/* Coding system handler (conversion, detection, etc).
- Copyright (C) 2001, 2002, 2003, 2004, 2005,
- 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
+ Copyright (C) 2001-2011 Free Software Foundation, Inc.
Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
- 2005, 2006, 2007, 2008, 2009, 2010
+ 2005, 2006, 2007, 2008, 2009, 2010, 2011
National Institute of Advanced Industrial Science and Technology (AIST)
Registration Number H14PRO021
Copyright (C) 2003
while (1)
{
- /* Get one byte from the source. If the souce is exausted, jump
+ /* Get one byte from the source. If the source is exhausted, jump
to no_more_source:. */
ONE_MORE_BYTE (c);
return 0;
no_more_source:
- /* The source exausted successfully. */
+ /* The source exhausted successfully. */
detect_info->found |= found;
return 1;
}
symbol as a coding system. */
static Lisp_Object Qcoding_system_define_form;
-int coding_system_require_warning;
-
-Lisp_Object Vselect_safe_coding_system_function;
-
-/* Mnemonic string for each format of end-of-line. */
-Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac;
-/* Mnemonic string to indicate format of end-of-line is not yet
- decided. */
-Lisp_Object eol_mnemonic_undecided;
-
/* Format of end-of-line decided by system. This is Qunix on
Unix and Mac, Qdos on DOS/Windows.
This has an effect only for external encoding (i.e. for output to
#ifdef emacs
-Lisp_Object Vcoding_system_list, Vcoding_system_alist;
-
Lisp_Object Qcoding_system_p, Qcoding_system_error;
/* Coding system emacs-mule and raw-text are for converting only
/* Coding-systems are handed between Emacs Lisp programs and C internal
routines by the following three variables. */
-/* Coding-system for reading files and receiving data from process. */
-Lisp_Object Vcoding_system_for_read;
-/* Coding-system for writing files and sending data to process. */
-Lisp_Object Vcoding_system_for_write;
-/* Coding-system actually used in the latest I/O. */
-Lisp_Object Vlast_coding_system_used;
-/* Set to non-nil when an error is detected while code conversion. */
-Lisp_Object Vlast_code_conversion_error;
-/* A vector of length 256 which contains information about special
- Latin codes (especially for dealing with Microsoft codes). */
-Lisp_Object Vlatin_extra_code_table;
-
-/* Flag to inhibit code conversion of end-of-line format. */
-int inhibit_eol_conversion;
-
-/* Flag to inhibit ISO2022 escape sequence detection. */
-int inhibit_iso_escape_detection;
-
-/* Flag to inhibit detection of binary files through null bytes. */
-int inhibit_null_byte_detection;
-
-/* Flag to make buffer-file-coding-system inherit from process-coding. */
-int inherit_process_coding_system;
-
/* Coding system to be used to encode text for terminal display when
terminal coding system is nil. */
struct coding_system safe_terminal_coding;
-Lisp_Object Vfile_coding_system_alist;
-Lisp_Object Vprocess_coding_system_alist;
-Lisp_Object Vnetwork_coding_system_alist;
-
-Lisp_Object Vlocale_coding_system;
-
#endif /* emacs */
-/* Flag to tell if we look up translation table on character code
- conversion. */
-Lisp_Object Venable_character_translation;
-/* Standard translation table to look up on decoding (reading). */
-Lisp_Object Vstandard_translation_table_for_decode;
-/* Standard translation table to look up on encoding (writing). */
-Lisp_Object Vstandard_translation_table_for_encode;
-
Lisp_Object Qtranslation_table;
Lisp_Object Qtranslation_table_id;
Lisp_Object Qtranslation_table_for_decode;
Lisp_Object Qtranslation_table_for_encode;
-/* Alist of charsets vs revision number. */
-static Lisp_Object Vcharset_revision_table;
-
-/* Default coding systems used for process I/O. */
-Lisp_Object Vdefault_process_coding_system;
-
-/* Char table for translating Quail and self-inserting input. */
-Lisp_Object Vtranslation_table_for_input;
-
/* Two special coding systems. */
Lisp_Object Vsjis_coding_system;
Lisp_Object Vbig5_coding_system;
/* Control characters of ISO2022. */
/* code */ /* function */
-#define ISO_CODE_LF 0x0A /* line-feed */
-#define ISO_CODE_CR 0x0D /* carriage-return */
#define ISO_CODE_SO 0x0E /* shift-out */
#define ISO_CODE_SI 0x0F /* shift-in */
#define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */
on output. */
#define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400
-/* If set, do not encode unsafe charactes on output. */
+/* If set, do not encode unsafe characters on output. */
#define CODING_ISO_FLAG_SAFE 0x0800
/* If set, extra latin codes (128..159) are accepted as a valid code
#define CODING_ISO_FLAG_COMPOSITION 0x2000
-#define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000
+/* #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 */
#define CODING_ISO_FLAG_USE_ROMAN 0x8000
| 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. */
-static Lisp_Object Vcoding_category_list;
-
/* Table of coding categories (Lisp symbols). This variable is for
- internal use oly. */
+ internal use only. */
static Lisp_Object Vcoding_category_table;
/* Table of coding-categories ordered by priority. */
} while (0)
-#define ONE_MORE_BYTE_NO_CHECK(c) \
- do { \
- c = *src++; \
- if (multibytep && (c & 0x80)) \
- { \
- if ((c & 0xFE) == 0xC0) \
- c = ((c & 1) << 6) | *src++; \
- else \
- { \
- src--; \
- c = - string_char (src, &src, NULL); \
- record_conversion_result \
- (coding, CODING_RESULT_INVALID_SRC); \
- } \
- } \
- consumed_chars++; \
- } while (0)
-
-
/* Store a byte C in the place pointed by DST and increment DST to the
next free point, and increment PRODUCED_CHARS. The caller should
assure that C is 0..127, and declare and set the variable `dst'
} while (0)
-/* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */
+/* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */
#define EMIT_TWO_ASCII_BYTES(c1, c2) \
do { \
EMACS_INT, unsigned char *);
static void setup_iso_safe_charsets (Lisp_Object);
static unsigned char *encode_designation_at_bol (struct coding_system *,
- int *, int *,
- unsigned char *);
+ int *, unsigned char *);
static int detect_eol (const unsigned char *,
EMACS_INT, enum coding_category);
static Lisp_Object adjust_coding_eol_type (struct coding_system *, int);
coding->source = SDATA (coding->src_object) + coding->src_pos_byte;
}
else
- /* Otherwise, the source is C string and is never relocated
- automatically. Thus we don't have to update anything. */
- ;
+ {
+ /* Otherwise, the source is C string and is never relocated
+ automatically. Thus we don't have to update anything. */
+ }
}
static void
}
}
else
- /* Otherwise, the destination is C string and is never relocated
- automatically. Thus we don't have to update anything. */
- ;
+ {
+ /* Otherwise, the destination is C string and is never relocated
+ automatically. Thus we don't have to update anything. */
+ }
}
METHOD is one of enum composition_method.
