Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(458)

Unified Diff: components/translate/core/language_detection/chinese_script_classifier.cc

Issue 2743843002: Implements ChineseScriptClassifier functionality without icu::Transliterator (Closed)
Patch Set: Removes references to unused translit.h Created 3 years, 9 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « components/translate/core/language_detection/chinese_script_classifier.h ('k') | no next file » | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: components/translate/core/language_detection/chinese_script_classifier.cc
diff --git a/components/translate/core/language_detection/chinese_script_classifier.cc b/components/translate/core/language_detection/chinese_script_classifier.cc
index f37cfe475e2f4f51f1d5526da0e06bcbc3b8c166..c34d0e6f6c5fa2d94dc16257aa201554a2086be2 100644
--- a/components/translate/core/language_detection/chinese_script_classifier.cc
+++ b/components/translate/core/language_detection/chinese_script_classifier.cc
@@ -9,8 +9,8 @@
#include <string>
#include "base/logging.h"
#include "base/strings/string_util.h"
+#include "third_party/icu/source/common/unicode/uniset.h"
#include "third_party/icu/source/common/unicode/unistr.h"
-#include "third_party/icu/source/i18n/unicode/translit.h"
namespace translate {
@@ -23,25 +23,750 @@ const char kChineseTraditionalCode[] = "zh-Hant";
} // namespace
ChineseScriptClassifier::ChineseScriptClassifier() {
- UParseError parse_status;
- UErrorCode status = U_ZERO_ERROR;
- // The Transliterator IDs are defined in:
- // third_party/icu/source/data/translit/root.txt.
+ // zh-Hans and zh-Hant codepoints extracted from:
+ // third_party/icu/source/data/translit/Hans_Hant.txt
//
- // Chromium keeps only a subset of these, defined in:
- // third_party/icu/source/data/translit/root_subset.txt
- hans2hant_.reset(icu::Transliterator::createInstance(
- icu::UnicodeString("Hans-Hant"), UTRANS_FORWARD, parse_status, status));
- DVLOG(1) << "Hans-Hant Transliterator initialization status: "
- << u_errorName(status);
- hant2hans_.reset(icu::Transliterator::createInstance(
- icu::UnicodeString("Hant-Hans"), UTRANS_FORWARD, parse_status, status));
- DVLOG(1) << "Hant-Hans Transliterator initialization status: "
- << u_errorName(status);
