blob: 8b08f7ef0f982173774d1d59abdfb8da28ebb9b5 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
|
import struct
import cPickle
class Batch(object):
"""
Used to store multiple RDD entries as a single Java object.
This relieves us from having to explicitly track whether an RDD
is stored as batches of objects and avoids problems when processing
the union() of batched and unbatched RDDs (e.g. the union() of textFile()
with another RDD).
"""
def __init__(self, items):
self.items = items
def batched(iterator, batchSize):
items = []
count = 0
for item in iterator:
items.append(item)
count += 1
if count == batchSize:
yield Batch(items)
items = []
count = 0
if items:
yield Batch(items)
def dump_pickle(obj):
return cPickle.dumps(obj, 2)
load_pickle = cPickle.loads
def read_long(stream):
length = stream.read(8)
if length == "":
raise EOFError
return struct.unpack("!q", length)[0]
def read_int(stream):
length = stream.read(4)
if length == "":
raise EOFError
return struct.unpack("!i", length)[0]
def write_with_length(obj, stream):
stream.write(struct.pack("!i", len(obj)))
stream.write(obj)
def read_with_length(stream):
length = read_int(stream)
obj = stream.read(length)
if obj == "":
raise EOFError
return obj
def read_from_pickle_file(stream):
try:
while True:
obj = load_pickle(read_with_length(stream))
if type(obj) == Batch: # We don't care about inheritance
for item in obj.items:
yield item
else:
yield obj
except EOFError:
return
|