BACKLOG-22157 Update api, add dry run property, add tests (#6)

* BACKLOG-22157 Update api, add dry run property, add tests * BACKLOG-22157 Fix test
Jahia · Jan 16, 2024 · 73a7424 · 73a7424
1 parent 98d90a1
commit 73a7424
Show file tree

Hide file tree

Showing 11 changed files with 227 additions and 6 deletions.
diff --git a/src/main/java/org/jahia/modules/richtext/HtmlFilteringInterceptor.java b/src/main/java/org/jahia/modules/richtext/HtmlFilteringInterceptor.java
@@ -53,10 +53,12 @@
 import org.osgi.service.component.annotations.Component;
 import org.osgi.service.component.annotations.Deactivate;
 import org.osgi.service.component.annotations.Reference;
+import org.owasp.html.HtmlChangeListener;
 import org.owasp.html.PolicyFactory;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+import javax.annotation.Nullable;
 import javax.jcr.RepositoryException;
 import javax.jcr.Value;
 import javax.jcr.ValueFormatException;
@@ -129,6 +131,23 @@ public Value beforeSetValue(JCRNodeWrapper node, String name,
             }
         }
 
+        if (filteringConfig.htmlSanitizerDryRun(resolveSite.getSiteKey())) {
+            logger.info(String.format("Dry run: Skipping Sanitization of [%s]", node.getProperty("text").getRealProperty().getPath()));
+            policyFactory.sanitize(content, new HtmlChangeListener<Object>() {
+                @Override
+                public void discardedTag(@Nullable Object o, String tag) {
+                    logger.info(String.format("Removed tag: %s", tag));
+                }
+
+                @Override
+                public void discardedAttributes(@Nullable Object o, String tag, String... strings) {
+                    logger.info(String.format("Removed attributes %s for tag %s", String.join(", ", strings), tag));
+                }
+            }, null);
+
+            return originalValue;
+        }
+
         String result = policyFactory.sanitize(content);
 
         if (result != content && !result.equals(content)) {

diff --git a/src/main/java/org/jahia/modules/richtext/RichTextConfigurationInterface.java b/src/main/java/org/jahia/modules/richtext/RichTextConfigurationInterface.java
@@ -20,4 +20,6 @@ public interface RichTextConfigurationInterface {
     public JSONObject getMergedJSONPolicy(String... siteKeys);
 
     public boolean configExists(String siteKey);
+
+    public boolean htmlSanitizerDryRun(String siteKey);
 }
diff --git a/src/main/java/org/jahia/modules/richtext/configuration/RichTextConfiguration.java b/src/main/java/org/jahia/modules/richtext/configuration/RichTextConfiguration.java
@@ -137,6 +137,17 @@ public boolean configExists(String siteKey) {
         return false;
     }
 
+    @Override
+    public boolean htmlSanitizerDryRun(String siteKey) {
+        if (configExists(siteKey)) {
+            JSONObject f = configs.get(siteKeyToPid.get(siteKey)).getJSONObject("htmlFiltering");
+
+            return f.has("htmlSanitizerDryRun") && f.getBoolean("htmlSanitizerDryRun");
+        }
+
+        return false;
+    }
+
     private void mergeJsonObject(JSONObject target, JSONObject source) {
         for (String key : source.keySet()) {
             if (source.get(key) instanceof JSONObject) {

diff --git a/src/main/java/org/jahia/modules/richtext/graphql/models/GqlRichTextConfig.java b/src/main/java/org/jahia/modules/richtext/graphql/models/GqlRichTextConfig.java
@@ -10,11 +10,12 @@
 import java.util.Set;
 
 @GraphQLDescription("Model for richtext configuration")
-public class GqlRichTextConfig {
+public class GqlRichTextConfig implements RichTextConfigInterface {
 
     private Set<String> protocols = new HashSet<>();
     private Set<String> elements = new HashSet<>();
     private List<GqlRichTextConfigAttribute> attributes = new ArrayList<>();
+    private GqlRichTextDisallowedConfig disallow = new GqlRichTextDisallowedConfig();
 
