Initial commit
This commit is contained in:
@@ -0,0 +1,299 @@
|
||||
const ExcelJS = require('exceljs');
|
||||
const { PDFParse } = require('pdf-parse');
|
||||
const { PDFDocument } = require('pdf-lib');
|
||||
const readline = require('node:readline/promises');
|
||||
const { stdin: input, stdout: output } = require('node:process');
|
||||
const fs = require('fs');
|
||||
const os = require('os');
|
||||
const path = require('path');
|
||||
const sfdc = require('./sfdc2');
|
||||
require('dotenv').config();
|
||||
let excelFile = process.argv[2];
|
||||
let pdfFile = process.argv[3];
|
||||
// excel1 => /Users/ddatinguinoo/Downloads/Estratto IPP 5 Sic.xlsx
|
||||
// excel2 => /Users/ddatinguinoo/Downloads/Estratto Haccp IPP 5 (1).xlsx
|
||||
// pdf1 => /Users/ddatinguinoo/Downloads/G-S IPP 5.pdf
|
||||
// pdf2 => /Users/ddatinguinoo/Downloads/H IPP 5.pdf
|
||||
const data = []; // contains the info of all the clients
|
||||
const tempFilePath = [];
|
||||
|
||||
const authConfig = {
|
||||
sfdcTokenFile: process.env.SFDC_TOKEN_FILE, // Path to store/retrieve OAuth tokens
|
||||
sfdcClientId: process.env.SFDC_CLIENT_ID,
|
||||
sfdcClientSecret: process.env.SFDC_CLIENT_SECRET
|
||||
};
|
||||
|
||||
async function initializeSalesforceConnection() {
|
||||
// sfdc.setProductionBaseUrl(); // or sfdc.setSandboxBaseUrl();
|
||||
sfdc.setSandboxBaseUrl(); // Example: using sandbox
|
||||
sfdc.setTokenFile(authConfig.sfdcTokenFile);
|
||||
sfdc.setClientId(authConfig.sfdcClientId);
|
||||
sfdc.setClientSecret(authConfig.sfdcClientSecret);
|
||||
|
||||
// Try to load existing token or initiate OAuth flow
|
||||
if (!await sfdc.getSalesforceToken()) {
|
||||
console.log('No token found. Initiating OAuth2 flow...');
|
||||
// For command-line scripts where a browser can be opened:
|
||||
await sfdc.initToken((loginUrl) => {
|
||||
console.log(`Please open this URL to authenticate: ${loginUrl}`);
|
||||
});
|
||||
} else {
|
||||
console.log('Token loaded successfully.');
|
||||
}
|
||||
// Ensure the access token is valid and refresh if necessary
|
||||
await sfdc.checkToken();
|
||||
console.log('Salesforce connection is ready.');
|
||||
}
|
||||
|
||||
async function attachPdfToAccount(sfdc) {
|
||||
let parser;
|
||||
try {
|
||||
let contentVersion;
|
||||
for (let i = 0; i < tempFilePath.length; i++) {
|
||||
// 1. Read the local PDF file and convert it to Base64
|
||||
const pdfBuffer = fs.readFileSync(tempFilePath[i]); // pdfFilePath is tempFilePath
|
||||
const base64Pdf = pdfBuffer.toString('base64');
|
||||
parser = new PDFParse({ data: pdfBuffer });
|
||||
try {
|
||||
const result = await parser.getText();
|
||||
let conditions = [];
|
||||
|
||||
const userID = result.text.match(/Codice fiscale:\s*([A-Za-z0-9]+)/i);
|
||||
const codiceFiscale = userID ? userID[1].trim() : null;
|
||||
if (codiceFiscale) {
|
||||
conditions.push(`CF__c='${ codiceFiscale }'`);
|
||||
}
|
||||
|
||||
const nameMatch = result.text.match(/Il\s+Sig\.\/La\s+Sig\.ra[ \t]+([A-Za-zÀ-ÿ']+(?:[ \t]+[A-Za-zÀ-ÿ']+)+)/i);
|
||||
|
||||
if (nameMatch) {
|
||||
const rawName = nameMatch[1].trim(); // "Kan Jessica Shuk Yi"
|
||||
const parts = rawName.split(/\s+/);
|
||||
|
||||
if (parts.length >= 2) {
|
||||
const fullName = parts.join(' ');
|
||||
const reversedName = [...parts.slice(1), parts[0]].join(' ');
|
||||
|
||||
conditions.push(`Name='${fullName}'`);
|
||||
if (fullName !== reversedName) {
|
||||
conditions.push(`Name='${reversedName}'`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// use the soql comand to search in the database
|
||||
const soql = `SELECT Id, Name FROM Account WHERE (${conditions.join(' OR ')}) ORDER BY CreatedDate DESC LIMIT 1`;
|
||||
const result_soql = await sfdc.query(soql);
|
||||
if (result_soql && result_soql.records && result_soql.records.length > 0) { // if we find something
|
||||
contentVersion = await sfdc.create('ContentVersion', {
|
||||
Title: `${ result_soql.records[0].Name }_Document.pdf`,
|
||||
PathOnClient: `${ result_soql.records[0].Name }_Document.pdf`,
|
||||
VersionData: base64Pdf, // Must be Base64 string
|
||||
FirstPublishLocationId: result_soql.records[0].Id// Automatically creates the link to the Account!
