feat: Add new gcloud commands, API clients, and third-party libraries across various services.

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/__init__.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2016 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Command group for ml video."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.calliope import base
+
+
+@base.ReleaseTracks(
+    base.ReleaseTrack.GA, base.ReleaseTrack.BETA, base.ReleaseTrack.ALPHA)
+class VideoIntelligence(base.Group):
+  """Cloud ML Video-Intelligence command groups."""

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/__init__.yaml

@@ -0,0 +1,64 @@
+request:
+  collection: videointelligence.videos
+  method: annotate
+  api_version: v1
+
+async:
+  collection: videointelligence.projects.locations.operations
+  extract_resource_result: false
+  result_attribute: response
+
+args:
+- arg_name: input_path
+  is_positional: true
+  help_text: |
+    Path to the video to be analyzed. Must be a local path or a Google
+    Cloud Storage URI.
+- api_field: outputUri
+  arg_name: output-uri
+  help_text: |
+    Location to which the results should be written. Must be a Google
+    Cloud Storage URI.
+  processor: googlecloudsdk.command_lib.ml.video.util:ValidateOutputUri
+
+- api_field: videoContext.segments
+  arg_name: segments
+  help_text: |
+    Segments from the video which you want to analyze (by default, the
+    entire video will be treated as one segment). Must be in the format
+    START1:END1[,START2:END2,...] (inclusive). START and END of segments must
+    be a properly formatted duration string of the form `HhMmSs` where:
+
+    ```
+    *  H is the number of hours from beginning of video
+    *  M is the number of minutes from the beginning of video
+    *  S is the number of seconds from the beginning of the video
+    ```
+
+    H, M and S can be specified as ints or floats for fractional units
+    (to microsecond resolution). Unit chars (e.g. `h`, `m` or `s`) are
+    required. Microseconds can be specified using fractional seconds
+    e.g. 0.000569s == 569 microseconds.
+
+    Examples:
+
+    0s:23.554048s,24s:29.528064s
+
+    0:1m40s,3m50s:5m10.232265s
+  type: str
+  processor: googlecloudsdk.command_lib.ml.video.util:ValidateAndParseSegments
+
+- api_field: locationId
+  arg_name: region
+  choices:
+  - arg_value: us-east1
+    enum_value: us-east1
+  - arg_value: us-west1
+    enum_value: us-west1
+  - arg_value: europe-west1
+    enum_value: europe-west1
+  - arg_value: asia-east1
+    enum_value: asia-east1
+  help_text: |
+    Optional Cloud region where annotation should take place. If no region
+    is specified, a region will be determined based on video file location.

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/detect_explicit_content.yaml

@@ -0,0 +1,33 @@
+- release_tracks: []
+
+  help_text:
+    brief: Detect explicit content in videos.
+    description: |
+      Detect adult content within a video. Adult content is content generally
+      appropriate for 18 years of age and older, including but not limited to
+      nudity, sexual activities, and pornography (including cartoons or anime).
+
+      The response includes a bucketized likelihood value, from VERY_UNLIKELY to
+      VERY_LIKELY. When Explicit Content Detection evaluates a video, it does so on
+      a per-frame basis and considers visual content only (not audio).
+    examples: |
+      To detect explicit content in a video file named 'gs://my_bucket/input_file.mp4', run the following command.:
+
+        $ {command} gs://my_bucket/input_file.mp4
+
+  request:
+    _COMMON_: request
+    static_fields:
+      features: [EXPLICIT_CONTENT_DETECTION]
+    modify_request_hooks:
+    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput
+
+  async:
+    _COMMON_: async
+
+  arguments:
+    params:
+    - _COMMON_args
+
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/detect_labels.yaml

@@ -0,0 +1,43 @@
+- release_tracks: []
+
+  help_text:
+    brief: Detect general labels for videos.
+    description: |
+      Detect general categories in videos, such as modes of transportation or
+      animals. Use the --detection-mode flag to control whether labels are
+      detected for shots, frames, or both.
+    examples: |
+      To detect labels in video file 'gs://my_bucket/input_file.mp4':
+
+        $ {command} gs://my_bucket/input_file.mp4
+
+  request:
+    _COMMON_: request
+    static_fields:
+      features: [LABEL_DETECTION]
+    modify_request_hooks:
+    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput
+
+  async:
+    _COMMON_: async
+
+  arguments:
+    params:
+    - _COMMON_args
+    - api_field: videoContext.labelDetectionConfig.labelDetectionMode
+      arg_name: detection-mode
+      help_text: The mode of label detection requested.
+      choices:
+      - arg_value: shot
+        enum_value: SHOT_MODE
+        help_text: Detect labels at the per-shot level.
+      - arg_value: frame
+        enum_value: FRAME_MODE
+        help_text: Detect labels at the per-frame level.
+      - arg_value: shot-and-frame
+        enum_value: SHOT_AND_FRAME_MODE
+        help_text: Detect labels at both the per-shot and per-frame level.
+      default: shot
+
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/detect_object.yaml

