From eb8675ff1cf63de56bb858305fc927ee51b514d7 Mon Sep 17 00:00:00 2001 From: Eric Schmidt Date: Thu, 26 Mar 2020 11:10:13 -0700 Subject: [PATCH] chore: removes unneeded samples (#25) --- document-ai/snippets/parseForm.js | 135 ---------------------------- document-ai/snippets/parseTable.js | 140 ----------------------------- 2 files changed, 275 deletions(-) delete mode 100644 document-ai/snippets/parseForm.js delete mode 100644 document-ai/snippets/parseTable.js diff --git a/document-ai/snippets/parseForm.js b/document-ai/snippets/parseForm.js deleted file mode 100644 index c23cf37eae7..00000000000 --- a/document-ai/snippets/parseForm.js +++ /dev/null @@ -1,135 +0,0 @@ -/** - * Copyright 2020 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 - * - * http://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. - */ - -'use strict'; - -const uuid = require('uuid'); - -async function main( - projectId = 'YOUR_PROJECT_ID', - gcsOutputUri = 'output-bucket', - gcsOutputUriPrefix = uuid.v4(), - gcsInputUri = 'gs://cloud-samples-data/documentai/invoice.pdf' -) { - // [START document_parse_form] - /** - * TODO(developer): Uncomment these variables before running the sample. - */ - // const projectId = 'YOUR_PROJECT_ID'; - // const gcsOutputUri = 'YOUR_STORAGE_BUCKET'; - // const gcsOutputUriPrefix = 'YOUR_STORAGE_PREFIX'; - - // Imports the Google Cloud client library - const { - DocumentUnderstandingServiceClient, - } = require('@google-cloud/documentai'); - const {Storage} = require('@google-cloud/storage'); - - const client = new DocumentUnderstandingServiceClient(); - const storage = new Storage(); - - async function parseFormGCS(inputUri, outputUri, outputUriPrefix) { - // Configure the batch process request. - const request = { - inputConfig: { - gcsSource: { - uri: inputUri, - }, - mimeType: 'application/pdf', - }, - outputConfig: { - gcsDestination: { - uri: `${outputUri}${outputUriPrefix}`, - }, - pagesPerShard: 1, - }, - formExtractionParams: { - enabled: true, - keyValuePairHints: [ - { - key: 'Phone', - valueTypes: ['PHONE_NUMBER'], - }, - { - key: 'Contact', - valueTypes: ['EMAIL', 'NAME'], - }, - ], - }, - }; - - // Configure the request for batch process - const requests = { - parent: `projects/${projectId}/locations/us-central1`, - requests: [request], - }; - - // Batch process document using a long-running operation. - // You can wait for now, or get results later. - const [operation] = await client.batchProcessDocuments(requests); - - // Wait for operation to complete. - await operation.promise(); - - console.log('Document processing complete.'); - - // Query Storage bucket for the results file(s). - const query = { - prefix: outputUriPrefix, - }; - - console.log('Fetching results ...'); - - // List all of the files in the Storage bucket - const [files] = await storage.bucket(gcsOutputUri).getFiles(query); - - files.forEach(async (fileInfo, index) => { - // Get the file as a buffer - const [file] = await fileInfo.download(); - - console.log(`Fetched file #${index + 1}:`); - - // Read the results - const results = JSON.parse(file.toString()); - - // Get all of the document text as one big string. - const text = results.text; - - // Utility to extract text anchors from text field. - const getText = textAnchor => { - const startIndex = textAnchor.textSegments[0].startIndex || 0; - const endIndex = textAnchor.textSegments[0].endIndex; - - return `\t${text.substring(startIndex, endIndex)}`; - }; - - // Process the output - const [page1] = results.pages; - const formFields = page1.formFields; - - formFields.forEach(field => { - const fieldName = getText(field.fieldName.textAnchor); - const fieldValue = getText(field.fieldValue.textAnchor); - - console.log('Extracted key value