Introduce an option to ignore broken links (PacoVK#35)

beyondlex · Jul 26, 2024 · 0213320 · 0213320
1 parent 66f32a7
commit 0213320
Show file tree

Hide file tree

Showing 6 changed files with 30 additions and 16 deletions.
diff --git a/README.md b/README.md
@@ -93,16 +93,17 @@ The Captain will keep track of the pages it has created in Confluence. This is t
 
 ### Configuration
 
-| Option           | Description                                                                                                                  | Info                       |
-| ---------------- | ---------------------------------------------------------------------------------------------------------------------------- | -------------------------- |
-| confluence-api   | URL to your Confluence API endpoint                                                                                          | **required**               |
-| confluence-space | The Confluence space key to publish the pages to                                                                             | **required**               |
-| editor-version   | The Confluence editor version to use to create pages                                                                         | v1 (default) / v2          |
-| filters          | Specify paths or files that you want to publish to Confluence                                                                | [] (default)               |
-| ancestor-id      | Specify the overall parent page for your docs. Needs to be the pageId of the parent page, not the DisplayName.               | defaults to the space root |
-| show-banner      | Specify if all your pages should contain an info banner, that this pages were created by automation and changes may be lost. | false (default)            |
-| mapper           | Specify a custom mapper to map the Antora pages to Confluence pages.                                                         | [] (default)               |
-| exclude-files    | Specify files that should be excluded from the publishing process. Wildcards and Glob-patterns are supported                 | [] (default)               |
+| Option              | Description                                                                                                                  | Info                       |
+|---------------------|------------------------------------------------------------------------------------------------------------------------------|----------------------------|
+| confluence-api      | URL to your Confluence API endpoint                                                                                          | **required**               |
+| confluence-space    | The Confluence space key to publish the pages to                                                                             | **required**               |
+| editor-version      | The Confluence editor version to use to create pages                                                                         | v1 (default) / v2          |
+| filters             | Specify paths or files that you want to publish to Confluence                                                                | [] (default)               |
+| ancestor-id         | Specify the overall parent page for your docs. Needs to be the pageId of the parent page, not the DisplayName.               | defaults to the space root |
+| ignore-broken-links | Specify whether to ignore broken link references to other pages that are not included                                        | defaults to false          |
+| show-banner         | Specify if all your pages should contain an info banner, that this pages were created by automation and changes may be lost. | false (default)            |
+| mapper              | Specify a custom mapper to map the Antora pages to Confluence pages.                                                         | [] (default)               |
+| exclude-files       | Specify files that should be excluded from the publishing process. Wildcards and Glob-patterns are supported                 | [] (default)               |
 
 #### Using Mappers
 

diff --git a/index.ts b/index.ts
@@ -40,6 +40,7 @@ const publishToConfluence = async (
     baseUrl: new URL(destConfig.confluenceApi),
     spaceKey: destConfig.confluenceSpace,
     ancestorId: destConfig.ancestorId,
+    ignoreBrokenLinks: destConfig.ignoreBrokenLinks,
   });
   await confluenceClient.init();
   const pageStructure = new Map();

diff --git a/lib/client/ConfluenceClient.ts b/lib/client/ConfluenceClient.ts
@@ -10,6 +10,7 @@ interface ConfluenceClientOptions {
   spaceKey: string;
   editorVersion: string;
   ancestorId?: string;
+  ignoreBrokenLinks?: boolean;
 }
 
 const LOGGER = getLogger();
@@ -27,6 +28,7 @@ export abstract class ConfluenceClient {
   readonly BASE_URL;
   readonly AUTHORIZATION_HEADER;
   readonly ANCESTOR_ID;
+  readonly IGNORE_BROKEN_LINKS;
 
   constructor(config: ConfluenceClientOptions) {
     this.BASE_URL = new URL(config.baseUrl.origin);
@@ -42,6 +44,7 @@ export abstract class ConfluenceClient {
     this.API_V2_PATH = apiContext + this.API_V2_IDENTIFIER;
     this.AUTHORIZATION_HEADER = this.buildAuthHeader();
     this.ANCESTOR_ID = config.ancestorId;
+    this.IGNORE_BROKEN_LINKS = config.ignoreBrokenLinks ?? false;
   }
 
   async init() {

diff --git a/lib/service/PageService.ts b/lib/service/PageService.ts
@@ -247,6 +247,7 @@ const publish = async (
           outPutDir,
           showBanner,
           flatPages,
+          confluenceClient.IGNORE_BROKEN_LINKS,
         );
         if (confluencePage) {
           const localHash = confluencePage.hash;
@@ -394,6 +395,7 @@ const processPage = (
   outPutDir: string,
   showBanner: boolean,
   flatPages: any,
+  ignoreBrokenLinks: boolean,
 ) => {
   LOGGER.info(`Processing ${page.fileName}`);
   const baseUrl = path.join(process.cwd(), outPutDir, Path.dirname(page.fqfn));
@@ -411,7 +413,7 @@ const processPage = (
     rewriteAdmonitionBlocks(content);
     rewriteCodeBlocks(content);
     rewriteMarks(content);
-    rewriteInternalLinks(content, page.fqfn, flatPages);
+    rewriteInternalLinks(content, page.fqfn, flatPages, ignoreBrokenLinks);
     rewriteDescriptionLists(content);
     rewriteCDATASections(content);
 

diff --git a/lib/transformer/LinkTransformer.ts b/lib/transformer/LinkTransformer.ts
@@ -77,6 +77,7 @@ const rewriteInternalLinks = (
   content: HTMLElement,
   baseUrl: string,
   flatPages: any,
+  ignoreBrokenLinks: boolean,
 ) => {
   content.querySelectorAll("a[href]").forEach((a) => {
     const href = a.getAttribute("href");
@@ -100,13 +101,18 @@ const rewriteInternalLinks = (
           linkedPageFqfn = hrefWithAnchor[0];
           anchor = hrefWithAnchor[1];
         }
-        pageTitle = findLinkedPageInTree(
+        const linkedPage = findLinkedPageInTree(
           flatPages,
           path.join(path.dirname(baseUrl), linkedPageFqfn),
-        )?.pageTitle;
-        LOGGER.debug(
-          `Rewrite link to other page with title ${pageTitle} original link was ${href}`,
-        );
+        )
+        if (linkedPage) {
+          pageTitle = linkedPage.pageTitle;
+          LOGGER.debug(`Rewrite link to other page with title ${pageTitle}, original link was ${href}`);
+        } else {
+          if (!ignoreBrokenLinks) {
+            throw new Error(`The page '${baseUrl}' contains broken links, you can ignore this by setting 'ignore-broken-links' to true.`);
+          }
+        }
       }
       if (pageTitle && a.text) {
         const linkMacro =

diff --git a/lib/types/index.ts b/lib/types/index.ts
@@ -46,6 +46,7 @@ export type CaptainConfig = {
   excludeFiles?: string[];
   mapper?: PathMapper[];
   filter?: PageFilter[];
+  ignoreBrokenLinks?: boolean;
 };
 
 export interface PathMapper {