@@ -0,0 +1,26 @@
+- release_tracks: [ALPHA, BETA]
+
+  help_text:
+    brief: Detect and track objects in a video.
+    description: |
+      Detect and track objects in a video.
+    examples: |
+      To detect and track objects in video file 'gs://my_bucket/input_file.mp4':
+
+        $ {command} gs://my_bucket/input_file.mp4
+  request:
+    _COMMON_: request
+    static_fields:
+      features: [OBJECT_TRACKING]
+    modify_request_hooks:
+    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput
+
+  async:
+    _COMMON_: async
+
+  arguments:
+    params:
+    - _COMMON_args
+
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/detect_shot_changes.yaml

@@ -0,0 +1,27 @@
+- release_tracks: []
+
+  help_text:
+    brief: Detect shot changes in videos.
+    description: |
+      Detect when the shot changes in a video.
+    examples: |
+      To detect shot changes in a video file named 'gs://my_bucket/input_file.mp4', run the following command:
+
+        $ {command} gs://my_bucket/input_file.mp4
+
+  request:
+    _COMMON_: request
+    static_fields:
+      features: [SHOT_CHANGE_DETECTION]
+    modify_request_hooks:
+    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput
+
+  async:
+    _COMMON_: async
+
+  arguments:
+    params:
+    - _COMMON_args
+
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/detect_text.yaml

@@ -0,0 +1,33 @@
+- release_tracks: [ALPHA, BETA]
+
+  help_text:
+    brief: Detect text in videos.
+    description: |
+      Detect text in videos.
+    examples: |
+      To detect text in video file 'gs://my_bucket/input_file.mp4':
+
+        $ {command} gs://my_bucket/input_file.mp4
+
+  request:
+    _COMMON_: request
+    static_fields:
+      features: [TEXT_DETECTION]
+    modify_request_hooks:
+    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput
+
+  async:
+    _COMMON_: async
+
+  arguments:
+    params:
+    - _COMMON_args
+    - api_field: videoContext.textDetectionConfig.languageHints
+      arg_name: language-hints
+      default: []
+      help_text: Language hints can be specified if the languages to be detected are known
+        beforehand. It can increase the accuracy of the detection. Language hints must be language
+        codes in BCP-47 format. Automatic language detection is performed if no language hints are
+        provided.
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/operations/__init__.py

@@ -0,0 +1,26 @@
+# -*- coding: utf-8 -*- #
+# Copyright 2016 Google LLC. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Command group for ml operations."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import unicode_literals
+
+from googlecloudsdk.calliope import base
+
+
+class Operations(base.Group):
+  """Command group for working with Cloud Video Intelligence operations."""

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/operations/describe.yaml

@@ -0,0 +1,22 @@
+- release_tracks: []
+
+  help_text:
+    brief: Get description of a long-running video analysis operation.
+    description: |
+      Get information about a long-running video analysis operation.
+    examples: |-
+      To get information about a long-running operation with name 'projects/my-project/locations/us-east1/operations/123', run the following command:
+
+        $ {command} projects/my-project/locations/us-east1/operations/123
+
+  request:
+    collection: videointelligence.projects.locations.operations
+    api_version: v1
+
+  arguments:
+    resource:
+      help_text: The ID of the operation to describe.
+      spec: !REF googlecloudsdk.command_lib.ml.video.resources:operation
+
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/operations/wait.yaml

