From: Kenichi Handa <handa@m17n.org>
Cc: emacs-unicode@gnu.org, emacs-devel@gnu.org
Subject: Re: Error building emacs-unicode-2 from CVS
Date: Mon, 13 Sep 2004 08:14:47 +0900 (JST) [thread overview]
Message-ID: <200409122314.IAA09736@etlken.m17n.org> (raw)
In-Reply-To: <16703.18275.260109.175662@gargle.gargle.HOWL> (jemarch@gnu.org)
Sorry for the late response on this thread.
In article <16703.18275.260109.175662@gargle.gargle.HOWL>, "Jose E. Marchesi" <jemarch@gnu.org> writes:
> I get the following error on the `make bootstrap' while building the
> `emacs-unicode-2' branch from CVS:
> Wrote /home/jemarch/gnu/src/emacs/emacs-unicode-2/emacs/lisp/loaddefs.el
> Loading ange-ftp (source)...
> In toplevel form:
> eshell/em-term.el:46:1:Error: Symbol's value as variable is void: ...
The source of the bug is that utf-16 detector was too
greedy. I've just fixed it. The attached is the relevant
patch. I'll commit it as soon as cvs start to work.
---
Ken'ichi HANDA
handa@m17n.org
2004-09-13 Kenichi Handa <handa@m17n.org>
* coding.c (detect_coding_utf_16): Don't set detect_info->found if
BOM is not found.
(detect_coding): Optimization for ISO-2022 when no 8-bit data is
found.
(detect_coding_system): Likewise.
*** coding.c 28 Apr 2004 22:03:43 +0900 1.289.2.36
--- coding.c 12 Sep 2004 21:41:00 +0900
***************
*** 1418,1443 ****
}
else if (c1 >= 0 && c2 >= 0)
{
- unsigned char b1[256], b2[256];
- int b1_variants = 1, b2_variants = 1;
- int n;
-
- bzero (b1, 256), bzero (b2, 256);
- b1[c1]++, b2[c2]++;
- for (n = 0; n < 256 && src < src_end; n++)
- {
- src_base = src;
- ONE_MORE_BYTE (c1);
- ONE_MORE_BYTE (c2);
- if (c1 < 0 || c2 < 0)
- break;
- if (! b1[c1++]) b1_variants++;
- if (! b2[c2++]) b2_variants++;
- }
- if (b1_variants < b2_variants)
- detect_info->found |= CATEGORY_MASK_UTF_16_BE_NOSIG;
- else
- detect_info->found |= CATEGORY_MASK_UTF_16_LE_NOSIG;
detect_info->rejected
|= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE);
}
--- 1418,1423 ----
***************
*** 5421,5473 ****
if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided))
{
int c, i;
for (i = 0, src = coding->source; src < src_end; i++, src++)
{
c = *src;
! if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC
! || c == ISO_CODE_SI
! || c == ISO_CODE_SO)))
break;
}
coding->head_ascii = src - (coding->source + coding->consumed);
! if (coding->head_ascii < coding->src_bytes)
{
- struct coding_detection_info detect_info;
enum coding_category category;
struct coding_system *this;
! detect_info.checked = detect_info.found = detect_info.rejected = 0;
! for (i = 0; i < coding_category_raw_text; i++)
! {
! category = coding_priorities[i];
! this = coding_categories + category;
! if (this->id < 0)
! {
! /* No coding system of this category is defined. */
! detect_info.rejected |= (1 << category);
! }
! else if (category >= coding_category_raw_text)
! continue;
! else if (detect_info.checked & (1 << category))
! {
! if (detect_info.found & (1 << category))
! break;
! }
! else if ((*(this->detector)) (coding, &detect_info)
! && detect_info.found & (1 << category))
! {
! if (category == coding_category_utf_16_auto)
! {
! if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
! category = coding_category_utf_16_le;
! else
! category = coding_category_utf_16_be;
! }
break;
! }
! }
if (i < coding_category_raw_text)
setup_coding_system (CODING_ID_NAME (this->id), coding);
else if (detect_info.rejected == CATEGORY_MASK_ANY)
--- 5401,5478 ----
if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided))
{
int c, i;
+ struct coding_detection_info detect_info;
+ detect_info.checked = detect_info.found = detect_info.rejected = 0;
for (i = 0, src = coding->source; src < src_end; i++, src++)
{
c = *src;
! if (c & 0x80)
break;
+ if (c < 0x20
+ && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
+ && ! inhibit_iso_escape_detection
+ && ! detect_info.checked)
+ {
+ coding->head_ascii = src - (coding->source + coding->consumed);
+ if (detect_coding_iso_2022 (coding, &detect_info))
+ {
+ /* We have scanned the whole data. */
+ if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
+ /* We didn't find an 8-bit code. */
+ src = src_end;
+ break;
+ }
+ }
}
coding->head_ascii = src - (coding->source + coding->consumed);
! if (coding->head_ascii == coding->src_bytes
! || detect_info.found)
{
enum coding_category category;
struct coding_system *this;
! if (coding->head_ascii == coding->src_bytes)
! /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */
! for (i = 0; i < coding_category_raw_text; i++)
! {
! category = coding_priorities[i];
! this = coding_categories + category;
! if (detect_info.found & (1 << category))
break;
! }
! else
! for (i = 0; i < coding_category_raw_text; i++)
! {
! category = coding_priorities[i];
! this = coding_categories + category;
! if (this->id < 0)
! {
! /* No coding system of this category is defined. */
! detect_info.rejected |= (1 << category);
! }
! else if (category >= coding_category_raw_text)
! continue;
! else if (detect_info.checked & (1 << category))
! {
! if (detect_info.found & (1 << category))
! break;
! }
! else if ((*(this->detector)) (coding, &detect_info)
! && detect_info.found & (1 << category))
! {
! if (category == coding_category_utf_16_auto)
! {
! if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
! category = coding_category_utf_16_le;
! else
! category = coding_category_utf_16_be;
! }
! break;
! }
! }
!
