diff options
| author | Kenichi Handa | 2009-03-06 07:51:52 +0000 |
|---|---|---|
| committer | Kenichi Handa | 2009-03-06 07:51:52 +0000 |
| commit | e951386e3862e77b38b96e00652b8ce4ba788aff (patch) | |
| tree | 73c3c8e41ed92ade080a6bcf3ce759e00bfb1860 /src | |
| parent | c8644de0d406a99a4a493a0b78a1f3df62d4cfda (diff) | |
| download | emacs-e951386e3862e77b38b96e00652b8ce4ba788aff.tar.gz emacs-e951386e3862e77b38b96e00652b8ce4ba788aff.zip | |
(CODING_ISO_CMP_STATUS): New macro.
(CODING_ISO_EXTSEGMENT_LEN, CODING_ISO_EMBEDDED_UTF_8): New macros.
(MAX_ANNOTATION_LENGTH): Defined to 5.
(ADD_COMPOSITION_DATA): New arg nbytes.
(emacs_mule_char): New arg cmp_status.
(DECODE_EMACS_MULE_COMPOSITION_CHAR): Delete it.
(DECODE_EMACS_MULE_COMPOSITION_RULE_20): New arg c.
(DECODE_EMACS_MULE_COMPOSITION_RULE_21): New arg c.
(DECODE_EMACS_MULE_21_COMPOSITION): Delete the arg c.
(DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION): Likewise.
(DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION): Likewise.
(DECODE_EMACS_MULE_COMPOSITION_START): New macro.
(EMACS_MULE_COMPOSITION_END): New macro.
(emacs_mule_finish_composition): New function.
(EMACS_MULE_MAYBE_FINISH_COMPOSITION): New macro.
(decode_coding_emacs_mule): Avoid long looking ahead while
handling composition.
(DECODE_COMPOSITION_RULE): Argument changed to rule and nbytes.
(ENCODE_COMPOSITION_RULE): New macro.
(finish_composition): New function.
(MAYBE_FINISH_COMPOSITION): Call finish_composition.
(DECODE_COMPOSITION_START): New implementation.
(DECODE_COMPOSITION_END): Likewise.
(STORE_COMPOSITION_RULE): New macro.
(decode_coding_iso_2022): Avoid long looking ahead while handling
composition, CTEXT extended segment, and embedded UTF-8.
(setup_coding_system): For a coding of type iso-2022, reset
CODING_ISO_EXTSEGMENT_LEN (coding) and
CODING_ISO_EMBEDDED_UTF_8 (coding).
(get_translation): Delete arguments last_block, from_nchars,
to_nchars. Callers changed.
(produce_chars): Don't modify charbuf. Adjusted for the change of
get_translation.
(produce_composition): Adjusted for the new annotation sequence.
(handle_composition_annotation): Likewise.
(consume_chars): Adjusted for the change of get_translation.
Diffstat (limited to 'src')
| -rw-r--r-- | src/coding.c | 1443 |
1 files changed, 906 insertions, 537 deletions
diff --git a/src/coding.c b/src/coding.c index 91811f79bfe..8d5304dc114 100644 --- a/src/coding.c +++ b/src/coding.c | |||
| @@ -452,6 +452,12 @@ Lisp_Object Vbig5_coding_system; | |||
| 452 | ((coding)->spec.iso_2022.bol) | 452 | ((coding)->spec.iso_2022.bol) |
| 453 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | 453 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ |
| 454 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | 454 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) |
| 455 | #define CODING_ISO_CMP_STATUS(coding) \ | ||
| 456 | (&(coding)->spec.iso_2022.cmp_status) | ||
| 457 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | ||
| 458 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | ||
| 459 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | ||
| 460 | ((coding)->spec.iso_2022.embedded_utf_8) | ||
| 455 | 461 | ||
| 456 | /* Control characters of ISO2022. */ | 462 | /* Control characters of ISO2022. */ |
| 457 | /* code */ /* function */ | 463 | /* code */ /* function */ |
| @@ -945,11 +951,8 @@ static int detect_eol P_ ((const unsigned char *, | |||
| 945 | static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int)); | 951 | static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int)); |
| 946 | static void decode_eol P_ ((struct coding_system *)); | 952 | static void decode_eol P_ ((struct coding_system *)); |
| 947 | static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *)); | 953 | static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *)); |
| 948 | static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *, | 954 | static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *)); |
| 949 | int, int *, int *)); | ||
| 950 | static int produce_chars P_ ((struct coding_system *, Lisp_Object, int)); | 955 | static int produce_chars P_ ((struct coding_system *, Lisp_Object, int)); |
| 951 | static INLINE void produce_composition P_ ((struct coding_system *, int *, | ||
| 952 | EMACS_INT)); | ||
| 953 | static INLINE void produce_charset P_ ((struct coding_system *, int *, | 956 | static INLINE void produce_charset P_ ((struct coding_system *, int *, |
| 954 | EMACS_INT)); | 957 | EMACS_INT)); |
| 955 | static void produce_annotation P_ ((struct coding_system *, EMACS_INT)); | 958 | static void produce_annotation P_ ((struct coding_system *, EMACS_INT)); |
| @@ -1208,10 +1211,6 @@ alloc_destination (coding, nbytes, dst) | |||
| 1208 | 1211 | ||
| 1209 | /** Macros for annotations. */ | 1212 | /** Macros for annotations. */ |
| 1210 | 1213 | ||
| 1211 | /* Maximum length of annotation data (sum of annotations for | ||
| 1212 | composition and charset). */ | ||
| 1213 | #define MAX_ANNOTATION_LENGTH (4 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 4) | ||
| 1214 | |||
| 1215 | /* An annotation data is stored in the array coding->charbuf in this | 1214 | /* An annotation data is stored in the array coding->charbuf in this |
| 1216 | format: | 1215 | format: |
| 1217 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] | 1216 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
| @@ -1223,13 +1222,26 @@ alloc_destination (coding, nbytes, dst) | |||
| 1223 | 1222 | ||
| 1224 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | 1223 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements |
| 1225 | follows: | 1224 | follows: |
| 1226 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | 1225 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
| 1226 | |||
| 1227 | NBYTES is the number of bytes specified in the header part of | ||
| 1228 | old-style emacs-mule encoding, or 0 for the other kind of | ||
| 1229 | composition. | ||
| 1230 | |||
| 1227 | METHOD is one of enum composition_method. | 1231 | METHOD is one of enum composition_method. |
| 1232 | |||
| 1228 | Optionnal COMPOSITION-COMPONENTS are characters and composition | 1233 | Optionnal COMPOSITION-COMPONENTS are characters and composition |
| 1229 | rules. | 1234 | rules. |
| 1230 | 1235 | ||
| 1231 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | 1236 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID |
| 1232 | follows. */ | 1237 | follows. |
| 1238 | |||
| 1239 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | ||
| 1240 | recover from an invalid annotation, and should be skipped by | ||
| 1241 | produce_annotation. */ | ||
| 1242 | |||
| 1243 | /* Maximum length of the header of annotation data. */ | ||
| 1244 | #define MAX_ANNOTATION_LENGTH 5 | ||
| 1233 | 1245 | ||
| 1234 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ | 1246 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
| 1235 | do { \ | 1247 | do { \ |
| @@ -1239,9 +1251,10 @@ alloc_destination (coding, nbytes, dst) | |||
| 1239 | coding->annotated = 1; \ | 1251 | coding->annotated = 1; \ |
| 1240 | } while (0); | 1252 | } while (0); |
| 1241 | 1253 | ||
| 1242 | #define ADD_COMPOSITION_DATA(buf, nchars, method) \ | 1254 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
| 1243 | do { \ | 1255 | do { \ |
| 1244 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ | 1256 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
| 1257 | *buf++ = nbytes; \ | ||
| 1245 | *buf++ = method; \ | 1258 | *buf++ = method; \ |
| 1246 | } while (0) | 1259 | } while (0) |
| 1247 | 1260 | ||
| @@ -1920,12 +1933,12 @@ encode_coding_utf_16 (coding) | |||
| 1920 | Next, character composition data are represented by the byte | 1933 | Next, character composition data are represented by the byte |
| 1921 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | 1934 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., |
| 1922 | where, | 1935 | where, |
| 1923 | METHOD is 0xF0 plus one of composition method (enum | 1936 | METHOD is 0xF2 plus one of composition method (enum |
| 1924 | composition_method), | 1937 | composition_method), |
| 1925 | 1938 | ||
| 1926 | BYTES is 0xA0 plus a byte length of this composition data, | 1939 | BYTES is 0xA0 plus a byte length of this composition data, |
| 1927 | 1940 | ||
| 1928 | CHARS is 0x20 plus a number of characters composed by this | 1941 | CHARS is 0xA0 plus a number of characters composed by this |
| 1929 | data, | 1942 | data, |
| 1930 | 1943 | ||
| 1931 | COMPONENTs are characters of multibye form or composition | 1944 | COMPONENTs are characters of multibye form or composition |
| @@ -1947,11 +1960,107 @@ encode_coding_utf_16 (coding) | |||
| 1947 | 1960 | ||
| 1948 | char emacs_mule_bytes[256]; | 1961 | char emacs_mule_bytes[256]; |
| 1949 | 1962 | ||
| 1963 | |||
| 1964 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | ||
| 1965 | Check if a text is encoded in `emacs-mule'. If it is, return 1, | ||
| 1966 | else return 0. */ | ||
| 1967 | |||
| 1968 | static int | ||
| 1969 | detect_coding_emacs_mule (coding, detect_info) | ||
| 1970 | struct coding_system *coding; | ||
| 1971 | struct coding_detection_info *detect_info; | ||
| 1972 | { | ||
| 1973 | const unsigned char *src = coding->source, *src_base; | ||
| 1974 | const unsigned char *src_end = coding->source + coding->src_bytes; | ||
| 1975 | int multibytep = coding->src_multibyte; | ||
| 1976 | int consumed_chars = 0; | ||
| 1977 | int c; | ||
| 1978 | int found = 0; | ||
| 1979 | |||
| 1980 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | ||
| 1981 | /* A coding system of this category is always ASCII compatible. */ | ||
| 1982 | src += coding->head_ascii; | ||
| 1983 | |||
| 1984 | while (1) | ||
| 1985 | { | ||
| 1986 | src_base = src; | ||
| 1987 | ONE_MORE_BYTE (c); | ||
| 1988 | if (c < 0) | ||
| 1989 | continue; | ||
| 1990 | if (c == 0x80) | ||
| 1991 | { | ||
| 1992 | /* Perhaps the start of composite character. We simply skip | ||
| 1993 | it because analyzing it is too heavy for detecting. But, | ||
| 1994 | at least, we check that the composite character | ||
| 1995 | constitutes of more than 4 bytes. */ | ||
| 1996 | const unsigned char *src_base; | ||
| 1997 | |||
| 1998 | repeat: | ||
| 1999 | src_base = src; | ||
| 2000 | do | ||
| 2001 | { | ||
| 2002 | ONE_MORE_BYTE (c); | ||
| 2003 | } | ||
| 2004 | while (c >= 0xA0); | ||
| 2005 | |||
| 2006 | if (src - src_base <= 4) | ||
| 2007 | break; | ||
