public inbox for glibc-cvs@sourceware.org help / color / mirror / Atom feed
From: Adhemerval Zanella <azanella@sourceware.org> To: glibc-cvs@sourceware.org Subject: [glibc/azanella/imap-utf7] iconv: Better mapping to RFC for UTF-7 Date: Mon, 21 Mar 2022 12:26:56 +0000 (GMT) [thread overview] Message-ID: <20220321122656.CE8A33858403@sourceware.org> (raw) https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=09abb567a94e4e33504bb863f9d36f253287d333 commit 09abb567a94e4e33504bb863f9d36f253287d333 Author: Max Gautier <mg@max.gautier.name> Date: Sun Mar 20 17:41:05 2022 +0100 iconv: Better mapping to RFC for UTF-7 - Direct use of characters instead of arcane arrays - isxbase64 is not the Modified BASE64 alphabet, but the characters who needs to trigger an explicit shift back to US-ASCII. Make that clearer Signed-off-by: Max Gautier <mg@max.gautier.name> Reviewed-by: Adhemerval Zanellla <adhemerval.zanella@linaro.org> Diff: --- iconvdata/utf-7.c | 60 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 31 insertions(+), 29 deletions(-) diff --git a/iconvdata/utf-7.c b/iconvdata/utf-7.c index b5af9b217c..815b1891c7 100644 --- a/iconvdata/utf-7.c +++ b/iconvdata/utf-7.c @@ -30,20 +30,27 @@ +static bool +between (uint32_t const ch, + uint32_t const lower_bound, uint32_t const upper_bound) +{ + return (ch >= lower_bound && ch <= upper_bound); +} + /* The set of "direct characters": A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr */ -static const unsigned char direct_tab[128 / 8] = - { - 0x00, 0x26, 0x00, 0x00, 0x81, 0xf3, 0xff, 0x87, - 0xfe, 0xff, 0xff, 0x07, 0xfe, 0xff, 0xff, 0x07 - }; - -static int +static bool isdirect (uint32_t ch) { - return (ch < 128 && ((direct_tab[ch >> 3] >> (ch & 7)) & 1)); + return (between (ch, 'A', 'Z') + || between (ch, 'a', 'z') + || between (ch, '0', '9') + || ch == '\'' || ch == '(' || ch == ')' + || between (ch, ',', '/') + || ch == ':' || ch == '?' + || ch == ' ' || ch == '\t' || ch == '\n' || ch == '\r'); } @@ -52,33 +59,27 @@ isdirect (uint32_t ch) ! " # $ % & * ; < = > @ [ ] ^ _ ` { | } */ -static const unsigned char xdirect_tab[128 / 8] = - { - 0x00, 0x26, 0x00, 0x00, 0xff, 0xf7, 0xff, 0xff, - 0xff, 0xff, 0xff, 0xef, 0xff, 0xff, 0xff, 0x3f - }; - -static int +static bool isxdirect (uint32_t ch) { - return (ch < 128 && ((xdirect_tab[ch >> 3] >> (ch & 7)) & 1)); + return (ch == '\t' + || ch == '\n' + || ch == '\r' + || (between (ch, ' ', '}') && ch != '+' && ch != '\\')); } -/* The set of "extended base64 characters": +/* Characters which needs to trigger an explicit shift back to US-ASCII (UTF-7 + only): Modified base64 + '-' (shift back character) A-Z a-z 0-9 + / - */ -static const unsigned char xbase64_tab[128 / 8] = - { - 0x00, 0x00, 0x00, 0x00, 0x00, 0xa8, 0xff, 0x03, - 0xfe, 0xff, 0xff, 0x07, 0xfe, 0xff, 0xff, 0x07 - }; - -static int -isxbase64 (uint32_t ch) +static bool +needs_explicit_shift (uint32_t ch) { - return (ch < 128 && ((xbase64_tab[ch >> 3] >> (ch & 7)) & 1)); + return (between (ch, 'A', 'Z') + || between (ch, 'a', 'z') + || between (ch, '/', '9') || ch == '+' || ch == '-'); } @@ -252,7 +253,7 @@ base64 (unsigned int i) indeed form a Low Surrogate. */ \ uint32_t wc2 = wch & 0xffff; \ \ - if (! __builtin_expect (wc2 >= 0xdc00 && wc2 < 0xe000, 1)) \ + if (! __glibc_likely (wc2 >= 0xdc00 && wc2 < 0xe000)) \ { \ STANDARD_FROM_LOOP_ERR_HANDLER ((statep->__count = 0, 1));\ } \ @@ -372,7 +373,8 @@ base64 (unsigned int i) /* deactivate base64 encoding */ \ size_t count; \ \ - count = ((statep->__count & 0x18) >= 0x10) + isxbase64 (ch) + 1; \ + count = ((statep->__count & 0x18) >= 0x10) \ + + needs_explicit_shift (ch) + 1; \ if (__glibc_unlikely (outptr + count > outend)) \ { \ result = __GCONV_FULL_OUTPUT; \ @@ -381,7 +383,7 @@ base64 (unsigned int i) \ if ((statep->__count & 0x18) >= 0x10) \ *outptr++ = base64 ((statep->__count >> 3) & ~3); \ - if (isxbase64 (ch)) \ + if (needs_explicit_shift (ch)) \ *outptr++ = '-'; \ *outptr++ = (unsigned char) ch; \ statep->__count = 0; \
reply other threads:[~2022-03-21 12:26 UTC|newest] Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20220321122656.CE8A33858403@sourceware.org \ --to=azanella@sourceware.org \ --cc=glibc-cvs@sourceware.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).