Add UMA for measuring Content-Dispostion header use and abuse.

content/browser/download/download_stats.cc

Index: content/browser/download/download_stats.cc
diff --git a/content/browser/download/download_stats.cc b/content/browser/download/download_stats.cc
index 2da505a27a00e85e61d46f28f4c2995e71b8d3ce..52f90a1bdb82d51391b7f703b394480af5faad6e 100644
--- a/content/browser/download/download_stats.cc
+++ b/content/browser/download/download_stats.cc
@@ -8,9 +8,12 @@
 #include "base/string_util.h"
 #include "content/browser/download/download_resource_handler.h"
 #include "content/public/browser/download_interrupt_reasons.h"
+#include "net/http/http_content_disposition.h"
 
 namespace content {
 
+namespace {
+
 // All possible error codes from the network module. Note that the error codes
 // are all positive (since histograms expect positive sample values).
 const int kAllInterruptReasonCodes[] = {
@@ -19,6 +22,45 @@ const int kAllInterruptReasonCodes[] = {
 #undef INTERRUPT_REASON
 };
 
+// These values are based on net::HttpContentDisposition::ParseResult values.
+// Values other than HEADER_PRESENT and IS_VALID are only measured if |is_valid|
+// is true.
+enum ContentDispositionCountTypes {
+  // Count of downloads which had a Content-Disposition headers. The total
+  // number of downloads is measured by UNTHROTTLED_COUNT.
+  CONTENT_DISPOSITION_HEADER_PRESENT = 0,
+
+  // At least one of 'name', 'filename' or 'filenae*' attributes were valid and
+  // yielded a non-empty filename.
+  CONTENT_DISPOSITION_IS_VALID,
+
+  // The following enum values correspond to
+  // net::HttpContentDisposition::ParseResult.
+  CONTENT_DISPOSITION_HAS_DISPOSITION_TYPE,
+  CONTENT_DISPOSITION_HAS_UNKNOWN_TYPE,
+  CONTENT_DISPOSITION_HAS_NAME,
+  CONTENT_DISPOSITION_HAS_FILENAME,
+  CONTENT_DISPOSITION_HAS_EXT_FILENAME,
+  CONTENT_DISPOSITION_HAS_NON_ASCII_STRINGS,
+  CONTENT_DISPOSITION_HAS_PERCENT_ENCODED_STRINGS,
+  CONTENT_DISPOSITION_HAS_RFC2047_ENCODED_STRINGS,
+
+  // Only have the 'name' attribute is present.
+  CONTENT_DISPOSITION_HAS_NAME_ONLY,
+
+  CONTENT_DISPOSITION_LAST_ENTRY
+};
+
+void RecordContentDispositionCount(ContentDispositionCountTypes type,
+                                   bool record) {
+  if (!record)
+    return;
+  UMA_HISTOGRAM_ENUMERATION(
+      "Download.ContentDisposition", type, CONTENT_DISPOSITION_LAST_ENTRY);
+}
+
+} // namespace
+
 void RecordDownloadCount(DownloadCountTypes type) {
   UMA_HISTOGRAM_ENUMERATION(
       "Download.Counts", type, DOWNLOAD_COUNT_TYPES_LAST_ENTRY);
@@ -252,6 +294,41 @@ void RecordDownloadMimeType(const std::string& mime_type_string) {
                             DOWNLOAD_CONTENT_MAX);
 }
 
+void RecordDownloadContentDisposition(
+    const std::string& content_disposition_string) {
+  if (content_disposition_string.empty())
+    return;
+  net::HttpContentDisposition content_disposition(
+      content_disposition_string, "");
+  const net::HttpContentDisposition::ParseResult& result =
+      content_disposition.parse_result();
+
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HEADER_PRESENT, true);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_IS_VALID,
+                                (result.has_name || result.has_filename ||
+                                 result.has_ext_filename));

[Randy Smith (Not in Mondays), 2012/12/12 16:10:36]

Isn't this contradictory to the comment in the enum that nothing else will be
recorded if !is_valid?  You may be sure that the parsing won't produce any other
true booleans if these three booleans are false, but that doesn't seem wise to
rely on at this point in the code.

[asanka, 2012/12/14 01:28:01]

Done.

+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_DISPOSITION_TYPE,
+                                result.has_disposition_type);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_UNKNOWN_TYPE,
+                                result.has_unknown_disposition_type);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_NAME,
+                                result.has_name);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_FILENAME,
+                                result.has_filename);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_EXT_FILENAME,
+                                result.has_ext_filename);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_NON_ASCII_STRINGS,
+                                result.has_non_ascii_strings);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_PERCENT_ENCODED_STRINGS,
+                                result.has_percent_encoded_strings);
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_RFC2047_ENCODED_STRINGS,
+                                result.has_rfc2047_encoded_strings);
+
+  RecordContentDispositionCount(CONTENT_DISPOSITION_HAS_NAME_ONLY,
+                                (result.has_name && !result.has_filename &&
+                                 !result.has_ext_filename));
+}
+
 void RecordFileThreadReceiveBuffers(size_t num_buffers) {
     UMA_HISTOGRAM_CUSTOM_COUNTS(
       "Download.FileThreadReceiveBuffers", num_buffers, 1,