[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Emacs-diffs] Changes to emacs/src/coding.h,v
|
From: |
Miles Bader |
|
Subject: |
[Emacs-diffs] Changes to emacs/src/coding.h,v |
|
Date: |
Fri, 01 Feb 2008 16:02:24 +0000 |
CVSROOT: /cvsroot/emacs
Module name: emacs
Changes by: Miles Bader <miles> 08/02/01 16:01:31
Index: src/coding.h
===================================================================
RCS file: /cvsroot/emacs/emacs/src/coding.h,v
retrieving revision 1.87
retrieving revision 1.88
diff -u -b -r1.87 -r1.88
--- src/coding.h 8 Jan 2008 20:44:34 -0000 1.87
+++ src/coding.h 1 Feb 2008 16:00:58 -0000 1.88
@@ -5,6 +5,9 @@
2005, 2006, 2007, 2008
National Institute of Advanced Industrial Science and Technology (AIST)
Registration Number H14PRO021
+ Copyright (C) 2003
+ National Institute of Advanced Industrial Science and Technology (AIST)
+ Registration Number H13PRO009
This file is part of GNU Emacs.
@@ -26,306 +29,253 @@
#ifndef EMACS_CODING_H
#define EMACS_CODING_H
-#include "ccl.h"
+/* Index to arguments of Fdefine_coding_system_internal. */
-/*** EMACS' INTERNAL FORMAT (emacs-mule) section ***/
+enum define_coding_system_arg_index
+ {
+ coding_arg_name,
+ coding_arg_mnemonic,
+ coding_arg_coding_type,
+ coding_arg_charset_list,
+ coding_arg_ascii_compatible_p,
+ coding_arg_decode_translation_table,
+ coding_arg_encode_translation_table,
+ coding_arg_post_read_conversion,
+ coding_arg_pre_write_conversion,
+ coding_arg_default_char,
+ coding_arg_for_unibyte,
+ coding_arg_plist,
+ coding_arg_eol_type,
+ coding_arg_max
+ };
+
+enum define_coding_iso2022_arg_index
+ {
+ coding_arg_iso2022_initial = coding_arg_max,
+ coding_arg_iso2022_reg_usage,
+ coding_arg_iso2022_request,
+ coding_arg_iso2022_flags,
+ coding_arg_iso2022_max
+ };
-/* All code (1-byte) of Emacs' internal format is classified into one
- of the followings. See also `charset.h'. */
-enum emacs_code_class_type
- {
- EMACS_control_code, /* Control codes in the range
- 0x00..0x1F and 0x7F except for the
- following two codes. */
- EMACS_linefeed_code, /* 0x0A (linefeed) to denote
- end-of-line. */
- EMACS_carriage_return_code, /* 0x0D (carriage-return) to be used
- in selective display mode. */
- EMACS_ascii_code, /* ASCII characters. */
- EMACS_leading_code_2, /* Base leading code of official
- TYPE9N character. */
- EMACS_leading_code_3, /* Base leading code of private TYPE9N
- or official TYPE9Nx9N character. */
- EMACS_leading_code_4, /* Base leading code of private
- TYPE9Nx9N character. */
- EMACS_invalid_code /* Invalid code, i.e. a base leading
- code not yet assigned to any
- charset, or a code of the range
- 0xA0..0xFF. */
+enum define_coding_utf16_arg_index
+ {
+ coding_arg_utf16_bom = coding_arg_max,
+ coding_arg_utf16_endian,
+ coding_arg_utf16_max
+ };
+
+enum define_coding_ccl_arg_index
+ {
+ coding_arg_ccl_decoder = coding_arg_max,
+ coding_arg_ccl_encoder,
+ coding_arg_ccl_valids,
+ coding_arg_ccl_max
};
-extern enum emacs_code_class_type emacs_code_class[256];
+/* Hash table for all coding systems. Keys are coding system symbols
+ and values are spec vectors of the corresponding coding system. A
+ spec vector has the form [ ATTRS ALIASES EOL-TYPE ]. ATTRS is a
+ vector of attribute of the coding system. ALIASES is a list of
+ aliases (symbols) of the coding system. EOL-TYPE is `unix', `dos',
+ `mac' or a vector of coding systems (symbols). */
-/*** ISO2022 section ***/
+extern Lisp_Object Vcoding_system_hash_table;
-/* Macros to define code of control characters for ISO2022's functions. */
- /* 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 */
-#define ISO_CODE_ESC 0x1B /* escape */
-#define ISO_CODE_SS2 0x8E /* single-shift-2 */
-#define ISO_CODE_SS3 0x8F /* single-shift-3 */
-#define ISO_CODE_CSI 0x9B /* control-sequence-introduce */
-
-/* All code (1-byte) of ISO2022 is classified into one of the
- followings. */
-enum iso_code_class_type
- {
- ISO_control_0, /* Control codes in the range
- 0x00..0x1F and 0x7F, except for the
- following 5 codes. */
- ISO_carriage_return, /* ISO_CODE_CR (0x0D) */
- ISO_shift_out, /* ISO_CODE_SO (0x0E) */
- ISO_shift_in, /* ISO_CODE_SI (0x0F) */
- ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */
- ISO_escape, /* ISO_CODE_SO (0x1B) */
- ISO_control_1, /* Control codes in the range
- 0x80..0x9F, except for the
- following 3 codes. */
- ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */
- ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */
- ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */
- ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */
- ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */
- ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */
- ISO_graphic_plane_1 /* Graphic codes in the range
0xA1..0xFE. */
+
+/* Enumeration of coding system type. */
+
+enum coding_system_type
+ {
+ coding_type_charset,
+ coding_type_utf_8,
+ coding_type_utf_16,
+ coding_type_iso_2022,
+ coding_type_emacs_mule,
+ coding_type_sjis,
+ coding_type_ccl,
+ coding_type_raw_text,
+ coding_type_undecided,
+ coding_type_max
+ };
+
+
+/* Enumeration of end-of-line format type. */
+
+enum end_of_line_type
+ {
