/* Coding system handler (conversion, detection, etc).
- Copyright (C) 2001-2014 Free Software Foundation, Inc.
+ Copyright (C) 2001-2015 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)
Lisp_Object Vcoding_system_hash_table;
-static Lisp_Object Qcoding_system, Qeol_type;
-static Lisp_Object Qcoding_aliases;
-Lisp_Object Qunix, Qdos;
-static Lisp_Object Qmac;
-Lisp_Object Qbuffer_file_coding_system;
-static Lisp_Object Qpost_read_conversion, Qpre_write_conversion;
-static Lisp_Object Qdefault_char;
-Lisp_Object Qno_conversion, Qundecided;
-Lisp_Object Qcharset, Qutf_8;
-static Lisp_Object Qiso_2022;
-static Lisp_Object Qutf_16, Qshift_jis, Qbig5;
-static Lisp_Object Qbig, Qlittle;
-static Lisp_Object Qcoding_system_history;
-static Lisp_Object Qvalid_codes;
-static Lisp_Object QCcategory, QCmnemonic, QCdefault_char;
-static Lisp_Object QCdecode_translation_table, QCencode_translation_table;
-static Lisp_Object QCpost_read_conversion, QCpre_write_conversion;
-static Lisp_Object QCascii_compatible_p;
-
-Lisp_Object Qcall_process, Qcall_process_region;
-Lisp_Object Qstart_process, Qopen_network_stream;
-static Lisp_Object Qtarget_idx;
-
-static Lisp_Object Qinsufficient_source, Qinvalid_source, Qinterrupted;
-
-/* If a symbol has this property, evaluate the value to define the
- symbol as a coding system. */
-static Lisp_Object Qcoding_system_define_form;
-
/* 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 Qcoding_system_p, Qcoding_system_error;
-
-/* Coding system emacs-mule and raw-text are for converting only
- end-of-line format. */
-Lisp_Object Qemacs_mule, Qraw_text;
-Lisp_Object Qutf_8_emacs;
-
-#if defined (WINDOWSNT) || defined (CYGWIN)
-static Lisp_Object Qutf_16le;
-#endif
-
/* Coding-systems are handed between Emacs Lisp programs and C internal
routines by the following three variables. */
/* Coding system to be used to encode text for terminal display when
#endif /* emacs */
-Lisp_Object Qtranslation_table;
-Lisp_Object Qtranslation_table_id;
-static Lisp_Object Qtranslation_table_for_decode;
-static Lisp_Object Qtranslation_table_for_encode;
-
/* Two special coding systems. */
static Lisp_Object Vsjis_coding_system;
static Lisp_Object Vbig5_coding_system;
#define CODING_ISO_BOL(coding) \
((coding)->spec.iso_2022.bol)
#define CODING_ISO_INVOKED_CHARSET(coding, plane) \
- CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane)))
+ (CODING_ISO_INVOCATION (coding, plane) < 0 ? -1 \
+ : CODING_ISO_DESIGNATION (coding, CODING_ISO_INVOCATION (coding, plane)))
#define CODING_ISO_CMP_STATUS(coding) \
(&(coding)->spec.iso_2022.cmp_status)
#define CODING_ISO_EXTSEGMENT_LEN(coding) \
Nth coding category. */
static struct coding_system coding_categories[coding_category_max];
-/*** Commonly used macros and functions ***/
-
-#ifndef min
-#define min(a, b) ((a) < (b) ? (a) : (b))
-#endif
-#ifndef max
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#endif
-
/* Encode a flag that can be nil, something else, or t as -1, 0, 1. */
static int
ONE_MORE_BYTE (c1);
if (c1 < ' ' || c1 >= 0x80
|| (id = iso_charset_table[0][c >= ','][c1]) < 0)
- /* Invalid designation sequence. Just ignore. */
- break;
+ {
+ /* Invalid designation sequence. Just ignore. */
+ if (c1 >= 0x80)
+ rejected |= (CATEGORY_MASK_ISO_7BIT
+ | CATEGORY_MASK_ISO_7_ELSE);
+ break;
+ }
}
else if (c == '$')
{
ONE_MORE_BYTE (c1);
if (c1 < ' ' || c1 >= 0x80
|| (id = iso_charset_table[1][c >= ','][c1]) < 0)
- /* Invalid designation sequence. Just ignore. */
- break;
+ {
+ /* Invalid designation sequence. Just ignore. */
+ if (c1 >= 0x80)
+ rejected |= (CATEGORY_MASK_ISO_7BIT
+ | CATEGORY_MASK_ISO_7_ELSE);
+ break;
+ }
}
else
