.red(sleigh.numOfTags())))
if not jk.isupper() \
and not jk.startswith('match') \
and not jk.startswith('name') \
and jk != 'relieves'])
title = tagdef['namefull'] if 'namefull' in tagdef.keys(
) else tagdef['name']
subt = ('<br/><em>' + tagdef['namelong'] +
'</em>') if 'namelong' in tagdef.keys() else ''
links = '<strong>{}</strong>{}<hr/>'.format(title, subt) + '\n'.join(
sorted(links))
dl = '<dl class="toc">' + '\n'.join(lst) + '</dl>'
# hack to get from tags to papers
dl = dl.replace('href="', 'href="../')
f.write(tagHTML.format(\
title=key+' tag',
etag=escape(key),
tag=key,
above='',
boxlinks=links,
listname='{} papers'.format(len(lst)),
dl=dl))
f.close()
print('Tag pages:', C.yellow('{}'.format(len(ts))), C.blue('generated'))
# tag index
f = open(outputdir + '/tag/index.html', 'w', encoding='utf-8')
keyz = [q for q in ts.keys() if len(ts[q]) > 2]
keyz.sort(key=lambda t: len(ts[t]), reverse=True)
lst = [
'<li>#<a href="{}.html">{}</a> ({})</li>'.format(
escape(t), t, len(ts[t])) for t in keyz
]