[email protected] | e7bba5f8 | 2013-04-10 20:10:52 | [diff] [blame^] | 1 | // Copyright 2007, Google Inc. |
| 2 | // All rights reserved. |
| 3 | // |
| 4 | // Redistribution and use in source and binary forms, with or without |
| 5 | // modification, are permitted provided that the following conditions are |
| 6 | // met: |
| 7 | // |
| 8 | // * Redistributions of source code must retain the above copyright |
| 9 | // notice, this list of conditions and the following disclaimer. |
| 10 | // * Redistributions in binary form must reproduce the above |
| 11 | // copyright notice, this list of conditions and the following disclaimer |
| 12 | // in the documentation and/or other materials provided with the |
| 13 | // distribution. |
| 14 | // * Neither the name of Google Inc. nor the names of its |
| 15 | // contributors may be used to endorse or promote products derived from |
| 16 | // this software without specific prior written permission. |
| 17 | // |
| 18 | // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 19 | // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 20 | // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 21 | // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 22 | // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 23 | // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 24 | // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 25 | // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 26 | // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 27 | // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 28 | // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 29 | |
| 30 | // Contains common inline helper functions used by the URL parsing routines. |
| 31 | |
| 32 | #ifndef GOOGLEURL_SRC_URL_PARSE_INTERNAL_H__ |
| 33 | #define GOOGLEURL_SRC_URL_PARSE_INTERNAL_H__ |
| 34 | |
| 35 | #include "googleurl/src/url_parse.h" |
| 36 | |
| 37 | namespace url_parse { |
| 38 | |
| 39 | // We treat slashes and backslashes the same for IE compatability. |
| 40 | inline bool IsURLSlash(char16 ch) { |
| 41 | return ch == '/' || ch == '\\'; |
| 42 | } |
| 43 | |
| 44 | // Returns true if we should trim this character from the URL because it is a |
| 45 | // space or a control character. |
| 46 | inline bool ShouldTrimFromURL(char16 ch) { |
| 47 | return ch <= ' '; |
| 48 | } |
| 49 | |
| 50 | // Given an already-initialized begin index and length, this shrinks the range |
| 51 | // to eliminate "should-be-trimmed" characters. Note that the length does *not* |
| 52 | // indicate the length of untrimmed data from |*begin|, but rather the position |
| 53 | // in the input string (so the string starts at character |*begin| in the spec, |
| 54 | // and goes until |*len|). |
| 55 | template<typename CHAR> |
| 56 | inline void TrimURL(const CHAR* spec, int* begin, int* len) { |
| 57 | // Strip leading whitespace and control characters. |
| 58 | while (*begin < *len && ShouldTrimFromURL(spec[*begin])) |
| 59 | (*begin)++; |
| 60 | |
| 61 | // Strip trailing whitespace and control characters. We need the >i test for |
| 62 | // when the input string is all blanks; we don't want to back past the input. |
| 63 | while (*len > *begin && ShouldTrimFromURL(spec[*len - 1])) |
| 64 | (*len)--; |
| 65 | } |
| 66 | |
| 67 | // Counts the number of consecutive slashes starting at the given offset |
| 68 | // in the given string of the given length. |
| 69 | template<typename CHAR> |
| 70 | inline int CountConsecutiveSlashes(const CHAR *str, |
| 71 | int begin_offset, int str_len) { |
| 72 | int count = 0; |
| 73 | while (begin_offset + count < str_len && |
| 74 | IsURLSlash(str[begin_offset + count])) |
| 75 | ++count; |
| 76 | return count; |
| 77 | } |
| 78 | |
| 79 | // Internal functions in url_parse.cc that parse the path, that is, everything |
| 80 | // following the authority section. The input is the range of everything |
| 81 | // following the authority section, and the output is the identified ranges. |
| 82 | // |
| 83 | // This is designed for the file URL parser or other consumers who may do |
| 84 | // special stuff at the beginning, but want regular path parsing, it just |
| 85 | // maps to the internal parsing function for paths. |
| 86 | void ParsePathInternal(const char* spec, |
| 87 | const Component& path, |
| 88 | Component* filepath, |
| 89 | Component* query, |
| 90 | Component* ref); |
| 91 | void ParsePathInternal(const char16* spec, |
| 92 | const Component& path, |
| 93 | Component* filepath, |
| 94 | Component* query, |
| 95 | Component* ref); |
| 96 | |
| 97 | |
| 98 | // Given a spec and a pointer to the character after the colon following the |
| 99 | // scheme, this parses it and fills in the structure, Every item in the parsed |
| 100 | // structure is filled EXCEPT for the scheme, which is untouched. |
| 101 | void ParseAfterScheme(const char* spec, |
| 102 | int spec_len, |
| 103 | int after_scheme, |
| 104 | Parsed* parsed); |
| 105 | void ParseAfterScheme(const char16* spec, |
| 106 | int spec_len, |
| 107 | int after_scheme, |
| 108 | Parsed* parsed); |
| 109 | |
| 110 | } // namespace url_parse |
| 111 | |
| 112 | #endif // GOOGLEURL_SRC_URL_PARSE_INTERNAL_H__ |