improved PDF/UA support:

- added testing via Makefile
- added tagging methods
- fixed examples E015, E016, E017 and E063

Author: nicolaasuni

Makefile

@@ -101,6 +101,9 @@ PHPDOC=$(shell which phpDocumentor)
 # phpstan version
 PHPSTANVER=2.1.40
 
+# veraPDF binary path (can be overridden, e.g. make verapdf-ua VERAPDF_BIN=/opt/verapdf/bin/verapdf)
+VERAPDF_BIN?=$(shell command -v verapdf 2>/dev/null)
+
 # --- MAKE TARGETS ---
 
 # Display general help about this command
@@ -245,6 +248,32 @@ report: ensuretarget
 preflight: ensuretarget
 	bash ./resources/preflight/run_preflight_matrix.sh
 
+## Generate PDF/UA examples and validate with veraPDF
+.PHONY: verapdf-ua
+verapdf-ua: ensuretarget
+	@if [[ -z "$(VERAPDF_BIN)" ]]; then \
+		echo "veraPDF CLI not found. Set VERAPDF_BIN=/path/to/verapdf or add verapdf to PATH."; \
+		exit 2; \
+	fi
+	$(PHP) examples/E015_pdfua.php > $(TARGETDIR)/report/E015_pdfua.pdf
+	$(PHP) examples/E016_pdfua1.php > $(TARGETDIR)/report/E016_pdfua1.pdf
+	$(PHP) examples/E017_pdfua2.php > $(TARGETDIR)/report/E017_pdfua2.pdf
+	@fail=0; \
+	for spec in "E015_pdfua.pdf:ua1" "E016_pdfua1.pdf:ua1" "E017_pdfua2.pdf:ua2"; do \
+		file="$${spec%%:*}"; \
+		flavour="$${spec##*:}"; \
+		input="$(TARGETDIR)/report/$${file}"; \
+		report="$(TARGETDIR)/report/$${file%.pdf}.verapdf.txt"; \
+		if "$(VERAPDF_BIN)" --format text --verbose --flavour "$${flavour}" "$${input}" > "$${report}" 2>&1; then \
+			echo "[ok] $${file} ($${flavour})"; \
+		else \
+			echo "[fail] $${file} ($${flavour}) - see $${report}"; \
+			fail=1; \
+		fi; \
+	done; \
+	echo "veraPDF reports written to $(TARGETDIR)/report/*.verapdf.txt"; \
+	exit $$fail
+
 ## Build the RPM package for RedHat-like Linux distributions
 .PHONY: rpm
 rpm:

README.md

@@ -602,13 +602,29 @@ When a PDF/UA mode is active the library automatically:
 - Tags text content with MCIDs and wraps each run in the appropriate structure element (`P`, `H1`–`H6`, `Link`, etc.)
 - Tags `<img>` elements as `Figure` with their `alt` attribute written as `/Alt` in the structure element
 - Emits `ActualText` entries for ligatures and special glyphs so text extraction and screen readers work correctly
+- Provides Artifact marked-content helpers for non-semantic content (`beginArtifact()`, `endArtifact()`, `addArtifactContent()`)
 
 To provide the document language explicitly:
 
 ```php
 $pdf->setDocInfo(['a_meta_language' => 'de-DE']);
 ```
 
+To tag decorative or repeated content as Artifact (for example headers, footers, and page numbers):
+
+```php
+$pid = $pdf->addPage()['pid'];
+
+$headerOperators = $pdf->graph->getLine(10, 10, 200, 10);
+$pdf->addArtifactContent($headerOperators, $pid, 'Pagination', 'Header');
+
+$footerText = $pdf->getTextCell('Page 1', 180, 280, 20, 5);
+$pdf->addArtifactContent($footerText, $pid, 'Pagination', 'Footer');
+```
+
+In PDF/UA mode, the built-in `defaultPageContent()` page-number footer is emitted as `Artifact` with
+`/Type /Pagination /Subtype /Footer`.
+
 Runnable examples: [examples/E015_pdfua.php](examples/E015_pdfua.php) through [examples/E017_pdfua2.php](examples/E017_pdfua2.php).
 
