Update excel export and value coersion to pb field expectations

This commit is contained in:
2025-12-01 23:28:07 -06:00
parent 1cd0faf179
commit ce373afb88
5 changed files with 264 additions and 2191 deletions
-1
View File
@@ -1,7 +1,6 @@
{
"tenantId": "3fd97ea7-b124-41f1-855f-52d8ac3b16c7",
"clientId": "3c846e71-9609-40e1-b458-0eb805e21b9f",
"sharepointFileUrl": "https://czflex.sharepoint.com/:x:/r/sites/Team/Shared%20Documents/General/JOBS%201000-9999.xls",
"pbUrl": "http://10.10.1.109:8080",
"pbCollection": "Job_Info_TestEnv",
"pbEmail": "pbserviceupdate@cardoza.construction"
+60 -1915
View File
File diff suppressed because it is too large Load Diff
+203 -275
View File
@@ -1,9 +1,13 @@
//12/1/2025 Allows Excel download and conversion of headers mapped to pb headers.
//coersion added to match pb field types. however, may still have difficulty in assimilating certain date formats from excel to pb date fields.
//due to Excel storing as all caps for boolean fields
// excelsync.js
import { FIELD_CONFIG } from "./fieldConfig.js";
import fs from "fs";
import axios from "axios";
import qs from "qs";
import * as XLSX from "xlsx";
import ExcelJS from "exceljs";
import dotenv from "dotenv";
import { serve } from "bun";
import PocketBase from "pocketbase"
@@ -11,38 +15,17 @@ import PocketBase from "pocketbase"
dotenv.config();
// -----------------------------
// EXCEL PARSER
// -----------------------------
const HEADER_ROW_INDEX = 2; // Row 3
const DATA_START_ROW_INDEX = 3; // Row 4
// -----------------------------
// CONFIG
// CONFIG FOR TOKEN ACQUISITION GRAPH API + POCKETBASE
// -----------------------------
const CONFIG = JSON.parse(fs.readFileSync("config.json", "utf8"));
const tenantId = CONFIG.tenantId;
const clientId = CONFIG.clientId;
const sharepointFileUrl = CONFIG.sharepointFileUrl; // production Excel file URL
const pbUrl = CONFIG.pbUrl;
const pbCollection = CONFIG.pbCollection || "Job_Info_TestEnv";
const pbCollection = CONFIG.pbCollection;
const pbEmail = CONFIG.pbEmail;
const clientSecret = process.env.CLIENT_SECRET;
const pbPassword = process.env.PB_PASSWORD;
if (!tenantId || !clientId || !clientSecret || !sharepointFileUrl || !pbUrl || !pbEmail || !pbPassword) {
console.error("❌ Missing required config/env values");
process.exit(1);
}
console.log({
tenantId,
clientId,
clientSecret: clientSecret ? clientSecret.slice(0,4) + "..." : null,
sharepointFileUrl,
pbUrl,
pbEmail,
pbPassword: pbPassword ? "***" : null
});
// -----------------------------
// LOGGING
// -----------------------------
@@ -52,7 +35,7 @@ function log(message) {
}
// -----------------------------
// HEADER + ROW DETECTION HELPERS
// HEADER DETECTOR
// -----------------------------
//Gets the last column letter in the table converting from 0 index to excel actual column in letter form.
