/* * Called from control when a #define is scanned. This module * parses formal parameters and the replacement string. When * the formal parameter name is encountered in the replacement * string, it is replaced by a character in the range 128 to * 128+NPARAM (this allows up to 32 parameters within the * Dec Multinational range). * * There is some special case code to distinguish * #define foo bar * from #define foo() bar * * Also, we make sure that * #define foo foo * expands to "foo" but doesn't put cpp into an infinite loop. * * A warning message is printed if you redefine a symbol to a * different text. I.e, * #define foo 123 * #define foo 123 * is ok, but * #define foo 123 * #define foo +123 * is not. * * The following subroutines are called from define(): * checkparm called when a token is scanned. It checks through the * array of formal parameters. If a match is found, the * token is replaced by a control byte which will be used * to locate the parameter when the macro is expanded. * textput puts a string in the macro work area (parm[]), updating * parmp to point to the first free byte in parm[]. * textput() tests for work buffer overflow. * charput puts a single character in the macro work area (parm[]) * in a manner analogous to textput(). */ void dodefine() { int c; DEFBUF* dp; /* -> new definition */ int isredefine; /* TRUE if redefined */ char* old = NULL; /* Remember redefined */ if (type[(c = skipws())] != LET) goto bad_define; isredefine = FALSE; /* Set if redefining */ if ((dp = lookid(c)) == NULL) /* If not known now */ dp = defendel(token, FALSE); /* Save the name */ else /* It's known: */ { isredefine = TRUE; /* Remember this fact */ old = dp->repl; /* Remember replacement */ dp->repl = NULL; /* No replacement now */ } parlist[0] = parmp = parm; /* Setup parm buffer */ if ((c = get()) == '(') /* With arguments? */ { nargs = 0; /* Init formals counter */ do /* Collect formal parms */ { if (nargs >= LASTPARM) cfatal("Too many arguments for macro", NULLST); else if ((c = skipws()) == ')') break; /* Got them all */ else if (type[c] != LET) /* Bad formal syntax */ goto bad_define; scanid(c); /* Get the formal param */ parlist[nargs++] = parmp; /* Save its start */ textput(token); /* Save text in parm[] */ } while ((c = skipws()) == ','); /* Get another argument */ if (c != ')') /* Must end at ) */ goto bad_define; c = ' '; /* Will skip to body */ } else { /* * DEF_NOARGS is needed to distinguish between * "#define foo" and "#define foo()". */ nargs = DEF_NOARGS; /* No () parameters */ } if (type[c] == SPA) /* At whitespace? */ c = skipws(); /* Not any more. */ workp = work; /* Replacement put here */ inmacro = TRUE; /* Keep \<newline> now */ while (c != EOF_CHAR && c != '\n') /* Compile macro body */ { if (c == '#') /* Token concatenation? */ { while (workp > work && type[(int)workp[-1]] == SPA) --workp; /* Erase leading spaces */ save(TOK_SEP); /* Stuff a delimiter */ c = skipws(); /* Eat whitespace */ if (type[c] == LET) /* Another token here? */ ; /* Stuff it normally */ else if (type[c] == DIG) /* Digit string after? */ { while (type[c] == DIG) /* Stuff the digits */ { save(c); c = get(); } save(TOK_SEP); /* Delimit 2nd token */ } else { ciwarn("Strange character after # (%d.)", c); } continue; } switch (type[c]) { case LET: checkparm(c, dp); /* Might be a formal */ break; case DIG: /* Number in mac. body */ case DOT: /* Maybe a float number */ scannumber(c, save); /* Scan it off */ break; case QUO: /* String in mac. body */ stparmscan(c); break; case BSH: /* Backslash */ save('\\'); if ((c = get()) == '\n') wrongline = TRUE; save(c); break; case SPA: /* Absorb whitespace */ /* * Note: the "end of comment" marker is passed on * to allow comments to separate tokens. */ if (workp[-1] == ' ') /* Absorb multiple */ break; /* spaces */ else if (c == '\t') c = ' '; /* Normalize tabs */ /* Fall through to store character */ default: /* Other character */ save(c); break; } c = get(); } inmacro = FALSE; /* Stop newline hack */ unget(); /* For control check */ if (workp > work && workp[-1] == ' ') /* Drop trailing blank */ workp--; *workp = EOS; /* Terminate work */ dp->repl = savestring(work); /* Save the string */ dp->nargs = nargs; /* Save arg count */ #if OSL_DEBUG_LEVEL > 1 if (debug) dumpadef("macro definition", dp); else if (bDumpDefs) dumpadef(NULL, dp); #endif if (isredefine) /* Error if redefined */ { if ((old != NULL && dp->repl != NULL && !streq(old, dp->repl)) || (old == NULL && dp->repl != NULL) || (old != NULL && dp->repl == NULL)) { #ifdef STRICT_UNDEF cerror("Redefining defined variable \"%s\"", dp->name); #else cwarn("Redefining defined variable \"%s\"", dp->name); #endif } if (old != NULL) /* We don't need the */ free(old); /* old definition now. */ } return; bad_define: cerror("#define syntax error", NULLST); inmacro = FALSE; /* Stop <newline> hack */ }
ReturnCode dodefine(struct Global *global) { /* * Called from control when a #define is scanned. This module * parses formal parameters and the replacement string. When * the formal parameter name is encountered in the replacement * string, it is replaced by a character in the range 128 to * 128+NPARAM (this allows up to 32 parameters within the * Dec Multinational range). If cpp is ported to an EBCDIC * machine, you will have to make other arrangements. * * There is some special case code to distinguish * #define foo bar * from #define foo() bar * * Also, we make sure that * #define foo foo * expands to "foo" but doesn't put cpp into an infinite loop. * * A warning message is printed if you redefine a symbol to a * different text. I.e, * #define foo 123 * #define foo 123 * is ok, but * #define foo 123 * #define foo +123 * is not. * * The following subroutines are called from define(): * checkparm called when a token is scanned. It checks through the * array of formal parameters. If a match is found, the * token is replaced by a control byte which will be used * to locate the parameter when the macro is expanded. * textput puts a string in the macro work area (parm[]), updating * parmp to point to the first free byte in parm[]. * textput() tests for work buffer overflow. * charput puts a single character in the macro work area (parm[]) * in a manner analogous to textput(). */ int c; DEFBUF *dp; /* -> new definition */ int isredefine; /* TRUE if redefined */ char *old = NULL; /* Remember redefined */ ReturnCode ret; #if OK_CONCAT int quoting; /* Remember we saw a # */ #endif if (type[(c = skipws(global))] != LET) { cerror(global, ERROR_DEFINE_SYNTAX); global->inmacro = FALSE; /* Stop <newline> hack */ return(FPP_OK); } isredefine = FALSE; /* Set if redefining */ if ((dp = lookid(global, c)) == NULL) { /* If not known now */ dp = defendel(global, global->tokenbuf, FALSE); /* Save the name */ if(!dp) return(FPP_OUT_OF_MEMORY); } else { /* It's known: */ isredefine = TRUE; /* Remember this fact */ old = dp->repl; /* Remember replacement */ dp->repl = NULL; /* No replacement now */ } global->parlist[0] = global->parmp = global->parm; /* Setup parm buffer */ if ((c = get(global)) == '(') { /* With arguments? */ global->nargs = 0; /* Init formals counter */ do { /* Collect formal parms */ if (global->nargs >= LASTPARM) { cfatal(global, FATAL_TOO_MANY_ARGUMENTS_MACRO); return(FPP_TOO_MANY_ARGUMENTS); } else if ((c = skipws(global)) == ')') break; /* Got them all */ else if (type[c] != LET) { /* Bad formal syntax */ cerror(global, ERROR_DEFINE_SYNTAX); global->inmacro = FALSE; /* Stop <newline> hack */ return(FPP_OK); } scanid(global, c); /* Get the formal param */ global->parlist[global->nargs++] = global->parmp; /* Save its start */ ret=textput(global, global->tokenbuf); /* Save text in parm[] */ if(ret) return(ret); } while ((c = skipws(global)) == ','); /* Get another argument */ if (c != ')') { /* Must end at ) */ cerror(global, ERROR_DEFINE_SYNTAX); global->inmacro = FALSE; /* Stop <newline> hack */ return(FPP_OK); } c = ' '; /* Will skip to body */ } else { /* * DEF_NOARGS is needed to distinguish between * "#define foo" and "#define foo()". */ global->nargs = DEF_NOARGS; /* No () parameters */ } if (type[c] == SPA) /* At whitespace? */ c = skipws(global); /* Not any more. */ global->workp = global->work; /* Replacement put here */ global->inmacro = TRUE; /* Keep \<newline> now */ quoting = 0; /* No # seen yet. */ while (c != EOF_CHAR && c != '\n') { /* Compile macro body */ #if OK_CONCAT if (c == '#') { /* Token concatenation? */ if ((c = get(global)) != '#') { /* No, not really */ quoting = 1; /* Maybe quoting op. */ continue; } while (global->workp > global->work && type[(unsigned)*(global->workp - 1)] == SPA) --global->workp; /* Erase leading spaces */ if((ret=save(global, TOK_SEP))) /* Stuff a delimiter */ return(ret); c = skipws(global); /* Eat whitespace */ continue; } #endif switch (type[c]) { case LET: #if OK_CONCAT ret=checkparm(global, c, dp, quoting); /* Might be a formal */ #else ret=checkparm(c, dp); /* Might be a formal */ #endif if(ret) return(ret); break; case DIG: /* Number in mac. body */ case DOT: /* Maybe a float number */ ret=scannumber(global, c, save); /* Scan it off */ if(ret) return(ret); break; case QUO: /* String in mac. body */ ret=stparmscan(global, c); if(ret) return(ret); break; case BSH: /* Backslash */ ret=save(global, '\\'); if(ret) return(ret); if ((c = get(global)) == '\n') global->wrongline = TRUE; ret=save(global, c); if(ret) return(ret); break; case SPA: /* Absorb whitespace */ /* * Note: the "end of comment" marker is passed on * to allow comments to separate tokens. */ if (global->workp[-1] == ' ') /* Absorb multiple */ break; /* spaces */ else if (c == '\t') c = ' '; /* Normalize tabs */ /* Fall through to store character */ default: /* Other character */ ret=save(global, c); if(ret) return(ret); break; } c = get(global); quoting = 0; /* Only when immediately*/ /* preceding a formal */ } global->inmacro = FALSE; /* Stop newline hack */ unget(global); /* For control check */ if (global->workp > global->work && global->workp[-1] == ' ') /* Drop trailing blank */ global->workp--; *global->workp = EOS; /* Terminate work */ dp->repl = savestring(global, global->work); /* Save the string */ dp->nargs = global->nargs; /* Save arg count */ if (isredefine) { /* Error if redefined */ if ((old != NULL && dp->repl != NULL && !streq(old, dp->repl)) || (old == NULL && dp->repl != NULL) || (old != NULL && dp->repl == NULL)) { cerror(global, ERROR_REDEFINE, dp->name); } if (old != NULL) /* We don't need the */ free(old); /* old definition now. */ } return(FPP_OK); }
/* * Main process for cpp -- copies tokens from the current input * stream (main file, include file, or a macro) to the output * file. */ void cppmain() { int c; /* Current character */ int counter; /* newlines and spaces */ /* * Explicitly output a #line at the start of cpp output so * that lint (etc.) knows the name of the original source * file. If we don't do this explicitly, we may get * the name of the first #include file instead. * We also seem to need a blank line following that first #line. */ #ifdef EVALDEFS if ( !bIsInEval ) #endif { sharp(); PUTCHAR('\n'); } /* * This loop is started "from the top" at the beginning of each line * wrongline is set TRUE in many places if it is necessary to write * a #line record. (But we don't write them when expanding macros.) * * The counter variable has two different uses: at * the start of a line, it counts the number of blank lines that * have been skipped over. These are then either output via * #line records or by outputting explicit blank lines. * When expanding tokens within a line, the counter remembers * whether a blank/tab has been output. These are dropped * at the end of the line, and replaced by a single blank * within lines. */ for (;;) { counter = 0; /* Count empty lines */ for (;;) { /* For each line, ... */ while (type[(c = get())] == SPA) /* Skip leading blanks */ ; /* in this line. */ if (c == '\n') /* If line's all blank, */ ++counter; /* Do nothing now */ else if (c == '#') { /* Is 1st non-space '#' */ keepcomments = FALSE; /* Don't pass comments */ counter = control(counter); /* Yes, do a #command */ keepcomments = (cflag && compiling); } else if (c == EOF_CHAR) /* At end of file? */ { break; } else if (!compiling) { /* #ifdef false? */ skipnl(); /* Skip to newline */ counter++; /* Count it, too. */ } else { break; /* Actual token */ } } if (c == EOF_CHAR) /* Exit process at */ break; /* End of file */ /* * If the loop didn't terminate because of end of file, we * know there is a token to compile. First, clean up after * absorbing newlines. counter has the number we skipped. */ if ((wrongline && infile->fp != NULL) || counter > 4) sharp(); /* Output # line number */ else { /* If just a few, stuff */ while (--counter >= 0) /* them out ourselves */ PUTCHAR('\n'); } /* * Process each token on this line. */ unget(); /* Reread the char. */ for (;;) { /* For the whole line, */ do { /* Token concat. loop */ for (counter = 0; type[(c = get())] == SPA;) { #if COMMENT_INVISIBLE if (c != COM_SEP) #endif counter++; /* Skip over blanks */ } if (c == EOF_CHAR || c == '\n') goto end_line; /* Exit line loop */ else if (counter > 0) /* If we got any spaces */ PUTCHAR(' '); /* Output one space */ c = macroid(c); /* Grab the token */ } while (type[c] == LET && catenate()); if (c == EOF_CHAR || c == '\n') /* From macro exp error */ goto end_line; /* Exit line loop */ switch (type[c]) { case LET: fputs(token, pCppOut); /* Quite ordinary token */ #ifdef EVALDEFS { int len; if ( bIsInEval && nEvalOff + (len=strlen(token)) < NEVALBUF ) { strcpy( &EvalBuf[nEvalOff], token ); nEvalOff += len; } } #endif break; case DIG: /* Output a number */ case DOT: /* Dot may begin floats */ #ifdef EVALDEFS if ( bIsInEval ) scannumber(c, outputEval); else scannumber(c, output); #else scannumber(c, output); #endif break; case QUO: /* char or string const */ scanstring(c, output); /* Copy it to output */ break; default: /* Some other character */ cput(c); /* Just output it */ #ifdef EVALDEFS if ( bIsInEval && nEvalOff < NEVALBUF ) EvalBuf[nEvalOff++] = c; #endif break; } /* Switch ends */ } /* Line for loop */ end_line: if (c == '\n') { /* Compiling at EOL? */ PUTCHAR('\n'); /* Output newline, if */ if (infile->fp == NULL) /* Expanding a macro, */ wrongline = TRUE; /* Output # line later */ } } /* Continue until EOF */ #ifdef EVALDEFS if ( bIsInEval ) EvalBuf[nEvalOff++] = '\0'; #endif }
INLINE FILE_LOCAL ReturnCode cppmain(struct Global *global) { /* * Main process for cpp -- copies tokens from the current input * stream (main file, include file, or a macro) to the output * file. */ int c; /* Current character */ int counter; /* newlines and spaces */ ReturnCode ret; /* return code variable type */ long bracelevel = 0; long parenlevel = 0; long bracketlevel = 0; int fake = 0; #define MAX_FUNC_LENGTH 50 char tempfunc[MAX_FUNC_LENGTH + 1]; char tempfunc2[MAX_FUNC_LENGTH + 1]; char define = 0; /* probability of a function define phase in the program */ char prev = 0; /* previous type */ char go = 0; char include = 0; char initfunc = 0; /* Initialize for reading tokens */ global->tokenbsize = 50; global->tokenbuf = malloc(global->tokenbsize + 1); if(!global->tokenbuf) return(FPP_OUT_OF_MEMORY); global->functionname = malloc(global->tokenbsize + 1); if(!global->functionname) return(FPP_OUT_OF_MEMORY); global->functionname[0] = '\0'; if(global->showspace) { global->spacebuf = (char *)malloc(MAX_SPACE_SIZE); if(!global->spacebuf) return(FPP_OUT_OF_MEMORY); } if(global->showversion) Error(global, VERSION_TEXT); /* * Explicitly output a #line at the start of cpp output so * that lint (etc.) knows the name of the original source * file. If we don't do this explicitly, we may get * the name of the first #include file instead. */ if(global->linelines) /* if #line lines are wanted! */ sharp(global); /* * This loop is started "from the top" at the beginning of each line * wrongline is set TRUE in many places if it is necessary to write * a #line record. (But we don't write them when expanding macros.) * * The counter variable has two different uses: at * the start of a line, it counts the number of blank lines that * have been skipped over. These are then either output via * #line records or by outputting explicit blank lines. * When expanding tokens within a line, the counter remembers * whether a blank/tab has been output. These are dropped * at the end of the line, and replaced by a single blank * within lines. */ include = global->included; while(include--) { openinclude(global, global->include[include], TRUE); } for (;;) { counter = 0; /* Count empty lines */ for (;;) { /* For each line, ... */ global->comment = FALSE; /* No comment yet! */ global->chpos = 0; /* Count whitespaces */ while (type[(c = get(global))] == SPA) /* Skip leading blanks */ if(global->showspace) { if(global->chpos<MAX_SPACE_SIZE-1) /* we still have buffer to store this! */ global->spacebuf[global->chpos++]=(char)c; } if (c == '\n') { /* If line's all blank, */ if(global->comment) { /* A comment was output! */ Putchar(global, '\n'); } else ++counter; /* Do nothing now */ } else if (c == '#') { /* Is 1st non-space '#' */ global->keepcomments = FALSE; /* Don't pass comments */ ret = control(global, &counter); /* Yes, do a #command */ if(ret) return(ret); global->keepcomments = (global->cflag && compiling); } else if (c == EOF_CHAR) /* At end of file? */ break; else if (!compiling) { /* #ifdef false? */ skipnl(global); /* Skip to newline */ counter++; /* Count it, too. */ } else { break; /* Actual token */ } } if (c == EOF_CHAR) /* Exit process at */ break; /* End of file */ /* * If the loop didn't terminate because of end of file, we * know there is a token to compile. First, clean up after * absorbing newlines. counter has the number we skipped. */ if(global->linelines) { /* if #line lines are wanted! */ if ((global->wrongline && global->infile->fp != NULL) || counter > 4) sharp(global); /* Output # line number */ else { /* If just a few, stuff */ while (--counter >= 0) /* them out ourselves */ Putchar(global, (int)'\n'); } } if(global->showspace) { /* Show all whitespaces! */ global->spacebuf[global->chpos] = '\0'; Putstring(global, global->spacebuf); } /* * Process each token on this line. */ unget(global); /* Reread the char. */ for (;;) { /* For the whole line, */ do { /* Token concat. loop */ for (global->chpos = counter = 0; (type[(c = get(global))] == SPA);) { #if COMMENT_INVISIBLE if (c != COM_SEP) counter++; #else if(global->showspace && global->chpos < MAX_SPACE_SIZE-1) { global->spacebuf[global->chpos++]=(char)c; } counter++; /* Skip over blanks */ #endif } if (c == EOF_CHAR || c == '\n') break; /* Exit line loop */ else if (counter > 0) { /* If we got any spaces */ if(!global->showspace) /* We don't output all spaces */ Putchar(global, (int)' ');/* Output one space */ else { global->spacebuf[global->chpos] = '\0'; Putstring(global, global->spacebuf); /* Output all whitespaces */ } } if(ret=macroid(global, &c)) /* Grab the token */ return(ret); } while (type[c] == LET && catenate(global, &ret) && !ret); if(ret) /* If the loop was broken because of a fatal error! */ return(ret); if (c == EOF_CHAR || c == '\n') /* From macro exp error */ break; /* Exit line loop */ go++; switch (type[c]) { case LET: go =0; /* Quite ordinary token */ Putstring(global, global->tokenbuf); if(!define) { /* Copy the name */ strncpy(tempfunc, global->tokenbuf, MAX_FUNC_LENGTH); tempfunc[MAX_FUNC_LENGTH]=0; } /* fputs(global->tokenbuf, stdout); */ break; case DIG: /* Output a number */ case DOT: /* Dot may begin floats */ go = 0; ret=scannumber(global, c, (ReturnCode(*)(struct Global *, int))output); if(ret) return(ret); break; case QUO: /* char or string const */ go = 0; /* Copy it to output */ if(!global->webmode) { ret=scanstring(global, c, (ReturnCode(*)(struct Global *, int))output); if(ret) return(ret); break; } /* FALLTHROUGH */ default: /* Some other character */ define++; switch(c) { case '{': if(! bracelevel++ && define > 2) { /* * This is a starting brace. If there is a probability of a * function defining, we copy the `tempfunc' function name to * `global->functionname'. */ strcpy(global->functionname, tempfunc2); global->funcline = global->line; if(global->outputfunctions) { /* * Output the discovered function name to stderr! */ Error(global, "#> Function defined at line %d: %s <#\n", global->line, global->functionname); } if(global->initialfunc) { int a; for(a=0; a<global->excluded; a++) { /* check for excluded functions */ if(!strcmp(global->functionname, global->excludedinit[a])) break; } if(a==global->excluded) { expstuff(global, "__brace__", "{"); expstuff(global, "__init_func__", global->initialfunc); initfunc = TRUE; } } } break; case '}': go = 0; if( (--bracelevel == initfunc) && strcmp(global->infile->filename, "__init_func__") ) { /* we just stepped out of the function! */ global->functionname[0] = '\0'; global->funcline = 0; define = 1; if(initfunc) { Putchar(global, '}'); bracelevel--; initfunc=0; } } fake = 0; break; case ';': case ',': if(go == 2) { define = 1; fake = 0; go--; break; } break; case '(': if(! parenlevel++ && !bracelevel) { if(go == 2) { /* foobar(text) -> "(" is found. This can't be a function */ go--; define = 1; break; } if( define < 2 && prev == LET) { /* This is the first parenthesis on the ground brace level, and we did previously not have a probable function name */ strncpy(tempfunc2, global->tokenbuf, MAX_FUNC_LENGTH); tempfunc2[MAX_FUNC_LENGTH]=0; define++; } else { /* we have a fake start */ fake++; } } break; case ')': if(! --parenlevel && !bracelevel && define>1 && !fake) { /* * The starting parentheses level and * the starting brace level. * This might be the start of a function defining coming * up! */ define++; /* increase probability */ fake = 0; go = 1; } break; case '[': bracketlevel++; break; case ']': bracketlevel--; break; } define--; /* decrease function probability */ Putchar(global, c); /* Just output it */ break; } /* Switch ends */ prev = type[c]; } /* Line for loop */ if (c == '\n') { /* Compiling at EOL? */ Putchar(global, '\n'); /* Output newline, if */ if (global->infile->fp == NULL) /* Expanding a macro, */ global->wrongline = TRUE; /* Output # line later */ } } /* Continue until EOF */ if(global->showbalance) { if(bracketlevel) { cwarn(global, WARN_BRACKET_DEPTH, bracketlevel); } if(parenlevel) { cwarn(global, WARN_PAREN_DEPTH, parenlevel); } if(bracelevel) { cwarn(global, WARN_BRACE_DEPTH, bracelevel); } } if (global->wflag) { global->out = TRUE; /* enable output */ outdefines(global); /* Write out #defines */ } return(FPP_OK); }