From patchwork Sun Mar 20 16:42:08 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Max Gautier X-Patchwork-Id: 52152 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 028F53857811 for ; Sun, 20 Mar 2022 16:42:36 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 028F53857811 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1647794556; bh=2fMn1hbWfAoXP9BdTo8xmNJNvx7GK0LeyH+8ZM+Y0Fc=; h=Date:To:Subject:References:In-Reply-To:List-Id:List-Unsubscribe: List-Archive:List-Post:List-Help:List-Subscribe:From:Reply-To:Cc: From; b=BEpvLVMKIaV7UVOf7AXXbtJmM1IXEyy989w7U2R78RNgq3UTOstndr+qKIwVedyHH Kv+EDSmj4miR3usHKBcGv63fjxhSi/qON/NLi0s1oIBUdQcI1gweO8mdRWeOiINMCf C0AMGhUPYNzbsjt/EZefI6tiLqF//ed9q1Sow6uE= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from mout-p-201.mailbox.org (mout-p-201.mailbox.org [80.241.56.171]) by sourceware.org (Postfix) with ESMTPS id D83C33858C74 for ; Sun, 20 Mar 2022 16:42:13 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org D83C33858C74 Received: from smtp1.mailbox.org (smtp1.mailbox.org [IPv6:2001:67c:2050:105:465:1:1:0]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange ECDHE (P-384) server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mout-p-201.mailbox.org (Postfix) with ESMTPS id 4KM3SN6HyTz9sT4; Sun, 20 Mar 2022 17:42:12 +0100 (CET) Date: Sun, 20 Mar 2022 17:42:08 +0100 To: libc-alpha@sourceware.org Subject: [PATCH v5 3/4] iconv: make utf-7.c able to use variants Message-ID: Mail-Followup-To: Max Gautier , libc-alpha@sourceware.org References: <87blcw9ptq.fsf@oldenburg.str.redhat.com> <20211209093152.313872-1-mg@max.gautier.name> <20211209093152.313872-4-mg@max.gautier.name> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <20211209093152.313872-4-mg@max.gautier.name> X-Spam-Status: No, score=-11.9 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, GIT_PATCH_0, RCVD_IN_DNSWL_LOW, SPF_HELO_NONE, SPF_PASS, TXREP, T_FILL_THIS_FORM_SHORT, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Max Gautier via Libc-alpha From: Max Gautier Reply-To: Max Gautier Cc: Max Gautier Errors-To: libc-alpha-bounces+patchwork=sourceware.org@sourceware.org Sender: "Libc-alpha" Add infrastructure in utf-7.c to handle variants. The approach comes from iso646.c The variant is defined at gconv_init time and is passed as a supplementary variable. Signed-off-by: Max Gautier --- iconvdata/utf-7.c | 230 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 170 insertions(+), 60 deletions(-) diff --git a/iconvdata/utf-7.c b/iconvdata/utf-7.c index 15f3669ac8..b639d8ff3e 100644 --- a/iconvdata/utf-7.c +++ b/iconvdata/utf-7.c @@ -29,6 +29,24 @@ #include +enum variant +{ + UTF7, +}; + +/* Must be in the same order as enum variant above. */ +static const char names[] = + "UTF-7//\0" + "\0"; + +static uint32_t +shift_character (enum variant const var) +{ + if (var == UTF7) + return '+'; + else + abort (); +} static bool between (uint32_t const ch, @@ -38,23 +56,27 @@ between (uint32_t const ch, } /* The set of "direct characters": + FOR UTF-7 A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr */ static bool isdirect (uint32_t ch, enum variant var) { - 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'); + if (var == UTF7) + 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'); + abort (); } /* The set of "direct and optional direct characters": + (UTF-7 only) A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr ! " # $ % & * ; < = > @ [ ] ^ _ ` { | } */ @@ -62,10 +84,15 @@ isdirect (uint32_t ch, enum variant var) static bool isxdirect (uint32_t ch, enum variant var) { - return (ch == '\t' - || ch == '\n' - || ch == '\r' - || (between (ch, ' ', '}') && ch != '+' && ch != '\\')); + if (isdirect (ch, var)) + return true; + if (var != UTF7) + return false; + return between (ch, '!', '&') + || ch == '*' + || between (ch, ';', '@') + || (between (ch, '[', '`') && ch != '\\') + || between (ch, '{', '}'); } @@ -85,7 +112,7 @@ needs_explicit_shift (uint32_t ch) /* Converts a value in the range 0..63 to a base64 encoded char. */ static unsigned char -base64 (unsigned int i) +base64 (unsigned int i, enum variant var) { if (i < 26) return i + 'A'; @@ -95,7 +122,7 @@ base64 (unsigned int i) return i - 52 + '0'; else if (i == 62) return '+'; - else if (i == 63) + else if (i == 63 && var == UTF7) return '/'; else abort (); @@ -103,9 +130,8 @@ base64 (unsigned int i) /* Definitions used in the body of the `gconv' function. */ -#define CHARSET_NAME "UTF-7//" -#define DEFINE_INIT 1 -#define DEFINE_FINI 1 +#define DEFINE_INIT 0 +#define DEFINE_FINI 0 #define FROM_LOOP from_utf7_loop #define TO_LOOP to_utf7_loop #define MIN_NEEDED_FROM 1 @@ -113,11 +139,27 @@ base64 (unsigned int i) #define MIN_NEEDED_TO 4 #define MAX_NEEDED_TO 4 #define ONE_DIRECTION 0 +#define FROM_DIRECTION (dir == from_utf7) #define PREPARE_LOOP \ mbstate_t saved_state; \ - mbstate_t *statep = data->__statep; -#define EXTRA_LOOP_ARGS , statep + mbstate_t *statep = data->__statep; \ + enum direction dir = ((struct utf7_data *) step->__data)->dir; \ + enum direction var = ((struct utf7_data *) step->__data)->var; +#define EXTRA_LOOP_ARGS , statep, var + +enum direction +{ + illegal_dir, + from_utf7, + to_utf7 +}; + +struct utf7_data +{ + enum direction dir; + enum variant var; +}; /* Since we might have to reset input pointer we must be able to save and restore the state. */ @@ -127,6 +169,70 @@ base64 (unsigned int i) else \ *statep = saved_state +int +gconv_init (struct __gconv_step *step) +{ + /* Determine which direction. */ + struct utf7_data *new_data; + enum direction dir = illegal_dir; + + enum variant var = 0; + for (const char *name = names; *name != '\0'; + name = __rawmemchr (name, '\0') + 1) + { + if (__strcasecmp (step->__from_name, name) == 0) + { + dir = from_utf7; + break; + } + else if (__strcasecmp (step->__to_name, name) == 0) + { + dir = to_utf7; + break; + } + ++var; + } + + if (__glibc_likely (dir != illegal_dir)) + { + new_data = malloc (sizeof (*new_data)); + if (new_data == NULL) + return __GCONV_NOMEM; + + new_data->dir = dir; + new_data->var = var; + step->__data = new_data; + + if (dir == from_utf7) + { + step->__min_needed_from = MIN_NEEDED_FROM; + step->__max_needed_from = MAX_NEEDED_FROM; + step->__min_needed_to = MIN_NEEDED_TO; + step->__max_needed_to = MAX_NEEDED_TO; + } + else + { + step->__min_needed_from = MIN_NEEDED_TO; + step->__max_needed_from = MAX_NEEDED_TO; + step->__min_needed_to = MIN_NEEDED_FROM; + step->__max_needed_to = MAX_NEEDED_FROM; + } + } + else + return __GCONV_NOCONV; + + step->__stateful = 1; + + return __GCONV_OK; +} + +void +gconv_end (struct __gconv_step *data) +{ + free (data->__data); +} + + /* First define the conversion function from UTF-7 to UCS4. The state is structured as follows: @@ -154,13 +260,13 @@ base64 (unsigned int i) if ((statep->__count >> 3) == 0) \ { \ /* base64 encoding inactive. */ \ - if (isxdirect (ch)) \ + if (isxdirect (ch, var)) \ { \ inptr++; \ put32 (outptr, ch); \ outptr += 4; \ } \ - else if (__glibc_likely (ch == '+')) \ + else if (__glibc_likely (ch == shift_character (var))) \ { \ if (__glibc_unlikely (inptr + 2 > inend)) \ { \ @@ -285,7 +391,7 @@ base64 (unsigned int i) } \ } #define LOOP_NEED_FLAGS -#define EXTRA_LOOP_DECLS , mbstate_t *statep +#define EXTRA_LOOP_DECLS , mbstate_t *statep, enum variant var #include @@ -316,7 +422,7 @@ base64 (unsigned int i) if ((statep->__count & 0x18) == 0) \ { \ /* base64 encoding inactive */ \ - if (isdirect (ch)) \ + if (isdirect (ch, var)) \ { \ *outptr++ = (unsigned char) ch; \ } \ @@ -324,7 +430,7 @@ base64 (unsigned int i) { \ size_t count; \ \ - if (ch == '+') \ + if (ch == shift_character (var)) \ count = 2; \ else if (ch < 0x10000) \ count = 3; \ @@ -339,13 +445,13 @@ base64 (unsigned int i) break; \ } \ \ - *outptr++ = '+'; \ - if (ch == '+') \ + *outptr++ = shift_character (var); \ + if (ch == shift_character (var)) \ *outptr++ = '-'; \ else if (ch < 0x10000) \ { \ - *outptr++ = base64 (ch >> 10); \ - *outptr++ = base64 ((ch >> 4) & 0x3f); \ + *outptr++ = base64 (ch >> 10, var); \ + *outptr++ = base64 ((ch >> 4) & 0x3f, var); \ statep->__count = ((ch & 15) << 5) | (3 << 3); \ } \ else if (ch < 0x110000) \ @@ -354,11 +460,11 @@ base64 (unsigned int i) uint32_t ch2 = 0xdc00 + ((ch - 0x10000) & 0x3ff); \ \ ch = (ch1 << 16) | ch2; \ - *outptr++ = base64 (ch >> 26); \ - *outptr++ = base64 ((ch >> 20) & 0x3f); \ - *outptr++ = base64 ((ch >> 14) & 0x3f); \ - *outptr++ = base64 ((ch >> 8) & 0x3f); \ - *outptr++ = base64 ((ch >> 2) & 0x3f); \ + *outptr++ = base64 (ch >> 26, var); \ + *outptr++ = base64 ((ch >> 20) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 14) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 8) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 2) & 0x3f, var); \ statep->__count = ((ch & 3) << 7) | (2 << 3); \ } \ else \ @@ -368,7 +474,7 @@ base64 (unsigned int i) else \ { \ /* base64 encoding active */ \ - if (isdirect (ch)) \ + if (isdirect (ch, var)) \ { \ /* deactivate base64 encoding */ \ size_t count; \ @@ -382,7 +488,7 @@ base64 (unsigned int i) } \ \ if ((statep->__count & 0x18) >= 0x10) \ - *outptr++ = base64 ((statep->__count >> 3) & ~3); \ + *outptr++ = base64 ((statep->__count >> 3) & ~3, var); \ if (needs_explicit_shift (ch)) \ *outptr++ = '-'; \ *outptr++ = (unsigned char) ch; \ @@ -410,22 +516,24 @@ base64 (unsigned int i) switch ((statep->__count >> 3) & 3) \ { \ case 1: \ - *outptr++ = base64 (ch >> 10); \ - *outptr++ = base64 ((ch >> 4) & 0x3f); \ + *outptr++ = base64 (ch >> 10, var); \ + *outptr++ = base64 ((ch >> 4) & 0x3f, var); \ statep->__count = ((ch & 15) << 5) | (3 << 3); \ break; \ case 2: \ *outptr++ = \ - base64 (((statep->__count >> 3) & ~3) | (ch >> 12)); \ - *outptr++ = base64 ((ch >> 6) & 0x3f); \ - *outptr++ = base64 (ch & 0x3f); \ + base64 (((statep->__count >> 3) & ~3) | (ch >> 12), \ + var); \ + *outptr++ = base64 ((ch >> 6) & 0x3f, var); \ + *outptr++ = base64 (ch & 0x3f, var); \ statep->__count = (1 << 3); \ break; \ case 3: \ *outptr++ = \ - base64 (((statep->__count >> 3) & ~3) | (ch >> 14)); \ - *outptr++ = base64 ((ch >> 8) & 0x3f); \ - *outptr++ = base64 ((ch >> 2) & 0x3f); \ + base64 (((statep->__count >> 3) & ~3) | (ch >> 14), \ + var); \ + *outptr++ = base64 ((ch >> 8) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 2) & 0x3f, var); \ statep->__count = ((ch & 3) << 7) | (2 << 3); \ break; \ default: \ @@ -441,30 +549,32 @@ base64 (unsigned int i) switch ((statep->__count >> 3) & 3) \ { \ case 1: \ - *outptr++ = base64 (ch >> 26); \ - *outptr++ = base64 ((ch >> 20) & 0x3f); \ - *outptr++ = base64 ((ch >> 14) & 0x3f); \ - *outptr++ = base64 ((ch >> 8) & 0x3f); \ - *outptr++ = base64 ((ch >> 2) & 0x3f); \ + *outptr++ = base64 (ch >> 26, var); \ + *outptr++ = base64 ((ch >> 20) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 14) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 8) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 2) & 0x3f, var); \ statep->__count = ((ch & 3) << 7) | (2 << 3); \ break; \ case 2: \ *outptr++ = \ - base64 (((statep->__count >> 3) & ~3) | (ch >> 28)); \ - *outptr++ = base64 ((ch >> 22) & 0x3f); \ - *outptr++ = base64 ((ch >> 16) & 0x3f); \ - *outptr++ = base64 ((ch >> 10) & 0x3f); \ - *outptr++ = base64 ((ch >> 4) & 0x3f); \ + base64 (((statep->__count >> 3) & ~3) | (ch >> 28), \ + var); \ + *outptr++ = base64 ((ch >> 22) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 16) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 10) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 4) & 0x3f, var); \ statep->__count = ((ch & 15) << 5) | (3 << 3); \ break; \ case 3: \ *outptr++ = \ - base64 (((statep->__count >> 3) & ~3) | (ch >> 30)); \ - *outptr++ = base64 ((ch >> 24) & 0x3f); \ - *outptr++ = base64 ((ch >> 18) & 0x3f); \ - *outptr++ = base64 ((ch >> 12) & 0x3f); \ - *outptr++ = base64 ((ch >> 6) & 0x3f); \ - *outptr++ = base64 (ch & 0x3f); \ + base64 (((statep->__count >> 3) & ~3) | (ch >> 30), \ + var); \ + *outptr++ = base64 ((ch >> 24) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 18) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 12) & 0x3f, var); \ + *outptr++ = base64 ((ch >> 6) & 0x3f, var); \ + *outptr++ = base64 (ch & 0x3f, var); \ statep->__count = (1 << 3); \ break; \ default: \ @@ -480,7 +590,7 @@ base64 (unsigned int i) inptr += 4; \ } #define LOOP_NEED_FLAGS -#define EXTRA_LOOP_DECLS , mbstate_t *statep +#define EXTRA_LOOP_DECLS , mbstate_t *statep, enum variant var #include @@ -510,7 +620,7 @@ base64 (unsigned int i) { \ /* Write out the shift sequence. */ \ if ((state & 0x18) >= 0x10) \ - *outbuf++ = base64 ((state >> 3) & ~3); \ + *outbuf++ = base64 ((state >> 3) & ~3, var); \ *outbuf++ = '-'; \ \ data->__statep->__count = 0; \