/**
 * Conservative subject-block strip: stop on body actions / Dear / 新增*
 */
import fs from "fs";

const STRIP_FN = `
function stripSubjectLines(text: string): string {
  const lines = text.split(/\\n/);
  const out: string[] = [];
  let inSubject = false;
  let cont = 0;
  for (const line of lines) {
    // "\\u4e3b\\u9898 Re:..." often has NO colon
    if (/(?:\u4e3b\u9898|\u4e3b\u65e8|Subject)\\s*[\uFF1A:]?/i.test(line)) {
      inSubject = true;
      cont = 0;
      continue;
    }
    if (inSubject) {
      const t = line.trim();
      if (!t) {
        inSubject = false;
        continue;
      }
      // real body starts
      if (
        BODY_ACTION_RE.test(line) ||
        /Dear[,，]/.test(t) ||
        /(?:\u65b0\u589e\u8f6c\u4ed3|\u65b0\u589e\u9884\u62a5|\u8bf7\u67e5\u6536|\u66f4\u65b0\u6d3e\u9001\u5355)/.test(
          t,
        ) ||
        /^\\d+[\\.\\u3001\\uff1a:]/.test(t)
      ) {
        inSubject = false;
        out.push(line);
        continue;
      }
      if (
        /^(?:\u5bc4\u4ef6\u4eba|\u53d1\u4ef6\u4eba|\u6536\u4ef6\u4eba|\u6284\u9001|\u65e5\u671f|\u53d1\u9001\u65f6\u95f4|From|To|Cc|Date|Sent|----)/i.test(
          t,
        ) ||
        /^date@/i.test(t) ||
        t === "date"
      ) {
        inSubject = false;
        out.push(line);
        continue;
      }
      // wrapped subject: ETA / container / voyage fragments only (max 4 lines)
      if (
        cont < 4 &&
        /Fw:|\u8f6c\u53d1|ETA|ETD|\u8239\u540d|\u822a\u6b21|\u67dc\u53f7|[A-Z]{4}\\d{7}|40HQ|20GP|\u4ef6\\+|\\+\\s*$/i.test(
          line,
        )
      ) {
        cont += 1;
        continue;
      }
      inSubject = false;
      out.push(line);
      continue;
    }
    out.push(line);
  }
  return out.join("\\n");
}
`.trimStart();

function replaceStripInLexicon() {
  const path = "src/services/parse/instruction-lexicon.ts";
  let src = fs.readFileSync(path, "utf8");
  const a = src.indexOf("function stripSubjectLines");
  const b = src.indexOf("export function isForwardShellSegment");
  if (a < 0 || b < 0) throw new Error("lexicon markers");
  let start = src.lastIndexOf("/**", a);
  if (start < 0 || a - start > 200) start = a;
  src =
    src.slice(0, start) +
    "/** Drop subject block; stop early on real body actions */\n" +
    STRIP_FN +
    "\n" +
    src.slice(b);
  fs.writeFileSync(path, src);
  console.log("lexicon ok");
}

function replaceBodyDetect() {
  const path = "src/services/parse/split-instructions.ts";
  let src = fs.readFileSync(path, "utf8");
  // Import BODY_ACTION already exists from lexicon
  const neu = `function bodyForKindDetect(segBody: string): string {
  const lines = segBody.split(/\\n/);
  const out: string[] = [];
  let inSubject = false;
  let cont = 0;
  for (const line of lines) {
    if (/(?:\u4e3b\u9898|\u4e3b\u65e8|Subject)\\s*[\uFF1A:]?/i.test(line)) {
      inSubject = true;
      cont = 0;
      continue;
    }
    if (inSubject) {
      const t = line.trim();
      if (!t) {
        inSubject = false;
        continue;
      }
      if (
        BODY_ACTION_RE.test(line) ||
        /Dear[,，]/.test(t) ||
        /(?:\u65b0\u589e\u8f6c\u4ed3|\u65b0\u589e\u9884\u62a5|\u8bf7\u67e5\u6536|\u66f4\u65b0\u6d3e\u9001\u5355)/.test(
          t,
        ) ||
        /^\\d+[\\.\\u3001\\uff1a:]/.test(t)
      ) {
        inSubject = false;
        out.push(line);
        continue;
      }
      if (
        /^(?:\u5bc4\u4ef6\u4eba|\u53d1\u4ef6\u4eba|\u6536\u4ef6\u4eba|\u6284\u9001|\u65e5\u671f|\u53d1\u9001\u65f6\u95f4|From|To|Cc|Date|Sent|----)/i.test(
          t,
        ) ||
        /^date@/i.test(t) ||
        t === "date"
      ) {
        inSubject = false;
        out.push(line);
        continue;
      }
      if (
        cont < 4 &&
        /Fw:|\u8f6c\u53d1|ETA|ETD|\u8239\u540d|\u822a\u6b21|\u67dc\u53f7|[A-Z]{4}\\d{7}|40HQ|20GP|\u4ef6\\+|\\+\\s*$/i.test(
          line,
        )
      ) {
        cont += 1;
        continue;
      }
      inSubject = false;
      out.push(line);
      continue;
    }
    out.push(line);
  }
  return out.join("\\n");
}
`;
  const a = src.indexOf("function bodyForKindDetect");
  const b = src.indexOf("export function detectKindsForSegment");
  if (a < 0 || b < 0) throw new Error("split markers");
  src = src.slice(0, a) + neu + "\n" + src.slice(b);
  fs.writeFileSync(path, src);
  console.log("split ok");
}

replaceStripInLexicon();
replaceBodyDetect();