diff options
Diffstat (limited to 'libguile/chars.c')
-rw-r--r-- | libguile/chars.c | 149 |
1 files changed, 98 insertions, 51 deletions
diff --git a/libguile/chars.c b/libguile/chars.c index ca47c0d82..511ffc7c8 100644 --- a/libguile/chars.c +++ b/libguile/chars.c @@ -298,61 +298,108 @@ scm_c_downcase (unsigned int c) return c; } + -#ifdef _DCC -# define ASCII -#else -# if (('\n'=='\025') && (' '=='\100') && ('a'=='\201') && ('A'=='\301')) -# define EBCDIC -# endif /* (('\n'=='\025') && (' '=='\100') && ('a'=='\201') && ('A'=='\301')) */ -# if (('\n'=='\012') && (' '=='\040') && ('a'=='\141') && ('A'=='\101')) -# define ASCII -# endif /* (('\n'=='\012') && (' '=='\040') && ('a'=='\141') && ('A'=='\101')) */ -#endif /* def _DCC */ +/* There are a few sets of character names: R5RS, Guile + extensions for control characters, and leftover Guile extensions. + They are listed in order of precedence. */ + +const char *const scm_r5rs_charnames[] = + { + "space", "newline" + }; + +const scm_t_uint32 const scm_r5rs_charnums[] = + { + 0x20, 0x0A + }; + +const int scm_n_r5rs_charnames = sizeof (scm_r5rs_charnames) / sizeof (char *); + +/* The abbreviated names for control characters. */ +const char *const scm_C0_control_charnames[] = + { + /* C0 controls */ + "nul", "soh", "stx", "etx", "eot", "enq", "ack", "bel", + "bs", "ht", "lf", "vt", "ff", "cr", "so", "si", + "dle", "dc1", "dc2", "dc3", "dc4", "nak", "syn", "etb", + "can", "em", "sub", "esc", "fs", "gs", "rs", "us", + "sp", "del" + }; + +const scm_t_uint32 const scm_C0_control_charnums[] = + { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, + 0x20, 0x7f + }; + +int scm_n_C0_control_charnames = sizeof (scm_C0_control_charnames) / sizeof (char *); + +const char *const scm_alt_charnames[] = + { + "null", "backspace", "tab", "nl", "newline", "np", "page", "return", + }; + +const scm_t_uint32 const scm_alt_charnums[] = + { + 0x00, 0x08, 0x09, 0x0a, 0x0a, 0x0c, 0x0c, 0x0d + }; + +const int scm_n_alt_charnames = sizeof (scm_alt_charnames) / sizeof (char *); + +/* Returns the string charname for a character if it exists, or NULL + otherwise. */ +const char * +scm_i_charname (SCM chr) +{ + int c; + scm_t_uint32 i = SCM_CHAR (chr); + for (c = 0; c < scm_n_r5rs_charnames; c++) + if (scm_r5rs_charnums[c] == i) + return scm_r5rs_charnames[c]; -#ifdef EBCDIC -char *const scm_charnames[] = -{ - "nul", "soh", "stx", "etx", "pf", "ht", "lc", "del", - 0 , 0 , "smm", "vt", "ff", "cr", "so", "si", - "dle", "dc1", "dc2", "dc3", "res", "nl", "bs", "il", - "can", "em", "cc", 0 , "ifs", "igs", "irs", "ius", - "ds", "sos", "fs", 0 , "byp", "lf", "eob", "pre", - 0 , 0 , "sm", 0 , 0 , "enq", "ack", "bel", - 0 , 0 , "syn", 0 , "pn", "rs", "uc", "eot", - 0 , 0 , 0 , 0 , "dc4", "nak", 0 , "sub", - "space", scm_s_newline, "tab", "backspace", "return", "page", "null"}; - -const char scm_charnums[] = -"\000\001\002\003\004\005\006\007\ -\010\011\012\013\014\015\016\017\ -\020\021\022\023\024\025\026\027\ -\030\031\032\033\034\035\036\037\ -\040\041\042\043\044\045\046\047\ -\050\051\052\053\054\055\056\057\ -\060\061\062\063\064\065\066\067\ -\070\071\072\073\074\075\076\077\ - \n\t\b\r\f\0"; -#endif /* def EBCDIC */ -#ifdef ASCII -char *const scm_charnames[] = -{ - "nul","soh","stx","etx","eot","enq","ack","bel", - "bs", "ht", "newline", "vt", "np", "cr", "so", "si", - "dle","dc1","dc2","dc3","dc4","nak","syn","etb", - "can", "em","sub","esc", "fs", "gs", "rs", "us", - "space", "sp", "nl", "tab", "backspace", "return", "page", "null", "del"}; -const char scm_charnums[] = -"\000\001\002\003\004\005\006\007\ -\010\011\012\013\014\015\016\017\ -\020\021\022\023\024\025\026\027\ -\030\031\032\033\034\035\036\037\ - \n\t\b\r\f\0\177"; -#endif /* def ASCII */ - -int scm_n_charnames = sizeof (scm_charnames) / sizeof (char *); + for (c = 0; c < scm_n_C0_control_charnames; c++) + if (scm_C0_control_charnums[c] == i) + return scm_C0_control_charnames[c]; + + for (c = 0; c < scm_n_alt_charnames; c++) + if (scm_alt_charnums[c] == i) + return scm_alt_charnames[i]; + return NULL; +} + +/* Return a character from a string charname. */ +SCM +scm_i_charname_to_char (const char *charname, size_t charname_len) +{ + int c; + + /* The R5RS charnames. These are supposed to be case + insensitive. */ + for (c = 0; c < scm_n_r5rs_charnames; c++) + if ((strlen (scm_r5rs_charnames[c]) == charname_len) + && (!strncasecmp (scm_r5rs_charnames[c], charname, charname_len))) + return SCM_MAKE_CHAR (scm_r5rs_charnums[c]); + + /* Then come the controls. These are not case sensitive. */ + for (c = 0; c < scm_n_C0_control_charnames; c++) + if ((strlen (scm_C0_control_charnames[c]) == charname_len) + && (!strncasecmp (scm_C0_control_charnames[c], charname, charname_len))) + return SCM_MAKE_CHAR (scm_C0_control_charnums[c]); + + /* Lastly are some old names carried over for compatibility. */ + for (c = 0; c < scm_n_alt_charnames; c++) + if ((strlen (scm_alt_charnames[c]) == charname_len) + && (!strncasecmp (scm_alt_charnames[c], charname, charname_len))) + return SCM_MAKE_CHAR (scm_alt_charnums[c]); + + return SCM_BOOL_F; +} |