--- org/geniconvtbl.4 Mon Apr 26 14:54:27 2010 +++ geniconvtbl.4 Thu Apr 29 13:07:32 2010 @@ -13,7 +13,7 @@ The geniconvtbl utility accepts the code conversion defini- tion file(s) and writes code conversion binary table file(s) that can be used in iconv(1) and iconv(3C) to support user- - defined code conversions. See iconv(1) and iconv(3C)for more + defined code conversions. See iconv(1) and iconv(3C) for more | detail on the iconv code conversion and geniconvtbl(1) for more detail on the utility. @@ -52,17 +52,27 @@ The following keywords are reserved: - automatic between binary - break condition default - dense direction discard - else error escapeseq - false if index - init input inputsize - map maptype no_change_copy - non_identical_conversion non_identical_count_increment operation | - output output_byte_length outputsize | - printchr printhd printint | - reset return true | + automatic between | + binary break | + condition default | + dense direction | + disable discard | + else enable | + error escapeseq | + false if | + illegal_discard illegal_replace_hex | + illegal_restore_hex index | + init input | + inputsize map | + maptype no_change_copy | + non_identical_conversion non_identical_count_increment | + non_identical_discard non_identical_replace_hex | + non_identical_restore_hex non_identical_transliterate | + operation output | + output_byte_length outputsize | + printchr printhd | + printint reset | + return true | Additionally, the following symbols are also reserved as tokens: @@ -485,6 +495,83 @@ The control operation expression can be any one of the fol- lowing expressions: + // When specified, the support for code conversion behavior | + // modification with "//ILLEGAL_DISCARD" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable illegal_discard; | + | + // When specified, the support for code conversion behavior | + // modification with "//ILLEGAL_REPLACE_HEX" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable illegal_replace_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//ILLEGAL_RESTORE_HEX" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable illegal_restore_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_DISCARD" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable non_identical_discard; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_REPLACE_HEX" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable non_identical_replace_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_RESTORE_HEX" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable non_identical_restore_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_TRANSLITERATE" is disabled and | + // not supported by the current conversion. By default, | + // it is enabled: | + disable non_identical_transliterate; | + | + // When specified, the support for code conversion behavior | + // modification with "//ILLEGAL_DISCARD" is enabled and | + // supported by the current conversion: | + enable illegal_discard; | + | + // When specified, the support for code conversion behavior | + // modification with "//ILLEGAL_REPLACE_HEX" is enabled and | + // supported by the current conversion: | + enable illegal_replace_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//ILLEGAL_RESTORE_HEX" is enabled and | + // supported by the current conversion: | + enable illegal_restore_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_DISCARD" is enabled and | + // supported by the current conversion: | + enable non_identical_discard; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_REPLACE_HEX" is enabled and | + // supported by the current conversion: | + enable non_identical_replace_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_RESTORE_HEX" is enabled and | + // supported by the current conversion: | + enable non_identical_restore_hex; | + | + // When specified, the support for code conversion behavior | + // modification with "//NON_IDENTICAL_TRANSLITERATE" is enabled and | + // supported by the current conversion: | + enable non_identical_transliterate; | + | // Return (size_t)-1 as the return value with an EINVAL errno: error; @@ -538,6 +625,21 @@ // 10 input buffer bytes: map Map_ISO8859_1_to_US_ASCII 10; + When illegal_discard, illegal_replace_hex, illegal_restore_hex, | + non_identical_discard, non_identical_replace_hex, | + non_identical_restore_hex, non_identical_transliterate, or any | + combination of them are enabled and one or more of corresponding | + valid conversion behavior modifications are requested, the current | + code conversion transparently and automatically does necessary | + conversions on non-identical characters, illegal characters, or both | + as specified in iconv_open(3C). In so doing, if requested and to | + properly transliterate non-identical characters, at least a mapping | + table for non_identical_transliterate is needed which is described at | + the map element description at below. Alternatively, instead of | + the non_identical_transliterate mapping table, an algorithmic mapping | + can also be supplied. For more detail on the code conversion | + behavior modification requests, refer to iconv_open(3C). | + | In case of init and reset operations, if there is no pre- defined init and/or reset operations in the iconv code conversions, only system-defined internal init and reset @@ -577,6 +679,21 @@ } + If the name of the map element is non_identical_transliterate, | + it