- Optionnal COMPOSITION-COMPONENTS are characters and composition
+ Optional COMPOSITION-COMPONENTS are characters and composition
rules.
In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID
#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
int multibytep = coding->src_multibyte;
enum utf_bom_type bom = CODING_UTF_8_BOM (coding);
Lisp_Object attr, charset_list;
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
}
else if (UTF_8_1_OCTET_P (c1))
{
- if (eol_crlf && c1 == '\r')
+ if (eol_dos && c1 == '\r')
ONE_MORE_BYTE (byte_after_cr);
c = c1;
}
#define UTF_16_LOW_SURROGATE_P(val) \
(((val) & 0xFC00) == 0xDC00)
-#define UTF_16_INVALID_P(val) \
- (((val) == 0xFFFE) \
- || ((val) == 0xFFFF) \
- || UTF_16_LOW_SURROGATE_P (val))
-
static int
detect_coding_utf_16 (struct coding_system *coding,
struct coding_detection_info *detect_info)
{
- const unsigned char *src = coding->source, *src_base = src;
+ const unsigned char *src = coding->source;
const unsigned char *src_end = coding->source + coding->src_bytes;
int multibytep = coding->src_multibyte;
- int consumed_chars = 0;
int c1, c2;
detect_info->checked |= CATEGORY_MASK_UTF_16;
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 =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr1 = -1, byte_after_cr2 = -1;
CODING_UTF_16_SURROGATE (coding) = surrogate = c;
else
{
- if (eol_crlf && c == '\r')
+ if (eol_dos && c == '\r')
{
ONE_MORE_BYTE (byte_after_cr1);
ONE_MORE_BYTE (byte_after_cr2);
CHARS is 0xA0 plus a number of characters composed by this
data,
- COMPONENTs are characters of multibye form or composition
+ COMPONENTs are characters of multibyte form or composition
rules encoded by two-byte of ASCII codes.
In addition, for backward compatibility, the following formats are
it because analyzing it is too heavy for detecting. But,
at least, we check that the composite character
constitutes of more than 4 bytes. */
- const unsigned char *src_base;
+ const unsigned char *src_start;
repeat:
- src_base = src;
+ src_start = src;
do
{
ONE_MORE_BYTE (c);
}
while (c >= 0xA0);
- if (src - src_base <= 4)
+ if (src - src_start <= 4)
break;
found = CATEGORY_MASK_EMACS_MULE;
if (c == 0x80)
}
else
{
- int more_bytes = emacs_mule_bytes[*src_base] - 1;
+ int more_bytes = emacs_mule_bytes[c] - 1;
while (more_bytes > 0)
{
the decoded character or rule. If an invalid byte is found, return
-1. If SRC is too short, return -2. */
-int
+static int
emacs_mule_char (struct coding_system *coding, const unsigned char *src,
int *nbytes, int *nchars, int *id,
struct composition_status *cmp_status)
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base = src;
int multibytep = coding->src_multibyte;
- struct charset *charset;
+ int charset_ID;
unsigned code;
int c;
int consumed_chars = 0;
if (c < 0)
{
c = -c;
- charset = emacs_mule_charset[0];
+ charset_ID = emacs_mule_charset[0];
}
else
{
switch (emacs_mule_bytes[c])
{
case 2:
- if (! (charset = emacs_mule_charset[c]))
+ if ((charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
|| c == EMACS_MULE_LEADING_CODE_PRIVATE_12)
{
ONE_MORE_BYTE (c);
- if (c < 0xA0 || ! (charset = emacs_mule_charset[c]))
+ if (c < 0xA0 || (charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
}
else
{
- if (! (charset = emacs_mule_charset[c]))
+ if ((charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
case 4:
ONE_MORE_BYTE (c);
- if (c < 0 || ! (charset = emacs_mule_charset[c]))
+ if (c < 0 || (charset_ID = emacs_mule_charset[c]) < 0)
goto invalid_code;
ONE_MORE_BYTE (c);
if (c < 0xA0)
case 1:
code = c;
- charset = CHARSET_FROM_ID (ASCII_BYTE_P (code)
- ? charset_ascii : charset_eight_bit);
+ charset_ID = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit;
break;
default:
abort ();
}
- CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, code, c);
+ CODING_DECODE_CHAR (coding, src, src_base, src_end,
+ CHARSET_FROM_ID (charset_ID), code, c);
if (c < 0)
goto invalid_code;
}
*nbytes = src - src_base;
*nchars = consumed_chars;
if (id)
- *id = charset->id;
+ *id = charset_ID;
return (mseq_found ? -c : c);
no_more_source:
#define DECODE_EMACS_MULE_21_COMPOSITION() \
do { \
enum composition_method method = c - 0xF2; \
- int *charbuf_base = charbuf; \
int nbytes, nchars; \
\
ONE_MORE_BYTE (c); \
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
- /* We may produce two annocations (charset and composition) in one
- loop and one more charset annocation at the end. */
+ /* We may produce two annotations (charset and composition) in one
+ loop and one more charset annotation at the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3);
int consumed_chars = 0, consumed_chars_base;
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status;
while (1)
{
- int c, id;
+ int c, id IF_LINT (= 0);
src_base = src;
consumed_chars_base = consumed_chars;
if (c < 0x80)
{
- if (eol_crlf && c == '\r')
+ if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
id = charset_ascii;
if (cmp_status->state != COMPOSING_NO)
}
else
{
- int nchars, nbytes;
+ int nchars IF_LINT (= 0), nbytes IF_LINT (= 0);
/* emacs_mule_char can load a charset map from a file, which
allocates a large structure and might cause buffer text
to be relocated as result. Thus, we need to remember the
- original pointer to buffer text, and fixup all related
+ original pointer to buffer text, and fix up all related
pointers after the call. */
const unsigned char *orig = coding->source;
EMACS_INT offset;
cmp_status->ncomps -= nchars;
}
- /* Now if C >= 0, we found a normally encoded characer, if C <
+ /* Now if C >= 0, we found a normally encoded character, if C <
0, we found an old-style composition component character or
rule. */
}
continue;
- retry:
- src = src_base;
- consumed_chars = consumed_chars_base;
- continue;
-
invalid_code:
EMACS_MULE_MAYBE_FINISH_COMPOSITION ();
src = src_base;
((id) <= (coding)->max_charset_id \
&& (coding)->safe_charsets[id] != 255)
-
-#define SHIFT_OUT_OK(category) \
- (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0)
-
static void
setup_iso_safe_charsets (Lisp_Object attrs)
{
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
- Check if a text is encoded in one of ISO-2022 based codig systems.
