/* Coding system handler (conversion, detection, etc).
- Copyright (C) 2001-2013 Free Software Foundation, Inc.
+ Copyright (C) 2001-2014 Free Software Foundation, Inc.
Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
2005, 2006, 2007, 2008, 2009, 2010, 2011
National Institute of Advanced Industrial Science and Technology (AIST)
#define CODING_ISO_FLAG_USE_OLDJIS 0x10000
+#define CODING_ISO_FLAG_LEVEL_4 0x20000
+
#define CODING_ISO_FLAG_FULL_SUPPORT 0x100000
/* A character to be produced on output if encoding of the original
bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
bool bom_found = 0;
- int nchars = coding->head_ascii;
+ ptrdiff_t nchars = coding->head_ascii;
int eol_seen = coding->eol_seen;
detect_info->checked |= CATEGORY_MASK_UTF_8;
means that we found a valid non-ASCII characters. */
detect_info->found |= CATEGORY_MASK_UTF_8_AUTO | CATEGORY_MASK_UTF_8_NOSIG;
}
+ coding->detected_utf8_bytes = src_base - coding->source;
coding->detected_utf8_chars = nchars;
return 1;
}
break;
}
+ /* In the simple case, rapidly handle ordinary characters */
+ if (multibytep && ! eol_dos
+ && charbuf < charbuf_end - 6 && src < src_end - 6)
+ {
+ while (charbuf < charbuf_end - 6 && src < src_end - 6)
+ {
+ c1 = *src;
+ if (c1 & 0x80)
+ break;
+ src++;
+ consumed_chars++;
+ *charbuf++ = c1;
+
+ c1 = *src;
+ if (c1 & 0x80)
+ break;
+ src++;
+ consumed_chars++;
+ *charbuf++ = c1;
+
+ c1 = *src;
+ if (c1 & 0x80)
+ break;
+ src++;
+ consumed_chars++;
+ *charbuf++ = c1;
+
+ c1 = *src;
+ if (c1 & 0x80)
+ break;
+ src++;
+ consumed_chars++;
+ *charbuf++ = c1;
+ }
+ /* If we handled at least one character, restart the main loop. */
+ if (src != src_base)
+ continue;
+ }
+
if (byte_after_cr >= 0)
c1 = byte_after_cr, byte_after_cr = -1;
else
int charset_ID;
unsigned code;
int c;
- int consumed_chars = 0;
+ ptrdiff_t consumed_chars = 0;
bool mseq_found = 0;
ONE_MORE_BYTE (c);
if (! single_shifting
&& ! (rejected & CATEGORY_MASK_ISO_8_2))
{
- int len = 1;
+ ptrdiff_t len = 1;
while (src < src_end)
{
src_base = src;
else
charset = CHARSET_FROM_ID (charset_id_2);
ONE_MORE_BYTE (c1);
- if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0))
+ if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)
+ || (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)
+ && ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LEVEL_4)
+ ? c1 >= 0x80 : c1 < 0x80)))
goto invalid_code;
break;
else
charset = CHARSET_FROM_ID (charset_id_3);
ONE_MORE_BYTE (c1);
- if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0))
+ if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)
+ || (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)
+ && ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LEVEL_4)
+ ? c1 >= 0x80 : c1 < 0x80)))
goto invalid_code;
break;
{
/* We have to produce designation sequences if any now. */
unsigned char desig_buf[16];
- int nbytes;
+ ptrdiff_t nbytes;
ptrdiff_t offset;
charset_map_loaded = 0;
source_charbuf[i++] = *p++;
if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK)
- ccl->last_block = 1;
+ ccl->last_block = true;
/* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */
charset_map_loaded = 0;
ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf,
CODING_GET_INFO (coding, attrs, charset_list);
if (coding->consumed_char == coding->src_chars
&& coding->mode & CODING_MODE_LAST_BLOCK)
- ccl->last_block = 1;
+ ccl->last_block = true;
do
{
coding->safe_charsets = SDATA (val);
coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs));
coding->carryover_bytes = 0;
+ coding->raw_destination = 0;
coding_type = CODING_ATTR_TYPE (attrs);
if (EQ (coding_type, Qundecided))
EOL_SEEN_LF, EOL_SEEN_CR, and EOL_SEEN_CRLF, but the value is
reliable only when all the source bytes are ASCII. */
-static int
+static ptrdiff_t
check_ascii (struct coding_system *coding)
{
const unsigned char *src, *end;
the value is reliable only when all the source bytes are valid
UTF-8. */
-static int
+static ptrdiff_t
check_utf_8 (struct coding_system *coding)
{
const unsigned char *src, *end;
int eol_seen;
- int nchars = coding->head_ascii;
+ ptrdiff_t nchars = coding->head_ascii;
if (coding->head_ascii < 0)
check_ascii (coding);
if (CHAR_TABLE_P (standard))
{
