def report(one, two):
print('[ {} ] {}'.format(one, two))
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:
report(statuses[r], fn)
return r
if __name__ == "__main__":
if len(sys.argv) > 1:
verbose = sys.argv[1] == '-v'
print('{}: {} venues, {} papers\n{}'.format(\
C.purple('BibSLEIGH'),
C.red(len(sleigh.venues)),
C.red(sleigh.numOfPapers()),
C.purple('='*42)))
cx = {0: 0, 1: 0, 2: 0}
for v in sleigh.venues:
for c in v.getConfs():
cx[checkreport(c.filename, c)] += 1
for p in c.papers:
cx[checkreport(p.filename, p)] += 1
print('{} files 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])))
def two(n):
if n < 10:
return '0{}'.format(n)
else:
return '{}'.format(n)
if __name__ == "__main__":
verbose = sys.argv[-1] == '-v'
peoplez = glob.glob(ienputdir + '/people/*.json')
print('{}: {} venues, {} papers by {} people\n{}'.format(\
C.purple('BibSLEIGH'),
C.red(len(sleigh.venues)),
C.red(sleigh.numOfPapers()),
C.red(len(peoplez)),
C.purple('='*42)))
cx = {0: 0, 1: 0, 2: 0}
# stem ALL the papers!
for v in sleigh.venues:
for c in v.getConfs():
for p in c.papers:
cx[checkreport(p.filename, p, None)] += 1
for b in v.getBrands():
cx[checkreport(b.filename, None, b)] += 1
# write all stems
listOfStems = sorted(filter(ifApproved, ALLSTEMS),
key=lambda w: two(len(w)) + w)
f = open(ienputdir + '/stems.json', 'w', encoding='utf-8')
f.write('[\n\t"' + '",\n\t"'.join(listOfStems) + '"\n]')
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:
# for each author with diacritics, its non-diacritic twin is considered harmful