+ Check if a text is encoded in one of ISO-2022 based coding systems.
If it is, return 1, else return 0. */
static int
break;
single_shifting = 0;
ONE_MORE_BYTE (c);
- if (c >= '(' && c <= '/')
- {
- /* Designation sequence for a charset of dimension 1. */
- ONE_MORE_BYTE (c1);
- if (c1 < ' ' || c1 >= 0x80
- || (id = iso_charset_table[0][c >= ','][c1]) < 0)
- /* Invalid designation sequence. Just ignore. */
- break;
- }
- else if (c == '$')
- {
- /* Designation sequence for a charset of dimension 2. */
- ONE_MORE_BYTE (c);
- if (c >= '@' && c <= 'B')
- /* Designation for JISX0208.1978, GB2312, or JISX0208. */
- id = iso_charset_table[1][0][c];
- else if (c >= '(' && c <= '/')
- {
- ONE_MORE_BYTE (c1);
- if (c1 < ' ' || c1 >= 0x80
- || (id = iso_charset_table[1][c >= ','][c1]) < 0)
- /* Invalid designation sequence. Just ignore. */
- break;
- }
- else
- /* Invalid designation sequence. Just ignore it. */
- break;
- }
- else if (c == 'N' || c == 'O')
+ if (c == 'N' || c == 'O')
{
/* ESC <Fe> for SS2 or SS3. */
single_shifting = 1;
rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT;
- break;
}
else if (c == '1')
{
{
/* ESC <Fp> for start/end composition. */
composition_count = 0;
- break;
}
else
{
- /* Invalid escape sequence. Just ignore it. */
- break;
- }
+ if (c >= '(' && c <= '/')
+ {
+ /* Designation sequence for a charset of dimension 1. */
+ ONE_MORE_BYTE (c1);
+ if (c1 < ' ' || c1 >= 0x80
+ || (id = iso_charset_table[0][c >= ','][c1]) < 0)
+ /* Invalid designation sequence. Just ignore. */
+ break;
+ }
+ else if (c == '$')
+ {
+ /* Designation sequence for a charset of dimension 2. */
+ ONE_MORE_BYTE (c);
+ if (c >= '@' && c <= 'B')
+ /* Designation for JISX0208.1978, GB2312, or JISX0208. */
+ id = iso_charset_table[1][0][c];
+ else if (c >= '(' && c <= '/')
+ {
+ ONE_MORE_BYTE (c1);
+ if (c1 < ' ' || c1 >= 0x80
+ || (id = iso_charset_table[1][c >= ','][c1]) < 0)
+ /* Invalid designation sequence. Just ignore. */
+ break;
+ }
+ else
+ /* Invalid designation sequence. Just ignore it. */
+ break;
+ }
+ else
+ {
+ /* Invalid escape sequence. Just ignore it. */
+ break;
+ }
- /* We found a valid designation sequence for CHARSET. */
- rejected |= CATEGORY_MASK_ISO_8BIT;
- if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7],
- id))
- found |= CATEGORY_MASK_ISO_7;
- else
- rejected |= CATEGORY_MASK_ISO_7;
- if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight],
- id))
- found |= CATEGORY_MASK_ISO_7_TIGHT;
- else
- rejected |= CATEGORY_MASK_ISO_7_TIGHT;
- if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else],
- id))
- found |= CATEGORY_MASK_ISO_7_ELSE;
- else
- rejected |= CATEGORY_MASK_ISO_7_ELSE;
- if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else],
- id))
- found |= CATEGORY_MASK_ISO_8_ELSE;
- else
- rejected |= CATEGORY_MASK_ISO_8_ELSE;
+ /* We found a valid designation sequence for CHARSET. */
+ rejected |= CATEGORY_MASK_ISO_8BIT;
+ if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7],
+ id))
+ found |= CATEGORY_MASK_ISO_7;
+ else
+ rejected |= CATEGORY_MASK_ISO_7;
+ if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight],
+ id))
+ found |= CATEGORY_MASK_ISO_7_TIGHT;
+ else
+ rejected |= CATEGORY_MASK_ISO_7_TIGHT;
+ if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else],
+ id))
+ found |= CATEGORY_MASK_ISO_7_ELSE;
+ else
+ rejected |= CATEGORY_MASK_ISO_7_ELSE;
+ if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else],
+ id))
+ found |= CATEGORY_MASK_ISO_8_ELSE;
+ else
+ rejected |= CATEGORY_MASK_ISO_8_ELSE;
+ }
break;
case ISO_CODE_SO:
rejected |= CATEGORY_MASK_ISO_7BIT;
if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
& CODING_ISO_FLAG_SINGLE_SHIFT)
- found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1;
+ {
+ found |= CATEGORY_MASK_ISO_8_1;
+ single_shifting = 1;
+ }
if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2])
& CODING_ISO_FLAG_SINGLE_SHIFT)
