X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flexer.c;h=e573bbb7818f9b3cce8d07fe9edd9b930c8936bc;hb=a1887dd91b27990bba31adb888a4273379a4bf8c;hp=94793bfb9557d4d0191b411c93405bc09fcd98e2;hpb=e91248ddc41199bda0676817debf080c2b7835a1;p=pspp-builds.git diff --git a/src/lexer.c b/src/lexer.c index 94793bfb..e573bbb7 100644 --- a/src/lexer.c +++ b/src/lexer.c @@ -19,7 +19,7 @@ #include #include "lexer.h" -#include +#include "error.h" #include #include #include @@ -71,12 +71,14 @@ static char *prog; /* Nonzero only if this line ends with a terminal dot. */ static int dot; -/* Nonzero only if the last token returned was T_EOF. */ +/* Nonzero only if the last token returned was T_STOP. */ static int eof; /* If nonzero, next token returned by lex_get(). Used only in exceptional circumstances. */ -static int put; +static int put_token; +static struct string put_tokstr; +static double put_tokval; static void unexpected_eof (void); static inline int check_id (const char *id, size_t len); @@ -93,22 +95,53 @@ static void dump_token (void); void lex_init (void) { + ds_init (&put_tokstr, 64); if (!lex_get_line ()) unexpected_eof (); } + +void +lex_done (void) +{ + ds_destroy(&put_tokstr); +} + /* Common functions. */ +/* Copies put_token, put_tokstr, put_tokval into token, tokstr, + tokval, respectively, and sets tokid appropriately. */ +static void +restore_token (void) +{ + assert (put_token != 0); + token = put_token; + ds_replace (&tokstr, ds_c_str (&put_tokstr)); + strncpy (tokid, ds_c_str (&put_tokstr), 8); + tokid[8] = 0; + tokval = put_tokval; + put_token = 0; +} + +/* Copies token, tokstr, tokval into put_token, put_tokstr, + put_tokval respectively. */ +static void +save_token (void) +{ + put_token = token; + ds_replace (&put_tokstr, ds_c_str (&tokstr)); + put_tokval = tokval; +} + /* Parses a single token, setting appropriate global variables to indicate the token's attributes. */ void lex_get (void) { /* If a token was pushed ahead, return it. */ - if (put) + if (put_token) { - token = put; - put = 0; + restore_token (); #if DUMP_TOKENS dump_token (); #endif @@ -150,10 +183,9 @@ lex_get (void) return; } - if (put) + if (put_token) { - token = put; - put = 0; + restore_token (); #if DUMP_TOKENS dump_token (); #endif @@ -183,7 +215,7 @@ lex_get (void) negative numbers into two tokens. */ if (*cp == '-') { - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); while (isspace ((unsigned char) *prog)) prog++; @@ -196,32 +228,32 @@ lex_get (void) /* Parse the number, copying it into tokstr. */ while (isdigit ((unsigned char) *prog)) - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); if (*prog == '.') { - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); while (isdigit ((unsigned char) *prog)) - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); } if (*prog == 'e' || *prog == 'E') { - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); if (*prog == '+' || *prog == '-') - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); while (isdigit ((unsigned char) *prog)) - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); } /* Parse as floating point. */ - tokval = strtod (ds_value (&tokstr), &tail); + tokval = strtod (ds_c_str (&tokstr), &tail); if (*tail) { msg (SE, _("%s does not form a valid number."), - ds_value (&tokstr)); + ds_c_str (&tokstr)); tokval = 0.0; ds_clear (&tokstr); - ds_putchar (&tokstr, '0'); + ds_putc (&tokstr, '0'); } token = T_NUM; @@ -321,15 +353,15 @@ lex_get (void) } /* Copy id to tokstr. */ - ds_putchar (&tokstr, toupper ((unsigned char) *prog++)); + ds_putc (&tokstr, toupper ((unsigned char) *prog++)); while (CHAR_IS_IDN (*prog)) - ds_putchar (&tokstr, toupper ((unsigned