Add classify and split document API methods

lib/classify/classifyDocumentBase64.js

@@ -0,0 +1,29 @@
+const Client = require('../client/constructor');
+/**
+ * Classify a document and extract all the fields from it. https://docs.veryfi.com/api/classify/classify-a-document/
+ * @example
+ * veryfi_client.classify_document_from_base64('base64_encoded_string',
+ *                                'receipt.png',
+ *                                {'extra': 'parameters'})
+ *
+ * @memberof Client
+ * @param {String} base64_encoded_string Buffer string of a file to submit for classify extraction
+ * @param {String} file_name The file name including the extension
+ * @param {Object} kwargs Additional request parameters
+ * @returns {JSON} Data extracted from the document
+ */
+Client.prototype.classify_document_from_base64 = async function (
+    base64_encoded_string,
+    file_name,
+    {...kwargs} = {}
+) {
+
+    let endpoint_name = "/classify/";
+    let request_arguments = {
+        "file_name": file_name,
+        "file_data": base64_encoded_string,
+    };
+    request_arguments = Object.assign(request_arguments, kwargs);
+    let document = await this._request("POST", endpoint_name, request_arguments, null, false);
+    return document['data'];
+}

lib/classify/classifyDocumentUrl.js

@@ -0,0 +1,26 @@
+const Client = require('../client/constructor');
+/**
+ * Classify document from url and extract all the fields from it. https://docs.veryfi.com/api/classify/classify-a-document/
+ * @example
+ * veryfi_client.classify_document_from_url('https://cdn.example.com/receipt.jpg')
+ *
+ * @memberof Client
+ * @param {string|null} file_url Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".
+ * @param {Array} file_urls Required if file_url isn't specified. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]
+ * @param {Object} kwargs Additional request parameters
+ * @return {JSON} Data extracted from the document.
+ */
+Client.prototype.classify_document_from_url = async function (
+    file_url = null,
+    file_urls = null,
+    {...kwargs} = {},
+) {
+    let endpoint_name = "/classify/";
+    let request_arguments = {
+        "file_url": file_url,
+        "file_urls": file_urls,
+    };
+    request_arguments = Object.assign(request_arguments, kwargs);
+    let response = await this._request("POST", endpoint_name, request_arguments, null, false);
+    return response['data'];
+}

lib/client/client.js

@@ -27,6 +27,8 @@ require('../checks/processCheck');
 require('../checks/processCheckBase64');
 require('../checks/processCheckStream');
 require('../checks/processCheckUrl');
+require('../classify/classifyDocumentBase64');
+require('../classify/classifyDocumentUrl');
 require('../documents/deleteDocument');
 require('../documents/getDocument');
 require('../documents/getDocuments');
@@ -39,6 +41,10 @@ require('../documents/tags/addTags');
 require('../documents/tags/addTag');
 require('../documents/tags/deleteTags');
 require('../documents/tags/replaceTags');
+require('../split/splitDocumentBase64');
+require('../split/splitDocumentUrl');
+require('../split/getSplitDocument');
+require('../split/getSplitDocuments');
 require('../w2s/deleteW2');
 require('../w2s/getW2');
 require('../w2s/getW2s');

lib/client/getHeaders.js

@@ -8,7 +8,7 @@ const Client = require('../client/constructor');
  */
 Client.prototype._get_headers = function (has_files = false) {
     let final_headers = {
-        "User-Agent": "Node.js Veryfi-Nodejs/1.4.5",
+        "User-Agent": "Node.js Veryfi-Nodejs/1.4.6",
         "Accept": "application/json",
         "Content-Type": "application/json",
         "Client-Id": this.client_id,

lib/split/getSplitDocument.js

@@ -0,0 +1,14 @@
+const Client = require('../client/constructor');
+/**
+ * Veryfi's Get a Documents from PDF endpoint allows you to retrieve a collection of previously processed documents. https://docs.veryfi.com/api/receipts-invoices/get-documents-from-pdf/
+ * @memberof Client
+ * @param {string} document_id ID of the document you'd like to retrieve
+ * @param {Object} kwargs Additional request parameters
+ * @returns {JSON} Data extracted from the Document
+ */
+Client.prototype.get_split_document = async function (document_id,  {...kwargs} = {}) {
+    let endpoint_name = `/documents-set//${document_id}/`;
+    let request_arguments = {"id": document_id};
+    let document = await this._request("GET", endpoint_name, request_arguments, kwargs, false);
+    return document['data'];
+}