+ eol_lf, /* Line-feed only, same as Emacs' internal
+ format. */
+ eol_crlf, /* Sequence of carriage-return and
+ line-feed. */
+ eol_cr, /* Carriage-return only. */
+ eol_any, /* Accept any of above. Produce line-feed
+ only. */
+ eol_undecided, /* This value is used to denote that the
+ eol-type is not yet undecided. */
+ eol_type_max
};
-/** The macros CODING_FLAG_ISO_XXX defines a flag bit of the `flags'
- element in the structure `coding_system'. This information is used
- while encoding a text to ISO2022. **/
+/* Enumeration of index to an attribute vector of a coding system. */
-/* If set, produce short-form designation sequence (e.g. ESC $ A)
- instead of long-form sequence (e.g. ESC $ ( A). */
-#define CODING_FLAG_ISO_SHORT_FORM 0x0001
+enum coding_attr_index
+ {
+ coding_attr_base_name,
+ coding_attr_docstring,
+ coding_attr_mnemonic,
+ coding_attr_type,
+ coding_attr_charset_list,
+ coding_attr_ascii_compat,
+ coding_attr_decode_tbl,
+ coding_attr_encode_tbl,
+ coding_attr_trans_tbl,
+ coding_attr_post_read,
+ coding_attr_pre_write,
+ coding_attr_default_char,
+ coding_attr_for_unibyte,
+ coding_attr_plist,
+
+ coding_attr_category,
+ coding_attr_safe_charsets,
+
+ /* The followings are extra attributes for each type. */
+ coding_attr_charset_valids,
+
+ coding_attr_ccl_decoder,
+ coding_attr_ccl_encoder,
+ coding_attr_ccl_valids,
+
+ coding_attr_iso_initial,
+ coding_attr_iso_usage,
+ coding_attr_iso_request,
+ coding_attr_iso_flags,
-/* If set, reset graphic planes and registers at end-of-line to the
- initial state. */
-#define CODING_FLAG_ISO_RESET_AT_EOL 0x0002
+ coding_attr_utf_16_bom,
+ coding_attr_utf_16_endian,
-/* If set, reset graphic planes and registers before any control
- characters to the initial state. */
-#define CODING_FLAG_ISO_RESET_AT_CNTL 0x0004
+ coding_attr_emacs_mule_full,
-/* If set, encode by 7-bit environment. */
-#define CODING_FLAG_ISO_SEVEN_BITS 0x0008
+ coding_attr_last_index
+ };
-/* If set, use locking-shift function. */
-#define CODING_FLAG_ISO_LOCKING_SHIFT 0x0010
-/* If set, use single-shift function. Overwrite
- CODING_FLAG_ISO_LOCKING_SHIFT. */
-#define CODING_FLAG_ISO_SINGLE_SHIFT 0x0020
+/* Macros to access an element of an attribute vector. */
-/* If set, designate JISX0201-Roman instead of ASCII. */
-#define CODING_FLAG_ISO_USE_ROMAN 0x0040
+#define CODING_ATTR_BASE_NAME(attrs) AREF (attrs, coding_attr_base_name)
+#define CODING_ATTR_TYPE(attrs) AREF (attrs, coding_attr_type)
+#define CODING_ATTR_CHARSET_LIST(attrs) AREF (attrs,
coding_attr_charset_list)
+#define CODING_ATTR_MNEMONIC(attrs) AREF (attrs, coding_attr_mnemonic)
+#define CODING_ATTR_DOCSTRING(attrs) AREF (attrs, coding_attr_docstring)
+#define CODING_ATTR_ASCII_COMPAT(attrs) AREF (attrs,
coding_attr_ascii_compat)
+#define CODING_ATTR_DECODE_TBL(attrs) AREF (attrs, coding_attr_decode_tbl)
+#define CODING_ATTR_ENCODE_TBL(attrs) AREF (attrs, coding_attr_encode_tbl)
+#define CODING_ATTR_TRANS_TBL(attrs) AREF (attrs, coding_attr_trans_tbl)
+#define CODING_ATTR_POST_READ(attrs) AREF (attrs, coding_attr_post_read)
+#define CODING_ATTR_PRE_WRITE(attrs) AREF (attrs, coding_attr_pre_write)
+#define CODING_ATTR_DEFAULT_CHAR(attrs) AREF (attrs,
coding_attr_default_char)
+#define CODING_ATTR_FOR_UNIBYTE(attrs) AREF (attrs, coding_attr_for_unibyte)
+#define CODING_ATTR_FLUSHING(attrs) AREF (attrs, coding_attr_flushing)
+#define CODING_ATTR_PLIST(attrs) AREF (attrs, coding_attr_plist)
+#define CODING_ATTR_CATEGORY(attrs) AREF (attrs, coding_attr_category)
+#define CODING_ATTR_SAFE_CHARSETS(attrs)AREF (attrs, coding_attr_safe_charsets)
-/* If set, designate JISX0208-1978 instead of JISX0208-1983. */
-#define CODING_FLAG_ISO_USE_OLDJIS 0x0080
-/* If set, do not produce ISO6429's direction specifying sequence. */
-#define CODING_FLAG_ISO_NO_DIRECTION 0x0100
+/* Return the name of a coding system specified by ID. */
+#define CODING_ID_NAME(id) \
+ (HASH_KEY (XHASH_TABLE (Vcoding_system_hash_table), id))
-/* If set, assume designation states are reset at beginning of line on
- output. */
-#define CODING_FLAG_ISO_INIT_AT_BOL 0x0200
+/* Return the attribute vector of a coding system specified by ID. */
-/* If set, designation sequence should be placed at beginning of line
- on output. */
-#define CODING_FLAG_ISO_DESIGNATE_AT_BOL 0x0400
+#define CODING_ID_ATTRS(id) \
+ (AREF (HASH_VALUE (XHASH_TABLE (Vcoding_system_hash_table), id), 0))
-/* If set, do not encode unsafe characters on output. */
-#define CODING_FLAG_ISO_SAFE 0x0800
+/* Return the list of aliases of a coding system specified by ID. */
-/* If set, extra latin codes (128..159) are accepted as a valid code
- on input. */
-#define CODING_FLAG_ISO_LATIN_EXTRA 0x1000
+#define CODING_ID_ALIASES(id) \
+ (AREF (HASH_VALUE (XHASH_TABLE (Vcoding_system_hash_table), id), 1))
-/* If set, use designation escape sequence. */
-#define CODING_FLAG_ISO_DESIGNATION 0x10000
+/* Return the eol-type of a coding system specified by ID. */
-/* A character to be produced on output if encoding of the original
- character is inhibitted by CODING_MODE_INHIBIT_UNENCODABLE_CHAR.
- It must be an ASCII character. */
-#define CODING_REPLACEMENT_CHARACTER '?'
