PDF Accessibility: Adding test for paragraphs and heading.

This CL adds a test for validating the paragraph and heading support in
PDF accessibility pipeline. A single PDF has been added which has a
heading and multiple paragraphs.

Bug: 981448
Change-Id: I40fe2b958e29fba2c8e0d98de254c438ad6ea248
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/1723851Reviewed-by: Kevin Babbitt <kbabbitt@microsoft.com>
Reviewed-by: Lei Zhang <thestig@chromium.org>
Commit-Queue: Ankit Kumar 🌪️ <ankk@microsoft.com>
Cr-Commit-Position: refs/heads/master@{#682167}

chrome/browser/pdf/pdf_extension_test.cc

@@ -2358,3 +2358,8 @@ INSTANTIATE_TEST_SUITE_P(
 IN_PROC_BROWSER_TEST_P(PDFExtensionAccessibilityTreeDumpTest, HelloWorld) {
   RunPDFTest(FILE_PATH_LITERAL("hello-world.pdf"));
 }
+
+IN_PROC_BROWSER_TEST_P(PDFExtensionAccessibilityTreeDumpTest,
+                       ParagraphsAndHeadingUntagged) {
+  RunPDFTest(FILE_PATH_LITERAL("paragraphs-and-heading-untagged.pdf"));
+}

chrome/test/data/pdf/accessibility/paragraphs-and-heading-untagged-expected-auralinux.txt

+[embedded component]
+++[panel]
+++++[landmark] name='Page 1'
+++++++[heading]
+++++++++[text] name='Heading<newline>'
+++++++[paragraph]
+++++++++[text] name='This is a small pdf file:<newline>'
+++++++[paragraph]
+++++++++[text] name='Lorem Ipsum is simply dummy text of the printing and typesetting industry.<newline>Lorem Ipsum has been the industry's standard dummy text ever since the 1500s.<newline>'
+++++++[paragraph]
+++++++++[text] name='It has survived not only five centuries, but also the leap into electronic typesetting,<newline>remaining essentially unchanged. It was popularised in the 1960s with the release of<newline>Letraset sheets containing Lorem Ipsum passages, and more recently with desktop<newline>publishing software like Aldus PageMaker including versions of Lorem Ipsum.<newline>'
+++++++[paragraph]
+++++++++[text] name='Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots<newline>in a piece of classical Latin literature from 45 BC, making it over 2000 years old.'

chrome/test/data/pdf/accessibility/paragraphs-and-heading-untagged-expected-blink.txt

+embeddedObject
+++group restriction=readOnly
+++++region name='Page 1' restriction=readOnly
+++++++heading hierarchicalLevel=2 restriction=readOnly
+++++++++staticText name='Heading<newline>' restriction=readOnly
+++++++++++inlineTextBox name='Heading<newline>' restriction=readOnly
+++++++paragraph restriction=readOnly
+++++++++staticText name='This is a small pdf file:<newline>' restriction=readOnly
+++++++++++inlineTextBox name='This is a small pdf file:<newline>' restriction=readOnly
+++++++paragraph restriction=readOnly
+++++++++staticText name='Lorem Ipsum is simply dummy text of the printing and typesetting industry.<newline>Lorem Ipsum has been the industry's standard dummy text ever since the 1500s.<newline>' restriction=readOnly
+++++++++++inlineTextBox name='Lorem Ipsum is simply dummy text of the printing and typesetting industry.<newline>' restriction=readOnly
+++++++++++inlineTextBox name='Lorem Ipsum has been the industry's standard dummy text ever since the 1500s.<newline>' restriction=readOnly
+++++++paragraph restriction=readOnly
+++++++++staticText name='It has survived not only five centuries, but also the leap into electronic typesetting,<newline>remaining essentially unchanged. It was popularised in the 1960s with the release of<newline>Letraset sheets containing Lorem Ipsum passages, and more recently with desktop<newline>publishing software like Aldus PageMaker including versions of Lorem Ipsum.<newline>' restriction=readOnly
+++++++++++inlineTextBox name='It ' restriction=readOnly
+++++++++++inlineTextBox name='has survived not only five centuries, but also the leap into electronic typesetting,<newline>' restriction=readOnly
+++++++++++inlineTextBox name='remaining essentially unchanged. It was popularised in the 1960s with the release of<newline>' restriction=readOnly
+++++++++++inlineTextBox name='Letraset sheets containing Lorem Ipsum passages, and more recently with desktop<newline>' restriction=readOnly
+++++++++++inlineTextBox name='publishing software like Aldus PageMaker including versions of Lorem Ipsum.<newline>' restriction=readOnly
+++++++paragraph restriction=readOnly
+++++++++staticText name='Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots<newline>in a piece of classical Latin literature from 45 BC, making it over 2000 years old.' restriction=readOnly
+++++++++++inlineTextBox name='Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots<newline>' restriction=readOnly
+++++++++++inlineTextBox name='in a piece of classical Latin literature from 45 BC, making it over 2000 years old.' restriction=readOnly

chrome/test/data/pdf/accessibility/paragraphs-and-heading-untagged-expected-mac.txt