+ // zh-Hans codepoints to be stored in a UnicodeSet for later reference.
+ const std::string& hans_codepoints =
groby1 2017/03/10 19:27:17 Maybe I'm weird about this, but given this is data
riesa 2017/03/10 19:32:01 Sure -- fine with me. I don't know anything about
+ "[\u4e07\u4e0e\u4e13\u4e1a\u4e1b\u4e1c"
+ "\u4e1d\u4e22\u4e24\u4e25\u4e27\u4e2a\u4e2b"
+ "\u4e30\u4e34\u4e3a\u4e3d\u4e3e\u4e49\u4e4c\u4e50"
+ "\u4e54\u4e60\u4e61\u4e66\u4e70\u4e71\u4e89"
+ "\u4e8f\u4e98\u4e9a\u4ea7\u4ea9\u4eae\u4eb2\u4eb5"
+ "\u4eb8\u4ebf\u4ec0\u4ec5\u4ec6\u4ece\u4ed1"
+ "\u4ed3\u4ed7\u4eea\u4eec\u4ef7\u4f17\u4f18\u4f1a"
+ "\u4f1b\u4f1e\u4f1f\u4f20\u4f23\u4f24\u4f25"
+ "\u4f26\u4f27\u4f2a\u4f2b\u4f53\u4f5d\u4f63\u4f65"
+ "\u4fa0\u4fa3\u4fa5\u4fa6\u4fa7\u4fa8\u4fa9"
+ "\u4faa\u4fac\u4fe3\u4fe6\u4fe8\u4fe9\u4fea\u4feb"
+ "\u4fed\u503a\u503e\u506c\u507b\u507e\u507f"
+ "\u50a5\u50a7\u50a8\u50a9\u513f\u5151\u5156\u515a"
+ "\u5170\u5173\u5174\u5179\u517b\u517d\u5181"
+ "\u5185\u5188\u518c\u5199\u519b\u519c\u51a2\u51af"
+ "\u51b1\u51b3\u51b5\u51bb\u51c4\u51c9\u51cf"
+ "\u51d1\u51db\u51e4\u51eb\u51ed\u51ef\u51fb\u51ff"
+ "\u520d\u5218\u5219\u521a\u521b\u5220\u522b"
+ "\u522c\u522d\u5239\u523d\u523f\u5240\u5242\u5250"
+ "\u5251\u5265\u5267\u529d\u529e\u52a1\u52a2"
+ "\u52a8\u52b1\u52b2\u52b3\u52bf\u52cb\u52d6\u52da"
+ "\u52e4\u5300\u5326\u532e\u533a\u533b\u534e"
+ "\u534f\u5355\u5356\u5362\u5364\u5367\u536b\u5374"
+ "\u5382\u5384\u5385\u5386\u5389\u538b\u538c"
+ "\u538d\u5390\u5395\u5398\u53a2\u53a3\u53a6\u53a8"
+ "\u53a9\u53ae\u53bf\u53c1\u53c2\u53cc\u53d8"
+ "\u53d9\u53e0\u53f7\u53f9\u53fd\u5401\u540c\u5413"
+ "\u5415\u5417\u5423\u5428\u542c\u542f\u5434"
+ "\u5450\u5452\u5453\u5455\u5456\u5457\u5458\u5459"
+ "\u545b\u545c\u548f\u5499\u549b\u549d\u54a4"
+ "\u54c4\u54cd\u54d1\u54d2\u54d3\u54d4\u54d5\u54d7"
+ "\u54d9\u54dc\u54dd\u54df\u551b\u551d\u5520"
+ "\u5521\u5522\u5524\u5555\u5567\u556c\u556d\u556e"
+ "\u5570\u5574\u5578\u5582\u55b7\u55bd\u55be"
+ "\u55eb\u55f3\u5618\u5624\u5631\u565c\u566a\u56a3"
+ "\u56e2\u56ed\u56f1\u56f4\u56f5\u56fd\u56fe"
+ "\u5706\u5723\u5739\u573a\u5742\u574f\u5757\u575a"
+ "\u575b\u575c\u575d\u575e\u575f\u5760\u5784"
+ "\u5785\u5786\u5792\u57a6\u57a9\u57ab\u57ad\u57b1"
+ "\u57b2\u57b4\u57d8\u57d9\u57da\u57ef\u5811"
+ "\u5815\u5824\u5899\u58ee\u58f0\u58f3\u58f6\u58f8"
+ "\u5904\u5907\u590d\u591f\u5934\u5938\u5939"
