feat(client-textract): This release adds support for specifying and extracting information from documents using the Queries feature within Analyze Document API

Author: awstools

clients/client-textract/src/Textract.ts

@@ -74,11 +74,16 @@ export class Textract extends TextractClient {
    *         All lines and words that are detected in the document are returned (including text that doesn't have a
    *                relationship with the value of <code>FeatureTypes</code>). </p>
    *             </li>
+   *             <li>
+   *                <p>Queries.A QUERIES_RESULT Block object contains the answer to the query, the alias associated and an ID that
+   *             connect it to the query asked. This Block also contains a location and attached confidence score.</p>
+   *             </li>
    *          </ul>
    *
    *          <p>Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in tables.
    *          A SELECTION_ELEMENT <code>Block</code> object contains information about a selection element,
    *          including the selection status.</p>
+   *
    *          <p>You can choose which type of analysis to perform by specifying the <code>FeatureTypes</code> list.
    *       </p>
    *          <p>The output is returned in a list of <code>Block</code> objects.</p>
@@ -165,7 +170,8 @@ export class Textract extends TextractClient {
   /**
    * <p>Analyzes identity documents for relevant information. This information is extracted
    *          and returned as <code>IdentityDocumentFields</code>, which records both the normalized
-   *          field and value of the extracted text.</p>
+   *          field and value of the extracted text.Unlike other Amazon Textract operations, <code>AnalyzeID</code>
+   *       doesn't return any Geometry data.</p>
    */
   public analyzeID(args: AnalyzeIDCommandInput, options?: __HttpHandlerOptions): Promise<AnalyzeIDCommandOutput>;
   public analyzeID(args: AnalyzeIDCommandInput, cb: (err: any, data?: AnalyzeIDCommandOutput) => void): void;
@@ -192,7 +198,7 @@ export class Textract extends TextractClient {
 
   /**
    * <p>Detects text in the input document. Amazon Textract can detect lines of text and the
-   *          words that make up a line of text. The input document must be an image in JPEG or PNG
+   *          words that make up a line of text. The input document must be an image in JPEG, PNG, PDF, or TIFF
    *          format. <code>DetectDocumentText</code> returns the detected text in an array of <a>Block</a> objects. </p>
    *          <p>Each document page has as an associated <code>Block</code> of type PAGE. Each PAGE <code>Block</code> object
    *          is the parent of LINE <code>Block</code> objects that represent the lines of detected text on a page. A LINE <code>Block</code> object is
@@ -262,14 +268,17 @@ export class Textract extends TextractClient {
    *             relationship with the value of the <code>StartDocumentAnalysis</code>
    *                   <code>FeatureTypes</code> input parameter). </p>
    *             </li>
+   *             <li>
+   *                <p>Queries. A QUERIES_RESULT Block object contains the answer to the query, the alias associated and an ID that
+   *             connect it to the query asked. This Block also contains a location and attached confidence score</p>
+   *             </li>
    *          </ul>
    *
    *          <p>Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in tables.
    *          A SELECTION_ELEMENT <code>Block</code> object contains information about a selection element,
    *          including the selection status.</p>
    *
    *
-   *
    *          <p>Use the <code>MaxResults</code> parameter to limit the number of blocks that are
    *          returned. If there are more results than specified in <code>MaxResults</code>, the value of
    *             <code>NextToken</code> in the operation response contains a pagination token for getting

clients/client-textract/src/commands/AnalyzeDocumentCommand.ts

@@ -41,11 +41,16 @@ export interface AnalyzeDocumentCommandOutput extends AnalyzeDocumentResponse, _
  *         All lines and words that are detected in the document are returned (including text that doesn't have a
  *                relationship with the value of <code>FeatureTypes</code>). </p>
  *             </li>
+ *             <li>
+ *                <p>Queries.A QUERIES_RESULT Block object contains the answer to the query, the alias associated and an ID that
+ *             connect it to the query asked. This Block also contains a location and attached confidence score.</p>
+ *             </li>
  *          </ul>
  *
  *          <p>Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in tables.
  *          A SELECTION_ELEMENT <code>Block</code> object contains information about a selection element,
  *          including the selection status.</p>
+ *
  *          <p>You can choose which type of analysis to perform by specifying the <code>FeatureTypes</code> list.
  *       </p>
  *          <p>The output is returned in a list of <code>Block</code> objects.</p>

