GoogleCloudPlatform · telpirion · Aug 24, 2023 · Aug 21, 2023 · Aug 22, 2023 · Aug 22, 2023
@@ -0,0 +1,63 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+# To install the latest published package dependency, execute the following:
+#   pip install google-cloud-language
+
+# sample-metadata
+#   title: Classify Content (GCS)
+#   description: Classifying Content in text file stored in Cloud Storage
+
+# [START language_classify_gcs]
+from google.cloud import language_v2
+
+
+def sample_classify_text(
+    gcs_content_uri: str = "gs://cloud-samples-data/language/classify-entertainment.txt",
+) -> None:
+    """
+    Classifies Content in text file stored in Cloud Storage.
+
+    Args:
+      gcs_content_uri: Google Cloud Storage URI where the file content is located.
+        e.g. gs://[Your Bucket]/[Path to File].
+    """
+
+    client = language_v2.LanguageServiceClient()
+
+    # Available types: PLAIN_TEXT, HTML
+    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT
+
+    # Optional. If not specified, the language is automatically detected.
+    # For list of supported languages:
+    # https://cloud.google.com/natural-language/docs/languages
+    language_code = "en"
+    document = {
+        "gcs_content_uri": gcs_content_uri,
+        "type_": document_type_in_plain_text,
+        "language_code": language_code,
+    }
+
+    response = client.classify_text(request={"document": document})
+    # Loop through classified categories returned from the API
+    for category in response.categories:
+        # Get the name of the category representing the document.
+        # See the predefined taxonomy of categories:
+        # https://cloud.google.com/natural-language/docs/categories
+        print(f"Category name: {category.name}")
+        # Get the confidence. Number representing how certain the classifier
+        # is that this category represents the provided text.
+        print(f"Confidence: {category.confidence}")
+# [END language_classify_gcs]
@@ -0,0 +1,27 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+import os
+
+import language_classify_gcs
+
+
+def test_sample_classify_text_gcs(capsys: ...) -> None:
+    assert os.environ["GOOGLE_CLOUD_PROJECT"] != ""
+
+    language_classify_gcs.sample_classify_text()
+    captured = capsys.readouterr()
+    assert "Category name: " in captured.out
+    assert "Confidence: " in captured.out
@@ -0,0 +1,62 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+# To install the latest published package dependency, execute the following:
+#   pip install google-cloud-language
+
+# sample-metadata
+#   title: Classify Content
+#   description: Classifying Content in a String
+
+# [START language_classify_text]
+from google.cloud import language_v2
+
+
+def sample_classify_text(
+    text_content: str = "That actor on TV makes movies in Hollywood and also stars in a variety of popular new TV shows.",
+) -> None:
+    """
+    Classifies Content in a string.
+
+    Args:
+      text_content: The text content to analyze.
+    """
+
+    client = language_v2.LanguageServiceClient()
+
+    # Available types: PLAIN_TEXT, HTML
+    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT
+
+    # Optional. If not specified, the language is automatically detected.
+    # For list of supported languages:
+    # https://cloud.google.com/natural-language/docs/languages
+    language_code = "en"
+    document = {
+        "content": text_content,
+        "type_": document_type_in_plain_text,
+        "language_code": language_code,
+    }
+
+    response = client.classify_text(request={"document": document})
+    # Loop through classified categories returned from the API
+    for category in response.categories:
+        # Get the name of the category representing the document.
+        # See the predefined taxonomy of categories:
+        # https://cloud.google.com/natural-language/docs/categories
+        print(f"Category name: {category.name}")
+        # Get the confidence. Number representing how certain the classifier
+        # is that this category represents the provided text.
+        print(f"Confidence: {category.confidence}")
+# [END language_classify_text]
@@ -0,0 +1,27 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+import os
+
+import language_classify_text
+
+
+def test_sample_classify_text(capsys: ...) -> None:
+    assert os.environ["GOOGLE_CLOUD_PROJECT"] != ""
+
+    language_classify_text.sample_classify_text()
+    captured = capsys.readouterr()
+    assert "Category name: " in captured.out
+    assert "Confidence: " in captured.out
@@ -0,0 +1,91 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+# To install the latest published package dependency, execute the following:
+#   pip install google-cloud-language
+
+# sample-metadata
+#   title: Analyzing Entities (GCS)
+#   description: Analyzing Entities in text file stored in Cloud Storage
+
+# [START language_entities_gcs]
+from google.cloud import language_v2
+
+
+def sample_analyze_entities(
+    gcs_content_uri: str = "gs://cloud-samples-data/language/entity.txt",
+) -> None:
+    """
+    Analyzes Entities in text file stored in Cloud Storage.
+
+    Args:
+      gcs_content_uri: Google Cloud Storage URI where the file content is located.
+        e.g. gs://[Your Bucket]/[Path to File]
+    """
+
+    client = language_v2.LanguageServiceClient()
+
+    # Available types: PLAIN_TEXT, HTML
+    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT
+
+    # Optional. If not specified, the language is automatically detected.
