mirror of
https://github.com/hanzoai/azure-sdk-for-js.git
synced 2026-10-30 19:51:51 +00:00
Overhauls tests and samples for Azure Cognitive Services for Language SDKs by implementing safe secret standards: - Updates `test-resources.bicep` to not output API keys nor SAS tokens - Updates the tests to retrieve API keys using the arm client - Updates the tests to create SAS tokens for Storage container access - Updates the samples and snippets to use Entra ID authentication - Fix live tests by enabling SAS access to the persistent storage account Live tests run: https://dev.azure.com/azure-sdk/internal/_build/results?buildId=4694655&view=results
85 lines
2.7 KiB
TypeScript
85 lines
2.7 KiB
TypeScript
// Copyright (c) Microsoft Corporation.
|
|
// Licensed under the MIT License.
|
|
|
|
/**
|
|
* This sample shows how to extract only the basic layout information from a document using the `beginExtractLayout`
|
|
* method. Layout information consists of the arrangement of basic OCR elements, such as pages (including their contents
|
|
* such as lines, words, and selection marks), tables, and text font styles.
|
|
*
|
|
* @summary use the prebuilt layout model to extract basic document elements only
|
|
* @azsdk-skip-javascript
|
|
*/
|
|
|
|
import type { AnalyzeOperationOutput } from "@azure-rest/ai-document-intelligence";
|
|
import DocumentIntelligence, {
|
|
getLongRunningPoller,
|
|
isUnexpected,
|
|
} from "@azure-rest/ai-document-intelligence";
|
|
import { DefaultAzureCredential } from "@azure/identity";
|
|
import "dotenv/config";
|
|
|
|
async function main(): Promise<void> {
|
|
const client = DocumentIntelligence(
|
|
process.env["DOCUMENT_INTELLIGENCE_ENDPOINT"] || "<cognitive services endpoint>",
|
|
new DefaultAzureCredential(),
|
|
);
|
|
|
|
const initialResponse = await client
|
|
.path("/documentModels/{modelId}:analyze", "prebuilt-layout")
|
|
.post({
|
|
contentType: "application/json",
|
|
body: {
|
|
urlSource:
|
|
"https://raw.githubusercontent.com/Azure/azure-sdk-for-js/main/sdk/formrecognizer/ai-form-recognizer/assets/forms/Invoice_1.pdf",
|
|
},
|
|
});
|
|
|
|
if (isUnexpected(initialResponse)) {
|
|
throw initialResponse.body.error;
|
|
}
|
|
|
|
const poller = getLongRunningPoller(client, initialResponse);
|
|
const analyzeResult = ((await poller.pollUntilDone()).body as AnalyzeOperationOutput)
|
|
.analyzeResult;
|
|
|
|
const pages = analyzeResult?.pages;
|
|
const tables = analyzeResult?.tables;
|
|
|
|
if (!pages || pages.length <= 0) {
|
|
console.log("No pages were extracted from the document.");
|
|
} else {
|
|
console.log("Pages:");
|
|
for (const page of pages) {
|
|
console.log("- Page", page.pageNumber, `(unit: ${page.unit})`);
|
|
console.log(` ${page.width}x${page.height}, angle: ${page.angle}`);
|
|
console.log(
|
|
` ${page.lines && page.lines.length} lines, ${page.words && page.words.length} words`,
|
|
);
|
|
|
|
if (page.lines && page.lines.length > 0) {
|
|
console.log(" Lines:");
|
|
|
|
for (const line of page.lines) {
|
|
console.log(` - "${line.content}"`);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
if (!tables || tables.length <= 0) {
|
|
console.log("No tables were extracted from the document.");
|
|
} else {
|
|
console.log("Tables:");
|
|
for (const table of tables) {
|
|
console.log(
|
|
`- Extracted table: ${table.columnCount} columns, ${table.rowCount} rows (${table.cells.length} cells)`,
|
|
);
|
|
}
|
|
}
|
|
}
|
|
|
|
main().catch((error) => {
|
|
console.error("An error occurred:", error);
|
|
process.exit(1);
|
|
});
|