|
|
import fs from "fs";
|
|
|
|
|
|
const lexPath = "src/services/parse/instruction-lexicon.ts";
|
|
|
let lex = fs.readFileSync(lexPath, "utf8");
|
|
|
|
|
|
if (!lex.includes("isForwardShellSegment")) {
|
|
|
lex = lex.replace(
|
|
|
`export function isNonInstructionSegment(text: string): boolean {
|
|
|
const compact = text.replace(/\\s+/g, " ").trim();
|
|
|
if (compact.length < 6) return true;`,
|
|
|
`/** QQ/中间人纯转发壳，无客<E697A0>?Dear 正文 */
|
|
|
export function isForwardShellSegment(text: string): boolean {
|
|
|
const compact = text.replace(/\\s+/g, " ").trim();
|
|
|
if (/发自我的iPhone/.test(compact)) return true;
|
|
|
if (
|
|
|
/date@usasinogroup\\.com/i.test(compact) &&
|
|
|
!/Dear[,，]/.test(compact) &&
|
|
|
!BODY_ACTION_RE.test(compact)
|
|
|
) {
|
|
|
return true;
|
|
|
}
|
|
|
return false;
|
|
|
}
|
|
|
|
|
|
export function isNonInstructionSegment(text: string): boolean {
|
|
|
const compact = text.replace(/\\s+/g, " ").trim();
|
|
|
if (compact.length < 6) return true;
|
|
|
if (isForwardShellSegment(text)) return true;`,
|
|
|
);
|
|
|
fs.writeFileSync(lexPath, lex, "utf8");
|
|
|
}
|
|
|
|
|
|
const splitPath = "src/services/parse/split-instructions.ts";
|
|
|
let sp = fs.readFileSync(splitPath, "utf8");
|
|
|
|
|
|
if (!sp.includes("bodyForKindDetect")) {
|
|
|
sp = sp.replace(
|
|
|
`export function detectKindsForSegment(
|
|
|
segSubject: string,
|
|
|
segBody: string,
|
|
|
): InstructionUiKind[] {
|
|
|
if (isNonInstructionSegment(segBody)) return [];
|
|
|
const bodyHits = matchKeywordRules(segBody, "body");
|
|
|
const useSubject =
|
|
|
!BODY_ACTION_RE.test(segBody) ||
|
|
|
/新增预报|请查收新增预<E5A29E>?.test(segBody);
|
|
|
const subjectHits = useSubject
|
|
|
? matchKeywordRules(segSubject, "subject")
|
|
|
: [];
|
|
|
const kinds = new Set<InstructionUiKind>([
|
|
|
...bodyHits.map((h) => h.uiKind),
|
|
|
...subjectHits.map((h) => h.uiKind),
|
|
|
]);
|
|
|
return UI_KIND_ORDER.filter((k) => kinds.has(k));
|
|
|
}`,
|
|
|
`/** 去掉段内「主<E3808C>? Re:Re:新增预报」历史主题污<E9A298>?*/
|
|
|
function bodyForKindDetect(segBody: string): string {
|
|
|
if (!BODY_ACTION_RE.test(segBody)) return segBody;
|
|
|
return segBody
|
|
|
.split(/\\n/)
|
|
|
.filter(
|
|
|
(line) =>
|
|
|
!/(?:主题|主旨|Subject)\\s*[<5B>?].*(?:新增预报|Fw:|转发)/i.test(line),
|
|
|
)
|
|
|
.join("\\n");
|
|
|
}
|
|
|
|
|
|
export function detectKindsForSegment(
|
|
|
segSubject: string,
|
|
|
segBody: string,
|
|
|
): InstructionUiKind[] {
|
|
|
if (isNonInstructionSegment(segBody)) return [];
|
|
|
const bodyText = bodyForKindDetect(segBody);
|
|
|
const bodyHits = matchKeywordRules(bodyText, "body");
|
|
|
const useSubject =
|
|
|
!BODY_ACTION_RE.test(segBody) ||
|
|
|
/请查收新增预<E5A29E>?.test(bodyText);
|
|
|
const subjectHits = useSubject
|
|
|
? matchKeywordRules(segSubject, "subject")
|
|
|
: [];
|
|
|
const kinds = new Set<InstructionUiKind>([
|
|
|
...bodyHits.map((h) => h.uiKind),
|
|
|
...subjectHits.map((h) => h.uiKind),
|
|
|
]);
|
|
|
return UI_KIND_ORDER.filter((k) => kinds.has(k));
|
|
|
}`,
|
|
|
);
|
|
|
fs.writeFileSync(splitPath, sp, "utf8");
|
|
|
}
|
|
|
|
|
|
console.log(
|
|
|
JSON.stringify({
|
|
|
lex: fs.readFileSync(lexPath, "utf8").includes("isForwardShellSegment"),
|
|
|
split: fs.readFileSync(splitPath, "utf8").includes("bodyForKindDetect"),
|
|
|
}),
|
|
|
);
|