|
||||
});
|
||||
}
|
||||
}
|
||||
finally {
|
||||
if (parser) {
|
||||
await parser.destroy();
|
||||
}
|
||||
}
|
||||
}
|
||||
console.log(`PDFs successfully attached!`);
|
||||
|
||||
} catch (error) {
|
||||
console.error(`Error uploading PDF: `, error);
|
||||
}
|
||||
}
|
||||
|
||||
// here we create an Account for each client and upload their pdf file
|
||||
async function uploadUserAccount() {
|
||||
await initializeSalesforceConnection();
|
||||
|
||||
// now for each client we need to create an Account on Salesforce
|
||||
try {
|
||||
for (let i = 0; i < data.length; i++) {
|
||||
const firstName = (data[i].NOME || '').toString().trim();
|
||||
const lastName = (data[i].COGNOME || '').toString().trim();
|
||||
|
||||
let userData = {
|
||||
Name: `${ firstName } ${ lastName }`.trim(),
|
||||
CF__c: data[i].CODICE_FISCALE || null,
|
||||
};
|
||||
const newAccount = await sfdc.create('Account', userData); // it creates the Account
|
||||
}
|
||||
console.log('Accounts created successfully!');
|
||||
}
|
||||
catch (error) {
|
||||
console.log('Something went wrong while creating the accounts: ', error);
|
||||
}
|
||||
}
|
||||
// this is where i need to store each page in a common temporary pdf file
|
||||
async function processPage(pdfDoc, pageIndex) {
|
||||
try {
|
||||
const newDoc = await PDFDocument.create();
|
||||
const [ copiedPage ] = await newDoc.copyPages(pdfDoc, [pageIndex]);
|
||||
newDoc.addPage(copiedPage);
|
||||
const pdfBytes = await newDoc.save();
|
||||
|
||||
const filepath = path.join(os.tmpdir(), `fileTemp_page_${pageIndex}.pdf`);
|
||||
fs.writeFileSync(filepath, pdfBytes);
|
||||
tempFilePath.push(filepath);
|
||||
}
|
||||
catch (error) {
|
||||
console.error('Error in processPage:', error);
|
||||
}
|
||||
}
|
||||
|
||||
async function splitExcelFile(inputFile) {
|
||||
let numRows; // this parameter is needed when we need to analyze the pdf file in case it has duplicates
|
||||
const columnNames = []; // contains the names of the columns (header names)
|
||||
|
||||
try {
|
||||
console.log(`Loading excel file: ${ inputFile }\n`);
|
||||
|
||||
const workbook = new ExcelJS.Workbook();
|
||||
await workbook.xlsx.readFile(inputFile);
|
||||
const worksheet = workbook.getWorksheet(1);
|
||||
|
||||
const headerRow = worksheet.getRow(1).actualCellCount; //number of columns of the table
|
||||
numRows = (worksheet.actualRowCount) - 1;
|
||||
|
||||
worksheet.getRow(1) // to convert every title of the first row to upper case
|
||||
.eachCell((col, col_num) => {
|
||||
if (typeof col.value === 'string') {
|
||||
col.value = col.value.toUpperCase().trim();
|
||||
}
|
||||
})
|
||||
|
||||
// convert every letter of CF to uppercase and store the CFs in the array cf
|
||||
if (worksheet.getRow(1).getCell(6).value.trim() === 'CODICE FISCALE') {
|
||||
worksheet.getColumn(6)
|
||||
.eachCell((row, row_num) => {
|
||||
row.value = (row.value).toString().toUpperCase();
|
||||
})
|
||||
}
|
||||
|
||||
worksheet.getColumn(8) // of the first file
|
||||
.eachCell((cell, rownumber) => {
|
||||
if (typeof cell.value === 'string') {
|
||||
cell.value = (cell.value).replace(/\b\w/g, char => char.toUpperCase());
|
||||
/* \b finds the start of a word (the boundary of a word)
|
||||
\w targets the first letter following that boundary
|
||||
/g (global flag) ensures it updates every word
|
||||
*/
|
||||
}
|
||||
})
|
||||
|
||||
// to store the names of the columns in columnNames
|
||||
worksheet.getRow(1).eachCell((cell, cell_num) => {
|
||||
columnNames.push(cell.value);
|
||||
})
|
||||
|
||||
// now we need to store the data of each user
|
||||
for (let i = 2; i <= numRows + 1; i++) {
|
||||
let dataUser = {};
|
||||
worksheet.getRow(i)
|
||||
.eachCell((cell, cell_num) => {
|
||||
const rawColumnName = columnNames[cell_num - 1] || `column_${cell_num}`;
|
||||
|
||||
// 1. Trim whitespace and replace spaces with underscores
|
||||
const cleanKey = rawColumnName
|
||||
.toString()
|
||||
.trim()
|
||||
.replace(/\s+/g, '_'); // \s => matches any whitespaces
|
||||
// + => groups multiple consecutive spaces together into a
|
||||
// single match so you don't end up with multiple underscores.
