Translate / Client / translate_document

translate_document#

Translate.Client.translate_document(**kwargs)#

Translates the input document from the source language to the target language. This synchronous operation supports text, HTML, or Word documents as the input document. TranslateDocument supports translations from English to any supported language, and from any supported language to English. Therefore, specify either the source language code or the target language code as “en” (English).

If you set the Formality parameter, the request will fail if the target language does not support formality. For a list of target languages that support formality, see Setting formality.

See also: AWS API Documentation

Request Syntax

response = client.translate_document(
    Document={
        'Content': b'bytes',
        'ContentType': 'string'
    },
    TerminologyNames=[
        'string',
    ],
    SourceLanguageCode='string',
    TargetLanguageCode='string',
    Settings={
        'Formality': 'FORMAL'|'INFORMAL',
        'Profanity': 'MASK',
        'Brevity': 'ON'
    }
)
Parameters:
  • Document (dict) –

    [REQUIRED]

    The content and content type for the document to be translated. The document size must not exceed 100 KB.

    • Content (bytes) – [REQUIRED]

      The ``Content``field type is Binary large object (blob). This object contains the document content converted into base64-encoded binary data. If you use one of the AWS SDKs, the SDK performs the Base64-encoding on this field before sending the request.

    • ContentType (string) – [REQUIRED]

      Describes the format of the document. You can specify one of the following:

      • text/html - The input data consists of HTML content. Amazon Translate translates only the text in the HTML element.

      • text/plain - The input data consists of unformatted text. Amazon Translate translates every character in the content.

      • application/vnd.openxmlformats-officedocument.wordprocessingml.document - The input data consists of a Word document (.docx).

  • TerminologyNames (list) –

    The name of a terminology list file to add to the translation job. This file provides source terms and the desired translation for each term. A terminology list can contain a maximum of 256 terms. You can use one custom terminology resource in your translation request.

    Use the ListTerminologies operation to get the available terminology lists.

    For more information about custom terminology lists, see Custom terminology.

    • (string) –

  • SourceLanguageCode (string) –

    [REQUIRED]

    The language code for the language of the source text. For a list of supported language codes, see Supported languages.

    To have Amazon Translate determine the source language of your text, you can specify auto in the SourceLanguageCode field. If you specify auto, Amazon Translate will call Amazon Comprehend to determine the source language.

    Note

    If you specify auto, you must send the TranslateDocument request in a region that supports Amazon Comprehend. Otherwise, the request returns an error indicating that autodetect is not supported.

  • TargetLanguageCode (string) –

    [REQUIRED]

    The language code requested for the translated document. For a list of supported language codes, see Supported languages.

  • Settings (dict) –

    Settings to configure your translation output. You can configure the following options:

    • Brevity: not supported.

    • Formality: sets the formality level of the output text.

    • Profanity: masks profane words and phrases in your translation output.

    • Formality (string) –

      You can specify the desired level of formality for translations to supported target languages. The formality setting controls the level of formal language usage (also known as register) in the translation output. You can set the value to informal or formal. If you don’t specify a value for formality, or if the target language doesn’t support formality, the translation will ignore the formality setting.

      If you specify multiple target languages for the job, translate ignores the formality setting for any unsupported target language.

      For a list of target languages that support formality, see Supported languages in the Amazon Translate Developer Guide.

    • Profanity (string) –

      You can enable the profanity setting if you want to mask profane words and phrases in your translation output.

      To mask profane words and phrases, Amazon Translate replaces them with the grawlix string “?$#@$“. This 5-character sequence is used for each profane word or phrase, regardless of the length or number of words.

      Amazon Translate doesn’t detect profanity in all of its supported languages. For languages that don’t support profanity detection, see Unsupported languages in the Amazon Translate Developer Guide.

      If you specify multiple target languages for the job, all the target languages must support profanity masking. If any of the target languages don’t support profanity masking, the translation job won’t mask profanity for any target language.