- /* Invalid designation sequence. Just ignore it. */
- break;
+ {
+ /* Invalid designation sequence. Just ignore it. */
+ if (c >= 0x80)
+ rejected |= (CATEGORY_MASK_ISO_7BIT
+ | CATEGORY_MASK_ISO_7_ELSE);
+ break;
+ }
}
else
{
/* Invalid escape sequence. Just ignore it. */
+ if (c >= 0x80)
+ rejected |= (CATEGORY_MASK_ISO_7BIT
+ | CATEGORY_MASK_ISO_7_ELSE);
break;
}
if (inhibit_iso_escape_detection)
break;
single_shifting = 0;
- rejected |= CATEGORY_MASK_ISO_7BIT;
+ rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE;
if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
& CODING_ISO_FLAG_SINGLE_SHIFT)
{
single_shifting = 0;
break;
}
+ rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE;
if (c >= 0xA0)
{
- rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE;
found |= CATEGORY_MASK_ISO_8_1;
/* Check the length of succeeding codes of the range
0xA0..0FF. If the byte length is even, we include
: AREF (raw_text_eol_type, 2));
}
+/* Return true if CODING corresponds to raw-text coding-system. */
+
+bool
+raw_text_coding_system_p (struct coding_system *coding)
+{
+ return (coding->decoder == decode_coding_raw_text
+ && coding->encoder == encode_coding_raw_text) ? true : false;
+}
+
/* 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
doc: /* Internal use only. */)
(Lisp_Object coding_system, Lisp_Object terminal)
{
- struct terminal *term = get_terminal (terminal, 1);
+ struct terminal *term = decode_live_terminal (terminal);
struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term);
CHECK_SYMBOL (coding_system);
setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding);
(Lisp_Object terminal)
{
struct coding_system *terminal_coding
- = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1));
+ = TERMINAL_TERMINAL_CODING (decode_live_terminal (terminal));
Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id);
/* For backward compatibility, return nil if it is `undecided'. */
doc: /* Internal use only. */)
(Lisp_Object coding_system, Lisp_Object terminal)
{
- struct terminal *t = get_terminal (terminal, 1);
+ struct terminal *t = decode_live_terminal (terminal);
CHECK_SYMBOL (coding_system);
if (NILP (coding_system))
coding_system = Qno_conversion;
(Lisp_Object terminal)
{
return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING
- (get_terminal (terminal, 1))->id);
+ (decode_live_terminal (terminal))->id);
}
\f
DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist,
1, 1, 0,
- doc: "Return the property list of CODING-SYSTEM.")
+ doc: /* Return the property list of CODING-SYSTEM. */)
(Lisp_Object coding_system)
{
Lisp_Object spec, attrs;
syms_of_coding (void)
{
staticpro (&Vcoding_system_hash_table);
- {
- Lisp_Object args[2];
- args[0] = QCtest;
- args[1] = Qeq;
- Vcoding_system_hash_table = Fmake_hash_table (2, args);
- }
+ Vcoding_system_hash_table = CALLN (Fmake_hash_table, QCtest, Qeq);
staticpro (&Vsjis_coding_system);
Vsjis_coding_system = Qnil;
DEFSYM (Qcoding_system_p, "coding-system-p");
+ /* Error signaled when there's a problem with detecting a coding system. */
DEFSYM (Qcoding_system_error, "coding-system-error");
Fput (Qcoding_system_error, Qerror_conditions,
listn (CONSTYPE_PURE, 2, Qcoding_system_error, Qerror));
DEFSYM (Qvalid_codes, "valid-codes");
+ /* Coding system emacs-mule and raw-text are for converting only
+ end-of-line format. */
DEFSYM (Qemacs_mule, "emacs-mule");
DEFSYM (QCcategory, ":category");
DEFSYM (Qinsufficient_source, "insufficient-source");
DEFSYM (Qinvalid_source, "invalid-source");
DEFSYM (Qinterrupted, "interrupted");
+
+ /* If a symbol has this property, evaluate the value to define the
+ symbol as a coding system. */
DEFSYM (Qcoding_system_define_form, "coding-system-define-form");