| 2008 | found = CATEGORY_MASK_EMACS_MULE; | ||
| 2009 | if (c == 0x80) | ||
| 2010 | goto repeat; | ||
| 2011 | } | ||
| 2012 | |||
| 2013 | if (c < 0x80) | ||
| 2014 | { | ||
| 2015 | if (c < 0x20 | ||
| 2016 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | ||
| 2017 | break; | ||
| 2018 | } | ||
| 2019 | else | ||
| 2020 | { | ||
| 2021 | int more_bytes = emacs_mule_bytes[*src_base] - 1; | ||
| 2022 | |||
| 2023 | while (more_bytes > 0) | ||
| 2024 | { | ||
| 2025 | ONE_MORE_BYTE (c); | ||
| 2026 | if (c < 0xA0) | ||
| 2027 | { | ||
| 2028 | src--; /* Unread the last byte. */ | ||
| 2029 | break; | ||
| 2030 | } | ||
| 2031 | more_bytes--; | ||
| 2032 | } | ||
| 2033 | if (more_bytes != 0) | ||
| 2034 | break; | ||
| 2035 | found = CATEGORY_MASK_EMACS_MULE; | ||
| 2036 | } | ||
| 2037 | } | ||
| 2038 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | ||
| 2039 | return 0; | ||
| 2040 | |||
| 2041 | no_more_source: | ||
| 2042 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | ||
| 2043 | { | ||
| 2044 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | ||
| 2045 | return 0; | ||
| 2046 | } | ||
| 2047 | detect_info->found |= found; | ||
| 2048 | return 1; | ||
| 2049 | } | ||
| 2050 | |||
| 2051 | |||
| 2052 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | ||
| 2053 | character. If CMP_STATUS indicates that we must expect MSEQ or | ||
| 2054 | RULE described above, decode it and return the negative value of | ||
| 2055 | the deocded character or rule. If an invalid byte is found, return | ||
| 2056 | -1. If SRC is too short, return -2. */ | ||
| 2057 | |||
| 1950 | int | 2058 | int |
| 1951 | emacs_mule_char (coding, src, nbytes, nchars, id) | 2059 | emacs_mule_char (coding, src, nbytes, nchars, id, cmp_status) |
| 1952 | struct coding_system *coding; | 2060 | struct coding_system *coding; |
| 1953 | const unsigned char *src; | 2061 | const unsigned char *src; |
| 1954 | int *nbytes, *nchars, *id; | 2062 | int *nbytes, *nchars, *id; |
| 2063 | struct composition_status *cmp_status; | ||
| 1955 | { | 2064 | { |
| 1956 | const unsigned char *src_end = coding->source + coding->src_bytes; | 2065 | const unsigned char *src_end = coding->source + coding->src_bytes; |
| 1957 | const unsigned char *src_base = src; | 2066 | const unsigned char *src_base = src; |
| @@ -1960,6 +2069,7 @@ emacs_mule_char (coding, src, nbytes, nchars, id) | |||
| 1960 | unsigned code; | 2069 | unsigned code; |
| 1961 | int c; | 2070 | int c; |
| 1962 | int consumed_chars = 0; | 2071 | int consumed_chars = 0; |
| 2072 | int mseq_found = 0; | ||
| 1963 | 2073 | ||
| 1964 | ONE_MORE_BYTE (c); | 2074 | ONE_MORE_BYTE (c); |
| 1965 | if (c < 0) | 2075 | if (c < 0) |
| @@ -1971,14 +2081,31 @@ emacs_mule_char (coding, src, nbytes, nchars, id) | |||
| 1971 | { | 2081 | { |
| 1972 | if (c >= 0xA0) | 2082 | if (c >= 0xA0) |
| 1973 | { | 2083 | { |
| 1974 | /* Old style component character of a composition. */ | 2084 | if (cmp_status->state != COMPOSING_NO |
| 1975 | if (c == 0xA0) | 2085 | && cmp_status->old_form) |
| 1976 | { | 2086 | { |
| 1977 | ONE_MORE_BYTE (c); | 2087 | if (cmp_status->state == COMPOSING_CHAR) |
| 1978 | c -= 0x80; | 2088 | { |
| 2089 | if (c == 0xA0) | ||
| 2090 | { | ||
| 2091 | ONE_MORE_BYTE (c); | ||
| 2092 | c -= 0x80; | ||
| 2093 | if (c < 0) | ||
| 2094 | goto invalid_code; | ||
| 2095 | } | ||
| 2096 | else | ||
| 2097 | c -= 0x20; | ||
| 2098 | mseq_found = 1; | ||
| 2099 | } | ||
| 2100 | else | ||
| 2101 | { | ||
| 2102 | *nbytes = src - src_base; | ||
| 2103 | *nchars = consumed_chars; | ||
| 2104 | return -c; | ||
| 2105 | } | ||
| 1979 | } | 2106 | } |
| 1980 | else | 2107 | else |
| 1981 | c -= 0x20; | 2108 | goto invalid_code; |
| 1982 | } | 2109 | } |
| 1983 | 2110 | ||
| 1984 | switch (emacs_mule_bytes[c]) | 2111 | switch (emacs_mule_bytes[c]) |
| @@ -2050,7 +2177,7 @@ emacs_mule_char (coding, src, nbytes, nchars, id) | |||
| 2050 | *nchars = consumed_chars; | 2177 | *nchars = consumed_chars; |
| 2051 | if (id) | 2178 | if (id) |
| 2052 | *id = charset->id; | 2179 | *id = charset->id; |
| 2053 | return c; | 2180 | return (mseq_found ? -c : c); |
| 2054 | 2181 | ||
| 2055 | no_more_source: | 2182 | no_more_source: |
| 2056 | return -2; | 2183 | return -2; |
| @@ -2060,259 +2187,250 @@ emacs_mule_char (coding, src, nbytes, nchars, id) | |||
| 2060 | } | 2187 | } |
| 2061 | 2188 | ||
| 2062 | 2189 | ||
| 2063 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | 2190 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
| 2064 | Check if a text is encoded in `emacs-mule'. If it is, return 1, | ||
| 2065 | else return 0. */ | ||
| 2066 | 2191 | ||
| 2067 | static int | 2192 | /* Handle these composition sequence ('|': the end of header elements, |
| 2068 | detect_coding_emacs_mule (coding, detect_info) | 2193 | BYTES and CHARS >= 0xA0): |
| 2069 | struct coding_system *coding; | ||
| 2070 | struct coding_detection_info *detect_info; | ||
| 2071 | { | ||
| 2072 | const unsigned char *src = coding->source, *src_base; | ||
| 2073 | const unsigned char *src_end = coding->source + coding->src_bytes; | ||
| 2074 | int multibytep = coding->src_multibyte; | ||
| 2075 | int consumed_chars = 0; | ||
| 2076 | int c; | ||
| 2077 | int found = 0; | ||
| 2078 | 2194 | ||
| 2079 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | 2195 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
| 2080 | /* A coding system of this category is always ASCII compatible. */ | 2196 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... |
| 2081 | src += coding->head_ascii; | 2197 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... |
| 2082 | 2198 | ||
| 2083 | while (1) | 2199 | and these old form: |
| 2084 | { | 2200 | |
| 2085 | src_base = src; | 2201 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
| 2086 | ONE_MORE_BYTE (c); | 2202 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ |
| 2087 | if (c < 0) | ||
| 2088 | continue; | ||
| 2089 | if (c == 0x80) | ||
| 2090 | { | ||
| 2091 | /* Perhaps the start of composite character. We simple skip | ||
| 2092 | it because analyzing it is too heavy for detecting. But, | ||
| 2093 | at least, we check that the composite character | ||
| 2094 | constitutes of more than 4 bytes. */ | ||
| 2095 | const unsigned char *src_base; | ||
| 2096 | 2203 | ||
| 2097 | repeat: | 2204 | When the starter 0x80 and the following header elements are found, |
| 2098 | src_base = src; | 2205 | this annotation header is produced. |
| 2099 | do | ||
| 2100 | { | ||
| 2101 | ONE_MORE_BYTE (c); | ||
| 2102 | } | ||
| 2103 | while (c >= 0xA0); | ||
| 2104 | 2206 | ||
| 2105 | if (src - src_base <= 4) | 2207 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
| 2106 | break; | ||
| 2107 | found = CATEGORY_MASK_EMACS_MULE; | ||
| 2108 | if (c == 0x80) | ||
| 2109 | goto repeat; | ||
| 2110 | } | ||
| 2111 | 2208 | ||
| 2112 | if (c < 0x80) | 2209 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
| 2113 | { | 2210 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
| 2114 | if (c < 0x20 | ||
| 2115 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | ||
| 2116 | break; | ||
| 2117 | } | ||
| 2118 | else | ||
| 2119 | { | ||
| 2120 | int more_bytes = emacs_mule_bytes[*src_base] - 1; | ||
| 2121 | 2211 | ||
| 2122 | while (more_bytes > 0) | 2212 | Then, upon reading the following elements, these codes are produced |
| 2123 | { | 2213 | until the composition end is found: |
| 2124 | ONE_MORE_BYTE (c); | ||
| 2125 | if (c < 0xA0) | ||
| 2126 | { | ||
| 2127 | src--; /* Unread the last byte. */ | ||
| 2128 | break; | ||
| 2129 | } | ||
| 2130 | more_bytes--; | ||
| 2131 | } | ||
| 2132 | if (more_bytes != 0) | ||
| 2133 | break; | ||
| 2134 | found = CATEGORY_MASK_EMACS_MULE; | ||
| 2135 | } | ||
| 2136 | } | ||
| 2137 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | ||
| 2138 | return 0; | ||
| 2139 | 2214 | ||
| 2140 | no_more_source: | 2215 | (1) CHAR ... CHAR |
| 2141 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | 2216 | (2) ALT ... ALT CHAR ... CHAR |
| 2142 | { | 2217 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR |
| 2143 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | 2218 | (4) CHAR ... CHAR |
| 2144 | return 0; | 2219 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR |
| 2145 | } | ||
| 2146 | detect_info->found |= found; | ||
| 2147 | return 1; | ||
| 2148 | } | ||
| 2149 | 2220 | ||
| 2221 | When the composition end is found, LENGTH and NCHARS in the | ||
| 2222 | annotation header is updated as below: | ||
| 2150 | 2223 | ||
| 2151 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ | 2224 | (1) LENGTH: unchanged, NCHARS: unchanged |
| 2225 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | ||
| 2226 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | ||
| 2227 | (4) LENGTH: unchanged, NCHARS: number of CHARs | ||
| 2228 | (5) LENGTH: unchanged, NCHARS: number of CHARs | ||
| 2152 | 2229 | ||
| 2153 | /* Decode a character represented as a component of composition | 2230 | If an error is found while composing, the annotation header is |
| 2154 | sequence of Emacs 20/21 style at SRC. Set C to that character and | 2231 | changed to the original composition header (plus filler -1s) as |
| 2155 | update SRC to the head of next character (or an encoded composition | 2232 | below: |
| 2156 | rule). If SRC doesn't points a composition component, set C to -1. | 2233 | |
| 2157 | If SRC points an invalid byte sequence, global exit by a return | 2234 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] |
| 2158 | value 0. */ | 2235 | (5) [ 0x80 0xFF -1 -1- -1 ] |
| 2159 | 2236 | ||
| 2160 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | 2237 | and the sequence [ -2 DECODED-RULE ] is changed to the original |
| 2161 | do \ | 2238 | byte sequence as below: |
| 2162 | { \ | 2239 | o the original byte sequence is B: [ B -1 ] |
| 2163 | int c; \ | 2240 | o the original byte sequence is B1 B2: [ B1 B2 ] |
| 2164 | int nbytes, nchars; \ | 2241 | |
| 2165 | \ | 2242 | Most of the routines are implemented by macros because many |
| 2166 | if (src == src_end) \ | 2243 | variables and labels in the caller decode_coding_emacs_mule must be |
| 2167 | break; \ | 2244 | accessible, and they are usually called just once (thus doesn't |
| 2168 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ | 2245 | increase the size of compiled object). */ |
| 2169 | if (c < 0) \ | 2246 | |
| 2170 | { \ | 2247 | /* Decode a composition rule represented by C as a component of |