+#define CODING_ID_EOL_TYPE(id) \
+ (AREF (HASH_VALUE (XHASH_TABLE (Vcoding_system_hash_table), id), 2))
-/* Structure of the field `spec.iso2022' in the structure `coding_system'. */
-struct iso2022_spec
-{
- /* The current graphic register invoked to each graphic plane. */
- int current_invocation[2];
- /* The current charset designated to each graphic register. */
- int current_designation[4];
+/* Return the spec vector of CODING_SYSTEM_SYMBOL. */
- /* A charset initially designated to each graphic register. */
- int initial_designation[4];
+#define CODING_SYSTEM_SPEC(coding_system_symbol) \
+ (Fgethash (coding_system_symbol, Vcoding_system_hash_table, Qnil))
- /* If not -1, it is a graphic register specified in an invalid
- designation sequence. */
- int last_invalid_designation_register;
-
- /* A graphic register to which each charset should be designated. */
- unsigned char requested_designation[MAX_CHARSET + 1];
-
- /* A revision number to be specified for each charset on encoding.
- The value 255 means no revision number for the corresponding
- charset. */
- unsigned char charset_revision_number[MAX_CHARSET + 1];
- /* Set to 1 temporarily only when graphic register 2 or 3 is invoked
- by single-shift while encoding. */
- int single_shifting;
+/* Return the ID of CODING_SYSTEM_SYMBOL. */
+
+#define CODING_SYSTEM_ID(coding_system_symbol) \
+ hash_lookup (XHASH_TABLE (Vcoding_system_hash_table), \
+ coding_system_symbol, NULL)
+
+/* Return 1 if CODING_SYSTEM_SYMBOL is a coding system. */
+
+#define CODING_SYSTEM_P(coding_system_symbol) \
+ (CODING_SYSTEM_ID (coding_system_symbol) >= 0 \
+ || (! NILP (coding_system_symbol) \
+ && ! NILP (Fcoding_system_p (coding_system_symbol))))
+
+/* Check if X is a coding system or not. */
+
+#define CHECK_CODING_SYSTEM(x) \
+ do { \
+ if (CODING_SYSTEM_ID (x) < 0 \
+ && NILP (Fcheck_coding_system (x))) \
+ wrong_type_argument (Qcoding_system_p, (x)); \
+ } while (0)
- /* Set to 1 temporarily only when processing at beginning of line. */
- int bol;
-};
-/* Macros to access each field in the structure `spec.iso2022'. */
-#define CODING_SPEC_ISO_INVOCATION(coding, plane) \
- (coding)->spec.iso2022.current_invocation[plane]
-#define CODING_SPEC_ISO_DESIGNATION(coding, reg) \
- (coding)->spec.iso2022.current_designation[reg]
-#define CODING_SPEC_ISO_INITIAL_DESIGNATION(coding, reg) \
- (coding)->spec.iso2022.initial_designation[reg]
-#define CODING_SPEC_ISO_REQUESTED_DESIGNATION(coding, charset) \
- (coding)->spec.iso2022.requested_designation[charset]
-#define CODING_SPEC_ISO_REVISION_NUMBER(coding, charset) \
- (coding)->spec.iso2022.charset_revision_number[charset]
-#define CODING_SPEC_ISO_SINGLE_SHIFTING(coding) \
- (coding)->spec.iso2022.single_shifting
-#define CODING_SPEC_ISO_BOL(coding) \
- (coding)->spec.iso2022.bol
-
-/* A value which may appear in
- coding->spec.iso2022.requested_designation indicating that the
- corresponding charset does not request any graphic register to be
- designated. */
-#define CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION 4
-
-/* Return a charset which is currently designated to the graphic plane
- PLANE in the coding-system CODING. */
-#define CODING_SPEC_ISO_PLANE_CHARSET(coding, plane) \
- ((CODING_SPEC_ISO_INVOCATION (coding, plane) < 0) \
- ? -1 \
- : CODING_SPEC_ISO_DESIGNATION (coding, \
- CODING_SPEC_ISO_INVOCATION (coding, plane)))
-
-/*** BIG5 section ***/
-
-/* Macros to denote each type of BIG5 coding system. */
-#define CODING_FLAG_BIG5_HKU 0x00 /* BIG5-HKU is one of variants of
- BIG5 developed by Hong Kong
- University. */
-#define CODING_FLAG_BIG5_ETEN 0x01 /* BIG5_ETen is one of variants
- of BIG5 developed by the
- company ETen in Taiwan. */
+/* Check if X is a coding system or not. If it is, set SEPC to the
+ spec vector of the coding system. */
+
+#define CHECK_CODING_SYSTEM_GET_SPEC(x, spec) \
+ do { \
+ spec = CODING_SYSTEM_SPEC (x); \
+ if (NILP (spec)) \
+ { \
+ Fcheck_coding_system (x); \
+ spec = CODING_SYSTEM_SPEC (x); \
+ } \
+ if (NILP (spec)) \
+ x = wrong_type_argument (Qcoding_system_p, (x)); \
+ } while (0)
+
+
+/* Check if X is a coding system or not. If it is, set ID to the
+ ID of the coding system. */
+
+#define CHECK_CODING_SYSTEM_GET_ID(x, id) \
+ do \
+ { \
+ id = CODING_SYSTEM_ID (x); \
+ if (id < 0) \
+ { \
+ Fcheck_coding_system (x); \
+ id = CODING_SYSTEM_ID (x); \
+ } \
+ if (id < 0) \
+ x = wrong_type_argument (Qcoding_system_p, (x)); \
+ } while (0)
+
/*** GENERAL section ***/
-/* Types of coding system. */
-enum coding_type
+/* Enumeration of result code of code conversion. */
+enum coding_result_code
{
- coding_type_no_conversion, /* A coding system which requires no
- conversion for reading and writing
- including end-of-line format. */
- coding_type_emacs_mule, /* A coding system used in Emacs'
- buffer and string. Requires no
- conversion for reading and writing
- except for end-of-line format. */
- coding_type_undecided, /* A coding system which requires
- automatic detection of a real
- coding system. */
- coding_type_sjis, /* SJIS coding system for Japanese. */
- coding_type_iso2022, /* Any coding system of ISO2022
- variants. */
- coding_type_big5, /* BIG5 coding system for Chinese. */
- coding_type_ccl, /* The coding system of which decoder
- and encoder are written in CCL. */
- coding_type_raw_text /* A coding system for a text
- containing random 8-bit code which
- does not require code conversion
- except for end-of-line format. */
+ CODING_RESULT_SUCCESS,
+ CODING_RESULT_INSUFFICIENT_SRC,
+ CODING_RESULT_INSUFFICIENT_DST,
+ CODING_RESULT_INCONSISTENT_EOL,
+ CODING_RESULT_INVALID_SRC,
+ CODING_RESULT_INTERRUPT,
+ CODING_RESULT_INSUFFICIENT_MEM
};
-/* Formats of end-of-line. */
-#define CODING_EOL_LF 0 /* Line-feed only, same as Emacs'
- internal format. */
-#define CODING_EOL_CRLF 1 /* Sequence of carriage-return and
- line-feed. */
-#define CODING_EOL_CR 2 /* Carriage-return only. */
-#define CODING_EOL_UNDECIDED 3 /* This value is used to denote the
- eol-type is not yet decided. */
-#define CODING_EOL_INCONSISTENT 4 /* This value is used to denote the
- eol-type is not consistent
- through the file. */
-
-/* 1 if composing. */
-#define COMPOSING_P(coding) ((int) coding->composing > (int) COMPOSITION_NO)
-
-#define COMPOSITION_DATA_SIZE 4080
-#define COMPOSITION_DATA_MAX_BUNCH_LENGTH (4 + MAX_COMPOSITION_COMPONENTS*2)
-
-/* Data structure to hold information about compositions of text that
- is being decoded or encode. ISO 2022 base code conversion routines
- handle special ESC sequences for composition specification. But,
- they can't get/put such information directly from/to a buffer in
- the deepest place. So, they store or retrieve the information
- through this structure.
