From: Michal Nazarewicz <mina86@mina86.com>
To: Eli Zaretskii <eliz@gnu.org>,
Andreas Schwab <schwab@linux-m68k.org>,
24603@debbugs.gnu.org
Subject: bug#24603: [PATCHv6 4/6] Split up casify_region function (bug#24603)
Date: Tue, 21 Mar 2017 02:27:07 +0100 [thread overview]
Message-ID: <20170321012709.19402-5-mina86@mina86.com> (raw)
In-Reply-To: <20170321012709.19402-1-mina86@mina86.com>
No functional changes at this time but splitting casify_region into
a function dealing with multibyte and another dealing with unibyte
buffers will make future code changes slightly easier.
* src/casefiddle.c (casify_region): Move most of the code into two
new functions:
(do_casify_multibyte_region, do_casify_unibyte_region): new functions.
---
src/casefiddle.c | 159 ++++++++++++++++++++++++++++++-------------------------
1 file changed, 86 insertions(+), 73 deletions(-)
diff --git a/src/casefiddle.c b/src/casefiddle.c
index a83469cbdc7..b1a5f8e236e 100644
--- a/src/casefiddle.c
+++ b/src/casefiddle.c
@@ -231,102 +231,115 @@ The argument object is not altered--the value is a copy. */)
return casify_object (CASE_CAPITALIZE_UP, obj);
}
\f
-/* flag is CASE_UP, CASE_DOWN or CASE_CAPITALIZE or CASE_CAPITALIZE_UP.
- b and e specify range of buffer to operate on. */
-
-static void
-casify_region (enum case_action flag, Lisp_Object b, Lisp_Object e)
+/* Based on CTX, case region in a unibyte buffer from POS to *ENDP. Return
+ first position that has changed and save last position in *ENDP. If no
+ characters were changed, return -1 and *ENDP is unspecified. */
+static ptrdiff_t
+do_casify_unibyte_region (struct casing_context *ctx,
+ ptrdiff_t pos, ptrdiff_t *endp)
{
- bool multibyte = !NILP (BVAR (current_buffer, enable_multibyte_characters));
- ptrdiff_t start, end;
- ptrdiff_t start_byte;
+ ptrdiff_t first = -1, last = -1; /* Position of first and last changes. */
+ ptrdiff_t end = *endp;
+ int ch, cased;
- /* Position of first and last changes. */
- ptrdiff_t first = -1, last;
+ for (; pos < end; ++pos)
+ {
+ ch = FETCH_BYTE (pos);
+ MAKE_CHAR_MULTIBYTE (ch);
- ptrdiff_t opoint = PT;
- ptrdiff_t opoint_byte = PT_BYTE;
+ cased = case_character (ctx, ch);
+ if (cased == ch)
+ continue;
- struct casing_context ctx;
+ last = pos;
+ if (first < 0)
+ first = pos;
- if (EQ (b, e))
- /* Not modifying because nothing marked */
- return;
+ MAKE_CHAR_UNIBYTE (cased);
+ FETCH_BYTE (pos) = cased;
+ }
- validate_region (&b, &e);
- start = XFASTINT (b);
- end = XFASTINT (e);
