elasticsearch/_async/client/__init__.py [6158:6472]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
self,
*,
index: t.Union[str, t.Sequence[str]],
allow_no_indices: t.Optional[bool] = None,
analyze_wildcard: t.Optional[bool] = None,
analyzer: t.Optional[str] = None,
conflicts: t.Optional[t.Union[str, t.Literal["abort", "proceed"]]] = None,
default_operator: t.Optional[t.Union[str, t.Literal["and", "or"]]] = None,
df: t.Optional[str] = None,
error_trace: t.Optional[bool] = None,
expand_wildcards: t.Optional[
t.Union[
t.Sequence[
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]]
],
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]],
]
] = None,
filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
from_: t.Optional[int] = None,
human: t.Optional[bool] = None,
ignore_unavailable: t.Optional[bool] = None,
lenient: t.Optional[bool] = None,
max_docs: t.Optional[int] = None,
pipeline: t.Optional[str] = None,
preference: t.Optional[str] = None,
pretty: t.Optional[bool] = None,
q: t.Optional[str] = None,
query: t.Optional[t.Mapping[str, t.Any]] = None,
refresh: t.Optional[bool] = None,
request_cache: t.Optional[bool] = None,
requests_per_second: t.Optional[float] = None,
routing: t.Optional[str] = None,
script: t.Optional[t.Mapping[str, t.Any]] = None,
scroll: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
scroll_size: t.Optional[int] = None,
search_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
search_type: t.Optional[
t.Union[str, t.Literal["dfs_query_then_fetch", "query_then_fetch"]]
] = None,
slice: t.Optional[t.Mapping[str, t.Any]] = None,
slices: t.Optional[t.Union[int, t.Union[str, t.Literal["auto"]]]] = None,
sort: t.Optional[t.Sequence[str]] = None,
stats: t.Optional[t.Sequence[str]] = None,
terminate_after: t.Optional[int] = None,
timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
version: t.Optional[bool] = None,
version_type: t.Optional[bool] = None,
wait_for_active_shards: t.Optional[
t.Union[int, t.Union[str, t.Literal["all", "index-setting"]]]
] = None,
wait_for_completion: t.Optional[bool] = None,
body: t.Optional[t.Dict[str, t.Any]] = None,
) -> ObjectApiResponse[t.Any]:
"""
.. raw:: html
Update documents.
Updates documents that match the specified query.
If no query is specified, performs an update on every document in the data stream or index without modifying the source, which is useful for picking up mapping changes.
If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or alias:
You can specify the query criteria in the request URI or the request body using the same syntax as the search API.
When you submit an update by query request, Elasticsearch gets a snapshot of the data stream or index when it begins processing the request and updates matching documents using internal versioning.
When the versions match, the document is updated and the version number is incremented.
If a document changes between the time that the snapshot is taken and the update operation is processed, it results in a version conflict and the operation fails.
You can opt to count version conflicts instead of halting and returning by setting conflicts to proceed.
Note that if you opt to count version conflicts, the operation could attempt to update more documents from the source than max_docs until it has successfully updated max_docs documents or it has gone through every document in the source query.
NOTE: Documents with a version equal to 0 cannot be updated using update by query because internal versioning does not support 0 as a valid version number.
While processing an update by query request, Elasticsearch performs multiple search requests sequentially to find all of the matching documents.
A bulk update request is performed for each batch of matching documents.
Any query or update failures cause the update by query request to fail and the failures are shown in the response.
Any update requests that completed successfully still stick, they are not rolled back.
Throttling update requests
To control the rate at which update by query issues batches of update operations, you can set requests_per_second to any positive decimal number.
This pads each batch with a wait time to throttle the rate.
Set requests_per_second to -1 to turn off throttling.
Throttling uses a wait time between batches so that the internal scroll requests can be given a timeout that takes the request padding into account.
The padding time is the difference between the batch size divided by the requests_per_second and the time spent writing.
By default the batch size is 1000, so if requests_per_second is set to 500:
target_time = 1000 / 500 per second = 2 seconds
wait_time = target_time - write_time = 2 seconds - .5 seconds = 1.5 seconds
Since the batch is issued as a single _bulk request, large batch sizes cause Elasticsearch to create many requests and wait before starting the next set.