@@ -0,0 +1,28 @@
+- release_tracks: []
+
+  help_text:
+    brief: Poll long-running video analysis operation until it completes.
+    description: |
+      Poll a long-running video analysis operation until it completes. When
+      the operation is complete, this command will display the results of the
+      analysis.
+    examples: |
+      To poll a long-running video analysis operation named 'projects/my-project/locations/us-east1/operations/123' until it completes, run the following:
+
+        $ {command} projects/my-project/locations/us-east1/operations/123
+
+  request:
+    collection: videointelligence.projects.locations.operations
+    api_version: v1
+
+  arguments:
+    resource:
+      help_text: ID for the operation to poll until complete.
+      spec: !REF googlecloudsdk.command_lib.ml.video.resources:operation
+
+  async:
+    collection: videointelligence.projects.locations.operations
+    result_attribute: response
+
+  output:
+    format: json

gcloud auth application-default login/google-cloud-sdk/lib/surface/ml/video/transcribe_speech.yaml

@@ -0,0 +1,86 @@
+- release_tracks: [ALPHA, BETA]
+
+  help_text:
+    brief: Transcribe speech in a video.
+    description: |
+      Transcribe speech within a video.
+    examples: |
+      To transcribe speech in video file 'gs://my_bucket/input_file.mp4':
+
+        $ {command} gs://my_bucket/input_file.mp4
+  request:
+    _COMMON_: request
+    static_fields:
+      features: [SPEECH_TRANSCRIPTION]
+    modify_request_hooks:
+    - googlecloudsdk.command_lib.ml.video.util:UpdateRequestWithInput
+
+  async:
+    _COMMON_: async
+
+  arguments:
+    params:
+    - _COMMON_args
+    - api_field: videoContext.speechTranscriptionConfig.enableAutomaticPunctuation
+      arg_name: enable-automatic-punctuation
+      help_text: |
+        If enabled, adds punctuation to recognition result hypotheses. This feature is only
+        available in select languages. Setting this for requests in other languages has no effect at
+        all. The default disabled case does not add punctuation to result hypotheses.
+    - api_field: videoContext.speechTranscriptionConfig.enableSpeakerDiarization
+      arg_name: enable-speaker-diarization
+      help_text: |
+        If enabled, perform speaker detection for each recognized word in the top alternative of the
+        recognition result using a speaker_tag provided in the WordInfo results section. When this
+        is enabled, we send all the words from the beginning of the audio for the top alternative in
+        every consecutive responses. This is done in order to improve our speaker tags as our models
+        learn to identify the speakers in the conversation over time.
+    - api_field: videoContext.speechTranscriptionConfig.diarizationSpeakerCount
+      arg_name: diarization-speaker-count
+      help_text: |
+        Optional estimated number of speakers in the conversation. If not specified, defaults to
+        '2'. Ignored unless --enable-speaker-diarization is enabled.
+    - api_field: videoContext.speechTranscriptionConfig.maxAlternatives
+      arg_name: max-alternatives
+      help_text: |
+        Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of
+        `SpeechRecognitionAlternative` messages within each `SpeechTranscription`. The server may
+        return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will
+        return a maximum of one. If omitted, will return a maximum of one
+    - api_field: videoContext.speechTranscriptionConfig.languageCode
+      arg_name: language-code
+      required: true
+      help_text: |
+          The language of the supplied audio as a
+          [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
+          language tag. Example: "en-US". See
+          [Language Support](https://cloud.google.com/speech/docs/languages) for a list of the
+          currently supported language codes.
+    - api_field: videoContext.speechTranscriptionConfig.filterProfanity
+      arg_name: filter-profanity
+      help_text: |
+        If enabled, the server will attempt to filter out profanities, replacing all but the
+        initial character in each filtered word with asterisks, e.g. ```f***```. If disabled or
+        omitted, profanities will not be filtered out.
+    - api_field: videoContext.speechTranscriptionConfig.enableWordConfidence
+      arg_name: enable-word-confidence
+      help_text: |
+        If enabled, the top result includes a list of words and the confidence for those words. If
+        disabled, no word-level confidence information is returned. The default is disabled.
+    - api_field: videoContext.speechTranscriptionConfig.audioTracks
+      arg_name: audio-tracks
+      processor: googlecloudsdk.command_lib.ml.video.util:AudioTrackProcessor
+      help_text: |
+        For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two
+        commas separated tracks. Default track is 0.
+    - api_field: videoContext.speechTranscriptionConfig.speechContexts.phrases
+      arg_name: hints
+      default: []
+      help_text: |
+        list of strings containing words and phrases "hints" so that the speech recognition is
+        more likely to recognize them. This can be used to improve the accuracy for specific words
+        and phrases, for example, if specific commands are typically spoken by the user. This can
+        also be used to add additional words to the vocabulary of the recognizer. See
+        (https://cloud.google.com/speech/limits#content).
+  output:
+    format: yaml