| 2171 | if (c == -2) \ | 2248 | composition sequence of Emacs 20 style. Set RULE to the decoded |
| 2172 | break; \ | 2249 | rule. */ |
| 2173 | goto invalid_code; \ | 2250 | |
| 2174 | } \ | 2251 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ |
| 2175 | *buf++ = c; \ | ||
| 2176 | src += nbytes; \ | ||
| 2177 | consumed_chars += nchars; \ | ||
| 2178 | } \ | ||
| 2179 | while (0) | ||
| 2180 | |||
| 2181 | |||
| 2182 | /* Decode a composition rule represented as a component of composition | ||
| 2183 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, | ||
| 2184 | and increment BUF. If SRC points an invalid byte sequence, set C | ||
| 2185 | to -1. */ | ||
| 2186 | |||
| 2187 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ | ||
| 2188 | do { \ | 2252 | do { \ |
| 2189 | int c, gref, nref; \ | 2253 | int gref, nref; \ |
| 2190 | \ | 2254 | \ |
| 2191 | if (src >= src_end) \ | ||
| 2192 | goto invalid_code; \ | ||
| 2193 | ONE_MORE_BYTE_NO_CHECK (c); \ | ||
| 2194 | c -= 0xA0; \ | 2255 | c -= 0xA0; \ |
| 2195 | if (c < 0 || c >= 81) \ | 2256 | if (c < 0 || c >= 81) \ |
| 2196 | goto invalid_code; \ | 2257 | goto invalid_code; \ |
| 2197 | \ | ||
| 2198 | gref = c / 9, nref = c % 9; \ | 2258 | gref = c / 9, nref = c % 9; \ |
| 2199 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | 2259 | if (gref == 4) gref = 10; \ |
| 2260 | if (nref == 4) nref = 10; \ | ||
| 2261 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | ||
| 2200 | } while (0) | 2262 | } while (0) |
| 2201 | 2263 | ||
| 2202 | 2264 | ||
| 2203 | /* Decode a composition rule represented as a component of composition | 2265 | /* Decode a composition rule represented by C and the following byte |
| 2204 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | 2266 | at SRC as a component of composition sequence of Emacs 21 style. |
| 2205 | and increment BUF. If SRC points an invalid byte sequence, set C | 2267 | Set RULE to the decoded rule. */ |
| 2206 | to -1. */ | ||
| 2207 | 2268 | ||
| 2208 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | 2269 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
| 2209 | do { \ | 2270 | do { \ |
| 2210 | int gref, nref; \ | 2271 | int gref, nref; \ |
| 2211 | \ | 2272 | \ |
| 2212 | if (src + 1>= src_end) \ | 2273 | gref = c - 0x20; \ |
| 2274 | if (gref < 0 || gref >= 81) \ | ||
| 2213 | goto invalid_code; \ | 2275 | goto invalid_code; \ |
| 2214 | ONE_MORE_BYTE_NO_CHECK (gref); \ | 2276 | ONE_MORE_BYTE (c); \ |
| 2215 | gref -= 0x20; \ | 2277 | nref = c - 0x20; \ |
| 2216 | ONE_MORE_BYTE_NO_CHECK (nref); \ | 2278 | if (nref < 0 || nref >= 81) \ |
| 2217 | nref -= 0x20; \ | ||
| 2218 | if (gref < 0 || gref >= 81 \ | ||
| 2219 | || nref < 0 || nref >= 81) \ | ||
| 2220 | goto invalid_code; \ | 2279 | goto invalid_code; \ |
| 2221 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | 2280 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
| 2222 | } while (0) | 2281 | } while (0) |
| 2223 | 2282 | ||
| 2224 | 2283 | ||
| 2225 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ | 2284 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
| 2285 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | ||
| 2286 | byte length of this composition information, CHARS is the number of | ||
| 2287 | characters composed by this composition. */ | ||
| 2288 | |||
| 2289 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | ||
| 2226 | do { \ | 2290 | do { \ |
| 2227 | /* Emacs 21 style format. The first three bytes at SRC are \ | ||
| 2228 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ | ||
| 2229 | the byte length of this composition information, CHARS is the \ | ||
| 2230 | number of characters composed by this composition. */ \ | ||
| 2231 | enum composition_method method = c - 0xF2; \ | 2291 | enum composition_method method = c - 0xF2; \ |
| 2232 | int *charbuf_base = charbuf; \ | 2292 | int *charbuf_base = charbuf; \ |
| 2233 | int consumed_chars_limit; \ | ||
| 2234 | int nbytes, nchars; \ | 2293 | int nbytes, nchars; \ |
| 2235 | \ | 2294 | \ |
| 2236 | ONE_MORE_BYTE (c); \ | 2295 | ONE_MORE_BYTE (c); \ |
| 2237 | if (c < 0) \ | 2296 | if (c < 0) \ |
| 2238 | goto invalid_code; \ | 2297 | goto invalid_code; \ |
| 2239 | nbytes = c - 0xA0; \ | 2298 | nbytes = c - 0xA0; \ |
| 2240 | if (nbytes < 3) \ | 2299 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
| 2241 | goto invalid_code; \ | 2300 | goto invalid_code; \ |
| 2242 | ONE_MORE_BYTE (c); \ | 2301 | ONE_MORE_BYTE (c); \ |
| 2243 | if (c < 0) \ | ||
| 2244 | goto invalid_code; \ | ||
| 2245 | nchars = c - 0xA0; \ | 2302 | nchars = c - 0xA0; \ |
| 2246 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ | 2303 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
| 2247 | consumed_chars_limit = consumed_chars_base + nbytes; \ | 2304 | goto invalid_code; \ |
| 2248 | if (method != COMPOSITION_RELATIVE) \ | 2305 | cmp_status->old_form = 0; \ |
| 2249 | { \ | 2306 | cmp_status->method = method; \ |
| 2250 | int i = 0; \ | 2307 | if (method == COMPOSITION_RELATIVE) \ |
| 2251 | while (consumed_chars < consumed_chars_limit) \ | 2308 | cmp_status->state = COMPOSING_CHAR; \ |
| 2252 | { \ | 2309 | else \ |
| 2253 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ | 2310 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ |
| 2254 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ | 2311 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ |
| 2255 | else \ | 2312 | cmp_status->nchars = nchars; \ |
| 2256 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | 2313 | cmp_status->ncomps = nbytes - 4; \ |
| 2257 | i++; \ | 2314 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ |
| 2258 | } \ | ||
| 2259 | if (consumed_chars < consumed_chars_limit) \ | ||
| 2260 | goto invalid_code; \ | ||
| 2261 | charbuf_base[0] -= i; \ | ||
| 2262 | } \ | ||
| 2263 | } while (0) | 2315 | } while (0) |
| 2264 | 2316 | ||
| 2265 | 2317 | ||
| 2266 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ | 2318 | /* Start of Emacs 20 style format for relative composition. */ |
| 2267 | do { \ | 2319 | |
| 2268 | /* Emacs 20 style format for relative composition. */ \ | 2320 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ |
| 2269 | /* Store multibyte form of characters to be composed. */ \ | 2321 | do { \ |
| 2270 | enum composition_method method = COMPOSITION_RELATIVE; \ | 2322 | cmp_status->old_form = 1; \ |
| 2271 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ | 2323 | cmp_status->method = COMPOSITION_RELATIVE; \ |
| 2272 | int *buf = components; \ | 2324 | cmp_status->state = COMPOSING_CHAR; \ |
| 2273 | int i, j; \ | 2325 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ |
| 2274 | \ | 2326 | cmp_status->nchars = cmp_status->ncomps = 0; \ |
| 2275 | src = src_base; \ | 2327 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ |
| 2276 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | ||
| 2277 | for (i = 0; *src >= 0xA0 && i < MAX_COMPOSITION_COMPONENTS; i++) \ | ||
| 2278 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | ||
| 2279 | if (i < 2) \ | ||
| 2280 | goto invalid_code; \ | ||
| 2281 | ADD_COMPOSITION_DATA (charbuf, i, method); \ | ||
| 2282 | for (j = 0; j < i; j++) \ | ||
| 2283 | *charbuf++ = components[j]; \ | ||
| 2284 | } while (0) | 2328 | } while (0) |
| 2285 | 2329 | ||
| 2286 | 2330 | ||
| 2287 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | 2331 | /* Start of Emacs 20 style format for rule-base composition. */ |
| 2332 | |||
| 2333 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | ||
| 2334 | do { \ | ||
| 2335 | cmp_status->old_form = 1; \ | ||
| 2336 | cmp_status->method = COMPOSITION_WITH_RULE; \ | ||
| 2337 | cmp_status->state = COMPOSING_CHAR; \ | ||
| 2338 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | ||
| 2339 | cmp_status->nchars = cmp_status->ncomps = 0; \ | ||
| 2340 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | ||
| 2341 | } while (0) | ||
| 2342 | |||
| 2343 | |||
| 2344 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ | ||
| 2345 | do { \ | ||
| 2346 | const unsigned char *current_src = src; \ | ||
| 2347 | \ | ||
| 2348 | ONE_MORE_BYTE (c); \ | ||
| 2349 | if (c < 0) \ | ||
| 2350 | goto invalid_code; \ | ||
| 2351 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | ||
| 2352 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | ||
| 2353 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | ||
| 2354 | else if (c < 0xA0) \ | ||
| 2355 | goto invalid_code; \ | ||
| 2356 | else if (c < 0xC0) \ | ||
| 2357 | { \ | ||
| 2358 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | ||
| 2359 | /* Re-read C as a composition component. */ \ | ||
| 2360 | src = current_src; \ | ||
| 2361 | } \ | ||
| 2362 | else if (c == 0xFF) \ | ||
| 2363 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | ||
| 2364 | else \ | ||
| 2365 | goto invalid_code; \ | ||
| 2366 | } while (0) | ||
| 2367 | |||
| 2368 | #define EMACS_MULE_COMPOSITION_END() \ | ||
| 2288 | do { \ | 2369 | do { \ |
| 2289 | /* Emacs 20 style format for rule-base composition. */ \ | 2370 | int idx = - cmp_status->length; \ |
| 2290 | /* Store multibyte form of characters to be composed. */ \ | ||
| 2291 | enum composition_method method = COMPOSITION_WITH_RULE; \ | ||
| 2292 | int *charbuf_base = charbuf; \ | ||
| 2293 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ | ||
| 2294 | int *buf = components; \ | ||
| 2295 | int i, j; \ | ||
| 2296 | \ | 2371 | \ |
| 2297 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | 2372 | if (cmp_status->old_form) \ |
| 2298 | for (i = 1; i < MAX_COMPOSITION_COMPONENTS; i++) \ | 2373 | charbuf[idx + 2] = cmp_status->nchars; \ |
| 2299 | { \ | 2374 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ |
| 2300 | if (*src < 0xA0) \ | 2375 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ |
| 2301 | break; \ | 2376 | cmp_status->state = COMPOSING_NO; \ |
| 2302 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ | 2377 | } while (0) |
| 2303 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | 2378 | |
| 2304 | } \ | 2379 | |
| 2305 | if (i <= 1 || (buf - components) % 2 == 0) \ | 2380 | static int |
| 2306 | goto invalid_code; \ | 2381 | emacs_mule_finish_composition (charbuf, cmp_status) |
| 2307 | if (charbuf + i + (i / 2) + 1 >= charbuf_end) \ | 2382 | int *charbuf; |
| 2308 | goto no_more_source; \ | 2383 | struct composition_status *cmp_status; |
| 2309 | ADD_COMPOSITION_DATA (charbuf, i, method); \ | 2384 | { |