lib/split/getSplitDocuments.js

@@ -0,0 +1,25 @@
+const Client = require('../client/constructor');
+/**
+ * Veryfi's Get a Submitted PDF endpoint allows you to retrieve a collection of previously processed documents. https://docs.veryfi.com/api/receipts-invoices/get-submitted-pdf/
+ * @memberof Client
+ * @param {number} page The page number. The response is capped to maximum of 50 results per page.
+ * @param {number} page_size The number of Documents per page.
+ * @param {Object} kwargs Additional request parameters
+ * @returns {JSON} JSON object of previously processed documents
+ */
+Client.prototype.get_split_documents = async function (
+    page = 1,
+    page_size = 50,
+    {...kwargs} = {}
+) {
+    let endpoint_name = "/documents-set/";
+    let request_arguments = {
+        "page": page,
+        "page_size": page_size
+    };
+    let documents = await this._request("GET", endpoint_name, request_arguments, kwargs, false);
+    if ("data" in documents) {
+        documents = documents["data"];
+    }
+    return documents;
+}

lib/split/splitDocumentBase64.js

@@ -0,0 +1,29 @@
+const Client = require('../client/constructor');
+/**
+ * Split document PDF from url and extract all the fields from it. https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/
+ * @example
+ * veryfi_client.split_document_from_base64('base64_encoded_string',
+ *                                'receipt.png',
+ *                                {'extra': 'parameters'})
+ *
+ * @memberof Client
+ * @param {String} base64_encoded_string Buffer string of a file to submit for classify extraction
+ * @param {String} file_name The file name including the extension
+ * @param {Object} kwargs Additional request parameters
+ * @returns {JSON} Data extracted from the document
+ */
+Client.prototype.split_document_from_base64 = async function (
+    base64_encoded_string,
+    file_name,
+    {...kwargs} = {}
+) {
+
+    let endpoint_name = "/documents-set/";
+    let request_arguments = {
+        "file_name": file_name,
+        "file_data": base64_encoded_string,
+    };
+    request_arguments = Object.assign(request_arguments, kwargs);
+    let document = await this._request("POST", endpoint_name, request_arguments, null, false);
+    return document['data'];
+}

lib/split/splitDocumentUrl.js

@@ -0,0 +1,26 @@
+const Client = require('../client/constructor');
+/**
+ * Split document PDF from url and extract all the fields from it. https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/
+ * @example
+ * veryfi_client.split_document_from_url('https://cdn.example.com/receipts.pdf')
+ *
+ * @memberof Client
+ * @param {string|null} file_url Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".
+ * @param {Array} file_urls Required if file_url isn't specified. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]
+ * @param {Object} kwargs Additional request parameters
+ * @return {JSON} Data extracted from the document.
+ */
+Client.prototype.split_document_from_url = async function (
+    file_url = null,
+    file_urls = null,
+    {...kwargs} = {},
+) {
+    let endpoint_name = "/documents-set/";
+    let request_arguments = {
+        "file_url": file_url,
+        "file_urls": file_urls
+    };
+    request_arguments = Object.assign(request_arguments, kwargs);
+    let response = await this._request("POST", endpoint_name, request_arguments, null, false);
+    return response['data'];
+}

lib/types/Client.ts

@@ -45,6 +45,95 @@ export declare class Client {
      */
     public _request(http_verb: String, endpoint_name: String, request_arguments: Object, params: Object, has_files: boolean): Promise<any>;
 
