fix(tools): recognized zip-family archives and pruned unconvertible extensions
- Treated ZIP-based .jar/.war/.ear/.apk as zip archives in archiveFormatFromPath and parseArchivePathCandidates so read/write member access works. - Shared one archive-extension alternation between format detection and path splitting to stop them drifting. - Derived the markit convertible-extension set from a single source of truth (utils/markit) matching the registered converters (pdf/docx/pptx/xlsx/epub), dropping legacy .doc/.ppt/.xls/.rtf that had no converter and only produced Unsupported format errors. - Updated read/write tool prompts to document the zip-family extensions. Fixes #5808
This commit is contained in:
@@ -9,13 +9,12 @@ import chalk from "chalk";
|
||||
import { resolveReadPath } from "../tools/path-utils";
|
||||
import { formatBytes } from "../tools/render-utils";
|
||||
import { formatDimensionNote, resizeImage } from "../utils/image-resize";
|
||||
import { convertFileWithMarkit } from "../utils/markit";
|
||||
import { CONVERTIBLE_EXTENSIONS, convertFileWithMarkit } from "../utils/markit";
|
||||
|
||||
// Keep CLI startup responsive and avoid OOM when users pass huge files.
|
||||
// If a file exceeds these limits, we include it as a path-only <file/> block.
|
||||
const MAX_CLI_TEXT_BYTES = 5 * 1024 * 1024; // 5MB
|
||||
const MAX_CLI_IMAGE_BYTES = 25 * 1024 * 1024; // 25MB
|
||||
const CONVERTIBLE_EXTENSIONS = new Set([".pdf", ".doc", ".docx", ".ppt", ".pptx", ".xls", ".xlsx", ".rtf", ".epub"]);
|
||||
|
||||
export interface ProcessedFiles {
|
||||
text: string;
|
||||
|
||||
Reference in New Issue
Block a user