| 2310 | i = i * 2 - 1; \ | 2385 | int idx = - cmp_status->length; |
| 2311 | for (j = 0; j < i; j++) \ | 2386 | int new_chars; |
| 2312 | *charbuf++ = components[j]; \ | 2387 | |
| 2313 | charbuf_base[0] -= i; \ | 2388 | if (cmp_status->old_form && cmp_status->nchars > 0) |
| 2314 | for (j = 0; j < i; j += 2) \ | 2389 | { |
| 2315 | *charbuf++ = components[j]; \ | 2390 | charbuf[idx + 2] = cmp_status->nchars; |
| 2391 | new_chars = 0; | ||
| 2392 | if (cmp_status->method == COMPOSITION_WITH_RULE | ||
| 2393 | && cmp_status->state == COMPOSING_CHAR) | ||
| 2394 | { | ||
| 2395 | /* The last rule was invalid. */ | ||
| 2396 | int rule = charbuf[-1] + 0xA0; | ||
| 2397 | |||
| 2398 | charbuf[-2] = BYTE8_TO_CHAR (rule); | ||
| 2399 | charbuf[-1] = -1; | ||
| 2400 | new_chars = 1; | ||
| 2401 | } | ||
| 2402 | } | ||
| 2403 | else | ||
| 2404 | { | ||
| 2405 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | ||
| 2406 | |||
| 2407 | if (cmp_status->method == COMPOSITION_WITH_RULE) | ||
| 2408 | { | ||
| 2409 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | ||
| 2410 | charbuf[idx++] = -3; | ||
| 2411 | charbuf[idx++] = 0; | ||
| 2412 | new_chars = 1; | ||
| 2413 | } | ||
| 2414 | else | ||
| 2415 | { | ||
| 2416 | int nchars = charbuf[idx + 1] + 0xA0; | ||
| 2417 | int nbytes = charbuf[idx + 2] + 0xA0; | ||
| 2418 | |||
| 2419 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | ||
| 2420 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | ||
| 2421 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | ||
| 2422 | charbuf[idx++] = -1; | ||
| 2423 | new_chars = 4; | ||
| 2424 | } | ||
| 2425 | } | ||
| 2426 | cmp_status->state = COMPOSING_NO; | ||
| 2427 | return new_chars; | ||
| 2428 | } | ||
| 2429 | |||
| 2430 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | ||
| 2431 | do { \ | ||
| 2432 | if (cmp_status->state != COMPOSING_NO) \ | ||
| 2433 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | ||
| 2316 | } while (0) | 2434 | } while (0) |
| 2317 | 2435 | ||
| 2318 | 2436 | ||
| @@ -2335,12 +2453,22 @@ decode_coding_emacs_mule (coding) | |||
| 2335 | int eol_crlf = | 2453 | int eol_crlf = |
| 2336 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | 2454 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
| 2337 | int byte_after_cr = -1; | 2455 | int byte_after_cr = -1; |
| 2456 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; | ||
| 2338 | 2457 | ||
| 2339 | CODING_GET_INFO (coding, attrs, charset_list); | 2458 | CODING_GET_INFO (coding, attrs, charset_list); |
| 2340 | 2459 | ||
| 2460 | if (cmp_status->state != COMPOSING_NO) | ||
| 2461 | { | ||
| 2462 | int i; | ||
| 2463 | |||
| 2464 | for (i = 0; i < cmp_status->length; i++) | ||
| 2465 | *charbuf++ = cmp_status->carryover[i]; | ||
| 2466 | coding->annotated = 1; | ||
| 2467 | } | ||
| 2468 | |||
| 2341 | while (1) | 2469 | while (1) |
| 2342 | { | 2470 | { |
| 2343 | int c; | 2471 | int c, id; |
| 2344 | 2472 | ||
| 2345 | src_base = src; | 2473 | src_base = src; |
| 2346 | consumed_chars_base = consumed_chars; | 2474 | consumed_chars_base = consumed_chars; |
| @@ -2356,64 +2484,160 @@ decode_coding_emacs_mule (coding) | |||
| 2356 | c = byte_after_cr, byte_after_cr = -1; | 2484 | c = byte_after_cr, byte_after_cr = -1; |
| 2357 | else | 2485 | else |
| 2358 | ONE_MORE_BYTE (c); | 2486 | ONE_MORE_BYTE (c); |
| 2359 | if (c < 0) | 2487 | |
| 2488 | if (c < 0 || c == 0x80) | ||
| 2360 | { | 2489 | { |
| 2361 | *charbuf++ = -c; | 2490 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
| 2362 | char_offset++; | 2491 | if (c < 0) |
| 2492 | { | ||
| 2493 | *charbuf++ = -c; | ||
| 2494 | char_offset++; | ||
| 2495 | } | ||
| 2496 | else | ||
| 2497 | DECODE_EMACS_MULE_COMPOSITION_START (); | ||
| 2498 | continue; | ||
| 2363 | } | 2499 | } |
| 2364 | else if (c < 0x80) | 2500 | |
| 2501 | if (c < 0x80) | ||
| 2365 | { | 2502 | { |
| 2366 | if (eol_crlf && c == '\r') | 2503 | if (eol_crlf && c == '\r') |
| 2367 | ONE_MORE_BYTE (byte_after_cr); | 2504 | ONE_MORE_BYTE (byte_after_cr); |
| 2368 | *charbuf++ = c; | 2505 | id = charset_ascii; |
| 2369 | char_offset++; | 2506 | if (cmp_status->state != COMPOSING_NO) |
| 2370 | } | 2507 | { |
| 2371 | else if (c == 0x80) | 2508 | if (cmp_status->old_form) |
| 2372 | { | 2509 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
| 2373 | ONE_MORE_BYTE (c); | 2510 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) |
| 2374 | if (c < 0) | 2511 | cmp_status->ncomps--; |
| 2375 | goto invalid_code; | 2512 | } |
| 2376 | if (c - 0xF2 >= COMPOSITION_RELATIVE | ||
| 2377 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | ||
| 2378 | DECODE_EMACS_MULE_21_COMPOSITION (c); | ||
| 2379 | else if (c < 0xC0) | ||
| 2380 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | ||
| 2381 | else if (c == 0xFF) | ||
| 2382 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | ||
| 2383 | else | ||
| 2384 | goto invalid_code; | ||
| 2385 | } | 2513 | } |
| 2386 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | 2514 | else |
| 2387 | { | 2515 | { |
| 2388 | int nbytes, nchars; | 2516 | int nchars, nbytes; |
| 2389 | int id; | ||
| 2390 | 2517 | ||
| 2391 | src = src_base; | 2518 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, |
| 2392 | consumed_chars = consumed_chars_base; | 2519 | cmp_status); |
| 2393 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); | ||
| 2394 | if (c < 0) | 2520 | if (c < 0) |
| 2395 | { | 2521 | { |
| 2522 | if (c == -1) | ||
| 2523 | goto invalid_code; | ||
| 2396 | if (c == -2) | 2524 | if (c == -2) |
| 2397 | break; | 2525 | break; |
| 2398 | goto invalid_code; | ||
| 2399 | } | 2526 | } |
| 2527 | src = src_base + nbytes; | ||
| 2528 | consumed_chars = consumed_chars_base + nchars; | ||
| 2529 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | ||
| 2530 | cmp_status->ncomps -= nchars; | ||
| 2531 | } | ||
| 2532 | |||
| 2533 | /* Now if C >= 0, we found a normally encoded characer, if C < | ||
| 2534 | 0, we found an old-style composition component character or | ||
| 2535 | rule. */ | ||
| 2536 | |||
| 2537 | if (cmp_status->state == COMPOSING_NO) | ||
| 2538 | { | ||
| 2400 | if (last_id != id) | 2539 | if (last_id != id) |
| 2401 | { | 2540 | { |
| 2402 | if (last_id != charset_ascii) | 2541 | if (last_id != charset_ascii) |
| 2403 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); | 2542 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, |
| 2543 | last_id); | ||
| 2404 | last_id = id; | 2544 | last_id = id; |
| 2405 | last_offset = char_offset; | 2545 | last_offset = char_offset; |
| 2406 | } | 2546 | } |
| 2407 | *charbuf++ = c; | 2547 | *charbuf++ = c; |
| 2408 | src += nbytes; | ||
| 2409 | consumed_chars += nchars; | ||
| 2410 | char_offset++; | 2548 | char_offset++; |
| 2411 | } | 2549 | } |
| 2412 | else | 2550 | else if (cmp_status->state == COMPOSING_CHAR) |
| 2413 | goto invalid_code; | 2551 | { |
| 2552 | if (cmp_status->old_form) | ||
| 2553 | { | ||
| 2554 | if (c >= 0) | ||
| 2555 | { | ||
| 2556 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | ||
| 2557 | *charbuf++ = c; | ||
| 2558 | char_offset++; | ||
| 2559 | } | ||
| 2560 | else | ||
| 2561 | { | ||
| 2562 | *charbuf++ = -c; | ||
| 2563 | cmp_status->nchars++; | ||
| 2564 | cmp_status->length++; | ||
| 2565 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | ||
| 2566 | EMACS_MULE_COMPOSITION_END (); | ||
| 2567 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | ||
| 2568 | cmp_status->state = COMPOSING_RULE; | ||
| 2569 | } | ||
| 2570 | } | ||
| 2571 | else | ||
| 2572 | { | ||
| 2573 | *charbuf++ = c; | ||
| 2574 | cmp_status->length++; | ||
| 2575 | cmp_status->nchars--; | ||
| 2576 | if (cmp_status->nchars == 0) | ||
| 2577 | EMACS_MULE_COMPOSITION_END (); | ||
| 2578 | } | ||
| 2579 | } | ||
| 2580 | else if (cmp_status->state == COMPOSING_RULE) | ||
| 2581 | { | ||
| 2582 | int rule; | ||
| 2583 | |||
| 2584 | if (c >= 0) | ||
| 2585 | { | ||
| 2586 | EMACS_MULE_COMPOSITION_END (); | ||
| 2587 | *charbuf++ = c; | ||
| 2588 | char_offset++; | ||
| 2589 | } | ||
| 2590 | else | ||
| 2591 | { | ||
| 2592 | c = -c; | ||
| 2593 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | ||
| 2594 | if (rule < 0) | ||
| 2595 | goto invalid_code; | ||
| 2596 | *charbuf++ = -2; | ||
| 2597 | *charbuf++ = rule; | ||
| 2598 | cmp_status->length += 2; | ||
| 2599 | cmp_status->state = COMPOSING_CHAR; | ||
| 2600 | } | ||
| 2601 | } | ||
| 2602 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | ||
| 2603 | { | ||
| 2604 | *charbuf++ = c; | ||
| 2605 | cmp_status->length++; | ||
| 2606 | if (cmp_status->ncomps == 0) | ||
| 2607 | cmp_status->state = COMPOSING_CHAR; | ||
| 2608 | else if (cmp_status->ncomps > 0) | ||
| 2609 | { | ||
| 2610 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | ||
| 2611 | cmp_status->state = COMPOSING_COMPONENT_RULE; | ||
| 2612 | } | ||
| 2613 | else | ||
| 2614 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | ||
| 2615 | } | ||
| 2616 | else /* COMPOSING_COMPONENT_RULE */ | ||
| 2617 | { | ||
| 2618 | int rule; | ||
| 2619 | |||
| 2620 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | ||
| 2621 | if (rule < 0) | ||
| 2622 | goto invalid_code; | ||
| 2623 | *charbuf++ = -2; | ||
| 2624 | *charbuf++ = rule; | ||
| 2625 | cmp_status->length += 2; | ||
| 2626 | cmp_status->ncomps--; | ||
| 2627 | if (cmp_status->ncomps > 0) | ||
| 2628 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | ||
| 2629 | else | ||
| 2630 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | ||
| 2631 | } | ||
| 2632 | continue; | ||
| 2633 | |||
| 2634 | retry: | ||
| 2635 | src = src_base; | ||
| 2636 | consumed_chars = consumed_chars_base; | ||
| 2414 | continue; | 2637 | continue; |
| 2415 | 2638 | ||
| 2416 | invalid_code: | 2639 | invalid_code: |
| 2640 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | ||
| 2417 | src = src_base; | 2641 | src = src_base; |
| 2418 | consumed_chars = consumed_chars_base; | 2642 | consumed_chars = consumed_chars_base; |
| 2419 | ONE_MORE_BYTE (c); | 2643 | ONE_MORE_BYTE (c); |
| @@ -2423,6 +2647,19 @@ decode_coding_emacs_mule (coding) | |||
| 2423 | } | 2647 | } |
| 2424 | 2648 | ||
| 2425 | no_more_source: | 2649 | no_more_source: |
| 2650 | if (cmp_status->state != COMPOSING_NO) | ||
| 2651 | { | ||
| 2652 | if (coding->mode & CODING_MODE_LAST_BLOCK) | ||
| 2653 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | ||
| 2654 | else | ||
| 2655 | { | ||
| 2656 | int i; | ||
