chore: cleaned up repetative testing for dom

src/extractor/generic/utils/dom/brs-to-ps.js

@@ -1,4 +1,4 @@
-import paragraphize from './paragraphize'
+import { paragraphize } from './index'
 
 // ## NOTES:
 // Another good candidate for refactoring/optimizing.

src/extractor/generic/utils/dom/brs-to-ps.test.js

@@ -1,17 +1,12 @@
 import assert from 'assert'
 import cheerio from 'cheerio'
 
-import { clean } from './test-helpers'
+import { assertBeforeAndAfter } from './test-helpers'
 import HTML from '../fixtures/html'
 import {
   brsToPs
 } from './index'
 
-function assertBeforeAndAfter(key, fn) {
-  const $ = cheerio.load(HTML[key].before)
-  assert.equal(clean(fn($).html()), clean(HTML[key].after))
-}
-
 describe('Generic Extractor Utils', () => {
   describe('brsToPs(node)', () => {
 

src/extractor/generic/utils/dom/convert-to-paragraphs.test.js

@@ -1,22 +1,23 @@
 import assert from 'assert'
 import cheerio from 'cheerio'
 
-import { clean } from './test-helpers'
+import {
+  assertBeforeAndAfter,
+  assertClean
+} from './test-helpers'
 import HTML from '../fixtures/html'
+
 import {
   convertToParagraphs
 } from './index'
+
 import { convertNodeToP } from './convert-to-paragraphs'
 
 describe('Generic Extractor Utils', () => {
   describe('convertToParagraphs($)', () => {
 
     it("performs all conversions", () => {
-      const $ = cheerio.load(HTML.convertToParagraphs.before)
-      // Note: Result is not valid html
-      // Cheerio's parser will fix this elsewhere
-      const result = convertToParagraphs($).html()
-      assert.equal(clean(result), clean(HTML.convertToParagraphs.after))
+      assertBeforeAndAfter('convertToParagraphs', convertToParagraphs)
     })
 
   })
@@ -25,9 +26,10 @@ describe('Generic Extractor Utils', () => {
     it('takes a node with any tag and turns it into a P tag', () => {
       const $ = cheerio.load(HTML.convertNodeToP.before)
       const node = $('div').first()
+
       const result = convertNodeToP(node, $).html()
-      assert.equal(clean(result), clean(HTML.convertNodeToP.after))
 
+      assertClean(result, HTML.convertNodeToP.after)
     })
 
   })

src/extractor/generic/utils/dom/paragraphize.js

@@ -7,7 +7,7 @@ import { BLOCK_LEVEL_TAGS_RE } from '../constants'
 // If the node is a <br />, it treats the following inline siblings
 // as if they were its children.
 //
-// :param node: The node to paragraphize
+// :param node: The node to paragraphize; this is a raw node
 // :param $: The cheerio object to handle dom manipulation
 // :param br: Whether or not the passed node is a br
 

src/extractor/generic/utils/dom/paragraphize.test.js

@@ -13,16 +13,20 @@ describe('Generic Extractor Utils', () => {
     it("conversts a BR into P and moves inline contents to P tag after current parent", () => {
       const $ = cheerio.load(HTML.paragraphize.before)
       let node = $('br').get(0)
+
       // note: result here is not valid html; will handle elsewhere
       let result = paragraphize(node, $, true).html()
+
       assert.equal(clean(result), clean(HTML.paragraphize.after))
     })
 
     it("conversts a BR into P and stops when block element hit", () => {
       const $ = cheerio.load(HTML.paragraphizeBlock.before)
       let node = $('br').get(0)
+
       // note: result here is not valid html; will handle elsewhere
       let result = paragraphize(node, $, true).html()
+
       assert.equal(clean(result), clean(HTML.paragraphizeBlock.after))
     })
 

src/extractor/generic/utils/dom/strip-unlikely-candidates.test.js

@@ -1,7 +1,7 @@
 import assert from 'assert'
 import cheerio from 'cheerio'
 
-import { clean } from './test-helpers'
+import { assertBeforeAndAfter } from './test-helpers'
 import HTML from '../fixtures/html'
 import {
   stripUnlikelyCandidates
@@ -16,21 +16,15 @@ describe('Generic Extractor Utils', () => {
     })
 
     it("strips unlikely matches from the doc", () => {
-      const $ = cheerio.load(HTML.whitelistMatch.before)
-      const stripped = clean(stripUnlikelyCandidates($).html())
-      assert.equal(stripped, clean(HTML.whitelistMatch.after))
+      assertBeforeAndAfter('whitelistMatch', stripUnlikelyCandidates)
     })
 
     it("keeps likely matches even when they also match the blacklist", () => {
-      const $ = cheerio.load(HTML.whiteAndBlack.before)
-      const stripped = clean(stripUnlikelyCandidates($).html())
-      assert.equal(stripped, clean(HTML.whiteAndBlack.after))
+      assertBeforeAndAfter('whiteAndBlack', stripUnlikelyCandidates)
     })
 
     it("removed likely matches when inside blacklist node", () => {
-      const $ = cheerio.load(HTML.whiteInsideBlack.before)
-      const stripped = clean(stripUnlikelyCandidates($).html())
-      assert.equal(stripped, clean(HTML.whiteInsideBlack.after))
+      assertBeforeAndAfter('whiteInsideBlack', stripUnlikelyCandidates)
     })
 
 

src/extractor/generic/utils/dom/test-helpers.js

@@ -1,3 +1,17 @@
+import assert from 'assert'
+import cheerio from 'cheerio'
+import HTML from '../fixtures/html'
+
 export function clean(string) {
   return string.trim().replace(/\r?\n|\r/g, '').replace(/\s+/g, ' ')
 }
+
+export function assertBeforeAndAfter(key, fn) {
+  const $ = cheerio.load(HTML[key].before)
+  assert.equal(clean(fn($).html()), clean(HTML[key].after))
+}
+
+export function assertClean(a, b) {
+  assert.equal(clean(a), clean(b))
+}
+