def main(encoders, printer):
summary = OrderedDict()
for name, encoder in encoders:
summary[name] = 0
for index, count, name, values in get_all():
item = {}
for enc_name, encoder in encoders:
size = encoder.bytes_length(values)
item[enc_name] = size
summary[enc_name] += size
printer.write_item(name, index + 1, count, item)
else:
printer.write_summary(summary)
from sampledata import get_all class Stats: def __init__(self): self.count = 0 self.sum = 0 self.min = None self.max = None value = Stats() length = Stats() all_values = set() for i, count, name, values in get_all(): value.count += 1 all_values.update(set(values)) if value.min is None: value.min = min(values) value.max = max(values) else: value.min = min(value.min, min(values)) value.max = max(value.max, max(values)) if length.min is None: length.min = length.max = len(values) length.min = min(length.min, len(values)) length.max = max(length.max, len(values)) length.count += 1
def demo(values): enc = Encoder(values) sequence, pairs = enc.encode() orig_size = sum(encoded_size(v) for v in values) seq_size = sum(encoded_size(v) for v in sequence) pairs_size = sum(encoded_size(v) for v in pairs) pairs_size += sum(encoded_size(pair[0]) + encoded_size(pair[1]) for pair in pairs.itervalues()) print 'original size: ', orig_size print print 'sequence size: ', seq_size print ' pairs size: ', pairs_size print ' total size: ', seq_size + pairs_size if __name__ == '__main__': def get_diff(values): return [values[0]] + [b - a for a, b in zip(values, values[1:])] for index, count, name, values in get_all(): print "verifying %d/%d..." % (index + 1, count) verify(get_diff(values)) print "ok" print "encoding example" demo(get_diff(sample()))
