[+]: added more tests from "https://github.com/soundasleep/html2text/…

…tree/master/tests" thx @soundasleep
voku · Aug 19, 2016 · 5a64b0f · 5a64b0f
1 parent 834c21d
commit 5a64b0f
Show file tree

Hide file tree

Showing 9 changed files with 135 additions and 0 deletions.
diff --git a/tests/MailTest.php b/tests/MailTest.php
@@ -142,6 +142,50 @@ public function testHtmlToText10()
     self::assertSame($this->file_get_contents(__DIR__ . '/fixtures/test10Html.txt'), $text);
   }
 
+  public function testHtmlToTextMsOffice()
+  {
+    $html = UTF8::file_get_contents(__DIR__ . '/fixtures/msoffice.html');
+
+    $html2text = new Html2Text($html, false, array('directConvert' => true));
+
+    $text = $html2text->getText();
+
+    self::assertSame($this->file_get_contents(__DIR__ . '/fixtures/msoffice.txt'), $text);
+  }
+
+  public function testHtmlToTextNbsp()
+  {
+    $html = UTF8::file_get_contents(__DIR__ . '/fixtures/nbsp.html');
+
+    $html2text = new Html2Text($html, false, array('directConvert' => true));
+
+    $text = $html2text->getText();
+
+    self::assertSame($this->file_get_contents(__DIR__ . '/fixtures/nbsp.txt'), $text);
+  }
+
+  public function testHtmlToTextNonBreakingSpace()
+  {
+    $html = UTF8::file_get_contents(__DIR__ . '/fixtures/non-breaking-spaces.html');
+
+    $html2text = new Html2Text($html, false, array('directConvert' => true));
+
+    $text = $html2text->getText();
+
+    self::assertSame($this->file_get_contents(__DIR__ . '/fixtures/non-breaking-spaces.txt'), $text);
+  }
+
+  public function testHtmlToTextTable()
+  {
+    $html = UTF8::file_get_contents(__DIR__ . '/fixtures/table.html');
+
+    $html2text = new Html2Text($html, false, array('directConvert' => true));
+
+    $text = $html2text->getText();
+
+    self::assertSame($this->file_get_contents(__DIR__ . '/fixtures/table.txt'), $text);
+  }
+
   /**
    * @param string $filename
    *

diff --git a/tests/fixtures/msoffice.html b/tests/fixtures/msoffice.html
@@ -0,0 +1 @@
+<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:x="urn:schemas-microsoft-com:office:excel" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!-- /* Font Definitions */ @font-face {font-family:"Cambria Math"; panose-1:2 4 5 3 5 4 6 3 2 4;} @font-face {font-family:Calibri; panose-1:2 15 5 2 2 2 4 3 2 4;} /* Style Definitions */ p.MsoNormal, li.MsoNormal, div.MsoNormal {margin:0cm; margin-bottom:.0001pt; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-fareast-language:EN-US;} a:link, span.MsoHyperlink {mso-style-priority:99; color:#0563C1; text-decoration:underline;} a:visited, span.MsoHyperlinkFollowed {mso-style-priority:99; color:#954F72; text-decoration:underline;} span.EmailStyle17 {mso-style-type:personal-compose; font-family:"Calibri",sans-serif; color:windowtext;} .MsoChpDefault {mso-style-type:export-only; font-family:"Calibri",sans-serif; mso-fareast-language:EN-US;} @page WordSection1 {size:612.0pt 792.0pt; margin:72.0pt 72.0pt 72.0pt 72.0pt;} div.WordSection1 {page:WordSection1;} --></style><!--[if gte mso 9]><xml> <o:shapedefaults v:ext="edit" spidmax="1026" /> </xml><![endif]--><!--[if gte mso 9]><xml> <o:shapelayout v:ext="edit"> <o:idmap v:ext="edit" data="1" /> </o:shapelayout></xml><![endif]--></head><body lang=EN-GB link="#0563C1" vlink="#954F72"><div class=WordSection1><p class=MsoNormal>Dear html2text,<o:p></o:p></p><p class=MsoNormal><o:p>&nbsp;</o:p></p><p class=MsoNormal>This is an example email that can be used to test html2text conversion of outlook / exchange emails.<o:p></o:p></p><p class=MsoNormal><o:p>&nbsp;</o:p></p><p class=MsoNormal>The addition of &lt;o:p&gt; tags is very annoying!<o:p></o:p></p><p class=MsoNormal>This is a single line return<o:p></o:p></p><p class=MsoNormal><o:p>&nbsp;</o:p></p><p class=MsoNormal><b>This is bold<o:p></o:p></b></p><p class=MsoNormal><i>This is italic<o:p></o:p></i></p><p class=MsoNormal><u>This is underline<o:p></o:p></u></p><p class=MsoNormal><o:p>&nbsp;</o:p></p><p class=MsoNormal>Andrew<o:p></o:p></p></div></body></html>
diff --git a/tests/fixtures/msoffice.txt b/tests/fixtures/msoffice.txt
@@ -0,0 +1,15 @@
+Dear html2text,
+
+This is an example email that can be used to test html2text conversion of outlook / exchange emails.
+
+The addition of tags is very annoying!
+
+This is a single line return
+
+THIS IS BOLD
+
+_This is italic_
+
+This is underline
+
+Andrew
diff --git a/tests/fixtures/nbsp.html b/tests/fixtures/nbsp.html
@@ -0,0 +1 @@
+hello &nbsp; world &amp; people &lt; &gt; &NBSP;
diff --git a/tests/fixtures/nbsp.txt b/tests/fixtures/nbsp.txt
@@ -0,0 +1 @@
+hello   world & people < >
diff --git a/tests/fixtures/non-breaking-spaces.html b/tests/fixtures/non-breaking-spaces.html
@@ -0,0 +1 @@
+these spaces are non-breaking
diff --git a/tests/fixtures/non-breaking-spaces.txt b/tests/fixtures/non-breaking-spaces.txt
@@ -0,0 +1 @@
+these spaces are non-breaking
diff --git a/tests/fixtures/table.html b/tests/fixtures/table.html
@@ -0,0 +1,53 @@
+<html>
+<title>Ignored Title</title>
+<body>
+  <h1>Hello, World!</h1>
+  <table>
+    <thead>
+      <tr>
+        <th>Col A</th>
+        <th>Col B</th>
+      </tr>
+    </thead>
+    <tbody>
+      <tr>
+        <td>
+          Data A1
+        </td>
+        <td>
+          Data B1
+        </td>
+      </tr>
+      <tr>
+          <td>
+            Data A2
+          </td>
+          <td>
+            Data B2
+          </td>
+      </tr>
+      <tr>
+        <td>
+          Data A3
+        </td>
+        <td>
+          Data B4
+        </td>
+      </tr>
+    </tbody>
+    <tfoot>
+      <tr>
+          <td>
+            Total A
+          </td>
+          <td>
+            Total B
+          </td>
+       </tr>
+
+    </tfoot>
+
+  </table>
+
+</body>
+</html>
diff --git a/tests/fixtures/table.txt b/tests/fixtures/table.txt
@@ -0,0 +1,18 @@
+Ignored Title
+
+HELLO, WORLD!
+
+COL A
+COL B
+
+Data A1
+Data B1
+
+Data A2
+Data B2
+
+Data A3
+Data B4
+
+Total A
+Total B