def get(self, filename):
#self.response.write(self.request.url)
pass
path = '/gs/%s' % (urllib.quote(filename))
fp = files.BufferedFile(path)
data = fp.read(1000*1024*1024*2)
self.response.content_type= 'application/octet-stream';
#self.response.write(self.response.content_type)
self.response.write(data)
def __iter__(self):
"""Iterate over records in input files.
self._offsets is always correctly updated so that stopping iterations
doesn't skip records and doesn't read the same record twice.
"""
ctx = context.get()
mapper_spec = ctx.mapreduce_spec.mapper
shard_number = ctx.shard_state.shard_number
filenames = mapper_spec.params[self.FILES_PARAM][shard_number]
if len(filenames) != len(self._offsets):
raise Exception("Files list and offsets do not match.")
readers = []
for (i, filename) in enumerate(filenames):
offset = self._offsets[i]
reader = records.RecordsReader(files.BufferedFile(filename))
reader.seek(offset)
readers.append((None, None, i, reader))
current_result = None
while readers:
(key, value, index, reader) = readers[0]
if key is not None:
if current_result and key != current_result[0]:
yield current_result
if not current_result or key != current_result[0]:
current_result = (key, [])
current_result[1].append(value)
try:
self._offsets[index] = reader.tell()
start_time = time.time()
binary_record = reader.read()
if context.get():
operation.counters.Increment(
input_readers.COUNTER_IO_READ_BYTES,
len(binary_record))(context.get())
operation.counters.Increment(
input_readers.COUNTER_IO_READ_MSEC,
int((time.time() - start_time) * 1000))(context.get())
proto = file_service_pb.KeyValue()
proto.ParseFromString(binary_record)
heapq.heapreplace(readers,
(proto.key(), proto.value(), index, reader))
except EOFError:
heapq.heappop(readers)
if current_result:
yield current_result
def __iter__(self):
"""Iterate over records in input files.
self._offsets is always correctly updated so that stopping iterations
doesn't skip records and doesn't read the same record twice.
"""
ctx = context.get()
mapper_spec = ctx.mapreduce_spec.mapper
shard_number = ctx._shard_state.shard_number
filenames = mapper_spec.params[self.FILES_PARAM][shard_number]
if len(filenames) != len(self._offsets):
raise Exception("Files list and offsets do not match.")
# Heap with (Key, Value, Index, reader) pairs.
readers = []
# Initialize heap
for (i, filename) in enumerate(filenames):
offset = self._offsets[i]
reader = records.RecordsReader(files.BufferedFile(filename))
reader.seek(offset)
readers.append((None, None, i, reader))
# Read records from heap and merge values with the same key.
# current_result is yielded and consumed buy _merge_map.
# current_result = (key, value, is_partial)
current_result = None
current_count = 0
current_size = 0
while readers:
(key, value, index, reader) = readers[0]
if key is not None:
current_count += 1
current_size += len(value)
should_yield = False
if current_result:
if key != current_result[0]:
# New key encountered
should_yield = True
elif (self._max_values_count != -1 and
current_count >= self._max_values_count):
# Maximum number of values encountered.
current_result[2] = True
should_yield = True
elif (self._max_values_size != -1 and
current_size >= self._max_values_size):
# Maximum size of values encountered
current_result[2] = True
should_yield = True
if should_yield:
# New key encountered or maximum count hit. Yield current key.
yield current_result
if not current_result or should_yield:
current_result = [key, [], False]
current_count = 0
current_size = 0
current_result[1].append(value)
# Read next key/value from reader.
try:
self._offsets[index] = reader.tell()
start_time = time.time()
binary_record = reader.read()
# update counters
if context.get():
operation.counters.Increment(
input_readers.COUNTER_IO_READ_BYTES,
len(binary_record))(context.get())
operation.counters.Increment(
input_readers.COUNTER_IO_READ_MSEC,
int((time.time() - start_time) * 1000))(context.get())
proto = file_service_pb.KeyValue()
proto.ParseFromString(binary_record)
# Put read data back into heap.
heapq.heapreplace(readers,
(proto.key(), proto.value(), index, reader))
except EOFError:
heapq.heappop(readers)
# Yield leftovers.
if current_result:
yield current_result