    • Brevity (string) –

      When you turn on brevity, Amazon Translate reduces the length of the translation output for most translations (when compared with the same translation with brevity turned off). By default, brevity is turned off.

      If you turn on brevity for a translation request with an unsupported language pair, the translation proceeds with the brevity setting turned off.

      For the language pairs that brevity supports, see Using brevity in the Amazon Translate Developer Guide.

Return type:

dict

Returns:

Response Syntax

{
    'TranslatedDocument': {
        'Content': b'bytes'
    },
    'SourceLanguageCode': 'string',
    'TargetLanguageCode': 'string',
    'AppliedTerminologies': [
        {
            'Name': 'string',
            'Terms': [
                {
                    'SourceText': 'string',
                    'TargetText': 'string'
                },
            ]
        },
    ],
    'AppliedSettings': {
        'Formality': 'FORMAL'|'INFORMAL',
        'Profanity': 'MASK',
        'Brevity': 'ON'
    }
}

Response Structure

  • (dict) –

    • TranslatedDocument (dict) –

      The document containing the translated content. The document format matches the source document format.

      • Content (bytes) –

        The document containing the translated content.

    • SourceLanguageCode (string) –

      The language code of the source document.

    • TargetLanguageCode (string) –

      The language code of the translated document.

    • AppliedTerminologies (list) –

      The names of the custom terminologies applied to the input text by Amazon Translate to produce the translated text document.

      • (dict) –

        The custom terminology applied to the input text by Amazon Translate for the translated text response. This is optional in the response and will only be present if you specified terminology input in the request. Currently, only one terminology can be applied per TranslateText request.

        • Name (string) –

          The name of the custom terminology applied to the input text by Amazon Translate for the translated text response.

        • Terms (list) –

          The specific terms of the custom terminology applied to the input text by Amazon Translate for the translated text response. A maximum of 250 terms will be returned, and the specific terms applied will be the first 250 terms in the source text.

          • (dict) –

            The term being translated by the custom terminology.

            • SourceText (string) –

              The source text of the term being translated by the custom terminology.

            • TargetText (string) –

              The target text of the term being translated by the custom terminology.

    • AppliedSettings (dict) –

      Settings to configure your translation output. You can configure the following options:

      • Brevity: reduces the length of the translation output for most translations. Available for TranslateText only.

      • Formality: sets the formality level of the translation output.

      • Profanity: masks profane words and phrases in the translation output.

      • Formality (string) –

        You can specify the desired level of formality for translations to supported target languages. The formality setting controls the level of formal language usage (also known as register) in the translation output. You can set the value to informal or formal. If you don’t specify a value for formality, or if the target language doesn’t support formality, the translation will ignore the formality setting.

        If you specify multiple target languages for the job, translate ignores the formality setting for any unsupported target language.

        For a list of target languages that support formality, see Supported languages in the Amazon Translate Developer Guide.

      • Profanity (string) –

        You can enable the profanity setting if you want to mask profane words and phrases in your translation output.

        To mask profane words and phrases, Amazon Translate replaces them with the grawlix string “?$#@$“. This 5-character sequence is used for each profane word or phrase, regardless of the length or number of words.

        Amazon Translate doesn’t detect profanity in all of its supported languages. For languages that don’t support profanity detection, see Unsupported languages in the Amazon Translate Developer Guide.

        If you specify multiple target languages for the job, all the target languages must support profanity masking. If any of the target languages don’t support profanity masking, the translation job won’t mask profanity for any target language.

      • Brevity (string) –

        When you turn on brevity, Amazon Translate reduces the length of the translation output for most translations (when compared with the same translation with brevity turned off). By default, brevity is turned off.

        If you turn on brevity for a translation request with an unsupported language pair, the translation proceeds with the brevity setting turned off.

        For the language pairs that brevity supports, see Using brevity in the Amazon Translate Developer Guide.

Exceptions