# -*- encoding: utf-8 -*-
import glob
import codecs
from collections import defaultdict
with codecs.open('data/kubhist.txt',encoding='utf-8') as f:
yp = defaultdict(list)
for l in f:
(year,_,papers) = l.strip().split('\t')
yp[int(year)] = [t.split('-')[1] for t in papers.replace('[','').replace(']','').split(', ')]
for f in glob.glob('data/*.txt'):
f = f.split('/')[1]
if f != 'kubhist.txt':
span = f.split('.')[0]
(y1,y2) = span.split('-')
papers = set([t for y in range(int(y1),int(y2)+1) for t in yp[y]])
d = []
with codecs.open('data/' + f, encoding='utf-8') as fi:
for l in fi:
try:
xs = l[:-1].split('\t')
w1 = xs[0]
w2 = xs[1]
fr = xs[2]
year = xs[3].split(' ')[0]
ex = xs[3].split(' ',1)[1].strip()
sids = xs[4:]
except:
print l
d.append(((w1,w2),int(float(fr)),year,ex))
with codecs.open(span+'.html', encoding='utf-8',mode='w') as fi:
fi.write(u"""
Experiment 1: %s
Experiment 1: %s
Tidningar: %s
ord
ord
frekvens
år
exempel
""" % (span, span, ", ".join(papers)))
for ((w1,w2),fr,year,ex) in d:
fi.write(u"""