defsubr (&Scoding_system_p);
Use of this variable for character code unification was rendered
obsolete in Emacs 23.1 and later, since Unicode is now the basis of
internal character representation. */);
- Vtranslation_table_for_input = Qnil;
-
- {
- Lisp_Object args[coding_arg_undecided_max];
- Lisp_Object plist[16];
- int i;
-
- for (i = 0; i < coding_arg_undecided_max; i++)
- args[i] = Qnil;
-
- plist[0] = intern_c_string (":name");
- plist[1] = args[coding_arg_name] = Qno_conversion;
- plist[2] = intern_c_string (":mnemonic");
- plist[3] = args[coding_arg_mnemonic] = make_number ('=');
- plist[4] = intern_c_string (":coding-type");
- plist[5] = args[coding_arg_coding_type] = Qraw_text;
- plist[6] = intern_c_string (":ascii-compatible-p");
- plist[7] = args[coding_arg_ascii_compatible_p] = Qt;
- plist[8] = intern_c_string (":default-char");
- plist[9] = args[coding_arg_default_char] = make_number (0);
- plist[10] = intern_c_string (":for-unibyte");
- plist[11] = args[coding_arg_for_unibyte] = Qt;
- plist[12] = intern_c_string (":docstring");
- plist[13] = build_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_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[1] = args[coding_arg_name] = Qundecided;
- plist[3] = args[coding_arg_mnemonic] = make_number ('-');
- plist[5] = args[coding_arg_coding_type] = Qundecided;
- /* This is already set.
- plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */
- 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_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);
- args[coding_arg_undecided_inhibit_null_byte_detection] = make_number (0);
- args[coding_arg_undecided_inhibit_iso_escape_detection] = make_number (0);
- Fdefine_coding_system_internal (coding_arg_undecided_max, args);
- }
+ Vtranslation_table_for_input = Qnil;
+
+ Lisp_Object args[coding_arg_undecided_max];
+ memclear (args, sizeof args);
+
+ Lisp_Object plist[] =
+ {
+ QCname,
+ args[coding_arg_name] = Qno_conversion,
+ QCmnemonic,
+ args[coding_arg_mnemonic] = make_number ('='),
+ intern_c_string (":coding-type"),
+ args[coding_arg_coding_type] = Qraw_text,
+ QCascii_compatible_p,
+ args[coding_arg_ascii_compatible_p] = Qt,
+ QCdefault_char,
+ args[coding_arg_default_char] = make_number (0),
+ intern_c_string (":for-unibyte"),
+ args[coding_arg_for_unibyte] = Qt,
+ intern_c_string (":docstring"),
+ (build_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.")),
+ intern_c_string (":eol-type"),
+ args[coding_arg_eol_type] = Qunix,
+ };
+ args[coding_arg_plist] = CALLMANY (Flist, plist);
+ Fdefine_coding_system_internal (coding_arg_max, args);
+
+ plist[1] = args[coding_arg_name] = Qundecided;
+ plist[3] = args[coding_arg_mnemonic] = make_number ('-');
+ plist[5] = args[coding_arg_coding_type] = Qundecided;
+ /* This is already set.
+ plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */
+ 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_pure_c_string ("No conversion on encoding, "
+ "automatic conversion on decoding.");
+ plist[15] = args[coding_arg_eol_type] = Qnil;
+ args[coding_arg_plist] = CALLMANY (Flist, plist);
+ args[coding_arg_undecided_inhibit_null_byte_detection] = make_number (0);
+ args[coding_arg_undecided_inhibit_iso_escape_detection] = make_number (0);
+ Fdefine_coding_system_internal (coding_arg_undecided_max, args);
setup_coding_system (Qno_conversion, &safe_terminal_coding);
- {
- int i;
+ for (int i = 0; i < coding_category_max; i++)
+ Fset (AREF (Vcoding_category_table, i), Qno_conversion);
- for (i = 0; i < coding_category_max; i++)
- Fset (AREF (Vcoding_category_table, i), Qno_conversion);
- }
#if defined (DOS_NT)
system_eol_type = Qdos;
#else