| 2657 | |||
| 2658 | charbuf -= cmp_status->length; | ||
| 2659 | for (i = 0; i < cmp_status->length; i++) | ||
| 2660 | cmp_status->carryover[i] = charbuf[i]; | ||
| 2661 | } | ||
| 2662 | } | ||
| 2426 | if (last_id != charset_ascii) | 2663 | if (last_id != charset_ascii) |
| 2427 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); | 2664 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
| 2428 | coding->consumed_char += consumed_chars_base; | 2665 | coding->consumed_char += consumed_chars_base; |
| @@ -3077,134 +3314,237 @@ detect_coding_iso_2022 (coding, detect_info) | |||
| 3077 | } while (0) | 3314 | } while (0) |
| 3078 | 3315 | ||
| 3079 | 3316 | ||
| 3080 | #define MAYBE_FINISH_COMPOSITION() \ | 3317 | /* Handle these composition sequence (ALT: alternate char): |
| 3318 | |||
| 3319 | (1) relative composition: ESC 0 CHAR ... ESC 1 | ||
| 3320 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | ||
| 3321 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | ||
| 3322 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | ||
| 3323 | |||
| 3324 | When the start sequence (ESC 0/2/3/4) is found, this annotation | ||
| 3325 | header is produced. | ||
| 3326 | |||
| 3327 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | ||
| 3328 | |||
| 3329 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | ||
| 3330 | produced until the end sequence (ESC 1) is found: | ||
| 3331 | |||
| 3332 | (1) CHAR ... CHAR | ||
| 3333 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | ||
| 3334 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | ||
| 3335 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | ||
| 3336 | |||
| 3337 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | ||
| 3338 | annotation header is updated as below: | ||
| 3339 | |||
| 3340 | (1) LENGTH: unchanged, NCHARS: number of CHARs | ||
| 3341 | (2) LENGTH: unchanged, NCHARS: number of CHARs | ||
| 3342 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | ||
| 3343 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | ||
| 3344 | |||
| 3345 | If an error is found while composing, the annotation header is | ||
| 3346 | changed to: | ||
| 3347 | |||
| 3348 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | ||
| 3349 | |||
| 3350 | and the sequence [ -2 DECODED-RULE ] is changed to the original | ||
| 3351 | byte sequence as below: | ||
| 3352 | o the original byte sequence is B: [ B -1 ] | ||
| 3353 | o the original byte sequence is B1 B2: [ B1 B2 ] | ||
| 3354 | and the sequence [ -1 -1 ] is changed to the original byte | ||
| 3355 | sequence: | ||
| 3356 | [ ESC '0' ] | ||
| 3357 | */ | ||
| 3358 | |||
| 3359 | /* Decode a composition rule C1 and maybe one more byte from the | ||
| 3360 | source, and set RULE to the encoded composition rule, NBYTES to the | ||
| 3361 | length of the composition rule. If the rule is invalid, set RULE | ||
| 3362 | to some negative value. */ | ||
| 3363 | |||
| 3364 | #define DECODE_COMPOSITION_RULE(rule, nbytes) \ | ||
| 3365 | do { \ | ||
| 3366 | rule = c1 - 32; \ | ||
| 3367 | if (rule < 0) \ | ||
| 3368 | break; \ | ||
| 3369 | if (rule < 81) /* old format (before ver.21) */ \ | ||
| 3370 | { \ | ||
| 3371 | int gref = (rule) / 9; \ | ||
| 3372 | int nref = (rule) % 9; \ | ||
| 3373 | if (gref == 4) gref = 10; \ | ||
| 3374 | if (nref == 4) nref = 10; \ | ||
| 3375 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | ||
| 3376 | nbytes = 1; \ | ||
| 3377 | } \ | ||
| 3378 | else /* new format (after ver.21) */ \ | ||
| 3379 | { \ | ||
| 3380 | int c; \ | ||
| 3381 | \ | ||
| 3382 | ONE_MORE_BYTE (c); \ | ||
| 3383 | rule = COMPOSITION_ENCODE_RULE (rule - 81, c - 32); \ | ||
| 3384 | if (rule >= 0) \ | ||
| 3385 | rule += 0x100; /* to destinguish it from the old format */ \ | ||
| 3386 | nbytes = 2; \ | ||
| 3387 | } \ | ||
| 3388 | } while (0) | ||
| 3389 | |||
| 3390 | #define ENCODE_COMPOSITION_RULE(rule) \ | ||
| 3081 | do { \ | 3391 | do { \ |
| 3082 | int i; \ | 3392 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
| 3083 | if (composition_state == COMPOSING_NO) \ | 3393 | \ |
| 3084 | break; \ | 3394 | if (rule < 0x100) /* old format */ \ |
| 3085 | /* It is assured that we have enough room for producing \ | ||
| 3086 | characters stored in the table `components'. */ \ | ||
| 3087 | if (charbuf + component_idx > charbuf_end) \ | ||
| 3088 | goto no_more_source; \ | ||
| 3089 | composition_state = COMPOSING_NO; \ | ||
| 3090 | if (method == COMPOSITION_RELATIVE \ | ||
| 3091 | || method == COMPOSITION_WITH_ALTCHARS) \ | ||
| 3092 | { \ | 3395 | { \ |
| 3093 | for (i = 0; i < component_idx; i++) \ | 3396 | if (gref == 10) gref = 4; \ |
| 3094 | *charbuf++ = components[i]; \ | 3397 | if (nref == 10) nref = 4; \ |
| 3095 | char_offset += component_idx; \ | 3398 | charbuf[idx] = 32 + gref * 9 + nref; \ |
| 3399 | charbuf[idx + 1] = -1; \ | ||
| 3400 | new_chars++; \ | ||
| 3096 | } \ | 3401 | } \ |
| 3097 | else \ | 3402 | else /* new format */ \ |
| 3098 | { \ | 3403 | { \ |
| 3099 | for (i = 0; i < component_idx; i += 2) \ | 3404 | charbuf[idx] = 32 + 81 + gref; \ |
| 3100 | *charbuf++ = components[i]; \ | 3405 | charbuf[idx + 1] = 32 + nref; \ |
| 3101 | char_offset += (component_idx / 2) + 1; \ | 3406 | new_chars += 2; \ |
| 3102 | } \ | 3407 | } \ |
| 3103 | } while (0) | 3408 | } while (0) |
| 3104 | 3409 | ||
| 3410 | /* Finish the current composition as invalid. */ | ||
| 3411 | |||
| 3412 | static int finish_composition P_ ((int *, struct composition_status *)); | ||
| 3413 | |||
| 3414 | static int | ||
| 3415 | finish_composition (charbuf, cmp_status) | ||
| 3416 | int *charbuf; | ||
| 3417 | struct composition_status *cmp_status; | ||
| 3418 | { | ||
| 3419 | int idx = - cmp_status->length; | ||
| 3420 | int new_chars; | ||
| 3421 | |||
| 3422 | /* Recover the original ESC sequence */ | ||
| 3423 | charbuf[idx++] = ISO_CODE_ESC; | ||
| 3424 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | ||
| 3425 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | ||
| 3426 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | ||
| 3427 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | ||
| 3428 | : '4'); | ||
| 3429 | charbuf[idx++] = -2; | ||
| 3430 | charbuf[idx++] = 0; | ||
| 3431 | charbuf[idx++] = -1; | ||
| 3432 | new_chars = cmp_status->nchars; | ||
| 3433 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | ||
| 3434 | for (; idx < 0; idx++) | ||
| 3435 | { | ||
| 3436 | int elt = charbuf[idx]; | ||
| 3437 | |||
| 3438 | if (elt == -2) | ||
| 3439 | { | ||
| 3440 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | ||
| 3441 | idx++; | ||
| 3442 | } | ||
| 3443 | else if (elt == -1) | ||
| 3444 | { | ||
| 3445 | charbuf[idx++] = ISO_CODE_ESC; | ||
| 3446 | charbuf[idx] = '0'; | ||
| 3447 | new_chars += 2; | ||
| 3448 | } | ||
| 3449 | } | ||
| 3450 | cmp_status->state = COMPOSING_NO; | ||
| 3451 | return new_chars; | ||
| 3452 | } | ||
| 3453 | |||
| 3454 | /* If characers are under composition, finish the composition. */ | ||
| 3455 | #define MAYBE_FINISH_COMPOSITION() \ | ||
| 3456 | do { \ | ||
| 3457 | if (cmp_status->state != COMPOSING_NO) \ | ||
| 3458 | char_offset += finish_composition (charbuf, cmp_status); \ | ||
| 3459 | } while (0) | ||
| 3105 | 3460 | ||
| 3106 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. | 3461 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
| 3462 | |||
| 3107 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | 3463 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
| 3108 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | 3464 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 |
| 3109 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 | 3465 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
| 3110 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | 3466 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 |
| 3111 | */ | ||
| 3112 | 3467 | ||
| 3113 | #define DECODE_COMPOSITION_START(c1) \ | 3468 | Produce this annotation sequence now: |
| 3114 | do { \ | 3469 | |
| 3115 | if (c1 == '0' \ | 3470 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] |
| 3116 | && composition_state == COMPOSING_COMPONENT_RULE) \ | 3471 | */ |
| 3117 | { \ | 3472 | |
| 3118 | component_len = component_idx; \ | 3473 | #define DECODE_COMPOSITION_START(c1) \ |
| 3119 | composition_state = COMPOSING_CHAR; \ | 3474 | do { \ |
| 3120 | } \ | 3475 | if (c1 == '0' \ |
| 3121 | else \ | 3476 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ |
| 3122 | { \ | 3477 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
| 3123 | const unsigned char *p; \ | 3478 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ |
| 3124 | \ | 3479 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ |
| 3125 | MAYBE_FINISH_COMPOSITION (); \ | 3480 | { \ |
| 3126 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | 3481 | *charbuf++ = -1; \ |
| 3127 | goto no_more_source; \ | 3482 | *charbuf++= -1; \ |
| 3128 | for (p = src; p < src_end - 1; p++) \ | 3483 | cmp_status->state = COMPOSING_CHAR; \ |
| 3129 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | 3484 | cmp_status->length += 2; \ |
| 3130 | break; \ | 3485 | } \ |
| 3131 | if (p == src_end - 1) \ | 3486 | else \ |
| 3132 | { \ | 3487 | { \ |
| 3133 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | 3488 | MAYBE_FINISH_COMPOSITION (); \ |
| 3134 | goto invalid_code; \ | 3489 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ |
| 3135 | /* The current composition doesn't end in the current \ | 3490 | : c1 == '2' ? COMPOSITION_WITH_RULE \ |
| 3136 | source. */ \ | 3491 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ |
| 3137 | record_conversion_result \ | 3492 | : COMPOSITION_WITH_RULE_ALTCHARS); \ |
| 3138 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | 3493 | cmp_status->state \ |
| 3139 | goto no_more_source; \ | 3494 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ |
| 3140 | } \ | 3495 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ |
| 3141 | \ | 3496 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ |
| 3142 | /* This is surely the start of a composition. */ \ | 3497 | cmp_status->nchars = cmp_status->ncomps = 0; \ |
| 3143 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | 3498 | coding->annotated = 1; \ |
| 3144 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | 3499 | } \ |
| 3145 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | ||
| 3146 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | ||
