Lisp_Object Vfile_name_coding_system;
/* Table of symbols identifying each coding category. */
-Lisp_Object coding_category_symbol[CODING_CATEGORY_LAST + 1];
+Lisp_Object coding_category_symbol[CODING_CATEGORY_LAST];
struct file_coding_dump {
/* Coding system currently associated with each coding category. */
- Lisp_Object coding_category_system[CODING_CATEGORY_LAST + 1];
+ Lisp_Object coding_category_system[CODING_CATEGORY_LAST];
/* Table of all coding categories in decreasing order of priority.
This describes a permutation of the possible coding categories. */
- int coding_category_by_priority[CODING_CATEGORY_LAST + 1];
+ int coding_category_by_priority[CODING_CATEGORY_LAST];
#ifdef MULE
Lisp_Object ucs_to_mule_table[65536];
} *fcd;
static const struct lrecord_description fcd_description_1[] = {
- { XD_LISP_OBJECT_ARRAY, offsetof (struct file_coding_dump, coding_category_system), CODING_CATEGORY_LAST + 1 },
+ { XD_LISP_OBJECT_ARRAY, offsetof (struct file_coding_dump, coding_category_system), CODING_CATEGORY_LAST },
#ifdef MULE
{ XD_LISP_OBJECT_ARRAY, offsetof (struct file_coding_dump, ucs_to_mule_table), countof (fcd->ucs_to_mule_table) },
#endif
#ifdef MULE
struct detection_state;
static int detect_coding_sjis (struct detection_state *st,
- const Extbyte *src, size_t n);
+ const Extbyte *src, Lstream_data_count n);
static void decode_coding_sjis (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void encode_coding_sjis (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static int detect_coding_big5 (struct detection_state *st,
- const Extbyte *src, size_t n);
+ const Extbyte *src, Lstream_data_count n);
static void decode_coding_big5 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void encode_coding_big5 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static int detect_coding_ucs4 (struct detection_state *st,
- const Extbyte *src, size_t n);
+ const Extbyte *src, Lstream_data_count n);
static void decode_coding_ucs4 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void encode_coding_ucs4 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static int detect_coding_utf8 (struct detection_state *st,
- const Extbyte *src, size_t n);
+ const Extbyte *src, Lstream_data_count n);
static void decode_coding_utf8 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void encode_coding_utf8 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static int postprocess_iso2022_mask (int mask);
static void reset_iso2022 (Lisp_Object coding_system,
struct iso2022_decoder *iso);
static int detect_coding_iso2022 (struct detection_state *st,
- const Extbyte *src, size_t n);
+ const Extbyte *src, Lstream_data_count n);
static void decode_coding_iso2022 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void encode_coding_iso2022 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
#endif /* MULE */
static void decode_coding_no_conversion (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void encode_coding_no_conversion (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void mule_decode (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
static void mule_encode (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n);
+ unsigned_char_dynarr *dst, Lstream_data_count n);
typedef struct codesys_prop codesys_prop;
struct codesys_prop
int i;
CHECK_SYMBOL (symbol);
- for (i = 0; i <= CODING_CATEGORY_LAST; i++)
+ for (i = 0; i < CODING_CATEGORY_LAST; i++)
if (EQ (coding_category_symbol[i], symbol))
return i;
int i;
Lisp_Object list = Qnil;
- for (i = CODING_CATEGORY_LAST; i >= 0; i--)
+ for (i = CODING_CATEGORY_LAST - 1; i >= 0; i--)
list = Fcons (coding_category_symbol[i], list);
return list;
}
*/
(list))
{
- int category_to_priority[CODING_CATEGORY_LAST + 1];
+ int category_to_priority[CODING_CATEGORY_LAST];
int i, j;
Lisp_Object rest;
/* First generate a list that maps coding categories to priorities. */
- for (i = 0; i <= CODING_CATEGORY_LAST; i++)
+ for (i = 0; i < CODING_CATEGORY_LAST; i++)
category_to_priority[i] = -1;
/* Highest priority comes from the specified list. */
/* Now go through the existing categories by priority to retrieve
the categories not yet specified and preserve their priority
order. */
- for (j = 0; j <= CODING_CATEGORY_LAST; j++)
+ for (j = 0; j < CODING_CATEGORY_LAST; j++)
{
int cat = fcd->coding_category_by_priority[j];
if (category_to_priority[cat] < 0)
/* Now we need to construct the inverse of the mapping we just
constructed. */
- for (i = 0; i <= CODING_CATEGORY_LAST; i++)
+ for (i = 0; i < CODING_CATEGORY_LAST; i++)
fcd->coding_category_by_priority[category_to_priority[i]] = i;
/* Phew! That was confusing. */
int i;
Lisp_Object list = Qnil;
- for (i = CODING_CATEGORY_LAST; i >= 0; i--)
+ for (i = CODING_CATEGORY_LAST - 1; i >= 0; i--)