This is "bursty" instead of "smooth".
Slicing
Update by query supports sliced scroll to parallelize the update process.
This can improve efficiency and provide a convenient way to break the request down into smaller parts.
Setting slices to auto chooses a reasonable number for most data streams and indices.
This setting will use one slice per shard, up to a certain limit.
If there are multiple source data streams or indices, it will choose the number of slices based on the index or backing index with the smallest number of shards.
Adding slices to _update_by_query just automates the manual process of creating sub-requests, which means it has some quirks:
- You can see these requests in the tasks APIs. These sub-requests are "child" tasks of the task for the request with slices.
- Fetching the status of the task for the request with
slices only contains the status of completed slices.
- These sub-requests are individually addressable for things like cancellation and rethrottling.
- Rethrottling the request with
slices will rethrottle the unfinished sub-request proportionally.
- Canceling the request with slices will cancel each sub-request.
- Due to the nature of slices each sub-request won't get a perfectly even portion of the documents. All documents will be addressed, but some slices may be larger than others. Expect larger slices to have a more even distribution.
- Parameters like
requests_per_second and max_docs on a request with slices are distributed proportionally to each sub-request. Combine that with the point above about distribution being uneven and you should conclude that using max_docs with slices might not result in exactly max_docs documents being updated.
- Each sub-request gets a slightly different snapshot of the source data stream or index though these are all taken at approximately the same time.
If you're slicing manually or otherwise tuning automatic slicing, keep in mind that:
- Query performance is most efficient when the number of slices is equal to the number of shards in the index or backing index. If that number is large (for example, 500), choose a lower number as too many slices hurts performance. Setting slices higher than the number of shards generally does not improve efficiency and adds overhead.
- Update performance scales linearly across available resources with the number of slices.
Whether query or update performance dominates the runtime depends on the documents being reindexed and cluster resources.
Update the document source
Update by query supports scripts to update the document source.
As with the update API, you can set ctx.op to change the operation that is performed.
Set ctx.op = "noop" if your script decides that it doesn't have to make any changes.
The update by query operation skips updating the document and increments the noop counter.
Set ctx.op = "delete" if your script decides that the document should be deleted.
The update by query operation deletes the document and increments the deleted counter.
Update by query supports only index, noop, and delete.
Setting ctx.op to anything else is an error.
Setting any other field in ctx is an error.
This API enables you to only modify the source of matching documents; you cannot move them.
``_
:param index: A comma-separated list of data streams, indices, and aliases to
search. It supports wildcards (`*`). To search all data streams or indices,
omit this parameter or use `*` or `_all`.
:param allow_no_indices: If `false`, the request returns an error if any wildcard
expression, index alias, or `_all` value targets only missing or closed indices.
This behavior applies even if the request targets other open indices. For
example, a request targeting `foo*,bar*` returns an error if an index starts
with `foo` but no index starts with `bar`.
:param analyze_wildcard: If `true`, wildcard and prefix queries are analyzed.
This parameter can be used only when the `q` query string parameter is specified.
:param analyzer: The analyzer to use for the query string. This parameter can
be used only when the `q` query string parameter is specified.
:param conflicts: The preferred behavior when update by query hits version conflicts:
`abort` or `proceed`.
:param default_operator: The default operator for query string query: `AND` or
`OR`. This parameter can be used only when the `q` query string parameter
is specified.
:param df: The field to use as default where no field prefix is given in the
query string. This parameter can be used only when the `q` query string parameter
is specified.
:param expand_wildcards: The type of index that wildcard patterns can match.
If the request can target data streams, this argument determines whether
wildcard expressions match hidden data streams. It supports comma-separated
values, such as `open,hidden`. Valid values are: `all`, `open`, `closed`,
`hidden`, `none`.
:param from_: Skips the specified number of documents.
:param ignore_unavailable: If `false`, the request returns an error if it targets
a missing or closed index.
:param lenient: If `true`, format-based query failures (such as providing text
to a numeric field) in the query string will be ignored. This parameter can
be used only when the `q` query string parameter is specified.