function columnLetter(index) {
@@ -64,30 +47,8 @@ function columnLetter(index) {
return letter;
}
const headerRowIndex = HEADER_ROW_INDEX + 1;
function getColumnLetterForHeader(headerName, sheet, headerRowIndex) {
const headerRow = XLSX.utils.sheet_to_json(sheet, { header: 1, range: `${headerRowIndex}:${headerRowIndex}` })[0]
.map(h => (h || "").toString().trim().toLowerCase());
const idx = headerRow.findIndex(h => h === headerName.toLowerCase());
if (idx === -1) {
log(`❌ Header "${headerName}" not found. Row contents: ${JSON.stringify(headerRow)}`);
throw new Error(`Header "${headerName}" not found on row ${headerRowIndex}`);
}
log(`✅ Header "${headerName}" found at column index ${idx}`);
return columnLetter(idx);
}
function getNotesColumnLetterFromParsedHeaders(headerMap) {
const headers = Object.keys(headerMap);
const notesIndex = headers.findIndex(h => h.trim().toLowerCase() === "notes");
if (notesIndex === -1) {
log(`❌ 'Notes' header not found in HEADER_MAP keys: ${headers.join(", ")}`);
throw new Error("Notes column not found");
}
return columnLetter(notesIndex);
}
// -----------------------------
// GRAPH TOKEN
// GRAPH TOKEN ACQUISITION
// -----------------------------
async function getGraphToken() {
const tokenUrl = `https://login.microsoftonline.com/${tenantId}/oauth2/v2.0/token`;
@@ -117,22 +78,7 @@ async function downloadExcelFromGraph(graphToken, driveId, itemId) {
}
// -----------------------------
// GRAPH UPLOADER HELPER
// -----------------------------
async function uploadExcelToGraph(graphToken, driveId, itemId, buffer) {
const url = `https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/content`;
const res = await axios.put(url, buffer, {
headers: {
Authorization: `Bearer ${graphToken}`,
"Content-Type": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
}
});
log(`✅ Excel file updated in SharePoint: ${res.status} ${res.statusText}`);
}
// -----------------------------
// POCKETBASE LOGIN
// POCKETBASE LOGIN AND TOKEN ACQUISITION
// -----------------------------
async function getPocketBaseClient() {
const pb = new PocketBase(pbUrl);
@@ -141,215 +87,198 @@ async function getPocketBaseClient() {
return pb;
}
function parseExcelFile(input, headerMap) {
// -----------------------------
// Get Data From Excel File
// -----------------------------
const HEADER_ROW_INDEX = 2; // Row 3 in Excel
const DATA_START_ROW_INDEX = 3; // Row 4 in Excel → first data row
//clean and coerce Excel values to match PocketBase schema expectations
function cleanString(val) {
if (val == null) return "";
return String(val)
.replace(/\u00A0/g, " ") // normalize non-breaking spaces
.replace(/[\r\n\t]/g, " ") // strip control chars
.replace(/\s+/g, " ") // collapse whitespace
.trim();
}
function normalizeForPB(val, type) {
const cleaned = cleanString(val);
// Treat common placeholders as empty
const emptyTokens = ["n/a", "na", "null", "none"];
if (emptyTokens.includes(cleaned.toLowerCase())) {
switch (type) {
case "number": return 0; // PocketBase defaults to 0
case "bool": return null;
case "string": return null;
case "email": return null; // email empty
case "json": return null;
case "date": return null; // date empty
default: return null;
}
}
if (cleaned === "") {
switch (type) {
case "number": return 0;
case "bool": return null;
case "string": return null;
case "email": return null;
case "json": return null;
case "date": return null;
default: return null;
}
}
switch (type) {
case "bool":
case "boolean": {
const lower = cleaned.toLowerCase();
if (["true","yes","y","1"].includes(lower)) return true; // boolean true
if (["false","no","n","0"].includes(lower)) return false; // boolean false
