5.0 compatibility

Changelog.rst

@@ -3,6 +3,11 @@
 Changelog
 =========
 
+5.0.0 (dev)
+-----------
+
+Version compatible with elasticsearch 5.0
+
 2.3.0 (2016-02-29)
 ------------------
 

README

@@ -28,6 +28,9 @@ Compatibility
 The library is compatible with all Elasticsearch versions since ``0.90.x`` but you
 **have to use a matching major version**:
 
+For **Elasticsearch 5.0** and later, use the major version 5 (``5.x.y``) of the
+library.
+
 For **Elasticsearch 2.0** and later, use the major version 2 (``2.x.y``) of the
 library.
 
@@ -40,6 +43,9 @@ library.
 The recommended way to set your requirements in your `setup.py` or
 `requirements.txt` is::
 
+    # Elasticsearch 5.x
+    elasticsearch>=5.0.0,<6.0.0
+
     # Elasticsearch 2.x
     elasticsearch>=2.0.0,<3.0.0
 
@@ -49,7 +55,7 @@ The recommended way to set your requirements in your `setup.py` or
     # Elasticsearch 0.90.x
     elasticsearch<1.0.0
 
-The development is happening on ``master`` and ``1.x`` branches, respectively.
+The development is happening on ``master`` and ``2.x`` branches respectively.
 
 Installation
 ------------

docs/conf.py

@@ -50,11 +50,11 @@ copyright = u'2013, Honza Král'
 # built documents.
 #
 
-import elasticsearch
+
 # The short X.Y version.
-version = elasticsearch.__versionstr__
+version = '5.0.0'
 # The full version, including alpha/beta/rc tags.
-release = version
+release = '5.0.0-dev'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

elasticsearch/__init__.py

@@ -1,6 +1,6 @@
 from __future__ import absolute_import
 
-VERSION = (2, 3, 0)
+VERSION = (5, 0, 0, 'dev')
 __version__ = VERSION
 __versionstr__ = '.'.join(map(str, VERSION))
 

elasticsearch/client/__init__.py

@@ -6,10 +6,12 @@ from ..transport import Transport
 from ..exceptions import TransportError
 from ..compat import string_types, urlparse
 from .indices import IndicesClient
+from .ingest import IngestClient
 from .cluster import ClusterClient
 from .cat import CatClient
 from .nodes import NodesClient
 from .snapshot import SnapshotClient
+from .tasks import TasksClient
 from .utils import query_params, _make_path, SKIP_IN_PATH
 
 logger = logging.getLogger('elasticsearch')
@@ -64,13 +66,15 @@ class Elasticsearch(object):
     Elasticsearch low-level client. Provides a straightforward mapping from
     Python to ES REST endpoints.
 
-    The instance has attributes ``cat``, ``cluster``, ``indices``, ``nodes``
+    The instance has attributes ``cat``, ``cluster``, ``indices``, ``ingest``,
-    and ``snapshot`` that provide access to instances of
+    ``nodes``, ``snapshot`` and ``tasks`` that provide access to instances of
     :class:`~elasticsearch.client.CatClient`,
     :class:`~elasticsearch.client.ClusterClient`,
     :class:`~elasticsearch.client.IndicesClient`,
-    :class:`~elasticsearch.client.NodesClient` and
+    :class:`~elasticsearch.client.IngestClient`,
-    :class:`~elasticsearch.client.SnapshotClient` respectively. This is the
+    :class:`~elasticsearch.client.NodesClient`,
+    :class:`~elasticsearch.client.SnapshotClient` and
+    :class:`~elasticsearch.client.TasksClient` respectively. This is the
     preferred (and only supported) way to get access to those classes and their
     methods.
 
@@ -170,10 +174,12 @@ class Elasticsearch(object):
         # namespaced clients for compatibility with API names
         # use weakref to make GC's work a little easier
         self.indices = IndicesClient(weakref.proxy(self))
+        self.ingest = IngestClient(weakref.proxy(self))
         self.cluster = ClusterClient(weakref.proxy(self))
         self.cat = CatClient(weakref.proxy(self))
         self.nodes = NodesClient(weakref.proxy(self))
         self.snapshot = SnapshotClient(weakref.proxy(self))
+        self.tasks = TasksClient(weakref.proxy(self))
 
     def __repr__(self):
         try:
@@ -214,7 +220,7 @@ class Elasticsearch(object):
         """
         return self.transport.perform_request('GET', '/', params=params)
 
