[Ai-written] Reading local spreadsheet

take target language as a command line argument

using google translate

improve command line

refactor

Author: hatton

.gitignore

@@ -0,0 +1,177 @@
+# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
+
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Caches
+
+.cache
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+# IntelliJ based IDEs
+.idea
+
+# Finder (MacOS) folder config
+.DS_Store
+
+*.xlsx

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+    "editor.formatOnSave": true,
+    "editor.defaultFormatter": "vscode.typescript-language-features"
+}

bun.lockb

@@ -0,0 +1,123 @@
+#!/usr/bin/env bun
+import * as XLSX from 'xlsx';
+import { unlink } from 'node:fs/promises';
+import { existsSync } from 'node:fs';
+import { translateToLanguage } from './translate';
+import { Command } from 'commander';
+import { createRequire } from 'module';
+import { resolve, basename, dirname } from 'node:path';
+
+const require = createRequire(import.meta.url);
+const { version } = require('./package.json');
+
+interface Row {
+    "[en]": string;
+    [key: string]: any;
+}
+
+async function main() {
+    const program = new Command();
+
+    program
+        .name('bloom-translate-spreadsheet')
+        .description('Translates Bloom spreadsheet content to different languages')
+        .argument('<inputPath>', 'Input Excel file path')
+        .option('-o, --output <path>', 'Output Excel file path (default: {input-filename}-{language}.xlsx)')
+        .option('--target <tag>', 'BCP47 language code with model. If this is not provided, the program will look in the input spreadsheet for things columns translate. If it is specified, then the program will either add or re-use a column with the give tag. Example: fr-x-ai-gt would add or reuse a French column translated with Google Translate)', 'fr-x-ai-gt')
+        .option('--retranslate', 'If this is provided, then columns will be replaced if they already exist. Otherwise, the program will not re-translate.')
+        .version(version)
+        .addHelpText('after', `
+Example:
+  $ bloom-translate-spreadsheet foo.xlsx
+  $ bloom-translate-spreadsheet foo.xlsx --target es-x-ai-gt -o foo-with-spanish.xlsx
+  $ bloom-translate-spreadsheet foo.xlsx --target fr-x-ai-gt --retranslate`);
+
+    program.parse();
+
+    const options = program.opts();
+    const targetLangAndModel = options.target;
+    const shouldRetranslate = options.retranslate;
+    const inputPath = resolve(program.args[0]);
+    const sheetName = "BloomBook";
+
+    // The column name should be the full language code including the model
+    const columnName = `[${targetLangAndModel}]`;
+
+    // Generate default output path in the current directory
+    const inputBasename = basename(inputPath);
+    const defaultOutputPath = resolve(process.cwd(), inputBasename.replace(/\.xlsx$/, `-${targetLangAndModel}.xlsx`));
+    const outputPath = options.output ? resolve(options.output) : defaultOutputPath;
+
+    if (!existsSync(inputPath)) {
+        console.error(`Input file not found: ${inputPath}`);
+        process.exit(1);
+    }
+
+    // Delete existing file if it exists
+    if (existsSync(outputPath)) {
+        await unlink(outputPath);
+    }
+
+    // Read the Excel file
+    const workbook = XLSX.readFile(inputPath);
+
+    // Verify the sheet exists
+    if (!workbook.SheetNames.includes(sheetName)) {
+        console.error(`Sheet "${sheetName}" not found in workbook. Available sheets: ${workbook.SheetNames.join(', ')}`);
+        process.exit(1);
+    }
+
+    const sheet = workbook.Sheets[sheetName];
+
+    // Convert the sheet to JSON
+    const inputSheet = XLSX.utils.sheet_to_json<Row>(sheet);
+
+    // Get current headers from the first row
+    const headers = Object.keys(inputSheet[0] || {});
+
+    // if shouldRetranslate is false and the column is already there, print something and quit
+    if (!shouldRetranslate && headers.includes(columnName)) {
+        console.error(`Column ${columnName} already exists in the spreadsheet. Use --retranslate flag to overwrite.`);
+        process.exit(1);
+    }
+
+    // Find the position of [en] column and create new header array
+    const enIndex = headers.indexOf('[en]');
+    const newHeaders = [...headers];
+
+    // If we don't yet have a column for the target language and model, insert it right after the [en] column.
+    if (enIndex !== -1 && !headers.includes(columnName)) {
+        newHeaders.splice(enIndex + 1, 0, columnName);
+    }
+
+    // Create translations for texts
+    const textsToTranslate = inputSheet
+        .map(row => row['[en]'])
+        .filter(text => text); // Filter out any undefined or empty strings
+
+    const translations = await translateToLanguage(textsToTranslate, targetLangAndModel);
+
+    // Map the translations back to the rows
+    let translationIndex = 0;
+    for (const row of inputSheet) {
+        if (row['[en]']) {
+            row[columnName] = translations[translationIndex++];
+        }
+    }
+
+    // Create a new workbook
+    const newWorkbook = XLSX.utils.book_new();
+
+    // Convert back to sheet with the correct column order
+    const newSheet = XLSX.utils.json_to_sheet(inputSheet, {
+        header: newHeaders
+    });
+
+    XLSX.utils.book_append_sheet(newWorkbook, newSheet, "BloomBook");
+
+    // Write to file
+    XLSX.writeFile(newWorkbook, outputPath);
+    console.log(`Translated spreadsheet saved to: ${outputPath}`);
+}
+
+main().catch(console.error);