- modify_text (start, end);
- record_change (start, end - start);
- start_byte = CHAR_TO_BYTE (start);
+ *endp = last + 1;
+ return first;
+}
- prepare_casing_context (&ctx, flag, true);
+/* Based on CTX, case region in a multibyte buffer from POS to *ENDP. Return
+ first position that has changed and save last position in *ENDP. If no
+ characters were changed, return -1 and *ENDP is unspecified. */
+static ptrdiff_t
+do_casify_multibyte_region (struct casing_context *ctx,
+ ptrdiff_t pos, ptrdiff_t *endp)
+{
+ ptrdiff_t first = -1, last = -1; /* Position of first and last changes. */
+ ptrdiff_t pos_byte = CHAR_TO_BYTE (pos), end = *endp;
+ ptrdiff_t opoint = PT;
+ int ch, cased, len;
- while (start < end)
+ while (pos < end)
{
- int ch, cased, len;
-
- if (multibyte)
- {
- ch = FETCH_MULTIBYTE_CHAR (start_byte);
- len = CHAR_BYTES (ch);
- }
- else
- {
- ch = FETCH_BYTE (start_byte);
- MAKE_CHAR_MULTIBYTE (ch);
- len = 1;
- }
- cased = case_character (&ctx, ch);
- if (ch != cased)
+ ch = STRING_CHAR_AND_LENGTH (BYTE_POS_ADDR (pos_byte), len);
+ cased = case_character (ctx, ch);
+ if (cased != ch)
{
- last = start;
+ last = pos;
if (first < 0)
- first = start;
+ first = pos;
- if (! multibyte)
- {
- MAKE_CHAR_UNIBYTE (cased);
- FETCH_BYTE (start_byte) = cased;
- }
- else if (ASCII_CHAR_P (cased) && ASCII_CHAR_P (ch))
- FETCH_BYTE (start_byte) = cased;
+ if (ASCII_CHAR_P (cased) && ASCII_CHAR_P (ch))
+ FETCH_BYTE (pos_byte) = cased;
else
{
- int tolen = CHAR_BYTES (cased);
- int j;
unsigned char str[MAX_MULTIBYTE_LENGTH];
-
- CHAR_STRING (cased, str);
- if (len == tolen)
- {
- /* Length is unchanged. */
- for (j = 0; j < len; ++j)
- FETCH_BYTE (start_byte + j) = str[j];
- }
+ int totlen = CHAR_STRING (cased, str);
+ if (len == totlen)
+ memcpy (BYTE_POS_ADDR (pos_byte), str, len);
else
- {
- /* Replace one character with the other,
- keeping text properties the same. */
- replace_range_2 (start, start_byte,
- start + 1, start_byte + len,
- (char *) str, 1, tolen,
- 0);
- len = tolen;
- }
+ /* Replace one character with the other(s), keeping text
+ properties the same. */
+ replace_range_2 (pos, pos_byte, pos + 1, pos_byte + len,
+ (char *) str, 9, totlen, 0);
+ len = totlen;
}
}
- start++;
- start_byte += len;
+ pos++;
+ pos_byte += len;
}
if (PT != opoint)
- TEMP_SET_PT_BOTH (opoint, opoint_byte);
+ TEMP_SET_PT_BOTH (opoint, CHAR_TO_BYTE (opoint));
+
+ *endp = last;
+ return first;
+}
+
+/* flag is CASE_UP, CASE_DOWN or CASE_CAPITALIZE or CASE_CAPITALIZE_UP.
