X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/13818c30785d1253412c4e08c61417eb81a98c5b..9f2554de935574cb1168b8de6fb3b38079bc4b80:/src/coding.c
diff --git a/src/coding.c b/src/coding.c
index 8bac5c5ae8..e292f80859 100644
--- a/src/coding.c
+++ b/src/coding.c
@@ -11,10 +11,10 @@
This file is part of GNU Emacs.
-GNU Emacs is free software; you can redistribute it and/or modify
+GNU Emacs is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 3, or (at your option)
-any later version.
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
GNU Emacs is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -22,9 +22,7 @@ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
-along with GNU Emacs; see the file COPYING. If not, write to
-the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
-Boston, MA 02110-1301, USA. */
+along with GNU Emacs. If not, see . */
/*** TABLE OF CONTENTS ***
@@ -316,7 +314,7 @@ Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5;
Lisp_Object Qbig, Qlittle;
Lisp_Object Qcoding_system_history;
Lisp_Object Qvalid_codes;
-Lisp_Object QCcategory, QCmnemonic, QCdefalut_char;
+Lisp_Object QCcategory, QCmnemonic, QCdefault_char;
Lisp_Object QCdecode_translation_table, QCencode_translation_table;
Lisp_Object QCpost_read_conversion, QCpre_write_conversion;
Lisp_Object QCascii_compatible_p;
@@ -548,6 +546,9 @@ enum iso_code_class_type
character is prohibited by CODING_ISO_FLAG_SAFE. */
#define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?'
+/* UTF-8 section */
+#define CODING_UTF_8_BOM(coding) \
+ ((coding)->spec.utf_8_bom)
/* UTF-16 section */
#define CODING_UTF_16_BOM(coding) \
@@ -578,7 +579,9 @@ enum coding_category
coding_category_iso_8_2,
coding_category_iso_7_else,
coding_category_iso_8_else,
- coding_category_utf_8,
+ coding_category_utf_8_auto,
+ coding_category_utf_8_nosig,
+ coding_category_utf_8_sig,
coding_category_utf_16_auto,
coding_category_utf_16_be,
coding_category_utf_16_le,
@@ -602,7 +605,9 @@ enum coding_category
#define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2)
#define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else)
#define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else)
-#define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8)
+#define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto)
+#define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig)
+#define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig)
#define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto)
#define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be)
#define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le)
@@ -624,7 +629,10 @@ enum coding_category
| CATEGORY_MASK_ISO_8_2 \
| CATEGORY_MASK_ISO_7_ELSE \
| CATEGORY_MASK_ISO_8_ELSE \
- | CATEGORY_MASK_UTF_8 \
+ | CATEGORY_MASK_UTF_8_AUTO \
+ | CATEGORY_MASK_UTF_8_NOSIG \
+ | CATEGORY_MASK_UTF_8_SIG \
+ | CATEGORY_MASK_UTF_16_AUTO \
| CATEGORY_MASK_UTF_16_BE \
| CATEGORY_MASK_UTF_16_LE \
| CATEGORY_MASK_UTF_16_BE_NOSIG \
@@ -657,11 +665,16 @@ enum coding_category
| CATEGORY_MASK_ISO_ELSE)
#define CATEGORY_MASK_UTF_16 \
- (CATEGORY_MASK_UTF_16_BE \
+ (CATEGORY_MASK_UTF_16_AUTO \
+ | CATEGORY_MASK_UTF_16_BE \
| CATEGORY_MASK_UTF_16_LE \
| CATEGORY_MASK_UTF_16_BE_NOSIG \
| CATEGORY_MASK_UTF_16_LE_NOSIG)
+#define CATEGORY_MASK_UTF_8 \
+ (CATEGORY_MASK_UTF_8_AUTO \
+ | CATEGORY_MASK_UTF_8_NOSIG \
+ | CATEGORY_MASK_UTF_8_SIG)
/* List of symbols `coding-category-xxx' ordered by priority. This
variable is exposed to Emacs Lisp. */
@@ -898,7 +911,7 @@ static INLINE void produce_charset P_ ((struct coding_system *, int *,
static void produce_annotation P_ ((struct coding_system *, EMACS_INT));
static int decode_coding P_ ((struct coding_system *));
static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT,
- struct coding_system *,
+ struct coding_system *,
int *, EMACS_INT *));
static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT,
struct coding_system *,
@@ -955,6 +968,11 @@ record_conversion_result (struct coding_system *coding,
} while (0)
+/* If there are at least BYTES length of room at dst, allocate memory
+ for coding->destination and update dst and dst_end. We don't have
+ to take care of coding->source which will be relocated. It is
+ handled by calling coding_set_source in encode_coding. */
+
#define ASSURE_DESTINATION(bytes) \
do { \
if (dst + (bytes) >= dst_end) \
@@ -967,6 +985,66 @@ record_conversion_result (struct coding_system *coding,
} while (0)
+/* Store multibyte form of the character C in P, and advance P to the
+ end of the multibyte form. This is like CHAR_STRING_ADVANCE but it
+ never calls MAYBE_UNIFY_CHAR. */
+
+#define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \
+ do { \
+ if ((c) <= MAX_1_BYTE_CHAR) \
+ *(p)++ = (c); \
+ else if ((c) <= MAX_2_BYTE_CHAR) \
+ *(p)++ = (0xC0 | ((c) >> 6)), \
+ *(p)++ = (0x80 | ((c) & 0x3F)); \
+ else if ((c) <= MAX_3_BYTE_CHAR) \
+ *(p)++ = (0xE0 | ((c) >> 12)), \
+ *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \
+ *(p)++ = (0x80 | ((c) & 0x3F)); \
+ else if ((c) <= MAX_4_BYTE_CHAR) \
+ *(p)++ = (0xF0 | (c >> 18)), \
+ *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \
+ *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \
+ *(p)++ = (0x80 | (c & 0x3F)); \
+ else if ((c) <= MAX_5_BYTE_CHAR) \
+ *(p)++ = 0xF8, \
+ *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \
+ *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \
+ *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \
+ *(p)++ = (0x80 | (c & 0x3F)); \
+ else \
+ (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \
+ } while (0)
+
+
+/* Return the character code of character whose multibyte form is at
+ P, and advance P to the end of the multibyte form. This is like
+ STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */
+
+#define STRING_CHAR_ADVANCE_NO_UNIFY(p) \
+ (!((p)[0] & 0x80) \
+ ? *(p)++ \
+ : ! ((p)[0] & 0x20) \
+ ? ((p) += 2, \
+ ((((p)[-2] & 0x1F) << 6) \
+ | ((p)[-1] & 0x3F) \
+ | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \
+ : ! ((p)[0] & 0x10) \
+ ? ((p) += 3, \
+ ((((p)[-3] & 0x0F) << 12) \
+ | (((p)[-2] & 0x3F) << 6) \
+ | ((p)[-1] & 0x3F))) \
+ : ! ((p)[0] & 0x08) \
+ ? ((p) += 4, \
+ ((((p)[-4] & 0xF) << 18) \
+ | (((p)[-3] & 0x3F) << 12) \
+ | (((p)[-2] & 0x3F) << 6) \
+ | ((p)[-1] & 0x3F))) \
+ : ((p) += 5, \
+ ((((p)[-4] & 0x3F) << 18) \
+ | (((p)[-3] & 0x3F) << 12) \
+ | (((p)[-2] & 0x3F) << 6) \
+ | ((p)[-1] & 0x3F))))
+
static void
coding_set_source (coding)
@@ -1032,20 +1110,23 @@ coding_alloc_by_realloc (coding, bytes)
}
static void
-coding_alloc_by_making_gap (coding, offset, bytes)
+coding_alloc_by_making_gap (coding, gap_head_used, bytes)
struct coding_system *coding;
- EMACS_INT offset, bytes;
+ EMACS_INT gap_head_used, bytes;
{
- if (BUFFERP (coding->dst_object)
- && EQ (coding->src_object, coding->dst_object))
+ if (EQ (coding->src_object, coding->dst_object))
{
- EMACS_INT add = offset + (coding->src_bytes - coding->consumed);
+ /* The gap may contain the produced data at the head and not-yet
+ consumed data at the tail. To preserve those data, we at
