First pass on converting the paragraph length assessment to use the H…

…TML Parser
Yoast · FAMarfuaty · Nov 12, 2024 · Nov 13, 2024 · Nov 14, 2024 · Nov 27, 2024
commit e338b83c2588d333a9d0f1ba284152a196d4e123
diff --git a/packages/yoastseo/spec/languageProcessing/helpers/html/matchParagraphsSpec.js b/packages/yoastseo/spec/languageProcessing/helpers/html/matchParagraphsSpec.js
diff --git a/packages/yoastseo/spec/languageProcessing/languages/ar/ResearcherSpec.js b/packages/yoastseo/spec/languageProcessing/languages/ar/ResearcherSpec.js
@@ -1,6 +1,7 @@
 import Researcher from "../../../../src/languageProcessing/languages/ar/Researcher.js";
 import Paper from "../../../../src/values/Paper.js";
 import getMorphologyData from "../../../specHelpers/getMorphologyData";
+import buildTree from "../../../specHelpers/parse/buildTree";
 import functionWords from "../../../../src/languageProcessing/languages/ar/config/functionWords";
 import transitionWords from "../../../../src/languageProcessing/languages/ar/config/transitionWords";
 import firstWordExceptions from "../../../../src/languageProcessing/languages/ar/config/firstWordExceptions";
@@ -9,10 +10,12 @@ import twoPartTransitionWords from "../../../../src/languageProcessing/languages
 const morphologyDataAR = getMorphologyData( "ar" );
 
 describe( "a test for Arabic Researcher", function() {
-	const researcher = new Researcher( new Paper( "This is another paper!" ) );
+	const paper = new Paper( "This is another paper!" );
+	const researcher = new Researcher( paper );
+	buildTree( paper, researcher );
 
 	it( "checks if the Arabic Researcher still inherit the Abstract Researcher", function() {
-		expect( researcher.getResearch( "getParagraphLength" ) ).toEqual( [ { text: "This is another paper!", countLength: 4 } ] );
+		expect( researcher.getResearch( "getParagraphLength" )[ 0 ].paragraphLength ).toEqual( 4 );
 	} );
 
 	it( "returns false if the default research is deleted in Arabic Researcher", function() {

diff --git a/packages/yoastseo/spec/languageProcessing/researches/getParagraphLengthSpec.js b/packages/yoastseo/spec/languageProcessing/researches/getParagraphLengthSpec.js
@@ -2,127 +2,237 @@ import getParagraphLength from "../../../src/languageProcessing/researches/getPa
 import Paper from "../../../src/values/Paper.js";
 import JapaneseResearcher from "../../../src/languageProcessing/languages/ja/Researcher.js";
 import EnglishResearcher from "../../../src/languageProcessing/languages/en/Researcher.js";
+import buildTree from "../../specHelpers/parse/buildTree";
 
 describe( "a test for getting paragraph length", function() {
 	it( "returns the paragraph length of a paragraph between p tags", function() {
 		const mockPaper = new Paper( "<p>Lorem ipsum</p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 2 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 2 );
 	} );
 
 	it( "returns the paragraph length of a paragraph in Japanese between p tags", function() {
 		const mockPaper = new Paper( "<p>これに対し日本国有鉄道</p>" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 11 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 11 );
 	} );
 
 	it( "returns the paragraph length of two paragraphs divided by double linebreaks and ends with a double linebreak", function() {
 		const mockPaper = new Paper( "Lorem \n\n ipsum two \n\n" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 1 );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 1 ].countLength ).toBe( 2 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 1 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 2 );
 	} );
 
 	it( "returns the paragraph length of two paragraphs in Japanese divided by double linebreaks and ends with a double linebreak", function() {
 		const mockPaper = new Paper( "1964年 \n\n （昭和39年） \n\n" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 5 );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 1 ].countLength ).toBe( 7 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 5 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 7 );
 	} );
 
 	it( "returns the paragraph length of two paragraphs divided by double linebreaks that don't end with a double linebreak", function() {
 		const mockPaper = new Paper( "Lorem \n\n ipsum two" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 1 );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 1 ].countLength ).toBe( 2 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 1 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 2 );
 	} );
 
 	it( "returns the paragraph length of two paragraphs in Japanese divided by double linebreaks that don't end with a double linebreak", function() {
 		const mockPaper = new Paper( "1964年 \n\n （昭和39年）" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 5 );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 1 ].countLength ).toBe( 7 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 5 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 7 );
 	} );
 
 	it( "returns the paragraph length of a paragraph without tags or double linebreaks", function() {
 		const mockPaper = new Paper( "Lorem ipsum dolor sit amet" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 5 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 5 );
 	} );
 
 	it( "returns the paragraph length of a paragraph in Japanese without tags or double linebreaks", function() {
 		const mockPaper = new Paper( "東京オリンピック開会直前の1964年（昭和39年）10月1日に開業した。" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 36 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 36 );
 	} );
 
