1 /*

     2  * Copyright (c) 2004, Oracle and/or its affiliates. All rights reserved.

     3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

     4  *

     5  * This code is free software; you can redistribute it and/or modify it

     6  * under the terms of the GNU General Public License version 2 only, as

     7  * published by the Free Software Foundation.  Oracle designates this

     8  * particular file as subject to the "Classpath" exception as provided

     9  * by Oracle in the LICENSE file that accompanied this code.

    10  *

    11  * This code is distributed in the hope that it will be useful, but WITHOUT

    12  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

    13  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

    14  * version 2 for more details (a copy is included in the LICENSE file that

    15  * accompanied this code).

    16  *

    17  * You should have received a copy of the GNU General Public License version

    18  * 2 along with this work; if not, write to the Free Software Foundation,

    19  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

    20  *

    21  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

    22  * or visit www.oracle.com if you need additional information or have any

    23  * questions.

    24  */

    25 

    26 #include <stdio.h>

    27 #include <string.h>

    28 #include "jni.h"

    29 

    30 #ifndef max

    31 #define max(a,b) ( (a>b) ? a : b )

    32 #endif

    33 #ifndef min

    34 #define min(a,b) ( (a<b) ? a : b )

    35 #endif

    36 

    37 /*

    38  * Validates that a URI path component does not contain any illegal characters

    39  * - ported from src/share/classes/java/net/URI.java

    40  */

    41 

    42 static jlong L_HEX;

    43 static jlong H_HEX;

    44 static jlong L_PATH;

    45 static jlong H_PATH;

    46 

    47 /* Compute the low-order mask for the characters in the given string */

    48 static jlong lowMask(char* s) {

    49     size_t n = strlen(s);

    50     jlong m = 0;

    51     size_t i;

    52     for (i = 0; i < n; i++) {

    53         int c = (int)s[i];

    54         if (c < 64)

    55             m |= ((jlong)1 << c);

    56     }

    57     return m;

    58 }

    59 

    60 /* Compute the high-order mask for the characters in the given string */

    61 static jlong highMask(char* s) {

    62     size_t n = strlen(s);

    63     jlong m = 0;

    64     size_t i;

    65     for (i = 0; i < n; i++) {

    66         int c = (int)s[i];

    67         if ((c >= 64) && (c < 128))

    68             m |= ((jlong)1 << (c - 64));

    69     }

    70     return m;

    71 }

    72 

    73 /*

    74  * Compute a low-order mask for the characters

    75  * between first and last, inclusive

    76  */

    77 static jlong lowMaskRange(char first, char last) {

    78     jlong m = 0;

    79     int f = max(min(first, 63), 0);

    80     int l = max(min(last, 63), 0);

    81     int i;

    82 

    83     for (i = f; i <= l; i++)  {

    84         m |= (jlong)1 << i;

    85     }

    86     return m;

    87 }

    88 

    89 /*

    90  * Compute a high-order mask for the characters

    91  * between first and last, inclusive

    92  */

    93 static jlong highMaskRange(char first, char last) {

    94     jlong m = 0;

    95     int f = max(min(first, 127), 64) - 64;

    96     int l = max(min(last, 127), 64) - 64;

    97     int i;

    98     for (i = f; i <= l; i++) {

    99         m |= (jlong)1 << i;

   100     }

   101     return m;

   102 }

   103 

   104 /*

   105  * Tell whether the given character is permitted by the given mask pair

   106  */

   107 static int match(int c, jlong lowMask, jlong highMask) {

   108     if (c >= 0 && c < 64)

   109         if ((((jlong)1 << c) & lowMask) != 0) return 1;

   110     if (c >= 64 && c < 128)

   111         if ((((jlong)1 << (c - 64)) & highMask) != 0) return 1;

   112     return 0;

   113 }

   114 

   115 static void initialize() {

   116     // digit    = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" |

   117     //            "8" | "9"

   118     jlong L_DIGIT = lowMaskRange('0', '9');

   119     jlong H_DIGIT = 0;

   120 

   121     // upalpha  = "A" | "B" | "C" | "D" | "E" | "F" | "G" | "H" | "I" |

   122     //            "J" | "K" | "L" | "M" | "N" | "O" | "P" | "Q" | "R" |

   123     //            "S" | "T" | "U" | "V" | "W" | "X" | "Y" | "Z"

   124     jlong L_UPALPHA = 0;

   125     jlong H_UPALPHA = highMaskRange('A', 'Z');

   126 

   127     // lowalpha = "a" | "b" | "c" | "d" | "e" | "f" | "g" | "h" | "i" |

   128     //            "j" | "k" | "l" | "m" | "n" | "o" | "p" | "q" | "r" |

   129     //            "s" | "t" | "u" | "v" | "w" | "x" | "y" | "z"

   130     jlong L_LOWALPHA = 0;

   131     jlong H_LOWALPHA = highMaskRange('a', 'z');

   132 

   133     // alpha         = lowalpha | upalpha

   134     jlong L_ALPHA = L_LOWALPHA | L_UPALPHA;

   135     jlong H_ALPHA = H_LOWALPHA | H_UPALPHA;

   136 

   137     // alphanum      = alpha | digit

   138     jlong L_ALPHANUM = L_DIGIT | L_ALPHA;

   139     jlong H_ALPHANUM = H_DIGIT | H_ALPHA;

   140 

   141     // mark          = "-" | "_" | "." | "!" | "~" | "*" | "'" |

   142     //                 "(" | ")"

   143     jlong L_MARK = lowMask("-_.!~*'()");

   144     jlong H_MARK = highMask("-_.!~*'()");

   145 

   146     // unreserved    = alphanum | mark

   147     jlong L_UNRESERVED = L_ALPHANUM | L_MARK;

   148     jlong H_UNRESERVED = H_ALPHANUM | H_MARK;

   149 

   150     // pchar         = unreserved |

   151     //                 ":" | "@" | "&" | "=" | "+" | "$" | ","

   152     jlong L_PCHAR = L_UNRESERVED | lowMask(":@&=+$,");

   153     jlong H_PCHAR = H_UNRESERVED | highMask(":@&=+$,");

   154 

   155     // hex           = digit | "A" | "B" | "C" | "D" | "E" | "F" |

   156     //                         "a" | "b" | "c" | "d" | "e" | "f"

   157     L_HEX = L_DIGIT;

   158     H_HEX = highMaskRange('A', 'F') | highMaskRange('a', 'f');

   159 

   160     // All valid path characters

   161     L_PATH = L_PCHAR | lowMask(";/");

   162     H_PATH = H_PCHAR | highMask(";/");

   163 }

   164 

   165 

   166 /*

   167  * Validates that the given URI path component does not contain any

   168  * illegal characters. Returns 0 if only validate characters are present.

   169  */

   170 int validatePathChars(const char* path) {

   171     size_t i, n;

   172 

   173     /* initialize on first usage */

   174     if (L_HEX == 0) {

   175         initialize();

   176     }

   177 

   178     i=0;

   179     n = strlen(path);

   180     while (i < n) {

   181         int c = (int)(signed char)path[i];

   182 

   183         /* definitely not us-ascii */

   184         if (c < 0) return -1;

   185 

   186         /* start of an escapted character */

   187         if (c == '%') {

   188             if (i + 3 <= n) {

   189                 int h1 = (int)(signed char)path[i+1];

   190                 int h2 = (int)(signed char)path[i+2];

   191                 if (h1 < 0 || h2 < 0) return -1;

   192                 if (!match(h1, L_HEX, H_HEX)) return -1;

   193                 if (!match(h2, L_HEX, H_HEX)) return -1;

   194                 i += 3;

   195             } else {

   196                /* malformed escape pair */

   197                return -1;

   198             }

   199         } else {

   200             if (!match(c, L_PATH, H_PATH)) return -1;

   201             i++;

   202         }

   203     }

   204 

   205     return 0;

   206 }