- found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1;
+ {
+ found |= CATEGORY_MASK_ISO_8_2;
+ single_shifting = 1;
+ }
if (single_shifting)
break;
- goto check_extra_latin;
+ check_extra_latin:
+ if (! VECTORP (Vlatin_extra_code_table)
+ || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))
+ {
+ rejected = CATEGORY_MASK_ISO;
+ break;
+ }
+ if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
+ & CODING_ISO_FLAG_LATIN_EXTRA)
+ found |= CATEGORY_MASK_ISO_8_1;
+ else
+ rejected |= CATEGORY_MASK_ISO_8_1;
+ rejected |= CATEGORY_MASK_ISO_8_2;
+ break;
default:
if (c < 0)
if (! single_shifting
&& ! (rejected & CATEGORY_MASK_ISO_8_2))
{
- int i = 1;
+ int len = 1;
while (src < src_end)
{
src_base = src;
src = src_base;
break;
}
- i++;
+ len++;
}
- if (i & 1 && src < src_end)
+ if (len & 1 && src < src_end)
{
rejected |= CATEGORY_MASK_ISO_8_2;
if (composition_count >= 0)
- composition_count += i;
+ composition_count += len;
}
else
{
found |= CATEGORY_MASK_ISO_8_2;
if (composition_count >= 0)
- composition_count += i / 2;
+ composition_count += len / 2;
}
}
break;
}
- check_extra_latin:
- single_shifting = 0;
- if (! VECTORP (Vlatin_extra_code_table)
- || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))
- {
- rejected = CATEGORY_MASK_ISO;
- break;
- }
- if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
- & CODING_ISO_FLAG_LATIN_EXTRA)
- found |= CATEGORY_MASK_ISO_8_1;
- else
- rejected |= CATEGORY_MASK_ISO_8_1;
- rejected |= CATEGORY_MASK_ISO_8_2;
}
}
detect_info->rejected |= CATEGORY_MASK_ISO;
} \
else /* new format (after ver.21) */ \
{ \
- int c; \
+ int b; \
\
- ONE_MORE_BYTE (c); \
- rule = COMPOSITION_ENCODE_RULE (rule - 81, c - 32); \
+ ONE_MORE_BYTE (b); \
+ rule = COMPOSITION_ENCODE_RULE (rule - 81, b - 32); \
if (rule >= 0) \
rule += 0x100; /* to destinguish it from the old format */ \
nbytes = 2; \
return new_chars;
}
-/* If characers are under composition, finish the composition. */
+/* If characters are under composition, finish the composition. */
#define MAYBE_FINISH_COMPOSITION() \
do { \
if (cmp_status->state != COMPOSING_NO) \
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
- /* We may produce two annocations (charset and composition) in one
- loop and one more charset annocation at the end. */
+ /* We may produce two annotations (charset and composition) in one
+ loop and one more charset annotation at the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3);
int consumed_chars = 0, consumed_chars_base;
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
int i;
break;
case ISO_control_0:
- if (eol_crlf && c1 == '\r')
+ if (eol_dos && c1 == '\r')
ONE_MORE_BYTE (byte_after_cr);
MAYBE_FINISH_COMPOSITION ();
charset = CHARSET_FROM_ID (charset_ascii);
goto invalid_code;
/* For the moment, nested direction is not supported.
So, `coding->mode & CODING_MODE_DIRECTION' zero means
- left-to-right, and nozero means right-to-left. */
+ left-to-right, and nonzero means right-to-left. */
ONE_MORE_BYTE (c1);
switch (c1)
{
int size;
ONE_MORE_BYTE (dim);
- if (dim < 0 || dim > 4)
+ if (dim < '0' || dim > '4')
goto invalid_code;
ONE_MORE_BYTE (M);
if (M < 128)
}
continue;
}
+ break;
+
+ default:
+ abort ();
}
if (cmp_status->state == COMPOSING_NO
const char *intermediate_char_94 = "()*+"; \
const char *intermediate_char_96 = ",-./"; \
int revision = -1; \
- int c; \
\
if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \
revision = CHARSET_ISO_REVISION (charset); \
EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \
if (CHARSET_DIMENSION (charset) == 1) \
{ \
+ int b; \
if (! CHARSET_ISO_CHARS_96 (charset)) \
- c = intermediate_char_94[reg]; \
+ b = intermediate_char_94[reg]; \
else \
- c = intermediate_char_96[reg]; \
- EMIT_ONE_ASCII_BYTE (c); \
+ b = intermediate_char_96[reg]; \
+ EMIT_ONE_ASCII_BYTE (b); \
} \
else \
{ \
to use CHARSET. The element `spec.iso_2022' of *CODING is updated.