pair:'); - console.log(`\t(${fieldName}, ${fieldValue})`); - }); - }); - } - // [END document_parse_form] - - parseFormGCS(gcsInputUri, gcsOutputUri, gcsOutputUriPrefix); -} -main(...process.argv.slice(2)); diff --git a/document-ai/snippets/parseTable.js b/document-ai/snippets/parseTable.js deleted file mode 100644 index d5a72369add..00000000000 --- a/document-ai/snippets/parseTable.js +++ /dev/null @@ -1,140 +0,0 @@ -/** - * Copyright 2020 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 - * - * http://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. - */ - -'use strict'; - -const uuid = require('uuid'); - -async function main( - projectId = 'YOUR_PROJECT_ID', - gcsOutputUri = 'output-bucket', - gcsOutputUriPrefix = uuid.v4(), - gcsInputUri = 'gs://cloud-samples-data/documentai/invoice.pdf' -) { - // [START document_parse_table] - /** - * TODO(developer): Uncomment these variables before running the sample. - */ - // const projectId = 'YOUR_PROJECT_ID'; - // const gcsOutputUri = 'YOUR_STORAGE_BUCKET'; - // const gcsOutputUriPrefix = 'YOUR_STORAGE_PREFIX'; - - // Imports the Google Cloud client library - const { - DocumentUnderstandingServiceClient, - } = require('@google-cloud/documentai'); - const {Storage} = require('@google-cloud/storage'); - - const client = new DocumentUnderstandingServiceClient(); - const storage = new Storage(); - - async function parseTableGCS(inputUri, outputUri, outputUriPrefix) { - // Configure the batch process request. - const request = { - inputConfig: { - gcsSource: { - uri: inputUri, - }, - mimeType: 'application/pdf', - }, - outputConfig: { - gcsDestination: { - uri: `${outputUri}${outputUriPrefix}`, - }, - pagesPerShard: 1, - }, - tableExtractionParams: { - enabled: true, - tableBoundHints: [ - { - boundingBox: { - normalizedVertices: [ - {x: 0, y: 0}, - {x: 1, y: 0}, - {x: 1, y: 1}, - {x: 0, y: 1}, - ], - }, - }, - ], - }, - }; - - // Configure the request for batch process - const requests = { - parent: `projects/${projectId}/locations/us-central1`, - requests: [request], - }; - - // Batch process document using a long-running operation. - // You can wait for now, or get results later. - const [operation] = await client.batchProcessDocuments(requests); - - // Wait for operation to complete. - await operation.promise(); - - console.log('Document processing complete.'); - - // Query Storage bucket for the results file(s). - const query = { - prefix: outputUriPrefix, - }; - - console.log('Fetching results ...'); - - // List all of the files in the Storage bucket - const [files] = await storage.bucket(gcsOutputUri).getFiles(query); - - files.forEach(async (fileInfo, index) => { - // Get the file as a buffer - const [file] = await fileInfo.download(); - - console.log(`Fetched file #${index + 1}:`); - - // Read the results - const results = JSON.parse(file.toString()); - - // Get all of the document text as one big string - const text = results.text; - - // Get the first table in the document - const [page1] = results.pages; - const [table] = page1.tables; - const [headerRow] = table.headerRows; - - console.log('Results from first table processed:'); - console.log( - `First detected language: ${page1.detectedLanguages[0].languageCode}` - ); - - console.log('Header row:'); - headerRow.cells.forEach(tableCell => { - if (tableCell.layout.textAnchor.textSegments) { - // Extract shards from the text field - // First shard in document doesn't have startIndex property - const startIndex = - tableCell.layout.textAnchor.textSegments[0].startIndex || 0; - const endIndex = tableCell.layout.textAnchor.textSegments[0].endIndex; - - console.log(`\t${text.substring(startIndex, endIndex)}`); - } - }); - }); - } - // [END document_parse_table] - - parseTableGCS(gcsInputUri, gcsOutputUri, gcsOutputUriPrefix); -} -main(...process.argv.slice(2));