From 45727c4e6de7f6f6f61a4ae3589d5dd271ea8803 Mon Sep 17 00:00:00 2001
From: Lars Ingebrigtsen <larsi@gnus.org>
Date: Fri, 27 Sep 2019 00:32:37 +0200
Subject: [PATCH] Add a new `dom-search' function

* doc/lispref/text.texi (Document Object Model): Document it.

* lisp/dom.el (dom-search): New function.
---
 doc/lispref/text.texi |  5 +++++
 etc/NEWS              |  6 ++++++
 lisp/dom.el           | 12 ++++++++++++
 3 files changed, 23 insertions(+)

diff --git a/doc/lispref/text.texi b/doc/lispref/text.texi
index d7b04d2934f..8d78a9b24ff 100644
--- a/doc/lispref/text.texi
+++ b/doc/lispref/text.texi
@@ -5162,6 +5162,11 @@ which is a regular expression.
 Return all nodes in @var{dom} that have IDs that match @var{match},
 which is a regular expression.
 
+@item dom-search @var{dom} @var{predicate}
+Return all nodes in @var{dom} where @var{predicate} returns a
+non-@code{nil} value.  @var{predicate} is called with the node to be
+tested as its parameter.
+
 @item dom-strings @var{dom}
 Return all strings in @var{dom}.
 
diff --git a/etc/NEWS b/etc/NEWS
index 0a4ada3cc6c..afeb3877739 100644
--- a/etc/NEWS
+++ b/etc/NEWS
@@ -275,6 +275,12 @@ obsolete, and the new utility function 'xml-remove-comments' can be
 used to remove comments before calling the libxml functions to parse
 the data.
 
++++
+** A new DOM (the XML/HTML document structure returned by functions
+such as 'libxml-parse-html-region') traversal function has been added:
+'dom-search', which takes a DOM and a predicate and returns all nodes
+that match.
+
 +++
 ** The Network Security Manager now allows more fine-grained control
 of what checks to run via the 'network-security-protocol-checks'
diff --git a/lisp/dom.el b/lisp/dom.el
index d8c44339985..f01da5221b8 100644
--- a/lisp/dom.el
+++ b/lisp/dom.el
@@ -108,6 +108,18 @@ A name is a symbol like `td'."
 	(cons dom matches)
       matches)))
 
+(defun dom-search (dom predicate)
+  "Return elements in DOM where PREDICATE is non-nil.
+PREDICATE is called with the node as its only parameter."
+  (let ((matches (cl-loop for child in (dom-children dom)
+			  for matches = (and (not (stringp child))
+					     (dom-search child predicate))
+			  when matches
+			  append matches)))
+    (if (funcall predicate dom)
+	(cons dom matches)
+      matches)))
+
 (defun dom-strings (dom)
   "Return elements in DOM that are strings."
   (cl-loop for child in (dom-children dom)
-- 
2.39.2