/* Coding system handler (conversion, detection, etc).
Copyright (C) 2001, 2002, 2003, 2004, 2005,
- 2006, 2007, 2008, 2009 Free Software Foundation, Inc.
+ 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
- 2005, 2006, 2007, 2008, 2009
+ 2005, 2006, 2007, 2008, 2009, 2010
National Institute of Advanced Industrial Science and Technology (AIST)
Registration Number H14PRO021
Copyright (C) 2003
#include <config.h>
#include <stdio.h>
+#include <setjmp.h>
#include "lisp.h"
#include "buffer.h"
/* Prototypes for static functions. */
-static void record_conversion_result P_ ((struct coding_system *coding,
- enum coding_result_code result));
-static int detect_coding_utf_8 P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_utf_8 P_ ((struct coding_system *));
-static int encode_coding_utf_8 P_ ((struct coding_system *));
-
-static int detect_coding_utf_16 P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_utf_16 P_ ((struct coding_system *));
-static int encode_coding_utf_16 P_ ((struct coding_system *));
-
-static int detect_coding_iso_2022 P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_iso_2022 P_ ((struct coding_system *));
-static int encode_coding_iso_2022 P_ ((struct coding_system *));
-
-static int detect_coding_emacs_mule P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_emacs_mule P_ ((struct coding_system *));
-static int encode_coding_emacs_mule P_ ((struct coding_system *));
-
-static int detect_coding_sjis P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_sjis P_ ((struct coding_system *));
-static int encode_coding_sjis P_ ((struct coding_system *));
-
-static int detect_coding_big5 P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_big5 P_ ((struct coding_system *));
-static int encode_coding_big5 P_ ((struct coding_system *));
-
-static int detect_coding_ccl P_ ((struct coding_system *,
- struct coding_detection_info *info));
-static void decode_coding_ccl P_ ((struct coding_system *));
-static int encode_coding_ccl P_ ((struct coding_system *));
-
-static void decode_coding_raw_text P_ ((struct coding_system *));
-static int encode_coding_raw_text P_ ((struct coding_system *));
-
-static void coding_set_source P_ ((struct coding_system *));
-static void coding_set_destination P_ ((struct coding_system *));
-static void coding_alloc_by_realloc P_ ((struct coding_system *, EMACS_INT));
-static void coding_alloc_by_making_gap P_ ((struct coding_system *,
- EMACS_INT, EMACS_INT));
-static unsigned char *alloc_destination P_ ((struct coding_system *,
- EMACS_INT, unsigned char *));
-static void setup_iso_safe_charsets P_ ((Lisp_Object));
-static unsigned char *encode_designation_at_bol P_ ((struct coding_system *,
- int *, int *,
- unsigned char *));
-static int detect_eol P_ ((const unsigned char *,
- EMACS_INT, enum coding_category));
-static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int));
-static void decode_eol P_ ((struct coding_system *));
-static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *));
-static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *));
-static int produce_chars P_ ((struct coding_system *, Lisp_Object, int));
-static INLINE void produce_charset P_ ((struct coding_system *, int *,
- EMACS_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 *,
- int *, EMACS_INT *));
-static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT,
- struct coding_system *,
- int *, EMACS_INT *));
-static void consume_chars P_ ((struct coding_system *, Lisp_Object, int));
-static int encode_coding P_ ((struct coding_system *));
-static Lisp_Object make_conversion_work_buffer P_ ((int));
-static Lisp_Object code_conversion_restore P_ ((Lisp_Object));
-static INLINE int char_encodable_p P_ ((int, Lisp_Object));
-static Lisp_Object make_subsidiaries P_ ((Lisp_Object));
+static void record_conversion_result (struct coding_system *coding,
+ enum coding_result_code result);
+static int detect_coding_utf_8 (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_utf_8 (struct coding_system *);
+static int encode_coding_utf_8 (struct coding_system *);
+
+static int detect_coding_utf_16 (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_utf_16 (struct coding_system *);
+static int encode_coding_utf_16 (struct coding_system *);
+
+static int detect_coding_iso_2022 (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_iso_2022 (struct coding_system *);
+static int encode_coding_iso_2022 (struct coding_system *);
+
+static int detect_coding_emacs_mule (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_emacs_mule (struct coding_system *);
+static int encode_coding_emacs_mule (struct coding_system *);
+
+static int detect_coding_sjis (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_sjis (struct coding_system *);
+static int encode_coding_sjis (struct coding_system *);
+
