Add ability to read math in PDF documents

nvdaHelper/vbufBackends/adobeAcrobat/adobeAcrobat.cpp

@@ -437,7 +437,6 @@ AdobeAcrobatVBufStorage_controlFieldNode_t* AdobeAcrobatVBufBackend_t::fillVBuf(
 	}
 
 	BSTR stdName = NULL;
-	BSTR tagName = NULL;
 	int textFlags = 0;
 	// Whether to render just a space in place of the content.
 	bool renderSpace = false;
@@ -454,18 +453,8 @@ AdobeAcrobatVBufStorage_controlFieldNode_t* AdobeAcrobatVBufBackend_t::fillVBuf(
 				// This is an inline element.
 				parentNode->isBlock=false;
 			}
-		}
-
-		// Get tagName.
-		if ((res = domElement->GetTagName(&tagName)) != S_OK) {
-			LOG_DEBUG(L"IPDDomElement::GetTagName returned " << res);
-			tagName = NULL;
-		}
-		if (tagName) {
-			parentNode->addAttribute(L"acrobat::tagname", tagName);
-			if (wcscmp(tagName, L"math") == 0) {
-				// We don't want the content of math nodes here,
-				// As it will be fetched by NVDAObjects outside of the virtualBuffer.
+			if (wcscmp(stdName, L"Formula") == 0) {
+				// We don't want the content of formulas,
 				// but we still want a space so the user can get at them.
 				renderSpace = true;
 			}
@@ -747,8 +736,6 @@ AdobeAcrobatVBufStorage_controlFieldNode_t* AdobeAcrobatVBufBackend_t::fillVBuf(
 		delete pageNum;
 	if (stdName)
 		SysFreeString(stdName);
-	if (tagName)
-		SysFreeString(tagName);
 	if (domElement) {
 		LOG_DEBUG(L"Releasing IPDDomElement");
 		domElement->Release();

source/NVDAObjects/IAccessible/adobeAcrobat.py

@@ -76,11 +76,17 @@ def initOverlayClass(self):
 				self.accID = None
 
 		# Get the IPDDomNode.
+		try:
+			serv.QueryService(SID_GetPDDomNode, IGetPDDomNode)
+		except COMError:
+			log.debugWarning("FAILED: QueryService(SID_GetPDDomNode, IGetPDDomNode)")
+			self.pdDomNode = None
 		try:
 			self.pdDomNode = serv.QueryService(SID_GetPDDomNode, IGetPDDomNode).get_PDDomNode(
 				self.IAccessibleChildID,
 			)
 		except COMError:
+			log.debugWarning("FAILED: get_PDDomNode")
 			self.pdDomNode = None
 
 		if self.pdDomNode:
@@ -137,15 +143,30 @@ def _getNodeMathMl(self, node):
 		yield "</%s>" % tag
 
 	def _get_mathMl(self):
+		if self.pdDomNode is None:
+			log.debugWarning("_get_mathMl: self.pdDomNode is None!")
+			raise LookupError
 		# There could be other stuff before the math element. Ug.
+		mathMl = self.pdDomNode.GetValue()
+		log.debug(
+			f'\n_get_mathMl: math recognized: {mathMl.startswith("<math")}, child count={self.pdDomNode.GetChildCount()}',
+		)
+		log.debug(f"\nname={self.pdDomNode.GetName()}\nvalue={self.pdDomNode.GetValue()}")
+		# this test and the replacement doesn't work if someone uses a namespace tag (which they shouldn't, but..)
+		if mathMl.startswith("<math"):
+			return mathMl.replace('xmlns:mml="http://www.w3.org/1998/Math/MathML"', "")
 		for childNum in range(self.pdDomNode.GetChildCount()):
 			try:
 				child = self.pdDomNode.GetChild(childNum).QueryInterface(IPDDomElement)
 			except COMError:
+				log.debugWarning(f"COMError trying to get childNum={childNum}")
 				continue
+			log.debug(f"  get_mathMl: tag={child.GetTagName()}")
 			if child.GetTagName() == "math":
 				return "".join(self._getNodeMathMl(child))
-		raise LookupError
+		# fall back to return the contents, which is hopefully to be alt text
+		log.debug("_get_mathMl: didn't find MathML -- returning value as mtext")
+		return f"<math><mtext>{self.pdDomNode.GetValue()}</mtext></math>"
 
 
 class RootNode(AcrobatNode):

user_docs/en/changes.md

@@ -5,7 +5,7 @@
 ### Important notes
 
 ### New Features
-
+* Support for math in PDFs has been added. This works for formulas that have MathML in an Associated File. Tagged formulas are supported in newer versions of TeX/LaTeX (9288, @NSoiffer)
 * The volume of other applications can be adjusted by `NVDA+alt+pageUp` and `NVDA+alt+pageDown`. In order to use this feature, application volume adjuster needs to be enabled in Audio pane of NVDA settings. (#16052, @mltony)
 * Added command to mute or unmute all other applications, assigned to `NVDA+alt+delete`.
 In order to use this feature, the application volume adjuster needs to be enabled in the Audio category of NVDA settings. (#16052, @mltony)