base/i18n: Class for efficiently searching the same query over many texts.

base/i18n/string_search.cc

Index: base/i18n/string_search.cc
diff --git a/base/i18n/string_search.cc b/base/i18n/string_search.cc
index f4e53cb4b7c8b4f8bfb22bb896bae3cd2e85e862..cde5be5285e1afdbf81ce75ab797b2f8349746c5 100644
--- a/base/i18n/string_search.cc
+++ b/base/i18n/string_search.cc
@@ -7,71 +7,76 @@
 
 #include "third_party/icu/public/i18n/unicode/usearch.h"
 
-namespace {
+namespace base {
+namespace i18n {
+
+FixedPatternStringSearchIgnoringCaseAndAccents::
+FixedPatternStringSearchIgnoringCaseAndAccents(const string16& find_this)
+    : find_this_(find_this) {
+  // usearch_open requires a valid string argument to be searched, even if we
+  // want to set it by usearch_setText afterwards. So, supplying a dummy text.
+  const string16& dummy = find_this_;
 
-bool CollationSensitiveStringSearch(const string16& find_this,
-                                    const string16& in_this,
-                                    UCollationStrength strength,
-                                    size_t* match_index,
-                                    size_t* match_length) {
   UErrorCode status = U_ZERO_ERROR;
+  search_ = usearch_open(find_this_.data(), find_this_.size(),
+                         dummy.data(), dummy.size(),
+                         uloc_getDefault(),
+                         NULL,  // breakiter
+                         &status);
+  if (U_SUCCESS(status)) {
+    UCollator* collator = usearch_getCollator(search_);
+    ucol_setStrength(collator, UCOL_PRIMARY);
+    usearch_reset(search_);
+  }
+}
+
+FixedPatternStringSearchIgnoringCaseAndAccents::
+~FixedPatternStringSearchIgnoringCaseAndAccents() {
+  if (search_)
+    usearch_close(search_);
+}
 
-  UStringSearch* search = usearch_open(find_this.data(), -1,
-                                       in_this.data(), -1,
-                                       uloc_getDefault(),
-                                       NULL,  // breakiter
-                                       &status);
+bool FixedPatternStringSearchIgnoringCaseAndAccents::Search(
+    const string16& in_this, size_t* match_index, size_t* match_length) {
+  UErrorCode status = U_ZERO_ERROR;
+  if (!search_)
+    status = U_ILLEGAL_ARGUMENT_ERROR;
+  else
+    usearch_setText(search_, in_this.data(), in_this.size(), &status);

[jungshik at Google, 2013/07/10 21:27:52]

You don't need to check for |search_| != NULL here. |usearch_setText| will do
the job for you and set |status| to U_ILLEGAL_ARGUMENT_ERROR. 

[kinaba, 2013/07/11 03:14:22]

Done. Thanks,

 
   // Default to basic substring search if usearch fails. According to
   // http://icu-project.org/apiref/icu4c/usearch_8h.html, usearch_open will fail
   // if either |find_this| or |in_this| are empty. In either case basic
   // substring search will give the correct return value.
   if (!U_SUCCESS(status)) {
-    size_t index = in_this.find(find_this);
+    size_t index = in_this.find(find_this_);
     if (index == string16::npos) {
       return false;
     } else {
       if (match_index)
         *match_index = index;
       if (match_length)
-        *match_length = find_this.size();
+        *match_length = find_this_.size();
       return true;
     }
   }
 
-  UCollator* collator = usearch_getCollator(search);
-  ucol_setStrength(collator, strength);
-  usearch_reset(search);
-
-  int32_t index = usearch_first(search, &status);
-  if (!U_SUCCESS(status) || index == USEARCH_DONE) {
-    usearch_close(search);
+  int32_t index = usearch_first(search_, &status);
+  if (!U_SUCCESS(status) || index == USEARCH_DONE)
     return false;
-  }
-
   if (match_index)
     *match_index = static_cast<size_t>(index);
   if (match_length)
-    *match_length = static_cast<size_t>(usearch_getMatchedLength(search));
-
-  usearch_close(search);
+    *match_length = static_cast<size_t>(usearch_getMatchedLength(search_));
   return true;
 }
 
-}  // namespace
-
-namespace base {
-namespace i18n {
-
 bool StringSearchIgnoringCaseAndAccents(const string16& find_this,
                                         const string16& in_this,
                                         size_t* match_index,
                                         size_t* match_length) {
-  return CollationSensitiveStringSearch(find_this,
-                                        in_this,
-                                        UCOL_PRIMARY,
-                                        match_index,
-                                        match_length);
+  return FixedPatternStringSearchIgnoringCaseAndAccents(find_this).Search(
+      in_this, match_index, match_length);
 }
 
 }  // namespace i18n