+ first make the gap size to zero, then increase the gap
+ size. */
+ EMACS_INT add = GAP_SIZE;
- GPT += offset, GPT_BYTE += offset;
- GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add;
+ GPT += gap_head_used, GPT_BYTE += gap_head_used;
+ GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add;
make_gap (bytes);
GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add;
- GPT -= offset, GPT_BYTE -= offset;
+ GPT -= gap_head_used, GPT_BYTE -= gap_head_used;
}
else
{
@@ -1068,7 +1149,11 @@ alloc_destination (coding, nbytes, dst)
EMACS_INT offset = dst - coding->destination;
if (BUFFERP (coding->dst_object))
- coding_alloc_by_making_gap (coding, offset, nbytes);
+ {
+ struct buffer *buf = XBUFFER (coding->dst_object);
+
+ coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes);
+ }
else
coding_alloc_by_realloc (coding, nbytes);
record_conversion_result (coding, CODING_RESULT_SUCCESS);
@@ -1142,6 +1227,11 @@ alloc_destination (coding, nbytes, dst)
#define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0)
#define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8)
+#define UTF_BOM 0xFEFF
+#define UTF_8_BOM_1 0xEF
+#define UTF_8_BOM_2 0xBB
+#define UTF_8_BOM_3 0xBF
+
static int
detect_coding_utf_8 (coding, detect_info)
struct coding_system *coding;
@@ -1151,6 +1241,7 @@ detect_coding_utf_8 (coding, detect_info)
const unsigned char *src_end = coding->source + coding->src_bytes;
int multibytep = coding->src_multibyte;
int consumed_chars = 0;
+ int bom_found = 0;
int found = 0;
detect_info->checked |= CATEGORY_MASK_UTF_8;
@@ -1170,7 +1261,7 @@ detect_coding_utf_8 (coding, detect_info)
break;
if (UTF_8_2_OCTET_LEADING_P (c))
{
- found = CATEGORY_MASK_UTF_8;
+ found = 1;
continue;
}
ONE_MORE_BYTE (c2);
@@ -1178,7 +1269,10 @@ detect_coding_utf_8 (coding, detect_info)
break;
if (UTF_8_3_OCTET_LEADING_P (c))
{
- found = CATEGORY_MASK_UTF_8;
+ found = 1;
+ if (src_base == coding->source
+ && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3)
+ bom_found = 1;
continue;
}
ONE_MORE_BYTE (c3);
@@ -1186,7 +1280,7 @@ detect_coding_utf_8 (coding, detect_info)
break;
if (UTF_8_4_OCTET_LEADING_P (c))
{
- found = CATEGORY_MASK_UTF_8;
+ found = 1;
continue;
}
ONE_MORE_BYTE (c4);
@@ -1194,7 +1288,7 @@ detect_coding_utf_8 (coding, detect_info)
break;
if (UTF_8_5_OCTET_LEADING_P (c))
{
- found = CATEGORY_MASK_UTF_8;
+ found = 1;
continue;
}
break;
@@ -1208,7 +1302,17 @@ detect_coding_utf_8 (coding, detect_info)
detect_info->rejected |= CATEGORY_MASK_UTF_8;
return 0;
}
- detect_info->found |= found;
+ if (bom_found)
+ {
+ /* The first character 0xFFFE doesn't necessarily mean a BOM. */
+ detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG;
+ }
+ else
+ {
+ detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG;
+ if (found)
+ detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG;
+ }
return 1;
}
@@ -1222,12 +1326,48 @@ decode_coding_utf_8 (coding)
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
int *charbuf_end = coding->charbuf + coding->charbuf_size;
- int consumed_chars = 0, consumed_chars_base;
+ int consumed_chars = 0, consumed_chars_base = 0;
int multibytep = coding->src_multibyte;
+ enum utf_bom_type bom = CODING_UTF_8_BOM (coding);
Lisp_Object attr, charset_list;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr = -1;
CODING_GET_INFO (coding, attr, charset_list);
+ if (bom != utf_without_bom)
+ {
+ int c1, c2, c3;
+
+ src_base = src;
+ ONE_MORE_BYTE (c1);
+ if (! UTF_8_3_OCTET_LEADING_P (c1))
+ src = src_base;
+ else
+ {
+ ONE_MORE_BYTE (c2);
+ if (! UTF_8_EXTRA_OCTET_P (c2))
+ src = src_base;
+ else
+ {
+ ONE_MORE_BYTE (c3);
+ if (! UTF_8_EXTRA_OCTET_P (c3))
+ src = src_base;
+ else
+ {
+ if ((c1 != UTF_8_BOM_1)
+ || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3))
+ src = src_base;
+ else
+ CODING_UTF_8_BOM (coding) = utf_without_bom;
+ }
+ }
+ }
+ }
+ CODING_UTF_8_BOM (coding) = utf_without_bom;
+
+
+
while (1)
{
int c, c1, c2, c3, c4, c5;
@@ -1238,13 +1378,18 @@ decode_coding_utf_8 (coding)
if (charbuf >= charbuf_end)
break;
- ONE_MORE_BYTE (c1);
+ if (byte_after_cr >= 0)
+ c1 = byte_after_cr, byte_after_cr = -1;
+ else
+ ONE_MORE_BYTE (c1);
if (c1 < 0)
{
c = - c1;
}
else if (UTF_8_1_OCTET_P(c1))
{
+ if (eol_crlf && c1 == '\r')
+ ONE_MORE_BYTE (byte_after_cr);
c = c1;
}
else
@@ -1336,6 +1481,13 @@ encode_coding_utf_8 (coding)
int produced_chars = 0;
int c;
+ if (CODING_UTF_8_BOM (coding) == utf_with_bom)
+ {
+ ASSURE_DESTINATION (3);
+ EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3);
+ CODING_UTF_8_BOM (coding) = utf_without_bom;
+ }
+
if (multibytep)
{
int safe_room = MAX_MULTIBYTE_LENGTH * 2;
@@ -1353,7 +1505,7 @@ encode_coding_utf_8 (coding)
}
else
{
- CHAR_STRING_ADVANCE (c, pend);
+ CHAR_STRING_ADVANCE_NO_UNIFY (c, pend);
for (p = str; p < pend; p++)
EMIT_ONE_BYTE (*p);
}
@@ -1370,7 +1522,7 @@ encode_coding_utf_8 (coding)
if (CHAR_BYTE8_P (c))
*dst++ = CHAR_TO_BYTE8 (c);
else
- dst += CHAR_STRING (c, dst);
+ CHAR_STRING_ADVANCE_NO_UNIFY (c, dst);
produced_chars++;
}
}
@@ -1434,11 +1586,44 @@ detect_coding_utf_16 (coding, detect_info)
| CATEGORY_MASK_UTF_16_BE_NOSIG
| CATEGORY_MASK_UTF_16_LE_NOSIG);
}
- else if (c1 >= 0 && c2 >= 0)
+ else
{
+ /* We check the dispersion of Eth and Oth bytes where E is even and
+ O is odd. If both are high, we assume binary data.*/
+ unsigned char e[256], o[256];
+ unsigned e_num = 1, o_num = 1;
+
+ memset (e, 0, 256);
+ memset (o, 0, 256);
+ e[c1] = 1;
+ o[c2] = 1;
+
detect_info->rejected
|= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE);
+
+ while (1)
+ {
+ ONE_MORE_BYTE (c1);
+ ONE_MORE_BYTE (c2);
+ if (! e[c1])
+ {
+ e[c1] = 1;
+ e_num++;
+ if (e_num >= 128)
+ break;
+ }
+ if (! o[c2])
+ {
+ o[c1] = 1;
+ o_num++;
+ if (o_num >= 128)
+ break;
+ }
+ }
+ detect_info->rejected |= CATEGORY_MASK_UTF_16;
+ return 0;
}
+
no_more_source:
return 1;
}
@@ -1452,16 +1637,18 @@ decode_coding_utf_16 (coding)
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
int *charbuf_end = coding->charbuf + coding->charbuf_size;
- int consumed_chars = 0, consumed_chars_base;
+ int consumed_chars = 0, consumed_chars_base = 0;
int multibytep = coding->src_multibyte;
- enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding);
+ enum utf_bom_type bom = CODING_UTF_16_BOM (coding);
enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding);
int surrogate = CODING_UTF_16_SURROGATE (coding);
Lisp_Object attr, charset_list;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr1 = -1, byte_after_cr2 = -1;
CODING_GET_INFO (coding, attr, charset_list);
- if (bom == utf_16_with_bom)
+ if (bom == utf_with_bom)
{
int c, c1, c2;
@@ -1478,13 +1665,13 @@ decode_coding_utf_16 (coding)
src = src_base;
coding->errors++;
}
- CODING_UTF_16_BOM (coding) = utf_16_without_bom;
+ CODING_UTF_16_BOM (coding) = utf_without_bom;
}
- else if (bom == utf_16_detect_bom)
+ else if (bom == utf_detect_bom)
{
/* We have already tried to detect BOM and failed in
detect_coding. */
- CODING_UTF_16_BOM (coding) = utf_16_without_bom;
+ CODING_UTF_16_BOM (coding) = utf_without_bom;
}
while (1)
@@ -1497,13 +1684,19 @@ decode_coding_utf_16 (coding)