-    @query_params('consistency', 'parent', 'refresh', 'routing',
+    @query_params('consistency', 'parent', 'pipeline', 'refresh', 'routing',
         'timeout', 'timestamp', 'ttl', 'version', 'version_type')
     def create(self, index, doc_type, body, id=None, params=None):
         """
@@ -242,8 +248,8 @@ class Elasticsearch(object):
         """
         return self.index(index, doc_type, body, id=id, params=params, op_type='create')
 
-    @query_params('consistency', 'op_type', 'parent', 'refresh', 'routing',
+    @query_params('consistency', 'op_type', 'parent', 'pipeline', 'refresh',
-        'timeout', 'timestamp', 'ttl', 'version', 'version_type')
+        'routing', 'timeout', 'timestamp', 'ttl', 'version', 'version_type')
     def index(self, index, doc_type, body, id=None, params=None):
         """
         Adds or updates a typed JSON document in a specific index, making it searchable.
@@ -258,6 +264,7 @@ class Elasticsearch(object):
         :arg op_type: Explicit operation type, default 'index', valid choices
             are: 'index', 'create'
         :arg parent: ID of the parent document
+        :arg pipeline: The pipeline id to preprocess incoming documents with
         :arg refresh: Refresh the index after performing the operation
         :arg routing: Specific routing value
         :arg timeout: Explicit operation timeout
@@ -295,8 +302,8 @@ class Elasticsearch(object):
         for param in (index, doc_type, id):
             if param in SKIP_IN_PATH:
                 raise ValueError("Empty value passed for a required argument.")
-        return self.transport.perform_request('HEAD', _make_path(index, doc_type,
+        return self.transport.perform_request('HEAD', _make_path(index,
-                id), params=params)
+            doc_type, id), params=params)
 
     @query_params('_source', '_source_exclude', '_source_include', 'fields',
         'parent', 'preference', 'realtime', 'refresh', 'routing', 'version',
@@ -402,8 +409,8 @@ class Elasticsearch(object):
         return self.transport.perform_request('GET', _make_path(index,
             doc_type, '_mget'), params=params, body=body)
 
-    @query_params('consistency', 'detect_noop', 'fields', 'lang', 'parent',
+    @query_params('consistency', 'fields', 'lang', 'parent', 'refresh',
-        'refresh', 'retry_on_conflict', 'routing', 'script', 'script_id',
+        'retry_on_conflict', 'routing', 'script', 'script_id',
         'scripted_upsert', 'timeout', 'timestamp', 'ttl', 'version',
         'version_type')
     def update(self, index, doc_type, id, body=None, params=None):
@@ -417,9 +424,6 @@ class Elasticsearch(object):
         :arg body: The request definition using either `script` or partial `doc`
         :arg consistency: Explicit write consistency setting for the operation,
             valid choices are: 'one', 'quorum', 'all'
-        :arg detect_noop: Specifying as true will cause Elasticsearch to check
-            if there are changes and, if there aren't, turn the update request
-            into a noop.
         :arg fields: A comma-separated list of fields to return in the response
         :arg lang: The script language (default: groovy)
         :arg parent: ID of the parent document. Is is only used for routing and
@@ -504,7 +508,7 @@ class Elasticsearch(object):
         :arg scroll: Specify how long a consistent view of the index should be
             maintained for scrolled search
         :arg search_type: Search operation type, valid choices are:
-            'query_then_fetch', 'dfs_query_then_fetch', 'count', 'scan'
+            'query_then_fetch', 'dfs_query_then_fetch'
         :arg size: Number of hits to return (default: 10)
         :arg sort: A comma-separated list of <field>:<direction> pairs
         :arg stats: Specific 'tag' of the request for logging and statistical
@@ -591,7 +595,7 @@ class Elasticsearch(object):
             maintained for scrolled search
         :arg search_type: Search operation type, valid choices are:
             'query_then_fetch', 'query_and_fetch', 'dfs_query_then_fetch',
-            'dfs_query_and_fetch', 'count', 'scan'
+            'dfs_query_and_fetch'
         """
         return self.transport.perform_request('GET', _make_path(index,
             doc_type, '_search', 'template'), params=params, body=body)
@@ -746,7 +750,8 @@ class Elasticsearch(object):
         return self.transport.perform_request('GET', _make_path(index,
             doc_type, '_count'), params=params, body=body)
 