list = Fcons (coding_category_symbol[fcd->coding_category_by_priority[i]],
list);
return list;
static eol_type_t
detect_eol_type (struct detection_state *st, const Extbyte *src,
- size_t n)
+ Lstream_data_count n)
{
while (n--)
{
static int
detect_coding_type (struct detection_state *st, const Extbyte *src,
- size_t n, int just_do_eol)
+ Lstream_data_count n, int just_do_eol)
{
if (st->eol_type == EOL_AUTODETECT)
st->eol_type = detect_eol_type (st, src, n);
#endif
/* Look through the coding categories by priority and find
the first one that is allowed. */
- for (i = 0; i <= CODING_CATEGORY_LAST; i++)
+ for (i = 0; i < CODING_CATEGORY_LAST; i++)
{
cat = fcd->coding_category_by_priority[i];
if ((mask & (1 << cat)) &&
that should be unnecessary with the explicit eol-type argument. */
#define LENGTH(string_constant) (sizeof (string_constant) - 1)
+/* number of leading lines to check for a coding cookie */
+#define LINES_TO_CHECK 2
void
determine_real_coding_system (Lstream *stream, Lisp_Object *codesys_in_out,
Extbyte buf[4096];
Lisp_Object coding_system = Qnil;
Extbyte *p;
- ssize_t nread = Lstream_read (stream, buf, sizeof (buf));
+ Lstream_data_count nread = Lstream_read (stream, buf, sizeof (buf));
Extbyte *scan_end;
+ int lines_checked = 0;
/* Look for initial "-*-"; mode line prefix */
for (p = buf,
scan_end = buf + nread - LENGTH ("-*-coding:?-*-");
p <= scan_end
- && *p != '\n'
- && *p != '\r';
+ && lines_checked < LINES_TO_CHECK;
p++)
if (*p == '-' && *(p+1) == '*' && *(p+2) == '-')
{
for (p = local_vars_beg,
scan_end = buf + nread - LENGTH ("-*-");
p <= scan_end
- && *p != '\n'
- && *p != '\r';
+ && lines_checked < LINES_TO_CHECK;
p++)
if (*p == '-' && *(p+1) == '*' && *(p+2) == '-')
{
}
break;
}
+ /* #### file must use standard EOLs or we miss 2d line */
+ /* #### not to mention this is broken for UTF-16 DOS files */
+ else if (*p == '\n' || *p == '\r')
+ {
+ lines_checked++;
+ /* skip past multibyte (DOS) newline */
+ if (*p == '\r' && *(p+1) == '\n') p++;
+ }
break;
}
+ /* #### file must use standard EOLs or we miss 2d line */
+ /* #### not to mention this is broken for UTF-16 DOS files */
+ else if (*p == '\n' || *p == '\r')
+ {
+ lines_checked++;
+ /* skip past multibyte (DOS) newline */
+ if (*p == '\r' && *(p+1) == '\n') p++;
+ }
if (NILP (coding_system))
do
while (1)
{
Extbyte random_buffer[4096];
- ssize_t nread = Lstream_read (istr, random_buffer, sizeof (random_buffer));
+ Lstream_data_count nread = Lstream_read (istr, random_buffer, sizeof (random_buffer));
if (!nread)
break;
#ifdef MULE
decst.mask = postprocess_iso2022_mask (decst.mask);
#endif
- for (i = CODING_CATEGORY_LAST; i >= 0; i--)
+ for (i = CODING_CATEGORY_LAST - 1; i >= 0; i--)
{
int sys = fcd->coding_category_by_priority[i];
if (decst.mask & (1 << sys))
struct detection_state decst;
};
-static ssize_t decoding_reader (Lstream *stream,
- unsigned char *data, size_t size);
-static ssize_t decoding_writer (Lstream *stream,
- const unsigned char *data, size_t size);
+static Lstream_data_count decoding_reader (Lstream *stream,
+ unsigned char *data, Lstream_data_count size);
+static Lstream_data_count decoding_writer (Lstream *stream,
+ const unsigned char *data, Lstream_data_count size);
static int decoding_rewinder (Lstream *stream);
static int decoding_seekable_p (Lstream *stream);
static int decoding_flusher (Lstream *stream);
/* Read SIZE bytes of data and store it into DATA. We are a decoding stream
so we read data from the other end, decode it, and store it into DATA. */
-static ssize_t
-decoding_reader (Lstream *stream, unsigned char *data, size_t size)
+static Lstream_data_count
+decoding_reader (Lstream *stream, unsigned char *data, Lstream_data_count size)
{
struct decoding_stream *str = DECODING_STREAM_DATA (stream);
unsigned char *orig_data = data;
- ssize_t read_size;
+ Lstream_data_count read_size;
int error_occurred = 0;
/* We need to interface to mule_decode(), which expects to take some
most SIZE bytes, and delete the data from the runoff. */
if (Dynarr_length (str->runoff) > 0)
{
- size_t chunk = min (size, (size_t) Dynarr_length (str->runoff));
+ Lstream_data_count chunk = min (size, (Lstream_data_count) Dynarr_length (str->runoff));
memcpy (data, Dynarr_atp (str->runoff, 0), chunk);
Dynarr_delete_many (str->runoff, 0, chunk);
data += chunk;
return data - orig_data;
}
-static ssize_t
-decoding_writer (Lstream *stream, const unsigned char *data, size_t size)
+static Lstream_data_count
+decoding_writer (Lstream *stream, const unsigned char *data, Lstream_data_count size)
{
struct decoding_stream *str = DECODING_STREAM_DATA (stream);
- ssize_t retval;
+ Lstream_data_count retval;
/* Decode all our data into the runoff, and then attempt to write
it all out to the other end. Remove whatever chunk we succeeded