char) *prog++)); + ds_putc (&tokstr, toupper ((unsigned char) *prog++)); /* Copy tokstr to tokid, truncating it to 8 characters. */ - strncpy (tokid, ds_value (&tokstr), 8); + strncpy (tokid, ds_c_str (&tokstr), 8); tokid[8] = 0; - token = check_id (ds_value (&tokstr), ds_length (&tokstr)); + token = check_id (ds_c_str (&tokstr), ds_length (&tokstr)); break; default: @@ -422,7 +454,7 @@ lex_double_p (void) /* Returns the value of the current token, which must be a floating point number. */ -long +double lex_double (void) { assert (lex_double_p ()); @@ -615,8 +647,8 @@ lex_id_match (const char *kw, const char *tok) int lex_look_ahead (void) { - if (put) - return put; + if (put_token) + return put_token; for (;;) { @@ -635,8 +667,8 @@ lex_look_ahead (void) else if (!lex_get_line ()) unexpected_eof (); - if (put) - return put; + if (put_token) + return put_token; } if ((toupper ((unsigned char) *prog) == 'X' @@ -653,45 +685,41 @@ lex_look_ahead (void) void lex_put_back (int t) { - put = token; + save_token (); token = t; } -/* Makes T the next token read. */ +/* Makes the current token become the next token to be read; the + current token is set to the identifier ID. */ void -lex_put_forward (int t) +lex_put_back_id (const char *id) { - put = t; + save_token (); + token = T_ID; + ds_replace (&tokstr, id); + strncpy (tokid, ds_c_str (&tokstr), 8); + tokid[8] = 0; } /* Weird line processing functions. */ -/* Discards the rest of the current input line for tokenization - purposes, but returns the entire contents of the line for use by - the caller. */ -char * +/* Returns the entire contents of the current line. */ +const char * lex_entire_line (void) { - prog = ds_end (&getl_buf); - dot = 0; - return ds_value (&getl_buf); + return ds_c_str (&getl_buf); } /* As lex_entire_line(), but only returns the part of the current line that hasn't already been tokenized. - If HAD_DOT is non-null, stores nonzero into *HAD_DOT if the line + If END_DOT is non-null, stores nonzero into *END_DOT if the line ends with a terminal dot, or zero if it doesn't. */ -char * -lex_rest_of_line (int *had_dot) +const char * +lex_rest_of_line (int *end_dot) { - char *s = prog; - prog = ds_end (&getl_buf); - - if (had_dot) - *had_dot = dot; - dot = 0; - - return s; + if (end_dot) + *end_dot = dot; + return prog; } /* Causes the rest of the current input line to be ignored for @@ -699,11 +727,8 @@ lex_rest_of_line (int *had_dot) void lex_discard_line (void) { - msg (SW, _("The rest of this command has been discarded.")); - - ds_clear (&getl_buf); - prog = ds_value (&getl_buf); - dot = put = 0; + prog = ds_end (&getl_buf); + dot = put_token = 0; } /* Sets the current position in the current line to P, which must be @@ -746,7 +771,7 @@ lex_preprocess_line (void) /* Remove C-style comments begun by slash-star and terminated by star-slash or newline. */ quote = comment = 0; - for (cp = ds_value (&getl_buf); *cp; ) + for (cp = ds_c_str (&getl_buf); *cp; ) { /* If we're not commented out, toggle quoting. */ if (!comment) @@ -787,19 +812,19 @@ lex_preprocess_line (void) /* Strip trailing whitespace and terminal dot. */ { size_t len = ds_length (&getl_buf); - char *s = ds_value (&getl_buf); + char *s = ds_c_str (&getl_buf); /* Strip trailing whitespace. */ while (len > 0 && isspace ((unsigned char) s[len - 1])) len--; /* Check for and remove terminal dot. */ - if (len > 0 && s[len - 1] == set_endcmd) + if (len > 0 && s[len - 1] == get_endcmd() ) { dot = 1; len--; } - else if (len == 0 && set_nullline) + else if (len == 0 && get_nullline() ) dot = 1; else dot = 0; @@ -812,15 +837,15 @@ lex_preprocess_line (void) as necessary. */ if (getl_interactive != 2 && getl_mode == GETL_MODE_BATCH) { - char *s = ds_value (&getl_buf); + char *s = ds_c_str (&getl_buf); if (s[0] == '+' || s[0] == '-' || s[0] == '.') s[0] = ' '; else if (s[0] && !isspace ((unsigned char) s[0])) - lex_put_forward ('.'); + put_token = '.'; } - prog = ds_value (&getl_buf); + prog = ds_c_str (&getl_buf); } /* Token names. */ @@ -853,7 +878,7 @@ lex_token_representation (void) { case T_ID: case T_NUM: - return xstrdup (ds_value (&tokstr)); + return xstrdup (ds_c_str (&tokstr)); break; case T_STRING: @@ -861,7 +886,7 @@ lex_token_representation (void) int hexstring = 0; char *sp, *dp; - for (sp = ds_value (&tokstr); sp < ds_end (&tokstr); sp++) + for (sp = ds_c_str (&tokstr); sp < ds_end (&tokstr); sp++) if (!isprint ((unsigned char) *sp)) { hexstring = 1; @@ -876,14 +901,14 @@ lex_token_representation (void) *dp++ = '\''; if (!hexstring) - for (sp = ds_value (&tokstr); *sp; ) + for (sp = ds_c_str (&tokstr); *sp; ) { if (*sp == '\'') *dp++ = '\''; *dp++ = (unsigned char) *sp++; } else - for (sp = ds_value (&tokstr); sp < ds_end (&tokstr); sp++) + for (sp = ds_c_str (&tokstr); sp < ds_end (&tokstr); sp++) { *dp++ = (((unsigned char) *sp) >> 4)["0123456789ABCDEF"]; *dp++ = (((unsigned char) *sp) & 15)["0123456789ABCDEF"]; @@ -929,10 +954,11 @@ lex_negative_to_dash (void) { if (token == T_NUM && tokval < 0.0) { - token = '-'; + token = T_NUM; tokval = -tokval; - ds_replace (&tokstr, ds_value (&tokstr) + 1); - lex_put_forward (T_NUM); + ds_replace (&tokstr, ds_c_str (&tokstr) + 1); + save_token (); + token = '-'; } } @@ -949,8 +975,14 @@ lex_skip_comment (void) { for (;;) { - lex_get_line (); - if (put == '.') + if (!lex_get_line ()) + { + put_token = T_STOP; + eof = 1; + return; + } + + if (put_token == '.') break; prog = ds_end (&getl_buf); @@ -1009,7 +1041,7 @@ convert_numeric_string_to_char_string (int type) "multiple of %d."), gettext (base_name), ds_length (&tokstr), cpb); - p = ds_value (&tokstr); + p = ds_c_str (&tokstr); for (i = 0; i < nb; i++) { int value; @@ -1039,7 +1071,7 @@ convert_numeric_string_to_char_string (int type) value = value * base + v; } - ds_value (&tokstr)[i] = (unsigned char) value; + ds_c_str (&tokstr)[i] = (unsigned char) value; } ds_truncate (&tokstr, nb); @@ -1078,7 +1110,7 @@ parse_string (int type) break; } - ds_putchar (&tokstr, *prog++); + ds_putc (&tokstr, *prog++); } prog++; @@ -1148,7 +1180,7 @@ finish: int warned = 0; for (i = 0; i < ds_length (&tokstr); i++) - if (ds_value (&tokstr)[i] == 0) + if (ds_c_str (&tokstr)[i] == 0) { if (!warned) { @@ -1156,7 +1188,7 @@ finish: "characters. Replacing with spaces.")); warned = 1; } - ds_value (&tokstr)[i] = ' '; + ds_c_str (&tokstr)[i] = ' '; } } @@ -1175,41 +1207,41 @@ dump_token (void) getl_location (&curfn, &curln); if (curfn) - printf ("%s:%d\t", curfn, curln); + fprintf (stderr, "%s:%d\t", curfn, curln); } switch (token) { case T_ID: - printf ("ID\t%s\n", tokid); + fprintf (stderr, "ID\t%s\n", tokid); break; case T_NUM: - printf ("NUM\t%f\n", tokval); + fprintf (stderr, "NUM\t%f\n", tokval); break; case T_STRING: - printf ("STRING\t\"%s\"\n", ds_value (&tokstr)); + fprintf (stderr, "STRING\t\"%s\"\n", ds_c_str (&tokstr)); break; case T_STOP: - printf ("STOP\n"); + fprintf (stderr, "STOP\n"); break; case T_EXP: - puts ("MISC\tEXP"); + fprintf (stderr, "MISC\tEXP\""); break; case 0: - puts ("MISC\tEOF"); + fprintf (stderr, "MISC\tEOF\n"); break; default: if (token >= T_FIRST_KEYWORD && token <= T_LAST_KEYWORD) - printf ("KEYWORD\t%s\n", lex_token_name (token)); + fprintf (stderr, "KEYWORD\t%s\n", lex_token_name (token)); else - printf ("PUNCT\t%c\n", token); + fprintf (stderr, "PUNCT\t%c\n", token); break; } } -#endif /* DEBUGGING */ +#endif /* DUMP_TOKENS */