return null;
}
case "number": {
const num = Number(cleaned);
return Number.isNaN(num) ? 0 : num;
}
case "date": {
const d = new Date(cleaned);
return isNaN(d.getTime()) ? null : d.toISOString();
}
case "string":
default:
return cleaned;
}
}
export function parseExcelFile(input) {
let data;
// In case of data from graph
if (Buffer.isBuffer(input)) {
data = input;
log(`Reading Excel file from Graph buffer`);
// In case of file path (Not used at this time)
log("Reading Excel file from Graph buffer");
} else {
data = fs.readFileSync(input);
log(`Reading Excel file: ${input}`);
}
const workbook = XLSX.read(data, { type: "buffer", cellDates: true });
const sheet = workbook.Sheets["Job Sheet"]; // explicitly use Job Sheet
const range = XLSX.utils.decode_range(sheet["!ref"]);
const sheet = workbook.Sheets["Job Sheet"];
if (!sheet) throw new Error('Sheet named "Job Sheet" not found');
const range = XLSX.utils.decode_range(sheet["!ref"]);
const merges = sheet["!merges"] || [];
// Helper to get value from cell or merged region
const getValue = (r, c) => {
const addr = XLSX.utils.encode_cell({ r, c });
const cell = sheet[addr];
if (cell) return cell.v ?? cell.w ?? null;
for (const m of merges) {
if (m.s.r <= r && r <= m.e.r && m.s.c <= c && c <= m.e.c) {
const master = sheet[XLSX.utils.encode_cell({ r: m.s.r, c: m.s.c })];
const master = sheet[XLSX.utils.encode_cell(m.s)];
return master ? (master.v ?? master.w ?? null) : null;
}
}
return null;
};
// Read headers
// 1. Read headers (Row 3)
const rawHeaders = [];
for (let c = range.s.c; c <= range.e.c; c++) {
let h = getValue(HEADER_ROW_INDEX, c);
rawHeaders.push(h ? String(h).trim() : "");
const val = getValue(HEADER_ROW_INDEX, c);
rawHeaders.push(val ? String(val).trim() : "");
}
log(`Found ${rawHeaders.length} headers in Row 3`);
log(`Headers: ${rawHeaders.join(" | ")}`);
// Compare Excel headers against HEADER_MAP
const mappedHeaders = [];
const unmappedHeaders = [];
for (const h of rawHeaders) {
if (headerMap[h]) {
mappedHeaders.push([h, headerMap[h]]);
} else {
unmappedHeaders.push([h, ""]);
// 2. Build lookup map once
const excelHeaderToConfig = Object.values(FIELD_CONFIG).reduce((map, cfg) => {
if (cfg.excelHeader) {
const key = cfg.excelHeader.trim();
map[key] = cfg;
map[key.toLowerCase()] = cfg;
}
}
return map;
}, {});
// Output as CSV-style rows
console.log("\n📑 Header mapping preview (CSV style):");
console.log("ExcelHeader,PocketBaseField");
for (const [excel, pb] of mappedHeaders) {
console.log(`${excel},${pb}`);
}
for (const [excel, pb] of unmappedHeaders) {
console.log(`${excel},${pb}`);
}
// 3. Rich header mapping
const headerMapping = rawHeaders.map(raw => {
const clean = raw.trim();
const config = excelHeaderToConfig[clean] || excelHeaderToConfig[clean.toLowerCase()];
// Parse data rows
return config
? { original: clean, pbField: config.pbField, type: config.type, isMapped: true, config }
: { original: clean, pbField: "", type: "string", isMapped: false, isUnknown: true };
});
log(`Mapped ${headerMapping.filter(h => h.isMapped).length} columns`);
// 4. Parse data rows (starting Row 4)
const rows = [];
for (let r = DATA_START_ROW_INDEX; r <= range.e.r; r++) {
const row = {};
const values = [];
let hasData = false;
for (let c = range.s.c; c <= range.e.c; c++) {
const excelHeader = rawHeaders[c - range.s.c];
const pbField = headerMap[excelHeader];
if (!pbField) continue;
let val = getValue(r, c);
if (val !== null && val !== undefined) {
const s = String(val).trim();
if (s === "" || /^n\/?a$/i.test(s) || s === "#N/A") val = null;
}
row[pbField] = val;
const val = getValue(r, c);
values.push(val ?? null);