+    # For list of supported languages:
+    # https://cloud.google.com/natural-language/docs/languages
+    language_code = "en"
+    document = {
+        "gcs_content_uri": gcs_content_uri,
+        "type_": document_type_in_plain_text,
+        "language_code": language_code,
+    }
+
+    # Available values: NONE, UTF8, UTF16, UTF32.
+    # See https://cloud.google.com/natural-language/docs/reference/rest/v2/EncodingType.
+    encoding_type = language_v2.EncodingType.UTF8
+
+    response = client.analyze_entities(
+        request={"document": document, "encoding_type": encoding_type}
+    )
+
+    for entity in response.entities:
+        print(f"Representative name for the entity: {entity.name}")
+
+        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al.
+        # See https://cloud.google.com/natural-language/docs/reference/rest/v2/Entity#type.
+        print(f"Entity type: {language_v2.Entity.Type(entity.type_).name}")
+
+        # Loop over the metadata associated with entity.
+        # Some entity types may have additional metadata, e.g. ADDRESS entities
+        # may have metadata for the address street_name, postal_code, et al.
+        for metadata_name, metadata_value in entity.metadata.items():
+            print(f"{metadata_name}: {metadata_value}")
+
+        # Loop over the mentions of this entity in the input document.
+        # The API currently supports proper noun mentions.
+        for mention in entity.mentions:
+            print(f"Mention text: {mention.text.content}")
+
+            # Get the mention type, e.g. PROPER for proper noun
+            print(
+                "Mention type:" f" {language_v2.EntityMention.Type(mention.type_).name}"
+            )
+
+            # Get the probability score associated with the first mention of the entity in the (0, 1.0] range.
+            print(f"Probability score: {mention.probability}")
+
+    # Get the language of the text, which will be the same as
+    # the language specified in the request or, if not specified,
+    # the automatically-detected language.
+    print(f"Language of the text: {response.language_code}")
+# [END language_entities_gcs]
@@ -0,0 +1,31 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+import os
+
+import language_entities_gcs
+
+
+def test_sample_analyze_entities_gcs(capsys: ...) -> None:
+    assert os.environ["GOOGLE_CLOUD_PROJECT"] != ""
+
+    language_entities_gcs.sample_analyze_entities()
+    captured = capsys.readouterr()
+    assert "Representative name for the entity: " in captured.out
+    assert "Entity type: " in captured.out
+    assert "Mention text: " in captured.out
+    assert "Mention type: " in captured.out
+    assert "Probability score: " in captured.out
+    assert "Language of the text: " in captured.out
@@ -0,0 +1,86 @@
+#
+# Copyright 2023 Google LLC
+#
+# 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
+#
+#     https://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.
+
+# To install the latest published package dependency, execute the following:
+#   pip install google-cloud-language
+
+# sample-metadata
+#   title: Analyzing Entities
+#   description: Analyzing Entities in a String
+
+# [START language_entities_text]
+from google.cloud import language_v2
+
+
+def sample_analyze_entities(text_content: str = "California is a state.") -> None:
+    """
+    Analyzes Entities in a string.
+
+    Args:
+      text_content: The text content to analyze
+    """
+
+    client = language_v2.LanguageServiceClient()
+
+    # Available types: PLAIN_TEXT, HTML
+    document_type_in_plain_text = language_v2.Document.Type.PLAIN_TEXT
+
+    # Optional. If not specified, the language is automatically detected.
+    # For list of supported languages:
+    # https://cloud.google.com/natural-language/docs/languages
+    language_code = "en"
+    document = {
+        "content": text_content,
+        "type_": document_type_in_plain_text,
+        "language_code": language_code,
+    }
+
+    # Available values: NONE, UTF8, UTF16, UTF32.
+    # See https://cloud.google.com/natural-language/docs/reference/rest/v2/EncodingType.
+    encoding_type = language_v2.EncodingType.UTF8
+
+    response = client.analyze_entities(
+        request={"document": document, "encoding_type": encoding_type}
+    )
+
+    for entity in response.entities:
+        print(f"Representative name for the entity: {entity.name}")
+
+        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al.
+        # See https://cloud.google.com/natural-language/docs/reference/rest/v2/Entity#type.
+        print(f"Entity type: {language_v2.Entity.Type(entity.type_).name}")
+
+        # Loop over the metadata associated with entity.
+        # Some entity types may have additional metadata, e.g. ADDRESS entities
+        # may have metadata for the address street_name, postal_code, et al.
+        for metadata_name, metadata_value in entity.metadata.items():
+            print(f"{metadata_name}: {metadata_value}")
+
+        # Loop over the mentions of this entity in the input document.
+        # The API currently supports proper noun mentions.
+        for mention in entity.mentions:
+            print(f"Mention text: {mention.text.content}")
+
+            # Get the mention type, e.g. PROPER for proper noun
+            print(f"Mention type: {language_v2.EntityMention.Type(mention.type_).name}")
+
+            # Get the probability score associated with the first mention of the entity in the (0, 1.0] range.
+            print(f"Probability score: {mention.probability}")
+
+    # Get the language of the text, which will be the same as
+    # the language specified in the request or, if not specified,
+    # the automatically-detected language.
+    print(f"Language of the text: {response.language_code}")
+# [END language_entities_text]