Merge pull request #41 from alfpark/v2

1.0.0b1

Author: alfpark

.travis.yml

@@ -2,21 +2,14 @@ language: python
 cache: pip
 python:
   - 2.7
-  - 3.3
   - 3.4
   - 3.5
   - 3.6
 install:
   - travis_retry pip install --upgrade pip
-  - travis_retry pip install --upgrade setuptools wheel coveralls
+  - travis_retry pip install --upgrade setuptools wheel
+  - travis_retry pip install --upgrade coveralls tox-travis
 script:
-  - |
-    if [[ $TRAVIS_PYTHON_VERSION == '2.7' ]] || [[ $TRAVIS_PYTHON_VERSION == '3.3' ]] || [[ $TRAVIS_PYTHON_VERSION == '3.4' ]]; then
-        travis_retry pip install tox
-        tox -e $(echo py$TRAVIS_PYTHON_VERSION | tr -d .)
-    else
-        travis_retry pip install tox-travis
-        tox
-    fi
+  - tox
 after_success:
   - coveralls --rcfile=.coveragerc --verbose

CHANGELOG.md

@@ -2,6 +2,27 @@
 
 ## [Unreleased]
 
+## [1.0.0b1] - 2017-08-28
+### Added
+- Cross-mode synchronous copy support
+- Duplicate detection (different local source paths mapping to the same
+destination) on upload
+
+### Changed
+- Python 3.3 is no longer supported (due to `cryptography` dropping support
+for 3.3).
+- `--strip-components` now defaults to `0`
+- `timeout_sec` YAML property is now named `timeout` and is a complex property
+comprised of `connect` and `read` values expressed in seconds
+- Test coverage improved
+- Dependencies updated to latest
+
+### Fixed
+- Properly merge CLI options with YAML config options. You can now override
+most YAML config settings with CLI options at runtime.
+- Issue with zero-byte uploads
+- Check for max page blob size
+
 ## [1.0.0a5] - 2017-06-09
 ### Added
 - Synchronous copy support with the `synccopy` command. This command supports
@@ -210,7 +231,8 @@ usage documentation carefully when upgrading from 0.12.1.
   `--no-skiponmatch`.
 - 0.8.2: performance regression fixes
 
-[Unreleased]: https://github.com/Azure/blobxfer/compare/1.0.0a5...HEAD
+[Unreleased]: https://github.com/Azure/blobxfer/compare/1.0.0b1...HEAD
+[1.0.0b1]: https://github.com/Azure/blobxfer/compare/1.0.0a5...1.0.0b1
 [1.0.0a5]: https://github.com/Azure/blobxfer/compare/1.0.0a4...1.0.0a5
 [1.0.0a4]: https://github.com/Azure/blobxfer/compare/0.12.1...1.0.0a4
 [0.12.1]: https://github.com/Azure/blobxfer/compare/0.12.0...0.12.1

CODE_OF_CONDUCT.md

@@ -0,0 +1,8 @@
+# Code of Conduct
+
+This project has adopted the
+[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+For more information see the
+[Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
+or contact [<[email protected]>](mailto:[email protected]) with any
+additional questions or comments.

CONTRIBUTING.md

@@ -1,12 +1,4 @@
-Contributing Code
------------------
-
-This project has adopted the
-[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-For more information see the
-[Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
-or contact [[email protected]](mailto:[email protected]) with any
-additional questions or comments.
+# Contributing
 
 If you would like to contribute to this project, please view the
 [Microsoft Contribution guidelines](https://azure.github.io/guidelines/).

README.md

@@ -24,8 +24,8 @@ from Azure Blob and File Storage
     throughput limits
   * `replica` mode allows replication of a file across multiple destinations
     including to multiple storage accounts
-* Synchronous copy with replication support (including block-level copies
-for Block blobs)
+* Synchronous copy with cross-mode replication support (including block-level
+copies for Block blobs)
 * Client-side encryption support
 * Support all Azure Blob types and Azure Files for both upload and download
 * Advanced skip options for rsync-like operations
@@ -39,6 +39,7 @@ for Block blobs)
 * Include and exclude filtering support
 * Rsync-like delete support
 * No clobber support in either direction
+* Automatic content type tagging
 * File logging support
 
 ## Installation
@@ -56,11 +57,6 @@ For recent changes, please refer to the
 [CHANGELOG.md](https://github.com/Azure/blobxfer/blob/master/CHANGELOG.md)
 file.
 