clients/client-textract/src/commands/AnalyzeIDCommand.ts

@@ -21,7 +21,8 @@ export interface AnalyzeIDCommandOutput extends AnalyzeIDResponse, __MetadataBea
 /**
  * <p>Analyzes identity documents for relevant information. This information is extracted
  *          and returned as <code>IdentityDocumentFields</code>, which records both the normalized
- *          field and value of the extracted text.</p>
+ *          field and value of the extracted text.Unlike other Amazon Textract operations, <code>AnalyzeID</code>
+ *       doesn't return any Geometry data.</p>
  * @example
  * Use a bare-bones client and the command you need to make an API call.
  * ```javascript

clients/client-textract/src/commands/DetectDocumentTextCommand.ts

@@ -23,7 +23,7 @@ export interface DetectDocumentTextCommandOutput extends DetectDocumentTextRespo
 
 /**
  * <p>Detects text in the input document. Amazon Textract can detect lines of text and the
- *          words that make up a line of text. The input document must be an image in JPEG or PNG
+ *          words that make up a line of text. The input document must be an image in JPEG, PNG, PDF, or TIFF
  *          format. <code>DetectDocumentText</code> returns the detected text in an array of <a>Block</a> objects. </p>
  *          <p>Each document page has as an associated <code>Block</code> of type PAGE. Each PAGE <code>Block</code> object
  *          is the parent of LINE <code>Block</code> objects that represent the lines of detected text on a page. A LINE <code>Block</code> object is

clients/client-textract/src/commands/GetDocumentAnalysisCommand.ts

@@ -51,14 +51,17 @@ export interface GetDocumentAnalysisCommandOutput extends GetDocumentAnalysisRes
  *             relationship with the value of the <code>StartDocumentAnalysis</code>
  *                   <code>FeatureTypes</code> input parameter). </p>
  *             </li>
+ *             <li>
+ *                <p>Queries. A QUERIES_RESULT Block object contains the answer to the query, the alias associated and an ID that
+ *             connect it to the query asked. This Block also contains a location and attached confidence score</p>
+ *             </li>
  *          </ul>
  *
  *          <p>Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in tables.
  *          A SELECTION_ELEMENT <code>Block</code> object contains information about a selection element,
  *          including the selection status.</p>
  *
  *
- *
  *          <p>Use the <code>MaxResults</code> parameter to limit the number of blocks that are
  *          returned. If there are more results than specified in <code>MaxResults</code>, the value of
  *             <code>NextToken</code> in the operation response contains a pagination token for getting

clients/client-textract/src/models/models_0.ts

@@ -114,6 +114,7 @@ export namespace Document {
 
 export enum FeatureType {
   FORMS = "FORMS",
+  QUERIES = "QUERIES",
   TABLES = "TABLES",
 }
 
@@ -174,11 +175,79 @@ export namespace HumanLoopConfig {
   });
 }
 
+/**
+ * <p>Each query contains the question you want to ask in the Text and the alias you want to associate.</p>
+ */
+export interface Query {
+  /**
+   * <p>Question that Amazon Textract will apply to the document. An example would be "What is the customer's SSN?"</p>
+   */
+  Text: string | undefined;
+
+  /**
+   * <p>Alias attached to the query, for ease of location.</p>
+   */
+  Alias?: string;
+
+  /**
+   * <p>List of pages associated with the query. The following is a list of rules for using this parameter.</p>
+   *          <ul>
+   *             <li>
+   *                <p>If a page is not specified, it is set to <code>["1"]</code> by default.</p>
+   *             </li>
+   *             <li>
+   *                <p>The following characters are allowed in the parameter's string:
+   *                <code>0 1 2 3 4 5 6 7 8 9 - *</code>. No whitespace is allowed.</p>
+   *             </li>
+   *             <li>
+   *                <p>When using <code>*</code> to indicate all pages, it must be the only element
+   *                in the string.</p>
+   *             </li>
+   *             <li>