+ "\u593a\u5941\u5942\u594b\u5956\u5965\u5986\u5987"
+ "\u5988\u59a9\u59aa\u59ab\u59d7\u59f9\u5a04"
+ "\u5a05\u5a06\u5a07\u5a08\u5a18\u5a31\u5a32\u5a34"
+ "\u5a73\u5a74\u5a75\u5a76\u5aaa\u5abe\u5ad2"
+ "\u5ad4\u5af1\u5b37\u5b59\u5b66\u5b6a\u5b81\u5b9d"
+ "\u5b9e\u5ba0\u5ba1\u5baa\u5bab\u5bbd\u5bbe"
+ "\u5bdd\u5bf8\u5bf9\u5bfb\u5bfc\u5bff\u5c06\u5c14"
+ "\u5c18\u5c1d\u5c27\u5c34\u5c38\u5c3d\u5c42"
+ "\u5c43\u5c49\u5c4a\u5c5e\u5c61\u5c66\u5c7f\u5c81"
+ "\u5c82\u5c96\u5c97\u5c98\u5c99\u5c9a\u5c9b"
+ "\u5ca9\u5cad\u5cb3\u5cbd\u5cbf\u5cc4\u5ce1\u5ce3"
+ "\u5ce4\u5ce5\u5ce6\u5d02\u5d03\u5d04\u5d2d"
+ "\u5d58\u5d5a\u5d5d\u5dc5\u5de9\u5def\u5e01\u5e05"
+ "\u5e08\u5e0f\u5e10\u5e18\u5e1c\u5e26\u5e27"
+ "\u5e2e\u5e31\u5e3b\u5e3c\u5e42\u5e76\u5e7f\u5e84"
+ "\u5e86\u5e90\u5e91\u5e93\u5e94\u5e99\u5e9e"
+ "\u5e9f\u5ea6\u5eea\u5f00\u5f02\u5f03\u5f11\u5f20"
+ "\u5f25\u5f26\u5f2a\u5f2f\u5f39\u5f3a\u5f52"
+ "\u5f53\u5f55\u5f5d\u5f66\u5f7b\u5f84\u5f95\u5fad"
+ "\u5fc6\u5fcf\u5fe7\u5ffe\u6000\u6001\u6002"
+ "\u6003\u6004\u6005\u6006\u601c\u603b\u603c\u603f"
+ "\u604b\u6052\u6064\u6073\u6076\u6078\u6079"
+ "\u607a\u607b\u607c\u607d\u60a6\u60ab\u60ac\u60ad"
+ "\u60ae\u60af\u60ca\u60e7\u60e8\u60e9\u60eb"
+ "\u60ec\u60ed\u60ee\u60ef\u6120\u6124\u6126\u6151"
+ "\u61d1\u61d2\u61d4\u6206\u620b\u620f\u6217"
+ "\u6218\u621a\u622c\u622e\u622f\u6237\u6247\u6251"
+ "\u6263\u6267\u6269\u626a\u626b\u626c\u6270"
+ "\u6298\u629a\u629b\u629f\u62a0\u62a1\u62a2\u62a4"
+ "\u62a5\u62c5\u62d3\u62df\u62e2\u62e3\u62e5"
+ "\u62e6\u62e7\u62e8\u62e9\u6302\u631a\u631b\u631c"
+ "\u631d\u631e\u631f\u6320\u6321\u6322\u6323"
+ "\u6324\u6325\u6326\u633d\u6342\u6346\u635d\u635e"
+ "\u635f\u6361\u6362\u6363\u636e\u637b\u63b3"
+ "\u63b4\u63b7\u63b8\u63ba\u63bc\u63fd\u63fe\u63ff"
+ "\u6400\u6401\u6402\u6405\u643a\u6444\u6445"
+ "\u6446\u6447\u6448\u644a\u6484\u6491\u64b5\u64b7"
+ "\u64b8\u64ba\u64de\u6512\u654c\u655b\u6570"
+ "\u658b\u6593\u65a9\u65ad\u65c1\u65e0\u65e7\u65f6"
+ "\u65f7\u65f8\u6606\u660c\u6619\u6635\u663c"
+ "\u663d\u663e\u664b\u6652\u6653\u6654\u6655\u6656"
+ "\u6682\u66a7\u672f\u6731\u6740\u6742\u6743"
+ "\u6746\u6761\u6765\u6768\u6769\u676f\u6770\u6781"
+ "\u6784\u679e\u67a2\u67a3\u67a5\u67a7\u67a8"
+ "\u67aa\u67ab\u67ad\u67e0\u67e5\u67fd\u6800\u6805"
+ "\u6807\u6808\u6809\u680a\u680b\u680c\u680e"