if (CONSP (translation_table))
- translation_table = nconc2 (translation_table,
- Fcons (standard, Qnil));
+ translation_table = nconc2 (translation_table, list1 (standard));
else
- translation_table = Fcons (translation_table,
- Fcons (standard, Qnil));
+ translation_table = list2 (translation_table, standard);
}
}
coding->carryover_bytes = 0;
if (coding->consumed < coding->src_bytes)
{
- int nbytes = coding->src_bytes - coding->consumed;
+ ptrdiff_t nbytes = coding->src_bytes - coding->consumed;
const unsigned char *src;
coding_set_source (coding);
/* We found a composition. Store the corresponding
annotation data in BUF. */
int *head = buf;
- enum composition_method method = COMPOSITION_METHOD (prop);
+ enum composition_method method = composition_method (prop);
int nchars = COMPOSITION_LENGTH (prop);
ADD_COMPOSITION_DATA (buf, nchars, 0, method);
}
-static Lisp_Object
+static void
code_conversion_restore (Lisp_Object arg)
{
Lisp_Object current, workbuf;
}
set_buffer_internal (XBUFFER (current));
UNGCPRO;
- return Qnil;
}
Lisp_Object
coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters));
coding->head_ascii = -1;
- coding->detected_utf8_chars = -1;
+ coding->detected_utf8_bytes = coding->detected_utf8_chars = -1;
coding->eol_seen = EOL_SEEN_NONE;
if (CODING_REQUIRE_DETECTION (coding))
detect_coding (coding);
if (chars != bytes)
{
/* There exists a non-ASCII byte. */
- if (EQ (CODING_ATTR_TYPE (attrs), Qutf_8))
+ if (EQ (CODING_ATTR_TYPE (attrs), Qutf_8)
+ && coding->detected_utf8_bytes == coding->src_bytes)
{
if (coding->detected_utf8_chars >= 0)
chars = coding->detected_utf8_chars;
{
if (BUFFERP (coding->dst_object))
coding->dst_object = Fbuffer_string ();
+ else if (coding->raw_destination)
+ /* This is used to avoid creating huge Lisp string.
+ NOTE: caller who sets `raw_destination' is also
+ responsible for freeing `destination' buffer. */
+ coding->dst_object = Qnil;
else
{
coding->dst_object
}
Lisp_Object
-from_unicode_buffer (const wchar_t* wstr)
+from_unicode_buffer (const wchar_t *wstr)
{
return from_unicode (
make_unibyte_string (
- (char*) wstr,
+ (char *) wstr,
/* we get one of the two final 0 bytes for free. */
1 + sizeof (wchar_t) * wcslen (wstr)));
}
{
detect_info.found = CATEGORY_MASK_RAW_TEXT;
id = CODING_SYSTEM_ID (Qno_conversion);
- val = Fcons (make_number (id), Qnil);
+ val = list1 (make_number (id));
}
else if (! detect_info.rejected && ! detect_info.found)
{
detect_info.found = CATEGORY_MASK_ANY;
id = coding_categories[coding_category_undecided].id;
- val = Fcons (make_number (id), Qnil);
+ val = list1 (make_number (id));
}
else if (highest)
{
if (detect_info.found)
{
detect_info.found = 1 << category;
- val = Fcons (make_number (this->id), Qnil);
+ val = list1 (make_number (this->id));
}
else
for (i = 0; i < coding_category_raw_text; i++)
{
detect_info.found = 1 << coding_priorities[i];
id = coding_categories[coding_priorities[i]].id;
- val = Fcons (make_number (id), Qnil);
+ val = list1 (make_number (id));
break;
}
}
found |= 1 << category;
id = coding_categories[category].id;
if (id >= 0)
- val = Fcons (make_number (id), val);
+ val = list1 (make_number (id));
}
}
for (i = coding_category_raw_text - 1; i >= 0; i--)
this = coding_categories + coding_category_utf_8_sig;
else
this = coding_categories + coding_category_utf_8_nosig;
- val = Fcons (make_number (this->id), Qnil);
+ val = list1 (make_number (this->id));
}
}
else if (base_category == coding_category_utf_16_auto)
this = coding_categories + coding_category_utf_16_be_nosig;
else
this = coding_categories + coding_category_utf_16_le_nosig;
- val = Fcons (make_number (this->id), Qnil);
+ val = list1 (make_number (this->id));
}
}
else
{
detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs));
- val = Fcons (make_number (coding.id), Qnil);
+ val = list1 (make_number (coding.id));
}
/* Then, detect eol-format if necessary. */
attrs = AREF (CODING_SYSTEM_SPEC (elt), 0);
ASET (attrs, coding_attr_trans_tbl,
get_translation_table (attrs, 1, NULL));
- list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list);
+ list = Fcons (list2 (elt, attrs), list);
}
if (STRINGP (start))
setup_coding_system (coding_system, &coding);
coding.mode |= CODING_MODE_LAST_BLOCK;
