From 1214942eb7d36a3f51286046714d9020b7521355 Mon Sep 17 00:00:00 2001
From: twwu <twwu@dify.ai>
Date: Wed, 3 Sep 2025 20:32:48 +0800
Subject: [PATCH] refactor(datasets): rename 'markdown' to 'content' for
 consistency across components

---
 .../create/website/base/mock-crawl-result.ts     |  6 +++---
 .../create/website/jina-reader/index.tsx         |  9 +++++----
 .../datasets/create/website/preview.tsx          |  2 +-
 .../data-source/website-crawl/index.tsx          |  8 +-------
 .../documents/create-from-pipeline/hooks.ts      |  2 +-
 .../create-from-pipeline/preview/web-preview.tsx |  4 ++--
 .../detail/settings/document-settings.tsx        |  2 +-
 .../detail/settings/pipeline-settings/index.tsx  | 16 +++++++---------
 web/app/components/workflow/nodes/tool/panel.tsx |  2 +-
 web/models/datasets.ts                           |  3 ++-
 10 files changed, 24 insertions(+), 30 deletions(-)

diff --git a/web/app/components/datasets/create/website/base/mock-crawl-result.ts b/web/app/components/datasets/create/website/base/mock-crawl-result.ts
index 8fd5e6636f..88c05d3d0a 100644
--- a/web/app/components/datasets/create/website/base/mock-crawl-result.ts
+++ b/web/app/components/datasets/create/website/base/mock-crawl-result.ts
@@ -3,19 +3,19 @@ import type { CrawlResultItem } from '@/models/datasets'
 const result: CrawlResultItem[] = [
   {
     title: 'Start the frontend Docker container separately',
-    markdown: 'Markdown 1',
+    content: 'Markdown 1',
     description: 'Description 1',
     source_url: 'https://example.com/1',
   },
   {
     title: 'Advanced Tool Integration',
-    markdown: 'Markdown 2',
+    content: 'Markdown 2',
     description: 'Description 2',
     source_url: 'https://example.com/2',
   },
   {
     title: 'Local Source Code Start | English | Dify',
-    markdown: 'Markdown 3',
+    content: 'Markdown 3',
     description: 'Description 3',
     source_url: 'https://example.com/3',
   },
diff --git a/web/app/components/datasets/create/website/jina-reader/index.tsx b/web/app/components/datasets/create/website/jina-reader/index.tsx
index 6e513dd797..460c169fb4 100644
--- a/web/app/components/datasets/create/website/jina-reader/index.tsx
+++ b/web/app/components/datasets/create/website/jina-reader/index.tsx
@@ -150,14 +150,15 @@ const JinaReader: FC<Props> = ({
       }) as any
 
       if (res.data) {
+        const { title, content, description, url } = res.data
         const data = {
           current: 1,
           total: 1,
           data: [{
-            title: res.data.title,
-            markdown: res.data.content,
-            description: res.data.description,
-            source_url: res.data.url,
+            title,
+            content,
+            description,
+            source_url: url,
           }],
           time_consuming: (Date.now() - startTime) / 1000,
         }
diff --git a/web/app/components/datasets/create/website/preview.tsx b/web/app/components/datasets/create/website/preview.tsx
index f43dc83589..d148c87196 100644
--- a/web/app/components/datasets/create/website/preview.tsx
+++ b/web/app/components/datasets/create/website/preview.tsx
@@ -32,7 +32,7 @@ const WebsitePreview = ({
         <div className='system-xs-medium truncate text-text-tertiary' title={payload.source_url}>{payload.source_url}</div>
       </div>
       <div className={cn(s.previewContent, 'body-md-regular')}>
-        <div className={cn(s.fileContent)}>{payload.markdown}</div>
+        <div className={cn(s.fileContent)}>{payload.content}</div>
       </div>
     </div>
   )
diff --git a/web/app/components/datasets/documents/create-from-pipeline/data-source/website-crawl/index.tsx b/web/app/components/datasets/documents/create-from-pipeline/data-source/website-crawl/index.tsx
index 4861224661..4d39378e53 100644
--- a/web/app/components/datasets/documents/create-from-pipeline/data-source/website-crawl/index.tsx
+++ b/web/app/components/datasets/documents/create-from-pipeline/data-source/website-crawl/index.tsx
@@ -115,13 +115,7 @@ const WebsiteCrawl = ({
         onDataSourceNodeCompleted: (data: DataSourceNodeCompletedResponse) => {
           const { data: crawlData, time_consuming } = data
           const crawlResultData = {
-            data: crawlData.map((item: any) => {
-              const { content, ...rest } = item
-              return {
-                markdown: content || '',
-                ...rest,
-              } as CrawlResultItem
-            }),
+            data: crawlData as CrawlResultItem[],
             time_consuming: time_consuming ?? 0,
           }
           setCrawlResult(crawlResultData)
diff --git a/web/app/components/datasets/documents/create-from-pipeline/hooks.ts b/web/app/components/datasets/documents/create-from-pipeline/hooks.ts
index 45dcaa6111..2018d43910 100644
--- a/web/app/components/datasets/documents/create-from-pipeline/hooks.ts
+++ b/web/app/components/datasets/documents/create-from-pipeline/hooks.ts
@@ -196,7 +196,7 @@ export const useOnlineDrive = () => {
   const dataSourceStore = useDataSourceStore()
 
   const selectedOnlineDriveFileList = useMemo(() => {
-    return selectedFileIds.map(key => onlineDriveFileList.find(item => item.id === key)!)
+    return selectedFileIds.map(id => onlineDriveFileList.find(item => item.id === id)!)
   }, [onlineDriveFileList, selectedFileIds])
 