-
- The encoder stores the information in this structure when it meets
- ESC sequences for composition while encoding codes, then, after all
- text codes are encoded, puts `composition' properties on the text
- by referring to the structure.
-
- The decoder at first stores the information of a text to be
- decoded, then, while decoding codes, generates ESC sequences for
- composition at proper places by referring to the structure. */
-
-struct composition_data
-{
- /* The character position of the first character to be encoded or
- decoded. START and END (see below) are relative to this
- position. */
- int char_offset;
-
- /* The composition data. These elements are repeated for each
- composition:
- LENGTH START END METHOD [ COMPONENT ... ]
- where,
- LENGTH is the number of elements for this composition.
-
- START and END are starting and ending character positions of
- the composition relative to `char_offset'.
-
- METHOD is one of `enum composing_status' specifying the way of
- composition.
-
- COMPONENT is a character or an encoded composition rule. */
- int data[COMPOSITION_DATA_SIZE];
-
- /* The number of elements in `data' currently used. */
- int used;
-
- /* Pointers to the previous and next structures. When `data' is
- filled up, another structure is allocated and linked in `next'.
- The new structure has backward link to this structure in `prev'.
- The number of chained structures depends on how many compositions
- the text being encoded or decoded contains. */
- struct composition_data *prev, *next;
-};
-
-/* Macros used for the member `result' of the struct
- coding_system. */
-#define CODING_FINISH_NORMAL 0
-#define CODING_FINISH_INSUFFICIENT_SRC 1
-#define CODING_FINISH_INSUFFICIENT_DST 2
-#define CODING_FINISH_INCONSISTENT_EOL 3
-#define CODING_FINISH_INSUFFICIENT_CMP 4
-#define CODING_FINISH_INTERRUPT 5
/* Macros used for the member `mode' of the struct coding_system. */
@@ -334,7 +284,7 @@
#define CODING_MODE_INHIBIT_INCONSISTENT_EOL 0x01
/* If set, the decoding/encoding routines treat the current data as
- the last block of the whole text to be converted, and do
+ the last block of the whole text to be converted, and do the
appropriate finishing job. */
#define CODING_MODE_LAST_BLOCK 0x02
@@ -342,65 +292,106 @@
enables selective display. */
#define CODING_MODE_SELECTIVE_DISPLAY 0x04
-/* If set, replace unencodabae characters by `?' on encoding. */
-#define CODING_MODE_INHIBIT_UNENCODABLE_CHAR 0x08
-
/* This flag is used by the decoding/encoding routines on the fly. If
set, it means that right-to-left text is being processed. */
-#define CODING_MODE_DIRECTION 0x10
+#define CODING_MODE_DIRECTION 0x08
-struct coding_system
+#define CODING_MODE_FIXED_DESTINATION 0x10
+
+/* If set, it means that the encoding routines produces some safe
+ ASCII characters (usually '?') for unsupported characters. */
+#define CODING_MODE_SAFE_ENCODING 0x20
+
+/* Structure of the field `spec.iso_2022' in the structure
+ `coding_system'. */
+struct iso_2022_spec
{
- /* Type of the coding system. */
- enum coding_type type;
+ /* Bit-wise-or of CODING_ISO_FLAG_XXX. */
+ unsigned flags;
+
+ /* The current graphic register invoked to each graphic plane. */
+ int current_invocation[2];
+
+ /* The current charset designated to each graphic register. The
+ value -1 means that not charset is designated, -2 means that
+ there was an invalid designation previously. */
+ int current_designation[4];
+
+ /* Set to 1 temporarily only when graphic register 2 or 3 is invoked
+ by single-shift while encoding. */
+ int single_shifting;
+
+ /* Set to 1 temporarily only when processing at beginning of line. */
+ int bol;
+};
- /* Type of end-of-line format (LF, CRLF, or CR) of the coding system. */
- int eol_type;
+struct ccl_spec;
+
+enum utf_16_bom_type
+ {
+ utf_16_detect_bom,
+ utf_16_without_bom,
+ utf_16_with_bom
+ };
+
+enum utf_16_endian_type
+ {
+ utf_16_big_endian,
+ utf_16_little_endian
+ };
+
+struct utf_16_spec
+{
+ enum utf_16_bom_type bom;
+ enum utf_16_endian_type endian;
+ int surrogate;
+};
+
+struct coding_detection_info
+{
+ /* Values of these members are bitwise-OR of CATEGORY_MASK_XXXs. */
+ /* Which categories are already checked. */
+ int checked;
+ /* Which categories are strongly found. */
+ int found;
+ /* Which categories are rejected. */
+ int rejected;
+};
+
+
+struct coding_system
+{
+ /* ID number of the coding system. This is an index to
+ Vcoding_system_hash_table. This value is set by
+ setup_coding_system. At the early stage of building time, this
+ value is -1 in the array coding_categories to indicate that no
+ coding-system of that category is yet defined. */
+ int id;
/* Flag bits of the coding system. The meaning of each bit is common
to all types of coding systems. */
- unsigned int common_flags;
-
- /* Flag bits of the coding system. The meaning of each bit depends
- on the type of the coding system. */
- unsigned int flags;
+ int common_flags;
/* Mode bits of the coding system. See the comments of the macros
CODING_MODE_XXX. */
unsigned int mode;
- /* The current status of composition handling. */
- int composing;
-
- /* 1 if the next character is a composition rule. */
- int composition_rule_follows;
-
- /* Information of compositions are stored here on decoding and set
- in advance on encoding. */
- struct composition_data *cmp_data;
-
- /* Index to cmp_data->data for the first element for the current
- composition. */
- int cmp_data_start;
-
- /* Index to cmp_data->data for the current element for the current
- composition. */
- int cmp_data_index;
-
/* Detailed information specific to each type of coding system. */
- union spec
+ union
{
- struct iso2022_spec iso2022;
