From 9b383bd6cf96e1fe21c41528dec1f3ed508f335b Mon Sep 17 00:00:00 2001 From: matz Date: Fri, 9 Jun 2006 21:20:17 +0000 Subject: * sprintf.c (rb_str_format): allow %c to print one character string (e.g. ?x). * lib/tempfile.rb (Tempfile::make_tmpname): put dot between basename and pid. [ruby-talk:196272] * parse.y (do_block): remove -> style block. * parse.y (parser_yylex): remove tLAMBDA_ARG. * eval.c (rb_call0): binding for the return event hook should have consistent scope. [ruby-core:07928] * eval.c (proc_invoke): return behavior should depend whether it is surrounded by a lambda or a mere block. * eval.c (formal_assign): handles post splat arguments. * eval.c (rb_call0): ditto. * st.c (strhash): use FNV-1a hash. * parse.y (parser_yylex): removed experimental ';;' terminator. * eval.c (rb_node_arity): should be aware of post splat arguments. * eval.c (rb_proc_arity): ditto. * parse.y (f_args): syntax rule enhanced to support arguments after the splat. * parse.y (block_param): ditto for block parameters. * parse.y (f_post_arg): mandatory formal arguments after the splat argument. * parse.y (new_args_gen): generate nodes for mandatory formal arguments after the splat argument. * eval.c (rb_eval): dispatch mandatory formal arguments after the splat argument. * parse.y (args): allow more than one splat in the argument list. * parse.y (method_call): allow aref [] to accept all kind of method argument, including assocs, splat, and block argument. * eval.c (SETUP_ARGS0): prepare block argument as well. * lib/mathn.rb (Integer): remove Integer#gcd2. [ruby-core:07931] * eval.c (error_line): print receivers true/false/nil specially. * eval.c (rb_proc_yield): handles parameters in yield semantics. * eval.c (nil_yield): gives LocalJumpError to denote no block error. * io.c (rb_io_getc): now takes one-character string. * string.c (rb_str_hash): use FNV-1a hash from Fowler/Noll/Vo hashing algorithm. * string.c (rb_str_aref): str[0] now returns 1 character string, instead of a fixnum. [Ruby2] * parse.y (parser_yylex): ?c now returns 1 character string, instead of a fixnum. [Ruby2] * string.c (rb_str_aset): no longer support fixnum insertion. * eval.c (umethod_bind): should not update original class. [ruby-dev:28636] * eval.c (ev_const_get): should support constant access from within instance_eval(). [ruby-dev:28327] * time.c (time_timeval): should round for usec floating number. [ruby-core:07896] * time.c (time_add): ditto. * dir.c (sys_warning): should not call a vararg function rb_sys_warning() indirectly. [ruby-core:07886] * numeric.c (flo_divmod): the first element of Float#divmod should be an integer. [ruby-dev:28589] * test/ruby/test_float.rb: add tests for divmod, div, modulo and remainder. * re.c (rb_reg_initialize): should not allow modifying literal regexps. frozen check moved from rb_reg_initialize_m as well. * re.c (rb_reg_initialize): should not modify untainted objects in safe levels higher than 3. * re.c (rb_memcmp): type change from char* to const void*. * dir.c (dir_close): should not close untainted dir stream. * dir.c (GetDIR): add tainted/frozen check for each dir operation. * lib/rdoc/parsers/parse_rb.rb (RDoc::RubyParser::parse_symbol_arg): typo fixed. a patch from Florian Gross . * eval.c (EXEC_EVENT_HOOK): trace_func may remove itself from event_hooks. no guarantee for arbitrary hook deletion. [ruby-dev:28632] * util.c (ruby_strtod): differ addition to minimize error. [ruby-dev:28619] * util.c (ruby_strtod): should not raise ERANGE when the input string does not have any digits. [ruby-dev:28629] * eval.c (proc_invoke): should restore old ruby_frame->block. thanks to ts . [ruby-core:07833] also fix [ruby-dev:28614] as well. * signal.c (trap): sig should be less then NSIG. Coverity found this bug. a patch from Kevin Tew . [ruby-core:07823] * math.c (math_log2): add new method inspired by [ruby-talk:191237]. * math.c (math_log): add optional base argument to Math::log(). [ruby-talk:191308] * ext/syck/emitter.c (syck_scan_scalar): avoid accessing uninitialized array element. a patch from Pat Eyler . [ruby-core:07809] * array.c (rb_ary_fill): initialize local variables first. a patch from Pat Eyler . [ruby-core:07810] * ext/syck/yaml2byte.c (syck_yaml2byte_handler): need to free type_tag. a patch from Pat Eyler . [ruby-core:07808] * ext/socket/socket.c (make_hostent_internal): accept ai_family check from Sam Roberts . [ruby-core:07691] * util.c (ruby_strtod): should not cut off 18 digits for no reason. [ruby-core:07796] * array.c (rb_ary_fill): internalize local variable "beg" to pacify Coverity. [ruby-core:07770] * pack.c (pack_unpack): now supports CRLF newlines. a patch from . [ruby-dev:28601] * applied code clean-up patch from Stefan Huehner . [ruby-core:07764] * lib/jcode.rb (String::tr_s): should have translated non squeezing character sequence (i.e. a character) as well. thanks to Hiroshi Ichikawa [ruby-list:42090] * ext/socket/socket.c: document update patch from Sam Roberts . [ruby-core:07701] * lib/mathn.rb (Integer): need not to remove gcd2. a patch from NARUSE, Yui . [ruby-dev:28570] * parse.y (arg): too much NEW_LIST() * eval.c (SETUP_ARGS0): remove unnecessary access to nd_alen. * eval.c (rb_eval): use ARGSCAT for NODE_OP_ASGN1. [ruby-dev:28585] * parse.y (arg): use NODE_ARGSCAT for placeholder. * lib/getoptlong.rb (GetoptLong::get): RDoc update patch from mathew . [ruby-core:07738] * variable.c (rb_const_set): raise error when no target klass is supplied. [ruby-dev:28582] * prec.c (prec_prec_f): documentation patch from . [ruby-core:07689] * bignum.c (rb_big_pow): second operand may be too big even if it's a Fixnum. [ruby-talk:187984] * README.EXT: update symbol description. [ruby-talk:188104] * COPYING: explicitly note GPLv2. [ruby-talk:187922] * parse.y: remove some obsolete syntax rules (unparenthesized method calls in argument list). * eval.c (rb_call0): insecure calling should be checked for non NODE_SCOPE method invocations too. * eval.c (rb_alias): should preserve the current safe level as well as method definition. * process.c (rb_f_sleep): remove RDoc description about SIGALRM which is not valid on the current implementation. [ruby-dev:28464] Thu Mar 23 21:40:47 2006 K.Kosako * eval.c (method_missing): should support argument splat in super. a bug in combination of super, splat and method_missing. [ruby-talk:185438] * configure.in: Solaris SunPro compiler -rapth patch from . [ruby-dev:28443] * configure.in: remove enable_rpath=no for Solaris. [ruby-dev:28440] * ext/win32ole/win32ole.c (ole_val2olevariantdata): change behavior of converting OLE Variant object with VT_ARRAY|VT_UI1 and Ruby String object. * ruby.1: a clarification patch from David Lutterkort . [ruby-core:7508] * lib/rdoc/ri/ri_paths.rb (RI::Paths): adding paths from rubygems directories. a patch from Eric Hodel . [ruby-core:07423] * eval.c (rb_clear_cache_by_class): clearing wrong cache. * ext/extmk.rb: use :remove_destination to install extension libraries to avoid SEGV. [ruby-dev:28417] * eval.c (rb_thread_fd_writable): should not re-schedule output from KILLED thread (must be error printing). * array.c (rb_ary_flatten_bang): allow specifying recursion level. [ruby-talk:182170] * array.c (rb_ary_flatten): ditto. * gc.c (add_heap): a heap_slots may overflow. a patch from Stefan Weil . * eval.c (rb_call): use separate cache for fcall/vcall invocation. * eval.c (rb_eval): NODE_FCALL, NODE_VCALL can call local functions. * eval.c (rb_mod_local): a new method to specify newly added visibility "local". * eval.c (search_method): search for local methods which are visible only from the current class. * class.c (rb_class_local_methods): a method to list local methods. * object.c (Init_Object): add BasicObject class as a top level BlankSlate class. * ruby.h (SYM2ID): should not cast to signed long. [ruby-core:07414] * class.c (rb_include_module): allow module duplication. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10235 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- string.c | 164 ++++++++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 114 insertions(+), 50 deletions(-) (limited to 'string.c') diff --git a/string.c b/string.c index 46bc40662b..871fd9a70d 100644 --- a/string.c +++ b/string.c @@ -765,39 +765,103 @@ rb_str_concat(VALUE str1, VALUE str2) return str1; } +/* + * hash_32 - 32 bit Fowler/Noll/Vo FNV-1a hash code + * + * @(#) $Revision$ + * @(#) $Id$ + * @(#) $Source$ + * + *** + * + * Fowler/Noll/Vo hash + * + * The basis of this hash algorithm was taken from an idea sent + * as reviewer comments to the IEEE POSIX P1003.2 committee by: + * + * Phong Vo (http://www.research.att.com/info/kpv/) + * Glenn Fowler (http://www.research.att.com/~gsf/) + * + * In a subsequent ballot round: + * + * Landon Curt Noll (http://www.isthe.com/chongo/) + * + * improved on their algorithm. Some people tried this hash + * and found that it worked rather well. In an EMail message + * to Landon, they named it the ``Fowler/Noll/Vo'' or FNV hash. + * + * FNV hashes are designed to be fast while maintaining a low + * collision rate. The FNV speed allows one to quickly hash lots + * of data while maintaining a reasonable collision rate. See: + * + * http://www.isthe.com/chongo/tech/comp/fnv/index.html + * + * for more details as well as other forms of the FNV hash. + *** + * + * To use the recommended 32 bit FNV-1a hash, pass FNV1_32A_INIT as the + * Fnv32_t hashval argument to fnv_32a_buf() or fnv_32a_str(). + * + *** + * + * Please do not copyright this code. This code is in the public domain. + * + * LANDON CURT NOLL DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO + * EVENT SHALL LANDON CURT NOLL BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THIS SOFTWARE. + * + * By: + * chongo /\oo/\ + * http://www.isthe.com/chongo/ + * + * Share and Enjoy! :-) + */ + +/* + * 32 bit FNV-1 and FNV-1a non-zero initial basis + * + * The FNV-1 initial basis is the FNV-0 hash of the following 32 octets: + * + * chongo /\../\ + * + * NOTE: The \'s above are not back-slashing escape characters. + * They are literal ASCII backslash 0x5c characters. + * + * NOTE: The FNV-1a initial basis is the same value as FNV-1 by definition. + */ +#define FNV1_32A_INIT 0x811c9dc5 + +/* + * 32 bit magic FNV-1a prime + */ +#define FNV_32_PRIME 0x01000193 + int rb_str_hash(VALUE str) { register long len = RSTRING(str)->len; register char *p = RSTRING(str)->ptr; - register int key = 0; - -#ifdef HASH_ELFHASH - register unsigned int g; + register int hval = FNV1_32A_INIT; + /* + * FNV-1a hash each octet in the buffer + */ while (len--) { - key = (key << 4) + *p++; - if (g = key & 0xF0000000) - key ^= g >> 24; - key &= ~g; - } -#elif HASH_PERL - while (len--) { - key += *p++; - key += (key << 10); - key ^= (key >> 6); - } - key += (key << 3); - key ^= (key >> 11); - key += (key << 15); + /* xor the bottom with the current octet */ + hval ^= (int)*p++; + + /* multiply by the 32 bit FNV magic prime mod 2^32 */ +#if defined(FNV_GCC_OPTIMIZATION) + hval += (hval<<1) + (hval<<4) + (hval<<7) + (hval<<8) + (hval<<24); #else - while (len--) { - key = key*65599 + *p; - p++; - } - key = key + (key>>5); + hval *= FNV_32_PRIME; #endif - return key; + } + return hval; } /* @@ -810,8 +874,8 @@ rb_str_hash(VALUE str) static VALUE rb_str_hash_m(VALUE str) { - int key = rb_str_hash(str); - return INT2FIX(key); + int hval = rb_str_hash(str); + return INT2FIX(hval); } #define lesser(a,b) (((a)>(b))?(b):(a)) @@ -1414,13 +1478,7 @@ rb_str_aref(VALUE str, VALUE indx) idx = FIX2LONG(indx); num_index: - if (idx < 0) { - idx = RSTRING(str)->len + idx; - } - if (idx < 0 || RSTRING(str)->len <= idx) { - return Qnil; - } - return INT2FIX(RSTRING(str)->ptr[idx] & 0xff); + return rb_str_substr(str, idx, 1); case T_REGEXP: return rb_str_subpat(str, indx, 0); @@ -1456,21 +1514,21 @@ rb_str_aref(VALUE str, VALUE indx) /* * call-seq: - * str[fixnum] => fixnum or nil + * str[fixnum] => new_str or nil * str[fixnum, fixnum] => new_str or nil * str[range] => new_str or nil * str[regexp] => new_str or nil * str[regexp, fixnum] => new_str or nil * str[other_str] => new_str or nil - * str.slice(fixnum) => fixnum or nil + * str.slice(fixnum) => new_str or nil * str.slice(fixnum, fixnum) => new_str or nil * str.slice(range) => new_str or nil * str.slice(regexp) => new_str or nil * str.slice(regexp, fixnum) => new_str or nil * str.slice(other_str) => new_str or nil * - * Element Reference---If passed a single Fixnum, returns the code - * of the character at that position. If passed two Fixnum + * Element Reference---If passed a single Fixnum, returns a + * substring of one character at that position. If passed two Fixnum * objects, returns a substring starting at the offset given by the first, and * a length given by the second. If given a range, a substring containing * characters at offsets given by the range is returned. In all three cases, if @@ -1486,7 +1544,7 @@ rb_str_aref(VALUE str, VALUE indx) * match. * * a = "hello there" - * a[1] #=> 101 + * a[1] #=> "e" * a[1,3] #=> "ell" * a[1..3] #=> "ell" * a[-3,2] #=> "er" @@ -1615,17 +1673,7 @@ rb_str_aset(VALUE str, VALUE indx, VALUE val) goto out_of_range; idx += RSTRING(str)->len; } - if (FIXNUM_P(val)) { - rb_str_modify(str); - if (RSTRING(str)->len == idx) { - RSTRING(str)->len += 1; - RESIZE_CAPA(str, RSTRING(str)->len); - } - RSTRING(str)->ptr[idx] = FIX2INT(val) & 0xff; - } - else { - rb_str_splice(str, idx, 1, val); - } + rb_str_splice(str, idx, 1, val); return val; case T_REGEXP: @@ -1656,7 +1704,6 @@ rb_str_aset(VALUE str, VALUE indx, VALUE val) /* * call-seq: - * str[fixnum] = fixnum * str[fixnum] = new_str * str[fixnum, fixnum] = new_str * str[range] = aString @@ -2158,6 +2205,22 @@ rb_str_clear(VALUE str) return str; } +/* + * call-seq: + * string.chr -> string + * + * Returns a one-character string at the beginning of the string. + * + * a = "abcde" + * a.chr #=> "a" + */ + +static VALUE +rb_str_chr(VALUE str) +{ + return rb_str_substr(str, 0, 1); +} + /* * call-seq: * str.reverse! => str @@ -4217,6 +4280,7 @@ Init_String(void) rb_define_method(rb_cString, "rindex", rb_str_rindex_m, -1); rb_define_method(rb_cString, "replace", rb_str_replace, 1); rb_define_method(rb_cString, "clear", rb_str_clear, 0); + rb_define_method(rb_cString, "chr", rb_str_chr, 0); rb_define_method(rb_cString, "to_i", rb_str_to_i, -1); rb_define_method(rb_cString, "to_f", rb_str_to_f, 0); -- cgit v1.2.3