1 files changed, 173 insertions, 0 deletions
diff --git a/net/http/http_util.h b/net/http/http_util.h
new file mode 100644
index 0000000..f7802a7
--- /dev/null
+++ b/net/http/http_util.h
@@ -0,0 +1,173 @@
+// Copyright 2008, 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.
+
+#ifndef NET_HTTP_HTTP_UTIL_H_
+#define NET_HTTP_HTTP_UTIL_H_
+
+#include "base/string_tokenizer.h"
+
+// This is a macro to support extending this string literal at compile time.
+// Please excuse me polluting your global namespace!
+#define HTTP_LWS " \t"
+
+namespace net {
+
+class HttpUtil {
+ public:
+  // Locates the next occurance of delimiter in line, skipping over quoted
+  // strings (e.g., commas will not be treated as delimiters if they appear
+  // within a quoted string).  Returns the offset of the found delimiter or
+  // line.size() if no delimiter was found.
+  static size_t FindDelimiter(const std::string& line,
+                              size_t search_start,
+                              char delimiter);
+
+  // Parses the value of a Content-Type header.  The resulting mime_type and
+  // charset values are normalized to lowercase.  The mime_type and charset
+  // output values are only modified if the content_type_str contains a mime
+  // type and charset value, respectively.
+  static void ParseContentType(const std::string& content_type_str,
+                               std::string* mime_type,
+                               std::string* charset,
+                               bool *had_charset);
+
+  // Scans the '\r\n'-delimited headers for the given header name.  Returns
+  // true if a match is found.  Input is assumed to be well-formed.
+  // TODO(darin): kill this
+  static bool HasHeader(const std::string& headers, const char* name);
+
+  // Multiple occurances of some headers cannot be coalesced into a comma-
+  // separated list since their values are (or contain) unquoted HTTP-date
+  // values, which may contain a comma (see RFC 2616 section 3.3.1).
+  static bool IsNonCoalescingHeader(std::string::const_iterator name_begin,
+                                    std::string::const_iterator name_end);
+  static bool IsNonCoalescingHeader(const std::string& name) {
+    return IsNonCoalescingHeader(name.begin(), name.end());
+  }
+
+  // Trim HTTP_LWS chars from the beginning and end of the string.
+  static void TrimLWS(std::string::const_iterator* begin,
+                      std::string::const_iterator* end);
+
+  // Returns index beyond the end-of-headers marker or -1 if not found.  RFC
+  // 2616 defines the end-of-headers marker as a double CRLF; however, some
+  // servers only send back LFs (e.g., Unix-based CGI scripts written using the
+  // ASIS Apache module).  This function therefore accepts the pattern LF[CR]LF
+  // as end-of-headers (just like Mozilla).
+  static int LocateEndOfHeaders(const char* buf, int buf_len);
+
+  // Assemble "raw headers" in the format required by HttpResponseHeaders.
+  // This involves normalizing line terminators, converting [CR]LF to \0 and
+  // handling HTTP line continuations (i.e., lines starting with LWS are
+  // continuations of the previous line).  |buf_len| indicates the position of
+  // the end-of-headers marker as defined by LocateEndOfHeaders.
+  static std::string AssembleRawHeaders(const char* buf, int buf_len);
+
+  // Used to iterate over the name/value pairs of HTTP headers.  To iterate
+  // over the values in a multi-value header, use ValuesIterator.
+  class HeadersIterator {
+   public:
+    HeadersIterator(std::string::const_iterator headers_begin,
+                    std::string::const_iterator headers_end,
+                    const std::string& line_delimiter);
+
+    // Advances the iterator to the next header, if any.  Returns true if there
+    // is a next header.  Use name* and values* methods to access the resultant
+    // header name and values.
+    bool GetNext();
+
+    std::string::const_iterator name_begin() const {
+      return name_begin_;
+    }
+    std::string::const_iterator name_end() const {
+      return name_end_;
+    }
+    std::string name() const {
+      return std::string(name_begin_, name_end_);
+    }
+
+    std::string::const_iterator values_begin() const {
+      return values_begin_;
+    }
+    std::string::const_iterator values_end() const {
+      return values_end_;
+    }
+    std::string values() const {
+      return std::string(values_begin_, values_end_);
+    }
+
+   private:
+    StringTokenizer lines_;
+    std::string::const_iterator name_begin_;
+    std::string::const_iterator name_end_;
+    std::string::const_iterator values_begin_;
+    std::string::const_iterator values_end_;
+  };
+
+  // Used to iterate over deliminated values in a HTTP header.  HTTP LWS is
+  // automatically trimmed from the resulting values.
+  //
+  // When using this class to iterate over response header values, beware that
+  // for some headers (e.g., Last-Modified), commas are not used as delimiters.
+  // This iterator should be avoided for headers like that which are considered
+  // non-coalescing (see IsNonCoalescingHeader).
+  //
+  // This iterator is careful to skip over delimiters found inside an HTTP
+  // quoted string.
+  //
+  class ValuesIterator {
+   public:
+    ValuesIterator(std::string::const_iterator values_begin,
+                   std::string::const_iterator values_end,
+                   char delimiter);
+
+    // Advances the iterator to the next value, if any.  Returns true if there
+    // is a next value.  Use value* methods to access the resultant value.
+    bool GetNext();
+
+    std::string::const_iterator value_begin() const {
+      return value_begin_;
+    }
+    std::string::const_iterator value_end() const {
+      return value_end_;
+    }
+    std::string value() const {
+      return std::string(value_begin_, value_end_);
+    }
+
+   private:
+    StringTokenizer values_;
+    std::string::const_iterator value_begin_;
+    std::string::const_iterator value_end_;
+  };
+};
+
+}  // namespace net
+
+#endif  // NET_HTTP_HTTP_UTIL_H_