X-Git-Url: https://code.delx.au/gnu-emacs/blobdiff_plain/0ef691383d599b2b1cc2e4905cb21aa32ed771e4..a12aece30906d6a8b03611262169ba181b37b93b:/src/coding.h diff --git a/src/coding.h b/src/coding.h index 47777fddb9..fb24c17040 100644 --- a/src/coding.h +++ b/src/coding.h @@ -1,7 +1,9 @@ /* Header for coding system handler. - Ver.1.0 - Copyright (C) 1995 Free Software Foundation, Inc. - Copyright (C) 1995 Electrotechnical Laboratory, JAPAN. + Copyright (C) 2002, 2003, 2004, 2005, + 2006 Free Software Foundation, Inc. + Copyright (C) 1995, 1997, 1998, 2000 + National Institute of Advanced Industrial Science and Technology (AIST) + Registration Number H14PRO021 This file is part of GNU Emacs. @@ -17,15 +19,13 @@ GNU General Public License for more details. You should have received a copy of the GNU General Public License along with GNU Emacs; see the file COPYING. If not, write to -the Free Software Foundation, Inc., 59 Temple Place - Suite 330, -Boston, MA 02111-1307, USA. */ +the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, +Boston, MA 02110-1301, USA. */ -#ifndef _CODING_H -#define _CODING_H +#ifndef EMACS_CODING_H +#define EMACS_CODING_H -#ifndef _CCL_H -#include "../src/ccl.h" -#endif +#include "ccl.h" /*** EMACS' INTERNAL FORMAT (emacs-mule) section ***/ @@ -41,8 +41,6 @@ enum emacs_code_class_type EMACS_carriage_return_code, /* 0x0D (carriage-return) to be used in selective display mode. */ EMACS_ascii_code, /* ASCII characters. */ - EMACS_leading_code_composition, /* Leading code of a composite - character. */ EMACS_leading_code_2, /* Base leading code of official TYPE9N character. */ EMACS_leading_code_3, /* Base leading code of private TYPE9N @@ -75,15 +73,17 @@ extern enum emacs_code_class_type emacs_code_class[256]; followings. */ enum iso_code_class_type { - ISO_control_code, /* Control codes in the range - 0x00..0x1F, 0x7F, and 0x80..0x9F, - except for the following seven - codes. */ + 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) */ @@ -136,6 +136,21 @@ enum iso_code_class_type on output. */ #define CODING_FLAG_ISO_DESIGNATE_AT_BOL 0x0400 +/* If set, do not encode unsafe characters on output. */ +#define CODING_FLAG_ISO_SAFE 0x0800 + +/* If set, extra latin codes (128..159) are accepted as a valid code + on input. */ +#define CODING_FLAG_ISO_LATIN_EXTRA 0x1000 + +/* If set, use designation escape sequence. */ +#define CODING_FLAG_ISO_DESIGNATION 0x10000 + +/* 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 '?' + /* Structure of the field `spec.iso2022' in the structure `coding_system'. */ struct iso2022_spec { @@ -148,8 +163,17 @@ struct iso2022_spec /* A charset initially designated to each graphic register. */ int initial_designation[4]; + /* 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. */ - char requested_designation[MAX_CHARSET + 1]; + 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. */ @@ -161,17 +185,25 @@ struct iso2022_spec /* Macros to access each field in the structure `spec.iso2022'. */ #define CODING_SPEC_ISO_INVOCATION(coding, plane) \ - coding->spec.iso2022.current_invocation[plane] + (coding)->spec.iso2022.current_invocation[plane] #define CODING_SPEC_ISO_DESIGNATION(coding, reg) \ - coding->spec.iso2022.current_designation[reg] + (coding)->spec.iso2022.current_designation[reg] #define CODING_SPEC_ISO_INITIAL_DESIGNATION(coding, reg) \ - coding->spec.iso2022.initial_designation[reg] + (coding)->spec.iso2022.initial_designation[reg] #define CODING_SPEC_ISO_REQUESTED_DESIGNATION(coding, charset) \ - coding->spec.iso2022.requested_designation[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 + (coding)->spec.iso2022.single_shifting #define CODING_SPEC_ISO_BOL(coding) \ - coding->spec.iso2022.bol + (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. */ @@ -210,8 +242,12 @@ enum coding_type 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 + 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. */ }; /* Formats of end-of-line. */ @@ -222,55 +258,133 @@ enum coding_type #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. */ - -/* Character composition status while encoding/decoding. */ -#define COMPOSING_NO 0 /* not composing */ -#define COMPOSING_WITH_RULE_HEAD 1 /* 1st char of with-rule composing follow */ -#define COMPOSING_NO_RULE_HEAD 2 /* 1st char of no-rule composing follow */ -#define COMPOSING_WITH_RULE_TAIL 3 /* Nth char of with-rule composing follow */ -#define COMPOSING_NO_RULE_TAIL 4 /* Nth char of no-rule composing follow */ -#define COMPOSING_WITH_RULE_RULE 5 /* composition rule follow */ +#define CODING_EOL_INCONSISTENT 4 /* This value is used to denote the + eol-type is not consistent + through the file. */ /* 1 iff composing. */ -#define COMPOSING_P(composing) (composing) -/* 1 iff 1st char of composing element follows. */ -#define COMPOSING_HEAD_P(composing) \ - ((composing) && (composing) <= COMPOSING_NO_RULE_HEAD) -/* 1 iff composing with embeded composition rule. */ -#define COMPOSING_WITH_RULE_P(composing) ((composing) & 1) +#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. */ + +/* If set, recover the original CR or LF of the already decoded text + when the decoding routine encounters an inconsistent eol format. */ +#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 + appropriate finishing job. */ +#define CODING_MODE_LAST_BLOCK 0x02 + +/* If set, it means that the current source text is in a buffer which + 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 struct coding_system { /* Type of the coding system. */ enum coding_type type; - /* If the coding system requires specific code to be attached at the - tail of converted text, this value should be set to `1'. */ - int require_flushing; + /* Type of end-of-line format (LF, CRLF, or CR) of the coding system. */ + int eol_type; + + /* 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; - /* Type of end-of-line format (LF, CRLF, or CR) of the coding system. */ - int eol_type; - - /* Non-zero means that the current source text is the last block of the - whole text to be converted. */ - int last_block; + /* Mode bits of the coding system. See the comments of the macros + CODING_MODE_XXX. */ + unsigned int mode; - /* Non-zero means that characters are being composed currently while - decoding or encoding. See macros COMPOSING_XXXX above for the - meaing of each non-zero value. */ + /* The current status of composition handling. */ int composing; - /* 0 (left-to-right) or 1 (right-to-left): the direction of the text - being processed currently. */ - int direction; + /* 1 iff 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; - /* Non-zero means that the current source text is in a buffer which - enables selective display. */ - int selective; + /* 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 @@ -279,67 +393,124 @@ struct coding_system struct ccl_spec ccl; /* Defined in ccl.h. */ } spec; + /* Index number of coding category of the coding system. */ + int category_idx; + + /* 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). */ + unsigned src_multibyte : 1; + unsigned dst_multibyte : 1; + + /* How may heading bytes we can skip for decoding. This is set to + -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; + + /* The following members are set by encoding/decoding routine. */ + 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. */ + additional conversion, or nil. */ Lisp_Object post_read_conversion; /* Lisp function (symbol) to be called before encoding to do - additional conversion. */ + additional conversion, or nil. */ Lisp_Object pre_write_conversion; - /* Character unification table to look up, or nil. */ - Lisp_Object character_unification_table; - - /* Carryover yielded by decoding/encoding incomplete source. No - coding-system yields more than 7-byte of carryover. This does - not include a text which is not processed because of short of - output buffer. */ - char carryover[8]; - - /* Actual data length in the above array. */ - int carryover_size; + /* Character translation tables to look up, or nil. */ + Lisp_Object translation_table_for_decode; + Lisp_Object translation_table_for_encode; }; -/* Return 1 if the coding-system CODING requires conversion of - representation of a visible character (text). */ -#define CODING_REQUIRE_TEXT_CONVERSION(coding) \ - ((coding)->type != coding_type_no_conversion \ - && (coding)->type != coding_type_emacs_mule) - -/* Return 1 if the coding-system CODING requires conversion of the - format of end-of-line. */ -#define CODING_REQUIRE_EOL_CONVERSION(coding) \ - ((coding)->eol_type != CODING_EOL_UNDECIDED \ - && (coding)->eol_type != CODING_EOL_LF) - -/* Return 1 if the coding-system CODING requires some conversion. */ -#define CODING_REQUIRE_CONVERSION(coding) \ - (CODING_REQUIRE_TEXT_CONVERSION (coding) \ - || CODING_REQUIRE_EOL_CONVERSION (coding)) +#define CODING_REQUIRE_FLUSHING_MASK 1 +#define CODING_REQUIRE_DECODING_MASK 2 +#define CODING_REQUIRE_ENCODING_MASK 4 +#define CODING_REQUIRE_DETECTION_MASK 8 + +/* Return 1 if the coding system 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 + 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 + encoding. */ +#define CODING_REQUIRE_ENCODING(coding) \ + ((coding)->src_multibyte \ + || (coding)->common_flags & CODING_REQUIRE_ENCODING_MASK) + +/* Return 1 if the coding system 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 + 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_8_1 3 -#define CODING_CATEGORY_IDX_ISO_8_2 4 -#define CODING_CATEGORY_IDX_ISO_ELSE 5 -#define CODING_CATEGORY_IDX_BIG5 6 -#define CODING_CATEGORY_IDX_BINARY 7 -#define CODING_CATEGORY_IDX_MAX 8 +#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_ELSE (1 << CODING_CATEGORY_IDX_ISO_ELSE) +#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. */ @@ -347,10 +518,33 @@ struct coding_system ( 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_ELSE \ - | CODING_CATEGORY_MASK_BIG5) + | 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 @@ -377,30 +571,108 @@ struct coding_system s2 = c2 + 0x7E; \ } while (0) +/* Encode the file name NAME using the specified coding system + for file names, if any. */ +#define ENCODE_FILE(name) \ + (! NILP (Vfile_name_coding_system) \ + && !EQ (Vfile_name_coding_system, make_number (0)) \ + ? code_convert_string_norecord (name, Vfile_name_coding_system, 1) \ + : (! NILP (Vdefault_file_name_coding_system) \ + && !EQ (Vdefault_file_name_coding_system, make_number (0)) \ + ? 