if (charbuf + 2 >= charbuf_end)
break;
- ONE_MORE_BYTE (c1);
+ if (byte_after_cr1 >= 0)
+ c1 = byte_after_cr1, byte_after_cr1 = -1;
+ else
+ ONE_MORE_BYTE (c1);
if (c1 < 0)
{
*charbuf++ = -c1;
continue;
}
- ONE_MORE_BYTE (c2);
+ if (byte_after_cr2 >= 0)
+ c2 = byte_after_cr2, byte_after_cr2 = -1;
+ else
+ ONE_MORE_BYTE (c2);
if (c2 < 0)
{
*charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1);
@@ -1512,6 +1705,7 @@ decode_coding_utf_16 (coding)
}
c = (endian == utf_16_big_endian
? ((c1 << 8) | c2) : ((c2 << 8) | c1));
+
if (surrogate)
{
if (! UTF_16_LOW_SURROGATE_P (c))
@@ -1540,7 +1734,14 @@ decode_coding_utf_16 (coding)
if (UTF_16_HIGH_SURROGATE_P (c))
CODING_UTF_16_SURROGATE (coding) = surrogate = c;
else
- *charbuf++ = c;
+ {
+ if (eol_crlf && c == '\r')
+ {
+ ONE_MORE_BYTE (byte_after_cr1);
+ ONE_MORE_BYTE (byte_after_cr2);
+ }
+ *charbuf++ = c;
+ }
}
}
@@ -1560,7 +1761,7 @@ encode_coding_utf_16 (coding)
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
int safe_room = 8;
- enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding);
+ enum utf_bom_type bom = CODING_UTF_16_BOM (coding);
int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian;
int produced_chars = 0;
Lisp_Object attrs, charset_list;
@@ -1568,14 +1769,14 @@ encode_coding_utf_16 (coding)
CODING_GET_INFO (coding, attrs, charset_list);
- if (bom != utf_16_without_bom)
+ if (bom != utf_without_bom)
{
ASSURE_DESTINATION (safe_room);
if (big_endian)
EMIT_TWO_BYTES (0xFE, 0xFF);
else
EMIT_TWO_BYTES (0xFF, 0xFE);
- CODING_UTF_16_BOM (coding) = utf_16_without_bom;
+ CODING_UTF_16_BOM (coding) = utf_without_bom;
}
while (charbuf < charbuf_end)
@@ -1711,7 +1912,7 @@ emacs_mule_char (coding, src, nbytes, nchars, id)
{
if (c >= 0xA0)
{
- /* Old style component character of a compostion. */
+ /* Old style component character of a composition. */
if (c == 0xA0)
{
ONE_MORE_BYTE (c);
@@ -1831,7 +2032,7 @@ detect_coding_emacs_mule (coding, detect_info)
/* Perhaps the start of composite character. We simple skip
it because analyzing it is too heavy for detecting. But,
at least, we check that the composite character
- constitues of more than 4 bytes. */
+ constitutes of more than 4 bytes. */
const unsigned char *src_base;
repeat:
@@ -2072,6 +2273,8 @@ decode_coding_emacs_mule (coding)
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
@@ -2085,7 +2288,10 @@ decode_coding_emacs_mule (coding)
if (charbuf >= charbuf_end)
break;
- ONE_MORE_BYTE (c);
+ if (byte_after_cr >= 0)
+ c = byte_after_cr, byte_after_cr = -1;
+ else
+ ONE_MORE_BYTE (c);
if (c < 0)
{
*charbuf++ = -c;
@@ -2093,6 +2299,8 @@ decode_coding_emacs_mule (coding)
}
else if (c < 0x80)
{
+ if (eol_crlf && c == '\r')
+ ONE_MORE_BYTE (byte_after_cr);
*charbuf++ = c;
char_offset++;
}
@@ -2241,8 +2449,10 @@ encode_coding_emacs_mule (coding)
if (preferred_charset_id >= 0)
{
charset = CHARSET_FROM_ID (preferred_charset_id);
- if (! CHAR_CHARSET_P (c, charset))
- charset = char_charset (c, charset_list, NULL);
+ if (CHAR_CHARSET_P (c, charset))
+ code = ENCODE_CHAR (charset, c);
+ else
+ charset = char_charset (c, charset_list, &code);
}
else
charset = char_charset (c, charset_list, &code);
@@ -2550,6 +2760,7 @@ detect_coding_iso_2022 (coding, detect_info)
int i;
int rejected = 0;
int found = 0;
+ int composition_count = -1;
detect_info->checked |= CATEGORY_MASK_ISO;
@@ -2558,6 +2769,8 @@ detect_coding_iso_2022 (coding, detect_info)
struct coding_system *this = &(coding_categories[i]);
Lisp_Object attrs, val;
+ if (this->id < 0)
+ continue;
attrs = CODING_ID_ATTRS (this->id);
if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT
&& ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list))
@@ -2616,10 +2829,20 @@ detect_coding_iso_2022 (coding, detect_info)
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT;
break;
}
+ else if (c == '1')
+ {
+ /* End of composition. */
+ if (composition_count < 0
+ || composition_count > MAX_COMPOSITION_COMPONENTS)
+ /* Invalid */
+ break;
+ composition_count = -1;
+ found |= CATEGORY_MASK_ISO;
+ }
else if (c >= '0' && c <= '4')
{
/* ESC for start/end composition. */
- found |= CATEGORY_MASK_ISO;
+ composition_count = 0;
break;
}
else
@@ -2690,6 +2913,8 @@ detect_coding_iso_2022 (coding, detect_info)
continue;
if (c < 0x80)
{
+ if (composition_count >= 0)
+ composition_count++;
single_shifting = 0;
break;
}
@@ -2714,9 +2939,17 @@ detect_coding_iso_2022 (coding, detect_info)
}
if (i & 1 && src < src_end)
- rejected |= CATEGORY_MASK_ISO_8_2;
+ {
+ rejected |= CATEGORY_MASK_ISO_8_2;
+ if (composition_count >= 0)
+ composition_count += i;
+ }
else
- found |= CATEGORY_MASK_ISO_8_2;
+ {
+ found |= CATEGORY_MASK_ISO_8_2;
+ if (composition_count >= 0)
+ composition_count += i / 2;
+ }
}
break;
}
@@ -2833,6 +3066,8 @@ detect_coding_iso_2022 (coding, detect_info)
break; \
if (p == src_end - 1) \
{ \
+ if (coding->mode & CODING_MODE_LAST_BLOCK) \
+ goto invalid_code; \
/* The current composition doesn't end in the current \
source. */ \
record_conversion_result \
@@ -2945,6 +3180,8 @@ decode_coding_iso_2022 (coding)
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
setup_iso_safe_charsets (attrs);
@@ -2962,7 +3199,10 @@ decode_coding_iso_2022 (coding)
if (charbuf >= charbuf_end)
break;
- ONE_MORE_BYTE (c1);
+ if (byte_after_cr >= 0)
+ c1 = byte_after_cr, byte_after_cr = -1;
+ else
+ ONE_MORE_BYTE (c1);
if (c1 < 0)
goto invalid_code;
@@ -2975,10 +3215,15 @@ decode_coding_iso_2022 (coding)
if (composition_state == COMPOSING_RULE
|| composition_state == COMPOSING_COMPONENT_RULE)
{
- DECODE_COMPOSITION_RULE (c1);
- components[component_idx++] = c1;
- composition_state--;
- continue;
+ if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1)
+ {
+ DECODE_COMPOSITION_RULE (c1);
+ components[component_idx++] = c1;
+ composition_state--;
+ continue;
+ }
+ /* Too long composition. */
+ MAYBE_FINISH_COMPOSITION ();
}
}
if (charset_id_0 < 0
@@ -2995,10 +3240,14 @@ decode_coding_iso_2022 (coding)
if (composition_state == COMPOSING_RULE
|| composition_state == COMPOSING_COMPONENT_RULE)
{
- DECODE_COMPOSITION_RULE (c1);
- components[component_idx++] = c1;
- composition_state--;
- continue;
+ if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1)
+ {
+ DECODE_COMPOSITION_RULE (c1);
+ components[component_idx++] = c1;
+ composition_state--;
+ continue;
+ }
+ MAYBE_FINISH_COMPOSITION ();
}
}
if (charset_id_0 < 0)
@@ -3021,6 +3270,8 @@ decode_coding_iso_2022 (coding)
break;
case ISO_control_0:
+ if (eol_crlf && c1 == '\r')
+ ONE_MORE_BYTE (byte_after_cr);
MAYBE_FINISH_COMPOSITION ();
charset = CHARSET_FROM_ID (charset_ascii);
break;
@@ -3354,11 +3605,20 @@ decode_coding_iso_2022 (coding)
}
else
{
- components[component_idx++] = c;
- if (method == COMPOSITION_WITH_RULE
- || (method == COMPOSITION_WITH_RULE_ALTCHARS
- && composition_state == COMPOSING_COMPONENT_CHAR))
- composition_state++;
+ if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1)
+ {
+ components[component_idx++] = c;
+ if (method == COMPOSITION_WITH_RULE
+ || (method == COMPOSITION_WITH_RULE_ALTCHARS
+ && composition_state == COMPOSING_COMPONENT_CHAR))
