Merge branch '21223-arv-mount-nofile' refs #21223

[arvados.git] / sdk / python / arvados / stream.py

diff --git a/sdk/python/arvados/stream.py b/sdk/python/arvados/stream.py
index 042ed47e40edb495cf1a91073ea75cc4d08b5a01..37cd5d7db89f626c24560e0e965408d7de1191aa 100644 (file)
--- a/sdk/python/arvados/stream.py
+++ b/sdk/python/arvados/stream.py
@@ -1,5 +1,11 @@
+# Copyright (C) The Arvados Authors. All rights reserved.
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from __future__ import print_function
 from __future__ import absolute_import
+from future.utils import listvalues
+from builtins import object
 import collections
 import hashlib
 import os
@@ -11,14 +17,16 @@ import copy
 from ._ranges import locators_and_ranges, Range
 from .arvfile import StreamFileReader
 from arvados.retry import retry_method
-from .keep import *
+from arvados.keep import *
 from . import config
 from . import errors
+from . import util
 from ._normalize_stream import normalize_stream
 
 class StreamReader(object):
+    @util._deprecated('3.0', 'arvados.collection.Collecttion')
     def __init__(self, tokens, keep=None, debug=False, _empty=False,
-                 num_retries=0):
+                 num_retries=10):
         self._stream_name = None
         self._data_locators = []
         self._files = collections.OrderedDict()
@@ -36,15 +44,15 @@ class StreamReader(object):
 
             s = re.match(r'^[0-9a-f]{32}\+(\d+)(\+\S+)*$', tok)
             if s:
-                blocksize = long(s.group(1))
+                blocksize = int(s.group(1))
                 self._data_locators.append(Range(tok, streamoffset, blocksize, 0))
                 streamoffset += blocksize
                 continue
 
             s = re.search(r'^(\d+):(\d+):(\S+)', tok)
             if s:
-                pos = long(s.group(1))
-                size = long(s.group(2))
+                pos = int(s.group(1))
+                size = int(s.group(2))
                 name = s.group(3).replace('\\040', ' ')
                 if name not in self._files:
                     self._files[name] = StreamFileReader(self, [Range(pos, 0, size, 0)], name)
@@ -62,7 +70,7 @@ class StreamReader(object):
         return self._files
 
     def all_files(self):
-        return self._files.values()
+        return listvalues(self._files)
 
     def size(self):
         n = self._data_locators[-1]
@@ -79,13 +87,13 @@ class StreamReader(object):
     def readfrom(self, start, size, num_retries=None):
         """Read up to 'size' bytes from the stream, starting at 'start'"""
         if size == 0:
-            return ''
+            return b''
         if self._keep is None:
             self._keep = KeepClient(num_retries=self.num_retries)
         data = []
         for lr in locators_and_ranges(self._data_locators, start, size):
             data.append(self._keepget(lr.locator, num_retries=num_retries)[lr.segment_offset:lr.segment_offset+lr.segment_size])
-        return ''.join(data)
+        return b''.join(data)
 
     def manifest_text(self, strip=False):
         manifest_text = [self.name().replace(' ', '\\040')]
@@ -97,5 +105,5 @@ class StreamReader(object):
             manifest_text.extend([d.locator for d in self._data_locators])
         manifest_text.extend([' '.join(["{}:{}:{}".format(seg.locator, seg.range_size, f.name.replace(' ', '\\040'))
                                         for seg in f.segments])
-                              for f in self._files.values()])
+                              for f in listvalues(self._files)])
         return ' '.join(manifest_text) + '\n'