+static int detect_coding_big5 (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_big5 (struct coding_system *);
+static int encode_coding_big5 (struct coding_system *);
+
+static int detect_coding_ccl (struct coding_system *,
+ struct coding_detection_info *info);
+static void decode_coding_ccl (struct coding_system *);
+static int encode_coding_ccl (struct coding_system *);
+
+static void decode_coding_raw_text (struct coding_system *);
+static int encode_coding_raw_text (struct coding_system *);
+
+static void coding_set_source (struct coding_system *);
+static void coding_set_destination (struct coding_system *);
+static void coding_alloc_by_realloc (struct coding_system *, EMACS_INT);
+static void coding_alloc_by_making_gap (struct coding_system *,
+ EMACS_INT, EMACS_INT);
+static unsigned char *alloc_destination (struct coding_system *,
+ 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 *);
+static int detect_eol (const unsigned char *,
+ EMACS_INT, enum coding_category);
+static Lisp_Object adjust_coding_eol_type (struct coding_system *, int);
+static void decode_eol (struct coding_system *);
+static Lisp_Object get_translation_table (Lisp_Object, int, int *);
+static Lisp_Object get_translation (Lisp_Object, int *, int *);
+static int produce_chars (struct coding_system *, Lisp_Object, int);
+static INLINE void produce_charset (struct coding_system *, int *,
+ EMACS_INT);
+static void produce_annotation (struct coding_system *, EMACS_INT);
+static int decode_coding (struct coding_system *);
+static INLINE int *handle_composition_annotation (EMACS_INT, EMACS_INT,
+ struct coding_system *,
+ int *, EMACS_INT *);
+static INLINE int *handle_charset_annotation (EMACS_INT, EMACS_INT,
+ struct coding_system *,
+ int *, EMACS_INT *);
+static void consume_chars (struct coding_system *, Lisp_Object, int);
+static int encode_coding (struct coding_system *);
+static Lisp_Object make_conversion_work_buffer (int);
+static Lisp_Object code_conversion_restore (Lisp_Object);
+static INLINE int char_encodable_p (int, Lisp_Object);
+static Lisp_Object make_subsidiaries (Lisp_Object);
static void
record_conversion_result (struct coding_system *coding,
case CODING_RESULT_INSUFFICIENT_MEM:
Vlast_code_conversion_error = Qinsufficient_memory;
break;
+ case CODING_RESULT_INSUFFICIENT_DST:
+ /* Don't record this error in Vlast_code_conversion_error
+ because it happens just temporarily and is resolved when the
+ whole conversion is finished. */
+ break;
case CODING_RESULT_SUCCESS:
break;
default:
}
}
+/* This wrapper macro is used to preserve validity of pointers into
+ buffer text across calls to decode_char, which could cause
+ relocation of buffers if it loads a charset map, because loading a
+ charset map allocates large structures. */
#define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \
do { \
charset_map_loaded = 0; \
static void
-coding_set_source (coding)
- struct coding_system *coding;
+coding_set_source (struct coding_system *coding)
{
if (BUFFERP (coding->src_object))
{
}
static void
-coding_set_destination (coding)
- struct coding_system *coding;
+coding_set_destination (struct coding_system *coding)
{
if (BUFFERP (coding->dst_object))
{
static void
-coding_alloc_by_realloc (coding, bytes)
- struct coding_system *coding;
- EMACS_INT bytes;
+coding_alloc_by_realloc (struct coding_system *coding, EMACS_INT bytes)
{
coding->destination = (unsigned char *) xrealloc (coding->destination,
coding->dst_bytes + bytes);
}
static void
-coding_alloc_by_making_gap (coding, gap_head_used, bytes)
- struct coding_system *coding;
- EMACS_INT gap_head_used, bytes;
+coding_alloc_by_making_gap (struct coding_system *coding, EMACS_INT gap_head_used, EMACS_INT bytes)
{
if (EQ (coding->src_object, coding->dst_object))
{
static unsigned char *
-alloc_destination (coding, nbytes, dst)
- struct coding_system *coding;
- EMACS_INT nbytes;
- unsigned char *dst;
+alloc_destination (struct coding_system *coding, EMACS_INT nbytes, unsigned char *dst)
{
EMACS_INT offset = dst - coding->destination;
#define UTF_8_BOM_3 0xBF
static int
-detect_coding_utf_8 (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_utf_8 (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
static void
-decode_coding_utf_8 (coding)
- struct coding_system *coding;
+decode_coding_utf_8 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
static int
-encode_coding_utf_8 (coding)
- struct coding_system *coding;
+encode_coding_utf_8 (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
static int
-detect_coding_utf_16 (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+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_end = coding->source + coding->src_bytes;
}
static void
-decode_coding_utf_16 (coding)
- struct coding_system *coding;
+decode_coding_utf_16 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
