print('\t', C.red(len(dunno)), 'people with too much info on')
# should we build it?
maken2f = not os.path.exists(n2f_name)
if maken2f:
name2file = {}
for k in peoplekeys:
p = people[k]
if maken2f:
name2file[k] = 'person/' + p['FILE'].split('/')[-1].replace('.json', '.html')
if p['FILE']:
if os.path.exists(p['FILE']):
cur = parseJSON(p['FILE'])
if cur == p:
cx[0] += 1
if verbose:
print('[', C.green('FIXD'), ']', p['name'])
continue
print('[', C.yellow('FIXD'), ']', p['name'])
cx[2] += 1
f = open(p['FILE'], 'w')
del p['FILE']
f.write(jsonify(p))
f.close()
else:
print('How can that be?')
# caching to be used later (in other scripts mostly)
if maken2f:
f = open(n2f_name, 'w', encoding='utf8')
f.write(json.dumps(name2file, sort_keys=True, separators=(',\n\t', ': '), ensure_ascii=False))
f.close()
cx[1] = len(dunno)
CONFZ = {\
'FOSE': 'FoSE',
'MODELS': 'MoDELS'\
}
BLANK = ' '
lines = []
cur = ''
for fn in sys.argv[1:-1]:
if cur != fn.split('-')[0]:
if cur != '':
print()
name = fn.split('-')[0].upper()
if name in CONFZ:
name = CONFZ[name]
print('[{}]'.format(C.green(name)), end=': ')
cur = fn.split('-')[0]
print("'{}".format(fn.split('-')[-1][-6:-4]), end=' ')
f = open(fn, 'r', encoding='utf-8')
lines += [(fn, line[:10], line[10:].strip()) for line in f.readlines()\
if line.strip() \
and line[:10] != ' ' \
and not line.startswith('##########')]
f.close()
print()
succ = fail = 0
males = set(
line.strip()
for line in open('../naming/male.txt', 'r', encoding='utf-8').readlines())
femes = set(line.strip() for line in open(
else:
return 0
def checkreport(fn, o):
statuses = (C.blue('PASS'), C.red('FAIL'), C.yellow('FIXD'))
r = checkon(fn, o)
# non-verbose mode by default
if verbose or r != 0:
print('[ {} ] {}'.format(statuses[r], fn))
return r
if __name__ == "__main__":
verbose = sys.argv[-1] == '-v'
print('{}: {} venues, {} papers\n{}'.format(\
C.purple('BibSLEIGH'),
C.green(len(sleigh.venues)),
C.green(sleigh.numOfPapers()),
C.purple('='*42)))
aka = parseJSON(ienputdir + '/aliases.json')
CX = sum([len(aka[a]) for a in aka])
# self-adaptation heuristic:
# if a manual rule does the same as the other heuristic, it’s dumb
for a in sorted(aka.keys()):
if len(aka[a]) == 1 and aka[a][0] in (nodiaLatin(a), simpleLatin(a)):
print('[ {} ]'.format(C.blue('DUMB')), simpleLatin(a), 'aliasing was unnecessary manual work')
elif len(aka[a]) == 2 and (aka[a] == [nodiaLatin(a), simpleLatin(a)] \
or aka[a] == [simpleLatin(a), nodiaLatin(a)]):
print('[ {} ]'.format(C.blue('DUMB')), simpleLatin(a), 'aliasing was a lot of unnecessary manual work')
elif nodiaLatin(a) in aka[a] or simpleLatin(a) in aka[a]:
print('[ {} ]'.format(C.blue('DUMB')), simpleLatin(a), 'aliasing contains some unnecessary manual work')
# auto-aliasing heuristic:
report(
'{}: “{}” == “{}”?'.format(surname, variants[0], variants[1]),
2)
# print
pvariants = ['“{}”'.format(v) for v in variants]
report('{}: {}'.format(surname, ' vs '.join(pvariants)), 0)
# write back if changed
for k in people.keys():
p = people[k]
if p['FILE']:
if os.path.exists(p['FILE']):
cur = parseJSON(p['FILE'])
if cur == p:
cx[0] += 1
if verbose:
print('[', C.green('FIXD'), ']', p['name'])
continue
print('[', C.yellow('FIXD'), ']', p['name'])
cx[2] += 1
f = open(p['FILE'], 'w', encoding='utf-8')
del p['FILE']
f.write(jsonify(p))
f.close()
else:
print('How can that be?')
print('{} people checked, {} ok, {} fixed, {} failed'.format(\
C.bold(cx[0] + cx[1] + cx[2]),
C.blue(cx[0]),
C.yellow(cx[2]),
C.red(cx[1])))