 ---

VERSION

@@ -1 +1 @@
-8.16.0
+8.17.0

examples/E005_header_footer.php

@@ -100,19 +100,20 @@ public function defaultPageContent(int $pid = -1): string
             'lineColor' => '#555555',
         ];
 
-        $out = $this->graph->getStartTransform();
-        $out .= $this->defaultfont['out'];
+        $out = '';
 
         // ---- HEADER ------------------------------------------------
 
         $headerY = self::HF_MARGIN;
+        $headerOut = $this->graph->getStartTransform();
+        $headerOut .= $this->defaultfont['out'];
 
         // Title – left-aligned, bold
         if ($this->headerTitle !== '') {
             $bfontBold = $this->font->insert($this->pon, 'helvetica', 'B', 10);
-            $out .= $bfontBold['out'];
-            $out .= $this->color->getPdfColor('#1a3a6b');
-            $out .= $this->getTextCell(
+            $headerOut .= $bfontBold['out'];
+            $headerOut .= $this->color->getPdfColor('#1a3a6b');
+            $headerOut .= $this->getTextCell(
                 $this->headerTitle,
                 $lm,
                 $headerY,
@@ -123,13 +124,13 @@ public function defaultPageContent(int $pid = -1): string
                 'C',           // valign: centre inside the band
                 'L',           // halign: left
             );
-            $out .= $this->defaultfont['out'];
+            $headerOut .= $this->defaultfont['out'];
         }
 
         // Subtitle – right-aligned
         if ($this->headerSubtitle !== '') {
-            $out .= $this->color->getPdfColor('#555555');
-            $out .= $this->getTextCell(
+            $headerOut .= $this->color->getPdfColor('#555555');
+            $headerOut .= $this->getTextCell(
                 $this->headerSubtitle,
                 $lm + $tw * 0.65,
                 $headerY,
@@ -144,18 +145,25 @@ public function defaultPageContent(int $pid = -1): string
 
         // Separator line below the header
         $headerLineY = $headerY + self::HEADER_H;
-        $out .= $this->graph->getLine($lm, $headerLineY, $rm, $headerLineY, $lineStyle);
+        $headerOut .= $this->graph->getLine($lm, $headerLineY, $rm, $headerLineY, $lineStyle);
+        $headerOut .= $this->graph->getStopTransform();
+
+        $out .= $this->beginArtifact('Pagination', 'Header');
+        $out .= $headerOut;
+        $out .= $this->endArtifact();
 
         // ---- FOOTER ------------------------------------------------
 
         $footerLineY = $ph - self::HF_MARGIN - self::FOOTER_H;
+        $footerOut = $this->graph->getStartTransform();
+        $footerOut .= $this->defaultfont['out'];
 
         // Separator line above the footer
-        $out .= $this->graph->getLine($lm, $footerLineY, $rm, $footerLineY, $lineStyle);
+        $footerOut .= $this->graph->getLine($lm, $footerLineY, $rm, $footerLineY, $lineStyle);
 
         // Page number – centred
-        $out .= $this->color->getPdfColor('#555555');
-        $out .= $this->getTextCell(
+        $footerOut .= $this->color->getPdfColor('#555555');
+        $footerOut .= $this->getTextCell(
             'Page ' . ($pid + 1),
             $lm,
             $footerLineY,
@@ -166,8 +174,11 @@ public function defaultPageContent(int $pid = -1): string
             'C',               // valign: centre inside the band
             'C',               // halign: centre
         );
+        $footerOut .= $this->graph->getStopTransform();
 
-        $out .= $this->graph->getStopTransform();
+        $out .= $this->beginArtifact('Pagination', 'Footer');
+        $out .= $footerOut;
+        $out .= $this->endArtifact();
 
         return $out;
     }
@@ -181,7 +192,7 @@ public function defaultPageContent(int $pid = -1): string
     true,  // bool $isunicode = true,
     false, // bool $subsetfont = false,
     true,  // bool $compress = true,
-    '',    // string $mode = '',
+    'pdfua1', // string $mode = 'pdfua1',
     null,  // ?ObjEncrypt $objEncrypt = null,
 );
 
@@ -195,6 +206,7 @@ public function defaultPageContent(int $pid = -1): string
 $pdf->setPDFFilename('005_header_footer.pdf');
 
 $pdf->setViewerPreferences(['DisplayDocTitle' => true]);
+$pdf->setLanguageArray(['a_meta_language' => 'en-US']);
 
