doc: Check DocBook XML validity during the build

Building the documentation with XSLT does not check the DTD, like a
DSSSL build would.  One can often get away with having invalid XML, but
the stylesheets might then create incorrect output, as they are not
designed to handle that.  Therefore, check the validity of the XML
against the DTD, using xmllint, during the build.

Add xmllint detection to configure, and add some documentation.

xmllint comes with libxml2, which is already in use, but it might be in
a separate package, such as libxml2-utils on Debian.

Reviewed-by: Fabien COELHO <[email protected]>

5 files changed, 68 insertions, 2 deletions

diff --git a/configure b/configure
index f0580ceb5e..b403a04172 100755
--- a/configure
+++ b/configure
@@ -630,6 +630,7 @@ vpath_build
 PROVE
 OSX
 XSLTPROC
+XMLLINT
 DBTOEPUB
 COLLATEINDEX
 DOCBOOKSTYLE
@@ -14654,6 +14655,48 @@ fi
   test -n "$DBTOEPUB" && break
 done
 
+for ac_prog in xmllint
+do
+  # Extract the first word of "$ac_prog", so it can be a program name with args.
+set dummy $ac_prog; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_XMLLINT+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$XMLLINT"; then
+  ac_cv_prog_XMLLINT="$XMLLINT" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_XMLLINT="$ac_prog"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+fi
+fi
+XMLLINT=$ac_cv_prog_XMLLINT
+if test -n "$XMLLINT"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $XMLLINT" >&5
+$as_echo "$XMLLINT" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+  test -n "$XMLLINT" && break
+done
+
 for ac_prog in xsltproc
 do
   # Extract the first word of "$ac_prog", so it can be a program name with args.
diff --git a/configure.in b/configure.in
index 527b076205..df868823c0 100644
--- a/configure.in
+++ b/configure.in
@@ -1869,6 +1869,7 @@ PGAC_CHECK_DOCBOOK(4.2)
 PGAC_PATH_DOCBOOK_STYLESHEETS
 PGAC_PATH_COLLATEINDEX
 AC_CHECK_PROGS(DBTOEPUB, dbtoepub)
+AC_CHECK_PROGS(XMLLINT, xmllint)
 AC_CHECK_PROGS(XSLTPROC, xsltproc)
 AC_CHECK_PROGS(OSX, [osx sgml2xml sx])
 
diff --git a/doc/src/sgml/Makefile b/doc/src/sgml/Makefile
index 1d42be8951..8bdd26ce28 100644
--- a/doc/src/sgml/Makefile
+++ b/doc/src/sgml/Makefile
@@ -44,6 +44,10 @@ ifndef OSX
 OSX = $(missing) osx
 endif
 
+ifndef XMLLINT
+XMLLINT = $(missing) xmllint
+endif
+
 ifndef XSLTPROC
 XSLTPROC = $(missing) xsltproc
 endif
@@ -78,6 +82,7 @@ override SPFLAGS += -wall -wno-unused-param -wno-empty -wfully-tagged
 man distprep-man: man-stamp
 
 man-stamp: stylesheet-man.xsl postgres.xml
+	$(XMLLINT) --noout --valid postgres.xml
 	$(XSLTPROC) $(XSLTPROCFLAGS) $(XSLTPROC_MAN_FLAGS) $^
 	touch $@
 
@@ -254,11 +259,13 @@ endif
 xslthtml: xslthtml-stamp
 
 xslthtml-stamp: stylesheet.xsl postgres.xml
+	$(XMLLINT) --noout --valid postgres.xml
 	$(XSLTPROC) $(XSLTPROCFLAGS) $(XSLTPROC_HTML_FLAGS) $^
 	cp $(srcdir)/stylesheet.css html/
 	touch $@
 
 htmlhelp: stylesheet-hh.xsl postgres.xml
+	$(XMLLINT) --noout --valid postgres.xml
 	$(XSLTPROC) $(XSLTPROCFLAGS) $^
 
 %-A4.fo.tmp: stylesheet-fo.xsl %.xml
@@ -268,7 +275,6 @@ htmlhelp: stylesheet-hh.xsl postgres.xml
 	$(XSLTPROC) $(XSLTPROCFLAGS) --stringparam paper.type USletter -o $@ $^
 
 FOP = fop
-XMLLINT = xmllint
 
 # reformat FO output so that locations of errors are easier to find
 %.fo: %.fo.tmp
@@ -281,6 +287,7 @@ XMLLINT = xmllint
 
 epub: postgres.epub
 postgres.epub: postgres.xml
+	$(XMLLINT) --noout --valid $<
 	$(DBTOEPUB) $<
 
 
diff --git a/doc/src/sgml/docguide.sgml b/doc/src/sgml/docguide.sgml
index 0186ef4afb..e0ae262b8a 100644
--- a/doc/src/sgml/docguide.sgml
+++ b/doc/src/sgml/docguide.sgml
@@ -149,6 +149,20 @@
     </varlistentry>
 
     <varlistentry>
+     <term><ulink url="http://xmlsoft.org/">Libxml2</ulink> for <command>xmllint</command></term>
+     <listitem>
+      <para>
+       This library and the <command>xmllint</command> tool it contains are
+       used for processing XML.  Many developers will already
+       have <application>Libxml2</application> installed, because it is also
+       used when building the PostgreSQL code.  Note, however,
+       that <command>xmllint</command> might need to be installed from a
+       separate subpackage.
+      </para>
+     </listitem>
+     </varlistentry>
+
+    <varlistentry>
      <term><ulink url="http://xmlsoft.org/XSLT/">Libxslt</ulink> for <command>xsltproc</command></term>
      <listitem>
       <para>
@@ -255,7 +269,7 @@ yum install docbook-dtds docbook-style-dsssl docbook-style-xsl libxslt openjade
     available for <productname>Debian GNU/Linux</productname>.
     To install, simply use:
 <programlisting>
-apt-get install docbook docbook-dsssl docbook-xsl openjade1.3 opensp xsltproc
+apt-get install docbook docbook-dsssl docbook-xsl libxml2-utils openjade1.3 opensp xsltproc
 </programlisting>
    </para>
   </sect2>
diff --git a/src/Makefile.global.in b/src/Makefile.global.in
index e76b22fb2d..7648dba172 100644
--- a/src/Makefile.global.in
+++ b/src/Makefile.global.in
@@ -353,6 +353,7 @@ DOCBOOKSTYLE	= @DOCBOOKSTYLE@
 JADE			= @JADE@
 NSGMLS			= @NSGMLS@
 OSX				= @OSX@
+XMLLINT			= @XMLLINT@
 XSLTPROC		= @XSLTPROC@
 
 # Code coverage