 	it( "returns the paragraph length of 2 paragraphs, both between p tags", function() {
 		const mockPaper = new Paper( "<p>Lorem ipsum</p><p>dolor sit amet</p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 2 );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 1 ].countLength ).toBe( 3 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 2 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 3 );
 	} );
 
 	it( "returns the paragraph length of 2 paragraphs in Japanese, both between p tags", function() {
 		const mockPaper = new Paper( "<p>東京オリンピック開会直前の1964年</p><p>（昭和39年）10月1日に開業した。</p>" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 18 );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 1 ].countLength ).toBe( 18 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 18 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 18 );
 	} );
 
 	it( "returns the paragraph length of 2 paragraphs, both between p tags, divided by double linebreaks", function() {
 		const mockPaper = new Paper( "<p>Lorem ipsum</p> \n\n <p>dolor sit amet</p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 2 );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 1 ].countLength ).toBe( 3 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 2 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 3 );
 	} );
 
 	it( "returns the paragraph length of 2 paragraphs in Japanese, both between p tags, divided by double linebreaks", function() {
 		const mockPaper = new Paper( "<p>東京オリンピック開会直前の1964年</p> \n\n <p>（昭和39年）10月1日に開業した。</p>" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 18 );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 1 ].countLength ).toBe( 18 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 18 );
+		expect( paragraphLengths[ 1 ].paragraphLength ).toBe( 18 );
 	} );
 
 	it( "returns the paragraph length, with empty paragraphs", function() {
 		const mockPaper = new Paper( "<p>test</p><p></p><p>more text</p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() ).length ).toBe( 2 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.length ).toBe( 2 );
 	} );
 
 	it( "returns the paragraph length, ignoring text inside an element we want to exclude from the analysis", function() {
 		const mockPaper = new Paper( "<p>test <code>ignore me</code></p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() ).length ).toBe( 1 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.length ).toBe( 1 );
 	} );
 
 	it( "returns the paragraph length, ignoring shortcodes", function() {
 		const mockPaper = new Paper( "<p>test [shortcode]</p>", { shortcodes: [ "shortcode" ] } );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() ).length ).toBe( 1 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.length ).toBe( 1 );
 	} );
 
 	it( "returns the paragraph length of paragraph without p tags or double linebreaks, but with h2 tags", function() {
 		const mockPaper = new Paper( "<h2>Lorem ipsum dolor sit amet</h2>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() )[ 0 ].countLength ).toBe( 5 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 5 );
 	} );
 
 	it( "returns the paragraph length of paragraph in Japanese without p tags or double linebreaks, but with h2 tags", function() {
 		const mockPaper = new Paper( "<h2>（昭和39年）10月1日に開業した。</h2>" );
-		expect( getParagraphLength( mockPaper, new JapaneseResearcher() )[ 0 ].countLength ).toBe( 18 );
+		const mockResearcher = new JapaneseResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 18 );
 	} );
 
 	xit( "returns the paragraph length of an empty paragraph with p tags", function() {
 		const mockPaper = new Paper( "<p></p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() ).countLength ).not.toContain( 0 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.paragraphLength ).not.toContain( 0 );
 	} );
 
 	xit( "returns the paragraph length of an empty paragraph without p tags or double line breaks", function() {
 		const mockPaper = new Paper( "" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher() ).countLength ).not.toContain( 0 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.paragraphLength ).not.toContain( 0 );
 	} );
 } );
 
 describe( "a test for getting paragraph length of a text with image(s)", () => {
 	it( "should not count a paragraph containing only an image", function() {
 		// The paper contains 3 paragraphs: 2 paragraphs with text and one paragraph with only an image.
 		const mockPaper = new Paper( "<p>test</p><p><img src='image.com/image.png' /></p><p>more text</p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher( mockPaper ) ).length ).toBe( 2 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.length ).toBe( 2 );
 	} );
 
 	it( "should return 0 for paragraphs count when all paragraphs only contain images", function() {
 		const mockPaper = new Paper( "<p><img src='image.com/image.png' /></p><p><img src='image.com/image.png' /></p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher( mockPaper ) ).length ).toBe( 0 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.length ).toBe( 0 );
 	} );
 
 	it( "should not include the image in the paragraph length calculation", function() {
 		const mockPaper = new Paper( "<p><img src='image.com/image.png' />test</p><p><img src='image.com/image.png' /> test </p>" );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher( mockPaper ) ).length ).toBe( 2 );
-		expect( getParagraphLength( mockPaper, new EnglishResearcher( mockPaper ) )[ 0 ].countLength ).toBe( 1 );
+		const mockResearcher = new EnglishResearcher( mockPaper );
+		buildTree( mockPaper, mockResearcher );
+
+		const paragraphLengths = getParagraphLength( mockPaper, mockResearcher );
+
+		expect( paragraphLengths.length ).toBe( 2 );
+		expect( paragraphLengths[ 0 ].paragraphLength ).toBe( 1 );
 	} );
 } );