Doc: add check to detect non-breaking spaces in the docs.

There were multiple instances where accidentally adding non-breaking
space (nbsp, U+00A0, 0xc2a0 in UTF-8) to sgml files. This commit adds
additional checking to detect nbsp. You can check the nbsp by:

make -C doc/src/sgml check

or

make -C doc/src/sgml check-nbsp

Authors: Yugo Nagata, Daniel Gustafsson
Reviewed-by: Tatsuo Ishii, Daniel Gustafsson
Discussion: https://postgr.es/m/20240930.153404.202479334310259810.ishii%40postgresql.org

diff --git a/doc/src/sgml/Makefile b/doc/src/sgml/Makefile
index 9c9bbfe375d8412cb6ad21d99a561ee027baa39a..65ed32cd0aba7cd7ee563c23953a1f2201db2ade 100644 (file)
--- a/doc/src/sgml/Makefile
+++ b/doc/src/sgml/Makefile
@@ -194,7 +194,7 @@ MAKEINFO = makeinfo
 ##
 
 # Quick syntax check without style processing
-check: postgres.sgml $(ALLSGML) check-tabs
+check: postgres.sgml $(ALLSGML) check-tabs check-nbsp
        $(XMLLINT) $(XMLINCLUDE) --noout --valid $<
 
 
@@ -257,7 +257,15 @@ endif # sqlmansectnum != 7
 
 # tabs are harmless, but it is best to avoid them in SGML files
 check-tabs:
-       @( ! grep '     ' $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml $(srcdir)/*.xsl) ) || (echo "Tabs appear in SGML/XML files" 1>&2;  exit 1)
+       @( ! grep '     ' $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml $(srcdir)/*.xsl) ) || \
+       (echo "Tabs appear in SGML/XML files" 1>&2;  exit 1)
+
+# Non-breaking spaces are harmless, but it is best to avoid them in SGML files.
+# Use perl command because non-GNU grep or sed could not have hex escape sequence.
+check-nbsp:
+       @ ( $(PERL) -ne '/\xC2\xA0/ and print("$$ARGV:$$_"),$$n++; END {exit($$n>0)}' \
+         $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml $(srcdir)/*.xsl) ) || \
+       (echo "Non-breaking spaces appear in SGML/XML files" 1>&2;  exit 1)
 
 ##
 ## Clean