| 3147 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | ||
| 3148 | : COMPOSING_COMPONENT_CHAR); \ | ||
| 3149 | component_idx = component_len = 0; \ | ||
| 3150 | } \ | ||
| 3151 | } while (0) | 3500 | } while (0) |
| 3152 | 3501 | ||
| 3153 | 3502 | ||
| 3154 | /* Handle compositoin end sequence ESC 1. */ | 3503 | /* Handle composition end sequence ESC 1. */ |
| 3155 | 3504 | ||
| 3156 | #define DECODE_COMPOSITION_END() \ | 3505 | #define DECODE_COMPOSITION_END() \ |
| 3157 | do { \ | 3506 | do { \ |
| 3158 | int nchars = (component_len > 0 ? component_idx - component_len \ | 3507 | if (cmp_status->nchars == 0 \ |
| 3159 | : method == COMPOSITION_RELATIVE ? component_idx \ | 3508 | || ((cmp_status->state == COMPOSING_CHAR) \ |
| 3160 | : (component_idx + 1) / 2); \ | 3509 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ |
| 3161 | int i; \ | ||
| 3162 | int *saved_charbuf = charbuf; \ | ||
| 3163 | \ | ||
| 3164 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ | ||
| 3165 | if (method != COMPOSITION_RELATIVE) \ | ||
| 3166 | { \ | 3510 | { \ |
| 3167 | if (component_len == 0) \ | 3511 | MAYBE_FINISH_COMPOSITION (); \ |
| 3168 | for (i = 0; i < component_idx; i++) \ | 3512 | goto invalid_code; \ |
| 3169 | *charbuf++ = components[i]; \ | ||
| 3170 | else \ | ||
| 3171 | for (i = 0; i < component_len; i++) \ | ||
| 3172 | *charbuf++ = components[i]; \ | ||
| 3173 | *saved_charbuf = saved_charbuf - charbuf; \ | ||
| 3174 | } \ | 3513 | } \ |
| 3175 | if (method == COMPOSITION_WITH_RULE) \ | 3514 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
| 3176 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | 3515 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ |
| 3177 | *charbuf++ = components[i]; \ | 3516 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ |
| 3178 | else \ | 3517 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ |
| 3179 | for (i = component_len; i < component_idx; i++, char_offset++) \ | 3518 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ |
| 3180 | *charbuf++ = components[i]; \ | 3519 | char_offset += cmp_status->nchars; \ |
| 3181 | coding->annotated = 1; \ | 3520 | cmp_status->state = COMPOSING_NO; \ |
| 3182 | composition_state = COMPOSING_NO; \ | ||
| 3183 | } while (0) | 3521 | } while (0) |
| 3184 | 3522 | ||
| 3523 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ | ||
| 3185 | 3524 | ||
| 3186 | /* Decode a composition rule from the byte C1 (and maybe one more byte | 3525 | #define STORE_COMPOSITION_RULE(rule) \ |
| 3187 | from SRC) and store one encoded composition rule in | 3526 | do { \ |
| 3188 | coding->cmp_data. */ | 3527 | *charbuf++ = -2; \ |
| 3528 | *charbuf++ = rule; \ | ||
| 3529 | cmp_status->length += 2; \ | ||
| 3530 | cmp_status->state--; \ | ||
| 3531 | } while (0) | ||
| 3189 | 3532 | ||
| 3190 | #define DECODE_COMPOSITION_RULE(c1) \ | 3533 | /* Store a composed char or a component char C in charbuf, and update |
| 3534 | cmp_status. */ | ||
| 3535 | |||
| 3536 | #define STORE_COMPOSITION_CHAR(c) \ | ||
| 3191 | do { \ | 3537 | do { \ |
| 3192 | (c1) -= 32; \ | 3538 | *charbuf++ = (c); \ |
| 3193 | if (c1 < 81) /* old format (before ver.21) */ \ | 3539 | cmp_status->length++; \ |
| 3194 | { \ | 3540 | if (cmp_status->state == COMPOSING_CHAR) \ |
| 3195 | int gref = (c1) / 9; \ | 3541 | cmp_status->nchars++; \ |
| 3196 | int nref = (c1) % 9; \ | ||
| 3197 | if (gref == 4) gref = 10; \ | ||
| 3198 | if (nref == 4) nref = 10; \ | ||
| 3199 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ | ||
| 3200 | } \ | ||
| 3201 | else if (c1 < 93) /* new format (after ver.21) */ \ | ||
| 3202 | { \ | ||
| 3203 | ONE_MORE_BYTE (c2); \ | ||
| 3204 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ | ||
| 3205 | } \ | ||
| 3206 | else \ | 3542 | else \ |
| 3207 | c1 = 0; \ | 3543 | cmp_status->ncomps++; \ |
| 3544 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | ||
| 3545 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | ||
| 3546 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | ||
| 3547 | cmp_status->state++; \ | ||
| 3208 | } while (0) | 3548 | } while (0) |
| 3209 | 3549 | ||
| 3210 | 3550 | ||
| @@ -3219,7 +3559,7 @@ decode_coding_iso_2022 (coding) | |||
| 3219 | const unsigned char *src_base; | 3559 | const unsigned char *src_base; |
| 3220 | int *charbuf = coding->charbuf + coding->charbuf_used; | 3560 | int *charbuf = coding->charbuf + coding->charbuf_used; |
| 3221 | int *charbuf_end | 3561 | int *charbuf_end |
| 3222 | = coding->charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; | 3562 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; |
| 3223 | int consumed_chars = 0, consumed_chars_base; | 3563 | int consumed_chars = 0, consumed_chars_base; |
| 3224 | int multibytep = coding->src_multibyte; | 3564 | int multibytep = coding->src_multibyte; |
| 3225 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ | 3565 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
| @@ -3228,18 +3568,7 @@ decode_coding_iso_2022 (coding) | |||
| 3228 | int charset_id_2, charset_id_3; | 3568 | int charset_id_2, charset_id_3; |
| 3229 | struct charset *charset; | 3569 | struct charset *charset; |
| 3230 | int c; | 3570 | int c; |
| 3231 | /* For handling composition sequence. */ | 3571 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
| 3232 | #define COMPOSING_NO 0 | ||
| 3233 | #define COMPOSING_CHAR 1 | ||
| 3234 | #define COMPOSING_RULE 2 | ||
| 3235 | #define COMPOSING_COMPONENT_CHAR 3 | ||
| 3236 | #define COMPOSING_COMPONENT_RULE 4 | ||
| 3237 | |||
| 3238 | int composition_state = COMPOSING_NO; | ||
| 3239 | enum composition_method method; | ||
| 3240 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | ||
| 3241 | int component_idx; | ||
| 3242 | int component_len; | ||
| 3243 | Lisp_Object attrs, charset_list; | 3572 | Lisp_Object attrs, charset_list; |
| 3244 | int char_offset = coding->produced_char; | 3573 | int char_offset = coding->produced_char; |
| 3245 | int last_offset = char_offset; | 3574 | int last_offset = char_offset; |
| @@ -3247,6 +3576,7 @@ decode_coding_iso_2022 (coding) | |||
| 3247 | int eol_crlf = | 3576 | int eol_crlf = |
| 3248 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | 3577 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); |
| 3249 | int byte_after_cr = -1; | 3578 | int byte_after_cr = -1; |
| 3579 | int i; | ||
| 3250 | 3580 | ||
| 3251 | CODING_GET_INFO (coding, attrs, charset_list); | 3581 | CODING_GET_INFO (coding, attrs, charset_list); |
| 3252 | setup_iso_safe_charsets (attrs); | 3582 | setup_iso_safe_charsets (attrs); |
| @@ -3254,6 +3584,13 @@ decode_coding_iso_2022 (coding) | |||
| 3254 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | 3584 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
| 3255 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); | 3585 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
| 3256 | 3586 | ||
| 3587 | if (cmp_status->state != COMPOSING_NO) | ||
| 3588 | { | ||
| 3589 | for (i = 0; i < cmp_status->length; i++) | ||
| 3590 | *charbuf++ = cmp_status->carryover[i]; | ||
| 3591 | coding->annotated = 1; | ||
| 3592 | } | ||
| 3593 | |||
| 3257 | while (1) | 3594 | while (1) |
| 3258 | { | 3595 | { |
| 3259 | int c1, c2; | 3596 | int c1, c2; |
| @@ -3275,26 +3612,58 @@ decode_coding_iso_2022 (coding) | |||
| 3275 | if (c1 < 0) | 3612 | if (c1 < 0) |
| 3276 | goto invalid_code; | 3613 | goto invalid_code; |
| 3277 | 3614 | ||
| 3278 | /* We produce at most one character. */ | 3615 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
| 3279 | switch (iso_code_class [c1]) | ||
| 3280 | { | 3616 | { |
| 3281 | case ISO_0x20_or_0x7F: | 3617 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
| 3282 | if (composition_state != COMPOSING_NO) | 3618 | char_offset++; |
| 3619 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | ||
| 3620 | continue; | ||
| 3621 | } | ||
| 3622 | |||
| 3623 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | ||
| 3624 | { | ||
| 3625 | if (c1 == ISO_CODE_ESC) | ||
| 3283 | { | 3626 | { |
| 3284 | if (composition_state == COMPOSING_RULE | 3627 | if (src + 1 >= src_end) |
| 3285 | || composition_state == COMPOSING_COMPONENT_RULE) | 3628 | goto no_more_source; |
| 3629 | *charbuf++ = ISO_CODE_ESC; | ||
| 3630 | char_offset++; | ||
| 3631 | if (src[0] == '%' && src[1] == '@') | ||
| 3286 | { | 3632 | { |
| 3287 | if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1) | 3633 | src += 2; |
| 3288 | { | 3634 | consumed_chars += 2; |
| 3289 | DECODE_COMPOSITION_RULE (c1); | 3635 | char_offset += 2; |
| 3290 | components[component_idx++] = c1; | 3636 | /* We are sure charbuf can contain two more chars. */ |
| 3291 | composition_state--; | 3637 | *charbuf++ = '%'; |
| 3292 | continue; | 3638 | *charbuf++ = '@'; |
| 3293 | } | 3639 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; |
| 3294 | /* Too long composition. */ | ||
| 3295 | MAYBE_FINISH_COMPOSITION (); | ||
| 3296 | } | 3640 | } |
| 3297 | } | 3641 | } |
| 3642 | else | ||
| 3643 | { | ||
| 3644 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | ||
| 3645 | char_offset++; | ||
| 3646 | } | ||
| 3647 | continue; | ||
| 3648 | } | ||
| 3649 | |||
| 3650 | if ((cmp_status->state == COMPOSING_RULE | ||
| 3651 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | ||
| 3652 | && c1 != ISO_CODE_ESC) | ||
| 3653 | { | ||
| 3654 | int rule, nbytes; | ||
| 3655 | |||
| 3656 | DECODE_COMPOSITION_RULE (rule, nbytes); | ||
| 3657 | if (rule < 0) | ||
| 3658 | goto invalid_code; | ||
| 3659 | STORE_COMPOSITION_RULE (rule); | ||
| 3660 | continue; | ||
| 3661 | } | ||
| 3662 | |||
| 3663 | /* We produce at most one character. */ | ||
| 3664 | switch (iso_code_class [c1]) | ||
| 3665 | { | ||
| 3666 | case ISO_0x20_or_0x7F: | ||
| 3298 | if (charset_id_0 < 0 | 3667 | if (charset_id_0 < 0 |
| 3299 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | 3668 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) |
| 3300 | /* This is SPACE or DEL. */ | 3669 | /* This is SPACE or DEL. */ |
| @@ -3304,21 +3673,6 @@ decode_coding_iso_2022 (coding) | |||
| 3304 | break; | 3673 | break; |
| 3305 | 3674 | ||
| 3306 | case ISO_graphic_plane_0: | 3675 | case ISO_graphic_plane_0: |
| 3307 | if (composition_state != COMPOSING_NO) | ||
| 3308 | { | ||
| 3309 | if (composition_state == COMPOSING_RULE | ||
| 3310 | || composition_state == COMPOSING_COMPONENT_RULE) | ||
| 3311 | { | ||
| 3312 | if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1) | ||