+ composition_state++;
+ }
+ else
+ {
+ MAYBE_FINISH_COMPOSITION ();
+ *charbuf++ = c;
+ char_offset++;
+ }
}
continue;
@@ -4091,6 +4351,8 @@ decode_coding_sjis (coding)
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
@@ -4111,11 +4373,18 @@ decode_coding_sjis (coding)
if (charbuf >= charbuf_end)
break;
- ONE_MORE_BYTE (c);
+ if (byte_after_cr >= 0)
+ c = byte_after_cr, byte_after_cr = -1;
+ else
+ ONE_MORE_BYTE (c);
if (c < 0)
goto invalid_code;
if (c < 0x80)
- charset = charset_roman;
+ {
+ if (eol_crlf && c == '\r')
+ ONE_MORE_BYTE (byte_after_cr);
+ charset = charset_roman;
+ }
else if (c == 0x80 || c == 0xA0)
goto invalid_code;
else if (c >= 0xA1 && c <= 0xDF)
@@ -4193,6 +4462,8 @@ decode_coding_big5 (coding)
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
val = charset_list;
@@ -4210,12 +4481,19 @@ decode_coding_big5 (coding)
if (charbuf >= charbuf_end)
break;
- ONE_MORE_BYTE (c);
+ if (byte_after_cr >= 0)
+ c = byte_after_cr, byte_after_cr = -1;
+ else
+ ONE_MORE_BYTE (c);
if (c < 0)
goto invalid_code;
if (c < 0x80)
- charset = charset_roman;
+ {
+ if (eol_crlf && c == '\r')
+ ONE_MORE_BYTE (byte_after_cr);
+ charset = charset_roman;
+ }
else
{
/* BIG5 -> Big5 */
@@ -4590,7 +4868,7 @@ encode_coding_ccl (coding)
else
{
ASSURE_DESTINATION (ccl.produced);
- for (i = 0; i < ccl.produced; i++)
+ for (i = 0; i < ccl.produced; i++)
*dst++ = destination_charbuf[i] & 0xFF;
produced_chars += ccl.produced;
}
@@ -4632,10 +4910,19 @@ static void
decode_coding_raw_text (coding)
struct coding_system *coding;
{
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+
coding->chars_at_source = 1;
- coding->consumed_char = 0;
- coding->consumed = 0;
- record_conversion_result (coding, CODING_RESULT_SUCCESS);
+ coding->consumed_char = coding->src_chars;
+ coding->consumed = coding->src_bytes;
+ if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r')
+ {
+ coding->consumed_char--;
+ coding->consumed--;
+ record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC);
+ }
+ else
+ record_conversion_result (coding, CODING_RESULT_SUCCESS);
}
static int
@@ -4702,7 +4989,6 @@ encode_coding_raw_text (coding)
*dst++ = CHAR_TO_BYTE8 (c);
else
CHAR_STRING_ADVANCE (c, dst);
- produced_chars++;
}
}
else
@@ -4710,8 +4996,8 @@ encode_coding_raw_text (coding)
ASSURE_DESTINATION (charbuf_end - charbuf);
while (charbuf < charbuf_end && dst < dst_end)
*dst++ = *charbuf++;
- produced_chars = dst - (coding->destination + coding->dst_bytes);
}
+ produced_chars = dst - (coding->destination + coding->produced);
}
record_conversion_result (coding, CODING_RESULT_SUCCESS);
coding->produced_char += produced_chars;
@@ -4732,16 +5018,20 @@ detect_coding_charset (coding, detect_info)
const unsigned char *src_end = coding->source + coding->src_bytes;
int multibytep = coding->src_multibyte;
int consumed_chars = 0;
- Lisp_Object attrs, valids;
+ Lisp_Object attrs, valids, name;
int found = 0;
int head_ascii = coding->head_ascii;
+ int check_latin_extra = 0;
detect_info->checked |= CATEGORY_MASK_CHARSET;
coding = &coding_categories[coding_category_charset];
attrs = CODING_ID_ATTRS (coding->id);
valids = AREF (attrs, coding_attr_charset_valids);
-
+ name = CODING_ID_NAME (coding->id);
+ if (VECTORP (Vlatin_extra_code_table)
+ && strcmp ((char *) SDATA (SYMBOL_NAME (name)), "iso-8859-"))
+ check_latin_extra = 1;
if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)))
src += head_ascii;
@@ -4760,7 +5050,13 @@ detect_coding_charset (coding, detect_info)
if (NILP (val))
break;
if (c >= 0x80)
- found = CATEGORY_MASK_CHARSET;
+ {
+ if (c < 0xA0
+ && check_latin_extra
+ && NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))
+ break;
+ found = CATEGORY_MASK_CHARSET;
+ }
if (INTEGERP (val))
{
charset = CHARSET_FROM_ID (XFASTINT (val));
@@ -4770,7 +5066,7 @@ detect_coding_charset (coding, detect_info)
if (src == src_end)
goto too_short;
ONE_MORE_BYTE (c);
- if (c < charset->code_space[(dim - 1 - idx) * 2]
+ if (c < charset->code_space[(dim - 1 - idx) * 2]
|| c > charset->code_space[(dim - 1 - idx) * 2 + 1])
break;
}
@@ -4829,6 +5125,8 @@ decode_coding_charset (coding)
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
+ int eol_crlf = EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
+ int byte_after_cr = -1;
CODING_GET_INFO (coding, attrs, charset_list);
valids = AREF (attrs, coding_attr_charset_valids);
@@ -4848,13 +5146,23 @@ decode_coding_charset (coding)
if (charbuf >= charbuf_end)
break;
- ONE_MORE_BYTE (c);
+ if (byte_after_cr >= 0)
+ {
+ c = byte_after_cr;
+ byte_after_cr = -1;
+ }
+ else
+ {
+ ONE_MORE_BYTE (c);
+ if (eol_crlf && c == '\r')
+ ONE_MORE_BYTE (byte_after_cr);
+ }
if (c < 0)
goto invalid_code;
code = c;
val = AREF (valids, c);
- if (NILP (val))
+ if (! INTEGERP (val) && ! CONSP (val))
goto invalid_code;
if (INTEGERP (val))
{
@@ -5090,18 +5398,24 @@ setup_coding_system (coding_system, coding)
}
else if (EQ (coding_type, Qutf_8))
{
+ val = AREF (attrs, coding_attr_utf_bom);
+ CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom
+ : EQ (val, Qt) ? utf_with_bom
+ : utf_without_bom);
coding->detector = detect_coding_utf_8;
coding->decoder = decode_coding_utf_8;
coding->encoder = encode_coding_utf_8;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
+ if (CODING_UTF_8_BOM (coding) == utf_detect_bom)
+ coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
}
else if (EQ (coding_type, Qutf_16))
{
- val = AREF (attrs, coding_attr_utf_16_bom);
- CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom
- : EQ (val, Qt) ? utf_16_with_bom
- : utf_16_without_bom);
+ val = AREF (attrs, coding_attr_utf_bom);
+ CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom
+ : EQ (val, Qt) ? utf_with_bom
+ : utf_without_bom);
val = AREF (attrs, coding_attr_utf_16_endian);
CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian
: utf_16_little_endian);
@@ -5111,7 +5425,7 @@ setup_coding_system (coding_system, coding)
coding->encoder = encode_coding_utf_16;
coding->common_flags
|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
- if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom)
+ if (CODING_UTF_16_BOM (coding) == utf_detect_bom)
coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
}
else if (EQ (coding_type, Qccl))
@@ -5522,6 +5836,7 @@ detect_coding (coding)
coding_set_source (coding);
src_end = coding->source + coding->src_bytes;
+ coding->head_ascii = 0;
/* If we have not yet decided the text encoding type, detect it
now. */
@@ -5529,32 +5844,55 @@ detect_coding (coding)
{
int c, i;
struct coding_detection_info detect_info;
+ int null_byte_found = 0, eight_bit_found = 0;
detect_info.checked = detect_info.found = detect_info.rejected = 0;
- for (i = 0, src = coding->source; src < src_end; i++, src++)
+ for (src = coding->source; src < src_end; 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))
+ eight_bit_found = 1;
+ if (null_byte_found)
+ break;
+ }
+ else if (c < 0x20)
+ {
+ if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
+ && ! inhibit_iso_escape_detection
+ && ! detect_info.checked)
{
- /* 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;
