mesalogo
8a63ac9ee8
Image-only PPTX attachments failed with no indexable text even when a local OCR model was configured. PPTX parsing now recognizes embedded PNG, JPEG and WebP images through the existing local OCR path, preserves native text and slide locators, and honors the selected parsing workflow. OCR workers previously retained model sessions and WASM memory indefinitely after successful parsing. Release the worker after 60 seconds with no active or queued requests, reuse it for continuous work, and reload on demand. Fast text/index modes still skip OCR. This does not render Office layouts, recognize inherited master images, or change Agent execution permissions. Validated four real PPTX attachments (40 pages), idle memory release and a nine-page reimport after model reload on Windows x64 with PP-OCRv6 Tiny. 49 local OCR requests and zero text-model calls. All 4293 tests passed with 67 skipped; typecheck, lint and the isolated Electron build passed. Release note: 修复已配置本地 OCR 时图片型 PPTX 仍无法导入的问题，识别结果保留幻灯片定位。OCR 空闲 60 秒后自动释放模型运行内存，连续解析复用模型，下次使用时自动重新加载。
17 lines
636 B
TypeScript
17 lines
636 B
TypeScript
import { strToU8, zipSync } from 'fflate'
|
|
|
|
export function createImagePptx(nativeText = '', pageCount = 1): Buffer {
|
|
const files: Record<string, Uint8Array> = {
|
|
'ppt/media/image1.png': new Uint8Array([1, 2, 3])
|
|
}
|
|
for (let page = 1; page <= pageCount; page += 1) {
|
|
files[`ppt/slides/slide${page}.xml`] = strToU8(
|
|
`<p:sld><a:p><a:t>${nativeText}</a:t></a:p><p:pic><a:blip r:embed="rId1"/></p:pic></p:sld>`
|
|
)
|
|
files[`ppt/slides/_rels/slide${page}.xml.rels`] = strToU8(
|
|
'<Relationships><Relationship Id="rId1" Target="../media/image1.png"/></Relationships>'
|
|
)
|
|
}
|
|
return Buffer.from(zipSync(files))
|
|
}
|