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) \ + (! NILP (Vfile_name_coding_system) \ + && !EQ (Vfile_name_coding_system, make_number (0)) \ + ? code_convert_string_norecord (name, Vfile_name_coding_system, 0) \ + : (! NILP (Vdefault_file_name_coding_system) \ + && !EQ (Vdefault_file_name_coding_system, make_number (0)) \ + ? 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) \ + (! NILP (Vlocale_coding_system) \ + && !EQ (Vlocale_coding_system, make_number (0)) \ + ? code_convert_string_norecord (str, Vlocale_coding_system, 1) \ + : str) + +/* Decode the string STR using the specified coding system + for system functions, if any. */ +#define DECODE_SYSTEM(str) \ + (! NILP (Vlocale_coding_system) \ + && !EQ (Vlocale_coding_system, make_number (0)) \ + ? code_convert_string_norecord (str, Vlocale_coding_system, 0) \ + : str) + +#define ENCODE_UTF_8(str) code_convert_string_norecord (str, Qutf_8, 1) + /* Extern declarations. */ -extern int decode_coding (), encode_coding (); -extern int decoding_buffer_size (), encoding_buffer_size (); -extern int conversion_buffer_size; -extern char *conversion_buffer, *get_conversion_buffer (); -extern Lisp_Object Fcheck_coding_system (); +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 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 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 Qcoding_system, Qeol_type, Qcoding_category_index; +extern Lisp_Object Qraw_text, Qemacs_mule; extern Lisp_Object Qbuffer_file_coding_system; extern Lisp_Object Vcoding_category_list; +extern Lisp_Object Qutf_8; -/* Mnemonic character to indicate each type of end-of-line. */ -extern int eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; -/* Mnemonic character to indicate type of end-of-line is not yet decided. */ -extern int eol_mnemonic_undecided; +extern Lisp_Object Qtranslation_table; +extern Lisp_Object Qtranslation_table_id; -/* Table of coding-systems currently assigned to each coding-category. */ -extern Lisp_Object coding_category_table[CODING_CATEGORY_IDX_MAX]; -/* Table of names of symbol for each coding-category. */ -extern char *coding_category_name[CODING_CATEGORY_IDX_MAX]; +/* Mnemonic strings to indicate each type of end-of-line. */ +extern Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; +/* Mnemonic string to indicate type of end-of-line is not yet decided. */ +extern Lisp_Object eol_mnemonic_undecided; #ifdef emacs extern Lisp_Object Qfile_coding_system; -extern Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; +extern Lisp_Object Qcall_process, Qcall_process_region; extern Lisp_Object Qstart_process, Qopen_network_stream; +extern Lisp_Object Qwrite_region; + +extern char *emacs_strerror P_ ((int)); /* Coding-system for reading files and receiving data from process. */ extern Lisp_Object Vcoding_system_for_read; @@ -408,19 +680,54 @@ extern Lisp_Object Vcoding_system_for_read; extern Lisp_Object Vcoding_system_for_write; /* Coding-system actually used in the latest I/O. */ extern Lisp_Object Vlast_coding_system_used; +/* Coding-system to use with system messages (e.g. strerror). */ +extern Lisp_Object Vlocale_coding_system; + +/* If non-zero, process buffer inherits the coding system used to decode + the subprocess output. */ +extern int inherit_process_coding_system; /* Coding-system to be used for encoding terminal output. This structure contains information of a coding-system specified by the function `set-terminal-coding-system'. */ extern struct coding_system terminal_coding; +/* Coding system to be used to encode text for terminal display when + terminal coding system is nil. */ +extern struct coding_system safe_terminal_coding; + /* Coding-system of what is sent from terminal keyboard. This structure contains information of a coding-system specified by the function `set-keyboard-coding-system'. */ extern struct coding_system keyboard_coding; -extern Lisp_Object Vcoding_system_alist; +/* 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 + system. */ +extern Lisp_Object Vselect_safe_coding_system_function; + +/* If nonzero, on writing a file, Vselect_safe_coding_system_function + is called even if Vcoding_system_for_write is non-nil. */ +extern int coding_system_require_warning; + +/* Coding system for file names, or nil if none. */ +extern Lisp_Object Vfile_name_coding_system; + +/* Coding system for file names used only when + Vfile_name_coding_system is nil. */ +extern Lisp_Object Vdefault_file_name_coding_system; #endif -#endif /* _CODING_H */ +/* Error signaled when there's a problem with detecting coding system */ +extern Lisp_Object Qcoding_system_error; + +#endif /* EMACS_CODING_H */ + +/* arch-tag: 2bc3b4fa-6870-4f64-8135-b962b2d290e4 + (do not change this comment) */