+ 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. We may
+ have found a null-byte, but it's very
+ rare that a binary file confirm to
+ ISO-2022. */
+ src = src_end;
+ coding->head_ascii = src - coding->source;
+ }
+ detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE;
+ break;
+ }
}
+ else if (! c)
+ {
+ null_byte_found = 1;
+ if (eight_bit_found)
+ break;
+ }
+ if (! eight_bit_found)
+ coding->head_ascii++;
}
+ else if (! eight_bit_found)
+ coding->head_ascii++;
}
- coding->head_ascii = src - (coding->source + coding->consumed);
- if (coding->head_ascii < coding->src_bytes
+ if (null_byte_found || eight_bit_found
+ || coding->head_ascii < coding->src_bytes
|| detect_info.found)
{
enum coding_category category;
@@ -5570,39 +5908,49 @@ detect_coding (coding)
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))
+ {
+ if (null_byte_found)
+ {
+ detect_info.checked |= ~CATEGORY_MASK_UTF_16;
+ detect_info.rejected |= ~CATEGORY_MASK_UTF_16;
+ }
+ 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;
- }
- 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)
+ else if (null_byte_found)
+ setup_coding_system (Qno_conversion, coding);
+ else if ((detect_info.rejected & CATEGORY_MASK_ANY)
+ == CATEGORY_MASK_ANY)
setup_coding_system (Qraw_text, coding);
else if (detect_info.rejected)
for (i = 0; i < coding_category_raw_text; i++)
@@ -5614,6 +5962,25 @@ detect_coding (coding)
}
}
}
+ else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id)))
+ == coding_category_utf_8_auto)
+ {
+ Lisp_Object coding_systems;
+ struct coding_detection_info detect_info;
+
+ coding_systems
+ = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom);
+ detect_info.found = detect_info.rejected = 0;
+ coding->head_ascii = 0;
+ if (CONSP (coding_systems)
+ && detect_coding_utf_8 (coding, &detect_info))
+ {
+ if (detect_info.found & CATEGORY_MASK_UTF_8_SIG)
+ setup_coding_system (XCAR (coding_systems), coding);
+ else
+ setup_coding_system (XCDR (coding_systems), coding);
+ }
+ }
else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id)))
== coding_category_utf_16_auto)
{
@@ -5621,8 +5988,9 @@ detect_coding (coding)
struct coding_detection_info detect_info;
coding_systems
- = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom);
+ = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom);
detect_info.found = detect_info.rejected = 0;
+ coding->head_ascii = 0;
if (CONSP (coding_systems)
&& detect_coding_utf_16 (coding, &detect_info))
{
@@ -5641,7 +6009,7 @@ decode_eol (coding)
{
Lisp_Object eol_type;
unsigned char *p, *pbeg, *pend;
-
+
eol_type = CODING_ID_EOL_TYPE (coding->id);
if (EQ (eol_type, Qunix))
return;
@@ -5880,19 +6248,21 @@ produce_chars (coding, translation_table, last_block)
{
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
- int produced;
- int produced_chars = 0;
+ EMACS_INT produced;
+ EMACS_INT produced_chars = 0;
int carryover = 0;
if (! coding->chars_at_source)
{
- /* Characters are in coding->charbuf. */
+ /* Source characters are in coding->charbuf. */
int *buf = coding->charbuf;
int *buf_end = buf + coding->charbuf_used;
- if (BUFFERP (coding->src_object)
- && EQ (coding->src_object, coding->dst_object))
- dst_end = ((unsigned char *) coding->source) + coding->consumed;
+ if (EQ (coding->src_object, coding->dst_object))
+ {
+ coding_set_source (coding);
+ dst_end = ((unsigned char *) coding->source) + coding->consumed;
+ }
while (buf < buf_end)
{
@@ -5919,7 +6289,13 @@ produce_chars (coding, translation_table, last_block)
buf_end - buf
+ MAX_MULTIBYTE_LENGTH * to_nchars,
dst);
- dst_end = coding->destination + coding->dst_bytes;
+ if (EQ (coding->src_object, coding->dst_object))
+ {
+ coding_set_source (coding);
+ dst_end = ((unsigned char *) coding->source) + coding->consumed;
+ }
+ else
+ dst_end = coding->destination + coding->dst_bytes;
}
for (i = 0; i < to_nchars; i++)
@@ -5928,7 +6304,7 @@ produce_chars (coding, translation_table, last_block)
c = XINT (AREF (trans, i));
if (coding->dst_multibyte
|| ! CHAR_BYTE8_P (c))
- CHAR_STRING_ADVANCE (c, dst);
+ CHAR_STRING_ADVANCE_NO_UNIFY (c, dst);
else
*dst++ = CHAR_TO_BYTE8 (c);
}
@@ -5945,18 +6321,18 @@ produce_chars (coding, translation_table, last_block)
}
else
{
+ /* Source characters are at coding->source. */
const unsigned char *src = coding->source;
- const unsigned char *src_end = src + coding->src_bytes;
- Lisp_Object eol_type;
-
- eol_type = CODING_ID_EOL_TYPE (coding->id);
+ const unsigned char *src_end = src + coding->consumed;
+ if (EQ (coding->dst_object, coding->src_object))
+ dst_end = (unsigned char *) src;
if (coding->src_multibyte != coding->dst_multibyte)
{
if (coding->src_multibyte)
{
int multibytep = 1;
- int consumed_chars;
+ EMACS_INT consumed_chars = 0;
while (1)
{
@@ -5964,37 +6340,23 @@ produce_chars (coding, translation_table, last_block)
int c;
ONE_MORE_BYTE (c);
- if (c == '\r')
+ if (dst == dst_end)
{
- if (EQ (eol_type, Qdos))
+ if (EQ (coding->src_object, coding->dst_object))
+ dst_end = (unsigned char *) src;
+ if (dst == dst_end)
{
- if (src == src_end)
- {
- record_conversion_result
- (coding, CODING_RESULT_INSUFFICIENT_SRC);
- goto no_more_source;
- }
- if (*src == '\n')
- c = *src++;
+ EMACS_INT offset = src - coding->source;
+
+ dst = alloc_destination (coding, src_end - src + 1,
+ dst);
+ dst_end = coding->destination + coding->dst_bytes;
+ coding_set_source (coding);
+ src = coding->source + offset;
+ src_end = coding->source + coding->src_bytes;
+ if (EQ (coding->src_object, coding->dst_object))
+ dst_end = (unsigned char *) src;
}
- else if (EQ (eol_type, Qmac))
- c = '\n';
- }
- if (dst == dst_end)
- {
- coding->consumed = src - coding->source;
-
- if (EQ (coding->src_object, coding->dst_object))
- dst_end = (unsigned char *) src;
- if (dst == dst_end)
- {
- dst = alloc_destination (coding, src_end - src + 1,
- dst);
- dst_end = coding->destination + coding->dst_bytes;
- coding_set_source (coding);
- src = coding->source + coding->consumed;
- src_end = coding->source + coding->src_bytes;
- }
}
*dst++ = c;
produced_chars++;
@@ -6008,31 +6370,26 @@ produce_chars (coding, translation_table, last_block)
int multibytep = 1;
int c = *src++;
- if (c == '\r')
- {
- if (EQ (eol_type, Qdos))
- {
- if (src < src_end
- && *src == '\n')
- c = *src++;
- }
- else if (EQ (eol_type, Qmac))
- c = '\n';
- }
if (dst >= dst_end - 1)
{
- coding->consumed = src - coding->source;
-
if (EQ (coding->src_object, coding->dst_object))
dst_end = (unsigned char *) src;
if (dst >= dst_end - 1)
{
- dst = alloc_destination (coding, src_end - src + 2,
- dst);
+ EMACS_INT offset = src - coding->source;
+ EMACS_INT more_bytes;
+
+ if (EQ (coding->src_object, coding->dst_object))
+ more_bytes = ((src_end - src) / 2) + 2;
+ else
+ more_bytes = src_end - src + 2;
+ dst = alloc_destination (coding, more_bytes, dst);
dst_end = coding->destination + coding->dst_bytes;
coding_set_source (coding);
- src = coding->source + coding->consumed;
+ src = coding->source + offset;
src_end = coding->source + coding->src_bytes;
+ if (EQ (coding->src_object, coding->dst_object))
+ dst_end = (unsigned char *) src;
}
}
EMIT_ONE_BYTE (c);