Return new DST. */
-unsigned char *
+static unsigned char *
encode_invocation_designation (struct charset *charset,
struct coding_system *coding,
unsigned char *dst, int *p_nchars)
return dst;
}
-/* The following three macros produce codes for indicating direction
- of text. */
-#define ENCODE_CONTROL_SEQUENCE_INTRODUCER \
- do { \
- if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \
- EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \
- else \
- EMIT_ONE_BYTE (ISO_CODE_CSI); \
- } while (0)
-
-
-#define ENCODE_DIRECTION_R2L() \
- do { \
- ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \
- EMIT_TWO_ASCII_BYTES ('2', ']'); \
- } while (0)
-
-
-#define ENCODE_DIRECTION_L2R() \
- do { \
- ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \
- EMIT_TWO_ASCII_BYTES ('0', ']'); \
- } while (0)
-
/* Produce codes for designation and invocation to reset the graphic
planes and registers to initial state. */
static unsigned char *
encode_designation_at_bol (struct coding_system *coding, int *charbuf,
- int *charbuf_end, unsigned char *dst)
+ unsigned char *dst)
{
struct charset *charset;
/* Table of charsets to be designated to each graphic register. */
charset_list = CODING_ATTR_CHARSET_LIST (attrs);
coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs));
- ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs));
+ ascii_compatible
+ = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))
+ && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION
+ | CODING_ISO_FLAG_LOCKING_SHIFT)));
while (charbuf < charbuf_end)
{
unsigned char *dst_prev = dst;
/* We have to produce designation sequences if any now. */
- dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst);
+ dst = encode_designation_at_bol (coding, charbuf, dst);
bol_designation = 0;
/* We are sure that designation sequences are all ASCII bytes. */
produced_chars += dst - dst_prev;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
- /* We may produce one charset annocation in one loop and one more at
+ /* We may produce one charset annotation in one loop and one more at
the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2);
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
goto invalid_code;
if (c < 0x80)
{
- if (eol_crlf && c == '\r')
+ if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
charset = charset_roman;
}
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
- /* We may produce one charset annocation in one loop and one more at
+ /* We may produce one charset annotation in one loop and one more at
the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2);
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
goto invalid_code;
if (c < 0x80)
{
- if (eol_crlf && c == '\r')
+ if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
charset = charset_roman;
}
static void
decode_coding_raw_text (struct coding_system *coding)
{
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
coding->chars_at_source = 1;
coding->consumed_char = coding->src_chars;
coding->consumed = coding->src_bytes;
- if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r')
+ if (eol_dos && coding->source[coding->src_bytes - 1] == '\r')
{
coding->consumed_char--;
coding->consumed--;
unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str;
CHAR_STRING_ADVANCE (c, p1);
- while (p0 < p1)
+ do
{
EMIT_ONE_BYTE (*p0);
p0++;
}
+ while (p0 < p1);
}
}
else
attrs = CODING_ID_ATTRS (coding->id);
valids = AREF (attrs, coding_attr_charset_valids);
name = CODING_ID_NAME (coding->id);
- if (strncmp ((char *) SDATA (SYMBOL_NAME (name)),
+ if (strncmp (SSDATA (SYMBOL_NAME (name)),
"iso-8859-", sizeof ("iso-8859-") - 1) == 0
- || strncmp ((char *) SDATA (SYMBOL_NAME (name)),
+ || strncmp (SSDATA (SYMBOL_NAME (name)),
"iso-latin-", sizeof ("iso-latin-") - 1) == 0)
check_latin_extra = 1;
const unsigned char *src_end = coding->source + coding->src_bytes;
const unsigned char *src_base;
int *charbuf = coding->charbuf + coding->charbuf_used;
- /* We may produce one charset annocation in one loop and one more at
+ /* We may produce one charset annotation in one loop and one more at
the end. */
int *charbuf_end
= coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2);
int char_offset = coding->produced_char;
int last_offset = char_offset;
int last_id = charset_ascii;
- int eol_crlf =
+ int eol_dos =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
int byte_after_cr = -1;
else
{
ONE_MORE_BYTE (c);
- if (eol_crlf && c == '\r')
+ if (eol_dos && c == '\r')
ONE_MORE_BYTE (byte_after_cr);
}
if (c < 0)
}
-/* If CODING_SYSTEM doesn't specify end-of-line format but PARENT
- does, return one of the subsidiary that has the same eol-spec as
- PARENT. Otherwise, return CODING_SYSTEM. If PARENT is nil,
- inherit end-of-line format from the system's setting
+/* If CODING_SYSTEM doesn't specify end-of-line format, return one of
+ the subsidiary that has the same eol-spec as PARENT (if it is not
+ nil and specifies end-of-line format) or the system's setting
(system_eol_type). */
Lisp_Object
parent_spec = CODING_SYSTEM_SPEC (parent);
parent_eol_type = AREF (parent_spec, 2);
+ if (VECTORP (parent_eol_type))
+ parent_eol_type = system_eol_type;
}
else
parent_eol_type = system_eol_type;
return coding_system;
}
+
+/* Check if text-conversion and eol-conversion of CODING_SYSTEM are
+ decided for writing to a process. If not, complement them, and
+ return a new coding system. */
+
+Lisp_Object
+complement_process_encoding_system (Lisp_Object coding_system)
+{
+ Lisp_Object coding_base = Qnil, eol_base = Qnil;
+ Lisp_Object spec, attrs;
+ int i;
+
+ for (i = 0; i < 3; i++)
+ {
+ if (i == 1)
+ coding_system = CDR_SAFE (Vdefault_process_coding_system);
+ else if (i == 2)
+ coding_system = preferred_coding_system ();
+ spec = CODING_SYSTEM_SPEC (coding_system);
+ if (NILP (spec))
+ continue;
+ attrs = AREF (spec, 0);
+ if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided))
+ coding_base = CODING_ATTR_BASE_NAME (attrs);
+ if (NILP (eol_base) && ! VECTORP (AREF (spec, 2)))
+ eol_base = coding_system;
+ if (! NILP (coding_base) && ! NILP (eol_base))
+ break;
+ }
+
+ if (i > 0)
+ /* The original CODING_SYSTEM didn't specify text-conversion or
+ eol-conversion. Be sure that we return a fully complemented
+ coding system. */
+ coding_system = coding_inherit_eol_type (coding_base, eol_base);
+ return coding_system;
+}
+
+
/* Emacs has a mechanism to automatically detect a coding system if it
is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But,
it's impossible to distinguish some coding systems accurately
o coding-category-iso-7-else
The category for a coding system which has the same code range
- as ISO2022 of 7-bit environemnt but uses locking shift or
+ as ISO2022 of 7-bit environment but uses locking shift or
single shift functions. Assigned the coding-system (Lisp
symbol) `iso-2022-7bit-lock' by default.
o coding-category-iso-8-else
The category for a coding system which has the same code range
- as ISO2022 of 8-bit environemnt but uses locking shift or
+ as ISO2022 of 8-bit environment but uses locking shift or
single shift functions. Assigned the coding-system (Lisp
symbol) `iso-2022-8bit-ss2' by default.
{
/* The found type is different from what found before.
Allow for stray ^M characters in DOS EOL files. */
- if (eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF
- || eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)
+ if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF)
+ || (eol_seen == EOL_SEEN_CRLF
+ && this_eol == EOL_SEEN_CR))
eol_seen = EOL_SEEN_CRLF;
else
{
}
}
else
- {
- while (src < src_end)
- {
- c = *src++;
- if (c == '\n' || c == '\r')
- {
- int this_eol;
+ while (src < src_end)
+ {
+ c = *src++;
+ if (c == '\n' || c == '\r')
+ {
+ int this_eol;
- if (c == '\n')
- this_eol = EOL_SEEN_LF;
- else if (src >= src_end || *src != '\n')
- this_eol = EOL_SEEN_CR;
- else
- this_eol = EOL_SEEN_CRLF, src++;
+ if (c == '\n')
+ this_eol = EOL_SEEN_LF;
+ else if (src >= src_end || *src != '\n')
+ this_eol = EOL_SEEN_CR;
+ else
+ this_eol = EOL_SEEN_CRLF, src++;
- if (eol_seen == EOL_SEEN_NONE)
- /* This is the first end-of-line. */
- eol_seen = this_eol;
- else if (eol_seen != this_eol)
- {
- /* The found type is different from what found before.