+ b and e specify range of buffer to operate on. */
+static void
+casify_region (enum case_action flag, Lisp_Object b, Lisp_Object e)
+{
+ struct casing_context ctx;
+ ptrdiff_t start, end;
+
+ if (EQ (b, e))
+ /* Not modifying because nothing marked */
+ return;
+
+ validate_region (&b, &e);
+ start = XFASTINT (b);
+ end = XFASTINT (e);
+ modify_text (start, end);
+ record_change (start, end - start);
+ prepare_casing_context (&ctx, flag, true);
+
+ if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
+ start = do_casify_unibyte_region (&ctx, start, &end);
+ else
+ start = do_casify_multibyte_region (&ctx, start, &end);
- if (first >= 0)
+ if (start >= 0)
{
- signal_after_change (first, last + 1 - first, last + 1 - first);
- update_compositions (first, last + 1, CHECK_ALL);
+ signal_after_change (start, end + 1 - start, end + 1 - start);
+ update_compositions (start, end + 1, CHECK_ALL);
}
}
--
2.12.0.367.g23dc2f6d3c-goog
next prev parent reply other threads:[~2017-03-21 1:27 UTC|newest]
Thread overview: 89+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-04 1:05 bug#24603: [RFC 00/18] Improvement to casing Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 01/18] Add tests for casefiddle.c Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 02/18] Generate upcase and downcase tables from Unicode data Michal Nazarewicz
2016-10-04 7:27 ` Eli Zaretskii
2016-10-04 14:54 ` Michal Nazarewicz
2016-10-04 15:06 ` Eli Zaretskii
2016-10-04 16:57 ` Michal Nazarewicz
2016-10-04 17:27 ` Eli Zaretskii
2016-10-04 17:44 ` Eli Zaretskii
2016-10-06 20:29 ` Michal Nazarewicz
2016-10-07 6:52 ` Eli Zaretskii
2016-10-04 1:10 ` bug#24603: [RFC 03/18] Don’t assume character can be either upper- or lower-case when casing Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 04/18] Split casify_object into multiple functions Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 05/18] Introduce case_character function Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 06/18] Add support for title-casing letters Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 07/18] Split up casify_region function Michal Nazarewicz
2016-10-04 7:17 ` Eli Zaretskii
2016-10-18 2:27 ` Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 08/18] Support casing characters which map into multiple code points Michal Nazarewicz
2016-10-04 7:38 ` Eli Zaretskii
2016-10-06 21:40 ` Michal Nazarewicz
2016-10-07 7:46 ` Eli Zaretskii
2017-01-28 23:48 ` Michal Nazarewicz
2017-02-10 9:12 ` Eli Zaretskii
2016-10-04 1:10 ` bug#24603: [RFC 09/18] Implement special sigma casing rule Michal Nazarewicz
2016-10-04 7:22 ` Eli Zaretskii
2016-10-04 1:10 ` bug#24603: [RFC 10/18] Implement Turkic dotless and dotted i handling when casing strings Michal Nazarewicz
2016-10-04 7:12 ` Eli Zaretskii
2016-10-04 1:10 ` bug#24603: [RFC 11/18] Implement casing rules for Lithuanian Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 12/18] Implement rules for title-casing Dutch ij ‘letter’ Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 13/18] Add some tricky Unicode characters to regex test Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 14/18] Factor out character category lookup to separate function Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 15/18] Base lower- and upper-case tests on Unicode properties Michal Nazarewicz
2016-10-04 6:54 ` Eli Zaretskii
2016-10-04 1:10 ` bug#24603: [RFC 16/18] Refactor character class checking; optimise ASCII case Michal Nazarewicz
2016-10-04 7:48 ` Eli Zaretskii
2016-10-17 13:22 ` Michal Nazarewicz
2016-11-06 19:26 ` Michal Nazarewicz
2016-11-06 19:44 ` Eli Zaretskii
2016-12-20 14:32 ` Michal Nazarewicz
2016-12-20 16:39 ` Eli Zaretskii
2016-12-22 14:02 ` Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 17/18] Optimise character class matching in regexes Michal Nazarewicz
