Make eww more liberal when interpreting some invalid HTML

* lisp/net/eww.el (eww--preprocess-html): New function (bug#37009)
to be more lenient with invalid HTML and translate common invalid
HTML like "a <= b" into "a &lt;= b" to be more liberal in what we
accept before parsing.
(eww-display-html): Use it.
(eww-readable): Ditto.

diff --git a/lisp/net/eww.el b/lisp/net/eww.el
index 77e6cec9b049c0ff9e1cef26720274d9aa9f5905..2013604c9e7dc2b39016e46afbf6452e8fb8be5b 100644 (file)
--- a/lisp/net/eww.el
+++ b/lisp/net/eww.el
@@ -326,6 +326,18 @@ the default EWW buffer."
                               #'url-hexify-string (split-string url) "+"))))))
   url)
 
+(defun eww--preprocess-html (start end)
+  "Translate all < characters that do not look like start of tags into &lt;."
+  (save-excursion
+    (save-restriction
+      (narrow-to-region start end)
+      (goto-char start)
+      (let ((case-fold-search t))
+        (while (re-search-forward "<[^0-9a-z!/]" nil t)
+          (goto-char (match-beginning 0))
+          (delete-region (point) (1+ (point)))
+          (insert "&lt;"))))))
+
 ;;;###autoload (defalias 'browse-web 'eww)
 
 ;;;###autoload
@@ -479,6 +491,7 @@ Currently this means either text/html or application/xhtml+xml."
                  ;; Remove CRLF and replace NUL with &#0; before parsing.
                  (while (re-search-forward "\\(\r$\\)\\|\0" nil t)
                    (replace-match (if (match-beginning 1) "" "&#0;") t t)))
+                (eww--preprocess-html (point) (point-max))
                (libxml-parse-html-region (point) (point-max))))))
        (source (and (null document)
                     (buffer-substring (point) (point-max)))))
@@ -716,6 +729,7 @@ the like."
                (condition-case nil
                    (decode-coding-region (point-min) (point-max) 'utf-8)
                  (coding-system-error nil))
+                (eww--preprocess-html (point-min) (point-max))
                (libxml-parse-html-region (point-min) (point-max))))
          (base (plist-get eww-data :url)))
     (eww-score-readability dom)