- struct ccl_spec ccl; /* Defined in ccl.h. */
+ struct iso_2022_spec iso_2022;
+ struct ccl_spec *ccl; /* Defined in ccl.h. */
+ struct utf_16_spec utf_16;
+ int emacs_mule_full_support;
} spec;
- /* Index number of coding category of the coding system. */
- int category_idx;
+ int max_charset_id;
+ char *safe_charsets;
- /* The following two members specify how characters 128..159 are
- represented in source and destination text respectively. 1 means
- they are represented by 2-byte sequence, 0 means they are
- represented by 1-byte as is (see the comment in charset.h). */
+ /* The following two members specify how binary 8-bit code 128..255
+ are represented in source and destination text respectively. 1
+ means they are represented by 2-byte sequence, 0 means they are
+ represented by 1-byte as is (see the comment in character.h). */
unsigned src_multibyte : 1;
unsigned dst_multibyte : 1;
@@ -408,173 +399,200 @@
-1 in setup_coding_system, and updated by detect_coding. So,
when this is equal to the byte length of the text being
converted, we can skip the actual conversion process. */
- int heading_ascii;
+ int head_ascii;
/* The following members are set by encoding/decoding routine. */
- int produced, produced_char, consumed, consumed_char;
+ EMACS_INT produced, produced_char, consumed, consumed_char;
/* Number of error source data found in a decoding routine. */
int errors;
- /* Finish status of code conversion. It should be one of macros
- CODING_FINISH_XXXX. */
- int result;
-
- /* If nonzero, suppress error notification. */
- int suppress_error;
-
- /* The following members are all Lisp symbols. We don't have to
- protect them from GC because the current garbage collection
- doesn't relocate Lisp symbols. But, when it is changed, we must
- find a way to protect them. */
-
- /* Backward pointer to the Lisp symbol of the coding system. */
- Lisp_Object symbol;
-
- /* Lisp function (symbol) to be called after decoding to do
- additional conversion, or nil. */
- Lisp_Object post_read_conversion;
-
- /* Lisp function (symbol) to be called before encoding to do
- additional conversion, or nil. */
- Lisp_Object pre_write_conversion;
-
- /* Character translation tables to look up, or nil. */
- Lisp_Object translation_table_for_decode;
- Lisp_Object translation_table_for_encode;
+ /* Store the positions of error source data. */
+ EMACS_INT *error_positions;
+
+ /* Finish status of code conversion. */
+ enum coding_result_code result;
+
+ EMACS_INT src_pos, src_pos_byte, src_chars, src_bytes;
+ Lisp_Object src_object;
+ const unsigned char *source;
+
+ EMACS_INT dst_pos, dst_pos_byte, dst_bytes;
+ Lisp_Object dst_object;
+ unsigned char *destination;
+
+ /* Set to 1 if the source of conversion is not in the member
+ `charbuf', but at `src_object'. */
+ int chars_at_source;
+
+ /* If an element is non-negative, it is a character code.
+
+ If it is in the range -128..-1, it is a 8-bit character code
+ minus 256.
+
+ If it is less than -128, it specifies the start of an annotation
+ chunk. The length of the chunk is -128 minus the value of the
+ element. The following elements are OFFSET, ANNOTATION-TYPE, and
+ a sequence of actual data for the annotation. OFFSET is a
+ character position offset from dst_pos or src_pos,
+ ANNOTATION-TYPE specfies the meaning of the annotation and how to
+ handle the following data.. */
+ int *charbuf;
+ int charbuf_size, charbuf_used;
+
+ /* Set to 1 if charbuf contains an annotation. */
+ int annotated;
+
+ unsigned char carryover[64];
+ int carryover_bytes;
+
+ int default_char;
+
+ int (*detector) P_ ((struct coding_system *,
+ struct coding_detection_info *));
+ void (*decoder) P_ ((struct coding_system *));
+ int (*encoder) P_ ((struct coding_system *));
};
-/* Mask bits for (struct coding_system *)->common_flags. */
-#define CODING_REQUIRE_FLUSHING_MASK 0x01
-#define CODING_REQUIRE_DECODING_MASK 0x02
-#define CODING_REQUIRE_ENCODING_MASK 0x04
-#define CODING_REQUIRE_DETECTION_MASK 0x08
-#define CODING_ASCII_INCOMPATIBLE_MASK 0x10
+/* Meanings of bits in the member `common_flags' of the structure
+ coding_system. The lowest 8 bits are reserved for various kind of
+ annotations (currently two of them are used). */
+#define CODING_ANNOTATION_MASK 0x00FF
+#define CODING_ANNOTATE_COMPOSITION_MASK 0x0001
+#define CODING_ANNOTATE_DIRECTION_MASK 0x0002
+#define CODING_ANNOTATE_CHARSET_MASK 0x0003
+#define CODING_FOR_UNIBYTE_MASK 0x0100
+#define CODING_REQUIRE_FLUSHING_MASK 0x0200
+#define CODING_REQUIRE_DECODING_MASK 0x0400
+#define CODING_REQUIRE_ENCODING_MASK 0x0800
+#define CODING_REQUIRE_DETECTION_MASK 0x1000
+#define CODING_RESET_AT_BOL_MASK 0x2000
+
+/* Return 1 if the coding context CODING requires annotaion
+ handling. */
+#define CODING_REQUIRE_ANNOTATION(coding) \
+ ((coding)->common_flags & CODING_ANNOTATION_MASK)
+
+/* Return 1 if the coding context CODING prefers decoding into unibyte. */
+#define CODING_FOR_UNIBYTE(coding) \
+ ((coding)->common_flags & CODING_FOR_UNIBYTE_MASK)
-/* Return 1 if the coding system CODING requires specific code to be
+/* Return 1 if the coding context CODING requires specific code to be
attached at the tail of converted text. */
#define CODING_REQUIRE_FLUSHING(coding) \
((coding)->common_flags & CODING_REQUIRE_FLUSHING_MASK)
-/* Return 1 if the coding system CODING requires code conversion on
+/* Return 1 if the coding context CODING requires code conversion on
decoding. */
#define CODING_REQUIRE_DECODING(coding) \
((coding)->dst_multibyte \
|| (coding)->common_flags & CODING_REQUIRE_DECODING_MASK)
-/* Return 1 if the coding system CODING requires code conversion on
+
+/* Return 1 if the coding context CODING requires code conversion on
encoding.
