CXML embedding DTD incorrectly, https://stackoverflow.com/questions/26738465/non-valid-output-of-broadcast-handler-in-common-lisp-closure-xml-package/28528117#28528117

0001-Fix-DTD-embedding.patch

From 991fac513dbd9b86628f99741a66d791552b1f02 Mon Sep 17 00:00:00 2001
From: Olof-Joachim Frahm <[email protected]>
Date: Sun, 15 Feb 2015 15:56:21 +0000
Subject: [PATCH] Fix DTD embedding.

---
 xml/xml-parse.lisp |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/xml/xml-parse.lisp b/xml/xml-parse.lisp
index cfbb441..dc31e3a 100644
--- a/xml/xml-parse.lisp
+++ b/xml/xml-parse.lisp
@@ -2606,12 +2606,14 @@ (defun p/doctype-decl (input &optional dtd-extid)
               (let ((xi2 (xstream-open-extid effective-extid)))
                (with-zstream (zi2 :input-stack (list xi2))
                  (ensure-dtd)
+                 (sax:start-internal-subset (handler *ctx*))
                  (p/ext-subset zi2)
                  (when (and fresh-dtd-p
                             *cache-all-dtds*
                             *validate*
                             (not (standalone-p *ctx*)))
-                   (setf (getdtd sysid *dtd-cache*) (dtd *ctx*)))))))))
+                   (setf (getdtd sysid *dtd-cache*) (dtd *ctx*)))
+                 (sax:end-internal-subset (handler *ctx*))))))))
       (sax:end-dtd (handler *ctx*))
       (let ((dtd (dtd *ctx*)))
         (sax:entity-resolver
-- 
1.7.10.4

harem.dtd

<!ELEMENT EM #PCDATA>
<!ATTLIST EM ID CDATA #REQUIRED>
<!ATTLIST EM CATEG CDATA #IMPLIED>
<!ATTLIST EM TIPO CDATA #IMPLIED>
<!ATTLIST EM COMENT CDATA #IMPLIED>
<!ATTLIST EM SUBTIPO CDATA #IMPLIED>
<!ELEMENT ALT (#PCDATA|EM)*>
<!ELEMENT OMITIDO (#PCDATA|EM|ALT|p)*>
<!ELEMENT colHAREM (DOC)*>
<!ATTLIST colHAREM versao CDATA #REQUIRED>
<!ELEMENT p (#PCDATA|EM|OMITIDO|ALT)*>
<!ATTLIST p xml:space (default|preserve) "default">
<!ELEMENT DOC (#PCDATA|p|OMITIDO)*>
<!ATTLIST DOC DOCID CDATA #REQUIRED>

harem.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE colHAREM SYSTEM "harem.dtd">
<colHAREM versao="Segundo_dourada_com_relacoes_14Abril2010">
  <DOC DOCID="H2-dftre765">
    <p></p>
  </DOC>
</colHAREM>

teste.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE colHAREM SYSTEM "harem.dtd" [
<!ELEMENT EM #PCDATA>
<!ATTLIST EM ID CDATA #REQUIRED>
<!ATTLIST EM CATEG CDATA #IMPLIED>
<!ATTLIST EM TIPO CDATA #IMPLIED>
<!ATTLIST EM COMENT CDATA #IMPLIED>
<!ATTLIST EM SUBTIPO CDATA #IMPLIED>
<!ELEMENT ALT (#PCDATA|EM)*>
<!ELEMENT OMITIDO (#PCDATA|EM|ALT|p)*>
<!ELEMENT colHAREM (DOC)*>
<!ATTLIST colHAREM versao CDATA #REQUIRED>
<!ELEMENT p (#PCDATA|EM|OMITIDO|ALT)*>
<!ATTLIST p xml:space (default|preserve) "default">
<!ELEMENT DOC (#PCDATA|p|OMITIDO)*>
<!ATTLIST DOC DOCID CDATA #REQUIRED>
]>
<colHAREM versao="Segundo_dourada_com_relacoes_14Abril2010">
  <DOC DOCID="H2-dftre765">
    <p xml:space="default"/>
  </DOC>
</colHAREM>

xml.lisp

(defclass preproc (cxml:sax-proxy) ())

(defmethod sax:characters ((handler preproc) data)
  (let ((parts (cl-ppcre:split "\\|" data)))
    ;; check this on edge cases, though, e.g., "", "|", "a|", strings
    ;; without any "|", etc.
    (call-next-method handler (pop parts))
    (dolist (part parts)
      (sax:start-element handler nil nil "bar" '())
      (sax:end-element handler nil nil "bar")
      (call-next-method handler part))))

(defun foo ()
  (with-open-file (out #P"teste.xml" :if-exists :supersede :direction :output)
    (let ((h (make-instance 'preproc :chained-handler (cxml:make-character-stream-sink out))))
      (cxml:parse #P"harem.xml" h :validate t))))