-    @query_params('consistency', 'fields', 'refresh', 'routing', 'timeout')
+    @query_params('consistency', 'fields', 'pipeline', 'refresh', 'routing',
+        'timeout')
     def bulk(self, body, index=None, doc_type=None, params=None):
         """
         Perform many index/delete operations in a single API call.
@@ -763,6 +768,7 @@ class Elasticsearch(object):
             valid choices are: 'one', 'quorum', 'all'
         :arg fields: Default comma-separated list of fields to return in the
             response for updates
+        :arg pipeline: The pipeline id to preprocess incoming documents with
         :arg refresh: Refresh the index after performing the operation
         :arg routing: Specific routing value
         :arg timeout: Explicit operation timeout
@@ -785,7 +791,7 @@ class Elasticsearch(object):
             default
         :arg search_type: Search operation type, valid choices are:
             'query_then_fetch', 'query_and_fetch', 'dfs_query_then_fetch',
-            'dfs_query_and_fetch', 'count', 'scan'
+            'dfs_query_and_fetch'
         """
         if body in SKIP_IN_PATH:
             raise ValueError("Empty value passed for a required argument 'body'.")
@@ -941,9 +947,9 @@ class Elasticsearch(object):
         return self.transport.perform_request('GET', _make_path(index,
             doc_type, id, '_percolate', 'count'), params=params, body=body)
 
-    @query_params('dfs', 'field_statistics', 'fields', 'offsets', 'parent',
+    @query_params('field_statistics', 'fields', 'offsets', 'parent', 'payloads',
-        'payloads', 'positions', 'preference', 'realtime', 'routing',
+        'positions', 'preference', 'realtime', 'routing', 'term_statistics',
-        'term_statistics', 'version', 'version_type')
+        'version', 'version_type')
     def termvectors(self, index, doc_type, id=None, body=None, params=None):
         """
         Returns information and statistics on terms in the fields of a
@@ -959,8 +965,6 @@ class Elasticsearch(object):
             be supplied.
         :arg body: Define parameters and or supply a document to get termvectors
             for. See documentation.
-        :arg dfs: Specifies if distributed frequencies should be returned
-            instead shard frequencies., default False
         :arg field_statistics: Specifies if document count, sum of document
             frequencies and sum of total term frequencies should be returned.,
             default True

elasticsearch/client/cat.py

@@ -311,7 +311,7 @@ class CatClient(NamespacedClient):
         return self.transport.perform_request('GET', '/_cat/repositories',
             params=params)
 
-    @query_params('h', 'help', 'master_timeout', 'v')
+    @query_params('h', 'help', 'ignore_unavailable', 'master_timeout', 'v')
     def snapshots(self, repository=None, params=None):
         """
         `<http://www.elastic.co/guide/en/elasticsearch/reference/current/cat-snapshots.html>`_
@@ -320,6 +320,8 @@ class CatClient(NamespacedClient):
             information
         :arg h: Comma-separated list of column names to display
         :arg help: Return help information, default False
+        :arg ignore_unavailable: Set to true to ignore unavailable snapshots,
+            default False
         :arg master_timeout: Explicit operation timeout for connection to master
             node
         :arg v: Verbose mode. Display column headers, default False

elasticsearch/client/cluster.py

@@ -115,13 +115,16 @@ class ClusterClient(NamespacedClient):
         return self.transport.perform_request('POST', '/_cluster/reroute',
             params=params, body=body)
 
-    @query_params('flat_settings', 'master_timeout', 'timeout')
+    @query_params('flat_settings', 'include_defaults', 'master_timeout',
+        'timeout')
     def get_settings(self, params=None):
         """
         Get cluster settings.
         `<http://www.elastic.co/guide/en/elasticsearch/reference/current/cluster-update-settings.html>`_
 