static void
mule_decode (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
char tempbuf[1024]; /* some random amount */
Bufpos newpos, even_newer_pos;
Bufpos oldpos = lisp_buffer_stream_startpos (istr);
- ssize_t size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf));
+ Lstream_data_count size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf));
if (!size_in_bytes)
break;
#endif /* MULE */
};
-static ssize_t encoding_reader (Lstream *stream, unsigned char *data, size_t size);
-static ssize_t encoding_writer (Lstream *stream, const unsigned char *data,
- size_t size);
+static Lstream_data_count encoding_reader (Lstream *stream, unsigned char *data, Lstream_data_count size);
+static Lstream_data_count encoding_writer (Lstream *stream, const unsigned char *data,
+ Lstream_data_count size);
static int encoding_rewinder (Lstream *stream);
static int encoding_seekable_p (Lstream *stream);
static int encoding_flusher (Lstream *stream);
/* Read SIZE bytes of data and store it into DATA. We are a encoding stream
so we read data from the other end, encode it, and store it into DATA. */
-static ssize_t
-encoding_reader (Lstream *stream, unsigned char *data, size_t size)
+static Lstream_data_count
+encoding_reader (Lstream *stream, unsigned char *data, Lstream_data_count size)
{
struct encoding_stream *str = ENCODING_STREAM_DATA (stream);
unsigned char *orig_data = data;
- ssize_t read_size;
+ Lstream_data_count read_size;
int error_occurred = 0;
/* We need to interface to mule_encode(), which expects to take some
return data - orig_data;
}
-static ssize_t
-encoding_writer (Lstream *stream, const unsigned char *data, size_t size)
+static Lstream_data_count
+encoding_writer (Lstream *stream, const unsigned char *data, Lstream_data_count size)
{
struct encoding_stream *str = ENCODING_STREAM_DATA (stream);
- ssize_t retval;
+ Lstream_data_count retval;
/* Encode all our data into the runoff, and then attempt to write
it all out to the other end. Remove whatever chunk we succeeded
static void
mule_encode (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct encoding_stream *str = ENCODING_STREAM_DATA (encoding);
char tempbuf[1024]; /* some random amount */
Bufpos newpos, even_newer_pos;
Bufpos oldpos = lisp_buffer_stream_startpos (istr);
- ssize_t size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf));
+ Lstream_data_count size_in_bytes = Lstream_read (istr, tempbuf, sizeof (tempbuf));
if (!size_in_bytes)
break;
((c) >= 0xA1 && (c) <= 0xDF)
static int
-detect_coding_sjis (struct detection_state *st, const Extbyte *src, size_t n)
+detect_coding_sjis (struct detection_state *st, const Extbyte *src, Lstream_data_count n)
{
while (n--)
{
static void
decode_coding_sjis (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
unsigned int flags = str->flags;
static void
encode_coding_sjis (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct encoding_stream *str = ENCODING_STREAM_DATA (encoding);
unsigned int flags = str->flags;
} while (0)
static int
-detect_coding_big5 (struct detection_state *st, const Extbyte *src, size_t n)
+detect_coding_big5 (struct detection_state *st, const Extbyte *src, Lstream_data_count n)
{
while (n--)
{
static void
decode_coding_big5 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
unsigned int flags = str->flags;
static void
encode_coding_big5 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
unsigned char c;
struct encoding_stream *str = ENCODING_STREAM_DATA (encoding);
}
static int
-detect_coding_ucs4 (struct detection_state *st, const Extbyte *src, size_t n)
+detect_coding_ucs4 (struct detection_state *st, const Extbyte *src, Lstream_data_count n)
{
while (n--)
{
static void
decode_coding_ucs4 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
unsigned int flags = str->flags;
static void
encode_coding_ucs4 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct encoding_stream *str = ENCODING_STREAM_DATA (encoding);
unsigned int flags = str->flags;
/************************************************************************/
static int
-detect_coding_utf8 (struct detection_state *st, const Extbyte *src, size_t n)
+detect_coding_utf8 (struct detection_state *st, const Extbyte *src, Lstream_data_count n)
{
while (n--)
{
static void
decode_coding_utf8 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
unsigned int flags = str->flags;
static void
encode_coding_utf8 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct encoding_stream *str = ENCODING_STREAM_DATA (encoding);
unsigned int flags = str->flags;
If CHECK_INVALID_CHARSETS is non-zero, check for designation
or invocation of an invalid character set and treat that as
- an unrecognized escape sequence. */
+ an unrecognized escape sequence.
