|
|
/**
|
|
|
* Stop pipeline from overwriting bodyText with HTML-normalized / OCR-merged text.
|
|
|
* Parse still uses a local normalized body; OCR stays in ocrText only.
|
|
|
*/
|
|
|
import fs from "fs";
|
|
|
|
|
|
const path = "src/services/parse/pipeline.ts";
|
|
|
let src = fs.readFileSync(path, "utf8");
|
|
|
|
|
|
const oldNorm = ` const subject = mail.subject?.trim() ? mail.subject : "(无主<E697A0>?";
|
|
|
// 历史库可能存了原<E4BA86>?HTML；解析前先归一成纯文本
|
|
|
let body = plainTextFromMaybeHtml(mail.bodyText || "");
|
|
|
if (body && body !== (mail.bodyText || "").trim()) {
|
|
|
await prisma.mailMessage.update({
|
|
|
where: { id: mailId },
|
|
|
data: { bodyText: body },
|
|
|
});
|
|
|
}`;
|
|
|
|
|
|
const neuNorm = ` const subject = mail.subject?.trim() ? mail.subject : "(无主<E697A0>?";
|
|
|
// 解析用归一化正文；绝不回写 bodyText（排查用原文一字不落）
|
|
|
const bodyStored = mail.bodyText || "";
|
|
|
let body = plainTextFromMaybeHtml(bodyStored) || bodyStored;`;
|
|
|
|
|
|
if (!src.includes(oldNorm)) {
|
|
|
const oldCrlf = oldNorm.replace(/\n/g, "\r\n");
|
|
|
if (!src.includes(oldCrlf)) {
|
|
|
console.error("norm block missing");
|
|
|
process.exit(1);
|
|
|
}
|
|
|
src = src.replace(oldCrlf, neuNorm.replace(/\n/g, "\r\n"));
|
|
|
} else {
|
|
|
src = src.replace(oldNorm, neuNorm);
|
|
|
}
|
|
|
|
|
|
const oldOcr = ` body = body.trim()
|
|
|
? \`\${body}\\n\\n\${ocr.text}\`
|
|
|
: ocr.text;
|
|
|
await prisma.mailMessage.update({
|
|
|
where: { id: mailId },
|
|
|
data: { ocrText: ocr.text, bodyText: body },
|
|
|
});`;
|
|
|
|
|
|
const neuOcr = ` // OCR 只写<E58FAA>?ocrText，不污染 bodyText
|
|
|
if (!body.trim()) body = ocr.text;
|
|
|
else body = \`\${body}\\n\\n\${ocr.text}\`;
|
|
|
await prisma.mailMessage.update({
|
|
|
where: { id: mailId },
|
|
|
data: { ocrText: ocr.text },
|
|
|
});`;
|
|
|
|
|
|
if (!src.includes("ocrText: ocr.text, bodyText: body")) {
|
|
|
// try already patched
|
|
|
if (!src.includes("OCR 只写<E58FAA>?ocrText")) {
|
|
|
console.error("ocr block missing", src.includes("bodyText: body"));
|
|
|
process.exit(1);
|
|
|
}
|
|
|
} else {
|
|
|
src = src.replace(
|
|
|
/body = body\.trim\(\)\s*\?\s*`\$\{body\}\\n\\n\$\{ocr\.text\}`\s*:\s*ocr\.text;\s*await prisma\.mailMessage\.update\(\{\s*where: \{ id: mailId \},\s*data: \{ ocrText: ocr\.text, bodyText: body \},\s*\}\);/s,
|
|
|
`// OCR only in ocrText <20>?never overwrite bodyText
|
|
|
if (!body.trim()) body = ocr.text;
|
|
|
else body = \`\${body}\\n\\n\${ocr.text}\`;
|
|
|
await prisma.mailMessage.update({
|
|
|
where: { id: mailId },
|
|
|
data: { ocrText: ocr.text },
|
|
|
});`,
|
|
|
);
|
|
|
}
|
|
|
|
|
|
fs.writeFileSync(path, src);
|
|
|
console.log("pipeline body preserve ok", {
|
|
|
hasStored: src.includes("bodyStored"),
|
|
|
ocrOnly: src.includes("ocrText: ocr.text }") || src.includes("data: { ocrText: ocr.text }"),
|
|
|
});
|
