tm-content-parser - npm Package Compare versions

Comparing version 1.0.13 to 1.0.15

index.js

@@ -15,3 +15,4 @@ "use strict";
 const parseScript = content => content.is('script') ? 'IGNORE' : null;
-const parseBasicHTML = (ele, markup) => ele.is("ul,ol,table,h1,h2,h3,iframe") ? parseParagraph(markup) : null;
+const parseHTMLTable = (ele, markup) => ele.is("table") ? parseTable(markup) : null;
+const parseBasicHTML = (ele, markup) => ele.is("ul,ol,h1,h2,h3,iframe") ? parseParagraph(markup) : null;
 const parseEscenicImage = (ele, content) => {
@@ -162,2 +163,3 @@ if (ele.is('p')) {
     return parseScript(ele) ||
+        parseHTMLTable(ele, markup) ||
         parseBasicHTML(ele, markup)||
@@ -203,3 +205,2 @@ parseEscenicImage(ele, content) ||
             replaceEntityTags,
-            removeNewlinesFromLists,
             replaceNewLineCharacters,
@@ -211,2 +212,20 @@ formatHtml
 
+
+const parseTable = text => {
+    const $ = cheerio.load(text, {decodeEntities: false});
+    const tableToArray = $("tr").toArray().map( (tr) => {
+        const tds = $(tr).find("td");
+        return tds.map((idx, td) => $(td).text()).toArray();
+    });
+    const filtered = tableToArray.filter(arr => arr.length); // remove empty inner arrays []
+    const static_content = {
+        type: 'table',
+        body: JSON.stringify(filtered)
+    };
+    return {
+        type: 'static',
+        static_content
+    };
+};
+
 const removeEmptyHtmlTags = markup => {
@@ -231,4 +250,2 @@ const processedMarkup = R.replace(/<(\w*)><\/\1>|<(\w*)>\s<\/\2>/g, '', markup);
 
-const removeNewlinesFromLists = R.replace(/\/li>([^<]+)<li>/g, '\/li><li>');
-
 const replaceNewLineCharacters = R.replace(/\n/g, '<br>');
@@ -235,0 +252,0 @@

package.json

 {
   "name": "tm-content-parser",
-  "version": "1.0.13",
+  "version": "1.0.15",
   "description": "Trinity Mirror Content Type Parser",
@@ -5,0 +5,0 @@ "main": "index.js",

test/unit/contentTypeParser.js

@@ -107,16 +107,2 @@ "use strict";
 
-    describe('.removeNewlinesFromLists', () => {
-
-        const removeNewlinesFromLists = contentTypeParser.__get__("removeNewlinesFromLists");
-
-        it('should replace new line characters with correct html tags', () => {
-            removeNewlinesFromLists(
-                '<p>This is a paragraph with \n new \n lines \n <ul><li>Coffee</li>\n<li>Tea</li>\n<li>Milk</li></ul></p>'
-            ).should.eql(
-                '<p>This is a paragraph with \n new \n lines \n <ul><li>Coffee</li><li>Tea</li><li>Milk</li></ul></p>'
-            );
-        });
-
-    });
-
     describe('.replaceNewLineCharacters', () => {
@@ -157,2 +143,31 @@
 
+    describe('test table parser', () => {
+        const table = `
+        <table>
+        <tr>
+            <th>Company</th>
+            <th>Contact</th>
+            <th>Country</th>
+        </tr>
+        <tr>
+            <td>Alfreds Futterkiste</td>
+            <td>Maria Anders</td>
+            <td>Germany</td>
+        </tr>
+        <tr>
+            <td>Centro comercial Moctezuma</td>
+            <td>Francisco Chang</td>
+            <td>Mexico</td>
+        </tr>
+        </table>`;
+
+        const parseTable = contentTypeParser.__get__("parseTable");
+        it('should correctly parse table', () => {
+            const parsed = parseTable(table);
+            parsed.type.should.eql("static");
+            parsed.static_content.type.should.eql("table");
+            parsed.static_content.body.should.eql(`[["Alfreds Futterkiste","Maria Anders","Germany"],["Centro comercial Moctezuma","Francisco Chang","Mexico"]]`);
+        });
+    });
+
     describe('idAfterContent', () => {
@@ -159,0 +174,0 @@ const idAfterContent = contentTypeParser.__get__("idAfterContent");

No alert changes

Improved metrics

Total package byte prevSize

70889

increased by1.46%

Number of package files

12

increased by9.09%

Lines of code

1411

increased by2.39%

No dependency changes