Share link header parsing code between blink and content.

net/http/http_util.cc

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 // The rules for parsing content-types were borrowed from Firefox:
 // http://lxr.mozilla.org/mozilla/source/netwerk/base/src/nsURLHelper.cpp#834
 
 #include "net/http/http_util.h"
 
 #include <algorithm>
@@ skipping 427 matching lines @@
   while (*begin < *end && IsLWS((*end)[-1]))
     --(*end);
 }
 
 bool HttpUtil::IsQuote(char c) {
   // Single quote mark isn't actually part of quoted-text production,
   // but apparently some servers rely on this.
   return c == '"' || c == '\'';
 }
 
+namespace {
+bool IsTokenChar(unsigned char c) {
+  return !(c >= 0x80 || c <= 0x1F || c == 0x7F || c == '(' || c == ')' ||
+           c == '<' || c == '>' || c == '@' || c == ',' || c == ';' ||
+           c == ':' || c == '\\' || c == '"' || c == '/' || c == '[' ||
+           c == ']' || c == '?' || c == '=' || c == '{' || c == '}' ||
+           c == ' ' || c == '\t');
+}
+}  // anonymous namespace
+
 // See RFC 2616 Sec 2.2 for the definition of |token|.
 bool HttpUtil::IsToken(std::string::const_iterator begin,
                        std::string::const_iterator end) {
   if (begin == end)
     return false;
   for (std::string::const_iterator iter = begin; iter != end; ++iter) {
-    unsigned char c = *iter;
-    if (c >= 0x80 || c <= 0x1F || c == 0x7F ||
-        c == '(' || c == ')' || c == '<' || c == '>' || c == '@' ||
-        c == ',' || c == ';' || c == ':' || c == '\\' || c == '"' ||
-        c == '/' || c == '[' || c == ']' || c == '?' || c == '=' ||
-        c == '{' || c == '}' || c == ' ' || c == '\t')
+    if (!IsTokenChar(*iter))
       return false;
   }
   return true;
 }
 
-std::string HttpUtil::Unquote(std::string::const_iterator begin,
-                              std::string::const_iterator end) {
+// See RFC 5987 Sec 3.2.1 for the definition of |parmname|.
+bool HttpUtil::IsParmName(std::string::const_iterator begin,
+                          std::string::const_iterator end) {
+  if (begin == end)
+    return false;
+  for (std::string::const_iterator iter = begin; iter != end; ++iter) {
+    unsigned char c = *iter;
+    if (!IsTokenChar(c) || c == '*' || c == '\'' || c == '%')
+      return false;
+  }
+  return true;
+}
+
+namespace {
+bool UnquoteImpl(std::string::const_iterator begin,
+                 std::string::const_iterator end,
+                 bool strict_quotes,
+                 std::string* out) {
   // Empty string
   if (begin == end)
-    return std::string();
+    return false;
 
   // Nothing to unquote.
-  if (!IsQuote(*begin))
-    return std::string(begin, end);
+  if (!HttpUtil::IsQuote(*begin))
+    return false;
+
+  // Anything other than double quotes in strict mode.
+  if (strict_quotes && *begin != '"')
+    return false;
 
   // No terminal quote mark.
   if (end - begin < 2 || *begin != *(end - 1))
-    return std::string(begin, end);
+    return false;
+
+  char quote = *begin;
 
   // Strip quotemarks
   ++begin;
   --end;
 
   // Unescape quoted-pair (defined in RFC 2616 section 2.2)
+  bool prev_escape = false;
   std::string unescaped;
-  bool prev_escape = false;
   for (; begin != end; ++begin) {
     char c = *begin;
     if (c == '\\' && !prev_escape) {
       prev_escape = true;
       continue;
     }
+    if (strict_quotes && !prev_escape && c == quote)
+      return false;
     prev_escape = false;
     unescaped.push_back(c);
   }
-  return unescaped;
+
+  // Terminal quote is escaped.
+  if (strict_quotes && prev_escape)
+    return false;
+
+  *out = std::move(unescaped);
+  return true;
+}
+}  // anonymous namespace
+
+std::string HttpUtil::Unquote(std::string::const_iterator begin,
+                              std::string::const_iterator end) {
+  std::string result;
+  if (!UnquoteImpl(begin, end, false, &result))
+    return std::string(begin, end);
+
+  return result;
 }
 
 // static
 std::string HttpUtil::Unquote(const std::string& str) {
   return Unquote(str.begin(), str.end());
 }
 