- Allow for stray ^M characters in DOS EOL files. */
- if (eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF
- || eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)
- eol_seen = EOL_SEEN_CRLF;
- else
- {
- eol_seen = EOL_SEEN_LF;
- break;
- }
- }
- if (++total == MAX_EOL_CHECK_COUNT)
- break;
- }
- }
- }
+ if (eol_seen == EOL_SEEN_NONE)
+ /* This is the first end-of-line. */
+ eol_seen = this_eol;
+ else if (eol_seen != this_eol)
+ {
+ /* The found type is different from what found before.
+ Allow for stray ^M characters in DOS EOL files. */
+ if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF)
+ || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR))
+ eol_seen = EOL_SEEN_CRLF;
+ else
+ {
+ eol_seen = EOL_SEEN_LF;
+ break;
+ }
+ }
+ if (++total == MAX_EOL_CHECK_COUNT)
+ break;
+ }
+ }
return eol_seen;
}
}
else if (CONSP (translation_table))
{
- Lisp_Object tail, val;
+ Lisp_Object tail;
for (tail = translation_table; CONSP (tail); tail = XCDR (tail))
if (CHAR_TABLE_P (XCAR (tail))
&& CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1)
{
- val = XCHAR_TABLE (XCAR (tail))->extras[1];
- if (NATNUMP (val) && *max_lookup < XFASTINT (val))
- *max_lookup = XFASTINT (val);
+ Lisp_Object tailval = XCHAR_TABLE (XCAR (tail))->extras[1];
+ if (NATNUMP (tailval) && *max_lookup < XFASTINT (tailval))
+ *max_lookup = XFASTINT (tailval);
}
}
}
set_buffer_internal (XBUFFER (coding->dst_object));
if (GPT != PT)
move_gap_both (PT, PT_BYTE);
- undo_list = current_buffer->undo_list;
- current_buffer->undo_list = Qt;
+ undo_list = BVAR (current_buffer, undo_list);
+ BVAR (current_buffer, undo_list) = Qt;
}
coding->consumed = coding->consumed_char = 0;
decode_eol (coding);
if (BUFFERP (coding->dst_object))
{
- current_buffer->undo_list = undo_list;
+ BVAR (current_buffer, undo_list) = undo_list;
record_insert (coding->dst_pos, coding->produced_char);
}
return coding->result;
{
set_buffer_internal (XBUFFER (coding->dst_object));
coding->dst_multibyte
- = ! NILP (current_buffer->enable_multibyte_characters);
+ = ! NILP (BVAR (current_buffer, enable_multibyte_characters));
}
coding->consumed = coding->consumed_char = 0;
static int reused_workbuf_in_use;
-/* Return a working buffer of code convesion. MULTIBYTE specifies the
+/* Return a working buffer of code conversion. MULTIBYTE specifies the
multibyteness of returning buffer. */
static Lisp_Object
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;
+ BVAR (current_buffer, undo_list) = Qt;
+ BVAR (current_buffer, enable_multibyte_characters) = multibyte ? Qt : Qnil;
set_buffer_internal (current);
return workbuf;
}
coding->dst_object = coding->src_object;
coding->dst_pos = PT;
coding->dst_pos_byte = PT_BYTE;
- coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters);
+ coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters));
if (CODING_REQUIRE_DETECTION (coding))
detect_coding (coding);
Lisp_Object dst_object)
{
int count = SPECPDL_INDEX ();
- unsigned char *destination;
- EMACS_INT dst_bytes;
+ unsigned char *destination IF_LINT (= NULL);
+ EMACS_INT dst_bytes IF_LINT (= 0);
EMACS_INT chars = to - from;
EMACS_INT bytes = to_byte - from_byte;
Lisp_Object attrs;
- int saved_pt = -1, saved_pt_byte;
+ int saved_pt = -1, saved_pt_byte IF_LINT (= 0);
int need_marker_adjustment = 0;
Lisp_Object old_deactivate_mark;
coding->dst_pos = BUF_PT (XBUFFER (dst_object));
coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object));
coding->dst_multibyte
- = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters);
+ = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters));
}
else
{
TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte);
else if (saved_pt < from + chars)
TEMP_SET_PT_BOTH (from, from_byte);
- else if (! NILP (current_buffer->enable_multibyte_characters))
+ else if (! NILP (BVAR (current_buffer, enable_multibyte_characters)))
TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars),
saved_pt_byte + (coding->produced - bytes));
else
{
tail->bytepos = from_byte + coding->produced;
tail->charpos
- = (NILP (current_buffer->enable_multibyte_characters)
+ = (NILP (BVAR (current_buffer, enable_multibyte_characters))
? tail->bytepos : from + coding->produced_char);
}
}
EMACS_INT chars = to - from;
EMACS_INT bytes = to_byte - from_byte;
Lisp_Object attrs;
- int saved_pt = -1, saved_pt_byte;
+ int saved_pt = -1, saved_pt_byte IF_LINT (= 0);
int need_marker_adjustment = 0;
int kill_src_buffer = 0;
Lisp_Object old_deactivate_mark;
else if (BUFFERP (src_object))
insert_from_buffer (XBUFFER (src_object), from, chars, 0);
else
- insert_1_both (coding->source + from, chars, bytes, 0, 0, 0);
+ insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0);
if (EQ (src_object, dst_object))
{
set_buffer_temp (current);
}
coding->dst_multibyte
- = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters);
+ = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters));
}
else if (EQ (dst_object, Qt))
{
TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte);
else if (saved_pt < from + chars)
TEMP_SET_PT_BOTH (from, from_byte);
- else if (! NILP (current_buffer->enable_multibyte_characters))
+ else if (! NILP (BVAR (current_buffer, enable_multibyte_characters)))
TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars),
saved_pt_byte + (coding->produced - bytes));
else
{
tail->bytepos = from_byte + coding->produced;
tail->charpos
- = (NILP (current_buffer->enable_multibyte_characters)
+ = (NILP (BVAR (current_buffer, enable_multibyte_characters))
? tail->bytepos : from + coding->produced_char);
}
}
\f
/* Detect how the bytes at SRC of length SRC_BYTES are encoded. If
HIGHEST is nonzero, return the coding system of the highest
- priority among the detected coding systems. Otherwize return a
+ priority among the detected coding systems. Otherwise return a
list of detected coding systems sorted by their priorities. If
MULTIBYTEP is nonzero, it is assumed that the bytes are in correct
multibyte form but contains only ASCII and eight-bit chars.