+    /**
+     * Classify a document. https://docs.veryfi.com/api/classify/classify-a-document/
+     * @example
+     * veryfi_client.classify_document_from_base64('base64_encoded_string',
+     *                                'receipt.png',
+     *                                {'extra': 'parameters'})
+     *
+     * @memberof Client
+     * @param {String} base64_encoded_string Buffer string of a file to submit for classify and data extraction
+     * @param {String} file_name The file name including the extension
+     * @param {Object} kwargs Additional request parameters
+     * @returns {JSON} JSON of document classification
+     */
+    public classify_document_from_base64(
+        base64_encoded_string: string,
+        file_name: string,
+        {...kwargs}?: VeryfiExtraArgs
+    ): Promise<JsonObject>;
+
+    /**
+     * Classify document. https://docs.veryfi.com/api/receipts-invoices/process-a-document/
+     * @memberof Client
+     * @param {string} file_url Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. 'https://cdn.example.com/receipt.jpg'.
+     * @param {string[]} file_urls Required if file_url isn't specified. List of publicly accessible URLs to multiple files, e.g. ['https://cdn.example.com/receipt1.jpg', 'https://cdn.example.com/receipt2.jpg']
+     * @param {VeryfiExtraArgs} kwargs Additional request parameters
+     * @returns {JSON} JSON of document classification
+     */
+    public classify_document_from_url(
+        file_url?: string,
+        file_urls?: string[],
+        {...kwargs}?: VeryfiExtraArgs
+    ): Promise<JsonObject>;
+
+    /**
+     * Veryfi's PDF Splitter allows you to split a multipage PDF with different receipts and invoices inside into multiple Documents. This API supports .pdf,.zip. Min file size is 250bytes. The max pdf file size is 50mb. https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/
+     * @memberof Client
+     * @param {string} file_url Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. 'https://cdn.example.com/receipt.jpg'.
+     * @param {string[]} file_urls Required if file_url isn't specified. List of publicly accessible URLs to multiple files, e.g. ['https://cdn.example.com/receipt1.jpg', 'https://cdn.example.com/receipt2.jpg']
+     * @param {VeryfiExtraArgs} kwargs Additional request parameters
+     * @returns {JSON} JSON of document classification
+     */
+    public split_document_from_url(
+        file_url?: string,
+        file_urls?: string[],
+        {...kwargs}?: VeryfiExtraArgs
+    ): Promise<JsonObject>;
+
+    /**
+     * Veryfi's PDF Splitter allows you to split a multipage PDF with different receipts and invoices inside into multiple Documents. This API supports .pdf,.zip. Min file size is 250bytes. The max pdf file size is 50mb. https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/
+     * @example
+     * veryfi_client.split_document_from_base64('base64_encoded_string',
+     *                                'receipt.png',
+     *                                {'extra': 'parameters'})
+     *
+     * @memberof Client
+     * @param {String} base64_encoded_string Buffer string of a file to submit for classify and data extraction
+     * @param {String} file_name The file name including the extension
+     * @param {Object} kwargs Additional request parameters
+     * @returns {JSON} JSON of document classification
+     */
+    public split_document_from_base64(
+        base64_encoded_string: string,
+        file_name: string,
+        {...kwargs}?: VeryfiExtraArgs
+    ): Promise<JsonObject>;
+
+    /**
+     * Veryfi's Get a Documents from PDF endpoint allows you to retrieve a collection of previously processed documents. https://docs.veryfi.com/api/receipts-invoices/get-documents-from-pdf/
+     * @memberof Client
+     * @param {string} document_id ID of the document you'd like to retrieve
+     * @param {Object} kwargs Additional request parameters
+     * @returns {Promise<JsonObject>} Object of data extracted from the document
+     */
+    public get_split_document(document_id: string,
+                        {...kwargs}?: VeryfiExtraArgs): Promise<JsonObject>;
+
+    /**
+     * Veryfi's Get a Submitted PDF endpoint allows you to retrieve a collection of previously processed documents. https://docs.veryfi.com/api/receipts-invoices/get-submitted-pdf/
+     * @memberof Client
+     * @param {number} page The page number. The response is capped to maximum of 50 results per page.
+     * @param {number} page_size The number of Documents per page.
+     * @param {Object} kwargs Additional request parameters
+     * @returns {Promise<JsonObject>} Object of previously processed documents
+     */
+    public get_split_documents(
+        page?: number,
+        page_size?: number,
+        {...kwargs}?: VeryfiExtraArgs
+    ): Promise<JsonObject>;
 
     /**
      * Delete document from Veryfi. https://docs.veryfi.com/api/receipts-invoices/delete-a-document/

mocks/classify.json

@@ -0,0 +1,8 @@
+{
+  "data": {
+    "document_type": {
+      "value": "receipt",
+      "score": 0.97
+    }
+  }
+}

mocks/getSplit.json

@@ -0,0 +1,10 @@
+{
+  "data": {
+    "id": 351609,
+    "documents_id": [
+      337479740,
+      337479769
+    ],
+    "status": "processed"
+  }
+}

mocks/getSplits.json

@@ -0,0 +1,72 @@
+{
+  "data": {
+    "count": 8,
+    "next": "",
+    "previous": "",
+    "results": [
+      {
+        "id": 351628,
+        "documents_id": [
+          337482927
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 351623,
+        "documents_id": [
+          337482669,
+          337482689
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 351622,
+        "documents_id": [
+          337482309,
+          337482338
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 351620,
+        "documents_id": [
+          337481974,
+          337481997
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 351619,
+        "documents_id": [
+          337481287,
+          337481307
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 351609,
+        "documents_id": [
+          337479740,
+          337479769
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 2098,
+        "documents_id": [
+          126516809,
+          126516810
+        ],
+        "status": "processed"
+      },
+      {
+        "id": 2085,
+        "documents_id": [
+          126254495,
+          126254497
+        ],
+        "status": "processed"
+      }
+    ]
+  }
+}

mocks/split.json

@@ -0,0 +1,5 @@
+{
+  "data": {
+    "id": 351609
+  }
+}

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@veryfi/veryfi-sdk",
-  "version": "1.4.5",
+  "version": "1.4.6",
   "description": "Node.js module for communicating with the Veryfi OCR API",
   "main": "lib/client/client.js",
   "typings": "lib/types/Client.ts",