import fs from 'fs'
const all = JSON.parse(fs.readFileSync(process.argv[2], 'utf8'))
const norm = s => s.toLowerCase().replace(/[^a-z0-9 ]/g, ' ').replace(/\s+/g, ' ').trim()

// Closing roles only. `enterprise sales` was deliberately left out of INCLUDE:
// it added 46 postings, all of them sales engineers, managers, directors and
// one recruiter, while "Enterprise Account Executive" is already matched.
// EXCLUDE then removes leadership and pre-sales titles so the sample stays
// individual-contributor closers — a sales manager's posting asks for different
// things and would blur the finding.
const INCLUDE = /\b(account executive|sales representative)\b/i
const EXCLUDE = /\b(engineer|architect|developer|recruiter|manager|director|vice president|vp|head of|intern|enablement|operations)\b/i

const seen = new Set(), jobs = []
for (const j of all.filter(x => INCLUDE.test(x.title) && !EXCLUDE.test(x.title))) {
  const k = j.co + '|' + norm(j.title) + '|' + j.content.length
  if (!seen.has(k)) { seen.add(k); jobs.push(j) }
}
const unesc = s => s.replace(/&lt;/g,'<').replace(/&gt;/g,'>').replace(/&amp;/g,'&')
  .replace(/&quot;/g,'"').replace(/&#39;/g,"'").replace(/&nbsp;/g,' ')
const texts = jobs.map(j => unesc(j.content).replace(/<[^>]+>/g,' ').replace(/\s+/g,' '))

// Deliberately absent, and said so on the page:
//   Outreach  — 13.6% loose against 6.0% case-sensitive. The gap is generic
//               "customer outreach" / "outreach efforts", and capitalised
//               sentence-initial use makes case no help. Unfixable by regex.
//   Apollo    — 0.5%, and Apollo GraphQL is in this corpus. Both rare and dirty.
//   Chorus    — 0.4%. Real, too rare to report.
// Three terms are matched narrowly because the bare word was materially dirty:
//   closing    57.7% bare against 23.0% with a deal object ("closing date",
//              "closing the loop"). Narrow form used.
//   new logos  30.0% bare against 17.6% for "net new logos". Narrow form used.
//   discovery  23.0% bare against 2.1% for "discovery call/meeting/process".
//              Bare "discovery" in a posting is usually not the sales stage.
const T = [
 ['Methodology','MEDDIC / MEDDPICC',/\bMEDDP?I?CC?\b|\bMEDDIC\b/i],
 ['Methodology','Challenger',/\bChallenger\b/],
 ['Methodology','SPIN',/\bSPIN\b/],
 ['Methodology','Sandler',/\bSandler\b/i],
 ['Methodology','Force Management / Command of the Message',/\bForce Management\b|\bCommand of the Message\b/i],
 ['Methodology','BANT',/\bBANT\b/i],
 ['Methodology','value selling',/\bvalue[- ]based selling\b|\bvalue selling\b/i],
 ['Methodology','solution selling',/\bsolution selling\b/i],

 ['Tools & platforms','Salesforce',/\bSalesforce\b/i],
 ['Tools & platforms','LinkedIn Sales Navigator',/\bSales Navigator\b/i],
 ['Tools & platforms','Gong',/\bGong\b/],
 ['Tools & platforms','ZoomInfo',/\bZoomInfo\b/i],
 ['Tools & platforms','Salesloft',/\bSales ?loft\b/i],
 ['Tools & platforms','Clari',/\bClari\b/],
 ['Tools & platforms','HubSpot',/\bHubSpot\b/i],
 ['Tools & platforms','CRM (generic)',/\bCRM\b/i],

 ['Metrics & targets','quota',/\bquota\b/i],
 ['Metrics & targets','pipeline',/\bpipeline\b/i],
 ['Metrics & targets','ARR',/\bARR\b/],
 ['Metrics & targets','forecasting',/\bforecast/i],
 ['Metrics & targets','bookings',/\bbookings\b/i],
 ['Metrics & targets','ACV',/\bACV\b/],
 ['Metrics & targets','win rate',/\bwin rate\b/i],
 ['Metrics & targets','quota attainment',/\bquota attainment\b|\battainment\b/i],
 ['Metrics & targets',"President's Club",/\bPresident'?s Club\b/i],
 ['Metrics & targets','net new logos',/\bnet[- ]new logos?\b/i],

 ['Sales motion','prospecting',/\bprospect(ing|ed)?\b/i],
 ['Sales motion','discovery calls',/\bdiscovery (call|meeting|process|session)/i],
 ['Sales motion','negotiation',/\bnegotiat/i],
 ['Sales motion','closing deals',/\bclosing (deals|business|new|accounts|opportunities)\b|\bclose deals\b/i],
 ['Sales motion','cold calling / outbound',/\bcold[- ]call/i],
 ['Sales motion','outbound',/\boutbound\b/i],
 ['Sales motion','land and expand',/\bland[- ]and[- ]expand\b/i],
 ['Sales motion','upsell / cross-sell',/\bup[- ]?sell|\bcross[- ]?sell/i],
 ['Sales motion','territory planning',/\bterritory plan|\bterritory management\b/i],
 ['Sales motion','multithreading',/\bmulti[- ]?thread/i],
 ['Sales motion','C-level / executive engagement',/\bC[- ]level\b|\bC[- ]suite\b|\bexecutive stakeholders?\b/i],
 ['Sales motion','RFP',/\bRFP\b|\bRFI\b/i],
 ['Sales motion','channel / partner',/\bchannel partner|\bpartner ecosystem\b|\bresellers?\b/i],

 ['Segment & context','enterprise',/\benterprise\b/i],
 ['Segment & context','mid-market',/\bmid[- ]market\b/i],
 ['Segment & context','SMB',/\bSMB\b|\bsmall and medium\b/i],
 ['Segment & context','SaaS',/\bSaaS\b/i],
 // A bare \bfederal\b matched "protected by federal, state or local laws" in the EEO
 // boilerplate: on the 2026-09-25 corpus 179 of 261 matches named no public-sector
 // customer, and the published row overstated the segment about threefold. Federal
 // counts only when it qualifies a buyer (agencies, civilian, accounts, government).
 ['Segment & context','public sector / SLED',/\bSLED\b|\bpublic sector\b|\bstate and local government\b|\bfederal (?:government|agenc(?:y|ies)|sector|civilian|accounts?|customers?|market|space|business|sales|team|territor(?:y|ies)|systems? integrators?)\b/i],
]
const n = texts.length
const moe = p => +(1.96 * Math.sqrt((p/100)*(1-p/100)/n) * 100).toFixed(1)
const rows = T.map(([cat, term, re]) => {
  const c = texts.filter(t => re.test(t)).length
  const pct = +(100*c/n).toFixed(1)
  return { cat, term, n: c, pct, moe: moe(pct) }
}).sort((a,b) => b.n - a.n)
const out = { role: 'Sales / Account Executive', n, companies: [...new Set(jobs.map(j=>j.co))].sort(),
  collected: new Date(Date.now() - new Date().getTimezoneOffset() * 60000).toISOString().slice(0,10),
  medianWords: texts.map(t=>t.split(' ').length).sort((a,b)=>a-b)[Math.floor(n/2)], rows }
fs.writeFileSync(process.argv[3], JSON.stringify(out, null, 1))
console.log(`n=${n} from ${out.companies.length} companies, median ${out.medianWords} words`)
rows.forEach((r,i)=>console.log(`  ${String(i+1).padStart(2)}. ${r.term.padEnd(42)} ${String(r.pct).padStart(5)}% ±${r.moe}  (${r.n})`))