-------------------------------------------------------------------------
-
-This project has adopted the
-[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
-For more information see the
-[Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
-or contact [<[email protected]>](mailto:[email protected]) with any
-additional questions or comments.
+* * *
+Please see this project's [Code of Conduct](CODE_OF_CONDUCT.md) and
+[Contributing](CONTRIBUTING.md) guidelines.

blobxfer/__init__.py

@@ -30,15 +30,12 @@
 azure.storage._constants.USER_AGENT_STRING = 'blobxfer/{} {}'.format(
     __version__, azure.storage._constants.USER_AGENT_STRING)
 
-# monkeypatch SOCKET_TIMEOUT value in Azure Storage SDK
-azure.storage._constants.SOCKET_TIMEOUT = (5, 300)
-
 # set stdin source
-if sys.version_info >= (3, 0):
+if sys.version_info >= (3, 0):  # noqa
     STDIN = sys.stdin.buffer
-else:
+else:  # noqa
     # set stdin to binary mode on Windows
-    if sys.platform == 'win32':  # noqa
+    if sys.platform == 'win32':
         import msvcrt
         import os
         msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY)

blobxfer/models/download.py

@@ -191,7 +191,7 @@ class Descriptor(object):
     _AES_BLOCKSIZE = blobxfer.models.crypto.AES256_BLOCKSIZE_BYTES
 
     def __init__(self, lpath, ase, options, resume_mgr):
-        # type: (Descriptior, pathlib.Path,
+        # type: (Descriptor, pathlib.Path,
         #        blobxfer.models.azure.StorageEntity,
         #        blobxfer.models.options.Download,
         #        blobxfer.operations.resume.DownloadResumeManager) -> None
@@ -321,10 +321,10 @@ def compute_allocated_size(size, is_encrypted):
                     size //
                     blobxfer.models.download.Descriptor._AES_BLOCKSIZE - 1
                 ) * blobxfer.models.download.Descriptor._AES_BLOCKSIZE
+                if allocatesize < 0:
+                    raise RuntimeError('allocatesize is negative')
             else:
                 allocatesize = size
-            if allocatesize < 0:
-                allocatesize = 0
         else:
             allocatesize = 0
         return allocatesize
@@ -364,10 +364,9 @@ def convert_vectored_io_slice_to_final_path_name(local_path, ase):
         :rtype: pathlib.Path
         :return: converted final path
         """
-        name = local_path.name
         name = blobxfer.models.metadata.\
             remove_vectored_io_slice_suffix_from_name(
-                name, ase.vectored_io.slice_id)
+                local_path.name, ase.vectored_io.slice_id)
         _tmp = list(local_path.parts[:-1])
         _tmp.append(name)
         return pathlib.Path(*_tmp)
@@ -460,7 +459,7 @@ def _resume(self):
             return None
         self._allocate_disk_space()
         # check if final path exists
-        if not self.final_path.exists():
+        if not self.final_path.exists():  # noqa
             logger.warning('download path {} does not exist'.format(
                 self.final_path))
             return None
@@ -493,7 +492,7 @@ def _resume(self):
             if rr.md5hexdigest != hexdigest:
                 logger.warning(
                     'MD5 mismatch resume={} computed={} for {}'.format(
-                         rr.md5hexdigest, hexdigest, self.final_path))
+                        rr.md5hexdigest, hexdigest, self.final_path))
                 # reset hasher
                 self.md5 = blobxfer.util.new_md5_hasher()
                 return None
@@ -768,12 +767,12 @@ def _restore_file_attributes(self):
         if self._ase.file_attributes is None:
             return
         # set file uid/gid and mode
-        if blobxfer.util.on_windows():
+        if blobxfer.util.on_windows():  # noqa
             # TODO not implemented yet
             pass
         else:
             self.final_path.chmod(int(self._ase.file_attributes.mode, 8))
-            if os.getuid() == 0:
+            if os.getuid() == 0:  # noqa
                 os.chown(
                     str(self.final_path),
                     self._ase.file_attributes.uid,

