ray
138 lines
7.2 KiB
JavaScript
138 lines
7.2 KiB
JavaScript
// Production rule-based appointment parser from ShopProQuote project.
|
|
// Extracts multiple appointments from OCR text with no API dependencies.
|
|
// Handles: phones, VINs (OCR-tolerant), dates, times, durations, vehicles,
|
|
// advisor+RO stripping, cross-block name carryover, table format detection.
|
|
// See SKILL.md for the full architecture and pitfall documentation.
|
|
|
|
function parseWithRules(ocrText) {
|
|
var t = ocrText.replace(/\r\n/g, '\n').replace(/\r/g, '\n').trim();
|
|
if (!t) return [];
|
|
|
|
// Strip separator lines and short all-caps headers, KEEP blank lines
|
|
t = t.split('\n').map(function(line) {
|
|
var s = line.trim();
|
|
if (s.length === 0) return ''; // keep blank lines for block splitting
|
|
if (/^[\-\u2013=_*#]{3,}$/.test(s)) return '';
|
|
if (s.length < 25 && s === s.toUpperCase() && /^[A-Z\s]+$/.test(s) && s.length > 1) return '';
|
|
return line;
|
|
}).join('\n');
|
|
|
|
var appointments = [];
|
|
var phoneRe = /\(?\d{3}\)?[\s.\-]*\d{3}[\s.\-]*\d{4}/;
|
|
var vinRe = /\b[A-HJ-NPR-Z0-9OIQ]{17}\b/i;
|
|
function fixVin(v) { return v.toUpperCase().replace(/O/g,'0').replace(/I/g,'1').replace(/Q/g,'0'); }
|
|
function parseDate(str) { /* see SKILL.md for full implementation */ return null; }
|
|
var dateRe = /\b(?:\d{4}[\/\-.]\d{1,2}[\/\-.]\d{1,2}|\d{1,2}[\/]\d{1,2}(?:[\/]\d{4})?|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]*\s+\d{1,2}(?:[,\s]+\d{4})?)\b/i;
|
|
var timeRe = /\b(\d{1,2}):(\d{2})\s*(AM|PM|am|pm)?\b|\b(\d{1,2})\s*(AM|PM|am|pm)\b/;
|
|
var durRe = /\b(\d+)\s*(?:min|minutes?|hrs?|hours?)\b/i;
|
|
var makesRe = /\b(?:ford|chevy|chevrolet|toyota|honda|nissan|bmw|mercedes|audi|dodge|jeep|gmc|ram|hyundai|kia|subaru|mazda|vw|volkswagen|lexus|acura|infiniti|cadillac|buick|chrysler|lincoln|tesla|volvo)\b/i;
|
|
var yrRe = /\b(19|20)\d{2}\b/;
|
|
|
|
function parseOne(raw, carryName) {
|
|
var b = raw, appt = {};
|
|
if (carryName) { appt.customerName = carryName; }
|
|
// Extract structured fields
|
|
var pm = b.match(phoneRe); if (pm) { appt.customerPhone = pm[0].replace(/[^\d]/g, ''); b = b.replace(pm[0], ' '); }
|
|
var vm = b.match(vinRe); if (vm) { appt.vin = fixVin(vm[0]); b = b.replace(vm[0], ' '); }
|
|
var dm = b.match(dateRe); if (dm) { var pd = parseDate(dm[0]); if (pd) { appt.appointmentDate = pd; b = b.replace(dm[0], ' '); } }
|
|
var tm = b.match(timeRe);
|
|
if (tm) { /* parse time to HH:MM, see SKILL.md */ b = b.replace(tm[0], ' '); }
|
|
var dum = b.match(durRe); if (dum) { var val = parseInt(dum[1]); if (/hr|hour/i.test(dum[0])) val *= 60; appt.duration = val; b = b.replace(dum[0], ' '); }
|
|
|
|
// Boundary detection
|
|
var np = b.match(phoneRe), nv = b.match(vinRe);
|
|
var myText = b, nextText = '', nextName = null;
|
|
if (np || nv) {
|
|
var ni = b.length;
|
|
if (np) ni = Math.min(ni, b.indexOf(np[0]));
|
|
if (nv) ni = Math.min(ni, b.indexOf(nv[0]));
|
|
if (ni > 0 && ni < b.length) {
|
|
var before = b.substring(0, ni);
|
|
// Walk back to last multi-space gap before last 1-2 words (tolerate trailing spaces)
|
|
var gap = before.match(/\s{2,}(?=\S+(?:\s+\S+){0,1}\s*$)/);
|
|
var splitAt = ni;
|
|
if (gap) { splitAt = before.lastIndexOf(gap[0]) + gap[0].length; }
|
|
else {
|
|
// Fallback: split before last 1-2 capitalized words
|
|
var nw = before.match(/([A-Z][A-Za-z]+(?:\s+[A-Z][A-Za-z]+){0,1})\s*$/);
|
|
if (nw && nw[1].length > 2) splitAt = before.length - nw[0].length;