         :arg flat_settings: Return settings in flat format (default: false)
+        :arg include_defaults: Whether to return all default clusters setting.,
+            default False
         :arg master_timeout: Explicit operation timeout for connection to master
             node
         :arg timeout: Explicit operation timeout

elasticsearch/client/indices.py

@@ -1,8 +1,8 @@
 from .utils import NamespacedClient, query_params, _make_path, SKIP_IN_PATH
 
 class IndicesClient(NamespacedClient):
-    @query_params('analyzer', 'char_filters', 'field', 'filters', 'format',
+    @query_params('analyzer', 'attributes', 'char_filters', 'explain', 'field',
-        'prefer_local', 'text', 'tokenizer')
+        'filters', 'format', 'prefer_local', 'text', 'tokenizer')
     def analyze(self, index=None, body=None, params=None):
         """
         Perform the analysis process on a text and return the tokens breakdown of the text.
@@ -11,8 +11,12 @@ class IndicesClient(NamespacedClient):
         :arg index: The name of the index to scope the operation
         :arg body: The text on which the analysis should be performed
         :arg analyzer: The name of the analyzer to use
+        :arg attributes: A comma-separated list of token attributes to output,
+            this parameter works only with `explain=true`
         :arg char_filters: A comma-separated list of character filters to use
             for the analysis
+        :arg explain: With `true`, outputs more advanced details. (default:
+            false)
         :arg field: Use the analyzer configured for this field (instead of
             passing the analyzer name)
         :arg filters: A comma-separated list of filters to use for the analysis
@@ -513,7 +517,7 @@ class IndicesClient(NamespacedClient):
             _make_path('_template', name), params=params)
 
     @query_params('allow_no_indices', 'expand_wildcards', 'flat_settings',
-        'human', 'ignore_unavailable', 'local')
+        'human', 'ignore_unavailable', 'include_defaults', 'local')
     def get_settings(self, index=None, name=None, params=None):
         """
         Retrieve settings for one or more (or all) indices.
@@ -533,6 +537,8 @@ class IndicesClient(NamespacedClient):
             readable format., default False
         :arg ignore_unavailable: Whether specified concrete indices should be
             ignored when unavailable (missing or closed)
+        :arg include_defaults: Whether to return all default setting for each of
+            the indices., default False
         :arg local: Return local information, do not retrieve the state from
             master node (default: false)
         """
@@ -540,7 +546,7 @@ class IndicesClient(NamespacedClient):
             '_settings', name), params=params)
 
     @query_params('allow_no_indices', 'expand_wildcards', 'flat_settings',
-        'ignore_unavailable', 'master_timeout')
+        'ignore_unavailable', 'master_timeout', 'preserve_existing')
     def put_settings(self, body, index=None, params=None):
         """
         Change specific index level settings in real time.
@@ -559,96 +565,15 @@ class IndicesClient(NamespacedClient):
         :arg ignore_unavailable: Whether specified concrete indices should be
             ignored when unavailable (missing or closed)
         :arg master_timeout: Specify timeout for connection to master
+        :arg preserve_existing: Whether to update existing settings. If set to
+            `true` existing settings on an index remain unchanged, the default
+            is `false`
         """
         if body in SKIP_IN_PATH:
             raise ValueError("Empty value passed for a required argument 'body'.")
         return self.transport.perform_request('PUT', _make_path(index,
             '_settings'), params=params, body=body)
 