}
static int
-encode_coding_utf_16 (coding)
- struct coding_system *coding;
+encode_coding_utf_16 (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
{
ASSURE_DESTINATION (safe_room);
c = *charbuf++;
- if (c >= MAX_UNICODE_CHAR)
+ if (c > MAX_UNICODE_CHAR)
c = coding->default_char;
if (c < 0x10000)
else return 0. */
static int
-detect_coding_emacs_mule (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_emacs_mule (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
/* Parse emacs-mule multibyte sequence at SRC and return the decoded
character. If CMP_STATUS indicates that we must expect MSEQ or
RULE described above, decode it and return the negative value of
- the deocded character or rule. If an invalid byte is found, return
+ the decoded character or rule. If an invalid byte is found, return
-1. If SRC is too short, return -2. */
int
-emacs_mule_char (coding, src, nbytes, nchars, id, cmp_status)
- struct coding_system *coding;
- const unsigned char *src;
- int *nbytes, *nchars, *id;
- struct composition_status *cmp_status;
+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;
default:
abort ();
}
- c = DECODE_CHAR (charset, code);
+ CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, code, c);
if (c < 0)
goto invalid_code;
}
static int
-emacs_mule_finish_composition (charbuf, cmp_status)
- int *charbuf;
- struct composition_status *cmp_status;
+emacs_mule_finish_composition (int *charbuf, struct composition_status *cmp_status)
{
int idx = - cmp_status->length;
int new_chars;
static void
-decode_coding_emacs_mule (coding)
- struct coding_system *coding;
+decode_coding_emacs_mule (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
else
{
int nchars, nbytes;
+ /* 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
+ pointers after the call. */
+ const unsigned char *orig = coding->source;
+ EMACS_INT offset;
c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id,
cmp_status);
+ offset = coding->source - orig;
+ if (offset)
+ {
+ src += offset;
+ src_base += offset;
+ src_end += offset;
+ }
if (c < 0)
{
if (c == -1)
static int
-encode_coding_emacs_mule (coding)
- struct coding_system *coding;
+encode_coding_emacs_mule (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
(CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0)
static void
-setup_iso_safe_charsets (attrs)
- Lisp_Object attrs;
+setup_iso_safe_charsets (Lisp_Object attrs)
{
Lisp_Object charset_list, safe_charsets;
Lisp_Object request;
If it is, return 1, else return 0. */
static int
-detect_coding_iso_2022 (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_iso_2022 (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base = src;
const unsigned char *src_end = coding->source + coding->src_bytes;
int i = 1;
while (src < src_end)
{
+ src_base = src;
ONE_MORE_BYTE (c);
if (c < 0xA0)
- break;
+ {
+ src = src_base;
+ break;
+ }
i++;
}
/* Finish the current composition as invalid. */
-static int finish_composition P_ ((int *, struct composition_status *));
+static int finish_composition (int *, struct composition_status *);
static int
-finish_composition (charbuf, cmp_status)
- int *charbuf;
- struct composition_status *cmp_status;
+finish_composition (int *charbuf, struct composition_status *cmp_status)
{
int idx = - cmp_status->length;
int new_chars;
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
static void
-decode_coding_iso_2022 (coding)
- struct coding_system *coding;
+decode_coding_iso_2022 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
continue;
case ISO_single_shift_2_7:
+ if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS))
+ goto invalid_code;
case ISO_single_shift_2:
if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT))
goto invalid_code;
continue;
case '[': /* specification of direction */
- if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)
+ if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION))
goto invalid_code;
/* For the moment, nested direction is not supported.
So, `coding->mode & CODING_MODE_DIRECTION' zero means
Return new DST. */
unsigned char *
-encode_invocation_designation (charset, coding, dst, p_nchars)
- struct charset *charset;
- struct coding_system *coding;
- unsigned char *dst;
- int *p_nchars;
+encode_invocation_designation (struct charset *charset, struct coding_system *coding, unsigned char *dst, int *p_nchars)
{
int multibytep = coding->dst_multibyte;
int produced_chars = *p_nchars;
find all the necessary designations. */
static unsigned char *
-encode_designation_at_bol (coding, charbuf, charbuf_end, dst)
- struct coding_system *coding;
- int *charbuf, *charbuf_end;
- unsigned char *dst;
+encode_designation_at_bol (struct coding_system *coding, int *charbuf, int *charbuf_end, unsigned char *dst)
{
struct charset *charset;
/* Table of charsets to be designated to each graphic register. */
/* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */
static int
-encode_coding_iso_2022 (coding)
- struct coding_system *coding;
+encode_coding_iso_2022 (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
CATEGORY_MASK_SJIS, else return 0. */
static int
-detect_coding_sjis (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_sjis (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
int consumed_chars = 0;
int found = 0;
int c;
+ Lisp_Object attrs, charset_list;
+ int max_first_byte_of_2_byte_code;
+
+ CODING_GET_INFO (coding, attrs, charset_list);
+ max_first_byte_of_2_byte_code
+ = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF);
detect_info->checked |= CATEGORY_MASK_SJIS;
/* A coding system of this category is always ASCII compatible. */
ONE_MORE_BYTE (c);
if (c < 0x80)
continue;
- if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF))
+ if ((c >= 0x81 && c <= 0x9F)
+ || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code))
{
ONE_MORE_BYTE (c);
if (c < 0x40 || c == 0x7F || c > 0xFC)
CATEGORY_MASK_BIG5, else return 0. */
static int
-detect_coding_big5 (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_big5 (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */
static void
-decode_coding_sjis (coding)
- struct coding_system *coding;
+decode_coding_sjis (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
}
static void
-decode_coding_big5 (coding)
- struct coding_system *coding;
+decode_coding_big5 (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
SJIS text, else encode BIG5 text. */
static int
-encode_coding_sjis (coding)
- struct coding_system *coding;
+encode_coding_sjis (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int c1, c2;
c1 = code >> 8;
- if (c1 == 0x21 || (c1 >= 0x23 && c1 < 0x25)
+ if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25)
+ || c1 == 0x28
|| (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E)
{
JIS_TO_SJIS2 (code);
}
static int
-encode_coding_big5 (coding)
- struct coding_system *coding;
+encode_coding_big5 (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
CATEGORY_MASK_CCL, else return 0. */
static int
-detect_coding_ccl (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_ccl (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
}
static void
-decode_coding_ccl (coding)
- struct coding_system *coding;
+decode_coding_ccl (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
int *charbuf_end = coding->charbuf + coding->charbuf_size;
int consumed_chars = 0;
int multibytep = coding->src_multibyte;
- struct ccl_program ccl;
+ struct ccl_program *ccl = &coding->spec.ccl->ccl;
int source_charbuf[1024];
- int source_byteidx[1024];
+ int source_byteidx[1025];
Lisp_Object attrs, charset_list;
CODING_GET_INFO (coding, attrs, charset_list);
- setup_ccl_program (&ccl, CODING_CCL_DECODER (coding));
- while (src < src_end)
+ while (1)
{
const unsigned char *p = src;
- int *source, *source_end;
int i = 0;
if (multibytep)
- while (i < 1024 && p < src_end)
- {
- source_byteidx[i] = p - src;
- source_charbuf[i++] = STRING_CHAR_ADVANCE (p);
- }
+ {
+ while (i < 1024 && p < src_end)
+ {
+ source_byteidx[i] = p - src;
+ source_charbuf[i++] = STRING_CHAR_ADVANCE (p);
+ }
+ source_byteidx[i] = p - src;
+ }
else
while (i < 1024 && p < src_end)
source_charbuf[i++] = *p++;
if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK)
- ccl.last_block = 1;
-
- source = source_charbuf;
- source_end = source + i;
- while (source < source_end)
- {
- ccl_driver (&ccl, source, charbuf,
- source_end - source, charbuf_end - charbuf,
- charset_list);
- source += ccl.consumed;
- charbuf += ccl.produced;
- if (ccl.status != CCL_STAT_SUSPEND_BY_DST)
- break;
- }
- if (source < source_end)
- src += source_byteidx[source - source_charbuf];
+ ccl->last_block = 1;
+ ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf,
+ charset_list);
+ charbuf += ccl->produced;
+ if (multibytep)
+ src += source_byteidx[ccl->consumed];
else
- src = p;
- consumed_chars += source - source_charbuf;
-
- if (ccl.status != CCL_STAT_SUSPEND_BY_SRC
- && ccl.status != CODING_RESULT_INSUFFICIENT_SRC)
+ src += ccl->consumed;
+ consumed_chars += ccl->consumed;
+ if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC)
break;
}
- switch (ccl.status)
+ switch (ccl->status)
{
case CCL_STAT_SUSPEND_BY_SRC:
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC);
break;
case CCL_STAT_SUSPEND_BY_DST:
+ record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST);
break;
case CCL_STAT_QUIT:
case CCL_STAT_INVALID_CMD:
}
static int
-encode_coding_ccl (coding)
- struct coding_system *coding;
+encode_coding_ccl (struct coding_system *coding)
{
- struct ccl_program ccl;
+ struct ccl_program *ccl = &coding->spec.ccl->ccl;
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
Lisp_Object attrs, charset_list;
CODING_GET_INFO (coding, attrs, charset_list);
- setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding));
-
- ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK;
- ccl.dst_multibyte = coding->dst_multibyte;
+ if (coding->consumed_char == coding->src_chars
+ && coding->mode & CODING_MODE_LAST_BLOCK)
+ ccl->last_block = 1;
while (charbuf < charbuf_end)
{
- ccl_driver (&ccl, charbuf, destination_charbuf,
+ ccl_driver (ccl, charbuf, destination_charbuf,
charbuf_end - charbuf, 1024, charset_list);
if (multibytep)
{
- ASSURE_DESTINATION (ccl.produced * 2);
- for (i = 0; i < ccl.produced; i++)
+ ASSURE_DESTINATION (ccl->produced * 2);
+ for (i = 0; i < ccl->produced; i++)
EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF);
}
else
{
- ASSURE_DESTINATION (ccl.produced);
- for (i = 0; i < ccl.produced; i++)
+ ASSURE_DESTINATION (ccl->produced);
+ for (i = 0; i < ccl->produced; i++)
*dst++ = destination_charbuf[i] & 0xFF;
- produced_chars += ccl.produced;
+ produced_chars += ccl->produced;
}
- charbuf += ccl.consumed;
- if (ccl.status == CCL_STAT_QUIT
- || ccl.status == CCL_STAT_INVALID_CMD)
+ charbuf += ccl->consumed;
+ if (ccl->status == CCL_STAT_QUIT
+ || ccl->status == CCL_STAT_INVALID_CMD)
break;
}
- switch (ccl.status)
+ switch (ccl->status)
{
case CCL_STAT_SUSPEND_BY_SRC:
record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC);
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
static void
-decode_coding_raw_text (coding)
- struct coding_system *coding;
+decode_coding_raw_text (struct coding_system *coding)
{
int eol_crlf =
!inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
}
static int
-encode_coding_raw_text (coding)
- struct coding_system *coding;
+encode_coding_raw_text (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
is, return 1, else return 0. */
static int
-detect_coding_charset (coding, detect_info)
- struct coding_system *coding;
- struct coding_detection_info *detect_info;
+detect_coding_charset (struct coding_system *coding, struct coding_detection_info *detect_info)
{
const unsigned char *src = coding->source, *src_base;
const unsigned char *src_end = coding->source + coding->src_bytes;
}
static void
-decode_coding_charset (coding)
- struct coding_system *coding;
+decode_coding_charset (struct coding_system *coding)
{
const unsigned char *src = coding->source + coding->consumed;
const unsigned char *src_end = coding->source + coding->src_bytes;
}
static int
-encode_coding_charset (coding)
- struct coding_system *coding;
+encode_coding_charset (struct coding_system *coding)
{
int multibytep = coding->dst_multibyte;
int *charbuf = coding->charbuf;
CODING_SYSTEM is invalid, signal an error. */
void
-setup_coding_system (coding_system, coding)
- Lisp_Object coding_system;
- struct coding_system *coding;
+setup_coding_system (Lisp_Object coding_system, struct coding_system *coding)
{
Lisp_Object attrs;
Lisp_Object eol_type;
/* Return a list of charsets supported by CODING. */
Lisp_Object
-coding_charset_list (coding)
- struct coding_system *coding;
+coding_charset_list (struct coding_system *coding)
{
Lisp_Object attrs, charset_list;
/* Return a list of charsets supported by CODING-SYSTEM. */
Lisp_Object
-coding_system_charset_list (coding_system)
- Lisp_Object coding_system;
+coding_system_charset_list (Lisp_Object coding_system)
{
int id;
Lisp_Object attrs, charset_list;
eol_type as CODING-SYSTEM. */
Lisp_Object
-raw_text_coding_system (coding_system)
- Lisp_Object coding_system;
+raw_text_coding_system (Lisp_Object coding_system)
{
Lisp_Object spec, attrs;
Lisp_Object eol_type, raw_text_eol_type;
(system_eol_type). */
Lisp_Object
-coding_inherit_eol_type (coding_system, parent)
- Lisp_Object coding_system, parent;
+coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent)
{
Lisp_Object spec, eol_type;
#define MAX_EOL_CHECK_COUNT 3
static int
-detect_eol (source, src_bytes, category)
- const unsigned char *source;
- EMACS_INT src_bytes;
- enum coding_category category;
+detect_eol (const unsigned char *source, EMACS_INT src_bytes, enum coding_category category)
{
const unsigned char *src = source, *src_end = src + src_bytes;
unsigned char c;
static Lisp_Object
-adjust_coding_eol_type (coding, eol_seen)
- struct coding_system *coding;
- int eol_seen;
+adjust_coding_eol_type (struct coding_system *coding, int eol_seen)
{
Lisp_Object eol_type;
system. */
void
-detect_coding (coding)
- struct coding_system *coding;
+detect_coding (struct coding_system *coding)
{
const unsigned char *src, *src_end;
int saved_mode = coding->mode;
{
/* 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
+ rare that a binary file conforms to
ISO-2022. */
src = src_end;
coding->head_ascii = src - coding->source;
static void
-decode_eol (coding)
- struct coding_system *coding;
+decode_eol (struct coding_system *coding)
{
Lisp_Object eol_type;
