42790: make [[:blank:]] match non-ASCII blanks

5 files changed, 36 insertions, 4 deletions

diff --git a/ChangeLog b/ChangeLog
index 0d5a95d86..ac2acf349 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,8 @@
 2018-05-17  Oliver Kiddle  <okiddle@yahoo.co.uk>
 
+	* Stephane: 42790: Doc/Zsh/expn.yo, NEWS, Src/pattern.c,
+	configure.ac: make [[:blank:]] match non-ASCII blanks
+
 	* 42784: Completion/Zsh/Command/_typeset: complete -s and -x
 	options to the functions builtin
 
diff --git a/Doc/Zsh/expn.yo b/Doc/Zsh/expn.yo
index 8b447e2c7..c79109700 100644
--- a/Doc/Zsh/expn.yo
+++ b/Doc/Zsh/expn.yo
@@ -2004,7 +2004,7 @@ The character is 7-bit, i.e. is a single-byte character without
 the top bit set.
 )
 item(tt([:blank:]))(
-The character is either space or tab
+The character is a blank character
 )
 item(tt([:cntrl:]))(
 The character is a control character
diff --git a/NEWS b/NEWS
index 1db9da6f3..17868979b 100644
--- a/NEWS
+++ b/NEWS
@@ -4,7 +4,14 @@ CHANGES FROM PREVIOUS VERSIONS OF ZSH
 
 Note also the list of incompatibilities in the README file.
 
-Changes from %.5 to 5.5.1
+Changes from 5.5.1 to FIXME
+---------------------------
+
+In shell patterns, [[:blank:]] now honours the locale instead of
+matching exclusively on space and tab, like for the other POSIX
+character classes or for extended regular expressions.
+
+Changes from 5.5 to 5.5.1
 -------------------------
 
 Apart from a fix for a configuration problem finding singal names from
diff --git a/Src/pattern.c b/Src/pattern.c
index fc7c73739..737f5cdcb 100644
--- a/Src/pattern.c
+++ b/Src/pattern.c
@@ -3605,7 +3605,15 @@ mb_patmatchrange(char *range, wchar_t ch, int zmb_ind, wint_t *indptr, int *mtp)
 		    return 1;
 		break;
 	    case PP_BLANK:
-		if (ch == L' ' || ch == L'\t')
+#if !defined(HAVE_ISWBLANK) && !defined(iswblank)
+/*
+ * iswblank() is GNU and C99. There's a remote chance that some
+ * systems still don't support it (but would support the other ones
+ * if MULTIBYTE_SUPPORT is enabled).
+ */
+#define iswblank(c) (c == L' ' || c == L'\t')
+#endif
+		if (iswblank(ch))
 		    return 1;
 		break;
 	    case PP_CNTRL:
@@ -3840,7 +3848,14 @@ patmatchrange(char *range, int ch, int *indptr, int *mtp)
 		    return 1;
 		break;
 	    case PP_BLANK:
-		if (ch == ' ' || ch == '\t')
+#if !defined(HAVE_ISBLANK) && !defined(isblank)
+/*
+ * isblank() is GNU and C99. There's a remote chance that some
+ * systems still don't support it.
+ */
+#define isblank(c) (c == ' ' || c == '\t')
+#endif
+		if (isblank(ch))
 		    return 1;
 		break;
 	    case PP_CNTRL:
diff --git a/configure.ac b/configure.ac
index 4329afb9e..00c731864 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1304,6 +1304,7 @@ AC_CHECK_FUNCS(strftime strptime mktime timelocal \
 	       memcpy memmove strstr strerror strtoul \
 	       getrlimit getrusage \
 	       setlocale \
+	       isblank iswblank \
 	       uname \
 	       signgam tgamma \
 	       scalbn \
@@ -2564,6 +2565,12 @@ AC_HELP_STRING([--enable-multibyte], [support multibyte characters]),
 [AC_CACHE_VAL(zsh_cv_c_unicode_support,
   AC_MSG_NOTICE([checking for functions supporting multibyte characters])
   [zfuncs_absent=
+dnl
+dnl Note that iswblank is not included and checked separately.
+dnl As iswblank() was added to C long after the others, we still
+dnl want to enabled unicode support even if iswblank is not available
+dnl (we then just do the SPC+TAB approximation)
+dnl
    for zfunc in iswalnum iswcntrl iswdigit iswgraph iswlower iswprint \
 iswpunct iswspace iswupper iswxdigit mbrlen mbrtowc towupper towlower \
 wcschr wcscpy wcslen wcsncmp wcsncpy wcrtomb wcwidth wmemchr wmemcmp \