@@ -6042,7 +6399,7 @@ produce_chars (coding, translation_table, last_block)
{
if (!EQ (coding->src_object, coding->dst_object))
{
- int require = coding->src_bytes - coding->dst_bytes;
+ EMACS_INT require = coding->src_bytes - coding->dst_bytes;
if (require > 0)
{
@@ -6054,28 +6411,10 @@ produce_chars (coding, translation_table, last_block)
src_end = coding->source + coding->src_bytes;
}
}
- produced_chars = coding->src_chars;
+ produced_chars = coding->consumed_char;
while (src < src_end)
- {
- int c = *src++;
-
- if (c == '\r')
- {
- if (EQ (eol_type, Qdos))
- {
- if (src < src_end
- && *src == '\n')
- c = *src++;
- produced_chars--;
- }
- else if (EQ (eol_type, Qmac))
- c = '\n';
- }
- *dst++ = c;
- }
+ *dst++ = *src++;
}
- coding->consumed = coding->src_bytes;
- coding->consumed_char = coding->src_chars;
}
produced = dst - (coding->destination + coding->produced);
@@ -6538,12 +6877,12 @@ consume_chars (coding, translation_table, max_lookup)
if (coding->encoder == encode_coding_raw_text)
c = *src++, pos++;
else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0)
- c = STRING_CHAR_ADVANCE (src), pos += bytes;
+ c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes;
else
c = BYTE8_TO_CHAR (*src), src++, pos++;
}
else
- c = STRING_CHAR_ADVANCE (src), pos++;
+ c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++;
if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY))
c = '\n';
if (! EQ (eol_type, Qunix))
@@ -6686,14 +7025,18 @@ make_conversion_work_buffer (multibyte)
}
else
{
- name = Vcode_conversion_workbuf_name;
- workbuf = Fget_buffer_create (name);
- if (NILP (Vcode_conversion_reused_workbuf))
- Vcode_conversion_reused_workbuf = workbuf;
+ if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf)))
+ Vcode_conversion_reused_workbuf
+ = Fget_buffer_create (Vcode_conversion_workbuf_name);
+ workbuf = Vcode_conversion_reused_workbuf;
}
current = current_buffer;
set_buffer_internal (XBUFFER (workbuf));
- Ferase_buffer ();
+ /* We can't allow modification hooks to run in the work buffer. For
+ instance, directory_files_internal assumes that file decoding
+ doesn't compile new regexps. */
+ Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt);
+ Ferase_buffer ();
current_buffer->undo_list = Qt;
current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil;
set_buffer_internal (current);
@@ -6852,11 +7195,11 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
EMACS_INT chars = to - from;
EMACS_INT bytes = to_byte - from_byte;
Lisp_Object attrs;
- Lisp_Object buffer;
int saved_pt = -1, saved_pt_byte;
int need_marker_adjustment = 0;
+ Lisp_Object old_deactivate_mark;
- buffer = Fcurrent_buffer ();
+ old_deactivate_mark = Vdeactivate_mark;
if (NILP (dst_object))
{
@@ -6891,6 +7234,7 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
}
saved_pt = PT, saved_pt_byte = PT_BYTE;
TEMP_SET_PT_BOTH (from, from_byte);
+ current_buffer->text->inhibit_shrinking = 1;
del_range_both (from, from_byte, to, to_byte, 1);
coding->src_pos = -chars;
coding->src_pos_byte = -bytes;
@@ -6910,10 +7254,10 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
|| (! NILP (CODING_ATTR_POST_READ (attrs))
&& NILP (dst_object)))
{
- coding->dst_object = code_conversion_save (1, 1);
+ coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding);
+ coding->dst_object = code_conversion_save (1, coding->dst_multibyte);
coding->dst_pos = BEG;
coding->dst_pos_byte = BEG_BYTE;
- coding->dst_multibyte = 1;
}
else if (BUFFERP (dst_object))
{
@@ -6928,6 +7272,9 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
{
code_conversion_save (0, 0);
coding->dst_object = Qnil;
+ /* Most callers presume this will return a multibyte result, and they
+ won't use `binary' or `raw-text' anyway, so let's not worry about
+ CODING_FOR_UNIBYTE. */
coding->dst_multibyte = 1;
}
@@ -6938,12 +7285,13 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
if (! NILP (CODING_ATTR_POST_READ (attrs)))
{
- struct gcpro gcpro1, gcpro2;
+ struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5;
EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE;
Lisp_Object val;
TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte);
- GCPRO2 (coding->src_object, coding->dst_object);
+ GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object,
+ old_deactivate_mark);
val = safe_call1 (CODING_ATTR_POST_READ (attrs),
make_number (coding->produced_char));
UNGCPRO;
@@ -6961,8 +7309,7 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
set_buffer_internal (XBUFFER (coding->dst_object));
if (dst_bytes < coding->produced)
{
- destination
- = (unsigned char *) xrealloc (destination, coding->produced);
+ destination = xrealloc (destination, coding->produced);
if (! destination)
{
record_conversion_result (coding,
@@ -6984,6 +7331,7 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
As we have moved PT while replacing the original buffer
contents, we must recover it now. */
set_buffer_internal (XBUFFER (src_object));
+ current_buffer->text->inhibit_shrinking = 0;
if (saved_pt < from)
TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte);
else if (saved_pt < from + chars)
@@ -7019,6 +7367,7 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
}
}
+ Vdeactivate_mark = old_deactivate_mark;
unbind_to (count, coding->dst_object);
}
@@ -7035,12 +7384,12 @@ encode_coding_object (coding, src_object, from, from_byte, to, to_byte,
EMACS_INT chars = to - from;
EMACS_INT bytes = to_byte - from_byte;
Lisp_Object attrs;
- Lisp_Object buffer;
int saved_pt = -1, saved_pt_byte;
int need_marker_adjustment = 0;
int kill_src_buffer = 0;
+ Lisp_Object old_deactivate_mark;
- buffer = Fcurrent_buffer ();
+ old_deactivate_mark = Vdeactivate_mark;
coding->src_object = src_object;
coding->src_chars = chars;
@@ -7082,11 +7431,15 @@ encode_coding_object (coding, src_object, from, from_byte, to, to_byte,
{
Lisp_Object args[3];
+ struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5;
+ GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object,
+ old_deactivate_mark);
args[0] = CODING_ATTR_PRE_WRITE (attrs);
args[1] = make_number (BEG);
args[2] = make_number (Z);
safe_call (3, args);
+ UNGCPRO;
}
if (XBUFFER (coding->src_object) != current_buffer)
kill_src_buffer = 1;
@@ -7137,8 +7490,13 @@ encode_coding_object (coding, src_object, from, from_byte, to, to_byte,
}
else
{
- coding->dst_pos = BUF_PT (XBUFFER (dst_object));
- coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object));
+ struct buffer *current = current_buffer;
+
+ set_buffer_temp (XBUFFER (dst_object));
+ coding->dst_pos = PT;
+ coding->dst_pos_byte = PT_BYTE;
+ move_gap_both (coding->dst_pos, coding->dst_pos_byte);
+ set_buffer_temp (current);
}
coding->dst_multibyte
= ! NILP (XBUFFER (dst_object)->enable_multibyte_characters);
@@ -7217,6 +7575,8 @@ encode_coding_object (coding, src_object, from, from_byte, to, to_byte,
if (kill_src_buffer)
Fkill_buffer (coding->src_object);
+
+ Vdeactivate_mark = old_deactivate_mark;
unbind_to (count, Qnil);
}
@@ -7237,14 +7597,14 @@ DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0,
doc: /* Return t if OBJECT is nil or a coding-system.