:param max_docs: The maximum number of documents to update.
:param pipeline: The ID of the pipeline to use to preprocess incoming documents.
If the index has a default ingest pipeline specified, then setting the value
to `_none` disables the default ingest pipeline for this request. If a final
pipeline is configured it will always run, regardless of the value of this
parameter.
:param preference: The node or shard the operation should be performed on. It
is random by default.
:param q: A query in the Lucene query string syntax.
:param query: The documents to update using the Query DSL.
:param refresh: If `true`, Elasticsearch refreshes affected shards to make the
operation visible to search after the request completes. This is different
than the update API's `refresh` parameter, which causes just the shard that
received the request to be refreshed.
:param request_cache: If `true`, the request cache is used for this request.
It defaults to the index-level setting.
:param requests_per_second: The throttle for this request in sub-requests per
second.
:param routing: A custom value used to route operations to a specific shard.
:param script: The script to run to update the document source or metadata when
updating.
:param scroll: The period to retain the search context for scrolling.
:param scroll_size: The size of the scroll request that powers the operation.
:param search_timeout: An explicit timeout for each search request. By default,
there is no timeout.
:param search_type: The type of the search operation. Available options include
`query_then_fetch` and `dfs_query_then_fetch`.
:param slice: Slice the request manually using the provided slice ID and total
number of slices.
:param slices: The number of slices this task should be divided into.
:param sort: A comma-separated list of : pairs.
:param stats: The specific `tag` of the request for logging and statistical purposes.
:param terminate_after: The maximum number of documents to collect for each shard.
If a query reaches this limit, Elasticsearch terminates the query early.
Elasticsearch collects documents before sorting. IMPORTANT: Use with caution.
Elasticsearch applies this parameter to each shard handling the request.
When possible, let Elasticsearch perform early termination automatically.
Avoid specifying this parameter for requests that target data streams with
backing indices across multiple data tiers.
:param timeout: The period each update request waits for the following operations:
dynamic mapping updates, waiting for active shards. By default, it is one
minute. This guarantees Elasticsearch waits for at least the timeout before
failing. The actual wait time could be longer, particularly when multiple
waits occur.
:param version: If `true`, returns the document version as part of a hit.
:param version_type: Should the document increment the version number (internal)
on hit or not (reindex)
:param wait_for_active_shards: The number of shard copies that must be active
before proceeding with the operation. Set to `all` or any positive integer
up to the total number of shards in the index (`number_of_replicas+1`). The
`timeout` parameter controls how long each write request waits for unavailable
shards to become available. Both work exactly the way they work in the bulk
API.
:param wait_for_completion: If `true`, the request blocks until the operation
is complete. If `false`, Elasticsearch performs some preflight checks, launches
the request, and returns a task ID that you can use to cancel or get the
status of the task. Elasticsearch creates a record of this task as a document
at `.tasks/task/${taskId}`.
"""
if index in SKIP_IN_PATH:
raise ValueError("Empty value passed for parameter 'index'")