+   *                <p>You can use page intervals, such as <code>[“1-3”, “1-1”, “4-*”]</code>. Where <code>*</code> indicates last page of
+   *                document.</p>
+   *             </li>
+   *             <li>
+   *                <p>Specified pages must be greater than 0 and less than or equal to the number of pages in the document.</p>
+   *             </li>
+   *          </ul>
+   */
+  Pages?: string[];
+}
+
+export namespace Query {
+  /**
+   * @internal
+   */
+  export const filterSensitiveLog = (obj: Query): any => ({
+    ...obj,
+  });
+}
+
+/**
+ * <p></p>
+ */
+export interface QueriesConfig {
+  /**
+   * <p></p>
+   */
+  Queries: Query[] | undefined;
+}
+
+export namespace QueriesConfig {
+  /**
+   * @internal
+   */
+  export const filterSensitiveLog = (obj: QueriesConfig): any => ({
+    ...obj,
+  });
+}
+
 export interface AnalyzeDocumentRequest {
   /**
    * <p>The input document as base64-encoded bytes or an Amazon S3 object. If you use the AWS CLI
    *          to call Amazon Textract operations, you can't pass image bytes. The document must be an image
-   *          in JPEG or PNG format.</p>
+   *          in JPEG, PNG, PDF, or TIFF format.</p>
    *          <p>If you're using an AWS SDK to call Amazon Textract, you might not need to base64-encode
    *          image bytes that are passed using the <code>Bytes</code> field. </p>
    */
@@ -197,6 +266,11 @@ export interface AnalyzeDocumentRequest {
    * <p>Sets the configuration for the human in the loop workflow for analyzing documents.</p>
    */
   HumanLoopConfig?: HumanLoopConfig;
+
+  /**
+   * <p>Contains Queries and the alias for those Queries, as determined by the input. </p>
+   */
+  QueriesConfig?: QueriesConfig;
 }
 
 export namespace AnalyzeDocumentRequest {
@@ -214,6 +288,8 @@ export enum BlockType {
   LINE = "LINE",
   MERGED_CELL = "MERGED_CELL",
   PAGE = "PAGE",
+  QUERY = "QUERY",
+  QUERY_RESULT = "QUERY_RESULT",
   SELECTION_ELEMENT = "SELECTION_ELEMENT",
   TABLE = "TABLE",
   TITLE = "TITLE",
@@ -334,6 +410,7 @@ export namespace Geometry {
 }
 
 export enum RelationshipType {
+  ANSWER = "ANSWER",
   CHILD = "CHILD",
   COMPLEX_FEATURES = "COMPLEX_FEATURES",
   MERGED_CELL = "MERGED_CELL",
@@ -463,6 +540,17 @@ export interface Block {
    *                value of <code>SelectionStatus</code> to determine the status of the selection
    *                element.</p>
    *             </li>
+   *             <li>
+   *                <p>
+   *                   <i>QUERY</i> - A question asked during the call of AnalyzeDocument. Contains an
+   *                alias and an ID that attachs it to its answer.</p>
+   *             </li>
+   *             <li>
+   *                <p>
+   *                   <i>QUERY_RESULT</i> - A response to a question asked during the call
+   *                of analyze document. Comes with an alias and ID for ease of locating in a
+   *                response. Also contains location and confidence score.</p>
+   *             </li>
    *          </ul>
    */
   BlockType?: BlockType | string;
@@ -574,6 +662,11 @@ export interface Block {
    *          considered to be a single-page document.</p>
    */
   Page?: number;
+
+  /**
+   * <p></p>
+   */
+  Query?: Query;
 }
 
 export namespace Block {
@@ -880,8 +973,8 @@ export class ThrottlingException extends __BaseException {
 }
 
 /**
- * <p>The format of the input document isn't supported. Documents for synchronous operations can be in
- *          PNG or JPEG format only. Documents for asynchronous operations can be in PDF format.</p>
+ * <p>The format of the input document isn't supported. Documents for operations can be in
+ *          PNG, JPEG, PDF, or TIFF format.</p>
  */
 export class UnsupportedDocumentException extends __BaseException {
   readonly name: "UnsupportedDocumentException" = "UnsupportedDocumentException";
@@ -1826,6 +1919,11 @@ export interface StartDocumentAnalysisRequest {
    *          be encrypted server side,using SSE-S3.</p>
    */
   KMSKeyId?: string;
+
+  /**
+   * <p></p>
+   */
+  QueriesConfig?: QueriesConfig;
 }
 
 export namespace StartDocumentAnalysisRequest {