See the documentation of `define-coding-system' for information
about coding-system objects. */)
- (obj)
- Lisp_Object obj;
+ (object)
+ Lisp_Object object;
{
- if (NILP (obj)
- || CODING_SYSTEM_ID (obj) >= 0)
+ if (NILP (object)
+ || CODING_SYSTEM_ID (object) >= 0)
return Qt;
- if (! SYMBOLP (obj)
- || NILP (Fget (obj, Qcoding_system_define_form)))
+ if (! SYMBOLP (object)
+ || NILP (Fget (object, Qcoding_system_define_form)))
return Qnil;
return Qt;
}
@@ -7336,11 +7696,12 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
{
const unsigned char *src_end = src + src_bytes;
Lisp_Object attrs, eol_type;
- Lisp_Object val;
+ Lisp_Object val = Qnil;
struct coding_system coding;
int id;
struct coding_detection_info detect_info;
enum coding_category base_category;
+ int null_byte_found = 0, eight_bit_found = 0;
if (NILP (coding_system))
coding_system = Qundecided;
@@ -7355,6 +7716,7 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
coding.src_multibyte = multibytep;
coding.consumed = 0;
coding.mode |= CODING_MODE_LAST_BLOCK;
+ coding.head_ascii = 0;
detect_info.checked = detect_info.found = detect_info.rejected = 0;
@@ -7367,32 +7729,55 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
int c, i;
/* Skip all ASCII bytes except for a few ISO2022 controls. */
- for (i = 0; src < src_end; i++, src++)
+ for (; src < src_end; 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))
+ eight_bit_found = 1;
+ if (null_byte_found)
+ break;
+ }
+ else if (c < 0x20)
+ {
+ if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
+ && ! inhibit_iso_escape_detection
+ && ! detect_info.checked)
{
- /* 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;
+ 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. We may
+ have found a null-byte, but it's very
+ rare that a binary file confirm to
+ ISO-2022. */
+ src = src_end;
+ coding.head_ascii = src - coding.source;
+ }
+ detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE;
+ break;
+ }
+ }
+ else if (! c)
+ {
+ null_byte_found = 1;
+ if (eight_bit_found)
+ break;
}
+ if (! eight_bit_found)
+ coding.head_ascii++;
}
+ else if (! eight_bit_found)
+ coding.head_ascii++;
}
- coding.head_ascii = src - coding.source;
- if (src < src_end
+ if (null_byte_found || eight_bit_found
+ || coding.head_ascii < coding.src_bytes
|| detect_info.found)
{
- if (src == src_end)
+ 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++)
{
@@ -7402,44 +7787,48 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
break;
}
else
- for (i = 0; i < coding_category_raw_text; i++)
- {
- category = coding_priorities[i];
- this = coding_categories + category;
+ {
+ if (null_byte_found)
+ {
+ detect_info.checked |= ~CATEGORY_MASK_UTF_16;
+ detect_info.rejected |= ~CATEGORY_MASK_UTF_16;
+ }
+ 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;
- }
+ 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)
+ if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY)
{
detect_info.found = CATEGORY_MASK_RAW_TEXT;
id = coding_categories[coding_category_raw_text].id;
@@ -7472,7 +7861,6 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
{
int mask = detect_info.rejected | detect_info.found;
int found = 0;
- val = Qnil;
for (i = coding_category_raw_text - 1; i >= 0; i--)
{
@@ -7497,6 +7885,19 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
detect_info.found |= found;
}
}
+ else if (base_category == coding_category_utf_8_auto)
+ {
+ if (detect_coding_utf_8 (&coding, &detect_info))
+ {
+ struct coding_system *this;
+
+ if (detect_info.found & CATEGORY_MASK_UTF_8_SIG)
+ this = coding_categories + coding_category_utf_8_sig;
+ else
+ this = coding_categories + coding_category_utf_8_nosig;
+ val = Fcons (make_number (this->id), Qnil);
+ }
+ }
else if (base_category == coding_category_utf_16_auto)
{
if (detect_coding_utf_16 (&coding, &detect_info))
@@ -7522,14 +7923,19 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
/* Then, detect eol-format if necessary. */
{
- int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol;
+ int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1;
Lisp_Object tail;
if (VECTORP (eol_type))
{
if (detect_info.found & ~CATEGORY_MASK_UTF_16)
- normal_eol = detect_eol (coding.source, src_bytes,
- coding_category_raw_text);
+ {
+ if (null_byte_found)
+ normal_eol = EOL_SEEN_LF;
+ else
+ normal_eol = detect_eol (coding.source, src_bytes,
+ coding_category_raw_text);
+ }
if (detect_info.found & (CATEGORY_MASK_UTF_16_BE
| CATEGORY_MASK_UTF_16_BE_NOSIG))
utf_16_be_eol = detect_eol (coding.source, src_bytes,
@@ -7583,7 +7989,7 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
}
}
- return (highest ? XCAR (val) : val);
+ return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val);
}
@@ -7593,9 +7999,9 @@ DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region,
Return a list of possible coding systems ordered by priority.
If only ASCII characters are found (except for such ISO-2022 control
-characters ISO-2022 as ESC), it returns a list of single element
-`undecided' or its subsidiary coding system according to a detected
-end-of-line format.
+characters as ESC), it returns a list of single element `undecided'
+or its subsidiary coding system according to a detected end-of-line
+format.
If optional argument HIGHEST is non-nil, return the coding system of
highest priority. */)
@@ -7630,9 +8036,9 @@ DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string,
Return a list of possible coding systems ordered by priority.
If only ASCII characters are found (except for such ISO-2022 control
-characters ISO-2022 as ESC), it returns a list of single element
-`undecided' or its subsidiary coding system according to a detected
-end-of-line format.
+characters as ESC), it returns a list of single element `undecided'
+or its subsidiary coding system according to a detected end-of-line
+format.
If optional argument HIGHEST is non-nil, return the coding system of
highest priority. */)
@@ -7800,7 +8206,7 @@ DEFUN ("unencodable-char-position", Funencodable_char_position,
Sunencodable_char_position, 3, 5, 0,
doc: /*
Return position of first un-encodable character in a region.
-START and END specfiy the region and CODING-SYSTEM specifies the
+START and END specify the region and CODING-SYSTEM specifies the
encoding to check. Return nil if CODING-SYSTEM does encode the region.
If optional 4th argument COUNT is non-nil, it specifies at most how
@@ -7913,7 +8319,7 @@ START and END are buffer positions specifying the region.
CODING-SYSTEM-LIST is a list of coding systems to check.
The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where
-CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the
+CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the
whole region, POS0, POS1, ... are buffer positions where non-encodable
characters are found.
@@ -8082,13 +8488,14 @@ START and END are buffer positions.
Optional 4th arguments DESTINATION specifies where the decoded text goes.
If nil, the region between START and END is replaced by the decoded text.
-If buffer, the decoded text is inserted in the buffer.
-If t, the decoded text is returned.
+If buffer, the decoded text is inserted in that buffer after point (point
+does not move).
+In those cases, the length of the decoded text is returned.
+If DESTINATION is t, the decoded text is returned.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
-not fully specified.)
-It returns the length of the decoded text. */)
+not fully specified.) */)
(start, end, coding_system, destination)
Lisp_Object start, end, coding_system, destination;
{
@@ -8098,18 +8505,20 @@ It returns the length of the decoded text. */)
DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region,
3, 4, "r\nzCoding system: ",
doc: /* Encode the current region by specified coding system.
-When called from a program, takes three arguments:
-START, END, and CODING-SYSTEM. START and END are buffer positions.
+When called from a program, takes four arguments:
+ START, END, CODING-SYSTEM and DESTINATION.
+START and END are buffer positions.
Optional 4th arguments DESTINATION specifies where the encoded text goes.
If nil, the region between START and END is replace by the encoded text.
-If buffer, the encoded text is inserted in the buffer.
-If t, the encoded text is returned.
+If buffer, the encoded text is inserted in that buffer after point (point
+does not move).
+In those cases, the length of the encoded text is returned.
+If DESTINATION is t, the encoded text is returned.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
-not fully specified.)
-It returns the length of the encoded text. */)
+not fully specified.) */)
(start, end, coding_system, destination)
Lisp_Object start, end, coding_system, destination;
{
@@ -8182,13 +8591,13 @@ DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string,
Optional third arg NOCOPY non-nil means it is OK to return STRING itself
if the decoding operation is trivial.
-Optional fourth arg BUFFER non-nil meant that the decoded text is
-inserted in BUFFER instead of returned as a string. In this case,
-the return value is BUFFER.
+Optional fourth arg BUFFER non-nil means that the decoded text is
+inserted in that buffer after point (point does not move). In this
+case, the return value is the length of the decoded text.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
-not fully specified. */)
+not fully specified.) */)
(string, coding_system, nocopy, buffer)
Lisp_Object string, coding_system, nocopy, buffer;
{
@@ -8203,9 +8612,9 @@ DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string,
Optional third arg NOCOPY non-nil means it is OK to return STRING
itself if the encoding operation is trivial.