__path_parts: t.Dict[str, str] = {"index": _quote(index)}
__path = f'/{__path_parts["index"]}/_update_by_query'
__query: t.Dict[str, t.Any] = {}
__body: t.Dict[str, t.Any] = body if body is not None else {}
# The 'sort' parameter with a colon can't be encoded to the body.
if sort is not None and (
(isinstance(sort, str) and ":" in sort)
or (
isinstance(sort, (list, tuple))
and all(isinstance(_x, str) for _x in sort)
and any(":" in _x for _x in sort)
)
):
__query["sort"] = sort
sort = None
if allow_no_indices is not None:
__query["allow_no_indices"] = allow_no_indices
if analyze_wildcard is not None:
__query["analyze_wildcard"] = analyze_wildcard
if analyzer is not None:
__query["analyzer"] = analyzer
if default_operator is not None:
__query["default_operator"] = default_operator
if df is not None:
__query["df"] = df
if error_trace is not None:
__query["error_trace"] = error_trace
if expand_wildcards is not None:
__query["expand_wildcards"] = expand_wildcards
if filter_path is not None:
__query["filter_path"] = filter_path
if from_ is not None:
__query["from"] = from_
if human is not None:
__query["human"] = human
if ignore_unavailable is not None:
__query["ignore_unavailable"] = ignore_unavailable
if lenient is not None:
__query["lenient"] = lenient
if pipeline is not None:
__query["pipeline"] = pipeline
if preference is not None:
__query["preference"] = preference
if pretty is not None:
__query["pretty"] = pretty
if q is not None:
__query["q"] = q
if refresh is not None:
__query["refresh"] = refresh
if request_cache is not None:
__query["request_cache"] = request_cache
if requests_per_second is not None:
__query["requests_per_second"] = requests_per_second
if routing is not None:
__query["routing"] = routing
if scroll is not None:
__query["scroll"] = scroll
if scroll_size is not None:
__query["scroll_size"] = scroll_size
if search_timeout is not None:
__query["search_timeout"] = search_timeout
if search_type is not None:
__query["search_type"] = search_type
if slices is not None:
__query["slices"] = slices
if sort is not None:
__query["sort"] = sort
if stats is not None:
__query["stats"] = stats
if terminate_after is not None:
__query["terminate_after"] = terminate_after
if timeout is not None:
__query["timeout"] = timeout
if version is not None:
__query["version"] = version
if version_type is not None:
__query["version_type"] = version_type
if wait_for_active_shards is not None:
__query["wait_for_active_shards"] = wait_for_active_shards
if wait_for_completion is not None:
__query["wait_for_completion"] = wait_for_completion
if not __body:
if conflicts is not None:
__body["conflicts"] = conflicts
if max_docs is not None:
__body["max_docs"] = max_docs
if query is not None:
__body["query"] = query
if script is not None:
__body["script"] = script
if slice is not None:
__body["slice"] = slice
if not __body:
__body = None # type: ignore[assignment]
__headers = {"accept": "application/json"}
if __body is not None:
__headers["content-type"] = "application/json"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
elasticsearch/_sync/client/__init__.py [6156:6470]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
self,
*,
index: t.Union[str, t.Sequence[str]],
allow_no_indices: t.Optional[bool] = None,
analyze_wildcard: t.Optional[bool] = None,
analyzer: t.Optional[str] = None,
conflicts: t.Optional[t.Union[str, t.Literal["abort", "proceed"]]] = None,
default_operator: t.Optional[t.Union[str, t.Literal["and", "or"]]] = None,
df: t.Optional[str] = None,
error_trace: t.Optional[bool] = None,
expand_wildcards: t.Optional[
t.Union[
t.Sequence[
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]]
],
t.Union[str, t.Literal["all", "closed", "hidden", "none", "open"]],
]
] = None,
filter_path: t.Optional[t.Union[str, t.Sequence[str]]] = None,
from_: t.Optional[int] = None,
human: t.Optional[bool] = None,
ignore_unavailable: t.Optional[bool] = None,
lenient: t.Optional[bool] = None,
max_docs: t.Optional[int] = None,
pipeline: t.Optional[str] = None,
preference: t.Optional[str] = None,
pretty: t.Optional[bool] = None,
q: t.Optional[str] = None,
query: t.Optional[t.Mapping[str, t.Any]] = None,
refresh: t.Optional[bool] = None,
request_cache: t.Optional[bool] = None,
requests_per_second: t.Optional[float] = None,
routing: t.Optional[str] = None,
script: t.Optional[t.Mapping[str, t.Any]] = None,
scroll: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
scroll_size: t.Optional[int] = None,
search_timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
search_type: t.Optional[
t.Union[str, t.Literal["dfs_query_then_fetch", "query_then_fetch"]]
] = None,
slice: t.Optional[t.Mapping[str, t.Any]] = None,
slices: t.Optional[t.Union[int, t.Union[str, t.Literal["auto"]]]] = None,
sort: t.Optional[t.Sequence[str]] = None,
stats: t.Optional[t.Sequence[str]] = None,
terminate_after: t.Optional[int] = None,
timeout: t.Optional[t.Union[str, t.Literal[-1], t.Literal[0]]] = None,
version: t.Optional[bool] = None,
version_type: t.Optional[bool] = None,
wait_for_active_shards: t.Optional[
t.Union[int, t.Union[str, t.Literal["all", "index-setting"]]]
] = None,
wait_for_completion: t.Optional[bool] = None,
body: t.Optional[t.Dict[str, t.Any]] = None,
) -> ObjectApiResponse[t.Any]:
"""
.. raw:: html
Update documents.
