From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 76152 invoked by alias); 18 Feb 2020 10:38:46 -0000 Mailing-List: contact newlib-cvs-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: newlib-cvs-owner@sourceware.org Received: (qmail 76104 invoked by uid 9078); 18 Feb 2020 10:38:46 -0000 Date: Tue, 18 Feb 2020 10:38:00 -0000 Message-ID: <20200218103846.76102.qmail@sourceware.org> Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Corinna Vinschen To: newlib-cvs@sourceware.org Subject: [newlib-cygwin] Locale modifier "@cjksingle" to enforce single-width CJK width. X-Act-Checkin: newlib-cygwin X-Git-Author: Thomas Wolff X-Git-Refname: refs/heads/master X-Git-Oldrev: 40245925ce9d6b9a9c4ed6140cea39d948d10898 X-Git-Newrev: c8204b106988fd089a6d568f540100a3b88b628c X-SW-Source: 2020-q1/txt/msg00020.txt https://sourceware.org/git/gitweb.cgi?p=newlib-cygwin.git;h=c8204b106988fd089a6d568f540100a3b88b628c commit c8204b106988fd089a6d568f540100a3b88b628c Author: Thomas Wolff Date: Mon Feb 17 00:00:00 2020 +0100 Locale modifier "@cjksingle" to enforce single-width CJK width. This option follows a proposal in the Terminals Working Group Specifications (https://gitlab.freedesktop.org/terminal-wg/specifications/issues/9#note_406682). It makes locale width consistent with the corresponding mintty feature. Diff: --- newlib/libc/locale/locale.c | 13 +++++++++++-- newlib/libc/string/wcwidth.c | 8 ++++++-- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/newlib/libc/locale/locale.c b/newlib/libc/locale/locale.c index 4c343e4..7b1b066 100644 --- a/newlib/libc/locale/locale.c +++ b/newlib/libc/locale/locale.c @@ -85,6 +85,9 @@ it is 2 for <<"zh">> (Chinese), <<"ja">> (Japanese), and <<"ko">> (Korean), and 1 for everything else. Specifying <<"cjknarrow">> or <<"cjkwide">> forces a width of 1 or 2, respectively, independent of charset and language. +This implementation also supports the modifier <<"cjksingle">> +to enforce single-width character properties. + If you use <> as the <[locale]> argument, <> returns a pointer to the string representing the current locale. The acceptable values for <[category]> are defined in `<>' as macros @@ -480,6 +483,7 @@ __loadlocale (struct __locale_t *loc, int category, char *new_locale) int mbc_max; wctomb_p l_wctomb; mbtowc_p l_mbtowc; + int cjksingle = 0; int cjknarrow = 0; int cjkwide = 0; @@ -594,11 +598,13 @@ restart: } if (c && c[0] == '@') { - /* Modifier */ + /* Modifier "cjksingle" is recognized to enforce single-width mode. */ /* Modifiers "cjknarrow" or "cjkwide" are recognized to modify the behaviour of wcwidth() and wcswidth() for East Asian languages. For details see the comment at the end of this function. */ - if (!strcmp (c + 1, "cjknarrow")) + if (!strcmp (c + 1, "cjksingle")) + cjksingle = 1; + else if (!strcmp (c + 1, "cjknarrow")) cjknarrow = 1; else if (!strcmp (c + 1, "cjkwide")) cjkwide = 1; @@ -893,6 +899,7 @@ restart: loc->wctomb = l_wctomb; loc->mbtowc = l_mbtowc; __set_ctype (loc, charset); + /* Set CJK width mode (1: ambiguous-wide, 0: normal, -1: disabled). */ /* Determine the width for the "CJK Ambiguous Width" category of characters. This is used in wcwidth(). Assume single width for single-byte charsets, and double width for multi-byte charsets @@ -907,6 +914,8 @@ restart: || strncmp (locale, "ja", 2) == 0 || strncmp (locale, "ko", 2) == 0 || strncmp (locale, "zh", 2) == 0)); + if (cjksingle) + loc->cjk_lang = -1; /* Disable CJK dual-width */ #ifdef __HAVE_LOCALE_INFO__ ret = __ctype_load_locale (loc, locale, (void *) l_wctomb, charset, mbc_max); diff --git a/newlib/libc/string/wcwidth.c b/newlib/libc/string/wcwidth.c index 62e76ed..8348eef 100644 --- a/newlib/libc/string/wcwidth.c +++ b/newlib/libc/string/wcwidth.c @@ -197,8 +197,11 @@ __wcwidth (const wint_t ucs) if (ucs >= 0xd800 && ucs <= 0xdfff) return -1; + /* check CJK width mode (1: ambiguous-wide, 0: normal, -1: disabled) */ + int cjk_lang = __locale_cjk_lang (); + /* binary search in table of ambiguous characters */ - if (__locale_cjk_lang () + if (cjk_lang > 0 && bisearch(ucs, ambiguous, sizeof(ambiguous) / sizeof(struct interval) - 1)) return 2; @@ -211,7 +214,8 @@ __wcwidth (const wint_t ucs) /* if we arrive here, ucs is not a combining or C0/C1 control character */ /* binary search in table of wide character codes */ - if (bisearch(ucs, wide, + if (cjk_lang >= 0 + && bisearch(ucs, wide, sizeof(wide) / sizeof(struct interval) - 1)) return 2; else