-Optional fourth arg BUFFER non-nil meant that the encoded text is
-inserted in BUFFER instead of returned as a string. In this case,
-the return value is BUFFER.
+Optional fourth arg BUFFER non-nil means that the encoded text is
+inserted in that buffer after point (point does not move). In this
+case, the return value is the length of the encoded text.
This function sets `last-coding-system-used' to the precise coding system
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
@@ -8463,9 +8872,9 @@ whichever argument specifies the file name is TARGET.
TARGET has a meaning which depends on OPERATION:
For file I/O, TARGET is a file name (except for the special case below).
For process I/O, TARGET is a process name.
- For network I/O, TARGET is a service name or a port number
+ For network I/O, TARGET is a service name or a port number.
-This function looks up what specified for TARGET in,
+This function looks up what is specified for TARGET in
`file-coding-system-alist', `process-coding-system-alist',
or `network-coding-system-alist' depending on OPERATION.
They may specify a coding system, a cons of coding systems,
@@ -8495,7 +8904,7 @@ usage: (find-operation-coding-system OPERATION ARGUMENTS...) */)
operation = args[0];
if (!SYMBOLP (operation)
|| !INTEGERP (target_idx = Fget (operation, Qtarget_idx)))
- error ("Invalid first arguement");
+ error ("Invalid first argument");
if (nargs < 1 + XINT (target_idx))
error ("Too few arguments for operation: %s",
SDATA (SYMBOL_NAME (operation)));
@@ -8557,10 +8966,10 @@ usage: (find-operation-coding-system OPERATION ARGUMENTS...) */)
DEFUN ("set-coding-system-priority", Fset_coding_system_priority,
Sset_coding_system_priority, 0, MANY, 0,
doc: /* Assign higher priority to the coding systems given as arguments.
-If multiple coding systems belongs to the same category,
+If multiple coding systems belong to the same category,
all but the first one are ignored.
-usage: (set-coding-system-priority ...) */)
+usage: (set-coding-system-priority &rest coding-systems) */)
(nargs, args)
int nargs;
Lisp_Object *args;
@@ -8921,7 +9330,7 @@ usage: (define-coding-system-internal ...) */)
val = XCDR (bom);
CHECK_CODING_SYSTEM (val);
}
- ASET (attrs, coding_attr_utf_16_bom, bom);
+ ASET (attrs, coding_attr_utf_bom, bom);
endian = args[coding_arg_utf16_endian];
CHECK_SYMBOL (endian);
@@ -9100,8 +9509,27 @@ usage: (define-coding-system-internal ...) */)
}
else if (EQ (coding_type, Qutf_8))
{
- category = coding_category_utf_8;
+ Lisp_Object bom;
+
CODING_ATTR_ASCII_COMPAT (attrs) = Qt;
+
+ if (nargs < coding_arg_utf8_max)
+ goto short_args;
+
+ bom = args[coding_arg_utf8_bom];
+ if (! NILP (bom) && ! EQ (bom, Qt))
+ {
+ CHECK_CONS (bom);
+ val = XCAR (bom);
+ CHECK_CODING_SYSTEM (val);
+ val = XCDR (bom);
+ CHECK_CODING_SYSTEM (val);
+ }
+ ASET (attrs, coding_attr_utf_bom, bom);
+
+ category = (CONSP (bom) ? coding_category_utf_8_auto
+ : NILP (bom) ? coding_category_utf_8_nosig
+ : coding_category_utf_8_sig);
}
else if (EQ (coding_type, Qundecided))
category = coding_category_undecided;
@@ -9114,7 +9542,7 @@ usage: (define-coding-system-internal ...) */)
= Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category),
CODING_ATTR_PLIST (attrs)));
CODING_ATTR_PLIST (attrs)
- = Fcons (QCascii_compatible_p,
+ = Fcons (QCascii_compatible_p,
Fcons (CODING_ATTR_ASCII_COMPAT (attrs),
CODING_ATTR_PLIST (attrs)));
@@ -9193,7 +9621,7 @@ DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put,
CHECK_CHARACTER (val);
CODING_ATTR_MNEMONIC (attrs) = val;
}
- else if (EQ (prop, QCdefalut_char))
+ else if (EQ (prop, QCdefault_char))
{
if (NILP (val))
val = make_number (' ');
@@ -9245,7 +9673,7 @@ DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias,
CHECK_SYMBOL (alias);
CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
aliases = AREF (spec, 1);
- /* ALISES should be a list of length more than zero, and the first
+ /* ALIASES should be a list of length more than zero, and the first
element is a base coding system. Append ALIAS at the tail of the
list. */
while (!NILP (XCDR (aliases)))
@@ -9323,7 +9751,7 @@ DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases,
DEFUN ("coding-system-eol-type", Fcoding_system_eol_type,
Scoding_system_eol_type, 1, 1, 0,
doc: /* Return eol-type of CODING-SYSTEM.
-An eol-type is integer 0, 1, 2, or a vector of coding systems.
+An eol-type is an integer 0, 1, 2, or a vector of coding systems.
Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF,
and CR respectively.
@@ -9499,7 +9927,7 @@ syms_of_coding ()
DEFSYM (QCcategory, ":category");
DEFSYM (QCmnemonic, ":mnemonic");
- DEFSYM (QCdefalut_char, ":default-char");
+ DEFSYM (QCdefault_char, ":default-char");
DEFSYM (QCdecode_translation_table, ":decode-translation-table");
DEFSYM (QCencode_translation_table, ":encode-translation-table");
DEFSYM (QCpost_read_conversion, ":post-read-conversion");
@@ -9522,8 +9950,12 @@ syms_of_coding ()
intern ("coding-category-iso-7-else"));
ASET (Vcoding_category_table, coding_category_iso_8_else,
intern ("coding-category-iso-8-else"));
- ASET (Vcoding_category_table, coding_category_utf_8,
+ ASET (Vcoding_category_table, coding_category_utf_8_auto,
+ intern ("coding-category-utf-8-auto"));
+ ASET (Vcoding_category_table, coding_category_utf_8_nosig,
intern ("coding-category-utf-8"));
+ ASET (Vcoding_category_table, coding_category_utf_8_sig,
+ intern ("coding-category-utf-8-sig"));
ASET (Vcoding_category_table, coding_category_utf_16_be,
intern ("coding-category-utf-16-be"));
ASET (Vcoding_category_table, coding_category_utf_16_auto,
@@ -9601,7 +10033,7 @@ updated by the functions `define-coding-system' and
DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist,
doc: /* Alist of coding system names.
Each element is one element list of coding system name.
-This variable is given to `completing-read' as TABLE argument.
+This variable is given to `completing-read' as COLLECTION argument.
Do not alter the value of this variable manually. This variable should be
updated by the functions `make-coding-system' and
@@ -9631,8 +10063,8 @@ Don't modify this variable directly, but use `set-coding-priority'. */);
doc: /* Specify the coding system for read operations.
It is useful to bind this variable with `let', but do not set it globally.
If the value is a coding system, it is used for decoding on read operation.
-If not, an appropriate element is used from one of the coding system alists:
-There are three such tables, `file-coding-system-alist',
+If not, an appropriate element is used from one of the coding system alists.
+There are three such tables: `file-coding-system-alist',
`process-coding-system-alist', and `network-coding-system-alist'. */);
Vcoding_system_for_read = Qnil;
@@ -9643,8 +10075,8 @@ If the value is a coding system, it is used for encoding of output,
when writing it to a file and when sending it to a file or subprocess.
If this does not specify a coding system, an appropriate element
-is used from one of the coding system alists:
-There are three such tables, `file-coding-system-alist',
+is used from one of the coding system alists.
+There are three such tables: `file-coding-system-alist',
`process-coding-system-alist', and `network-coding-system-alist'.
For output to files, if the above procedure does not specify a coding system,
the value of `buffer-file-coding-system' is used. */);
@@ -9804,7 +10236,7 @@ If Nth element is non-nil, the existence of code N in a file
a coding system of ISO 2022 variant which has a flag
`accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file
or reading output of a subprocess.
-Only 128th through 159th elements has a meaning. */);
+Only 128th through 159th elements have a meaning. */);
Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil);
DEFVAR_LISP ("select-safe-coding-system-function",
@@ -9860,8 +10292,8 @@ escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argumen
DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input,
doc: /* Char table for translating self-inserting characters.
-This is applied to the result of input methods, not their input. See also
-`keyboard-translate-table'. */);
+This is applied to the result of input methods, not their input.
+See also `keyboard-translate-table'. */);
Vtranslation_table_for_input = Qnil;
{