defines the mapping table that is solely used for non-identical | + character conversion mappings if and only if non_identical_transliterate | + conversion behavior modification is enabled and supported, requested | + with iconv_open() or iconvctl() call, and there are one or more map | + pairs with non_identical_conversion defined in other map elements: | + | + map non_identical_transliterate { | + | + // one or more map pairs of transliterations for | + // non-identical characters here | + : | + : | + } | + | Each map element also can have one or two comma-separated map attribute elements like the following examples: @@ -661,6 +778,12 @@ // the code value 0x20 to an output character value 0x21: 0x20 0x21 + // Single mapping with non-identical character conversion indication. | + // This maps an input character denoted by the code value 0x20 to | + // an output character value 0x3f. Each of such mappings also | + // increases the non-identical character conversion count by one: | + 0x20 0x3f non_identical_conversion | + | // Multiple mapping. This maps 128 input characters to 128 // output characters. In this mapping, 0x0 maps to 0x10, 0x1 maps // to 0x11, 0x2 maps to 0x12, ..., and, 0x7f maps to 0x8f: @@ -669,8 +792,9 @@ // Multiple mapping with non-identical character conversion | // indication. This maps 128 input characters to 128 output | // characters. In this mapping, 0x0 maps to 0x10, 0x1 maps to 0x11, | - // 0x2 maps to 0x12, ..., and, 0x7f maps to 0x8f. Each mapping also | - // increases the non-identical character conversion count by one: | + // 0x2 maps to 0x12, ..., and, 0x7f maps to 0x8f. Each of such | + // mappings also increases the non-identical character conversion | + // count by one: | 0x0...0x7f 0x10 non_identical_conversion | | // Default mapping. If specified, every undefined input character @@ -682,8 +806,8 @@ // indication. If specified, every undefined input character in | // this mapping will be converted to a specified character (in | // the following case, a character with the code value of 0x3f). | - // Each mapping also increases the non-identical character conversion | - // count by one: | + // Each of such mappings also increases the non-identical character | + // conversion count by one: | default 0x3f non_identical_conversion | | // Default mapping. If specified, every undefined input character @@ -693,9 +817,9 @@ // Default mapping with direct copying and with non-identical | // character conversion indication. If specified, every undefined | - // input character in this mapping will not be converted but | - // directly copied to the output buffer. | - // Each mapping will also increase the non-identical character | + // input character in this mapping will be directly copied to | + // the output buffer without any change in byte values. Each of such | + // mappings will also increase the non-identical character | // conversion count by one: | default no_change_copy non_identical_conversion | | @@ -787,12 +911,16 @@ escseq : HEXADECIMAL ; - map : 'map' NAME '{' map_list '}' + map : 'map' map_name '{' map_list '}' | | 'map' '{' map_list '}' - | 'map' NAME map_attribute '{' map_list '}' + | 'map' map_name map_attribute '{' map_list '}' | | 'map' map_attribute '{' map_list '}' ; + map_name: NAME | + | 'non_identical_transliterate' | + ; | + | map_attribute : map_type ',' 'output_byte_length' '=' DECIMAL | map_type @@ -842,9 +970,11 @@ op_unit : ';' | expr ';' + | 'enable' enable_disable_options ';' | | 'error' ';' | 'error' expr ';' | 'discard' ';' + | 'disable' enable_disable_options ';' | | 'discard' expr ';' | 'non_identical_count_increment' ';' | | 'output' '=' expr ';' @@ -861,6 +991,16 @@ | 'printint' expr ';' ; + enable_disable_options | + : 'illegal_discard' | + | 'illegal_replace_hex' | + | 'illegal_restore_hex' | + | 'non_identical_discard' | + | 'non_identical_replace_hex' | + | 'non_identical_restore_hex' | + | 'non_identical_transliterate' | + ; | + | op_if_else : 'if' '(' expr ')' '{' op_list '}' | 'if' '(' expr ')' '{' op_list '}' 'else' op_if_else @@ -1026,6 +1166,47 @@ }; }; } + | + Example 3 Code conversion from ISO8859-1 to ISO646 with transliterations | + | + ISO8859-1%ISO646 { | + // A possible set of loose and minimal transliterations. | + map non_identical_transliterate { | + 0xaa 0x61 // a | + 0xb2 0x32 // 2 | + 0xb3 0x33 // 3 | + 0xb9 0x31 // 1 | + 0xba 0x6f // o | + 0xbc 0x312f34 // 1/4 | + 0xbd 0x312f32 // 1/2 | + 0xbe 0x332f34 // 3/4 | + 0xc6 0x4145 // AE | + 0xe6 0x6165 // ae | + }; | + | + // The default mapping table to be used. | + map maptype = automatic { | + default 0x3f non_identical_conversion | + 0x0...0x7f 0x0 | + }; | + } | + | + Example 4 Code conversion from ISO8859-1 to ISO646 with the support for | + discarding of non-identical characters disabled | + | + ISO8859-1%ISO646 { | + // This conversion does not support the conversion behavior | + // modification request with "//NON_IDENTICAL_DISCARD". | + operation init { | + disable non_identical_discard; | + }; | + | + // The default mapping table to be used. | + map { | + default 0x3f non_identical_conversion | + 0x0...0x7f 0x0 | + }; | + } | FILES @@ -1043,7 +1224,8 @@ SEE ALSO cpp(1), geniconvtbl(1), iconv(1), iconv(3C), - iconv_close(3C), iconv_open(3C), attributes(5), environ(5) + iconv_close(3C), iconvctl(3C), iconv_open(3C), iconvstr(3C), | + attributes(5), environ(5) | NOTES