--- orig/coreutils-7.2/src/sort.c 2009-03-29 13:44:10.000000000 -0400 +++ coreutils-7.2/src/sort.c 2009-04-25 04:46:06.000000000 -0400 @@ -176,6 +176,8 @@ bool random; /* Sort by random hash of key. */ bool general_numeric; /* Flag for general, numeric comparison. Handle numbers in exponential notation. */ + bool human_numeric; /* Flag for sorting by human readable + units with either SI or IEC prefixes */ bool month; /* Flag for comparison by month name. */ bool reverse; /* Reverse the sense of comparison. */ bool version; /* sort by version number */ @@ -336,6 +338,10 @@ -i, --ignore-nonprinting consider only printable characters\n\ -M, --month-sort compare (unknown) < `JAN' < ... < `DEC'\n\ "), stdout); + fputs(_("\ + -h, --human-numeric-sort compare string numerical values ending in units\n\ + prefixed with either SI xor IEC prefixes\n\ +"), stdout); fputs (_("\ -n, --numeric-sort compare according to string numerical value\n\ -R, --random-sort sort by random hash of keys\n\ @@ -426,7 +432,7 @@ SORT_OPTION }; -static char const short_options[] = "-bcCdfgik:mMno:rRsS:t:T:uVy:z"; +static char const short_options[] = "-bcCdfghik:mMno:rRsS:t:T:uVy:z"; static struct option const long_options[] = { @@ -442,6 +448,7 @@ {"merge", no_argument, NULL, 'm'}, {"month-sort", no_argument, NULL, 'M'}, {"numeric-sort", no_argument, NULL, 'n'}, + {"human-numeric-sort", no_argument, NULL, 'h'}, {"version-sort", no_argument, NULL, 'V'}, {"random-sort", no_argument, NULL, 'R'}, {"random-source", required_argument, NULL, RANDOM_SOURCE_OPTION}, @@ -1673,6 +1680,57 @@ return strnumcmp (a, b, decimal_point, thousands_sep); } +/* error if a mixture of SI and IEC units used. */ +static void +check_mixed_SI_IEC (char prefix) +{ + static int seen_si = -1; + bool si_present = prefix == 'i'; + if (seen_si != -1 && seen_si != si_present) + error (SORT_FAILURE, 0, _("Both SI and IEC prefixes present on units")); + seen_si = si_present; +} + +/* Compare numbers ending in units with SI xor IEC prefixes + < K < M < G < T < P < E < Z < Y + Assume that numbers are properly abbreviated. + i.e. input will never have 5000K instead of 5M +*/ +static int +human_compare(const char *a, const char *b) +{ + static const char weights [UCHAR_LIM] = { + ['K']=1, ['M']=2, ['G']=3, ['T']=4, ['P']=5, ['E']=6, ['Z']=7, ['Y']=8, + ['k']=1, + }; + + while (blanks[to_uchar (*a)]) + a++; + while (blanks[to_uchar (*b)]) + b++; + + const char *ar = a; + const char *br = b; + + while( ISDIGIT (*ar) || (*ar) == decimal_point || (*ar) == thousands_sep ) + ar++; + while( ISDIGIT (*br) || (*br) == decimal_point || (*br) == thousands_sep ) + br++; + + if( *ar ) + check_mixed_SI_IEC (*(ar+1)); + + if( *br ) + check_mixed_SI_IEC (*(br+1)); + + int aw = weights[to_uchar (*ar)]; + int bw = weights[to_uchar (*br)]; + + return (aw > bw ? 1 + : aw < bw ? -1 + : strnumcmp ( a , b , decimal_point , thousands_sep)); +} + static int general_numcompare (const char *sa, const char *sb) { @@ -1917,13 +1975,14 @@ if (key->random) diff = compare_random (texta, lena, textb, lenb); - else if (key->numeric | key->general_numeric) + else if (key->numeric | key->general_numeric | key->human_numeric) { char savea = *lima, saveb = *limb; *lima = *limb = '\0'; - diff = ((key->numeric ? numcompare : general_numcompare) - (texta, textb)); + diff = ((key->numeric ? numcompare + : key->general_numeric ? general_numcompare + : human_compare) (texta, textb)); *lima = savea, *limb = saveb; } else if (key->version) @@ -2887,7 +2946,7 @@ for (key = keylist; key; key = key->next) if ((1 < (key->random + key->numeric + key->general_numeric + key->month - + key->version + !!key->ignore)) + + key->version + (!!key->ignore) + key->human_numeric)) || (key->random && key->translate)) { /* The following is too big, but guaranteed to be "big enough". */ @@ -2899,6 +2958,8 @@ *p++ = 'f'; if (key->general_numeric) *p++ = 'g'; + if (key->human_numeric) + *p++ = 'h'; if (key->ignore == nonprinting) *p++ = 'i'; if (key->month) @@ -2990,6 +3051,9 @@ case 'g': key->general_numeric = true; break; + case 'h': + key->human_numeric = true; + break; case 'i': /* Option order should not matter, so don't let -i override -d. -d implies -i, but -i does not imply -d. */ @@ -3138,7 +3202,8 @@ gkey.sword = gkey.eword = SIZE_MAX; gkey.ignore = NULL; gkey.translate = NULL; - gkey.numeric = gkey.general_numeric = gkey.random = gkey.version = false; + gkey.numeric = gkey.general_numeric = gkey.human_numeric = false; + gkey.random = gkey.version = false; gkey.month = gkey.reverse = false; gkey.skipsblanks = gkey.skipeblanks = false; @@ -3217,6 +3282,7 @@ case 'd': case 'f': case 'g': + case 'h': case 'i': case 'M': case 'n': @@ -3469,6 +3535,7 @@ | key->numeric | key->version | key->general_numeric + | key->human_numeric | key->random))) { key->ignore = gkey.ignore; @@ -3478,6 +3545,7 @@ key->month = gkey.month; key->numeric = gkey.numeric; key->general_numeric = gkey.general_numeric; + key->human_numeric = gkey.human_numeric; key->random = gkey.random; key->reverse = gkey.reverse; key->version = gkey.version; @@ -3493,6 +3561,7 @@ | gkey.month | gkey.numeric | gkey.general_numeric + | gkey.human_numeric | gkey.random | gkey.version))) {