if (val !== null && val !== "") hasData = true;
}
if (hasData) rows.push(row);
if (!hasData) continue;
const rowObj = {};
headerMapping.forEach((map, i) => {
if (map.isMapped) {
rowObj[map.pbField] = normalizeForPB(values[i], map.type);
}
});
rows.push(rowObj);
}
log(`Loaded ${rows.length} real jobs`);
if (rows[0]) {
log(`First job preview: Job_Number=${rows[0].Job_Number}, pb_id=${rows[0].id}`);
}
return rows;
return {
data: rows, // parsed row objects
headerMapping, // rich info about headers
rawHeaders, // original headers for debugging
totalRows: rows.length // count of parsed rows
};
}
// -----------------------------
// HEADER MAP
// -----------------------------
const HEADER_MAP = {
"Job_Number": "Job_Number",
"Job_Full_Name": "Job_Full_Name",
"Job_Name": "Job_Name",
"Job Address": "Job_Address",
"Job Type": "Job_Type",
"Flag": "Flag",
"Tax_Exempt": "Tax_Exempt",
"Job Status": "Job_Status",
"Job Division": "Job_Division",
"Estimator": "Estimator",
"Office Rep": "Office_Rep",
"Manager": "Project_Manager",
"Company/Client": "Company_Client",
"Contact Person": "Contact_Person",
"Phone Number": "Phone_Number",
"Email": "Email",
"Due Date": "Due_Date",
"Due Date Source": "Due_Date_Source",
"Due Date Counter": "Due_Date_Counter",
"Due Time": "Due_Time",
"Tax_Exempt_Docs_Uploaded": "Tax_Exempt_Docs_Uploaded",
"Docs Uploaded": "Docs_Uploaded",
"QB Created": "QB_Created",
"Added to Calendar": "Added_To_Calendar",
"PSwift Uploaded": "PSwift_Uploaded",
"Voxer Created": "Voxer_Created",
"Estimate Reviewed": "Estimate_Reviewed",
"Estimate Draft": "Estimate_Draft",
"Estimate Approved": "Estimate_Approved",
"Start Date": "Start_Date",
"Schedule_Confidence": "Schedule_Confidence",
"Notes": "Notes",
"Job QB Link": "Job_QB_Link",
"Voxer Link": "Voxer_Link",
"Job_Codes": "Job_Codes",
"Submission Date": "Submission_Date",
"Active": "Active",
"Job Folder Link": "Job_Folder_Link",
"pb_id": "id"
};
// -----------------------------
// MAIN
// -----------------------------
let parsedRows = [];
let rawHeaders = [];
(async () => {
try {
log("🔵 Starting Excel Sync…");
const graphToken = await getGraphToken();
const pb = await getPocketBaseClient();
// These can be update if the Excel File changes
const driveId = "b!9YOqqr2xM0G2DFBwMEJYY4UzQgocFddEtpLYWuS9_AtkCKl2q8yjQJteQ7Ti4QSx";
const itemId = "01SPNXLDSQTMG4F6BDANCLJU2FZKEDQLVU";
const excelBuffer = await downloadExcelFromGraph(graphToken, driveId, itemId);
parsedRows = parseExcelFile(excelBuffer, HEADER_MAP);
// Run enhanced test (safe, no writes)
runEnhancedTest(parsedRows, graphToken, pb);
// At this stage you have:
// - graphToken (for SharePoint updates later)
// - pb client (for PB updates)
// - rows[] mapped to PB fields
const updatedBuffer = exportExcelforDL(parsedRows);
await updateNotesInSharePoint(graphToken, driveId, itemId, "Job Sheet", parsedRows, pb, excelBuffer);
// Sync to PocketBase
//await syncRowsToPocketBase(parsedRows, pb);
const parsed = parseExcelFile(excelBuffer);
parsedRows = parsed.data;
rawHeaders = parsed.rawHeaders;
log(rawHeaders)
log("✅ First part complete: tokens + Excel parsing ready");
} catch (err) {
log("❌ Sync failed: " + (err.message || err));
process.exit(1);
}
})();
// -----------------------------
// ENHANCED TEST HARNESS
// -----------------------------
function runEnhancedTest(rows, graphToken, pb) {
log("🔎 Running enhanced test (no writes)…");
// 1. Verify tokens
log(`Graph token length: ${graphToken.length}`);
log(`PocketBase token length: ${pb.authStore.token.length}`);
// 2. Verify Excel parsing
log(`Parsed ${rows.length} rows from Excel`);
if (rows.length > 0) {
const sample = rows[0];