+ "\u680f\u6811\u6816\u6837\u683e\u6860\u6861\u6862"
+ "\u6863\u6864\u6865\u6866\u6867\u6868\u6869"
+ "\u68a6\u68bc\u68be\u68bf\u68c0\u68c1\u68c2\u6901"
+ "\u691f\u6920\u6924\u692d\u696b\u697c\u6984"
+ "\u6985\u6987\u6988\u6989\u69a8\u69da\u69db\u69df"
+ "\u69e0\u6a2a\u6a2f\u6a31\u6a50\u6a65\u6a71"
+ "\u6a79\u6a7c\u6a90\u6aa9\u6b22\u6b24\u6b27\u6b7c"
+ "\u6b81\u6b87\u6b8b\u6b92\u6b93\u6b9a\u6ba1"
+ "\u6bb4\u6bb7\u6bc1\u6bc2\u6bd5\u6bd9\u6be1\u6bf5"
+ "\u6c07\u6c22\u6c29\u6c32\u6c47\u6c49\u6c64"
+ "\u6c79\u6c89\u6c9f\u6ca1\u6ca3\u6ca4\u6ca5\u6ca6"
+ "\u6ca7\u6ca9\u6caa\u6cbe\u6cde\u6cea\u6cf6"
+ "\u6cf7\u6cf8\u6cfa\u6cfb\u6cfc\u6cfd\u6cfe\u6d01"
+ "\u6d12\u6d3c\u6d43\u6d45\u6d46\u6d47\u6d48"
+ "\u6d4a\u6d4b\u6d4d\u6d4e\u6d4f\u6d50\u6d51\u6d52"
+ "\u6d53\u6d54\u6d5a\u6d82\u6d9b\u6d9d\u6d9e"
+ "\u6d9f\u6da0\u6da1\u6da3\u6da4\u6da6\u6da7\u6da8"
+ "\u6da9\u6dec\u6e0a\u6e0c\u6e0d\u6e0e\u6e10"
+ "\u6e11\u6e14\u6e17\u6e29\u6e7e\u6e7f\u6e83\u6e85"
+ "\u6e86\u6ed7\u6eda\u6ede\u6edf\u6ee0\u6ee1"
+ "\u6ee2\u6ee4\u6ee5\u6ee6\u6ee8\u6ee9\u6eea\u6f13"
+ "\u6f24\u6f46\u6f47\u6f4b\u6f4d\u6f5c\u6f74"
+ "\u6f9c\u6fd1\u6fd2\u704f\u706d\u706f\u7075\u707e"
+ "\u707f\u7080\u7089\u7096\u709c\u709d\u70ad"
+ "\u70b9\u70bc\u70bd\u70c1\u70c2\u70c3\u70db\u70e6"
+ "\u70e7\u70e8\u70e9\u70eb\u70ec\u70ed\u7115"
+ "\u7116\u7118\u7130\u7174\u718f\u7194\u7231\u7237"
+ "\u724d\u7266\u7275\u727a\u728a\u72b6\u72b7"
+ "\u72b8\u72b9\u72c8\u72dd\u72de\u72ec\u72ed\u72ee"
+ "\u72ef\u72f0\u72f1\u72f2\u7303\u730e\u7315"
+ "\u7321\u732a\u732b\u732c\u732e\u736d\u7391\u739a"
+ "\u739b\u73ae\u73af\u73b0\u73b1\u73ba\u73d0"
+ "\u73d1\u73f0\u73f2\u7403\u7405\u740f\u7410\u743c"
+ "\u7476\u7477\u748e\u74d2\u74ee\u74ef\u7535"
+ "\u753b\u7545\u7574\u7596\u7597\u759f\u75a0\u75a1"
+ "\u75ac\u75ad\u75ae\u75af\u75b1\u75b4\u75c8"
+ "\u75c9\u75d2\u75d6\u75e8\u75ea\u75eb\u7605\u7606"
+ "\u7617\u7618\u762a\u762b\u763e\u763f\u765e"
+ "\u7663\u766b\u7682\u7691\u76b1\u76b2\u76cf\u76d0"
+ "\u76d1\u76d6\u76d7\u76d8\u770d\u772c\u772f"
+ "\u7741\u7750\u7751\u777e\u7786\u7792\u77a9\u77eb"
+ "\u77f6\u77fe\u77ff\u7800\u7801\u7816\u7817"
+ "\u781a\u781c\u783a\u783b\u783e\u7840\u7841\u7855"
+ "\u7856\u7857\u7859\u786e\u7877\u788d\u789b"
+ "\u789c\u78b1\u78f7\u7934\u793c\u7943\u794e\u7962"
+ "\u796f\u7977\u7978\u7980\u7984\u7985\u79bb"