|
|
}
|
|
myText = b.substring(0, splitAt);
|
|
nextText = b.substring(splitAt);
|
|
}
|
|
}
|
|
|
|
// Split on multi-spaces (preserves column structure)
|
|
var parts = myText.split(/\s{2,}/).map(function(p) { return p.replace(/\s+/g,' ').trim(); }).filter(function(p) { return p.length > 1; });
|
|
|
|
// Strip advisor name + RO code
|
|
var roCode = null;
|
|
parts = parts.map(function(p) {
|
|
var m = p.match(/^([A-Z][a-z]+)\s+(\[[^\]]+\])\s*(.*)/);
|
|
if (m) { roCode = roCode || m[2]; return m[3] || ''; }
|
|
return p;
|
|
}).filter(function(p) { return p.length > 0; });
|
|
|
|
// Clean VIN artifacts
|
|
parts = parts.map(function(p) { return p.replace(/VIN\s*VIN:?\s*/gi,'').replace(/VIN:?\s*VIN\s*/gi,'').trim(); }).filter(function(p) { return p.length > 1; });
|
|
|
|
// Assign name (first part, unless carried from previous block)
|
|
if (!carryName && parts.length > 0) { appt.customerName = parts[0]; parts.shift(); }
|
|
|
|
// Vehicle detection: prefer part with BOTH year AND make
|
|
var vi = -1;
|
|
for (var i = 0; i < parts.length; i++) {
|
|
if (yrRe.test(parts[i]) && makesRe.test(parts[i])) { vi = i; break; }
|
|
}
|
|
if (vi < 0) for (var i = 0; i < parts.length; i++) {
|
|
if (yrRe.test(parts[i]) || makesRe.test(parts[i])) { vi = i; break; }
|
|
}
|
|
if (vi >= 0) { appt.vehicleInfo = parts[vi]; parts.splice(vi, 1); }
|
|
if (parts.length > 0) { appt.serviceType = parts.join(' ').replace(/^\s+|\s+$/g, ''); }
|
|
if (roCode) appt.notes = (appt.notes ? appt.notes + ' ' : '') + 'RO: ' + roCode;
|
|
|
|
// Cross-block name carryover: strip trailing all-caps name from service
|
|
if (appt.serviceType) {
|
|
var tn = appt.serviceType.match(/\s+([A-Z]{2,}(?:\s+[A-Z]{2,}){1,2})\s*$/);
|
|
if (tn && tn[1].length > 3) {
|
|
appt.serviceType = appt.serviceType.substring(0, appt.serviceType.length - tn[0].length).trim();
|
|
nextName = tn[1];
|
|
}
|
|
}
|
|
|
|
if (appt.customerName && appt.customerName.length > 1) appointments.push(appt);
|
|
if (nextText.length > 10) return parseOne(nextText, nextName);
|
|
return nextName; // return for cross-block carry
|
|
}
|
|
|
|
// Split into blocks, detect tables, parse
|
|
var blocks = t.split(/\n\s*\n/).filter(function(b) { return b.trim().length > 3; });
|
|
if (blocks.length === 0) blocks = [t];
|
|
|
|
// Table format detection
|
|
if (blocks.length === 1) {
|
|
var lines = t.split('\n').filter(function(l) { return l.trim().length > 0; });
|
|
if (lines.length >= 3 && lines.length <= 40) {
|
|
var fl = lines[0].trim();
|
|
var hw = (fl.match(/\b(name|phone|date|time|service|vehicle|vin|customer|appointment|mileage|advisor|status)\b/gi) || []).length;
|
|
var hd = phoneRe.test(fl) || vinRe.test(fl);
|
|
// Only strip if 3+ header words AND no phone/VIN (data guard)
|
|
if (hw >= 3 && !hd && lines.length > 2) lines = lines.slice(1);
|
|
var wc = lines.map(function(l) { return l.trim().split(/\s+/).length; });
|
|
var avg = wc.reduce(function(a,b) { return a+b; }, 0) / wc.length;
|
|
if (wc.every(function(w) { return Math.abs(w - avg) <= 3; }) && lines.length >= 2) {
|
|
lines.forEach(function(line) { parseOne(line.replace(/\t/g, ' ').replace(/\n/g, ' ')); });
|
|
return appointments;
|
|
}
|
|
}
|
|
}
|
|
|
|
// Standard block-by-block with cross-block name carry
|
|
var carry = null;
|
|
blocks.forEach(function(block) {
|
|
carry = parseOne(block.replace(/\t/g, ' ').replace(/\n/g, ' '), carry);
|
|
});
|
|
|
|
return appointments;
|
|
}
|