From: Max Gautier <mg@max.gautier.name>
To: libc-alpha@sourceware.org
Cc: mg@max.gautier.name
Subject: [PATCH v5 2/4] iconv: Better mapping to RFC for UTF-7
Date: Sun, 20 Mar 2022 17:41:05 +0100 [thread overview]
Message-ID: <YjdZIdeskC6Ncq0F@ol-mgautier> (raw)
In-Reply-To: <20211209093152.313872-3-mg@max.gautier.name>
- 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>
---
iconvdata/utf-7.c | 64 ++++++++++++++++++++++++-----------------------
1 file changed, 33 insertions(+), 31 deletions(-)
diff --git a/iconvdata/utf-7.c b/iconvdata/utf-7.c
index 9ba0974959..15f3669ac8 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
-isdirect (uint32_t ch)
+static bool
+isdirect (uint32_t ch, enum variant var)
{
- 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
-isxdirect (uint32_t ch)
+static bool
+isxdirect (uint32_t ch, enum variant var)
{
- 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; \
--
2.35.1
next prev parent reply other threads:[~2022-03-20 16:41 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-19 23:06 [PATCH 0/5] iconv: module for MODIFIED-UTF-7 Max Gautier
2020-08-19 23:06 ` [PATCH 1/5] Copy utf-7 module to modified-utf-7 Max Gautier
2020-08-19 23:06 ` [PATCH 2/5] Update gconv-modules file Max Gautier
2020-08-19 23:07 ` [PATCH 3/5] Transform UTF-7 to MODIFIED-UTF-7 Max Gautier
2020-08-19 23:07 ` [PATCH 4/5] Make terminating base64 sequences mandatory Max Gautier
2020-08-19 23:07 ` [PATCH 5/5] Add test case for MODIFIED-UTF-7 Max Gautier
2020-08-20 7:18 ` Andreas Schwab
2020-08-20 15:40 ` [PATCH v2 " Max Gautier
2020-08-20 8:03 ` [PATCH 0/5] iconv: module " Florian Weimer
2020-08-20 15:19 ` Max Gautier
2020-08-20 15:58 ` Florian Weimer
2020-09-02 15:24 ` Max Gautier
2020-09-02 20:01 ` Adhemerval Zanella
2020-09-03 9:47 ` Max Gautier
2020-09-03 10:56 ` Andreas Schwab
2021-01-25 9:02 ` [PATCH v3 0/5] iconv: module for IMAP-UTF-7 Max Gautier
2021-01-25 9:02 ` [PATCH v3 1/5] Copy utf-7 module to modified-utf-7 Max Gautier
2021-01-25 9:31 ` Andreas Schwab
2021-01-25 13:51 ` Max Gautier
2021-02-07 9:42 ` Florian Weimer
2021-02-07 12:29 ` Max Gautier
2021-02-07 12:34 ` Florian Weimer
2021-12-09 9:31 ` [PATCH v4 0/4] iconv: Add support for UTF-7-IMAP Max Gautier
2021-12-09 9:31 ` [PATCH v4 1/4] iconv: Always encode "optional direct" UTF-7 characters Max Gautier
2022-03-07 12:10 ` Adhemerval Zanella
2021-12-09 9:31 ` [PATCH v4 2/4] iconv: Better mapping to RFC for UTF-7 Max Gautier
2022-03-07 12:14 ` Adhemerval Zanella
2022-03-20 16:41 ` Max Gautier [this message]
2022-03-21 11:53 ` [PATCH v5 " Adhemerval Zanella
2022-03-21 11:59 ` Adhemerval Zanella
2022-03-21 12:06 ` Adhemerval Zanella
2022-03-21 14:07 ` Max Gautier
2021-12-09 9:31 ` [PATCH v4 3/4] iconv: make utf-7.c able to use variants Max Gautier
2022-03-07 12:34 ` Adhemerval Zanella
2022-03-12 11:07 ` Max Gautier
2022-03-14 12:17 ` Adhemerval Zanella
2022-03-20 16:42 ` [PATCH v5 " Max Gautier
2022-03-21 12:24 ` Adhemerval Zanella
2021-12-09 9:31 ` [PATCH v4 4/4] iconv: Add UTF-7-IMAP variant in utf-7.c Max Gautier
2022-03-07 12:46 ` Adhemerval Zanella
2022-03-20 16:43 ` [PATCH v5 " Max Gautier
2022-03-21 12:24 ` Adhemerval Zanella
2021-12-17 13:15 ` [PATCH v4 0/4] iconv: Add support for UTF-7-IMAP Max Gautier
2022-01-24 14:19 ` Adhemerval Zanella
2022-02-10 13:16 ` Max Gautier
2022-02-10 13:17 ` Adhemerval Zanella
2022-03-04 8:53 ` Max Gautier
2022-01-17 14:07 ` Max Gautier
2022-01-24 9:17 ` Max Gautier
2021-01-25 9:02 ` [PATCH v3 2/5] Update gconv-modules file Max Gautier
2021-02-07 9:49 ` Florian Weimer
2021-01-25 9:02 ` [PATCH v3 3/5] Transform UTF-7 to IMAP-UTF-7 Max Gautier
2021-01-25 9:02 ` [PATCH v3 4/5] Make terminating base64 sequences mandatory Max Gautier
2021-02-07 9:45 ` Florian Weimer
2021-01-25 9:02 ` [PATCH v3 5/5] Add test case for IMAP-UTF-7 Max Gautier
2021-02-07 9:49 ` Florian Weimer
2021-03-16 14:39 ` [PATCH v3 5/5][pw utf test] " Siddhesh Poyarekar
2022-03-21 12:28 ` [PATCH v3 0/5] iconv: module " Adhemerval Zanella
2022-03-21 14:09 ` Max Gautier
2021-01-12 9:12 ` [PATCH 0/5] iconv: module for MODIFIED-UTF-7 Florian Weimer
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=YjdZIdeskC6Ncq0F@ol-mgautier \
--to=mg@max.gautier.name \
--cc=libc-alpha@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: link
Be 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).