+AXGroup AXDescription='Page 1'
+++AXGroup
+++++AXGroup AXDescription='Page 1'
+++++++AXHeading AXValue='2'
+++++++++AXStaticText AXValue='Heading<newline>'
+++++++AXGroup
+++++++++AXStaticText AXValue='This is a small pdf file:<newline>'
+++++++AXGroup
+++++++++AXStaticText AXValue='Lorem Ipsum is simply dummy text of the printing and typesetting industry.<newline>Lorem Ipsum has been the industry's standard dummy text ever since the 1500s.<newline>'
+++++++AXGroup
+++++++++AXStaticText AXValue='It has survived not only five centuries, but also the leap into electronic typesetting,<newline>remaining essentially unchanged. It was popularised in the 1960s with the release of<newline>Letraset sheets containing Lorem Ipsum passages, and more recently with desktop<newline>publishing software like Aldus PageMaker including versions of Lorem Ipsum.<newline>'
+++++++AXGroup
+++++++++AXStaticText AXValue='Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots<newline>in a piece of classical Latin literature from 45 BC, making it over 2000 years old.'

chrome/test/data/pdf/accessibility/paragraphs-and-heading-untagged-expected-uia-win.txt

+group
+++group
+++++region Name='Page 1'
+++++++heading
+++++++group
+++++++group
+++++++group
+++++++group

chrome/test/data/pdf/accessibility/paragraphs-and-heading-untagged-expected-win.txt

+ROLE_SYSTEM_GROUPING FOCUSABLE
+++ROLE_SYSTEM_GROUPING READONLY
+++++IA2_ROLE_LANDMARK name='Page 1' READONLY
+++++++IA2_ROLE_HEADING READONLY
+++++++++ROLE_SYSTEM_STATICTEXT name='Heading<newline>' READONLY
+++++++IA2_ROLE_PARAGRAPH READONLY
+++++++++ROLE_SYSTEM_STATICTEXT name='This is a small pdf file:<newline>' READONLY
+++++++IA2_ROLE_PARAGRAPH READONLY
+++++++++ROLE_SYSTEM_STATICTEXT name='Lorem Ipsum is simply dummy text of the printing and typesetting industry.<newline>Lorem Ipsum has been the industry's standard dummy text ever since the 1500s.<newline>' READONLY
+++++++IA2_ROLE_PARAGRAPH READONLY
+++++++++ROLE_SYSTEM_STATICTEXT name='It has survived not only five centuries, but also the leap into electronic typesetting,<newline>remaining essentially unchanged. It was popularised in the 1960s with the release of<newline>Letraset sheets containing Lorem Ipsum passages, and more recently with desktop<newline>publishing software like Aldus PageMaker including versions of Lorem Ipsum.<newline>' READONLY
+++++++IA2_ROLE_PARAGRAPH READONLY
+++++++++ROLE_SYSTEM_STATICTEXT name='Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots<newline>in a piece of classical Latin literature from 45 BC, making it over 2000 years old.' READONLY

chrome/test/data/pdf/accessibility/paragraphs-and-heading-untagged.in

+{{header}}
+{{object 1 0}} <<
+  /Type /Catalog
+  /Pages 2 0 R
+>>
+endobj
+{{object 2 0}} <<
+  /Type /Pages
+  /Count 1
+  /Kids [3 0 R]
+>>
+endobj
+% Page number 0
+{{object 3 0}} <<
+  /Type /Page
+  /Parent 2 0 R
+  /Contents 4 0 R
+  /Resources <<
+    /Font <<
+      /F1 5 0 R
+    >>
+    /ProcSet [/PDF /Text]
+  >>
+  /MediaBox [0 0 612 792]
+>>
+endobj
+{{object 4 0}} <<
+  {{streamlen}}
+>>
+stream
+2 J
+BT
+0 0 0 rg
+/F1 0027 Tf
+69 723 Td
+(Heading) Tj
+ET
+BT
+/F1 0010 Tf
+69 688 Td
+(This is a small pdf file:) Tj
+ET
+BT
+/F1 0010 Tf
+69 664 Td
+(Lorem Ipsum is simply dummy text of the printing and typesetting industry.) Tj
+ET
+BT
+/F1 0010 Tf
+69 652 Td
+(Lorem Ipsum has been the industry's standard dummy text ever since the 1500s.) Tj
+ET
+BT
+/F1 0010 Tf
+69 628 Td
+(It has survived not only five centuries, but also the leap into electronic typesetting,) Tj
+ET
+BT
+/F1 0010 Tf
+69 616 Td
+(remaining essentially unchanged.  It was popularised in the 1960s with the release of) Tj
+ET
+BT
+/F1 0010 Tf
+69 604 Td
+(Letraset sheets containing Lorem Ipsum passages, and more recently with desktop) Tj
+ET
+BT
+/F1 0010 Tf
+69 592 Td
+(publishing software like Aldus PageMaker including versions of Lorem Ipsum.) Tj
+ET
+BT
+/F1 0010 Tf
+69 569 Td
+(Contrary to popular belief, Lorem Ipsum is not simply random text. It has roots) Tj
+ET
+BT
+/F1 0010 Tf
+69 557 Td
+(in a piece of classical Latin literature from 45 BC, making it over 2000 years old.) Tj
+ET
+endstream
+endobj
+{{object 5 0}} <<
+  /Type /Font
+  /SubType /Type1
+  /Name /F1
+  /BaseFont /Helvetica
+  /Encoding /WinAnsiEncoding
+>>
+endobj
+
+{{xref}}
+{{trailer}}
+{{startxref}}
+%EOF
\ No newline at end of file