 // Set the text that will appear in the header on every page.
 $pdf->setHeaderText('My Document Title', \date('Y-m-d'));

examples/E015_pdfua.php

@@ -33,7 +33,7 @@
 $pdf->setPDFFilename('E015_pdfua.pdf');
 $pdf->setLanguage('en-US');
 
-$font = $pdf->font->insert($pdf->pon, 'helvetica', '', 10);
+$font = $pdf->font->insert($pdf->pon, 'dejavusans', '', 10);
 $pdf->addPage();
 $pdf->page->addContent($font['out']);
 
@@ -58,9 +58,7 @@
     . '<blockquote>&ldquo;Tagged PDF is the foundation of accessible PDF. Without a'
     . ' well-formed structure tree, automated tools and assistive technologies cannot'
     . ' reliably interpret document content.&rdquo; &mdash; ISO&#160;14289-1 rationale</blockquote>'
-    . '<p>The <code>blockquote</code> tag maps to <strong>BlockQuote</strong>.'
-    . ' The <code>pre</code> tag maps to <strong>Code</strong>:</p>'
-    . '<pre>// pre / code block example&#10;function greet(string $name): string {&#10;    return "Hello, " . $name . "!";&#10;}</pre>'
+    . '<p>The <code>blockquote</code> tag maps to <strong>BlockQuote</strong>.</p>'
 
     . '<h2>3 — List Structure (L &gt; LI &gt; Lbl + LBody)</h2>'
     . '<p>Both <code>ul</code> and <code>ol</code> map to the <strong>L</strong> role.'
@@ -100,14 +98,14 @@
     . '<tr><td>figcaption, caption</td><td>Caption</td><td>Illustration</td></tr>'
     . '<tr><td>table</td><td>Table</td><td>Table</td></tr>'
     . '<tr><td>tr</td><td>TR</td><td>Table</td></tr>'
-    . '<tr><td>th</td><td>TH</td><td>Table</td></tr>'
     . '<tr><td>td</td><td>TD</td><td>Table</td></tr>'
+    . '<tr><td>th</td><td>TH</td><td>Table</td></tr>'
     . '<tr><td>a</td><td>Link</td><td>Inline</td></tr>'
     . '</table>'
 
     . '<h2>6 — Hyperlink (Link Role)</h2>'
     . '<p>This sentence contains a'
-    . ' <a href="https://github.com/tecnickcom/tc-lib-pdf">hyperlink to the tc-lib-pdf repository</a>;'
+    . ' <a href="https://github.com/tecnickcom/tc-lib-pdf" style="text-decoration:none;">hyperlink to the tc-lib-pdf repository</a>;'
     . ' the <code>a</code> element is tagged with the <strong>Link</strong> structure role'
     . ' automatically. The link text is accessible to screen readers via the structure tree.</p>';
 

examples/E016_pdfua1.php

@@ -40,7 +40,7 @@
 $pdf->setPDFFilename('E016_pdfua1.pdf');
 $pdf->setLanguage('en-US');
 
-$font = $pdf->font->insert($pdf->pon, 'helvetica', '', 10);
+$font = $pdf->font->insert($pdf->pon, 'dejavusans', '', 10);
 $pdf->addPage();
 $pdf->page->addContent($font['out']);
 
@@ -66,9 +66,7 @@
     . '<blockquote>&ldquo;Tagged PDF is the foundation of accessible PDF. Without a'
     . ' well-formed structure tree, automated tools and assistive technologies cannot'
     . ' reliably interpret document content.&rdquo; &mdash; ISO&#160;14289-1 rationale</blockquote>'
-    . '<p>The <code>blockquote</code> tag maps to <strong>BlockQuote</strong>.'
-    . ' The <code>pre</code> tag maps to <strong>Code</strong>:</p>'
-    . '<pre>// PDF/UA-1 requires MarkInfo /Marked true in the catalog&#10;// and a StructTreeRoot with a ParentTree mapping&#10;// every page to its tagged content blocks.</pre>'
+    . '<p>The <code>blockquote</code> tag maps to <strong>BlockQuote</strong>.</p>'
 
