From 2ca96320579c25643050b53c09a94edb7c89c00d Mon Sep 17 00:00:00 2001 From: sua yoo Date: Wed, 21 Aug 2024 14:03:43 -0700 Subject: [PATCH] feat: Add additional context around workflow job type options (#2032) - Updates workflow job type copy and adds additional clarifying text - Changes "List of URLs" label to "Crawl URL(s)" - Refactors `NewWorkflowDialog` into tailwind element --- docs/user-guide/workflow-setup.md | 12 +- frontend/src/components/ui/config-details.ts | 2 +- .../crawl-workflows/new-workflow-dialog.ts | 192 +++++++++++------- frontend/src/pages/org/workflow-editor.ts | 4 +- 4 files changed, 126 insertions(+), 84 deletions(-) diff --git a/docs/user-guide/workflow-setup.md b/docs/user-guide/workflow-setup.md index b2091070a..4d8163f0d 100644 --- a/docs/user-guide/workflow-setup.md +++ b/docs/user-guide/workflow-setup.md @@ -4,9 +4,13 @@ The first step in creating a new [crawl workflow](crawl-workflows.md) is to choose what type of crawl you want to run. Crawl types are fixed and cannot be converted or changed later. +### Known URLs + `URL List`{ .badge-blue } : The crawler visits every URL specified in a list, and optionally every URL linked on those pages. +### Automated Discovery + `Seeded Crawl`{ .badge-orange } : The crawler automatically discovers and archives pages starting from a single seed URL. @@ -18,7 +22,7 @@ The first step in creating a new [crawl workflow](crawl-workflows.md) is to choo **These credentials WILL BE WRITTEN into the archive.** We recommend exercising caution and only archiving with dedicated archival accounts, changing your password or deleting the account when finished. -### List of URLs +### Crawl URL(s) `URL List`{ .badge-blue } `Seeded Crawl`{ .badge-orange } @@ -30,10 +34,10 @@ It is also available under the _Additional URLs_ section for Seeded Crawls where `URL List`{ .badge-blue } -When enabled, the crawler will visit all the links it finds within each page defined in the _List of URLs_ field. +When enabled, the crawler will visit all the links it finds within each page defined in the _Crawl URL(s)_ field. ??? example "Crawling tags & search queries with URL List crawls" - This setting can be useful for crawling the content of specific tags or search queries. Specify the tag or search query URL(s) in the _List of URLs_ field, e.g: `https://example.com/search?q=tag`, and enable _Include Any Linked Page_ to crawl all the content present on that search query page. + This setting can be useful for crawling the content of specific tags or search queries. Specify the tag or search query URL(s) in the _Crawl URL(s)_ field, e.g: `https://example.com/search?q=tag`, and enable _Include Any Linked Page_ to crawl all the content present on that search query page. ### Fail Crawl on Failed URL @@ -235,7 +239,7 @@ When enabled, a crawl will run immediately on save as if the `Run Immediately on ### Name -Allows a custom name to be set for the workflow. If no name is set, the workflow's name will be set to the _Crawl Start URL_. For URL List crawls, the workflow's name will be set to the first URL present in the _List of URLs_ field, with an added `(+x)` where `x` represents the total number of URLs in the list. +Allows a custom name to be set for the workflow. If no name is set, the workflow's name will be set to the _Crawl Start URL_. For URL List crawls, the workflow's name will be set to the first URL present in the _Crawl URL(s)_ field, with an added `(+x)` where `x` represents the total number of URLs in the list. ### Description diff --git a/frontend/src/components/ui/config-details.ts b/frontend/src/components/ui/config-details.ts index 4189c70cc..106321c85 100644 --- a/frontend/src/components/ui/config-details.ts +++ b/frontend/src/components/ui/config-details.ts @@ -327,7 +327,7 @@ export class ConfigDetails extends LiteElement { return html` ${this.renderSetting( - msg("List of URLs"), + msg("Crawl URL(s)"), html`