The non-multibyte part of the condition is to support encoding of
unibyte strings/buffers generated by string-as-unibyte or
(set-buffer-multibyte nil) from multibyte strings/buffers. */
#define CODING_REQUIRE_ENCODING(coding) \
((coding)->src_multibyte \
- || (coding)->common_flags & CODING_REQUIRE_ENCODING_MASK)
+ || (coding)->common_flags & CODING_REQUIRE_ENCODING_MASK \
+ || (coding)->mode & CODING_MODE_SELECTIVE_DISPLAY)
+
-/* Return 1 if the coding system CODING requires some kind of code
+/* Return 1 if the coding context CODING requires some kind of code
detection. */
#define CODING_REQUIRE_DETECTION(coding) \
((coding)->common_flags & CODING_REQUIRE_DETECTION_MASK)
-/* Return 1 if the coding system CODING requires code conversion on
+/* Return 1 if the coding context CODING requires code conversion on
decoding or some kind of code detection. */
#define CODING_MAY_REQUIRE_DECODING(coding) \
(CODING_REQUIRE_DECODING (coding) \
|| CODING_REQUIRE_DETECTION (coding))
-/* Index for each coding category in `coding_category_table' */
-#define CODING_CATEGORY_IDX_EMACS_MULE 0
-#define CODING_CATEGORY_IDX_SJIS 1
-#define CODING_CATEGORY_IDX_ISO_7 2
-#define CODING_CATEGORY_IDX_ISO_7_TIGHT 3
-#define CODING_CATEGORY_IDX_ISO_8_1 4
-#define CODING_CATEGORY_IDX_ISO_8_2 5
-#define CODING_CATEGORY_IDX_ISO_7_ELSE 6
-#define CODING_CATEGORY_IDX_ISO_8_ELSE 7
-#define CODING_CATEGORY_IDX_CCL 8
-#define CODING_CATEGORY_IDX_BIG5 9
-#define CODING_CATEGORY_IDX_UTF_8 10
-#define CODING_CATEGORY_IDX_UTF_16_BE 11
-#define CODING_CATEGORY_IDX_UTF_16_LE 12
-#define CODING_CATEGORY_IDX_RAW_TEXT 13
-#define CODING_CATEGORY_IDX_BINARY 14
-#define CODING_CATEGORY_IDX_MAX 15
-
-/* Definitions of flag bits returned by the function
- detect_coding_mask (). */
-#define CODING_CATEGORY_MASK_EMACS_MULE (1 <<
CODING_CATEGORY_IDX_EMACS_MULE)
-#define CODING_CATEGORY_MASK_SJIS (1 << CODING_CATEGORY_IDX_SJIS)
-#define CODING_CATEGORY_MASK_ISO_7 (1 << CODING_CATEGORY_IDX_ISO_7)
-#define CODING_CATEGORY_MASK_ISO_7_TIGHT (1 << CODING_CATEGORY_IDX_ISO_7_TIGHT)
-#define CODING_CATEGORY_MASK_ISO_8_1 (1 << CODING_CATEGORY_IDX_ISO_8_1)
-#define CODING_CATEGORY_MASK_ISO_8_2 (1 << CODING_CATEGORY_IDX_ISO_8_2)
-#define CODING_CATEGORY_MASK_ISO_7_ELSE (1 <<
CODING_CATEGORY_IDX_ISO_7_ELSE)
-#define CODING_CATEGORY_MASK_ISO_8_ELSE (1 <<
CODING_CATEGORY_IDX_ISO_8_ELSE)
-#define CODING_CATEGORY_MASK_CCL (1 << CODING_CATEGORY_IDX_CCL)
-#define CODING_CATEGORY_MASK_BIG5 (1 << CODING_CATEGORY_IDX_BIG5)
-#define CODING_CATEGORY_MASK_UTF_8 (1 << CODING_CATEGORY_IDX_UTF_8)
-#define CODING_CATEGORY_MASK_UTF_16_BE (1 << CODING_CATEGORY_IDX_UTF_16_BE)
-#define CODING_CATEGORY_MASK_UTF_16_LE (1 << CODING_CATEGORY_IDX_UTF_16_LE)
-#define CODING_CATEGORY_MASK_RAW_TEXT (1 << CODING_CATEGORY_IDX_RAW_TEXT)
-#define CODING_CATEGORY_MASK_BINARY (1 << CODING_CATEGORY_IDX_BINARY)
-
-/* This value is returned if detect_coding_mask () find nothing other
- than ASCII characters. */
-#define CODING_CATEGORY_MASK_ANY \
- ( CODING_CATEGORY_MASK_EMACS_MULE \
- | CODING_CATEGORY_MASK_SJIS \
- | CODING_CATEGORY_MASK_ISO_7 \
- | CODING_CATEGORY_MASK_ISO_7_TIGHT \
- | CODING_CATEGORY_MASK_ISO_8_1 \
- | CODING_CATEGORY_MASK_ISO_8_2 \
- | CODING_CATEGORY_MASK_ISO_7_ELSE \
- | CODING_CATEGORY_MASK_ISO_8_ELSE \
- | CODING_CATEGORY_MASK_CCL \
- | CODING_CATEGORY_MASK_BIG5 \
- | CODING_CATEGORY_MASK_UTF_8 \
- | CODING_CATEGORY_MASK_UTF_16_BE \
- | CODING_CATEGORY_MASK_UTF_16_LE)
-
-#define CODING_CATEGORY_MASK_ISO_7BIT \
- (CODING_CATEGORY_MASK_ISO_7 | CODING_CATEGORY_MASK_ISO_7_TIGHT)
-
-#define CODING_CATEGORY_MASK_ISO_8BIT \
- (CODING_CATEGORY_MASK_ISO_8_1 | CODING_CATEGORY_MASK_ISO_8_2)
-
-#define CODING_CATEGORY_MASK_ISO_SHIFT \
- (CODING_CATEGORY_MASK_ISO_7_ELSE | CODING_CATEGORY_MASK_ISO_8_ELSE)
-
-#define CODING_CATEGORY_MASK_ISO \
- ( CODING_CATEGORY_MASK_ISO_7BIT \
- | CODING_CATEGORY_MASK_ISO_SHIFT \
- | CODING_CATEGORY_MASK_ISO_8BIT)
-
-#define CODING_CATEGORY_MASK_UTF_16_BE_LE \
- (CODING_CATEGORY_MASK_UTF_16_BE | CODING_CATEGORY_MASK_UTF_16_LE)
-
/* Macros to decode or encode a character of JISX0208 in SJIS. S1 and
S2 are the 1st and 2nd position-codes of JISX0208 in SJIS coding
system. C1 and C2 are the 1st and 2nd position codes of Emacs'
internal format. */
-#define DECODE_SJIS(s1, s2, c1, c2) \
+#define SJIS_TO_JIS(code) \
do { \