+ if (BUFFERP (dst_object) && !EQ (dst_object, src_object))
+ {
+ struct buffer *buf = XBUFFER (dst_object);
+ ptrdiff_t buf_pt = BUF_PT (buf);
+
+ invalidate_buffer_caches (buf, buf_pt, buf_pt);
+ }
+
if (encodep)
encode_coding_object (&coding, src_object, from, from_byte, to, to_byte,
dst_object);
coding.mode |= CODING_MODE_LAST_BLOCK;
chars = SCHARS (string);
bytes = SBYTES (string);
+
+ if (BUFFERP (dst_object))
+ {
+ struct buffer *buf = XBUFFER (dst_object);
+ ptrdiff_t buf_pt = BUF_PT (buf);
+
+ invalidate_buffer_caches (buf, buf_pt, buf_pt);
+ }
+
if (encodep)
encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object);
else
return code_convert_string (string, coding_system, Qt, encodep, 0, 1);
}
+/* Encode or decode a file name, to or from a unibyte string suitable
+ for passing to C library functions. */
+Lisp_Object
+decode_file_name (Lisp_Object fname)
+{
+#ifdef WINDOWSNT
+ /* The w32 build pretends to use UTF-8 for file-name encoding, and
+ converts the file names either to UTF-16LE or to the system ANSI
+ codepage internally, depending on the underlying OS; see w32.c. */
+ if (! NILP (Fcoding_system_p (Qutf_8)))
+ return code_convert_string_norecord (fname, Qutf_8, 0);
+ return fname;
+#else /* !WINDOWSNT */
+ if (! NILP (Vfile_name_coding_system))
+ return code_convert_string_norecord (fname, Vfile_name_coding_system, 0);
+ else if (! NILP (Vdefault_file_name_coding_system))
+ return code_convert_string_norecord (fname,
+ Vdefault_file_name_coding_system, 0);
+ else
+ return fname;
+#endif
+}
+
+Lisp_Object
+encode_file_name (Lisp_Object fname)
+{
+ /* This is especially important during bootstrap and dumping, when
+ file-name encoding is not yet known, and therefore any non-ASCII
+ file names are unibyte strings, and could only be thrashed if we
+ try to encode them. */
+ if (!STRING_MULTIBYTE (fname))
+ return fname;
+#ifdef WINDOWSNT
+ /* The w32 build pretends to use UTF-8 for file-name encoding, and
+ converts the file names either to UTF-16LE or to the system ANSI
+ codepage internally, depending on the underlying OS; see w32.c. */
+ if (! NILP (Fcoding_system_p (Qutf_8)))
+ return code_convert_string_norecord (fname, Qutf_8, 1);
+ return fname;
+#else /* !WINDOWSNT */
+ if (! NILP (Vfile_name_coding_system))
+ return code_convert_string_norecord (fname, Vfile_name_coding_system, 1);
+ else if (! NILP (Vdefault_file_name_coding_system))
+ return code_convert_string_norecord (fname,
+ Vdefault_file_name_coding_system, 1);
+ else
+ return fname;
+#endif
+}
DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string,
2, 4, 0,
tset_charset_list
(term, (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK
? coding_charset_list (terminal_coding)
- : Fcons (make_number (charset_ascii), Qnil)));
+ : list1 (make_number (charset_ascii))));
return Qnil;
}
{
dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp)));
if (dim < dim2)
- tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil));
+ tmp = list2 (XCAR (tail), tmp);
else
- tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil));
+ tmp = list2 (tmp, XCAR (tail));
}
else
{
break;
}
if (NILP (tmp2))
- tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil));
+ tmp = nconc2 (tmp, list1 (XCAR (tail)));
else
{
XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2)));
&& ! EQ (eol_type, Qmac))
error ("Invalid eol-type");
- aliases = Fcons (name, Qnil);
+ aliases = list1 (name);
if (NILP (eol_type))
{
Lisp_Object this_spec, this_name, this_aliases, this_eol_type;
this_name = AREF (eol_type, i);
- this_aliases = Fcons (this_name, Qnil);
+ this_aliases = list1 (this_name);
this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac);
this_spec = make_uninit_vector (3);
ASET (this_spec, 0, attrs);
list. */
while (!NILP (XCDR (aliases)))
aliases = XCDR (aliases);
- XSETCDR (aliases, Fcons (alias, Qnil));
+ XSETCDR (aliases, list1 (alias));
eol_type = AREF (spec, 2);
if (VECTORP (eol_type))
Fput (Qcoding_system_error, Qerror_message,
build_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_c_string ("char-table-extra-slots");
-
DEFSYM (Qtranslation_table, "translation-table");
Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2));
DEFSYM (Qtranslation_table_id, "translation-table-id");