Customize pdf export using Script Runner for Confluence Server

[Ramakrishnan Srinivasan]

Hi, 

I have made some customization of pdf export of a Confluence page. Sharing my approach here for others to try/benefit.

My Setup:

• Confluence Server - 7.3.2
• Script Runner for Confluence - 6.2.0-p5
• Table Filter and Charts for Confluence - 5.3.25
• Confluence has HTML macro enabled

My Approach:

• Create Custom Menu to do the job
• Create a temporary page which can be trashed once export job is done
• Get the page content as string, customize it (in my case remove jira issues hyperlinks)
• Edit the temporary page and update it with customized content, redirect the page;
• With delay from javascript redirect it to pdf export link again

My Configurations

• In Confluence Script Runner - Fragment -Create Script Fragments - Custom WebItem
  • What Section this should go in - system.content.action/secondary
  • Key: external-pdf
  • Menu Text - Custom
  • Weight - 1
  • Condition (such that this custom menu is displayed only in some pages)
    • if(context.space.key == "SOME_SPACE_KEY" && context.page.title.contains("SOME UNIQ TITLE STRING ") && !(context.page.title.contains("NEGATE TITLE"))) {
      return true
      } else {
      return false
      }
  • Do What - Navigate to Link
  • Link - https://HOST/wiki/rest/scriptrunner/latest/custom/exportPage_toPDF?spaceKey=<SOME SPACE KEY>&parentPageTitle=${page.title}
• In Confluence Script Runner - Jobs - setup to trash the temporary page

  • import com.atlassian.sal.api.component.ComponentLocator
    import com.atlassian.confluence.spaces.Space
    import com.atlassian.confluence.spaces.SpaceManager
    import com.atlassian.confluence.core.DefaultDeleteContext
    import com.atlassian.confluence.pages.Page
    import com.atlassian.confluence.pages.PageManager

    def spaceManager = ComponentLocator.getComponent(SpaceManager)
    def pageManager = ComponentLocator.getComponent(PageManager)

    def parentPage=pageManager.getPage("SOME_SPACE_KEY", "TO DELETE PAGES")
    def childPages = pageManager.getDescendants(parentPage)

    if(childPages) {
         childPages.each { thisChild ->
                   pageManager.trashPage(thisChild, DefaultDeleteContext.DEFAULT)
          }
    }

• In Confluence Script Runner - REST Endpoint

  • //This script is loaded in Confluence - Script Runner - Rest End Point
    //It takes the spaceKey and page title as url parameters
    //gets page content
    //replacesAll href of jira issue links
    //relacesAll Back to Top CDATA
    //creates a child page from replaced string
    //redirects that child page for pdf download after the page is loaded in browser
    
    /*import org.apache.log4j.Level
    import org.apache.log4j.Logger
    def logx = Logger.getLogger("com.acme.workflows")
    logx.setLevel(Level.DEBUG)*/
    
    import org.apache.http.HttpRequest
    import org.apache.http.protocol.HttpContext
    import groovy.json.JsonBuilder
    import groovy.json.JsonSlurper
    import org.apache.http.HttpRequestInterceptor
    import groovyx.net.http.HTTPBuilder
    import net.sf.json.JSONArray
    import groovyx.net.http.RESTClient
    import static groovyx.net.http.Method.GET
    import static groovyx.net.http.ContentType.JSON
    import groovy.transform.Field
    
    import org.codehaus.groovy.runtime.MethodClosure
    import org.apache.http.HttpEntity;
    import org.apache.http.HttpEntityEnclosingRequest
    
    import java.io.InputStreamReader
    
    import com.atlassian.confluence.setup.settings.SettingsManager
    import com.atlassian.confluence.core.BodyContent
    import com.atlassian.confluence.core.BodyType
    import com.atlassian.confluence.core.DefaultSaveContext
    import com.atlassian.confluence.core.DefaultDeleteContext
    import com.atlassian.confluence.pages.DuplicateDataRuntimeException
    import com.atlassian.confluence.pages.Page
    import com.atlassian.confluence.pages.PageManager
    import com.atlassian.confluence.pages.templates.PageTemplateManager
    import com.atlassian.confluence.security.Permission
    import com.atlassian.confluence.security.PermissionManager
    import com.atlassian.confluence.spaces.Space
    import com.atlassian.confluence.spaces.SpaceManager
    import com.atlassian.confluence.user.AuthenticatedUserThreadLocal
    import com.atlassian.sal.api.component.ComponentLocator
    import com.onresolve.scriptrunner.canned.confluence.utils.PermissionDeniedException
    import com.onresolve.scriptrunner.runner.rest.common.CustomEndpointDelegate
    import groovy.json.JsonOutput
    import groovy.transform.BaseScript
    import groovy.transform.Field
    import org.apache.log4j.Logger
    
    import javax.ws.rs.core.MultivaluedMap
    import javax.ws.rs.core.Response
    
    import java.text.SimpleDateFormat
    
    import groovy.time.TimeCategory 
    import groovy.time.TimeDuration
    
    
    Date start = new Date()
    