|
||||
|
||||
dataUser[cleanKey] = cell.value;
|
||||
})
|
||||
data.push(dataUser);
|
||||
}
|
||||
return numRows;
|
||||
}
|
||||
catch (error) {
|
||||
console.error('Error processing the excel file: ', error);
|
||||
}
|
||||
}
|
||||
|
||||
async function splitPDF(numRows, inputFile) {
|
||||
console.log(`Loading pdf file: ${ inputFile }...\n`);
|
||||
let parser;
|
||||
|
||||
try {
|
||||
|
||||
// 1. we use pdfParse to read and extract the content of a pdf file
|
||||
const existingPdfBytes = fs.readFileSync(inputFile);
|
||||
parser = new PDFParse({ data: existingPdfBytes });
|
||||
const result = await parser.getText();
|
||||
const pagesNumber = result.pages.length; //pages number of the pdf file
|
||||
|
||||
// 2. we use pdf-lib to create and edit a pdf file
|
||||
const srcPdf = await PDFDocument.load(existingPdfBytes);
|
||||
|
||||
// if there are duplicates (back to back duplicates), I only have to print one copy
|
||||
if (pagesNumber > numRows) { // comparison between the number of pages of the pdf file and those of the excel file
|
||||
let displayNumPage = 1;
|
||||
let i;
|
||||
for (i = 1; i < pagesNumber && displayNumPage <= numRows; i += 2) {
|
||||
if (result.pages[i].text.trim() === result.pages[i - 1].text.trim()) {
|
||||
continue;
|
||||
}
|
||||
|
||||
/*console.log(`--- PAGE ${ displayNumPage } ---`);
|
||||
console.log(result.pages[i].text);
|
||||
console.log("\n");*/
|
||||
|
||||
await processPage(srcPdf, i);
|
||||
displayNumPage++;
|
||||
}
|
||||
}
|
||||
else {
|
||||
for (let i = 0; i < pagesNumber; i++) {
|
||||
/*console.log(`--- PAGE ${i + 1} ---`);
|
||||
console.log(result.pages[i].text);
|
||||
console.log("\n");*/
|
||||
await processPage(srcPdf, i); // Pass 0-based index i
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (error) {
|
||||
console.error(`Error processing the pdf file: `, error);
|
||||
}
|
||||
finally {
|
||||
if (parser) {
|
||||
await parser.destroy();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function main() {
|
||||
const result = await splitExcelFile(excelFile);
|
||||
await splitPDF(result, pdfFile);
|
||||
const rl = readline.createInterface({ input, output });
|
||||
let reply = '';
|
||||
|
||||
try {
|
||||
while(!reply) {
|
||||
const response = await rl.question('Do you want to create accounts or upload pages (accounts/pages)? ');
|
||||
reply = response.trim();
|
||||
|
||||
if (!reply) {
|
||||
console.log('Please try again!');
|
||||
}
|
||||
}
|
||||
|
||||
if (reply === 'accounts') {
|
||||
await uploadUserAccount();
|
||||
}
|
||||
else if (reply === 'pages') {
|
||||
await initializeSalesforceConnection();
|
||||
await attachPdfToAccount(sfdc);
|
||||
}
|
||||
}
|
||||
finally {
|
||||
rl.close();
|
||||
}
|
||||
}
|
||||
|
||||
main();
|
||||
Reference in New Issue
Block a user