Этап 4 / Волна 19.1 выравнивание живого контура для слоя адресного сбора доказательной базы

llm_normalizer/backend/src/services/investigationState.ts

@@ -51,8 +51,162 @@ function capStrings(values: string[], max: number): string[] {
   return uniqueStrings(values).slice(0, max);
 }
 
+const INVESTIGATION_ACCOUNT_PREFIXES = new Set([
+  "01",
+  "02",
+  "07",
+  "08",
+  "10",
+  "13",
+  "19",
+  "20",
+  "21",
+  "23",
+  "25",
+  "26",
+  "28",
+  "29",
+  "41",
+  "43",
+  "44",
+  "45",
+  "50",
+  "51",
+  "52",
+  "55",
+  "57",
+  "58",
+  "60",
+  "62",
+  "66",
+  "67",
+  "68",
+  "69",
+  "70",
+  "71",
+  "73",
+  "76",
+  "90",
+  "91",
+  "94",
+  "96",
+  "97"
+]);
+
+function collectDateLikeSpans(text: string): Array<{ start: number; end: number }> {
+  const spans: Array<{ start: number; end: number }> = [];
+  const patterns = [
+    /\b20\d{2}(?:[-/.](?:0?[1-9]|1[0-2]))(?:[-/.](?:0?[1-9]|[12]\d|3[01]))?\b/g,
+    /\b(?:0?[1-9]|[12]\d|3[01])[./-](?:0?[1-9]|1[0-2])[./-](?:\d{2}|\d{4})\b/g,
+    /\b(?:0?[1-9]|[12]\d|3[01])\s+(?:январ[ьяе]|феврал[ьяе]|март[ае]?|апрел[ьяе]|ма[йея]|июн[ьяе]?|июл[ьяе]?|август[ае]?|сентябр[ьяе]?|октябр[ьяе]?|ноябр[ьяе]?|декабр[ьяе]?|january|february|march|april|may|june|july|august|september|october|november|december)(?:\s+20\d{2})?\b/giu
+  ];
+  for (const pattern of patterns) {
+    let match: RegExpExecArray | null = null;
+    while ((match = pattern.exec(text)) !== null) {
+      spans.push({
+        start: match.index,
+        end: match.index + match[0].length
+      });
+    }
+  }
+  return spans;
+}
+
+function collectAmountLikeSpans(text: string): Array<{ start: number; end: number }> {
+  const spans: Array<{ start: number; end: number }> = [];
+  const patterns = [/\b\d{1,3}(?:[ \u00A0]\d{3})+(?:[.,]\d{2})?\b/g, /\b\d+[.,]\d{2}\b/g];
+  for (const pattern of patterns) {
+    let match: RegExpExecArray | null = null;
+    while ((match = pattern.exec(text)) !== null) {
+      spans.push({
+        start: match.index,
+        end: match.index + match[0].length
+      });
+    }
+  }
+  return spans;
+}
+
+function collectPercentLikeSpans(text: string): Array<{ start: number; end: number }> {
+  const spans: Array<{ start: number; end: number }> = [];
+  const pattern = /\b\d{1,3}(?:[.,]\d+)?\s*%/g;
+  let match: RegExpExecArray | null = null;
+  while ((match = pattern.exec(text)) !== null) {
+    spans.push({
+      start: match.index,
+      end: match.index + match[0].length
+    });
+  }
+  return spans;
+}
+
+function intersectsSpan(start: number, end: number, spans: Array<{ start: number; end: number }>): boolean {
+  return spans.some((span) => start < span.end && end > span.start);
+}
+
+function hasAccountContextAround(text: string, start: number, end: number): boolean {
+  const left = text.slice(Math.max(0, start - 32), start);
+  const right = text.slice(end, Math.min(text.length, end + 32));
+  return /(?:счет|сч\.?|account|schet|оплат|расчет|расч[её]т|аванс|зачет|зач[её]т|ндс|закрыт|провод|постав|покуп|settlement|payment|vat|close|supplier|customer)/iu.test(
+    `${left} ${right}`
+  );
+}
+
 function detectAccounts(text: string): string[] {
-  return capStrings(text.match(/\b\d{2}(?:\.\d{2})?\b/g) ?? [], INVESTIGATION_MAX_PRIMARY_ACCOUNTS);
+  const lower = String(text ?? "").toLowerCase();
+  const blockedSpans = [...collectDateLikeSpans(lower), ...collectAmountLikeSpans(lower), ...collectPercentLikeSpans(lower)];
+  const hasAccountingLexeme =
+    /(?:\bсчет(?:а|у|ом|ов)?\b|\bсч\.?\b|\baccount(?:s)?\b|\bschet(?:a|u|om|ov)?\b|оплат|расчет|расч[её]т|аванс|долг|settlement|payment|supplier|customer|ндс|vat|рбп|deferred|амортиз)/iu.test(
+      lower
+    );
+  const accounts = new Set<string>();
+
+  const contextualPattern =
+    /(?:\b(?:счет(?:а|у|ом|ов)?|сч\.?|account(?:s)?|schet(?:a|u|om|ov)?)\b)\s*(?:№|#|:)?\s*(\d{2}(?:\.\d{1,2})?)/giu;
+  let contextualMatch: RegExpExecArray | null = null;
+  while ((contextualMatch = contextualPattern.exec(lower)) !== null) {
+    const token = String(contextualMatch[1] ?? "").trim();
+    const prefix = token.match(/^(\d{2})/)?.[1] ?? null;
+    if (prefix && INVESTIGATION_ACCOUNT_PREFIXES.has(prefix)) {
+      accounts.add(token);
+    }
+  }
+
+  const pairPattern = /\b(\d{2}\.\d{1,2})\s*\/\s*(\d{2}\.\d{1,2})\b/g;
+  let pairMatch: RegExpExecArray | null = null;
+  while ((pairMatch = pairPattern.exec(lower)) !== null) {
+    const left = String(pairMatch[1] ?? "").trim();
+    const right = String(pairMatch[2] ?? "").trim();
+    const leftPrefix = left.match(/^(\d{2})/)?.[1] ?? null;
+    const rightPrefix = right.match(/^(\d{2})/)?.[1] ?? null;
+    if (leftPrefix && INVESTIGATION_ACCOUNT_PREFIXES.has(leftPrefix)) {
+      accounts.add(left);
+    }
+    if (rightPrefix && INVESTIGATION_ACCOUNT_PREFIXES.has(rightPrefix)) {
+      accounts.add(right);
+    }
+  }
+
+  const genericPattern = /\b\d{2}(?:\.\d{1,2})?\b/g;
+  let genericMatch: RegExpExecArray | null = null;
+  while ((genericMatch = genericPattern.exec(lower)) !== null) {
+    const token = String(genericMatch[0] ?? "").trim();
+    const start = genericMatch.index;
+    const end = start + token.length;
+    if (intersectsSpan(start, end, blockedSpans)) {
+      continue;
+    }
+    const prefix = token.match(/^(\d{2})/)?.[1] ?? null;
+    if (!prefix || !INVESTIGATION_ACCOUNT_PREFIXES.has(prefix)) {
+      continue;
+    }
+    if (!hasAccountingLexeme && !hasAccountContextAround(lower, start, end)) {
+      continue;
+    }
+    accounts.add(token);
+  }
+
+  return capStrings(Array.from(accounts), INVESTIGATION_MAX_PRIMARY_ACCOUNTS);
 }
 
 function detectPeriod(text: string): string | null {