unsigned char *p, *pbeg, *pend;
decoding (ENCODEP is zero). */
static Lisp_Object
-get_translation_table (attrs, encodep, max_lookup)
- Lisp_Object attrs;
- int encodep, *max_lookup;
+get_translation_table (Lisp_Object attrs, int encodep, int *max_lookup)
{
Lisp_Object standard, translation_table;
Lisp_Object val;
If BUF is too short to lookup characters in FROM, return Qt. */
static Lisp_Object
-get_translation (trans, buf, buf_end)
- Lisp_Object trans;
- int *buf, *buf_end;
+get_translation (Lisp_Object trans, int *buf, int *buf_end)
{
if (INTEGERP (trans))
static int
-produce_chars (coding, translation_table, last_block)
- struct coding_system *coding;
- Lisp_Object translation_table;
- int last_block;
+produce_chars (struct coding_system *coding, Lisp_Object translation_table, int last_block)
{
unsigned char *dst = coding->destination + coding->produced;
unsigned char *dst_end = coding->destination + coding->dst_bytes;
*/
static INLINE void
-produce_composition (coding, charbuf, pos)
- struct coding_system *coding;
- int *charbuf;
- EMACS_INT pos;
+produce_composition (struct coding_system *coding, int *charbuf, EMACS_INT pos)
{
int len;
EMACS_INT to;
*/
static INLINE void
-produce_charset (coding, charbuf, pos)
- struct coding_system *coding;
- int *charbuf;
- EMACS_INT pos;
+produce_charset (struct coding_system *coding, int *charbuf, EMACS_INT pos)
{
EMACS_INT from = pos - charbuf[2];
struct charset *charset = CHARSET_FROM_ID (charbuf[3]);
static void
-produce_annotation (coding, pos)
- struct coding_system *coding;
- EMACS_INT pos;
+produce_annotation (struct coding_system *coding, EMACS_INT pos)
{
int *charbuf = coding->charbuf;
int *charbuf_end = charbuf + coding->charbuf_used;
*/
static int
-decode_coding (coding)
- struct coding_system *coding;
+decode_coding (struct coding_system *coding)
{
Lisp_Object attrs;
Lisp_Object undo_list;
Lisp_Object translation_table;
+ struct ccl_spec cclspec;
int carryover;
int i;
translation_table = get_translation_table (attrs, 0, NULL);
carryover = 0;
+ if (coding->decoder == decode_coding_ccl)
+ {
+ coding->spec.ccl = &cclspec;
+ setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding));
+ }
do
{
EMACS_INT pos = coding->dst_pos + coding->produced_char;
coding->charbuf[i]
= coding->charbuf[coding->charbuf_used - carryover + i];
}
- while (coding->consumed < coding->src_bytes
- && (coding->result == CODING_RESULT_SUCCESS
- || coding->result == CODING_RESULT_INVALID_SRC));
+ while (coding->result == CODING_RESULT_INSUFFICIENT_DST
+ || (coding->consumed < coding->src_bytes
+ && (coding->result == CODING_RESULT_SUCCESS
+ || coding->result == CODING_RESULT_INVALID_SRC)));
if (carryover > 0)
{
return BUF. */
static INLINE int *
-handle_composition_annotation (pos, limit, coding, buf, stop)
- EMACS_INT pos, limit;
- struct coding_system *coding;
- int *buf;
- EMACS_INT *stop;
+handle_composition_annotation (EMACS_INT pos, EMACS_INT limit, struct coding_system *coding, int *buf, EMACS_INT *stop)
{
EMACS_INT start, end;
Lisp_Object prop;
property value is non-nil (limiting by LIMIT), and return BUF. */
static INLINE int *
-handle_charset_annotation (pos, limit, coding, buf, stop)
- EMACS_INT pos, limit;
- struct coding_system *coding;
- int *buf;
- EMACS_INT *stop;
+handle_charset_annotation (EMACS_INT pos, EMACS_INT limit, struct coding_system *coding, int *buf, EMACS_INT *stop)
{
Lisp_Object val, next;
int id;
static void
-consume_chars (coding, translation_table, max_lookup)
- struct coding_system *coding;
- Lisp_Object translation_table;
- int max_lookup;
+consume_chars (struct coding_system *coding, Lisp_Object translation_table, int max_lookup)
{
int *buf = coding->charbuf;
int *buf_end = coding->charbuf + coding->charbuf_size;
{
EMACS_INT bytes;
- if (coding->encoder == encode_coding_raw_text)
+ if (coding->encoder == encode_coding_raw_text
+ || coding->encoder == encode_coding_ccl)
c = *src++, pos++;
else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0)
c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes;
memory area specified by CODING->destination. */
static int
-encode_coding (coding)
- struct coding_system *coding;
+encode_coding (struct coding_system *coding)
{
Lisp_Object attrs;
Lisp_Object translation_table;
int max_lookup;
+ struct ccl_spec cclspec;
attrs = CODING_ID_ATTRS (coding->id);
if (coding->encoder == encode_coding_raw_text)
ALLOC_CONVERSION_WORK_AREA (coding);
+ if (coding->encoder == encode_coding_ccl)
+ {
+ coding->spec.ccl = &cclspec;
+ setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding));
+ }
do {
coding_set_source (coding);
consume_chars (coding, translation_table, max_lookup);
multibyteness of returning buffer. */
static Lisp_Object
-make_conversion_work_buffer (multibyte)
- int multibyte;
+make_conversion_work_buffer (int multibyte)
{
Lisp_Object name, workbuf;