+
+ ********************************************************************
+
+ #### Strategies for error annotation and coding orthogonalization
+
+ We really want to separate out a number of things. Conceptually,
+ there is a nested syntax.
+
+ At the top level is the ISO 2022 extension syntax, including charset
+ designation and invocation, and certain auxiliary controls such as the
+ ISO 6429 direction specification. These are octet-oriented, with the
+ single exception (AFAIK) of the "exit Unicode" sequence which uses the
+ UTF's natural width (1 byte for UTF-7 and UTF-8, 2 bytes for UCS-2 and
+ UTF-16, and 4 bytes for UCS-4 and UTF-32). This will be treated as a
+ (deprecated) special case in Unicode processing.
+
+ The middle layer is ISO 2022 character interpretation. This will depend
+ on the current state of the ISO 2022 registers, and assembles octets
+ into the character's internal representation.
+
+ The lowest level is translating system control conventions. At present
+ this is restricted to newline translation, but one could imagine doing
+ tab conversion or line wrapping here. "Escape from Unicode" processing
+ would be done at this level.
+
+ At each level the parser will verify the syntax. In the case of a
+ syntax error or warning (such as a redundant escape sequence that affects
+ no characters), the parser will take some action, typically inserting the
+ erroneous octets directly into the output and creating an annotation
+ which can be used by higher level I/O to mark the affected region.
+
+ This should make it possible to do something sensible about separating
+ newline convention processing from character construction, and about
+ preventing ISO 2022 escape sequences from being recognized
+ inappropriately.
+
+ The basic strategy will be to have octet classification tables, and
+ switch processing according to the table entry.
+
+ It's possible that, by doing the processing with tables of functions or
+ the like, the parser can be used for both detection and translation. */
static int
parse_iso2022_esc (Lisp_Object codesys, struct iso2022_decoder *iso,
}
static int
-detect_coding_iso2022 (struct detection_state *st, const Extbyte *src, size_t n)
+detect_coding_iso2022 (struct detection_state *st, const Extbyte *src, Lstream_data_count n)
{
int mask;
static void
decode_coding_iso2022 (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
unsigned int flags = str->flags;
static void
encode_coding_iso2022 (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
unsigned char charmask, c;
unsigned char char_boundary;
interpreted as being in any particular decoding. */
static void
decode_coding_no_conversion (Lstream *decoding, const Extbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
struct decoding_stream *str = DECODING_STREAM_DATA (decoding);
unsigned int flags = str->flags;
static void
encode_coding_no_conversion (Lstream *encoding, const Bufbyte *src,
- unsigned_char_dynarr *dst, size_t n)
+ unsigned_char_dynarr *dst, Lstream_data_count n)
{
unsigned char c;
struct encoding_stream *str = ENCODING_STREAM_DATA (encoding);
int i;
fcd = xnew (struct file_coding_dump);
- dumpstruct (&fcd, &fcd_description);
+ dump_add_root_struct_ptr (&fcd, &fcd_description);
/* Initialize to something reasonable ... */
- for (i = 0; i <= CODING_CATEGORY_LAST; i++)
+ for (i = 0; i < CODING_CATEGORY_LAST; i++)
{
fcd->coding_category_system[i] = Qnil;
fcd->coding_category_by_priority[i] = i;
make_lisp_hash_table (50, HASH_TABLE_NON_WEAK, HASH_TABLE_EQ);
the_codesys_prop_dynarr = Dynarr_new (codesys_prop);
- dumpstruct (&the_codesys_prop_dynarr, &codesys_prop_dynarr_description);
+ dump_add_root_struct_ptr (&the_codesys_prop_dynarr, &codesys_prop_dynarr_description);
#define DEFINE_CODESYS_PROP(Prop_Type, Sym) do \
{ \