def optimize(encoder):
m, ids = index.load()
n_of_buckets = max(len(m) / 100 + 1, len(m))
res = [bytearray() for i in xrange(n_of_buckets)]
with open('back_index.bin', 'wb') as fout:
ptr = 0
for key in sorted(m.keys()):
values = map(lambda x: struct.unpack('I', x)[0],
[x for x in chunks(m[key], 4)])
l = encoder.compress(values, fout)
#res[key] = (ptr, l)
res[key % n_of_buckets].extend(struct.pack('i', key))
res[key % n_of_buckets].extend(struct.pack('i', ptr))
res[key % n_of_buckets].extend(struct.pack('i', l))
ptr += l
# check compression/decompression function
# with open('back_index.bin', 'rb') as f:
# for key in m:
# rr = simple9.decompress(f, res[key][0], res[key][1])
# if not (set(sorted(m[key])) == rr):
# print('ERROR')
# print(sorted(m[key]))
# print(rr)
# print(res[key])
# raise Exception()
dct = open('dict.bin', 'wb')
dct_head = open('dict_head.bin', 'wb')
it = 0
dct_head.write(struct.pack('I', n_of_buckets))
for i in xrange(n_of_buckets):
dct_head.write(struct.pack('I', it))
dct.write(res[i])
it += len(res[i])
dct_head.write(struct.pack('I', it))
dct_head.close()
dct.close()
def sync_index(from_file=None):
if from_file==None:
from_file = download_index()
index_file = open(from_file, 'r', encoding="Latin-1")
index_data = index.load(index_file)
changed_or_new_sources, deleted_sources = compare_index(index_data)
for s in changed_or_new_sources:
sync_source(s)
# index is saved in sync_sources;
# no need to explicitly save here
# delete removed sources
# TODO backup also?
if len(deleted_sources) > 0:
bulkOp = db.sources.initialize_unordered_bulk_op()
for s in deleted_sources:
bulkOp.find({"index.code": deleted_source["code"]}).remove()
#bulkOp.find({"_id": deleted_source["_id"]}).remove()
bulk_result = bulkOp.execute()
print(bulk_result)
import index
from random import randrange as rnd
index.load()
for n in range(6):
stars = sorted(index.pictures(), key=lambda p:p.rating, reverse=True)[:5+n*2]
query = []
print 'Checkpoints:'
for i in range(3+n):
p = stars[rnd(len(stars))]
query.append(p)
stars.remove(p)
print '{}. {}'.format(i+1, p.name)
path = index.chain(query=query)
print '\nPath:'
print ' > '.join([p.name for p in path])
reference = [p for p in query if p in path]
index.export_html(reference+[None]+path, 'path{}.html'.format(n))
# handlers implemented by browser
f = handlers.get(event.keycode)
if f:
f(browser, event.keycode)
if browser.redraw:
browser.update(event.keycode)
# print time(), 'leave keyhandler'
#if len(browser.img.relates.keys()) > 0:
#browser.img = browser.img.relates.keys()[0]
#print browser.img.location
# Ok Go
index.load(recover=True)
# create tkinter window
root = tk.Tk()
root.title('tumblr img browser')
# make the root window the size of the image
root.geometry("%dx%d+%d+%d" % (1024, 740, 0, 0))
root.bind("<Key>", key)
# instantiate browser class
browser = Browser(root)
# screen size:
w = root.winfo_screenwidth()
h = root.winfo_screenheight()
print 'screen size {}x{}'.format(w,h)
# start the event loop
import index
import source
import os
import urllib
indexfile = open("samples/index/Michael Dyck's Contradance Index_ Sources.html", encoding="Latin-1")
index_baseurl = "http://www.ibiblio.org/contradance/index/"
indexdata = index.load(indexfile)
set_to_download = set()
for row in indexdata:
code_url = urllib.request.urljoin(index_baseurl, row['code_link'], allow_fragments=False)
first_entered = row['date first entered']
last_revised = row['date last revised']
set_to_download.add(code_url)
for url in set_to_download:
filename = os.path.basename(urllib.request.urlparse(url).path)
urllib.request.urlretrieve(url, "samples/source/"+filename)
# -*- coding: utf-8 -*-
import index as ix
ix.load()
imgs=sorted(ix.picture.pictures(), key=lambda p:p.rating)
blogs=sorted(ix.tumblr.blogs(), key=lambda t:t.avg_img_rating())
print 'distributing blog scores...'
scores=ix.tumblr.dist_scores()
print 'sorting blogs by score'
hi=sorted(scores.items(), key=lambda t:t[1])
stars = {}
for p in imgs[-40:]:
t = p.origin
if t:
stars[t] = stars.get(t,0)+p.rating
print ' '.join(['name','stars','imgs','local/blog',
'links','in/out']),
print 'avg* - SCORE'
print '_'*75
for t,s in sorted(stars.items(),key=lambda x:x[1]):
print u'{} - {}* {}/{}imgs ⇶{}/{}⇶'.format(
t.name,s,len(t.proper_imgs),len(t.images),
len(t.linked),len(t.links)),
print '{:.2f}* - score {:.2f}'.format(t.avg_img_rating(),
scores.get(t))
print 'ok'
def __init__(self):
(self.index,self.graph) = index.load( conf.index_filename , conf.graph_filename )
self.revindex = {}
for filename, i in self.index.items():
self.revindex[i] = filename
print "Done loading"
#!/usr/bin/python import index import config as conf (index,g) = index.load( conf.index_filename , conf.graph_filename ) print "Done loading:" , len(index) , len(g.export())