Updates documents that match the specified query.
If no query is specified, performs an update on every document in the data stream or index without modifying the source, which is useful for picking up mapping changes.
If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or alias:
You can specify the query criteria in the request URI or the request body using the same syntax as the search API.
When you submit an update by query request, Elasticsearch gets a snapshot of the data stream or index when it begins processing the request and updates matching documents using internal versioning.
When the versions match, the document is updated and the version number is incremented.
If a document changes between the time that the snapshot is taken and the update operation is processed, it results in a version conflict and the operation fails.
You can opt to count version conflicts instead of halting and returning by setting conflicts to proceed.
Note that if you opt to count version conflicts, the operation could attempt to update more documents from the source than max_docs until it has successfully updated max_docs documents or it has gone through every document in the source query.
NOTE: Documents with a version equal to 0 cannot be updated using update by query because internal versioning does not support 0 as a valid version number.
While processing an update by query request, Elasticsearch performs multiple search requests sequentially to find all of the matching documents.
A bulk update request is performed for each batch of matching documents.
Any query or update failures cause the update by query request to fail and the failures are shown in the response.
Any update requests that completed successfully still stick, they are not rolled back.
Throttling update requests
To control the rate at which update by query issues batches of update operations, you can set requests_per_second to any positive decimal number.
This pads each batch with a wait time to throttle the rate.
Set requests_per_second to -1 to turn off throttling.
Throttling uses a wait time between batches so that the internal scroll requests can be given a timeout that takes the request padding into account.
The padding time is the difference between the batch size divided by the requests_per_second and the time spent writing.
By default the batch size is 1000, so if requests_per_second is set to 500:
target_time = 1000 / 500 per second = 2 seconds
wait_time = target_time - write_time = 2 seconds - .5 seconds = 1.5 seconds
Since the batch is issued as a single _bulk request, large batch sizes cause Elasticsearch to create many requests and wait before starting the next set.
This is "bursty" instead of "smooth".
Slicing
Update by query supports sliced scroll to parallelize the update process.
This can improve efficiency and provide a convenient way to break the request down into smaller parts.
Setting slices to auto chooses a reasonable number for most data streams and indices.
This setting will use one slice per shard, up to a certain limit.
If there are multiple source data streams or indices, it will choose the number of slices based on the index or backing index with the smallest number of shards.
Adding slices to _update_by_query just automates the manual process of creating sub-requests, which means it has some quirks:
- You can see these requests in the tasks APIs. These sub-requests are "child" tasks of the task for the request with slices.
- Fetching the status of the task for the request with
slices only contains the status of completed slices.
- These sub-requests are individually addressable for things like cancellation and rethrottling.
- Rethrottling the request with
slices will rethrottle the unfinished sub-request proportionally.
- Canceling the request with slices will cancel each sub-request.
- Due to the nature of slices each sub-request won't get a perfectly even portion of the documents. All documents will be addressed, but some slices may be larger than others. Expect larger slices to have a more even distribution.
- Parameters like
requests_per_second and max_docs on a request with slices are distributed proportionally to each sub-request. Combine that with the point above about distribution being uneven and you should conclude that using max_docs with slices might not result in exactly max_docs documents being updated.
- Each sub-request gets a slightly different snapshot of the source data stream or index though these are all taken at approximately the same time.
If you're slicing manually or otherwise tuning automatic slicing, keep in mind that:
- Query performance is most efficient when the number of slices is equal to the number of shards in the index or backing index. If that number is large (for example, 500), choose a lower number as too many slices hurts performance. Setting slices higher than the number of shards generally does not improve efficiency and adds overhead.
- Update performance scales linearly across available resources with the number of slices.
Whether query or update performance dominates the runtime depends on the documents being reindexed and cluster resources.