log("Sample row preview:");
log(` Job_Number: ${sample.Job_Number}`);
log(` Job_Full_Name: ${sample.Job_Full_Name}`);
log(` Active: ${sample.Active}`);
log(` pb_id: ${sample.id}`);
log(` Notes: ${sample.Notes}`);
}
// 3. Verify header mapping
const mappedFields = Object.values(HEADER_MAP);
const sampleKeys = Object.keys(rows[0] || {});
const missingFields = mappedFields.filter(f => !sampleKeys.includes(f));
if (missingFields.length > 0) {
log(`⚠️ Missing mapped fields in sample row: ${missingFields.join(", ")}`);
} else {
log("✅ All mapped fields present in sample row");
}
log("✅ Enhanced test complete — no writes performed");
}
// -------------------------
// Export to xlsx - Excel
// ---------------------------
// Toggle this flag to enable/disable the export server
const ENABLE_EXPORT = false; // set to false to bypass download
const ENABLE_EXPORT = true; // set to false to bypass download
function exportExcelforDL(parsedRows) {
if (!parsedRows || parsedRows.length === 0) {
@@ -424,90 +353,89 @@ if (ENABLE_EXPORT) {
// -----------------------------
// UPDATE NOTES CELLS IN SHAREPOINT (REAL-TIME)
// -----------------------------
function getNotesColumnLetterFromParsedHeaders(headerMap) {
const headers = Object.keys(headerMap);
const notesIndex = headers.findIndex(h => h.trim().toLowerCase() === "notes");
if (notesIndex === -1) {
log(`❌ 'Notes' header not found in HEADER_MAP keys: ${headers.join(", ")}`);
throw new Error("Notes column not found");
}
return columnLetter(notesIndex);
}
//function getNotesColumnLetterFromParsedHeaders(rawHeaders) {
// const notesIndex = rawHeaders.findIndex(h => h.trim().toLowerCase() === "notes");
// if (notesIndex === -1) {
// log(`❌ 'Notes' header not found in HEADER_MAP keys: ${rawHeaders.join(", ")}`);
// throw new Error("Notes column not found");
// }
// return columnLetter(notesIndex);
//}
//await updateNotesInSharePoint(graphToken, driveId, itemId, "Job Sheet", parsedRows, pb, excelBuffer);
// Update only changed Notes cells using workbook session + PATCH.
// This version relies solely on DATA_START_ROW_INDEX for row mapping.
async function updateNotesInSharePoint(graphToken, driveId, itemId, worksheetName, parsedRows, pb, workbookBuffer) {
const wb = XLSX.read(workbookBuffer, { type: "buffer", cellDates: true });
const sheet = wb.Sheets[worksheetName];
if (!sheet) throw new Error(`Worksheet "${worksheetName}" not found`);
//async function updateNotesInSharePoint(graphToken, driveId, itemId, worksheetName, parsedRows, pb, workbookBuffer) {
// const wb = XLSX.read(workbookBuffer, { type: "buffer", cellDates: true });
// const sheet = wb.Sheets[worksheetName];
// if (!sheet) throw new Error(`Worksheet "${worksheetName}" not found`);
// Column detection aligned to HEADER_MAP (same mapping used by parseExcelFile)
const notesColumnLetter = getNotesColumnLetterFromParsedHeaders(HEADER_MAP);
log(`✅ Notes column resolved to ${notesColumnLetter} via HEADER_MAP`);
//const notesColumnLetter = getNotesColumnLetterFromParsedHeaders(rawHeaders);
//og(`✅ Notes column resolved to ${notesColumnLetter} via rawHeaders`);
// Create a workbook session that persists changes
const sessionRes = await axios.post(
`https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/workbook/createSession`,
{ persistChanges: true },
{ headers: { Authorization: `Bearer ${graphToken}` } }
);
const sessionId = sessionRes.data.id;
//const sessionRes = await axios.post(
// `https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/workbook/createSession`,
// { persistChanges: true },
// { headers: { Authorization: `Bearer ${graphToken}` } }
// );