if (i < coding_category_raw_text)
setup_coding_system (CODING_ID_NAME (this->id), coding);
else if (detect_info.rejected == CATEGORY_MASK_ANY)
***************
*** 7120,7168 ****
for (i = 0; src < src_end; i++, src++)
{
c = *src;
! if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC
! || c == ISO_CODE_SI
! || c == ISO_CODE_SO)))
break;
}
coding.head_ascii = src - coding.source;
! if (src < src_end)
! for (i = 0; i < coding_category_raw_text; i++)
! {
! category = coding_priorities[i];
! this = coding_categories + category;
!
! if (this->id < 0)
! {
! /* No coding system of this category is defined. */
! detect_info.rejected |= (1 << category);
! }
! else if (category >= coding_category_raw_text)
! continue;
! else if (detect_info.checked & (1 << category))
{
! if (highest
! && (detect_info.found & (1 << category)))
break;
}
! else
{
! if ((*(this->detector)) (&coding, &detect_info)
! && highest
! && (detect_info.found & (1 << category)))
{
! if (category == coding_category_utf_16_auto)
{
! if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
! category = coding_category_utf_16_le;
! else
! category = coding_category_utf_16_be;
}
- break;
}
}
! }
if (detect_info.rejected == CATEGORY_MASK_ANY)
{
--- 7125,7197 ----
for (i = 0; src < src_end; i++, src++)
{
c = *src;
! if (c & 0x80)
break;
+ if (c < 0x20
+ && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
+ && inhibit_iso_escape_detection)
+ {
+ coding.head_ascii = src - coding.source;
+ if (detect_coding_iso_2022 (&coding, &detect_info))
+ {
+ /* We have scanned the whole data. */
+ if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
+ /* We didn't find an 8-bit code. */
+ src = src_end;
+ break;
+ }
+ }
}
coding.head_ascii = src - coding.source;
! if (src < src_end
! || detect_info.found)
! {
! if (src == src_end)
! /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */
! for (i = 0; i < coding_category_raw_text; i++)
{
! category = coding_priorities[i];
! if (detect_info.found & (1 << category))
break;
}
! else
! for (i = 0; i < coding_category_raw_text; i++)
{
! category = coding_priorities[i];
! this = coding_categories + category;
!
! if (this->id < 0)
{
! /* No coding system of this category is defined. */
! detect_info.rejected |= (1 << category);
! }
! else if (category >= coding_category_raw_text)
! continue;
! else if (detect_info.checked & (1 << category))
! {
! if (highest
! && (detect_info.found & (1 << category)))
! break;
! }
! else
! {
! if ((*(this->detector)) (&coding, &detect_info)
! && highest
! && (detect_info.found & (1 << category)))
{
! if (category == coding_category_utf_16_auto)
! {
! if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
! category = coding_category_utf_16_le;
! else
! category = coding_category_utf_16_be;
! }
! break;
}
}
}
! }
if (detect_info.rejected == CATEGORY_MASK_ANY)
{
prev parent reply other threads:[~2004-09-12 23:14 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-08 17:54 Error building emacs-unicode-2 from CVS Jose E. Marchesi
2004-09-09 4:39 ` Janusz S. Bień
2004-09-09 8:25 ` Katsumi Yamaoka
2004-09-09 13:48 ` Jose E. Marchesi
2004-09-12 23:14 ` Kenichi Handa [this message]
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=200409122314.IAA09736@etlken.m17n.org \
--to=handa@m17n.org \
--cc=emacs-devel@gnu.org \
--cc=emacs-unicode@gnu.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 external index
https://git.savannah.gnu.org/cgit/emacs.git
https://git.savannah.gnu.org/cgit/emacs/org-mode.git
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.