|
| 1 | +/* Compare strings while treating digits characters numerically. |
| 2 | + Copyright (C) 1997, 2002, 2005 Free Software Foundation, Inc. |
| 3 | + This file is part of the libiberty library. |
| 4 | + Contributed by Jean-François Bignolles <bignolle@ecoledoc.ibp.fr>, 1997. |
| 5 | +
|
| 6 | + Libiberty is free software; you can redistribute it and/or |
| 7 | + modify it under the terms of the GNU Lesser General Public |
| 8 | + License as published by the Free Software Foundation; either |
| 9 | + version 2.1 of the License, or (at your option) any later version. |
| 10 | +
|
| 11 | + Libiberty is distributed in the hope that it will be useful, |
| 12 | + but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 13 | + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 14 | + Lesser General Public License for more details. |
| 15 | +
|
| 16 | + You should have received a copy of the GNU Lesser General Public |
| 17 | + License along with the GNU C Library; if not, write to the Free |
| 18 | + Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA |
| 19 | + 02110-1301 USA. */ |
| 20 | + |
| 21 | +/* #include "libiberty.h" */ |
| 22 | +/* #include "safe-ctype.h" */ |
| 23 | +#include <ctype.h> |
| 24 | + |
| 25 | +/* |
| 26 | +@deftypefun int strverscmp (const char *@var{s1}, const char *@var{s2}) |
| 27 | +The @code{strverscmp} function compares the string @var{s1} against |
| 28 | +@var{s2}, considering them as holding indices/version numbers. Return |
| 29 | +value follows the same conventions as found in the @code{strverscmp} |
| 30 | +function. In fact, if @var{s1} and @var{s2} contain no digits, |
| 31 | +@code{strverscmp} behaves like @code{strcmp}. |
| 32 | +
|
| 33 | +Basically, we compare strings normally (character by character), until |
| 34 | +we find a digit in each string - then we enter a special comparison |
| 35 | +mode, where each sequence of digits is taken as a whole. If we reach the |
| 36 | +end of these two parts without noticing a difference, we return to the |
| 37 | +standard comparison mode. There are two types of numeric parts: |
| 38 | +"integral" and "fractional" (those begin with a '0'). The types |
| 39 | +of the numeric parts affect the way we sort them: |
| 40 | +
|
| 41 | +@itemize @bullet |
| 42 | +@item |
| 43 | +integral/integral: we compare values as you would expect. |
| 44 | +
|
| 45 | +@item |
| 46 | +fractional/integral: the fractional part is less than the integral one. |
| 47 | +Again, no surprise. |
| 48 | +
|
| 49 | +@item |
| 50 | +fractional/fractional: the things become a bit more complex. |
| 51 | +If the common prefix contains only leading zeroes, the longest part is less |
| 52 | +than the other one; else the comparison behaves normally. |
| 53 | +@end itemize |
| 54 | +
|
| 55 | +@smallexample |
| 56 | +strverscmp ("no digit", "no digit") |
| 57 | + @result{} 0 // @r{same behavior as strcmp.} |
| 58 | +strverscmp ("item#99", "item#100") |
| 59 | + @result{} <0 // @r{same prefix, but 99 < 100.} |
| 60 | +strverscmp ("alpha1", "alpha001") |
| 61 | + @result{} >0 // @r{fractional part inferior to integral one.} |
| 62 | +strverscmp ("part1_f012", "part1_f01") |
| 63 | + @result{} >0 // @r{two fractional parts.} |
| 64 | +strverscmp ("foo.009", "foo.0") |
| 65 | + @result{} <0 // @r{idem, but with leading zeroes only.} |
| 66 | +@end smallexample |
| 67 | +
|
| 68 | +This function is especially useful when dealing with filename sorting, |
| 69 | +because filenames frequently hold indices/version numbers. |
| 70 | +@end deftypefun |
| 71 | +
|
| 72 | +*/ |
| 73 | + |
| 74 | +/* states: S_N: normal, S_I: comparing integral part, S_F: comparing |
| 75 | + fractional parts, S_Z: idem but with leading Zeroes only */ |
| 76 | +#define S_N 0x0 |
| 77 | +#define S_I 0x4 |
| 78 | +#define S_F 0x8 |
| 79 | +#define S_Z 0xC |
| 80 | + |
| 81 | +/* result_type: CMP: return diff; LEN: compare using len_diff/diff */ |
| 82 | +#define CMP 2 |
| 83 | +#define LEN 3 |
| 84 | + |
| 85 | + |
| 86 | +/* Compare S1 and S2 as strings holding indices/version numbers, |
| 87 | + returning less than, equal to or greater than zero if S1 is less than, |
| 88 | + equal to or greater than S2 (for more info, see the Glibc texinfo doc). */ |
| 89 | + |
| 90 | +int |
| 91 | +strverscmp (const char *s1, const char *s2) |
| 92 | +{ |
| 93 | + const unsigned char *p1 = (const unsigned char *) s1; |
| 94 | + const unsigned char *p2 = (const unsigned char *) s2; |
| 95 | + unsigned char c1, c2; |
| 96 | + int state; |
| 97 | + int diff; |
| 98 | + |
| 99 | + /* Symbol(s) 0 [1-9] others (padding) |
| 100 | + Transition (10) 0 (01) d (00) x (11) - */ |
| 101 | + static const unsigned int next_state[] = |
| 102 | + { |
| 103 | + /* state x d 0 - */ |
| 104 | + /* S_N */ S_N, S_I, S_Z, S_N, |
| 105 | + /* S_I */ S_N, S_I, S_I, S_I, |
| 106 | + /* S_F */ S_N, S_F, S_F, S_F, |
| 107 | + /* S_Z */ S_N, S_F, S_Z, S_Z |
| 108 | + }; |
| 109 | + |
| 110 | + static const int result_type[] = |
| 111 | + { |
| 112 | + /* state x/x x/d x/0 x/- d/x d/d d/0 d/- |
| 113 | + 0/x 0/d 0/0 0/- -/x -/d -/0 -/- */ |
| 114 | + |
| 115 | + /* S_N */ CMP, CMP, CMP, CMP, CMP, LEN, CMP, CMP, |
| 116 | + CMP, CMP, CMP, CMP, CMP, CMP, CMP, CMP, |
| 117 | + /* S_I */ CMP, -1, -1, CMP, +1, LEN, LEN, CMP, |
| 118 | + +1, LEN, LEN, CMP, CMP, CMP, CMP, CMP, |
| 119 | + /* S_F */ CMP, CMP, CMP, CMP, CMP, LEN, CMP, CMP, |
| 120 | + CMP, CMP, CMP, CMP, CMP, CMP, CMP, CMP, |
| 121 | + /* S_Z */ CMP, +1, +1, CMP, -1, CMP, CMP, CMP, |
| 122 | + -1, CMP, CMP, CMP |
| 123 | + }; |
| 124 | + |
| 125 | + if (p1 == p2) |
| 126 | + return 0; |
| 127 | + |
| 128 | + c1 = *p1++; |
| 129 | + c2 = *p2++; |
| 130 | + /* Hint: '0' is a digit too. */ |
| 131 | + state = S_N | ((c1 == '0') + (isdigit (c1) != 0)); |
| 132 | + |
| 133 | + while ((diff = c1 - c2) == 0 && c1 != '\0') |
| 134 | + { |
| 135 | + state = next_state[state]; |
| 136 | + c1 = *p1++; |
| 137 | + c2 = *p2++; |
| 138 | + state |= (c1 == '0') + (isdigit (c1) != 0); |
| 139 | + } |
| 140 | + |
| 141 | + state = result_type[state << 2 | (((c2 == '0') + (isdigit (c2) != 0)))]; |
| 142 | + |
| 143 | + switch (state) |
| 144 | + { |
| 145 | + case CMP: |
| 146 | + return diff; |
| 147 | + |
| 148 | + case LEN: |
| 149 | + while (isdigit (*p1++)) |
| 150 | + if (!isdigit (*p2++)) |
| 151 | + return 1; |
| 152 | + |
| 153 | + return isdigit (*p2) ? -1 : diff; |
| 154 | + |
| 155 | + default: |
| 156 | + return state; |
| 157 | + } |
| 158 | +} |
0 commit comments