// const sessionId = sessionRes.data.id;
let changes = 0;
// let changes = 0;
// Loop parsed rows; map i to Excel row using DATA_START_ROW_INDEX (zero-based)
for (let i = 0; i < parsedRows.length; i++) {
const row = parsedRows[i];
const jobNumber = row.Job_Number;
if (jobNumber == null || jobNumber === "") continue;
// for (let i = 0; i < parsedRows.length; i++) {
// const row = parsedRows[i];
// const jobNumber = row.Job_Number;
// if (jobNumber == null || jobNumber === "") continue;
try {
const records = await pb.collection(pbCollection).getFullList({
filter: Number.isFinite(jobNumber) ? `Job_Number=${jobNumber}` : `Job_Number="${jobNumber}"`,
batchSize: 1
});
if (records.length === 0) continue;
// try {
// const records = await pb.collection(pbCollection).getFullList({
// filter: Number.isFinite(jobNumber) ? `Job_Number=${jobNumber}` : `Job_Number="${jobNumber}"`,
// batchSize: 1
// });
// if (records.length === 0) continue;
// Normalize notes for fair comparison
const normalize = v => (v ?? "").toString().replace(/\s+/g, " ").trim();
const pbNotes = normalize(records[0].Notes);
const excelNotes = normalize(row.Notes);
// const normalize = v => (v ?? "").toString().replace(/\s+/g, " ").trim();
// const pbNotes = normalize(records[0].Notes);
// const excelNotes = normalize(row.Notes);
if (pbNotes !== excelNotes) {
// if (pbNotes !== excelNotes) {
// Excel uses 1-based row numbers; DATA_START_ROW_INDEX is zero-based
const excelRowNumber = DATA_START_ROW_INDEX + i + 1;
const cellAddress = `${notesColumnLetter}${excelRowNumber}`;
// const excelRowNumber = DATA_START_ROW_INDEX + i + 1;
// const cellAddress = `${notesColumnLetter}${excelRowNumber}`;
log(`✏️ Notes change for Job_Number=${jobNumber}`);
log(` Before: "${excelNotes}"`);
log(` After : "${pbNotes}"`);
log(`➡️ Writing to ${worksheetName}!${cellAddress}`);
// log(`✏️ Notes change for Job_Number=${jobNumber}`);
// log(` Before: "${excelNotes}"`);
// log(` After : "${pbNotes}"`);
// log(`➡️ Writing to ${worksheetName}!${cellAddress}`);
await axios.patch(
`https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/workbook/worksheets('${worksheetName}')/range(address='${cellAddress}')`,
{ values: [[pbNotes]] },
{
headers: {
Authorization: `Bearer ${graphToken}`,
"Content-Type": "application/json",
"workbook-session-id": sessionId
}
}
);
// await axios.patch(
// `https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/workbook/worksheets('${worksheetName}')/range(address='${cellAddress}')`,
// { values: [[pbNotes]] },
// {
// headers: {
// Authorization: `Bearer ${graphToken}`,
// "Content-Type": "application/json",
// "workbook-session-id": sessionId
// }
// }
// );
row.Notes = pbNotes;
changes++;
}
} catch (err) {
log(`❌ Failed for Job_Number=${jobNumber}: ${err.message}`);
}
}
// row.Notes = pbNotes;
// changes++;
// }
// } catch (err) {
// log(`❌ Failed for Job_Number=${jobNumber}: ${err.message}`);
// }
// }
await axios.post(
`https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/workbook/closeSession`,
{},
{ headers: { Authorization: `Bearer ${graphToken}`, "workbook-session-id": sessionId } }
);
// await axios.post(
// `https://graph.microsoft.com/v1.0/drives/${driveId}/items/${itemId}/workbook/closeSession`,
// {},
// { headers: { Authorization: `Bearer ${graphToken}`, "workbook-session-id": sessionId } }
// );
log(`✅ Notes-only sync complete. Changes applied: ${changes}`);
}
// log(`✅ Notes-only sync complete. Changes applied: ${changes}`);
//}
View File
@@ -2,6 +2,7 @@
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>SharePoint Link Encoder</title>
<style>
body { font-family: sans-serif; margin: 2rem; }