| 3313 | { | ||
| 3314 | DECODE_COMPOSITION_RULE (c1); | ||
| 3315 | components[component_idx++] = c1; | ||
| 3316 | composition_state--; | ||
| 3317 | continue; | ||
| 3318 | } | ||
| 3319 | MAYBE_FINISH_COMPOSITION (); | ||
| 3320 | } | ||
| 3321 | } | ||
| 3322 | if (charset_id_0 < 0) | 3676 | if (charset_id_0 < 0) |
| 3323 | charset = CHARSET_FROM_ID (charset_ascii); | 3677 | charset = CHARSET_FROM_ID (charset_ascii); |
| 3324 | else | 3678 | else |
| @@ -3346,7 +3700,6 @@ decode_coding_iso_2022 (coding) | |||
| 3346 | break; | 3700 | break; |
| 3347 | 3701 | ||
| 3348 | case ISO_control_1: | 3702 | case ISO_control_1: |
| 3349 | MAYBE_FINISH_COMPOSITION (); | ||
| 3350 | goto invalid_code; | 3703 | goto invalid_code; |
| 3351 | 3704 | ||
| 3352 | case ISO_shift_out: | 3705 | case ISO_shift_out: |
| @@ -3484,11 +3837,17 @@ decode_coding_iso_2022 (coding) | |||
| 3484 | case '0': case '2': case '3': case '4': /* start composition */ | 3837 | case '0': case '2': case '3': case '4': /* start composition */ |
| 3485 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) | 3838 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
| 3486 | goto invalid_code; | 3839 | goto invalid_code; |
| 3840 | if (last_id != charset_ascii) | ||
| 3841 | { | ||
| 3842 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | ||
| 3843 | last_id = charset_ascii; | ||
| 3844 | last_offset = char_offset; | ||
| 3845 | } | ||
| 3487 | DECODE_COMPOSITION_START (c1); | 3846 | DECODE_COMPOSITION_START (c1); |
| 3488 | continue; | 3847 | continue; |
| 3489 | 3848 | ||
| 3490 | case '1': /* end composition */ | 3849 | case '1': /* end composition */ |
| 3491 | if (composition_state == COMPOSING_NO) | 3850 | if (cmp_status->state == COMPOSING_NO) |
| 3492 | goto invalid_code; | 3851 | goto invalid_code; |
| 3493 | DECODE_COMPOSITION_END (); | 3852 | DECODE_COMPOSITION_END (); |
| 3494 | continue; | 3853 | continue; |
| @@ -3539,10 +3898,16 @@ decode_coding_iso_2022 (coding) | |||
| 3539 | int size; | 3898 | int size; |
| 3540 | 3899 | ||
| 3541 | ONE_MORE_BYTE (dim); | 3900 | ONE_MORE_BYTE (dim); |
| 3901 | if (dim < 0 || dim > 4) | ||
| 3902 | goto invalid_code; | ||
| 3542 | ONE_MORE_BYTE (M); | 3903 | ONE_MORE_BYTE (M); |
| 3904 | if (M < 128) | ||
| 3905 | goto invalid_code; | ||
| 3543 | ONE_MORE_BYTE (L); | 3906 | ONE_MORE_BYTE (L); |
| 3907 | if (L < 128) | ||
| 3908 | goto invalid_code; | ||
| 3544 | size = ((M - 128) * 128) + (L - 128); | 3909 | size = ((M - 128) * 128) + (L - 128); |
| 3545 | if (charbuf + 8 + size > charbuf_end) | 3910 | if (charbuf + 6 > charbuf_end) |
| 3546 | goto break_loop; | 3911 | goto break_loop; |
| 3547 | *charbuf++ = ISO_CODE_ESC; | 3912 | *charbuf++ = ISO_CODE_ESC; |
| 3548 | *charbuf++ = '%'; | 3913 | *charbuf++ = '%'; |
| @@ -3550,11 +3915,7 @@ decode_coding_iso_2022 (coding) | |||
| 3550 | *charbuf++ = dim; | 3915 | *charbuf++ = dim; |
| 3551 | *charbuf++ = BYTE8_TO_CHAR (M); | 3916 | *charbuf++ = BYTE8_TO_CHAR (M); |
| 3552 | *charbuf++ = BYTE8_TO_CHAR (L); | 3917 | *charbuf++ = BYTE8_TO_CHAR (L); |
| 3553 | while (size-- > 0) | 3918 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
| 3554 | { | ||
| 3555 | ONE_MORE_BYTE (c1); | ||
| 3556 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | ||
| 3557 | } | ||
| 3558 | } | 3919 | } |
| 3559 | else if (c1 == 'G') | 3920 | else if (c1 == 'G') |
| 3560 | { | 3921 | { |
| @@ -3562,32 +3923,12 @@ decode_coding_iso_2022 (coding) | |||
| 3562 | ESC % G --UTF-8-BYTES-- ESC % @ | 3923 | ESC % G --UTF-8-BYTES-- ESC % @ |
| 3563 | We keep these bytes as is for the moment. | 3924 | We keep these bytes as is for the moment. |
| 3564 | They may be decoded by post-read-conversion. */ | 3925 | They may be decoded by post-read-conversion. */ |
| 3565 | int *p = charbuf; | 3926 | if (charbuf + 3 > charbuf_end) |
| 3566 | |||
| 3567 | if (p + 6 > charbuf_end) | ||
| 3568 | goto break_loop; | 3927 | goto break_loop; |
| 3569 | *p++ = ISO_CODE_ESC; | 3928 | *charbuf++ = ISO_CODE_ESC; |
| 3570 | *p++ = '%'; | 3929 | *charbuf++ = '%'; |
| 3571 | *p++ = 'G'; | 3930 | *charbuf++ = 'G'; |
| 3572 | while (p < charbuf_end) | 3931 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; |
| 3573 | { | ||
| 3574 | ONE_MORE_BYTE (c1); | ||
| 3575 | if (c1 == ISO_CODE_ESC | ||
| 3576 | && src + 1 < src_end | ||
| 3577 | && src[0] == '%' | ||
| 3578 | && src[1] == '@') | ||
| 3579 | { | ||
| 3580 | src += 2; | ||
| 3581 | break; | ||
| 3582 | } | ||
| 3583 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | ||
| 3584 | } | ||
| 3585 | if (p + 3 > charbuf_end) | ||
| 3586 | goto break_loop; | ||
| 3587 | *p++ = ISO_CODE_ESC; | ||
| 3588 | *p++ = '%'; | ||
| 3589 | *p++ = '@'; | ||
| 3590 | charbuf = p; | ||
| 3591 | } | 3932 | } |
| 3592 | else | 3933 | else |
| 3593 | goto invalid_code; | 3934 | goto invalid_code; |
| @@ -3625,7 +3966,8 @@ decode_coding_iso_2022 (coding) | |||
| 3625 | } | 3966 | } |
| 3626 | } | 3967 | } |
| 3627 | 3968 | ||
| 3628 | if (charset->id != charset_ascii | 3969 | if (cmp_status->state == COMPOSING_NO |
| 3970 | && charset->id != charset_ascii | ||
| 3629 | && last_id != charset->id) | 3971 | && last_id != charset->id) |
| 3630 | { | 3972 | { |
| 3631 | if (last_id != charset_ascii) | 3973 | if (last_id != charset_ascii) |
| @@ -3667,28 +4009,23 @@ decode_coding_iso_2022 (coding) | |||
| 3667 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | 4009 | *charbuf++ = BYTE8_TO_CHAR (*src_base); |
| 3668 | } | 4010 | } |
| 3669 | } | 4011 | } |
| 3670 | else if (composition_state == COMPOSING_NO) | 4012 | else if (cmp_status->state == COMPOSING_NO) |
| 3671 | { | 4013 | { |
| 3672 | *charbuf++ = c; | 4014 | *charbuf++ = c; |
| 3673 | char_offset++; | 4015 | char_offset++; |
| 3674 | } | 4016 | } |
| 3675 | else | 4017 | else if ((cmp_status->state == COMPOSING_CHAR |
| 4018 | ? cmp_status->nchars | ||
| 4019 | : cmp_status->ncomps) | ||
| 4020 | >= MAX_COMPOSITION_COMPONENTS) | ||
| 3676 | { | 4021 | { |
| 3677 | if (component_idx < MAX_COMPOSITION_COMPONENTS * 2 + 1) | 4022 | /* Too long composition. */ |
| 3678 | { | 4023 | MAYBE_FINISH_COMPOSITION (); |
| 3679 | components[component_idx++] = c; | 4024 | *charbuf++ = c; |
| 3680 | if (method == COMPOSITION_WITH_RULE | 4025 | char_offset++; |
| 3681 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | ||
| 3682 | && composition_state == COMPOSING_COMPONENT_CHAR)) | ||
| 3683 | composition_state++; | ||
| 3684 | } | ||
| 3685 | else | ||
| 3686 | { | ||
| 3687 | MAYBE_FINISH_COMPOSITION (); | ||
| 3688 | *charbuf++ = c; | ||
| 3689 | char_offset++; | ||
| 3690 | } | ||
| 3691 | } | 4026 | } |
| 4027 | else | ||
| 4028 | STORE_COMPOSITION_CHAR (c); | ||
| 3692 | continue; | 4029 | continue; |
| 3693 | 4030 | ||
| 3694 | invalid_code: | 4031 | invalid_code: |
| @@ -3706,7 +4043,18 @@ decode_coding_iso_2022 (coding) | |||
| 3706 | } | 4043 | } |
| 3707 | 4044 | ||
| 3708 | no_more_source: | 4045 | no_more_source: |
| 3709 | if (last_id != charset_ascii) | 4046 | if (cmp_status->state != COMPOSING_NO) |
| 4047 | { | ||
| 4048 | if (coding->mode & CODING_MODE_LAST_BLOCK) | ||
| 4049 | MAYBE_FINISH_COMPOSITION (); | ||
| 4050 | else | ||
| 4051 | { | ||
| 4052 | charbuf -= cmp_status->length; | ||
| 4053 | for (i = 0; i < cmp_status->length; i++) | ||
| 4054 | cmp_status->carryover[i] = charbuf[i]; | ||
| 4055 | } | ||
| 4056 | } | ||
| 4057 | else if (last_id != charset_ascii) | ||
| 3710 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); | 4058 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
| 3711 | coding->consumed_char += consumed_chars_base; | 4059 | coding->consumed_char += consumed_chars_base; |
| 3712 | coding->consumed = src_base - coding->source; | 4060 | coding->consumed = src_base - coding->source; |
| @@ -5476,6 +5824,10 @@ setup_coding_system (coding_system, coding) | |||
| 5476 | coding->safe_charsets = SDATA (val); | 5824 | coding->safe_charsets = SDATA (val); |
| 5477 | } | 5825 | } |
| 5478 | CODING_ISO_FLAGS (coding) = flags; | 5826 | CODING_ISO_FLAGS (coding) = flags; |
| 5827 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; | ||
| 5828 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | ||
| 5829 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | ||
| 5830 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | ||
| 5479 | } | 5831 | } |
| 5480 | else if (EQ (coding_type, Qcharset)) | 5832 | else if (EQ (coding_type, Qcharset)) |
| 5481 | { | 5833 | { |
| @@ -5533,6 +5885,7 @@ setup_coding_system (coding_system, coding) | |||
| 5533 | coding->encoder = encode_coding_emacs_mule; | 5885 | coding->encoder = encode_coding_emacs_mule; |
| 5534 | coding->common_flags | 5886 | coding->common_flags |
| 5535 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | 5887 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
| 5888 | coding->spec.emacs_mule.full_support = 1; | ||
| 5536 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | 5889 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) |
| 5537 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | 5890 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) |
| 5538 | { | 5891 | { |
| @@ -5550,7 +5903,10 @@ setup_coding_system (coding_system, coding) | |||
| 5550 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); | 5903 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
| 5551 | coding->max_charset_id = max_charset_id; | 5904 | coding->max_charset_id = max_charset_id; |
| 5552 | coding->safe_charsets = SDATA (safe_charsets); | 5905 | coding->safe_charsets = SDATA (safe_charsets); |
| 5906 | coding->spec.emacs_mule.full_support = 1; | ||
| 5553 | } | 5907 | } |
| 5908 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; | ||
| 5909 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | ||
| 5554 | } | 5910 | } |
| 5555 | else if (EQ (coding_type, Qshift_jis)) | 5911 | else if (EQ (coding_type, Qshift_jis)) |
| 5556 | { | 5912 | { |
| @@ -6338,51 +6694,39 @@ get_translation_table (attrs, encodep, max_lookup) | |||
| 6338 | } while (0) | 6694 | } while (0) |
| 6339 | 6695 | ||
| 6340 | 6696 | ||
| 6697 | /* Return a translation of character(s) at BUF according to TRANS. | ||
| 6698 | TRANS is TO-CHAR or ((FROM . TO) ...) where | ||
| 6699 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | ||
| 6700 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | ||
| 6701 | translation is found, and Qnil if not found.. | ||
| 6702 | If BUF is too short to lookup characters in FROM, return Qt. */ | ||