-    @query_params('allow_no_indices', 'expand_wildcards', 'ignore_unavailable',
-        'master_timeout', 'request_cache')
-    def put_warmer(self, name, body, index=None, doc_type=None, params=None):
-        """
-        Create an index warmer to run registered search requests to warm up the
-        index before it is available for search.
-        `<http://www.elastic.co/guide/en/elasticsearch/reference/current/indices-warmers.html>`_
-
-        :arg name: The name of the warmer
-        :arg body: The search request definition for the warmer (query, filters,
-            facets, sorting, etc)
-        :arg index: A comma-separated list of index names to register the warmer
-            for; use `_all` or omit to perform the operation on all indices
-        :arg doc_type: A comma-separated list of document types to register the
-            warmer for; leave empty to perform the operation on all types
-        :arg allow_no_indices: Whether to ignore if a wildcard indices
-            expression resolves into no concrete indices in the search request
-            to warm. (This includes `_all` string or when no indices have been
-            specified)
-        :arg expand_wildcards: Whether to expand wildcard expression to concrete
-            indices that are open, closed or both, in the search request to
-            warm., default 'open', valid choices are: 'open', 'closed', 'none',
-            'all'
-        :arg ignore_unavailable: Whether specified concrete indices should be
-            ignored when unavailable (missing or closed) in the search request
-            to warm
-        :arg master_timeout: Specify timeout for connection to master
-        :arg request_cache: Specify whether the request to be warmed should use
-            the request cache, defaults to index level setting
-        """
-        for param in (name, body):
-            if param in SKIP_IN_PATH:
-                raise ValueError("Empty value passed for a required argument.")
-        return self.transport.perform_request('PUT', _make_path(index,
-            doc_type, '_warmer', name), params=params, body=body)
-
-    @query_params('allow_no_indices', 'expand_wildcards', 'ignore_unavailable',
-        'local')
-    def get_warmer(self, index=None, doc_type=None, name=None, params=None):
-        """
-        Retreieve an index warmer.
-        `<http://www.elastic.co/guide/en/elasticsearch/reference/current/indices-warmers.html>`_
-
-        :arg index: A comma-separated list of index names to restrict the
-            operation; use `_all` to perform the operation on all indices
-        :arg doc_type: A comma-separated list of document types to restrict the
-            operation; leave empty to perform the operation on all types
-        :arg name: The name of the warmer (supports wildcards); leave empty to
-            get all warmers
-        :arg allow_no_indices: Whether to ignore if a wildcard indices
-            expression resolves into no concrete indices. (This includes `_all`
-            string or when no indices have been specified)
-        :arg expand_wildcards: Whether to expand wildcard expression to concrete
-            indices that are open, closed or both., default 'open', valid
-            choices are: 'open', 'closed', 'none', 'all'
-        :arg ignore_unavailable: Whether specified concrete indices should be
-            ignored when unavailable (missing or closed)
-        :arg local: Return local information, do not retrieve the state from
-            master node (default: false)
-        """
-        return self.transport.perform_request('GET', _make_path(index,
-            doc_type, '_warmer', name), params=params)
-
-    @query_params('master_timeout')
-    def delete_warmer(self, index, name, params=None):
-        """
-        Delete an index warmer.
-        `<http://www.elastic.co/guide/en/elasticsearch/reference/current/indices-warmers.html>`_
-
-        :arg index: A comma-separated list of index names to delete warmers from
-            (supports wildcards); use `_all` to perform the operation on all
-            indices.
-        :arg name: A comma-separated list of warmer names to delete (supports
-            wildcards); use `_all` to delete all warmers in the specified
-            indices. You must specify a name either in the uri or in the
-            parameters.
-        :arg master_timeout: Specify timeout for connection to master
-        """
-        for param in (index, name):
-            if param in SKIP_IN_PATH:
-                raise ValueError("Empty value passed for a required argument.")
-        return self.transport.perform_request('DELETE', _make_path(index,
-            '_warmer', name), params=params)
-
     @query_params('completion_fields', 'fielddata_fields', 'fields', 'groups',
         'human', 'level', 'types')
     def stats(self, index=None, metric=None, params=None):
@@ -678,7 +603,7 @@ class IndicesClient(NamespacedClient):
             '_stats', metric), params=params)
 
     @query_params('allow_no_indices', 'expand_wildcards', 'human',
-        'ignore_unavailable', 'operation_threading')
+        'ignore_unavailable', 'operation_threading', 'verbose')
     def segments(self, index=None, params=None):
         """
         Provide low level segments information that a Lucene index (shard level) is built with.
@@ -697,41 +622,11 @@ class IndicesClient(NamespacedClient):
         :arg ignore_unavailable: Whether specified concrete indices should be
             ignored when unavailable (missing or closed)
         :arg operation_threading: TODO: ?
+        :arg verbose: Includes detailed memory usage by Lucene., default False
         """
         return self.transport.perform_request('GET', _make_path(index,
             '_segments'), params=params)
 
-    @query_params('allow_no_indices', 'expand_wildcards', 'flush',
-        'ignore_unavailable', 'max_num_segments', 'only_expunge_deletes',
-        'operation_threading', 'wait_for_merge')
-    def optimize(self, index=None, params=None):
-        """
-        Explicitly optimize one or more indices through an API.
-        `<http://www.elastic.co/guide/en/elasticsearch/reference/current/indices-optimize.html>`_
-
-        :arg index: A comma-separated list of index names; use `_all` or empty
-            string to perform the operation on all indices
-        :arg allow_no_indices: Whether to ignore if a wildcard indices
-            expression resolves into no concrete indices. (This includes `_all`
-            string or when no indices have been specified)
-        :arg expand_wildcards: Whether to expand wildcard expression to concrete
-            indices that are open, closed or both., default 'open', valid
-            choices are: 'open', 'closed', 'none', 'all'
-        :arg flush: Specify whether the index should be flushed after performing
-            the operation (default: true)
-        :arg ignore_unavailable: Whether specified concrete indices should be
-            ignored when unavailable (missing or closed)
-        :arg max_num_segments: The number of segments the index should be merged
-            into (default: dynamic)
-        :arg only_expunge_deletes: Specify whether the operation should only
-            expunge deleted documents
-        :arg operation_threading: TODO: ?
-        :arg wait_for_merge: Specify whether the request should block until the
-            merge process is finished (default: true)
-        """
-        return self.transport.perform_request('POST', _make_path(index,
-            '_optimize'), params=params)
-
     @query_params('allow_no_indices', 'analyze_wildcard', 'analyzer',
         'default_operator', 'df', 'expand_wildcards', 'explain',
         'ignore_unavailable', 'lenient', 'lowercase_expanded_terms',

