diff options
Diffstat (limited to 'googleurl/url_canon_pathurl.cpp')
-rw-r--r-- | googleurl/url_canon_pathurl.cpp | 130 |
1 files changed, 130 insertions, 0 deletions
diff --git a/googleurl/url_canon_pathurl.cpp b/googleurl/url_canon_pathurl.cpp new file mode 100644 index 0000000..74b5721 --- /dev/null +++ b/googleurl/url_canon_pathurl.cpp @@ -0,0 +1,130 @@ +// Copyright 2007, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +// Functions for canonicalizing "path" URLs. Not to be confused with the path +// of a URL, these are URLs that have no authority section, only a path. For +// example, "javascript:" and "data:". + +#include "url_canon.h" +#include "url_canon_internal.h" + +namespace url_canon { + +namespace { + +template<typename CHAR, typename UCHAR> +bool DoCanonicalizePathURL(const URLComponentSource<CHAR>& source, + const url_parse::Parsed& parsed, + CanonOutput* output, + url_parse::Parsed* new_parsed) { + // Scheme: this will append the colon. + bool success = CanonicalizeScheme(source.scheme, parsed.scheme, + output, &new_parsed->scheme); + + // We assume there's no authority for path URLs. Note that hosts should never + // have -1 length. + new_parsed->username.reset(); + new_parsed->password.reset(); + new_parsed->host.reset(); + new_parsed->port.reset(); + + if (parsed.path.is_valid()) { + // Copy the path using path URL's more lax escaping rules (think for + // javascript:). We convert to UTF-8 and escape non-ASCII, but leave all + // ASCII characters alone. This helps readability of JavaStript. + new_parsed->path.begin = output->length(); + int end = parsed.path.end(); + for (int i = parsed.path.begin; i < end; i++) { + UCHAR uch = static_cast<UCHAR>(source.path[i]); + if (uch < 0x20 || uch >= 0x80) + success &= AppendUTF8EscapedChar(source.path, &i, end, output); + else + output->push_back(static_cast<char>(uch)); + } + new_parsed->path.len = output->length() - new_parsed->path.begin; + } else { + // Empty path. + new_parsed->path.reset(); + } + + // Assume there's no query or ref. + new_parsed->query.reset(); + new_parsed->ref.reset(); + + return success; +} + +} // namespace + +bool CanonicalizePathURL(const char* spec, + int spec_len, + const url_parse::Parsed& parsed, + CanonOutput* output, + url_parse::Parsed* new_parsed) { + (void)spec_len; + return DoCanonicalizePathURL<char, unsigned char>( + URLComponentSource<char>(spec), parsed, output, new_parsed); +} + +bool CanonicalizePathURL(const char16* spec, + int spec_len, + const url_parse::Parsed& parsed, + CanonOutput* output, + url_parse::Parsed* new_parsed) { + (void)spec_len; + return DoCanonicalizePathURL<char16, char16>( + URLComponentSource<char16>(spec), parsed, output, new_parsed); +} + +bool ReplacePathURL(const char* base, + const url_parse::Parsed& base_parsed, + const Replacements<char>& replacements, + CanonOutput* output, + url_parse::Parsed* new_parsed) { + URLComponentSource<char> source(base); + url_parse::Parsed parsed(base_parsed); + SetupOverrideComponents(base, replacements, &source, &parsed); + return DoCanonicalizePathURL<char, unsigned char>( + source, parsed, output, new_parsed); +} + +bool ReplacePathURL(const char* base, + const url_parse::Parsed& base_parsed, + const Replacements<char16>& replacements, + CanonOutput* output, + url_parse::Parsed* new_parsed) { + RawCanonOutput<1024> utf8; + URLComponentSource<char> source(base); + url_parse::Parsed parsed(base_parsed); + SetupUTF16OverrideComponents(base, replacements, &utf8, &source, &parsed); + return DoCanonicalizePathURL<char, unsigned char>( + source, parsed, output, new_parsed); +} + +} // namespace url_canon |