     . '<h2>3 — List Structure (L &gt; LI &gt; Lbl + LBody)</h2>'
     . '<p>Both <code>ul</code> and <code>ol</code> map to the <strong>L</strong> role.'
@@ -109,14 +107,14 @@
     . '<tr><td>figcaption, caption</td><td>Caption</td><td>Illustration</td></tr>'
     . '<tr><td>table</td><td>Table</td><td>Table</td></tr>'
     . '<tr><td>tr</td><td>TR</td><td>Table</td></tr>'
-    . '<tr><td>th</td><td>TH</td><td>Table</td></tr>'
     . '<tr><td>td</td><td>TD</td><td>Table</td></tr>'
+    . '<tr><td>th</td><td>TH</td><td>Table</td></tr>'
     . '<tr><td>a</td><td>Link</td><td>Inline</td></tr>'
     . '</table>'
 
     . '<h2>6 — Hyperlink (Link Role)</h2>'
     . '<p>This sentence contains a'
-    . ' <a href="https://github.com/tecnickcom/tc-lib-pdf">hyperlink to the tc-lib-pdf repository</a>;'
+    . ' <a href="https://github.com/tecnickcom/tc-lib-pdf" style="text-decoration:none;">hyperlink to the tc-lib-pdf repository</a>;'
     . ' the <code>a</code> element is tagged with the <strong>Link</strong> structure role'
     . ' automatically. PDF/UA-1 requires that link annotations have an accessible name,'
     . ' which the library derives from the link text in the structure tree.</p>';

examples/E017_pdfua2.php

@@ -38,7 +38,7 @@
 $pdf->setPDFFilename('E017_pdfua2.pdf');
 $pdf->setLanguage('en-US');
 
-$font = $pdf->font->insert($pdf->pon, 'helvetica', '', 10);
+$font = $pdf->font->insert($pdf->pon, 'dejavusans', '', 10);
 $pdf->addPage();
 $pdf->page->addContent($font['out']);
 
@@ -65,9 +65,7 @@
     . '<blockquote>&ldquo;Tagged PDF is the foundation of accessible PDF. Without a'
     . ' well-formed structure tree, automated tools and assistive technologies cannot'
     . ' reliably interpret document content.&rdquo; &mdash; ISO&#160;14289 rationale</blockquote>'
-    . '<p>The <code>blockquote</code> tag maps to <strong>BlockQuote</strong>.'
-    . ' The <code>pre</code> tag maps to <strong>Code</strong>:</p>'
-    . '<pre>// PDF/UA-2 targets PDF 2.0 — the catalog carries pdfver 2.0&#10;// and the XMP metadata block uses the PDF/UA-2 identification schema.&#10;// The structure-tree and MarkInfo rules are inherited from PDF/UA-1.</pre>'
+    . '<p>The <code>blockquote</code> tag maps to <strong>BlockQuote</strong>.</p>'
 
     . '<h2>3 — List Structure (L &gt; LI &gt; Lbl + LBody)</h2>'
     . '<p>Both <code>ul</code> and <code>ol</code> map to the <strong>L</strong> role.'
@@ -108,14 +106,14 @@
     . '<tr><td>figcaption, caption</td><td>Caption</td><td>Illustration</td></tr>'
     . '<tr><td>table</td><td>Table</td><td>Table</td></tr>'
     . '<tr><td>tr</td><td>TR</td><td>Table</td></tr>'
-    . '<tr><td>th</td><td>TH</td><td>Table</td></tr>'
     . '<tr><td>td</td><td>TD</td><td>Table</td></tr>'
+    . '<tr><td>th</td><td>TH</td><td>Table</td></tr>'
     . '<tr><td>a</td><td>Link</td><td>Inline</td></tr>'
     . '</table>'
 
     . '<h2>6 — Hyperlink (Link Role)</h2>'
     . '<p>This sentence contains a'
-    . ' <a href="https://github.com/tecnickcom/tc-lib-pdf">hyperlink to the tc-lib-pdf repository</a>;'
+    . ' <a href="https://github.com/tecnickcom/tc-lib-pdf" style="text-decoration:none;">hyperlink to the tc-lib-pdf repository</a>;'
     . ' the <code>a</code> element is tagged with the <strong>Link</strong> structure role'
     . ' automatically. In PDF/UA-2 (as in PDF/UA-1), link annotations must be accessible;'
     . ' the library derives the accessible name from the link text in the structure tree.</p>';