elasticsearch/client/ingest.py

@@ -0,0 +1,63 @@
+from .utils import NamespacedClient, query_params, _make_path, SKIP_IN_PATH
+
+class IngestClient(NamespacedClient):
+    @query_params('master_timeout')
+    def get_pipeline(self, id, params=None):
+        """
+        `<https://www.elastic.co/guide/en/elasticsearch/plugins/current/ingest.html>`_
+
+        :arg id: Comma separated list of pipeline ids. Wildcards supported
+        :arg master_timeout: Explicit operation timeout for connection to master
+            node
+        """
+        if id in SKIP_IN_PATH:
+            raise ValueError("Empty value passed for a required argument 'id'.")
+        return self.transport.perform_request('GET', _make_path('_ingest',
+            'pipeline', id), params=params)
+
+    @query_params('master_timeout', 'timeout')
+    def put_pipeline(self, id, body, params=None):
+        """
+        `<https://www.elastic.co/guide/en/elasticsearch/plugins/current/ingest.html>`_
+
+        :arg id: Pipeline ID
+        :arg body: The ingest definition
+        :arg master_timeout: Explicit operation timeout for connection to master
+            node
+        :arg timeout: Explicit operation timeout
+        """
+        for param in (id, body):
+            if param in SKIP_IN_PATH:
+                raise ValueError("Empty value passed for a required argument.")
+        return self.transport.perform_request('PUT', _make_path('_ingest',
+            'pipeline', id), params=params, body=body)
+
+    @query_params('master_timeout', 'timeout')
+    def delete_pipeline(self, id, params=None):
+        """
+        `<https://www.elastic.co/guide/en/elasticsearch/plugins/current/ingest.html>`_
+
+        :arg id: Pipeline ID
+        :arg master_timeout: Explicit operation timeout for connection to master
+            node
+        :arg timeout: Explicit operation timeout
+        """
+        if id in SKIP_IN_PATH:
+            raise ValueError("Empty value passed for a required argument 'id'.")
+        return self.transport.perform_request('DELETE', _make_path('_ingest',
+            'pipeline', id), params=params)
+
+    @query_params('verbose')
+    def simulate(self, body, id=None, params=None):
+        """
+        `<https://www.elastic.co/guide/en/elasticsearch/plugins/current/ingest.html>`_
+
+        :arg body: The simulate definition
+        :arg id: Pipeline ID
+        :arg verbose: Verbose mode. Display data output for each processor in
+            executed pipeline, default False
+        """
+        if body in SKIP_IN_PATH:
+            raise ValueError("Empty value passed for a required argument 'body'.")
+        return self.transport.perform_request('GET', _make_path('_ingest',
+            'pipeline', id, '_simulate'), params=params, body=body)