 // static
+bool HttpUtil::StrictUnquote(std::string::const_iterator begin,
+                             std::string::const_iterator end,
+                             std::string* out) {
+  return UnquoteImpl(begin, end, true, out);
+}
+
+// static
+bool HttpUtil::StrictUnquote(const std::string& str, std::string* out) {
+  return StrictUnquote(str.begin(), str.end(), out);
+}
+
+// static
 std::string HttpUtil::Quote(const std::string& str) {
   std::string escaped;
   escaped.reserve(2 + str.size());
 
   std::string::const_iterator begin = str.begin();
   std::string::const_iterator end = str.end();
 
   // Esape any backslashes or quotemarks within the string, and
   // then surround with quotes.
   escaped.push_back('"');
@@ skipping 389 matching lines @@
     if (value_begin_ != value_end_)
       return true;
   }
   return false;
 }
 
 HttpUtil::NameValuePairsIterator::NameValuePairsIterator(
     std::string::const_iterator begin,
     std::string::const_iterator end,
     char delimiter,
-    OptionalValues optional_values)
+    Values optional_values,
+    Quotes strict_quotes)
     : props_(begin, end, delimiter),
       valid_(true),
       name_begin_(end),
       name_end_(end),
       value_begin_(end),
       value_end_(end),
       value_is_quoted_(false),
-      values_optional_(optional_values == VALUES_OPTIONAL) {}
+      values_optional_(optional_values == Values::NOT_REQUIRED),
+      strict_quotes_(strict_quotes == Quotes::STRICT_QUOTES) {
+  if (strict_quotes_)
+    props_.set_quote_chars("\"");
+}
 
 HttpUtil::NameValuePairsIterator::NameValuePairsIterator(
     std::string::const_iterator begin,
     std::string::const_iterator end,
     char delimiter)
-    : NameValuePairsIterator(begin, end, delimiter, VALUES_NOT_OPTIONAL) {}
+    : NameValuePairsIterator(begin,
+                             end,
+                             delimiter,
+                             Values::REQUIRED,
+                             Quotes::NOT_STRICT) {}
 
 HttpUtil::NameValuePairsIterator::NameValuePairsIterator(
     const NameValuePairsIterator& other) = default;
 
 HttpUtil::NameValuePairsIterator::~NameValuePairsIterator() {}
 
 // We expect properties to be formatted as one of:
 //   name="value"
 //   name='value'
 //   name='\'value\''
@@ skipping 15 matching lines @@
   // Scan for the equals sign.
   std::string::const_iterator equals = std::find(value_begin_, value_end_, '=');
   if (equals == value_begin_)
     return valid_ = false;  // Malformed, no name
   if (equals == value_end_ && !values_optional_)
     return valid_ = false;  // Malformed, no equals sign and values are required
 
   // If an equals sign was found, verify that it wasn't inside of quote marks.
   if (equals != value_end_) {
     for (std::string::const_iterator it = value_begin_; it != equals; ++it) {
-      if (HttpUtil::IsQuote(*it))
+      if (IsQuote(*it))
         return valid_ = false;  // Malformed, quote appears before equals sign
     }
   }
 
   name_begin_ = value_begin_;
   name_end_ = equals;
   value_begin_ = (equals == value_end_) ? value_end_ : equals + 1;
 
   TrimLWS(&name_begin_, &name_end_);
   TrimLWS(&value_begin_, &value_end_);
   value_is_quoted_ = false;
   unquoted_value_.clear();
 
   if (equals != value_end_ && value_begin_ == value_end_) {
     // Malformed; value is empty
     return valid_ = false;
   }
 
-  if (value_begin_ != value_end_ && HttpUtil::IsQuote(*value_begin_)) {
+  if (value_begin_ != value_end_ && IsQuote(*value_begin_)) {
+    value_is_quoted_ = true;
+
+    if (strict_quotes_) {
+      if (!HttpUtil::StrictUnquote(value_begin_, value_end_, &unquoted_value_))
+        return valid_ = false;
+      return true;
+    }
+
     // Trim surrounding quotemarks off the value
     if (*value_begin_ != *(value_end_ - 1) || value_begin_ + 1 == value_end_) {
       // NOTE: This is not as graceful as it sounds:
       // * quoted-pairs will no longer be unquoted
       //   (["\"hello] should give ["hello]).
       // * Does not detect when the final quote is escaped
       //   (["value\"] should give [value"])
+      value_is_quoted_ = false;
       ++value_begin_;  // Gracefully recover from mismatching quotes.
     } else {
-      value_is_quoted_ = true;
       // Do not store iterators into this. See declaration of unquoted_value_.
       unquoted_value_ = HttpUtil::Unquote(value_begin_, value_end_);
     }
   }
 
   return true;
 }
 
+bool HttpUtil::NameValuePairsIterator::IsQuote(char c) const {
+  if (strict_quotes_)
+    return c == '"';
+  return HttpUtil::IsQuote(c);
+}
+
 }  // namespace net