    @Field SpaceManager spaceManager = ComponentLocator.getComponent(SpaceManager)
    @Field PageManager pageManager = ComponentLocator.getComponent(PageManager)
    @Field PermissionManager permissionManager = ComponentLocator.getComponent(PermissionManager)
    @Field PageTemplateManager pageTemplateManager = ComponentLocator.getComponent(PageTemplateManager)
    //@Field Logger log = Logger.getLogger("com.onresolve.scriptrunner.runner.ScriptRunnerImpl")
    
    @BaseScript CustomEndpointDelegate delegate
    
    //End point name is the same as the method's name
    //exportPage_toPDF_withoutJira_hyperLinks(httpMethod: "GET", groups: ["confluence-administrators", "confluence-users"]) { MultivaluedMap queryParams, String body ->
    exportPage_toPDF_withoutJira_hyperLinks(httpMethod: "GET") { MultivaluedMap queryParams, String body ->
    
    Date date = new Date()
    String datePart = date.format("dd/MMM/yyyy")
    String timePart = date.format("HH:mm:ss.SSS")
    String dateTimeStamp = date.format("dd/MMM/yyyy HH:mm:ss.SSS")
    
    pageManager = ComponentLocator.getComponent(PageManager)
    
    def spaceKey = queryParams.getFirst("spaceKey").toString()
    def parentPageTitle = queryParams.getFirst("parentPageTitle").toString()
    
    try {
    parentPage=pageManager.getPage(spaceKey, parentPageTitle)
    def contentEntityObject = parentPage.getEntity()
    def parentPageBody=parentPage.getBodyAsString()
    
    def space = spaceManager.getSpace(spaceKey) as Space
    def childPageTitle = parentPageTitle + " - External"
    def childPage = pageManager.getPage(spaceKey, childPageTitle)
    
    if(childPage) {
    pageManager.trashPage(childPage, DefaultDeleteContext.DEFAULT)
    }
    
    def HTML_A_HREF_TAG_PATTERN_jira = "\\s*(?i)href\\s*=\\s*\"([^\"]*jira/browse/[^\"]*\")"
    def regex_BacktoTop = "<p><ac:link ac:anchor=\"_wiki_toc\"><ri:content-entity ri:content-id=\"\\d+\" /><ac:plain-text-link-body><!\\[CDATA\\[Back to Top\\]\\]></ac:plain-text-link-body></ac:link></p>"
    
    
    def childPageContent = parentPageBody.replaceAll(HTML_A_HREF_TAG_PATTERN_jira, "dummy")
    childPageContent = childPageContent.replaceAll(regex_BacktoTop, "")
    
    
    def regex_jiraMacro = "<p style=\"font-size: 15.0px;\"><strong>G3 Issue used to create this Release Page</strong></p><p><ac:structured-macro ac:name=\"jira\" ac:schema-version=\"\\d+\" ac:macro-id=\"([a-zA-Z0-9*--]+)\"><ac:parameter ac:name=\"server\">Jira</ac:parameter><ac:parameter ac:name=\"serverId\">([a-zA-Z0-9*--]+)</ac:parameter><ac:parameter ac:name=\"key\">((?<!([A-Za-z]{1,10})-?)[A-Z]+-\\d+)</ac:parameter></ac:structured-macro></p>"
    childPageContent = childPageContent.replaceAll(regex_jiraMacro, "")
    
    def regex_history = "<h1>Document history</h1><p><ac:structured-macro ac:name=\"version-history\" ac:schema-version=\"\\d+\" ac:macro-id=\"([a-zA-Z0-9*--]+)\" /></p>"
    childPageContent = childPageContent.replaceAll(regex_history, "")
    
    def toDelete_parentPage=pageManager.getPage(spaceKey, "TO DELETE PAGES")
    
    def createdChildPageId = createBasicPage(space, toDelete_parentPage, childPageTitle, "Temporary Page")
    
    def tableFilterString = "<ac:structured-macro ac:name=\"table-filter\" ac:schema-version=\"1\""
    
    def loadResources = "" //tf-export-ready is Table filter element
    
    if(childPageContent.contains(tableFilterString)) {
    loadResources = "<ac:structured-macro ac:name=\"html\">\
    <ac:plain-text-body><![CDATA[\
    <script type=\"text/javascript\">\
    AJS.toInit(function() {\
    AJS.\$('#editPageLink').hide();\
    AJS.bind('tf-export-ready', function() {\
    setTimeout(function() {AJS.\$(location).prop('href', 'https://HOST/wiki/spaces/flyingpdf/pdfpageexport.action?pageId=" + createdChildPageId + "');}, 2000);\
    });\
    });\
    </script>]]>\
    </ac:plain-text-body>\
    </ac:structured-macro>"
    } else {
    //removed AJS.bind('tf-export-ready', function() {\
    loadResources = "<ac:structured-macro ac:name=\"html\">\
    <ac:plain-text-body><![CDATA[\
    <script type=\"text/javascript\">\
    AJS.toInit(function() {\
    AJS.\$('#editPageLink').hide();\
    setTimeout(function() {AJS.\$(location).prop('href', 'https://HOST/wiki/spaces/flyingpdf/pdfpageexport.action?pageId=" + createdChildPageId + "');}, 2000);\
    });\
    </script>]]>\
    </ac:plain-text-body>\
    </ac:structured-macro>"
    }
    
    childPageContent = childPageContent.replaceAll("dummy", "") + loadResources
    
    editPage("${createdChildPageId}", childPageTitle, childPageContent, "2")
    
    pageUrl = "https://HOST/wiki/pages/viewpage.action?pageId=${createdChildPageId}"
    return Response.temporaryRedirect(URI.create(pageUrl)).build()
    } catch(Exception ex) {
    //pageIdMap["Exception"] = "Exception to get page or append page for spaceKey = ${spaceKey} and title = ${title}: ${ex.toString()}"
    }
    }
    
    /**
    * Create a basic page. This is not linked in any hierarchy.
    *
    * @param space The space that this page belongs to.
    * @param title The title of the page we are creating.
    * @param content The content of the page we are creating.
    *
    * @return The create page object.
    */
    def createBasicPage(Space space, Page parentPage, String title, String content) {
    def pageManager = ComponentLocator.getComponent(PageManager)
    def page = new Page()
    def bodyContent = new BodyContent(page, content, BodyType.XHTML)
    page.with {
    setVersion(1)
    setSpace(space)
    setTitle(title)
    setBodyContent(bodyContent)
    setCreator(AuthenticatedUserThreadLocal.get())
    }
    linkPages(parentPage, page)
    pageManager.saveContentEntity(page, DefaultSaveContext.SUPPRESS_NOTIFICATIONS)
    
    return page.id
    }
    
    /**
    * Link a parent and a child page together. This method creates a bi-directional relationship between the two pages.
    *
    * @param parent The parent page that we wish to link.
    * @param child The child page that we wish to link.
    */
    void linkPages(Page parent, Page child) {
    // Set the parent page on the child
    child.setParentPage(parent)
    // Set the child page on the parent
    parent.addChild(child)
    // Set the ancestors on the child page
    def ancestors = []
    def parentPageAncestors = parent.ancestors as List
    if (parentPageAncestors) {
    ancestors.addAll(parentPageAncestors)
    }
    ancestors.add(parent)
    child.setAncestors(ancestors)
    }
    
    
    void editPage(String pageId, String pageTitle, String pageContent, String pageVersion) {
    //https://community.atlassian.com/t5/Confluence-questions/How-to-edit-the-page-content-using-rest-api/qaq-p/904345
    //def logx = Logger.getLogger("com.acme.workflows")
    //logx.setLevel(Level.DEBUG)
    
    def pageManager = ComponentLocator.getComponent(PageManager)
    
    def params = [
    id: pageId,
    type: "page",
    title: pageTitle,
    body: [storage:[value:pageContent, representation:"storage"]],
    version: [number:pageVersion]
    ]
    
    def jsonString = new JsonBuilder(params).toString()
    
    def rest_api_str = "https://HOST/wiki/rest/api/content/${pageId}"
    def http = new HTTPBuilder(rest_api_str)
    try { def json = http.request(groovyx.net.http.Method.PUT, groovyx.net.http.ContentType.JSON) { req ->
    req.addHeader('Authorization', 'Basic ' + 'USER:PASSWORD'.bytes.encodeBase64().toString())
    body = jsonString
    response.success = { resp, jsonData ->
    assert resp.status == 200
    return jsonData
    }
    response.failure = { resp ->
    return resp.status
    }
    }
    } catch(Exception ex) {
    
    }
    }