blobxfer/models/metadata.py

@@ -164,18 +164,6 @@ def fileattr_from_metadata(md):
         return fileattr
 
 
-def restore_fileattr(path, metadata):
-    # type: (pathlib.Path, dict) -> None
-    """Restore file attributes from metadata
-    :param pathlib.Path path: path to modify
-    :param dict metadata: existing metadata dict
-    """
-    if blobxfer.util.on_windows():
-        logger.warning(
-            'file attributes store/restore on Windows is not supported yet')
-    raise NotImplementedError()
-
-
 def create_vectored_io_next_entry(ase):
     # type: (blobxfer.models.azure.StorageEntity) -> str
     """Create Vectored IO next entry id

blobxfer/models/options.py

@@ -43,6 +43,8 @@
 
 # create logger
 logger = logging.getLogger(__name__)
+# global defines
+_DEFAULT_REQUESTS_TIMEOUT = (3.1, 12.1)
 
 # named tuples
 VectoredIo = collections.namedtuple(
@@ -95,13 +97,56 @@
 SyncCopy = collections.namedtuple(
     'SyncCopy', [
         'delete_extraneous_destination',
+        'dest_mode',
         'mode',
         'overwrite',
         'recursive',
     ]
 )
 
 
+class Timeout(object):
+    """Timeout Options"""
+    def __init__(self, connect, read):
+        """Ctor for Timeout options
+        :param Timeout self: this
+        :param float connect: connect timeout
+        :param float read: read timeout
+        """
+        if connect is None or connect <= 0:
+            self._connect = _DEFAULT_REQUESTS_TIMEOUT[0]
+        else:
+            self._connect = connect
+        if read is None or read <= 0:
+            self._read = _DEFAULT_REQUESTS_TIMEOUT[1]
+        else:
+            self._read = read
+
+    @property
+    def connect(self):
+        """Connect timeout
+        :rtype: float
+        :return: connect timeout
+        """
+        return self._connect
+
+    @property
+    def read(self):
+        """Read timeout
+        :rtype: float
+        :return: read timeout
+        """
+        return self._read
+
+    @property
+    def timeout(self):
+        """Timeout property in requests format
+        :rtype: tuple
+        :return: (connect, read) timeout tuple
+        """
+        return (self._connect, self._read)
+
+
 class Concurrency(object):
     """Concurrency Options"""
     def __init__(
@@ -157,14 +202,14 @@ class General(object):
     """General Options"""
     def __init__(
             self, concurrency, log_file=None, progress_bar=True,
-            resume_file=None, timeout_sec=None, verbose=False):
+            resume_file=None, timeout=None, verbose=False):
         """Ctor for General Options
         :param General self: this
         :param Concurrency concurrency: concurrency options
         :param bool progress_bar: progress bar
         :param str log_file: log file
         :param str resume_file: resume file
-        :param int timeout_sec: timeout in seconds
+        :param Timeout timeout: timeout options
         :param bool verbose: verbose output
         """
         if concurrency is None:
@@ -176,5 +221,5 @@ def __init__(
             self.resume_file = pathlib.Path(resume_file)
         else:
             self.resume_file = None
-        self.timeout_sec = timeout_sec
+        self.timeout = timeout
         self.verbose = verbose

blobxfer/models/resume.py

@@ -156,8 +156,7 @@ def __repr__(self):
                 'next_integrity_chunk={} completed={} md5={}>').format(
                     self.final_path, self.length, self.chunk_size,
                     self.next_integrity_chunk, self.completed,
-                    self.md5hexdigest,
-                )
+                    self.md5hexdigest)
 
 
 class Upload(object):
@@ -295,8 +294,7 @@ def __repr__(self):
                 'md5={}>').format(
                     self.local_path, self.length, self.chunk_size,
                     self.total_chunks, self.completed_chunks, self.completed,
-                    self.md5hexdigest,
-                )
+                    self.md5hexdigest)
 
 
 class SyncCopy(object):
@@ -428,5 +426,4 @@ def __repr__(self):
         return ('SyncCopy<length={} chunk_size={} total_chunks={} '
                 'completed_chunks={} completed={}>').format(
                     self.length, self.chunk_size, self.total_chunks,
-                    self.completed_chunks, self.completed,
-                )
+                    self.completed_chunks, self.completed)