     @GraphQLField
     @GraphQLName("protocols")
@@ -36,4 +37,11 @@ public Set<String> getElements() {
     public List<GqlRichTextConfigAttribute> getAttributes() {
         return attributes;
     }
+
+    @GraphQLField
+    @GraphQLName("disallow")
+    @GraphQLDescription("Disallowed html elements and attributes")
+    public GqlRichTextDisallowedConfig getDisallow() {
+        return disallow;
+    }
 }
diff --git a/src/main/java/org/jahia/modules/richtext/graphql/models/GqlRichTextDisallowedConfig.java b/src/main/java/org/jahia/modules/richtext/graphql/models/GqlRichTextDisallowedConfig.java
@@ -0,0 +1,39 @@
+package org.jahia.modules.richtext.graphql.models;
+
+import graphql.annotations.annotationTypes.GraphQLDescription;
+import graphql.annotations.annotationTypes.GraphQLField;
+import graphql.annotations.annotationTypes.GraphQLName;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+
+@GraphQLDescription("Model for disallowed richtext configuration")
+public class GqlRichTextDisallowedConfig implements RichTextConfigInterface {
+
+    private Set<String> protocols = new HashSet<>();
+    private Set<String> elements = new HashSet<>();
+    private List<GqlRichTextConfigAttribute> attributes = new ArrayList<>();
+
+    @GraphQLField
+    @GraphQLName("protocols")
+    @GraphQLDescription("Protocols")
+    public Set<String> getProtocols() {
+        return protocols;
+    }
+
+    @GraphQLField
+    @GraphQLName("elements")
+    @GraphQLDescription("HTML elements")
+    public Set<String> getElements() {
+        return elements;
+    }
+
+    @GraphQLField
+    @GraphQLName("attributes")
+    @GraphQLDescription("HTML attributes")
+    public List<GqlRichTextConfigAttribute> getAttributes() {
+        return attributes;
+    }
+}
diff --git a/src/main/java/org/jahia/modules/richtext/graphql/models/RichTextConfigInterface.java b/src/main/java/org/jahia/modules/richtext/graphql/models/RichTextConfigInterface.java
@@ -0,0 +1,11 @@
+package org.jahia.modules.richtext.graphql.models;
+
+import java.util.List;
+import java.util.Set;
+
+public interface RichTextConfigInterface {
+
+    public Set<String> getProtocols();
+    public Set<String> getElements();
+    public List<GqlRichTextConfigAttribute> getAttributes();
+}
diff --git a/...va/org/jahia/modules/richtext/graphql/query/impl/htmlFiltering/GqlHtmlFilteringQuery.java b/...va/org/jahia/modules/richtext/graphql/query/impl/htmlFiltering/GqlHtmlFilteringQuery.java
@@ -76,7 +76,7 @@ public List<String> getSitesWithActiveFiltering() {
     }
 
     @GraphQLField
-    @GraphQLName("richTextConfiguration")
+    @GraphQLName("richtextConfiguration")
     @GraphQLDescription("RichText filtering configuration for a given site")
     public GqlRichTextConfig getRichTextConfiguration(@GraphQLNonNull @GraphQLName("siteKey") @GraphQLDescription("Site key for the affected site") String siteKey) {
         RichTextConfigurationInterface filteringConfig = BundleUtils.getOsgiService(RichTextConfigurationInterface.class, null);
@@ -93,24 +93,38 @@ public GqlRichTextConfig getRichTextConfiguration(@GraphQLNonNull @GraphQLName("
         getElements(config, gqlRichTextConfig);
         getAttributes(config, gqlRichTextConfig);
 
+        if (config.has("disallow")) {
+            RichTextConfigInterface disallow = gqlRichTextConfig.getDisallow();
+            config = config.getJSONObject("disallow");
+            getProtocols(config, disallow);
+            getElements(config, disallow);
+            getAttributes(config, disallow);
+        }
+
         return gqlRichTextConfig;
     }
 
-    private void getProtocols(JSONObject config, GqlRichTextConfig gqlRichTextConfig) {
+    private void getProtocols(JSONObject config, RichTextConfigInterface gqlRichTextConfig) {
         if (config.has("protocols")) {
             JSONArray protocols = config.getJSONArray("protocols");
             protocols.forEach(p -> gqlRichTextConfig.getProtocols().add((String) p));
         }
     }
 
-    private void getElements(JSONObject config, GqlRichTextConfig gqlRichTextConfig) {
+    private void getElements(JSONObject config, RichTextConfigInterface gqlRichTextConfig) {
         if (config.has("elements")) {
             JSONArray elements = config.getJSONArray("elements");
-            elements.forEach(e -> ((JSONObject)e).getJSONArray("name").forEach(el -> gqlRichTextConfig.getElements().add((String) el)));
+            elements.forEach(e -> {
+                if (((JSONObject)e).get("name") instanceof JSONArray) {
+                    ((JSONObject)e).getJSONArray("name").forEach(el -> gqlRichTextConfig.getElements().add((String) el));
+                } else {
+                    gqlRichTextConfig.getElements().add(((JSONObject)e).getString("name"));
+                }
+            });
         }
     }
 