clients/client-textract/src/protocols/Aws_json1_1.ts

@@ -90,6 +90,8 @@ import {
   OutputConfig,
   Point,
   ProvisionedThroughputExceededException,
+  QueriesConfig,
+  Query,
   Relationship,
   S3Object,
   StartDocumentAnalysisRequest,
@@ -1117,6 +1119,10 @@ const serializeAws_json1_1AnalyzeDocumentRequest = (input: AnalyzeDocumentReques
       input.HumanLoopConfig !== null && {
         HumanLoopConfig: serializeAws_json1_1HumanLoopConfig(input.HumanLoopConfig, context),
       }),
+    ...(input.QueriesConfig !== undefined &&
+      input.QueriesConfig !== null && {
+        QueriesConfig: serializeAws_json1_1QueriesConfig(input.QueriesConfig, context),
+      }),
   };
 };
 
@@ -1265,6 +1271,44 @@ const serializeAws_json1_1OutputConfig = (input: OutputConfig, context: __SerdeC
   };
 };
 
+const serializeAws_json1_1Queries = (input: Query[], context: __SerdeContext): any => {
+  return input
+    .filter((e: any) => e != null)
+    .map((entry) => {
+      if (entry === null) {
+        return null as any;
+      }
+      return serializeAws_json1_1Query(entry, context);
+    });
+};
+
+const serializeAws_json1_1QueriesConfig = (input: QueriesConfig, context: __SerdeContext): any => {
+  return {
+    ...(input.Queries !== undefined &&
+      input.Queries !== null && { Queries: serializeAws_json1_1Queries(input.Queries, context) }),
+  };
+};
+
+const serializeAws_json1_1Query = (input: Query, context: __SerdeContext): any => {
+  return {
+    ...(input.Alias !== undefined && input.Alias !== null && { Alias: input.Alias }),
+    ...(input.Pages !== undefined &&
+      input.Pages !== null && { Pages: serializeAws_json1_1QueryPages(input.Pages, context) }),
+    ...(input.Text !== undefined && input.Text !== null && { Text: input.Text }),
+  };
+};
+
+const serializeAws_json1_1QueryPages = (input: string[], context: __SerdeContext): any => {
+  return input
+    .filter((e: any) => e != null)
+    .map((entry) => {
+      if (entry === null) {
+        return null as any;
+      }
+      return entry;
+    });
+};
+
 const serializeAws_json1_1S3Object = (input: S3Object, context: __SerdeContext): any => {
   return {
     ...(input.Bucket !== undefined && input.Bucket !== null && { Bucket: input.Bucket }),
@@ -1294,6 +1338,10 @@ const serializeAws_json1_1StartDocumentAnalysisRequest = (
       }),
     ...(input.OutputConfig !== undefined &&
       input.OutputConfig !== null && { OutputConfig: serializeAws_json1_1OutputConfig(input.OutputConfig, context) }),
+    ...(input.QueriesConfig !== undefined &&
+      input.QueriesConfig !== null && {
+        QueriesConfig: serializeAws_json1_1QueriesConfig(input.QueriesConfig, context),
+      }),
   };
 };
 
@@ -1430,6 +1478,10 @@ const deserializeAws_json1_1Block = (output: any, context: __SerdeContext): Bloc
         : undefined,
     Id: __expectString(output.Id),
     Page: __expectInt32(output.Page),
+    Query:
+      output.Query !== undefined && output.Query !== null
+        ? deserializeAws_json1_1Query(output.Query, context)
+        : undefined,
     Relationships:
       output.Relationships !== undefined && output.Relationships !== null
         ? deserializeAws_json1_1RelationshipList(output.Relationships, context)
@@ -1921,6 +1973,29 @@ const deserializeAws_json1_1ProvisionedThroughputExceededException = (
   } as any;
 };
 
+const deserializeAws_json1_1Query = (output: any, context: __SerdeContext): Query => {
+  return {
+    Alias: __expectString(output.Alias),
+    Pages:
+      output.Pages !== undefined && output.Pages !== null
+        ? deserializeAws_json1_1QueryPages(output.Pages, context)
+        : undefined,
+    Text: __expectString(output.Text),
+  } as any;
+};
+
+const deserializeAws_json1_1QueryPages = (output: any, context: __SerdeContext): string[] => {
+  const retVal = (output || [])
+    .filter((e: any) => e != null)
+    .map((entry: any) => {
+      if (entry === null) {
+        return null as any;
+      }
+      return __expectString(entry) as any;
+    });
+  return retVal;
+};
+
 const deserializeAws_json1_1Relationship = (output: any, context: __SerdeContext): Relationship => {
   return {
     Ids: