diff options
| -rw-r--r-- | dquote_static.c | 108 | ||||
| -rw-r--r-- | embed.fnc | 8 | ||||
| -rw-r--r-- | embed.h | 4 | ||||
| -rw-r--r-- | proto.h | 14 | ||||
| -rw-r--r-- | regcomp.c | 22 | ||||
| -rw-r--r-- | toke.c | 10 |
6 files changed, 77 insertions, 89 deletions
diff --git a/dquote_static.c b/dquote_static.c index 5cc890b13c..fa8e354246 100644 --- a/dquote_static.c +++ b/dquote_static.c @@ -85,31 +85,30 @@ S_grok_bslash_c(pTHX_ const char source, const bool utf8, const bool output_warn } STATIC bool -S_grok_bslash_o(pTHX_ const char *s, - UV *uv, - STRLEN *len, - const char** error_msg, - const bool output_warning) +S_grok_bslash_o(pTHX_ char **s, UV *uv, const char** error_msg, + const bool output_warning) { /* Documentation to be supplied when interface nailed down finally * This returns FALSE if there is an error which the caller need not recover * from; , otherwise TRUE. In either case the caller should look at *len * On input: - * s points to a string that begins with 'o', and the previous character - * was a backslash. + * s is the address of a pointer to a NULL terminated string that begins + * with 'o', and the previous character was a backslash. At exit, *s + * will be advanced to the byte just after those absorbed by this + * function. Hence the caller can continue parsing from there. In + * the case of an error, this routine has generally positioned *s to + * point just to the right of the first bad spot, so that a message + * that has a "<--" to mark the spot will be correctly positioned. * uv points to a UV that will hold the output value, valid only if the * return from the function is TRUE - * len on success will point to the next character in the string past the - * end of this construct. - * on failure, it will point to the failure * error_msg is a pointer that will be set to an internal buffer giving an * error message upon failure (the return is FALSE). Untouched if * function succeeds * output_warning says whether to output any warning messages, or suppress * them */ - const char* e; + char* e; STRLEN numbers_len; I32 flags = PERL_SCAN_ALLOW_UNDERSCORES | PERL_SCAN_DISALLOW_PREFIX @@ -120,75 +119,74 @@ S_grok_bslash_o(pTHX_ const char *s, PERL_ARGS_ASSERT_GROK_BSLASH_O; - assert(*s == 'o'); - s++; + assert(**s == 'o'); + (*s)++; - if (*s != '{') { - *len = 1; /* Move past the o */ + if (**s != '{') { *error_msg = "Missing braces on \\o{}"; return FALSE; } - e = strchr(s, '}'); + e = strchr(*s, '}'); if (!e) { - *len = 2; /* Move past the o{ */ - *error_msg = "Missing right brace on \\o{"; + (*s)++; /* Move past the '{' */ + *error_msg = "Missing right brace on \\o{"; return FALSE; } - /* Return past the '}' no matter what is inside the braces */ - *len = e - s + 2; /* 2 = 1 for the 'o' + 1 for the '}' */ - - s++; /* Point to first digit */ - - numbers_len = e - s; + (*s)++; /* Point to expected first digit (could be first byte of utf8 + sequence if not a digit) */ + numbers_len = e - *s; if (numbers_len == 0) { + (*s)++; /* Move past the } */ *error_msg = "Number with no digits"; return FALSE; } - *uv = grok_oct(s, &numbers_len, &flags, NULL); + *uv = grok_oct(*s, &numbers_len, &flags, NULL); /* Note that if has non-octal, will ignore everything starting with that up * to the '}' */ - if (output_warning && numbers_len != (STRLEN) (e - s)) { + if (output_warning && numbers_len != (STRLEN) (e - *s)) { Perl_ck_warner(aTHX_ packWARN(WARN_DIGIT), /* diag_listed_as: Non-octal character '%c'. Resolved as "%s" */ "Non-octal character '%c'. Resolved as \"\\o{%.*s}\"", - *(s + numbers_len), + *(*s + numbers_len), (int) numbers_len, - s); + *s); } + /* Return past the '}' */ + *s = e + 1; + return TRUE; } PERL_STATIC_INLINE bool -S_grok_bslash_x(pTHX_ const char *s, - UV *uv, - STRLEN *len, - const char** error_msg, - const bool output_warning) +S_grok_bslash_x(pTHX_ char **s, UV *uv, const char** error_msg, + const bool output_warning) { /* Documentation to be supplied when interface nailed down finally * This returns FALSE if there is an error which the caller need not recover * from; , otherwise TRUE. In either case the caller should look at *len * On input: - * s points to a string that begins with 'x', and the previous character - * was a backslash. + * s is the address of a pointer to a NULL terminated string that begins + * with 'x', and the previous character was a backslash. At exit, *s + * will be advanced to the byte just after those absorbed by this + * function. Hence the caller can continue parsing from there. In + * the case of an error, this routine has generally positioned *s to + * point just to the right of the first bad spot, so that a message + * that has a "<--" to mark the spot will be correctly positioned. * uv points to a UV that will hold the output value, valid only if the * return from the function is TRUE - * len on success will point to the next character in the string past the - * end of this construct. - * on failure, it will point to the failure * error_msg is a pointer that will be set to an internal buffer giving an * error message upon failure (the return is FALSE). Untouched if * function succeeds * output_warning says whether to output any warning messages, or suppress * them */ - const char* e; + char* e; STRLEN numbers_len; I32 flags = PERL_SCAN_ALLOW_UNDERSCORES | PERL_SCAN_DISALLOW_PREFIX; @@ -197,20 +195,20 @@ S_grok_bslash_x(pTHX_ const char *s, PERL_UNUSED_ARG(output_warning); - assert(*s == 'x'); - s++; + assert(**s == 'x'); + (*s)++; - if (*s != '{') { - I32 flags = PERL_SCAN_DISALLOW_PREFIX; - *len = 2; - *uv = grok_hex(s, len, &flags, NULL); - (*len)++; + if (**s != '{') { + I32 flags = PERL_SCAN_DISALLOW_PREFIX; + STRLEN len = 2; + *uv = grok_hex(*s, &len, &flags, NULL); + *s += len; return TRUE; } - e = strchr(s, '}'); + e = strchr(*s, '}'); if (!e) { - *len = 2; /* Move past the 'x{' */ + (*s)++; /* Move past the '{' */ /* XXX The corresponding message above for \o is just '\\o{'; other * messages for other constructs include the '}', so are inconsistent. */ @@ -218,16 +216,16 @@ S_grok_bslash_x(pTHX_ const char *s, return FALSE; } - /* Return past the '}' no matter what is inside the braces */ - *len = e - s + 2; /* 2 = 1 for the 'x' + 1 for the '}' */ - - s++; /* Point to first digit */ - - numbers_len = e - s; - *uv = grok_hex(s, &numbers_len, &flags, NULL); + (*s)++; /* Point to expected first digit (could be first byte of utf8 + sequence if not a digit) */ + numbers_len = e - *s; + *uv = grok_hex(*s, &numbers_len, &flags, NULL); /* Note that if has non-hex, will ignore everything starting with that up * to the '}' */ + /* Return past the '}' */ + *s = e + 1; + return TRUE; } @@ -736,8 +736,12 @@ ApdR |I32 |looks_like_number|NN SV *const sv Apd |UV |grok_bin |NN const char* start|NN STRLEN* len_p|NN I32* flags|NULLOK NV *result #if defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_TOKE_C) EMsR |char |grok_bslash_c |const char source|const bool utf8|const bool output_warning -EMsR |bool |grok_bslash_o |NN const char* s|NN UV* uv|NN STRLEN* len|NN const char** error_msg|const bool output_warning -EMiR |bool |grok_bslash_x |NN const char* s|NN UV* uv|NN STRLEN* len|NN const char** error_msg|const bool output_warning +EMsR |bool |grok_bslash_o |NN char** s|NN UV* uv \ + |NN const char** error_msg \ + |const bool output_warning +EMiR |bool |grok_bslash_x |NN char** s|NN UV* uv \ + |NN const char** error_msg \ + |const bool output_warning #endif Apd |UV |grok_hex |NN const char* start|NN STRLEN* len_p|NN I32* flags|NULLOK NV *result Apd |int |grok_number |NN const char *pv|STRLEN len|NULLOK UV *valuep @@ -959,8 +959,8 @@ # endif # if defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_TOKE_C) #define grok_bslash_c(a,b,c) S_grok_bslash_c(aTHX_ a,b,c) -#define grok_bslash_o(a,b,c,d,e) S_grok_bslash_o(aTHX_ a,b,c,d,e) -#define grok_bslash_x(a,b,c,d,e) S_grok_bslash_x(aTHX_ a,b,c,d,e) +#define grok_bslash_o(a,b,c,d) S_grok_bslash_o(aTHX_ a,b,c,d) +#define grok_bslash_x(a,b,c,d) S_grok_bslash_x(aTHX_ a,b,c,d) #define regcurly(a) S_regcurly(aTHX_ a) # endif # if defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_UTF8_C) @@ -6756,23 +6756,21 @@ PERL_CALLCONV SV* Perl__core_swash_init(pTHX_ const char* pkg, const char* name, STATIC char S_grok_bslash_c(pTHX_ const char source, const bool utf8, const bool output_warning) __attribute__warn_unused_result__; -STATIC bool S_grok_bslash_o(pTHX_ const char* s, UV* uv, STRLEN* len, const char** error_msg, const bool output_warning) +STATIC bool S_grok_bslash_o(pTHX_ char** s, UV* uv, const char** error_msg, const bool output_warning) __attribute__warn_unused_result__ __attribute__nonnull__(pTHX_1) __attribute__nonnull__(pTHX_2) - __attribute__nonnull__(pTHX_3) - __attribute__nonnull__(pTHX_4); + __attribute__nonnull__(pTHX_3); #define PERL_ARGS_ASSERT_GROK_BSLASH_O \ - assert(s); assert(uv); assert(len); assert(error_msg) + assert(s); assert(uv); assert(error_msg) -PERL_STATIC_INLINE bool S_grok_bslash_x(pTHX_ const char* s, UV* uv, STRLEN* len, const char** error_msg, const bool output_warning) +PERL_STATIC_INLINE bool S_grok_bslash_x(pTHX_ char** s, UV* uv, const char** error_msg, const bool output_warning) __attribute__warn_unused_result__ __attribute__nonnull__(pTHX_1) __attribute__nonnull__(pTHX_2) - __attribute__nonnull__(pTHX_3) - __attribute__nonnull__(pTHX_4); + __attribute__nonnull__(pTHX_3); #define PERL_ARGS_ASSERT_GROK_BSLASH_X \ - assert(s); assert(uv); assert(len); assert(error_msg) + assert(s); assert(uv); assert(error_msg) PERL_STATIC_INLINE I32 S_regcurly(pTHX_ const char *s) __attribute__warn_unused_result__ @@ -10612,16 +10612,13 @@ tryagain: break; case 'o': { - STRLEN brace_len = len; UV result; const char* error_msg; - bool valid = grok_bslash_o(p, + bool valid = grok_bslash_o(&p, &result, - &brace_len, &error_msg, - 1); - p += brace_len; + TRUE); /* out warnings */ if (! valid) { RExC_parse = p; /* going to die anyway; point to exact spot of failure */ @@ -10641,16 +10638,13 @@ tryagain: } case 'x': { - STRLEN brace_len = len; UV result; const char* error_msg; - bool valid = grok_bslash_x(p, + bool valid = grok_bslash_x(&p, &result, - &brace_len, &error_msg, - 1); - p += brace_len; + TRUE); /* out warnings */ if (! valid) { RExC_parse = p; /* going to die anyway; point to exact spot of failure */ @@ -11571,12 +11565,10 @@ parseit: RExC_parse--; /* function expects to be pointed at the 'o' */ { const char* error_msg; - bool valid = grok_bslash_o(RExC_parse, + bool valid = grok_bslash_o(&RExC_parse, &value, - &numlen, &error_msg, SIZE_ONLY); - RExC_parse += numlen; if (! valid) { vFAIL(error_msg); } @@ -11589,12 +11581,10 @@ parseit: RExC_parse--; /* function expects to be pointed at the 'x' */ { const char* error_msg; - bool valid = grok_bslash_x(RExC_parse, + bool valid = grok_bslash_x(&RExC_parse, &value, - &numlen, &error_msg, 1); - RExC_parse += numlen; if (! valid) { vFAIL(error_msg); } @@ -3287,11 +3287,10 @@ S_scan_const(pTHX_ char *start) /* eg. \o{24} indicates the octal constant \024 */ case 'o': { - STRLEN len; const char* error; - bool valid = grok_bslash_o(s, &uv, &len, &error, 1); - s += len; + bool valid = grok_bslash_o(&s, &uv, &error, + TRUE); /* Output warning */ if (! valid) { yyerror(error); continue; @@ -3302,11 +3301,10 @@ S_scan_const(pTHX_ char *start) /* eg. \x24 indicates the hex constant 0x24 */ case 'x': { - STRLEN len; const char* error; - bool valid = grok_bslash_x(s, &uv, &len, &error, 1); - s += len; + bool valid = grok_bslash_x(&s, &uv, &error, + TRUE); /* Output warning */ if (! valid) { yyerror(error); continue; |