struct buffer *current;
static Lisp_Object
-code_conversion_restore (arg)
- Lisp_Object arg;
+code_conversion_restore (Lisp_Object arg)
{
Lisp_Object current, workbuf;
struct gcpro gcpro1;
}
Lisp_Object
-code_conversion_save (with_work_buf, multibyte)
- int with_work_buf, multibyte;
+code_conversion_save (int with_work_buf, int multibyte)
{
Lisp_Object workbuf = Qnil;
}
int
-decode_coding_gap (coding, chars, bytes)
- struct coding_system *coding;
- EMACS_INT chars, bytes;
+decode_coding_gap (struct coding_system *coding, EMACS_INT chars, EMACS_INT bytes)
{
int count = specpdl_ptr - specpdl;
Lisp_Object attrs;
}
int
-encode_coding_gap (coding, chars, bytes)
- struct coding_system *coding;
- EMACS_INT chars, bytes;
+encode_coding_gap (struct coding_system *coding, EMACS_INT chars, EMACS_INT bytes)
{
int count = specpdl_ptr - specpdl;
if (! destination)
{
record_conversion_result (coding,
- CODING_RESULT_INSUFFICIENT_DST);
+ CODING_RESULT_INSUFFICIENT_MEM);
unbind_to (count, Qnil);
return;
}
Lisp_Object
-preferred_coding_system ()
+preferred_coding_system (void)
{
int id = coding_categories[coding_priorities[0]].id;
static INLINE int
-char_encodable_p (c, attrs)
- int c;
- Lisp_Object attrs;
+char_encodable_p (int c, Lisp_Object attrs)
{
Lisp_Object tail;
struct charset *charset;
Lisp_Object
-code_convert_region (start, end, coding_system, dst_object, encodep, norecord)
- Lisp_Object start, end, coding_system, dst_object;
- int encodep, norecord;
+code_convert_region (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object dst_object, int encodep, int norecord)
{
struct coding_system coding;
EMACS_INT from, from_byte, to, to_byte;
ENCODE_FILE, thus we ignore character composition. */
Lisp_Object
-code_convert_string_norecord (string, coding_system, encodep)
- Lisp_Object string, coding_system;
- int encodep;
+code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, int encodep)
{
return code_convert_string (string, coding_system, Qt, encodep, 0, 1);
}
return Fnreverse (val);
}
-static char *suffixes[] = { "-unix", "-dos", "-mac" };
+static const char *const suffixes[] = { "-unix", "-dos", "-mac" };
static Lisp_Object
-make_subsidiaries (base)
- Lisp_Object base;
+make_subsidiaries (Lisp_Object base)
{
Lisp_Object subsidiaries;
int base_name_len = SBYTES (SYMBOL_NAME (base));
/*** 9. Post-amble ***/
void
-init_coding_once ()
+init_coding_once (void)
{
int i;
#ifdef emacs
void
-syms_of_coding ()
+syms_of_coding (void)
{
staticpro (&Vcoding_system_hash_table);
{
Vcode_conversion_reused_workbuf = Qnil;
staticpro (&Vcode_conversion_workbuf_name);
- Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*");
+ Vcode_conversion_workbuf_name = make_pure_c_string (" *code-conversion-work*");
reused_workbuf_in_use = 0;
DEFSYM (Qcoding_system_error, "coding-system-error");
Fput (Qcoding_system_error, Qerror_conditions,
- Fcons (Qcoding_system_error, Fcons (Qerror, Qnil)));
+ pure_cons (Qcoding_system_error, pure_cons (Qerror, Qnil)));
Fput (Qcoding_system_error, Qerror_message,
- build_string ("Invalid coding system"));
+ make_pure_c_string ("Invalid coding system"));
/* Intern this now in case it isn't already done.
Setting this variable twice is harmless.
But don't staticpro it here--that is done in alloc.c. */
- Qchar_table_extra_slots = intern ("char-table-extra-slots");
+ Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots");
DEFSYM (Qtranslation_table, "translation-table");
Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2));
staticpro (&Vcoding_category_table);
/* Followings are target of code detection. */
ASET (Vcoding_category_table, coding_category_iso_7,
- intern ("coding-category-iso-7"));
+ intern_c_string ("coding-category-iso-7"));
ASET (Vcoding_category_table, coding_category_iso_7_tight,
- intern ("coding-category-iso-7-tight"));
+ intern_c_string ("coding-category-iso-7-tight"));
ASET (Vcoding_category_table, coding_category_iso_8_1,
- intern ("coding-category-iso-8-1"));
+ intern_c_string ("coding-category-iso-8-1"));
ASET (Vcoding_category_table, coding_category_iso_8_2,
- intern ("coding-category-iso-8-2"));
+ intern_c_string ("coding-category-iso-8-2"));
ASET (Vcoding_category_table, coding_category_iso_7_else,
- intern ("coding-category-iso-7-else"));
+ intern_c_string ("coding-category-iso-7-else"));
ASET (Vcoding_category_table, coding_category_iso_8_else,
- intern ("coding-category-iso-8-else"));
+ intern_c_string ("coding-category-iso-8-else"));
ASET (Vcoding_category_table, coding_category_utf_8_auto,
- intern ("coding-category-utf-8-auto"));
+ intern_c_string ("coding-category-utf-8-auto"));
ASET (Vcoding_category_table, coding_category_utf_8_nosig,
- intern ("coding-category-utf-8"));
+ intern_c_string ("coding-category-utf-8"));
ASET (Vcoding_category_table, coding_category_utf_8_sig,