-    private void getAttributes(JSONObject config, GqlRichTextConfig gqlRichTextConfig) {
+    private void getAttributes(JSONObject config, RichTextConfigInterface gqlRichTextConfig) {
         if (config.has("attributes")) {
             JSONArray attributes = config.getJSONArray("attributes");
             List<GqlRichTextConfigAttribute> a = gqlRichTextConfig.getAttributes();

diff --git a/...in/resources/META-INF/configuration-default/org.jahia.modules.richtext.config-default.yml b/...in/resources/META-INF/configuration-default/org.jahia.modules.richtext.config-default.yml
@@ -1,4 +1,5 @@
 htmlFiltering:
+  htmlSanitizerDryRun: false
   protocols:
     - http
     - https

diff --git a/tests/cypress/e2e/filteringAPI.cy.ts b/tests/cypress/e2e/filteringAPI.cy.ts
@@ -0,0 +1,73 @@
+import {createSite, deleteSite} from '@jahia/cypress';
+import {DocumentNode} from 'graphql';
+import {enableHtmlFiltering, installConfig} from '../fixtures/utils';
+
+describe('HTML rich text filtering API', () => {
+    const siteKey = 'filteringSite';
+    const text = '<div id="myId" role="myRole" removed-attribute="removed">Testing <h1>Testing</h1><p><strong>Testing</strong></p></div>';
+    let previewMutation: DocumentNode;
+    let configQuery: DocumentNode;
+
+    before(() => {
+        createSite(siteKey);
+        installConfig('configs/org.jahia.modules.richtext.config-filteringSite.yml');
+        enableHtmlFiltering(siteKey);
+        previewMutation = require('graphql-tag/loader!../fixtures/filteringAPI/preview.graphql');
+        configQuery = require('graphql-tag/loader!../fixtures/filteringAPI/config.graphql');
+    });
+
+    after(() => {
+        deleteSite(siteKey);
+    });
+
+    it('filters via API and reports on removed elements/attributes', () => {
+        cy.apollo({
+            mutation: previewMutation,
+            variables: {
+                text: text,
+                siteKey: siteKey
+            }
+        }).then(response => {
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.removedAttributes).length(1);
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.removedAttributes[0].attributes[0]).to.equal('removed-attribute');
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.removedAttributes[0].element).to.equal('div');
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.removedElements).length(1);
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.removedElements).contain('strong');
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.html).contain('role="myRole"');
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.html).contain('id="myId"');
+            expect(response.data.richtextConfiguration.htmlFiltering.testFiltering.html).contain('<p>Testing</p>');
+        });
+    });
+
+    it('returns a list of configured elements and attributes', () => {
+        cy.apollo({
+            query: configQuery,
+            variables: {
+                siteKey: siteKey
+            }
+        }).then(response => {
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.attributes).length(37);
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.attributes.find(a => a.attribute === 'class')).to.deep.equal({
+                attribute: 'class',
+                elements: [],
+                isGlobal: true,
+                pattern: '(myclass1|myclass2)',
+                __typename: 'GqlRichTextConfigAttribute'
+            });
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.attributes.find(a => a.attribute === 'autoplay')).to.deep.equal({
+                attribute: 'autoplay',
+                elements: [
+                    'audio',
+                    'video'
+                ],
+                isGlobal: false,
+                pattern: null,
+                __typename: 'GqlRichTextConfigAttribute'
+            });
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.elements).length(70);
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.protocols).length(3);
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.disallow.elements).length(1);
+            expect(response.data.richtextConfiguration.htmlFiltering.richtextConfiguration.disallow.elements).contain('strong');
+        });
+    });
+});
diff --git a/tests/cypress/fixtures/filteringAPI/config.graphql b/tests/cypress/fixtures/filteringAPI/config.graphql
@@ -0,0 +1,26 @@
+query Config($siteKey: String!) {
+  richtextConfiguration {
+    htmlFiltering {
+      richtextConfiguration(siteKey: $siteKey) {
+        elements
+        protocols
+        attributes {
+          attribute
+          elements
+          isGlobal
+          pattern
+        }
+        disallow {
+          elements
+          protocols
+          attributes {
+            attribute
+            elements
+            isGlobal
+            pattern
+          }
+        }
+      }
+    }
+  }
+}
diff --git a/tests/cypress/fixtures/filteringAPI/preview.graphql b/tests/cypress/fixtures/filteringAPI/preview.graphql
@@ -0,0 +1,17 @@
+mutation PreviewFiltering($text: String!, $siteKey: String!) {
+  richtextConfiguration {
+    htmlFiltering {
+      testFiltering(
+        siteKey: $siteKey
+        html: $text
+      ) {
+        html
+        removedElements
+        removedAttributes {
+          element
+          attributes
+        }
+      }
+    }
+  }
+}