+ int s1, s2, j1, j2; \
+ \
+ s1 = (code) >> 8, s2 = (code) & 0xFF; \
+ \
if (s2 >= 0x9F) \
- c1 = s1 * 2 - (s1 >= 0xE0 ? 0x160 : 0xE0), \
- c2 = s2 - 0x7E; \
+ (j1 = s1 * 2 - (s1 >= 0xE0 ? 0x160 : 0xE0), \
+ j2 = s2 - 0x7E); \
else \
- c1 = s1 * 2 - ((s1 >= 0xE0) ? 0x161 : 0xE1), \
- c2 = s2 - ((s2 >= 0x7F) ? 0x20 : 0x1F); \
+ (j1 = s1 * 2 - ((s1 >= 0xE0) ? 0x161 : 0xE1), \
+ j2 = s2 - ((s2 >= 0x7F) ? 0x20 : 0x1F)); \
+ (code) = (j1 << 8) | j2; \
} while (0)
-#define ENCODE_SJIS(c1, c2, s1, s2) \
+#define SJIS_TO_JIS2(code) \
do { \
- if (c1 & 1) \
- s1 = c1 / 2 + ((c1 < 0x5F) ? 0x71 : 0xB1), \
- s2 = c2 + ((c2 >= 0x60) ? 0x20 : 0x1F); \
+ int s1, s2, j1, j2; \
+ \
+ s1 = (code) >> 8, s2 = (code) & 0xFF; \
+ \
+ if (s2 >= 0x9F) \
+ { \
+ j1 = (s1 == 0xF0 ? 0x28 \
+ : s1 == 0xF1 ? 0x24 \
+ : s1 == 0xF2 ? 0x2C \
+ : s1 == 0xF3 ? 0x2E \
+ : 0x6E + (s1 - 0xF4) * 2); \
+ j2 = s2 - 0x7E; \
+ } \
+ else \
+ { \
+ j1 = (s1 <= 0xF2 ? 0x21 + (s1 - 0xF0) * 2 \
+ : s1 <= 0xF4 ? 0x2D + (s1 - 0xF3) * 2 \
+ : 0x6F + (s1 - 0xF5) * 2); \
+ j2 = s2 - ((s2 >= 0x7F ? 0x20 : 0x1F)); \
+ } \
+ (code) = (j1 << 8) | j2; \
+ } while (0)
+
+
+#define JIS_TO_SJIS(code) \
+ do { \
+ int s1, s2, j1, j2; \
+ \
+ j1 = (code) >> 8, j2 = (code) & 0xFF; \
+ if (j1 & 1) \
+ (s1 = j1 / 2 + ((j1 < 0x5F) ? 0x71 : 0xB1), \
+ s2 = j2 + ((j2 >= 0x60) ? 0x20 : 0x1F)); \
else \
- s1 = c1 / 2 + ((c1 < 0x5F) ? 0x70 : 0xB0), \
- s2 = c2 + 0x7E; \
+ (s1 = j1 / 2 + ((j1 < 0x5F) ? 0x70 : 0xB0), \
+ s2 = j2 + 0x7E); \
+ (code) = (s1 << 8) | s2; \
+ } while (0)
+
+#define JIS_TO_SJIS2(code) \
+ do { \
+ int s1, s2, j1, j2; \
+ \
+ j1 = (code) >> 8, j2 = (code) & 0xFF; \
+ if (j1 & 1) \
+ { \
+ s1 = (j1 <= 0x25 ? 0xF0 + (j1 - 0x21) / 2 \
+ : j1 <= 0x27 ? 0xF3 + (j1 - 0x2D) / 2 \
+ : 0xF5 + (j1 - 0x6F) / 2); \
+ s2 = j2 + ((j2 >= 0x60) ? 0x20 : 0x1F); \
+ } \
+ else \
+ { \
+ s1 = (j1 == 0x28 ? 0xF0 \
+ : j1 == 0x24 ? 0xF1 \
+ : j1 == 0x2C ? 0xF2 \
+ : j1 == 0x2E ? 0xF3 \
+ : 0xF4 + (j1 - 0x6E) / 2); \
+ s2 = j2 + 0x7E; \
+ } \
+ (code) = (s1 << 8) | s2; \
} while (0)
/* Encode the file name NAME using the specified coding system
@@ -588,6 +606,7 @@
? code_convert_string_norecord (name, Vdefault_file_name_coding_system,
1) \
: name))
+
/* Decode the file name NAME using the specified coding system
for file names, if any. */
#define DECODE_FILE(name) \
@@ -599,6 +618,7 @@
? code_convert_string_norecord (name, Vdefault_file_name_coding_system,
0) \
: name))
+
/* Encode the string STR using the specified coding system
for system functions, if any. */
#define ENCODE_SYSTEM(str) \
@@ -615,54 +635,83 @@
? code_convert_string_norecord (str, Vlocale_coding_system, 0) \
: str)
+/* Used by the gtk menu code. Note that this encodes utf-8, not
+ utf-8-emacs, so it's not a no-op. */
#define ENCODE_UTF_8(str) code_convert_string_norecord (str, Qutf_8, 1)
/* Extern declarations. */
-extern int decode_coding P_ ((struct coding_system *, const unsigned char *,
- unsigned char *, int, int));
-extern int encode_coding P_ ((struct coding_system *, const unsigned char *,
- unsigned char *, int, int));
-extern void coding_save_composition P_ ((struct coding_system *, int, int,
- Lisp_Object));
-extern void coding_free_composition_data P_ ((struct coding_system *));
-extern void coding_adjust_composition_offset P_ ((struct coding_system *,
- int));
-extern void coding_allocate_composition_data P_ ((struct coding_system *,
- int));
-extern void coding_restore_composition P_ ((struct coding_system *,
- Lisp_Object));
-extern int code_convert_region P_ ((int, int, int, int, struct coding_system *,
- int, int));
-extern Lisp_Object run_pre_post_conversion_on_str P_ ((Lisp_Object,
- struct coding_system *,
- int));
-extern void run_pre_write_conversin_on_c_str P_ ((unsigned char **, int *,
- int, int,
- struct coding_system *));
-
+extern Lisp_Object code_conversion_save P_ ((int, int));
extern int decoding_buffer_size P_ ((struct coding_system *, int));
extern int encoding_buffer_size P_ ((struct coding_system *, int));
-extern void detect_coding P_ ((struct coding_system *, const unsigned char *,
- int));
-extern void detect_eol P_ ((struct coding_system *, const unsigned char *,
- int));
-extern int setup_coding_system P_ ((Lisp_Object, struct coding_system *));
-extern Lisp_Object code_convert_string P_ ((Lisp_Object,
