Merge 4edc60d into 8d6a860

NSoiffer · web-flow · commit b46a1cde7a7c · 2024-10-25T01:46:33.000Z
diff --git a/nvdaHelper/vbufBackends/adobeAcrobat/adobeAcrobat.cpp b/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();
diff --git a/source/NVDAObjects/IAccessible/adobeAcrobat.py b/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:
@@ -136,16 +142,38 @@ def _getNodeMathMl(self, node):
 					yield sub
 		yield "</%s>" % tag
 
-	def _get_mathMl(self):
-		# There could be other stuff before the math element. Ug.
+	def _get_mathMl(self) -> str:
+		"""Return the MathML associated with a Formula tag"""
+		if self.pdDomNode is None:
+			log.debugWarning("_get_mathMl: self.pdDomNode is None!")
+			raise LookupError
+		mathMl = self.pdDomNode.GetValue()
+		if log.isEnabledFor(log.DEBUG):
+			log.debug(
+				(
+					f"_get_mathMl: math recognized: {mathMl.startswith('<math')}, "
+					f"child count={self.pdDomNode.GetChildCount()},"
+					f"\n  name='{self.pdDomNode.GetName()}', value='{mathMl}'"
+				),
+			)
+		# 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"', "")
+		# Alternative for tagging: all the sub expressions are tagged -- gather up the 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
+			if log.isEnabledFor(log.DEBUG):
+				log.debug(f"\tget_mathMl: tag={child.GetTagName()}")
 			if child.GetTagName() == "math":
 				return "".join(self._getNodeMathMl(child))
-		raise LookupError
+		# fall back to return the contents, which is hopefully alt text
+		if log.isEnabledFor(log.DEBUG):
+			log.debug("_get_mathMl: didn't find MathML -- returning value as mtext")
+		return f"<math><mtext>{self.pdDomNode.GetValue()}</mtext></math>"
 
 
 class RootNode(AcrobatNode):
diff --git a/user_docs/en/changes.md b/user_docs/en/changes.md
@@ -6,6 +6,9 @@
 
 ### New Features
 
+* Support for math in PDFs has been added.
+This works for formulas with associated MathML, such as some files generated by newer versions of TeX/LaTeX.
+Currently this is only supported in Foxit Reader & Foxit Editor. (#9288, @NSoiffer)
 * Commands to adjust the volume of other applications besides NVDA have been added.
 To use this feature, "allow NVDA to control the volume of other applications" must be enabled in the audio settings panel. (#16052, @mltony, @codeofdusk)
   * `NVDA+alt+pageUp`: Increase the volume of all other applications.
