📄 re2c.man
字号:
RE2C(1) RE2C(1) s->tok = s->bot; s->ptr -= cnt; cursor -= cnt; s->pos -= cnt; s->lim -= cnt; } if((s->top - s->lim) < BSIZE){ uchar *buf = (uchar*) malloc(((s->lim - s->bot) + BSIZE)*sizeof(uchar)); memcpy(buf, s->tok, s->lim - s->tok); s->tok = buf; s->ptr = &buf[s->ptr - s->bot]; cursor = &buf[cursor - s->bot]; s->pos = &buf[s->pos - s->bot]; s->lim = &buf[s->lim - s->bot]; s->top = &s->lim[BSIZE]; free(s->bot); s->bot = buf; } if((cnt = read(s->fd, (char*) s->lim, BSIZE)) != BSIZE){ s->eof = &s->lim[cnt]; *(s->eof)++ = '\n'; } s->lim += cnt; } return cursor; } int scan(Scanner *s){ uchar *cursor = s->cur; std: s->tok = cursor; /*!re2c any = [\000-\377]; O = [0-7]; D = [0-9]; L = [a-zA-Z_]; H = [a-fA-F0-9]; E = [Ee] [+-]? D+; FS = [fFlL]; IS = [uUlL]*; ESC = [\\] ([abfnrtv?'"\\] | "x" H+ | O+); */ /*!re2c "/*" { goto comment; } "auto" { RET(AUTO); } "break" { RET(BREAK); } "case" { RET(CASE); } "char" { RET(CHAR); } "const" { RET(CONST); } "continue" { RET(CONTINUE); } "default" { RET(DEFAULT); } "do" { RET(DO); }Version 0.5 8 April 1994 6RE2C(1) RE2C(1) "double" { RET(DOUBLE); } "else" { RET(ELSE); } "enum" { RET(ENUM); } "extern" { RET(EXTERN); } "float" { RET(FLOAT); } "for" { RET(FOR); } "goto" { RET(GOTO); } "if" { RET(IF); } "int" { RET(INT); } "long" { RET(LONG); } "register" { RET(REGISTER); } "return" { RET(RETURN); } "short" { RET(SHORT); } "signed" { RET(SIGNED); } "sizeof" { RET(SIZEOF); } "static" { RET(STATIC); } "struct" { RET(STRUCT); } "switch" { RET(SWITCH); } "typedef" { RET(TYPEDEF); } "union" { RET(UNION); } "unsigned" { RET(UNSIGNED); } "void" { RET(VOID); } "volatile" { RET(VOLATILE); } "while" { RET(WHILE); } L (L|D)* { RET(ID); } ("0" [xX] H+ IS?) | ("0" D+ IS?) | (D+ IS?) | (['] (ESC|any\[\n\\'])* [']) { RET(ICON); } (D+ E FS?) | (D* "." D+ E? FS?) | (D+ "." D* E? FS?) { RET(FCON); } (["] (ESC|any\[\n\\"])* ["]) { RET(SCON); } "..." { RET(ELLIPSIS); } ">>=" { RET(RSHIFTEQ); } "<<=" { RET(LSHIFTEQ); } "+=" { RET(ADDEQ); } "-=" { RET(SUBEQ); } "*=" { RET(MULEQ); } "/=" { RET(DIVEQ); } "%=" { RET(MODEQ); } "&=" { RET(ANDEQ); } "^=" { RET(XOREQ); } "|=" { RET(OREQ); } ">>" { RET(RSHIFT); } "<<" { RET(LSHIFT); } "++" { RET(INCR); } "--" { RET(DECR); } "->" { RET(DEREF); } "&&" { RET(ANDAND); }Version 0.5 8 April 1994 7RE2C(1) RE2C(1) "||" { RET(OROR); } "<=" { RET(LEQ); } ">=" { RET(GEQ); } "==" { RET(EQL); } "!=" { RET(NEQ); } ";" { RET(';'); } "{" { RET('{'); } "}" { RET('}'); } "," { RET(','); } ":" { RET(':'); } "=" { RET('='); } "(" { RET('('); } ")" { RET(')'); } "[" { RET('['); } "]" { RET(']'); } "." { RET('.'); } "&" { RET('&'); } "!" { RET('!'); } "~" { RET('~'); } "-" { RET('-'); } "+" { RET('+'); } "*" { RET('*'); } "/" { RET('/'); } "%" { RET('%'); } "<" { RET('<'); } ">" { RET('>'); } "^" { RET('^'); } "|" { RET('|'); } "?" { RET('?'); } [ \t\v\f]+ { goto std; } "\n" { if(cursor == s->eof) RET(EOI); s->pos = cursor; s->line++; goto std; } any { printf("unexpected character: %c\n", *s->tok); goto std; } */ comment: /*!re2c "*/" { goto std; } "\n" { if(cursor == s->eof) RET(EOI); s->tok = s->pos = cursor; s->line++;Version 0.5 8 April 1994 8RE2C(1) RE2C(1) goto comment; } any { goto comment; } */ } main(){ Scanner in; int t; memset((char*) &in, 0, sizeof(in)); in.fd = 0; while((t = scan(&in)) != EOI){ /* printf("%d\t%.*s\n", t, in.cur - in.tok, in.tok); printf("%d\n", t); */ } close(in.fd); }SSEEEE AALLSSOO flex(1), lex(1).FFEEAATTUURREESS rree22cc does not provide a default action: the generated code assumes that the input will consist of a sequence of tokens. Typically this can be dealt with by adding a rule such as the one for unexpected characters in the example above. The user must arrange for a sentinel token to appear at the end of input (and provide a rule for matching it): rree22cc does not provide an <<<<EEOOFF>>>> expression. If the source is from a null-byte terminated string, a rule matching a null character will suffice. If the source is from a file then the approach taken in the example can be used: pad the input with a newline (or some other charac- ter that can't appear within another token); upon recog- nizing such a character check to see if it is the sentinel and act accordingly. rree22cc does not provide start conditions: use a separate scanner specification for each start condition (as illus- trated in the above example). No [^x]. Use difference instead.BBUUGGSS Only fixed length trailing context can be handled. The maximum value appearing as a parameter _n to YYYYFFIILLLL is not provided to the generated code (this value is neededVersion 0.5 8 April 1994 9RE2C(1) RE2C(1) for constructing the interface code). Note that this value is usually relatively small: for typical programming languages _n will be the length of the longest keyword plus one. Difference only works for character sets. The rree22cc internal algorithms need documentation.AAUUTTHHOORR Please send bug reports, fixes and feedback to: Peter Bumbulis Computer Systems Group University of Waterloo Waterloo, Ontario N2L 3G1 Internet: peterr@csg.uwaterloo.caVersion 0.5 8 April 1994 10
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -