diff --git a/b.c b/b.c index 89a7841..a54a234 100644 --- a/b.c +++ b/b.c @@ -823,7 +823,15 @@ int relex(void) /* lexical analyzer for reparse */ if (cc->cc_name != NULL && prestr[1 + cc->cc_namelen] == ':' && prestr[2 + cc->cc_namelen] == ']') { prestr += cc->cc_namelen + 3; - for (i = 0; i < NCHARS; i++) { + /* + * BUG: We begin at 1, instead of 0, since we + * would otherwise prematurely terminate the + * string for classes like [[:cntrl:]]. This + * means that we can't match the NUL character, + * not without first adapting the entire + * program to track each string's length. + */ + for (i = 1; i < NCHARS; i++) { if (!adjbuf((char **) &buf, &bufsz, bp-buf+1, 100, (char **) &bp, "relex2")) FATAL("out of space for reg expr %.10s...", lastre); if (cc->cc_func(i)) { diff --git a/bugs-fixed/README b/bugs-fixed/README index 59ff5b0..80c532d 100644 --- a/bugs-fixed/README +++ b/bugs-fixed/README @@ -30,4 +30,12 @@ being assigned to, meant that expressions like "print (a = 1) (a = 2)" would print "22" rather than "12". 9. missing-precision: When using the format string "%*s", the precision -argument was used without checking if it was present first. \ No newline at end of file +argument was used without checking if it was present first. + +10. missing-precision: When using the format string "%*s", the precision +argument was used without checking if it was present first. + +11. fmt-overflow: The buffer used for OFMT/CONVFMT conversions was written +to with sprintf(), which meant that some conversions could write past the +end. + diff --git a/bugs-fixed/fmt-overflow.awk b/bugs-fixed/fmt-overflow.awk new file mode 100644 index 0000000..bf5877e --- /dev/null +++ b/bugs-fixed/fmt-overflow.awk @@ -0,0 +1 @@ +BEGIN { OFMT = "%.1000f"; print 1.25; } diff --git a/bugs-fixed/fmt-overflow.ok b/bugs-fixed/fmt-overflow.ok new file mode 100644 index 0000000..5f7449e --- /dev/null +++ b/bugs-fixed/fmt-overflow.ok @@ -0,0 +1 @@ +1.2500000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 diff --git a/lex.c b/lex.c index d09f550..ad8e878 100644 --- a/lex.c +++ b/lex.c @@ -198,6 +198,7 @@ int yylex(void) yylval.i = c; switch (c) { case '\n': /* {EOL} */ + lineno++; RET(NL); case '\r': /* assume \n is coming */ case ' ': /* {WS}+ */ @@ -213,6 +214,7 @@ int yylex(void) case '\\': if (peek() == '\n') { input(); + lineno++; } else if (peek() == '\r') { input(); input(); /* \n */ lineno++; @@ -370,10 +372,11 @@ int string(void) case '\n': case '\r': case 0: + *bp = '\0'; SYNTAX( "non-terminated string %.10s...", buf ); - lineno++; if (c == 0) /* hopeless */ FATAL( "giving up" ); + lineno++; break; case '\\': c = input(); @@ -515,6 +518,7 @@ int regexpr(void) if (!adjbuf(&buf, &bufsz, bp-buf+3, 500, &bp, "regexpr")) FATAL("out of space for reg expr %.10s...", buf); if (c == '\n') { + *bp = '\0'; SYNTAX( "newline in regular expression %.10s...", buf ); unput('\n'); break; @@ -553,19 +557,19 @@ int input(void) /* get next lexical input character */ lexprog++; } else /* awk -f ... */ c = pgetc(); - if (c == '\n') - lineno++; - else if (c == EOF) + if (c == EOF) c = 0; if (ep >= ebuf + sizeof ebuf) ep = ebuf; - return *ep++ = c; + *ep = c; + if (c != 0) { + ep++; + } + return (c); } void unput(int c) /* put lexical character back on input */ { - if (c == '\n') - lineno--; if (yysptr >= yysbuf + sizeof(yysbuf)) FATAL("pushed back too much: %.20s...", yysbuf); *yysptr++ = c; diff --git a/lib.c b/lib.c index ba6ebd4..247ec9a 100644 --- a/lib.c +++ b/lib.c @@ -59,7 +59,7 @@ void recinit(unsigned int n) { if ( (record = (char *) malloc(n)) == NULL || (fields = (char *) malloc(n+1)) == NULL - || (fldtab = (Cell **) malloc((nfields+1) * sizeof(Cell *))) == NULL + || (fldtab = (Cell **) malloc((nfields+2) * sizeof(Cell *))) == NULL || (fldtab[0] = (Cell *) malloc(sizeof(Cell))) == NULL ) FATAL("out of space for $0 and fields"); *fldtab[0] = dollar0; diff --git a/main.c b/main.c index a183c45..1c38a1e 100644 --- a/main.c +++ b/main.c @@ -88,7 +88,7 @@ int main(int argc, char *argv[]) exit(0); break; } - if (strncmp(argv[1], "--", 2) == 0) { /* explicit end of args */ + if (strcmp(argv[1], "--") == 0) { /* explicit end of args */ argc--; argv++; break; diff --git a/tran.c b/tran.c index 72ca6ff..6775b01 100644 --- a/tran.c +++ b/tran.c @@ -395,7 +395,7 @@ Awkfloat getfval(Cell *vp) /* get float val of a Cell */ static char *get_str_val(Cell *vp, char **fmt) /* get string val of a Cell */ { - char s[100]; /* BUG: unchecked */ + char s[256]; double dtemp; if ((vp->tval & (NUM | STR)) == 0) @@ -434,9 +434,9 @@ static char *get_str_val(Cell *vp, char **fmt) /* get string val of a Cel if (freeable(vp)) \ xfree(vp->sval); \ if (modf(vp->fval, &dtemp) == 0) /* it's integral */ \ - sprintf(s, "%.30g", vp->fval); \ + snprintf(s, sizeof (s), "%.30g", vp->fval); \ else \ - sprintf(s, *fmt, vp->fval); \ + snprintf(s, sizeof (s), *fmt, vp->fval); \ vp->sval = tostring(s); \ vp->tval &= ~DONTFREE; \ vp->tval |= STR; \