Update the document source
Update by query supports scripts to update the document source.
As with the update API, you can set ctx.op to change the operation that is performed.
Set ctx.op = "noop" if your script decides that it doesn't have to make any changes.
The update by query operation skips updating the document and increments the noop counter.
Set ctx.op = "delete" if your script decides that the document should be deleted.
The update by query operation deletes the document and increments the deleted counter.
Update by query supports only index, noop, and delete.
Setting ctx.op to anything else is an error.
Setting any other field in ctx is an error.
This API enables you to only modify the source of matching documents; you cannot move them.
``_
:param index: A comma-separated list of data streams, indices, and aliases to
search. It supports wildcards (`*`). To search all data streams or indices,
omit this parameter or use `*` or `_all`.
:param allow_no_indices: If `false`, the request returns an error if any wildcard
expression, index alias, or `_all` value targets only missing or closed indices.
This behavior applies even if the request targets other open indices. For
example, a request targeting `foo*,bar*` returns an error if an index starts
with `foo` but no index starts with `bar`.
:param analyze_wildcard: If `true`, wildcard and prefix queries are analyzed.
This parameter can be used only when the `q` query string parameter is specified.
:param analyzer: The analyzer to use for the query string. This parameter can
be used only when the `q` query string parameter is specified.
:param conflicts: The preferred behavior when update by query hits version conflicts:
`abort` or `proceed`.
:param default_operator: The default operator for query string query: `AND` or
`OR`. This parameter can be used only when the `q` query string parameter
is specified.
:param df: The field to use as default where no field prefix is given in the
query string. This parameter can be used only when the `q` query string parameter
is specified.
:param expand_wildcards: The type of index that wildcard patterns can match.
If the request can target data streams, this argument determines whether
wildcard expressions match hidden data streams. It supports comma-separated
values, such as `open,hidden`. Valid values are: `all`, `open`, `closed`,
`hidden`, `none`.
:param from_: Skips the specified number of documents.
:param ignore_unavailable: If `false`, the request returns an error if it targets
a missing or closed index.
:param lenient: If `true`, format-based query failures (such as providing text
to a numeric field) in the query string will be ignored. This parameter can
be used only when the `q` query string parameter is specified.
:param max_docs: The maximum number of documents to update.
:param pipeline: The ID of the pipeline to use to preprocess incoming documents.
If the index has a default ingest pipeline specified, then setting the value
to `_none` disables the default ingest pipeline for this request. If a final
pipeline is configured it will always run, regardless of the value of this
parameter.
:param preference: The node or shard the operation should be performed on. It
is random by default.
:param q: A query in the Lucene query string syntax.
:param query: The documents to update using the Query DSL.
:param refresh: If `true`, Elasticsearch refreshes affected shards to make the
operation visible to search after the request completes. This is different
than the update API's `refresh` parameter, which causes just the shard that
received the request to be refreshed.
:param request_cache: If `true`, the request cache is used for this request.
It defaults to the index-level setting.
:param requests_per_second: The throttle for this request in sub-requests per
second.
:param routing: A custom value used to route operations to a specific shard.
:param script: The script to run to update the document source or metadata when
updating.
:param scroll: The period to retain the search context for scrolling.
:param scroll_size: The size of the scroll request that powers the operation.
:param search_timeout: An explicit timeout for each search request. By default,
there is no timeout.
:param search_type: The type of the search operation. Available options include
`query_then_fetch` and `dfs_query_then_fetch`.
:param slice: Slice the request manually using the provided slice ID and total
number of slices.
:param slices: The number of slices this task should be divided into.
:param sort: A comma-separated list of : pairs.
:param stats: The specific `tag` of the request for logging and statistical purposes.
:param terminate_after: The maximum number of documents to collect for each shard.
If a query reaches this limit, Elasticsearch terminates the query early.
Elasticsearch collects documents before sorting. IMPORTANT: Use with caution.
Elasticsearch applies this parameter to each shard handling the request.
When possible, let Elasticsearch perform early termination automatically.
Avoid specifying this parameter for requests that target data streams with
backing indices across multiple data tiers.
:param timeout: The period each update request waits for the following operations:
dynamic mapping updates, waiting for active shards. By default, it is one
minute. This guarantees Elasticsearch waits for at least the timeout before
failing. The actual wait time could be longer, particularly when multiple
waits occur.
:param version: If `true`, returns the document version as part of a hit.
:param version_type: Should the document increment the version number (internal)
on hit or not (reindex)
:param wait_for_active_shards: The number of shard copies that must be active
before proceeding with the operation. Set to `all` or any positive integer
up to the total number of shards in the index (`number_of_replicas+1`). The
`timeout` parameter controls how long each write request waits for unavailable
shards to become available. Both work exactly the way they work in the bulk
API.
:param wait_for_completion: If `true`, the request blocks until the operation
is complete. If `false`, Elasticsearch performs some preflight checks, launches
the request, and returns a task ID that you can use to cancel or get the
status of the task. Elasticsearch creates a record of this task as a document
at `.tasks/task/${taskId}`.
"""
if index in SKIP_IN_PATH:
raise ValueError("Empty value passed for parameter 'index'")
__path_parts: t.Dict[str, str] = {"index": _quote(index)}
__path = f'/{__path_parts["index"]}/_update_by_query'
__query: t.Dict[str, t.Any] = {}
__body: t.Dict[str, t.Any] = body if body is not None else {}
# The 'sort' parameter with a colon can't be encoded to the body.
if sort is not None and (
(isinstance(sort, str) and ":" in sort)
or (
isinstance(sort, (list, tuple))
and all(isinstance(_x, str) for _x in sort)
and any(":" in _x for _x in sort)
)
):
__query["sort"] = sort
sort = None
if allow_no_indices is not None:
__query["allow_no_indices"] = allow_no_indices
if analyze_wildcard is not None:
__query["analyze_wildcard"] = analyze_wildcard
if analyzer is not None:
__query["analyzer"] = analyzer
if default_operator is not None:
__query["default_operator"] = default_operator
if df is not None:
__query["df"] = df
if error_trace is not None:
__query["error_trace"] = error_trace
if expand_wildcards is not None:
__query["expand_wildcards"] = expand_wildcards
if filter_path is not None:
__query["filter_path"] = filter_path
if from_ is not None:
__query["from"] = from_
if human is not None:
__query["human"] = human
if ignore_unavailable is not None:
__query["ignore_unavailable"] = ignore_unavailable
if lenient is not None:
__query["lenient"] = lenient
if pipeline is not None:
__query["pipeline"] = pipeline
if preference is not None:
__query["preference"] = preference
if pretty is not None:
__query["pretty"] = pretty
if q is not None:
__query["q"] = q
if refresh is not None:
__query["refresh"] = refresh
if request_cache is not None:
__query["request_cache"] = request_cache
if requests_per_second is not None:
__query["requests_per_second"] = requests_per_second
if routing is not None:
__query["routing"] = routing
if scroll is not None:
__query["scroll"] = scroll
if scroll_size is not None:
__query["scroll_size"] = scroll_size
if search_timeout is not None:
__query["search_timeout"] = search_timeout
if search_type is not None:
__query["search_type"] = search_type
if slices is not None:
__query["slices"] = slices
if sort is not None:
__query["sort"] = sort
if stats is not None:
__query["stats"] = stats
if terminate_after is not None:
__query["terminate_after"] = terminate_after
if timeout is not None:
__query["timeout"] = timeout
if version is not None:
__query["version"] = version
if version_type is not None:
__query["version_type"] = version_type
if wait_for_active_shards is not None:
__query["wait_for_active_shards"] = wait_for_active_shards
if wait_for_completion is not None:
__query["wait_for_completion"] = wait_for_completion
if not __body:
if conflicts is not None:
__body["conflicts"] = conflicts
if max_docs is not None:
__body["max_docs"] = max_docs
if query is not None:
__body["query"] = query
if script is not None:
__body["script"] = script
if slice is not None:
__body["slice"] = slice
if not __body:
__body = None # type: ignore[assignment]
__headers = {"accept": "application/json"}
if __body is not None:
__headers["content-type"] = "application/json"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -