feat: support the csv and svg formats

README.md

@@ -2,7 +2,7 @@
 
 [![GitHub](https://img.shields.io/badge/GitHub-181717?logo=github&logoColor=white)](https://github.com/ExaDev/documents) [![CI](https://img.shields.io/github/actions/workflow/status/ExaDev/documents/ci.yml?branch=main)](https://github.com/ExaDev/documents/actions)
 
-> A client-only, statically-built web UI for every conversion and editing tool in the [documents.js ecosystem](../README.md) — convert and edit docx, pptx, xlsx, odt, odp, ods, odg, pdf, and markdown documents entirely in the browser, with no server component.
+> A client-only, statically-built web UI for every conversion and editing tool in the [documents.js ecosystem](../README.md) — convert and edit docx, pptx, xlsx, odt, odp, ods, odg, csv, svg, pdf, and markdown documents entirely in the browser, with no server component.
 
 Private (unpublished to npm); deployed as a static site to GitHub Pages.
 

package.json

@@ -39,7 +39,7 @@
     "@vanilla-extract/recipes": "^0.5.7",
     "dexie": "^4.4.4",
     "dexie-react-hooks": "^4.4.0",
-    "documents.js": "^2.0.0",
+    "documents.js": "^2.3.0",
     "markdown-codec": "^2.0.0",
     "odf.js": "^3.0.1",
     "react": "^19.2.8",

src/hooks/useInspect.ts

@@ -5,7 +5,7 @@ import { getRpcClient } from '../rpc/client';
 import type { Diagnostic } from '../shared/diagnostics';
 import { contentSummary } from '../shared/contentCounts';
 
-// Reads a ContentDocument directly from bytes via the content.read RPC endpoint -- no conversion, no PDF layout pass. Used by every content-backed preview (markdown, docx, odt, xlsx, ods, pptx, odp, odg, odf).
+// Reads a ContentDocument directly from bytes via the content.read RPC endpoint -- no conversion, no PDF layout pass. Used by every content-backed preview (markdown, csv, svg, docx, odt, xlsx, ods, pptx, odp, odg, odf).
 export interface ReadContentInput {
   format: DocumentFormat;
   bytes: Uint8Array<ArrayBuffer>;

src/routes/convert.tsx

@@ -28,16 +28,18 @@ export const Route = createFileRoute('/convert')({
   component: ConvertLayout,
 });
 
+// csv reads as a spreadsheet-kind ContentDocument (readCsvContent), so it previews through the same data grid as xlsx/ods.
 function isSheetFormat(format: string | null): boolean {
-  return format === 'xlsx' || format === 'ods';
+  return format === 'xlsx' || format === 'ods' || format === 'csv';
 }
 
 function isWordProcessingFormat(format: string | null): boolean {
   return format === 'docx' || format === 'odt';
 }
 
+// svg reads as a drawing-kind ContentDocument (readSvgContent), so it previews through the same pages/shapes/vectors renderer as odg.
 function isSlidesFormat(format: string | null): boolean {
-  return format === 'pptx' || format === 'odp' || format === 'odg';
+  return format === 'pptx' || format === 'odp' || format === 'odg' || format === 'svg';
 }
 
 // True for every format whose preview renders the ContentDocument natively via content.read rather than a PDF rendition. PDF itself is the only exception -- its "native" representation IS the PDF bytes rendered in an iframe.

src/rpc/router.ts

@@ -8,6 +8,7 @@ import {
   DOCUMENT_FORMATS,
   extractSourceFontsForFormat,
   LayoutDocumentSchema,
+  readCsvContent,
   readDocxContent,
   readDocxExtras,
   readDocumentMetadata,
@@ -19,6 +20,7 @@ import {
   readMarkdownContent,
   readPptxContent,
   readPdf,
+  readSvgContent,
   readXlsxContent,
   setDocumentMetadata,
 } from 'documents.js';
@@ -184,9 +186,11 @@ const SanitizedLayoutDocumentSchema = LayoutDocumentSchema.extend({
   images: z.record(z.string(), SanitizedLayoutImageAssetSchema),
 });
 
-// Reads a ContentDocument directly from bytes, bypassing the conversion engine entirely -- no target build/encode, no PDF layout pass. Every format's standalone content reader is exported from documents.js (xlsx included since documents.js 2.0 -- before that, xlsx had to detour through the xlsx->ods bridge and read .content off the conversion result).
+// Reads a ContentDocument directly from bytes, bypassing the conversion engine entirely -- no target build/encode, no PDF layout pass. Every format's standalone content reader is exported from documents.js (xlsx included since documents.js 2.0 -- before that, xlsx had to detour through the xlsx->ods bridge and read .content off the conversion result). markdown, csv, and svg are the plain-text formats: their readers take the decoded string, not a package, so each decodes its bytes up front the way markdown always has.
 function readContentForFormat(format: DocumentFormat, bytes: Uint8Array<ArrayBuffer>): ContentDocument {
   if (format === 'markdown') return readMarkdownContent(new TextDecoder().decode(bytes));
+  if (format === 'csv') return readCsvContent(new TextDecoder().decode(bytes));
+  if (format === 'svg') return readSvgContent(new TextDecoder().decode(bytes));
   if (format === 'pdf') throw new Error('PDF has no standalone content reader');
   const pkg = decodeDocumentPackage(format, bytes);
   switch (format) {

src/shared/extensionToFormat.ts

@@ -21,6 +21,8 @@ const EXTENSION_TO_FORMAT: Readonly<Record<string, DocumentFormat>> = {
   otg: 'odg',
   odf: 'odf',
   otf: 'odf',
+  csv: 'csv',
+  svg: 'svg',
   markdown: 'markdown',
   md: 'markdown',
   pdf: 'pdf',