elasticsearch/client/tasks.py

@@ -0,0 +1,45 @@
+from .utils import NamespacedClient, query_params, _make_path, SKIP_IN_PATH
+
+class TasksClient(NamespacedClient):
+    @query_params('actions', 'detailed', 'node_id', 'parent_node',
+        'parent_task', 'wait_for_completion')
+    def list(self, task_id=None, params=None):
+        """
+        `<http://www.elastic.co/guide/en/elasticsearch/reference/current/tasks-list.html>`_
+
+        :arg task_id: Return the task with specified id
+        :arg actions: A comma-separated list of actions that should be returned.
+            Leave empty to return all.
+        :arg detailed: Return detailed task information (default: false)
+        :arg node_id: A comma-separated list of node IDs or names to limit the
+            returned information; use `_local` to return information from the
+            node you're connecting to, leave empty to get information from all
+            nodes
+        :arg parent_node: Return tasks with specified parent node.
+        :arg parent_task: Return tasks with specified parent task id. Set to -1
+            to return all.
+        :arg wait_for_completion: Wait for the matching tasks to complete
+            (default: false)
+        """
+        return self.transport.perform_request('GET', _make_path('_tasks',
+            task_id), params=params)
+
+    @query_params('actions', 'node_id', 'parent_node', 'parent_task')
+    def cancel(self, task_id=None, params=None):
+        """
+        `<http://www.elastic.co/guide/en/elasticsearch/reference/current/tasks-cancel.html>`_
+
+        :arg task_id: Cancel the task with specified id
+        :arg actions: A comma-separated list of actions that should be
+            cancelled. Leave empty to cancel all.
+        :arg node_id: A comma-separated list of node IDs or names to limit the
+            returned information; use `_local` to return information from the
+            node you're connecting to, leave empty to get information from all
+            nodes
+        :arg parent_node: Cancel tasks with specified parent node.
+        :arg parent_task: Cancel tasks with specified parent task id. Set to -1
+            to cancel all.
+        """
+        return self.transport.perform_request('POST', _make_path('_tasks',
+            task_id, '_cancel'), params=params)
+

elasticsearch/helpers/__init__.py

@@ -268,7 +268,8 @@ def scan(client, query=None, scroll='5m', raise_on_error=True, preserve_order=Fa
 
     """
     if not preserve_order:
-        kwargs['search_type'] = 'scan'
+        body = query.copy() if query else {}
+        body["sort"] = "_doc"
     # initial search
     resp = client.search(body=query, scroll=scroll, **kwargs)
 
@@ -279,7 +280,7 @@ def scan(client, query=None, scroll='5m', raise_on_error=True, preserve_order=Fa
     first_run = True
     while True:
         # if we didn't set search_type to scan initial search contains data
-        if preserve_order and first_run:
+        if first_run:
             first_run = False
         else:
             resp = client.scroll(scroll_id, scroll=scroll)

setup.py

@@ -4,7 +4,7 @@ from setuptools import setup, find_packages
 import sys
 import os
 
-VERSION = (2, 3, 0)
+VERSION = (5, 0, 0, 'dev')
 __version__ = VERSION
 __versionstr__ = '.'.join(map(str, VERSION))
 

test_elasticsearch/test_server/test_common.py

@@ -7,6 +7,7 @@ import re
 from os import walk, environ
 from os.path import exists, join, dirname, pardir
 import yaml
+from shutil import rmtree
 
 from elasticsearch import TransportError
 from elasticsearch.compat import string_types
@@ -48,6 +49,13 @@ class YamlTestCase(ElasticsearchTestCase):
         self.last_response = None
         self._state = {}
 
+    def tearDown(self):
+        super(YamlTestCase, self).tearDown()
+        for repo, definition in self.client.snapshot.get_repository(repository='_all').items():
+            self.client.snapshot.delete_repository(repository=repo)
+            if definition['type'] == 'fs':
+                rmtree('/tmp/%s' % definition['settings']['location'])
+
     def _resolve(self, value):
         # resolve variables
         if isinstance(value, string_types) and value.startswith('$'):

test_elasticsearch/test_server/test_helpers.py

@@ -191,7 +191,7 @@ class TestScan(ElasticsearchTestCase):
             bulk.append({"answer": x, "correct": x == 42})
         self.client.bulk(bulk, refresh=True)
 
-        docs = list(helpers.scan(self.client, index="test_index", doc_type="answers", size=2, query={"sort": ["answer"]}, preserve_order=True))
+        docs = list(helpers.scan(self.client, index="test_index", doc_type="answers", query={"sort": "answer"}, preserve_order=True))
 
         self.assertEquals(100, len(docs))
         self.assertEquals(list(map(str, range(100))), list(d['_id'] for d in docs))
@@ -229,7 +229,7 @@ class TestReindex(ElasticsearchTestCase):
         self.assertEquals({"answer": 42, "correct": True}, self.client.get(index="prod_index", doc_type="answers", id=42)['_source'])
 
     def test_reindex_accepts_a_query(self):
-        helpers.reindex(self.client, "test_index", "prod_index", query={"query": {"filtered": {"filter": {"term": {"_type": "answers"}}}}})
+        helpers.reindex(self.client, "test_index", "prod_index", query={"query": {"bool": {"filter": {"term": {"_type": "answers"}}}}})
         self.client.indices.refresh()
 
         self.assertTrue(self.client.indices.exists("prod_index"))