   const clearOnlineDriveData = useCallback(() => {
diff --git a/web/app/components/datasets/documents/create-from-pipeline/preview/web-preview.tsx b/web/app/components/datasets/documents/create-from-pipeline/preview/web-preview.tsx
index ce7a5da24c..bae4deb86e 100644
--- a/web/app/components/datasets/documents/create-from-pipeline/preview/web-preview.tsx
+++ b/web/app/components/datasets/documents/create-from-pipeline/preview/web-preview.tsx
@@ -27,7 +27,7 @@ const WebsitePreview = ({
             <span className='uppercase' title={currentWebsite.source_url}>{currentWebsite.source_url}</span>
             <span>·</span>
             <span>·</span>
-            <span>{`${formatNumberAbbreviated(currentWebsite.markdown.length)} ${t('datasetPipeline.addDocuments.characters')}`}</span>
+            <span>{`${formatNumberAbbreviated(currentWebsite.content.length)} ${t('datasetPipeline.addDocuments.characters')}`}</span>
           </div>
         </div>
         <button
@@ -39,7 +39,7 @@ const WebsitePreview = ({
         </button>
       </div>
       <div className='body-md-regular grow overflow-hidden px-6 py-5 text-text-secondary'>
-        {currentWebsite.markdown}
+        {currentWebsite.content}
       </div>
     </div>
   )
diff --git a/web/app/components/datasets/documents/detail/settings/document-settings.tsx b/web/app/components/datasets/documents/detail/settings/document-settings.tsx
index 199f77ca57..048645c9cf 100644
--- a/web/app/components/datasets/documents/detail/settings/document-settings.tsx
+++ b/web/app/components/datasets/documents/detail/settings/document-settings.tsx
@@ -70,7 +70,7 @@ const DocumentSettings = ({ datasetId, documentId }: DocumentSettingsProps) => {
               {
                 title: documentDetail.name,
                 source_url: documentDetail.data_source_info?.url,
-                markdown: '',
+                content: '',
                 description: '',
               },
             ]}
diff --git a/web/app/components/datasets/documents/detail/settings/pipeline-settings/index.tsx b/web/app/components/datasets/documents/detail/settings/pipeline-settings/index.tsx
index 0ebed7ab35..b13e7743b0 100644
--- a/web/app/components/datasets/documents/detail/settings/pipeline-settings/index.tsx
+++ b/web/app/components/datasets/documents/detail/settings/pipeline-settings/index.tsx
@@ -9,12 +9,11 @@ import ProcessDocuments from './process-documents'
 import LeftHeader from './left-header'
 import { usePipelineExecutionLog, useRunPublishedPipeline } from '@/service/use-pipeline'
 import type { OnlineDriveFile, PublishedPipelineRunPreviewResponse } from '@/models/pipeline'
-import { DatasourceType, OnlineDriveFileType } from '@/models/pipeline'
+import { DatasourceType } from '@/models/pipeline'
 import { noop } from 'lodash-es'
 import { useDatasetDetailContextWithSelector } from '@/context/dataset-detail'
 import { useRouter } from 'next/navigation'
 import { useInvalidDocumentDetail, useInvalidDocumentList } from '@/service/knowledge/use-document'
-import { isFile } from '../../../create-from-pipeline/data-source/online-drive/utils'
 
 type PipelineSettingsProps = {
   datasetId: string
@@ -56,7 +55,7 @@ const PipelineSettings = ({
     if (lastRunData?.datasource_type === DatasourceType.websiteCrawl) {
       const { content, description, source_url, title } = lastRunData.datasource_info
       websitePages.push({
-        markdown: content,
+        content,
         description,
         source_url,
         title,
@@ -80,13 +79,12 @@ const PipelineSettings = ({
   const onlineDriveFiles = useMemo(() => {
     const onlineDriveFiles: OnlineDriveFile[] = []
     if (lastRunData?.datasource_type === DatasourceType.onlineDrive) {
-      const { key } = lastRunData.datasource_info
-      const isFileType = isFile(key)
-      const filePathList = key.split('/')
+      const { id, type, name, size } = lastRunData.datasource_info
       onlineDriveFiles.push({
-        key,
-        displayName: `${isFileType ? filePathList.pop() : filePathList[filePathList.length - 2]}${isFileType ? '' : '/'}`,
-        type: isFileType ? OnlineDriveFileType.file : OnlineDriveFileType.folder,
+        id,
+        name,
+        type,
+        size,
       })
     }
     return onlineDriveFiles
diff --git a/web/app/components/workflow/nodes/tool/panel.tsx b/web/app/components/workflow/nodes/tool/panel.tsx
index 785ae027f6..b7bdb02a97 100644
--- a/web/app/components/workflow/nodes/tool/panel.tsx
+++ b/web/app/components/workflow/nodes/tool/panel.tsx
@@ -137,7 +137,7 @@ const Panel: FC<NodePanelProps<ToolNodeType>> = ({
                   )}
                 </div>
               )
-          })}
+            })}
           </>
         </OutputVars>
       </div>
diff --git a/web/models/datasets.ts b/web/models/datasets.ts
index 25fec8cfca..8132acb83f 100644
--- a/web/models/datasets.ts
+++ b/web/models/datasets.ts
@@ -153,7 +153,7 @@ export type CrawlOptions = {
 
 export type CrawlResultItem = {
   title: string
-  markdown: string
+  content: string
   description: string
   source_url: string
 }
@@ -324,6 +324,7 @@ export type DataSourceInfo = {
   provider?: DataSourceProvider
   job_id: string
   url: string
+  credential_id?: string
 }
 
 export type InitialDocumentDetail = {