base_category = XINT (CODING_ATTR_CATEGORY (attrs));
if (base_category == coding_category_undecided)
{
- enum coding_category category;
- struct coding_system *this;
+ enum coding_category category IF_LINT (= 0);
+ struct coding_system *this IF_LINT (= NULL);
int c, i;
/* Skip all ASCII bytes except for a few ISO2022 controls. */
return detect_coding_system (BYTE_POS_ADDR (from_byte),
to - from, to_byte - from_byte,
!NILP (highest),
- !NILP (current_buffer
- ->enable_multibyte_characters),
+ !NILP (BVAR (current_buffer
+ , enable_multibyte_characters)),
Qnil);
}
CHECK_NUMBER_COERCE_MARKER (end);
if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end))
args_out_of_range (start, end);
- if (NILP (current_buffer->enable_multibyte_characters))
+ if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
return Qt;
start_byte = CHAR_TO_BYTE (XINT (start));
end_byte = CHAR_TO_BYTE (XINT (end));
validate_region (&start, &end);
from = XINT (start);
to = XINT (end);
- if (NILP (current_buffer->enable_multibyte_characters)
+ if (NILP (BVAR (current_buffer, enable_multibyte_characters))
|| (ascii_compatible
&& (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from)))))
return Qnil;
CHECK_NUMBER_COERCE_MARKER (end);
if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end))
args_out_of_range (start, end);
- if (NILP (current_buffer->enable_multibyte_characters))
+ if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
return Qnil;
start_byte = CHAR_TO_BYTE (XINT (start));
end_byte = CHAR_TO_BYTE (XINT (end));
}
else
{
- int s1 = c >> 8, s2 = c & 0xFF;
+ int c1 = c >> 8, c2 = c & 0xFF;
- if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF
- || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC)
+ if (c1 < 0x81 || (c1 > 0x9F && c1 < 0xE0) || c1 > 0xEF
+ || c2 < 0x40 || c2 == 0x7F || c2 > 0xFC)
error ("Invalid code: %d", code);
SJIS_TO_JIS (c);
charset = charset_kanji;
doc: /* Internal use only. */)
(Lisp_Object coding_system, Lisp_Object terminal)
{
- struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1));
+ struct terminal *term = get_terminal (terminal, 1);
+ struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term);
CHECK_SYMBOL (coding_system);
setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding);
/* We had better not send unsafe characters to terminal. */
terminal_coding->mode |= CODING_MODE_SAFE_ENCODING;
- /* Characer composition should be disabled. */
+ /* Character composition should be disabled. */
terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK;
terminal_coding->src_multibyte = 1;
terminal_coding->dst_multibyte = 0;
+ if (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK)
+ term->charset_list = coding_charset_list (terminal_coding);
+ else
+ term->charset_list = Fcons (make_number (charset_ascii), Qnil);
return Qnil;
}
CHECK_SYMBOL (coding_system);
setup_coding_system (Fcheck_coding_system (coding_system),
&safe_terminal_coding);
- /* Characer composition should be disabled. */
+ /* Character composition should be disabled. */
safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK;
safe_terminal_coding.src_multibyte = 1;
safe_terminal_coding.dst_multibyte = 0;
else
Fcheck_coding_system (coding_system);
setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t));
- /* Characer composition should be disabled. */
+ /* Character composition should be disabled. */
TERMINAL_KEYBOARD_CODING (t)->common_flags
&= ~CODING_ANNOTATE_COMPOSITION_MASK;
return Qnil;
If Nth element is a list of charset IDs, N is the first byte
of one of them. The list is sorted by dimensions of the
- charsets. A charset of smaller dimension comes firtst. */
+ charsets. A charset of smaller dimension comes first. */
val = Fmake_vector (make_number (256), Qnil);
for (tail = charset_list; CONSP (tail); tail = XCDR (tail))
else if (EQ (coding_type, Qiso_2022))
{
Lisp_Object initial, reg_usage, request, flags;
- int i;
if (nargs < coding_arg_iso2022_max)
goto short_args;
for (tail = request; ! NILP (tail); tail = Fcdr (tail))
{
int id;
- Lisp_Object tmp;
+ Lisp_Object tmp1;
val = Fcar (tail);
CHECK_CONS (val);
- tmp = XCAR (val);
- CHECK_CHARSET_GET_ID (tmp, id);
+ tmp1 = XCAR (val);
+ CHECK_CHARSET_GET_ID (tmp1, id);
CHECK_NATNUM_CDR (val);
if (XINT (XCDR (val)) >= 4)
error ("Invalid graphic register number: %d", XINT (XCDR (val)));
defsubr (&Scoding_system_eol_type);
defsubr (&Scoding_system_priority_list);
- DEFVAR_LISP ("coding-system-list", &Vcoding_system_list,
+ DEFVAR_LISP ("coding-system-list", Vcoding_system_list,
doc: /* List of coding systems.
Do not alter the value of this variable manually. This variable should be
`define-coding-system-alias'. */);
Vcoding_system_list = Qnil;
- DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist,
+ 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 COLLECTION argument.
`define-coding-system-alias'. */);
Vcoding_system_alist = Qnil;
- DEFVAR_LISP ("coding-category-list", &Vcoding_category_list,
+ DEFVAR_LISP ("coding-category-list", Vcoding_category_list,
doc: /* List of coding-categories (symbols) ordered by priority.
On detecting a coding system, Emacs tries code detection algorithms
one algorithm agrees with a byte sequence of source text, the coding
system bound to the corresponding coding-category is selected.