| 6703 | |||
| 6341 | static Lisp_Object | 6704 | static Lisp_Object |
| 6342 | get_translation (val, buf, buf_end, last_block, from_nchars, to_nchars) | 6705 | get_translation (trans, buf, buf_end) |
| 6343 | Lisp_Object val; | 6706 | Lisp_Object trans; |
| 6344 | int *buf, *buf_end; | 6707 | int *buf, *buf_end; |
| 6345 | int last_block; | ||
| 6346 | int *from_nchars, *to_nchars; | ||
| 6347 | { | 6708 | { |
| 6348 | /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or | 6709 | |
| 6349 | [TO-CHAR ...]. */ | 6710 | if (INTEGERP (trans)) |
| 6350 | if (CONSP (val)) | 6711 | return trans; |
| 6712 | for (; CONSP (trans); trans = XCDR (trans)) | ||
| 6351 | { | 6713 | { |
| 6352 | Lisp_Object from, tail; | 6714 | Lisp_Object val = XCAR (trans); |
| 6353 | int i, len; | 6715 | Lisp_Object from = XCAR (val); |
| 6716 | int len = ASIZE (from); | ||
| 6717 | int i; | ||
| 6354 | 6718 | ||
| 6355 | for (tail = val; CONSP (tail); tail = XCDR (tail)) | 6719 | for (i = 0; i < len; i++) |
| 6356 | { | 6720 | { |
| 6357 | val = XCAR (tail); | 6721 | if (buf + i == buf_end) |
| 6358 | from = XCAR (val); | 6722 | return Qt; |
| 6359 | len = ASIZE (from); | 6723 | if (XINT (AREF (from, i)) != buf[i]) |
| 6360 | for (i = 0; i < len; i++) | 6724 | break; |
| 6361 | { | ||
| 6362 | if (buf + i == buf_end) | ||
| 6363 | { | ||
| 6364 | if (! last_block) | ||
| 6365 | return Qt; | ||
| 6366 | break; | ||
| 6367 | } | ||
| 6368 | if (XINT (AREF (from, i)) != buf[i]) | ||
| 6369 | break; | ||
| 6370 | } | ||
| 6371 | if (i == len) | ||
| 6372 | { | ||
| 6373 | val = XCDR (val); | ||
| 6374 | *from_nchars = len; | ||
| 6375 | break; | ||
| 6376 | } | ||
| 6377 | } | 6725 | } |
| 6378 | if (! CONSP (tail)) | 6726 | if (i == len) |
| 6379 | return Qnil; | 6727 | return val; |
| 6380 | } | 6728 | } |
| 6381 | if (VECTORP (val)) | 6729 | return Qnil; |
| 6382 | *buf = XINT (AREF (val, 0)), *to_nchars = ASIZE (val); | ||
| 6383 | else | ||
| 6384 | *buf = XINT (val); | ||
| 6385 | return val; | ||
| 6386 | } | 6730 | } |
| 6387 | 6731 | ||
| 6388 | 6732 | ||
| @@ -6422,11 +6766,23 @@ produce_chars (coding, translation_table, last_block) | |||
| 6422 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); | 6766 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
| 6423 | if (! NILP (trans)) | 6767 | if (! NILP (trans)) |
| 6424 | { | 6768 | { |
| 6425 | trans = get_translation (trans, buf, buf_end, last_block, | 6769 | trans = get_translation (trans, buf, buf_end); |
| 6426 | &from_nchars, &to_nchars); | 6770 | if (INTEGERP (trans)) |
| 6427 | if (EQ (trans, Qt)) | 6771 | c = XINT (trans); |
| 6772 | else if (CONSP (trans)) | ||
| 6773 | { | ||
| 6774 | from_nchars = ASIZE (XCAR (trans)); | ||
| 6775 | trans = XCDR (trans); | ||
| 6776 | if (INTEGERP (trans)) | ||
| 6777 | c = XINT (trans); | ||
| 6778 | else | ||
| 6779 | { | ||
| 6780 | to_nchars = ASIZE (trans); | ||
| 6781 | c = XINT (AREF (trans, 0)); | ||
| 6782 | } | ||
| 6783 | } | ||
| 6784 | else if (EQ (trans, Qt) && ! last_block) | ||
| 6428 | break; | 6785 | break; |
| 6429 | c = *buf; | ||
| 6430 | } | 6786 | } |
| 6431 | 6787 | ||
| 6432 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | 6788 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) |
| @@ -6438,7 +6794,8 @@ produce_chars (coding, translation_table, last_block) | |||
| 6438 | if (EQ (coding->src_object, coding->dst_object)) | 6794 | if (EQ (coding->src_object, coding->dst_object)) |
| 6439 | { | 6795 | { |
| 6440 | coding_set_source (coding); | 6796 | coding_set_source (coding); |
| 6441 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | 6797 | dst_end = (((unsigned char *) coding->source) |
| 6798 | + coding->consumed); | ||
| 6442 | } | 6799 | } |
| 6443 | else | 6800 | else |
| 6444 | dst_end = coding->destination + coding->dst_bytes; | 6801 | dst_end = coding->destination + coding->dst_bytes; |
| @@ -6455,9 +6812,7 @@ produce_chars (coding, translation_table, last_block) | |||
| 6455 | *dst++ = CHAR_TO_BYTE8 (c); | 6812 | *dst++ = CHAR_TO_BYTE8 (c); |
| 6456 | } | 6813 | } |
| 6457 | produced_chars += to_nchars; | 6814 | produced_chars += to_nchars; |
| 6458 | *buf++ = to_nchars; | 6815 | buf += from_nchars; |
| 6459 | while (--from_nchars > 0) | ||
| 6460 | *buf++ = 0; | ||
| 6461 | } | 6816 | } |
| 6462 | else | 6817 | else |
| 6463 | /* This is an annotation datum. (-C) is the length. */ | 6818 | /* This is an annotation datum. (-C) is the length. */ |
| @@ -6573,7 +6928,7 @@ produce_chars (coding, translation_table, last_block) | |||
| 6573 | 6928 | ||
| 6574 | /* Compose text in CODING->object according to the annotation data at | 6929 | /* Compose text in CODING->object according to the annotation data at |
| 6575 | CHARBUF. CHARBUF is an array: | 6930 | CHARBUF. CHARBUF is an array: |
| 6576 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | 6931 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
| 6577 | */ | 6932 | */ |
| 6578 | 6933 | ||
| 6579 | static INLINE void | 6934 | static INLINE void |
| @@ -6587,33 +6942,33 @@ produce_composition (coding, charbuf, pos) | |||
| 6587 | enum composition_method method; | 6942 | enum composition_method method; |
| 6588 | Lisp_Object components; | 6943 | Lisp_Object components; |
| 6589 | 6944 | ||
| 6590 | len = -charbuf[0]; | 6945 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
| 6591 | to = pos + charbuf[2]; | 6946 | to = pos + charbuf[2]; |
| 6592 | if (to <= pos) | 6947 | method = (enum composition_method) (charbuf[4]); |
| 6593 | return; | ||
| 6594 | method = (enum composition_method) (charbuf[3]); | ||
| 6595 | 6948 | ||
| 6596 | if (method == COMPOSITION_RELATIVE) | 6949 | if (method == COMPOSITION_RELATIVE) |
| 6597 | components = Qnil; | 6950 | components = Qnil; |
| 6598 | else if (method >= COMPOSITION_WITH_RULE | 6951 | else |
| 6599 | && method <= COMPOSITION_WITH_RULE_ALTCHARS) | ||
| 6600 | { | 6952 | { |
| 6601 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; | 6953 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
| 6602 | int i; | 6954 | int i, j; |
| 6603 | 6955 | ||
| 6604 | len -= 4; | 6956 | if (method == COMPOSITION_WITH_RULE) |
| 6605 | charbuf += 4; | 6957 | len = charbuf[2] * 3 - 2; |
| 6606 | for (i = 0; i < len; i++) | 6958 | charbuf += MAX_ANNOTATION_LENGTH; |
| 6959 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | ||
| 6960 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | ||
| 6607 | { | 6961 | { |
| 6608 | args[i] = make_number (charbuf[i]); | 6962 | if (charbuf[i] >= 0) |
| 6609 | if (charbuf[i] < 0) | 6963 | args[j] = make_number (charbuf[i]); |
| 6610 | return; | 6964 | else |
| 6965 | { | ||
| 6966 | i++; | ||
| 6967 | args[j] = make_number (charbuf[i] % 0x100); | ||
| 6968 | } | ||
| 6611 | } | 6969 | } |
| 6612 | components = (method == COMPOSITION_WITH_ALTCHARS | 6970 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
| 6613 | ? Fstring (len, args) : Fvector (len, args)); | ||
| 6614 | } | 6971 | } |
| 6615 | else | ||
| 6616 | return; | ||
| 6617 | compose_text (pos, to, components, Qnil, coding->dst_object); | 6972 | compose_text (pos, to, components, Qnil, coding->dst_object); |
| 6618 | } | 6973 | } |
| 6619 | 6974 | ||
| @@ -6675,21 +7030,21 @@ produce_annotation (coding, pos) | |||
| 6675 | while (charbuf < charbuf_end) | 7030 | while (charbuf < charbuf_end) |
| 6676 | { | 7031 | { |
| 6677 | if (*charbuf >= 0) | 7032 | if (*charbuf >= 0) |
| 6678 | pos += *charbuf++; | 7033 | pos++, charbuf++; |
| 6679 | else | 7034 | else |
| 6680 | { | 7035 | { |
| 6681 | int len = -*charbuf; | 7036 | int len = -*charbuf; |
| 6682 | switch (charbuf[1]) | 7037 | |
| 6683 | { | 7038 | if (len > 2) |
| 6684 | case CODING_ANNOTATE_COMPOSITION_MASK: | 7039 | switch (charbuf[1]) |
| 6685 | produce_composition (coding, charbuf, pos); | 7040 | { |
| 6686 | break; | 7041 | case CODING_ANNOTATE_COMPOSITION_MASK: |
| 6687 | case CODING_ANNOTATE_CHARSET_MASK: | 7042 | produce_composition (coding, charbuf, pos); |
| 6688 | produce_charset (coding, charbuf, pos); | 7043 | break; |
| 6689 | break; | 7044 | case CODING_ANNOTATE_CHARSET_MASK: |
| 6690 | default: | 7045 | produce_charset (coding, charbuf, pos); |
| 6691 | abort (); | 7046 | break; |
| 6692 | } | 7047 | } |
| 6693 | charbuf += len; | 7048 | charbuf += len; |
| 6694 | } | 7049 | } |
| 6695 | } | 7050 | } |
| @@ -6875,7 +7230,7 @@ handle_composition_annotation (pos, limit, coding, buf, stop) | |||
| 6875 | enum composition_method method = COMPOSITION_METHOD (prop); | 7230 | enum composition_method method = COMPOSITION_METHOD (prop); |
| 6876 | int nchars = COMPOSITION_LENGTH (prop); | 7231 | int nchars = COMPOSITION_LENGTH (prop); |
| 6877 | 7232 | ||
| 6878 | ADD_COMPOSITION_DATA (buf, nchars, method); | 7233 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
| 6879 | if (method != COMPOSITION_RELATIVE) | 7234 | if (method != COMPOSITION_RELATIVE) |
| 6880 | { | 7235 | { |
| 6881 | Lisp_Object components; | 7236 | Lisp_Object components; |
| @@ -7062,12 +7417,26 @@ consume_chars (coding, translation_table, max_lookup) | |||
| 7062 | for (i = 1; i < max_lookup && p < src_end; i++) | 7417 | for (i = 1; i < max_lookup && p < src_end; i++) |
| 7063 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | 7418 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); |
| 7064 | lookup_buf_end = lookup_buf + i; | 7419 | lookup_buf_end = lookup_buf + i; |
| 7065 | trans = get_translation (trans, lookup_buf, lookup_buf_end, 1, | 7420 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
| 7066 | &from_nchars, &to_nchars); | 7421 | if (INTEGERP (trans)) |
| 7067 | if (EQ (trans, Qt) | 7422 | c = XINT (trans); |
| 7068 | || buf + to_nchars > buf_end) | 7423 | else if (CONSP (trans)) |
| 7424 | { | ||
| 7425 | from_nchars = ASIZE (XCAR (trans)); | ||
| 7426 | trans = XCDR (trans); | ||
| 7427 | if (INTEGERP (trans)) | ||
| 7428 | c = XINT (trans); | ||
| 7429 | else | ||
| 7430 | { | ||
| 7431 | to_nchars = ASIZE (trans); | ||
| 7432 | if (buf + to_nchars > buf_end) | ||
| 7433 | break; | ||
| 7434 | c = XINT (AREF (trans, 0)); | ||
| 7435 | } | ||
| 7436 | } | ||
| 7437 | else | ||
| 7069 | break; | 7438 | break; |
| 7070 | *buf++ = *lookup_buf; | 7439 | *buf++ = c; |
| 7071 | for (i = 1; i < to_nchars; i++) | 7440 | for (i = 1; i < to_nchars; i++) |
| 7072 | *buf++ = XINT (AREF (trans, i)); | 7441 | *buf++ = XINT (AREF (trans, i)); |
| 7073 | for (i = 1; i < from_nchars; i++, pos++) | 7442 | for (i = 1; i < from_nchars; i++, pos++) |