- intern ("coding-category-utf-8-sig"));
+ intern_c_string ("coding-category-utf-8-sig"));
ASET (Vcoding_category_table, coding_category_utf_16_be,
- intern ("coding-category-utf-16-be"));
+ intern_c_string ("coding-category-utf-16-be"));
ASET (Vcoding_category_table, coding_category_utf_16_auto,
- intern ("coding-category-utf-16-auto"));
+ intern_c_string ("coding-category-utf-16-auto"));
ASET (Vcoding_category_table, coding_category_utf_16_le,
- intern ("coding-category-utf-16-le"));
+ intern_c_string ("coding-category-utf-16-le"));
ASET (Vcoding_category_table, coding_category_utf_16_be_nosig,
- intern ("coding-category-utf-16-be-nosig"));
+ intern_c_string ("coding-category-utf-16-be-nosig"));
ASET (Vcoding_category_table, coding_category_utf_16_le_nosig,
- intern ("coding-category-utf-16-le-nosig"));
+ intern_c_string ("coding-category-utf-16-le-nosig"));
ASET (Vcoding_category_table, coding_category_charset,
- intern ("coding-category-charset"));
+ intern_c_string ("coding-category-charset"));
ASET (Vcoding_category_table, coding_category_sjis,
- intern ("coding-category-sjis"));
+ intern_c_string ("coding-category-sjis"));
ASET (Vcoding_category_table, coding_category_big5,
- intern ("coding-category-big5"));
+ intern_c_string ("coding-category-big5"));
ASET (Vcoding_category_table, coding_category_ccl,
- intern ("coding-category-ccl"));
+ intern_c_string ("coding-category-ccl"));
ASET (Vcoding_category_table, coding_category_emacs_mule,
- intern ("coding-category-emacs-mule"));
+ intern_c_string ("coding-category-emacs-mule"));
/* Followings are NOT target of code detection. */
ASET (Vcoding_category_table, coding_category_raw_text,
- intern ("coding-category-raw-text"));
+ intern_c_string ("coding-category-raw-text"));
ASET (Vcoding_category_table, coding_category_undecided,
- intern ("coding-category-undecided"));
+ intern_c_string ("coding-category-undecided"));
DEFSYM (Qinsufficient_source, "insufficient-source");
DEFSYM (Qinconsistent_eol, "inconsistent-eol");
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 = build_string (":");
+ eol_mnemonic_unix = make_pure_c_string (":");
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 = build_string ("\\");
+ eol_mnemonic_dos = make_pure_c_string ("\\");
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 = build_string ("/");
+ eol_mnemonic_mac = make_pure_c_string ("/");
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 = build_string (":");
+ eol_mnemonic_undecided = make_pure_c_string (":");
DEFVAR_LISP ("enable-character-translation", &Venable_character_translation,
doc: /*
for (i = 0; i < coding_arg_max; i++)
args[i] = Qnil;
- plist[0] = intern (":name");
+ plist[0] = intern_c_string (":name");
plist[1] = args[coding_arg_name] = Qno_conversion;
- plist[2] = intern (":mnemonic");
+ plist[2] = intern_c_string (":mnemonic");
plist[3] = args[coding_arg_mnemonic] = make_number ('=');
- plist[4] = intern (":coding-type");
+ plist[4] = intern_c_string (":coding-type");
plist[5] = args[coding_arg_coding_type] = Qraw_text;
- plist[6] = intern (":ascii-compatible-p");
+ plist[6] = intern_c_string (":ascii-compatible-p");
plist[7] = args[coding_arg_ascii_compatible_p] = Qt;
- plist[8] = intern (":default-char");
+ plist[8] = intern_c_string (":default-char");
plist[9] = args[coding_arg_default_char] = make_number (0);
- plist[10] = intern (":for-unibyte");
+ plist[10] = intern_c_string (":for-unibyte");
plist[11] = args[coding_arg_for_unibyte] = Qt;
- plist[12] = intern (":docstring");
- plist[13] = build_string ("Do no conversion.\n\
+ plist[12] = intern_c_string (":docstring");
+ plist[13] = make_pure_c_string ("Do no conversion.\n\
\n\
When you visit a file with this coding, the file is read into a\n\
unibyte buffer as is, thus each byte of a file is treated as a\n\
character.");
- plist[14] = intern (":eol-type");
+ plist[14] = intern_c_string (":eol-type");
plist[15] = args[coding_arg_eol_type] = Qunix;
args[coding_arg_plist] = Flist (16, plist);
Fdefine_coding_system_internal (coding_arg_max, args);
plist[5] = args[coding_arg_coding_type] = Qundecided;
/* This is already set.
plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */
- plist[8] = intern (":charset-list");
+ plist[8] = intern_c_string (":charset-list");
plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil);
plist[11] = args[coding_arg_for_unibyte] = Qnil;
- plist[13] = build_string ("No conversion on encoding, automatic conversion on decoding.");
+ plist[13] = make_pure_c_string ("No conversion on encoding, automatic conversion on decoding.");
plist[15] = args[coding_arg_eol_type] = Qnil;
args[coding_arg_plist] = Flist (16, plist);
Fdefine_coding_system_internal (coding_arg_max, args);
}
char *
-emacs_strerror (error_number)
- int error_number;
+emacs_strerror (int error_number)
{
char *str;
HCoop / bpt / emacs.git / blobdiff