maint.mk: prohibit doubled words

Detect them also when they're separated by a newline.
There are 3 ways to customize it:
  - disable the test on a per file basis, as usual with rules using
    $(VC_LIST_EXCEPT)
  - replace the default doubled-word-selecting regexp (affects all files)
  - ignore a particular file-vs-doubled-word match
I nearly used that last one to ignore the "is is" match in
coreutils' NEWS file, since the text was "ls -is is ..."
To do that, I would have added this line to cfg.mk:
  ignore_doubled_word_match_RE_ = ^NEWS:[0-9]+:is[ ]is$
but it would have ignored any "is is" match in NEWS.
Low probability, but still...
Instead, I changed the text, slightly:
  -  ls -is is now consistent with ls -lis in ignoring values returned
  +  "ls -is" is now consistent with ls -lis in ignoring values returned
* top/maint.mk (prohibit_double_word_RE_): Provide default.
(prohibit_doubled_word_): Define.
(sc_prohibit_doubled_word): New rule.
(sc_prohibit_the_the): Remove.  Subsumed by the above.

diff --git a/ChangeLog b/ChangeLog
index 110cee574d056cb11c0497cbb7e18363b38e40c9..365dd2f6584f6feb15144a66faacd81c867b430e 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,26 @@
+2011-04-10  Jim Meyering  <meyering@redhat.com>
+
+       maint.mk: prohibit doubled words
+       Detect them also when they're separated by a newline.
+       There are 3 ways to customize it:
+         - disable the test on a per file basis, as usual with rules using
+           $(VC_LIST_EXCEPT)
+         - replace the default doubled-word-selecting regexp (affects all files)
+         - ignore a particular file-vs-doubled-word match
+       I nearly used that last one to ignore the "is is" match in
+       coreutils' NEWS file, since the text was "ls -is is ..."
+       To do that, I would have added this line to cfg.mk:
+         ignore_doubled_word_match_RE_ = ^NEWS:[0-9]+:is[ ]is$
+       but it would have ignored any "is is" match in NEWS.
+       Low probability, but still...
+       Instead, I changed the text, slightly:
+         -  ls -is is now consistent with ls -lis in ignoring values returned
+         +  "ls -is" is now consistent with ls -lis in ignoring values returned
+       * top/maint.mk (prohibit_double_word_RE_): Provide default.
+       (prohibit_doubled_word_): Define.
+       (sc_prohibit_doubled_word): New rule.
+       (sc_prohibit_the_the): Remove.  Subsumed by the above.
+
 2011-04-10  Jim Meyering  <meyering@redhat.com>
 
        maint: fix doubled-word typo in comment

diff --git a/top/maint.mk b/top/maint.mk
index ada00be4dc1de86b404fe8aa63b3aef66f7b5bc4..07a7773b9fe7b73400bd724c1922f5aecd32e495 100644 (file)
--- a/top/maint.mk
+++ b/top/maint.mk
@@ -841,10 +841,25 @@ sc_prohibit_S_IS_definition:
        halt='do not define S_IS* macros; include <sys/stat.h>'         \
          $(_sc_search_regexp)
 
-sc_prohibit_the_the:
-       @prohibit='\<the[ ]the\>'                                       \
-       halt='avoid double "the"'                                       \
-         $(_sc_search_regexp)
+prohibit_doubled_word_RE_ ?= \
+  /\b(then?|[iao]n|i[fst]|but|f?or|at|and|[dt]o)\s+\1\b/gims
+prohibit_doubled_word_ =                                               \
+    -e 'while ($(prohibit_doubled_word_RE_))'                          \
+    -e '  {'                                                           \
+    -e '    $$n = ($$` =~ tr/\n/\n/ + 1);'                             \
+    -e '    ($$v = $$&) =~ s/\n/\\n/g;'                                        \
+    -e '    print "$$ARGV:$$n:$$v\n";'                                 \
+    -e '  }'
+
+# Define this to a regular expression that matches
+# any filename:dd:match lines you want to ignore.
+# The default is to ignore no matches.
+ignore_doubled_word_match_RE_ ?= ^$$
+
+sc_prohibit_doubled_word:
+       @perl -n -0777 $(prohibit_doubled_word_) $$($(VC_LIST_EXCEPT))  \
+         | grep -vE '$(ignore_doubled_word_match_RE_)'                 \
+         | grep . && { echo '$(ME): doubled words' 1>&2; exit 1; } || :
 
 sc_prohibit_can_not:
        @prohibit='\<can[ ]not\>'                                       \