-Don't modify this variable directly, but use `set-coding-priority'. */);
+Don't modify this variable directly, but use `set-coding-system-priority'. */);
{
int i;
Vcoding_category_list);
}
- DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read,
+ DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read,
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.
`process-coding-system-alist', and `network-coding-system-alist'. */);
Vcoding_system_for_read = Qnil;
- DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write,
+ DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write,
doc: /* Specify the coding system for write operations.
Programs bind this variable with `let', but you should not set it globally.
If the value is a coding system, it is used for encoding of output,
the value of `buffer-file-coding-system' is used. */);
Vcoding_system_for_write = Qnil;
- DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used,
+ DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used,
doc: /*
Coding system used in the latest file or process I/O. */);
Vlast_coding_system_used = Qnil;
- DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error,
+ DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error,
doc: /*
Error status of the last code conversion.
conversion. */);
Vlast_code_conversion_error = Qnil;
- DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion,
+ DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion,
doc: /*
*Non-nil means always inhibit code conversion of end-of-line format.
See info node `Coding Systems' and info node `Text and Binary' concerning
such conversion. */);
inhibit_eol_conversion = 0;
- DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system,
+ DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system,
doc: /*
Non-nil means process buffer inherits coding system of process output.
Bind it to t if the process output is to be treated as if it were a file
read from some filesystem. */);
inherit_process_coding_system = 0;
- DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist,
+ DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist,
doc: /*
Alist to decide a coding system to use for a file I/O operation.
The format is ((PATTERN . VAL) ...),
and the variable `auto-coding-alist'. */);
Vfile_coding_system_alist = Qnil;
- DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist,
+ DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist,
doc: /*
Alist to decide a coding system to use for a process I/O operation.
The format is ((PATTERN . VAL) ...),
See also the function `find-operation-coding-system'. */);
Vprocess_coding_system_alist = Qnil;
- DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist,
+ DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist,
doc: /*
Alist to decide a coding system to use for a network I/O operation.
The format is ((PATTERN . VAL) ...),
See also the function `find-operation-coding-system'. */);
Vnetwork_coding_system_alist = Qnil;
- DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system,
+ DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system,
doc: /* Coding system to use with system messages.
Also used for decoding keyboard input on X Window system. */);
Vlocale_coding_system = Qnil;
/* The eol mnemonics are reset in startup.el system-dependently. */
- DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix,
+ DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix,
doc: /*
*String displayed in mode line for UNIX-like (LF) end-of-line format. */);
eol_mnemonic_unix = make_pure_c_string (":");
- DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos,
+ DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos,
doc: /*
*String displayed in mode line for DOS-like (CRLF) end-of-line format. */);
eol_mnemonic_dos = make_pure_c_string ("\\");
- DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac,
+ DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac,
doc: /*
*String displayed in mode line for MAC-like (CR) end-of-line format. */);
eol_mnemonic_mac = make_pure_c_string ("/");
- DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided,
+ DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided,
doc: /*
*String displayed in mode line when end-of-line format is not yet determined. */);
eol_mnemonic_undecided = make_pure_c_string (":");
- DEFVAR_LISP ("enable-character-translation", &Venable_character_translation,
+ DEFVAR_LISP ("enable-character-translation", Venable_character_translation,
doc: /*
*Non-nil enables character translation while encoding and decoding. */);
Venable_character_translation = Qt;
DEFVAR_LISP ("standard-translation-table-for-decode",
- &Vstandard_translation_table_for_decode,
+ Vstandard_translation_table_for_decode,
doc: /* Table for translating characters while decoding. */);
Vstandard_translation_table_for_decode = Qnil;
DEFVAR_LISP ("standard-translation-table-for-encode",
- &Vstandard_translation_table_for_encode,
+ Vstandard_translation_table_for_encode,
doc: /* Table for translating characters while encoding. */);
Vstandard_translation_table_for_encode = Qnil;
- DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table,
+ DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table,
doc: /* Alist of charsets vs revision numbers.
While encoding, if a charset (car part of an element) is found,
designate it with the escape sequence identifying revision (cdr part
Vcharset_revision_table = Qnil;
DEFVAR_LISP ("default-process-coding-system",
- &Vdefault_process_coding_system,
+ Vdefault_process_coding_system,
doc: /* Cons of coding systems used for process I/O by default.
The car part is used for decoding a process output,
the cdr part is used for encoding a text to be sent to a process. */);
Vdefault_process_coding_system = Qnil;
- DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table,
+ DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table,
doc: /*
Table of extra Latin codes in the range 128..159 (inclusive).
This is a vector of length 256.
Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil);
DEFVAR_LISP ("select-safe-coding-system-function",
- &Vselect_safe_coding_system_function,
+ Vselect_safe_coding_system_function,
doc: /*
Function to call to select safe coding system for encoding a text.
Vselect_safe_coding_system_function = Qnil;
DEFVAR_BOOL ("coding-system-require-warning",
- &coding_system_require_warning,
+ coding_system_require_warning,
doc: /* Internal use only.
If non-nil, on writing a file, `select-safe-coding-system-function' is
called even if `coding-system-for-write' is non-nil. The command
DEFVAR_BOOL ("inhibit-iso-escape-detection",
- &inhibit_iso_escape_detection,
+ inhibit_iso_escape_detection,
doc: /*
If non-nil, Emacs ignores ISO-2022 escape sequences during code detection.
inhibit_iso_escape_detection = 0;
DEFVAR_BOOL ("inhibit-null-byte-detection",
- &inhibit_null_byte_detection,
+ inhibit_null_byte_detection,
doc: /* If non-nil, Emacs ignores null bytes on code detection.
By default, Emacs treats it as binary data, and does not attempt to
decode it. The effect is as if you specified `no-conversion' for
decode text as usual. */);
inhibit_null_byte_detection = 0;
- DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input,
+ 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'.
Lisp_Object dec = code_convert_string_norecord (build_string (str),
Vlocale_coding_system,
0);
- str = (char *) SDATA (dec);
+ str = SSDATA (dec);
}
return str;
}
#endif /* emacs */
-
-/* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d
- (do not change this comment) */
HCoop / bpt / emacs.git / blobdiff