2016-10-04 1:10 ` bug#24603: [RFC 18/18] Fix case-fold-search character class matching Michal Nazarewicz
2016-10-17 22:03 ` bug#24603: [PATCH 0/3] Case table updates Michal Nazarewicz
2016-10-17 22:03 ` bug#24603: [PATCH 1/3] Add tests for casefiddle.c Michal Nazarewicz
2016-10-17 22:03 ` bug#24603: [PATCH 2/3] Generate upcase and downcase tables from Unicode data Michal Nazarewicz
2016-10-17 22:03 ` bug#24603: [PATCH 3/3] Don’t generate ‘X maps to X’ entries in case tables Michal Nazarewicz
2016-10-18 6:36 ` bug#24603: [PATCH 0/3] Case table updates Eli Zaretskii
2016-10-24 15:11 ` Michal Nazarewicz
2016-10-24 15:33 ` Eli Zaretskii
2017-03-09 21:51 ` bug#24603: [PATCHv5 00/11] Casing improvements Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 01/11] Split casify_object into multiple functions Michal Nazarewicz
2017-03-10 9:00 ` Andreas Schwab
2017-03-09 21:51 ` bug#24603: [PATCHv5 02/11] Introduce case_character function Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 03/11] Add support for title-casing letters (bug#24603) Michal Nazarewicz
2017-03-11 9:03 ` Eli Zaretskii
2017-03-09 21:51 ` bug#24603: [PATCHv5 04/11] Split up casify_region function (bug#24603) Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 05/11] Support casing characters which map into multiple code points (bug#24603) Michal Nazarewicz
2017-03-11 9:14 ` Eli Zaretskii
2017-03-21 2:09 ` Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 06/11] Implement special sigma casing rule (bug#24603) Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 07/11] Introduce ‘buffer-language’ buffer-locar variable Michal Nazarewicz
2017-03-11 9:29 ` Eli Zaretskii
2017-03-09 21:51 ` bug#24603: [PATCHv5 08/11] Implement rules for title-casing Dutch ij ‘letter’ (bug#24603) Michal Nazarewicz
2017-03-11 9:40 ` Eli Zaretskii
2017-03-16 21:30 ` Michal Nazarewicz
2017-03-17 13:43 ` Eli Zaretskii
2017-03-09 21:51 ` bug#24603: [PATCHv5 09/11] Implement Turkic dotless and dotted i casing rules (bug#24603) Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 10/11] Implement casing rules for Lithuanian (bug#24603) Michal Nazarewicz
2017-03-09 21:51 ` bug#24603: [PATCHv5 11/11] Implement Irish casing rules (bug#24603) Michal Nazarewicz
2017-03-11 9:44 ` Eli Zaretskii
2017-03-16 22:16 ` Michal Nazarewicz
2017-03-17 8:20 ` Eli Zaretskii
2017-03-11 10:00 ` bug#24603: [PATCHv5 00/11] Casing improvements Eli Zaretskii
2017-03-21 1:27 ` bug#24603: [PATCHv6 0/6] Casing improvements, language-independent part Michal Nazarewicz
2017-03-21 1:27 ` bug#24603: [PATCHv6 1/6] Split casify_object into multiple functions Michal Nazarewicz
2017-03-21 1:27 ` bug#24603: [PATCHv6 2/6] Introduce case_character function Michal Nazarewicz
2017-03-21 1:27 ` bug#24603: [PATCHv6 3/6] Add support for title-casing letters (bug#24603) Michal Nazarewicz
2017-03-21 1:27 ` Michal Nazarewicz [this message]
2017-03-21 1:27 ` bug#24603: [PATCHv6 5/6] Support casing characters which map into multiple code points (bug#24603) Michal Nazarewicz
2017-03-22 16:06 ` Eli Zaretskii
2017-04-03 9:01 ` Michal Nazarewicz
2017-04-03 14:52 ` Eli Zaretskii
2019-06-25 0:09 ` Lars Ingebrigtsen
2019-06-25 0:29 ` Michał Nazarewicz
2020-08-11 13:46 ` Lars Ingebrigtsen
2021-05-10 11:51 ` bug#24603: [RFC 00/18] Improvement to casing Lars Ingebrigtsen
2017-03-21 1:27 ` bug#24603: [PATCHv6 6/6] Implement special sigma casing rule (bug#24603) Michal Nazarewicz
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
List information: https://www.gnu.org/software/emacs/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170321012709.19402-5-mina86@mina86.com \
--to=mina86@mina86.com \
--cc=24603@debbugs.gnu.org \
--cc=eliz@gnu.org \
--cc=schwab@linux-m68k.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.
Code repositories for project(s) associated with this public inbox
https://git.savannah.gnu.org/cgit/emacs.git
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).