index.ts

@@ -0,0 +1,20 @@
+{
+  "name": "bloom-translate-spreadsheet",
+  "version": "0.0.1",
+  "module": "index.ts",
+  "type": "module",
+  "scripts": {
+    "start": "bun run index.ts"
+  },
+  "devDependencies": {
+    "@types/bun": "latest"
+  },
+  "peerDependencies": {
+    "typescript": "^5.0.0"
+  },
+  "dependencies": {
+    "@google-cloud/translate": "^8.5.0",
+    "commander": "^13.1.0",
+    "xlsx": "^0.18.5"
+  }
+}

package-lock.json

@@ -0,0 +1,26 @@
+import { v2 } from '@google-cloud/translate';
+
+// targetLang: language code that normally ends in a private use subtag of
+// the form "-x-ai-model" where "model" tells us which translation model to use/was used.
+export async function translateWithGoogleTranslate(
+    englishTexts: string[],
+    targetLang: string,
+    serviceAccountEmail: string,
+    serviceAccountPrivateKey: string
+): Promise<string[]> {
+    const translate = new v2.Translate({
+        credentials: {
+            client_email: serviceAccountEmail,
+            private_key: serviceAccountPrivateKey
+        }
+    });
+    try {
+        const [translations] = await translate.translate(englishTexts, targetLang);
+        return Array.isArray(translations)
+            ? translations
+            : [translations];
+    } catch (error) {
+        console.error('Translation error:', error);
+        throw error;
+    }
+}

package.json

@@ -0,0 +1,38 @@
+import { v2 } from '@google-cloud/translate';
+import { translateWithGoogleTranslate } from './src/googleTranslate';
+
+type TranslationModel = 'gt' | 'acts2';
+
+
+export function parseModelFromLanguageCode(langCode: string): TranslationModel | null {
+    if (langCode.includes('-acts2')) return 'acts2';
+    if (langCode.includes('-gt')) return 'gt';
+    return null;
+}
+
+export async function translateToLanguage(englishTexts: string[], targetCode: string): Promise<string[]> {
+    const model = parseModelFromLanguageCode(targetCode);
+
+    if (model === 'gt') {
+        if (!process.env.BLOOM_GOOGLE_TRANSLATION_SERVICE_ACCOUNT_EMAIL) {
+            throw new Error('Translating with Google requires the environment variables: BLOOM_GOOGLE_TRANSLATION_SERVICE_ACCOUNT_EMAIL. After setting it (and also BLOOM_GOOGLE_SERVICE_PRIVATE_KEY), you may have to restart your terminal.');
+        }
+        if (!process.env.BLOOM_GOOGLE_TRANSLATION_SERVICE_PRIVATE_KEY) {
+            throw new Error('Translating with Google requires the environment variables: BLOOM_GOOGLE_TRANSLATION_SERVICE_PRIVATE_KEY. After setting it (and also BLOOM_GOOGLE_SERVICE_ACCOUNT_EMAIL), you may have to restart your terminal.');
+        }
+
+        return await translateWithGoogleTranslate(englishTexts, targetCode.split('-x-')[0], process.env.BLOOM_GOOGLE_TRANSLATION_SERVICE_ACCOUNT_EMAIL, process.env.BLOOM_GOOGLE_TRANSLATION_SERVICE_PRIVATE_KEY.replace(
+            /\\n/g,
+            "\n"
+        ));
+    }
+    if (model === 'acts2') {
+        return englishTexts.map(text => `[Acts2 pretend] ${text}`);
+    }
+    if (model === 'piglatin') {
+        return englishTexts.map(text => text.split(' ').map(word => `${word.slice(1)}${word[0]}ay`).join(' '));
+    }
+    else {
+        throw new Error('Unknown translation model ${model}');
+    }
+}

src/googleTranslate.ts

@@ -0,0 +1,27 @@
+{
+  "compilerOptions": {
+    // Enable latest features
+    "lib": ["ESNext", "DOM"],
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleDetection": "force",
+    "jsx": "react-jsx",
+    "allowJs": true,
+
+    // Bundler mode
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "verbatimModuleSyntax": true,
+    "noEmit": true,
+
+    // Best practices
+    "strict": true,
+    "skipLibCheck": true,
+    "noFallthroughCasesInSwitch": true,
+
+    // Some stricter flags (disabled by default)
+    "noUnusedLocals": false,
+    "noUnusedParameters": false,
+    "noPropertyAccessFromIndexSignature": false
+  }
+}