- struct coding_system *, int, int));
-extern Lisp_Object code_convert_string1 P_ ((Lisp_Object, Lisp_Object,
- Lisp_Object, int));
+extern void setup_coding_system P_ ((Lisp_Object, struct coding_system *));
+extern Lisp_Object coding_charset_list P_ ((struct coding_system *));
+extern void detect_coding P_ ((struct coding_system *));
+extern Lisp_Object code_convert_region P_ ((Lisp_Object, Lisp_Object,
+ Lisp_Object, Lisp_Object,
+ int, int));
+extern Lisp_Object code_convert_string P_ ((Lisp_Object, Lisp_Object,
+ Lisp_Object, int, int, int));
extern Lisp_Object code_convert_string_norecord P_ ((Lisp_Object, Lisp_Object,
int));
-extern void setup_raw_text_coding_system P_ ((struct coding_system *));
-extern Lisp_Object encode_coding_string P_ ((Lisp_Object,
- struct coding_system *, int));
-extern Lisp_Object decode_coding_string P_ ((Lisp_Object,
- struct coding_system *, int));
+extern Lisp_Object raw_text_coding_system P_ ((Lisp_Object));
+extern Lisp_Object coding_inherit_eol_type P_ ((Lisp_Object, Lisp_Object));
+
+extern int decode_coding_gap P_ ((struct coding_system *,
+ EMACS_INT, EMACS_INT));
+extern int encode_coding_gap P_ ((struct coding_system *,
+ EMACS_INT, EMACS_INT));
+extern void decode_coding_object P_ ((struct coding_system *,
+ Lisp_Object, EMACS_INT, EMACS_INT,
+ EMACS_INT, EMACS_INT, Lisp_Object));
+extern void encode_coding_object P_ ((struct coding_system *,
+ Lisp_Object, EMACS_INT, EMACS_INT,
+ EMACS_INT, EMACS_INT, Lisp_Object));
+
+/* Macros for backward compatibility. */
+
+#define decode_coding_region(coding, from, to) \
+ decode_coding_object (coding, Fcurrent_buffer (), \
+ from, CHAR_TO_BYTE (from), \
+ to, CHAR_TO_BYTE (to), Fcurrent_buffer ())
+
+
+#define encode_coding_region(coding, from, to) \
+ encode_coding_object (coding, Fcurrent_buffer (), \
+ from, CHAR_TO_BYTE (from), \
+ to, CHAR_TO_BYTE (to), Fcurrent_buffer ())
+
+
+#define decode_coding_string(coding, string, nocopy) \
+ decode_coding_object (coding, string, 0, 0, XSTRING (string)->size, \
+ STRING_BYTES (XSTRING (string)), Qt)
+
+#define encode_coding_string(coding, string, nocopy) \
+ (encode_coding_object (coding, string, 0, 0, XSTRING (string)->size, \
+ STRING_BYTES (XSTRING (string)), Qt), \
+ (coding)->dst_object)
+
+
+#define decode_coding_c_string(coding, src, bytes, dst_object) \
+ do { \
+ (coding)->source = (src); \
+ (coding)->src_chars = (coding)->src_bytes = (bytes); \
+ decode_coding_object ((coding), Qnil, 0, 0, (bytes), (bytes), \
+ (dst_object)); \
+ } while (0)
+
+
+extern Lisp_Object preferred_coding_system P_ (());
+
+
+extern Lisp_Object Qutf_8, Qutf_8_emacs;
+
extern Lisp_Object Qcoding_system, Qeol_type, Qcoding_category_index;
-extern Lisp_Object Qraw_text, Qemacs_mule;
+extern Lisp_Object Qcoding_system_p;
+extern Lisp_Object Qraw_text, Qemacs_mule, Qno_conversion, Qundecided;
+extern Lisp_Object Qiso_2022;
extern Lisp_Object Qbuffer_file_coding_system;
-extern Lisp_Object Vcoding_category_list;
-extern Lisp_Object Qutf_8;
+
+extern Lisp_Object Qunix, Qdos, Qmac;
extern Lisp_Object Qtranslation_table;
extern Lisp_Object Qtranslation_table_id;
@@ -672,9 +721,6 @@
/* Mnemonic string to indicate type of end-of-line is not yet decided. */
extern Lisp_Object eol_mnemonic_undecided;
-/* Format of end-of-line decided by system. */
-extern int system_eol_type;
-
#ifdef emacs
extern Lisp_Object Qfile_coding_system;
extern Lisp_Object Qcall_process, Qcall_process_region;
@@ -700,13 +746,10 @@
terminal coding system is nil. */
extern struct coding_system safe_terminal_coding;
-/* Default coding system to be used to write a file. */
-extern struct coding_system default_buffer_file_coding;
-
/* Default coding systems used for process I/O. */
extern Lisp_Object Vdefault_process_coding_system;
-/* Function to call to force a user to force select a proper coding
+/* Function to call to force a user to force select a propert coding
system. */
extern Lisp_Object Vselect_safe_coding_system_function;
@@ -726,6 +769,9 @@
/* Error signaled when there's a problem with detecting coding system */
extern Lisp_Object Qcoding_system_error;
+extern char emacs_mule_bytes[256];
+extern int emacs_mule_string_char P_ ((unsigned char *));
+
#endif /* EMACS_CODING_H */
/* arch-tag: 2bc3b4fa-6870-4f64-8135-b962b2d290e4
- [Emacs-diffs] Changes to emacs/src/coding.h,v,
Miles Bader <=