+ "\u79c3\u79cd\u79d8\u79ef\u79f0\u79fd\u79fe\u7a06"
+ "\u7a0e\u7a23\u7a33\u7a51\u7a77\u7a83\u7a8d"
+ "\u7a8e\u7a91\u7a9c\u7a9d\u7aa5\u7aa6\u7aad\u7ad6"
+ "\u7ade\u7b03\u7b0b\u7b14\u7b15\u7b3a\u7b3c"
+ "\u7b3e\u7b51\u7b5a\u7b5b\u7b5c\u7b5d\u7b79\u7b7c"
+ "\u7b7e\u7b80\u7b93\u7ba6\u7ba7\u7ba8\u7ba9"
+ "\u7baa\u7bab\u7bd1\u7bd3\u7bea\u7bee\u7bf1\u7c16"
+ "\u7c41\u7c74\u7c7b\u7c7c\u7c9c\u7c9d\u7ca4"
+ "\u7caa\u7cae\u7cc1\u7cc7\u7cdf\u7d27\u7d77\u7e9f"
+ "\u7ea0\u7ea1\u7ea2\u7ea3\u7ea4\u7ea5\u7ea6"
+ "\u7ea7\u7ea8\u7ea9\u7eaa\u7eab\u7eac\u7ead\u7eae"
+ "\u7eaf\u7eb0\u7eb1\u7eb2\u7eb3\u7eb4\u7eb5"
+ "\u7eb6\u7eb7\u7eb8\u7eb9\u7eba\u7ebb\u7ebc\u7ebd"
+ "\u7ebe\u7ebf\u7ec0\u7ec1\u7ec2\u7ec3\u7ec4"
+ "\u7ec5\u7ec6\u7ec7\u7ec8\u7ec9\u7eca\u7ecb\u7ecc"
+ "\u7ecd\u7ece\u7ecf\u7ed0\u7ed1\u7ed2\u7ed3"
+ "\u7ed4\u7ed5\u7ed6\u7ed7\u7ed8\u7ed9\u7eda\u7edb"
+ "\u7edc\u7edd\u7ede\u7edf\u7ee0\u7ee1\u7ee2"
+ "\u7ee3\u7ee4\u7ee5\u7ee6\u7ee7\u7ee8\u7ee9\u7eea"
+ "\u7eeb\u7eec\u7eed\u7eee\u7eef\u7ef0\u7ef1"
+ "\u7ef2\u7ef3\u7ef4\u7ef5\u7ef6\u7ef7\u7ef8\u7ef9"
+ "\u7efa\u7efb\u7efc\u7efd\u7efe\u7eff\u7f00"
+ "\u7f01\u7f02\u7f03\u7f04\u7f05\u7f06\u7f07\u7f08"
+ "\u7f09\u7f0a\u7f0b\u7f0c\u7f0d\u7f0e\u7f0f"
+ "\u7f11\u7f12\u7f13\u7f14\u7f15\u7f16\u7f17\u7f18"
+ "\u7f19\u7f1a\u7f1b\u7f1c\u7f1d\u7f1e\u7f1f"
+ "\u7f20\u7f21\u7f22\u7f23\u7f24\u7f25\u7f26\u7f27"
+ "\u7f28\u7f29\u7f2a\u7f2b\u7f2c\u7f2d\u7f2e"
+ "\u7f2f\u7f30\u7f31\u7f32\u7f33\u7f34\u7f35\u7f42"
+ "\u7f51\u7f57\u7f5a\u7f62\u7f74\u7f81\u7f9f"
+ "\u7fa1\u7fd8\u7ff1\u8000\u8022\u8027\u8038\u8042"
+ "\u804b\u804c\u804d\u8054\u8069\u806a\u8083"
+ "\u80a0\u80a4\u80ae\u80b4\u80be\u80bf\u80c0\u80c1"
+ "\u80dc\u80e7\u80e8\u80ea\u80eb\u80f6\u8109"
+ "\u810d\u810f\u8110\u8111\u8113\u8114\u811a\u8131"
+ "\u8136\u8138\u814c\u816d\u817b\u817c\u817d"
+ "\u817e\u8191\u81bb\u81dc\u8206\u8223\u8230\u8231"
+ "\u823b\u8270\u8273\u827a\u8282\u8288\u8297"
+ "\u829c\u82a6\u82c1\u82c7\u82c8\u82cb\u82cc\u82cd"
+ "\u82cf\u8303\u830e\u830f\u8311\u8314\u8315"
+ "\u8327\u8346\u8350\u8359\u835a\u835b\u835c\u835e"
+ "\u835f\u8360\u8361\u8363\u8364\u8365\u8366"
+ "\u8367\u8368\u8369\u836a\u836b\u836c\u836d\u836e"
+ "\u836f\u8385\u83b1\u83b2\u83b3\u83b4\u83b6"
+ "\u83b7\u83b8\u83b9\u83ba\u83bc\u841d\u8424\u8425"
+ "\u8426\u8427\u8428\u8471\u8487\u8489\u848b"
+ "\u848c\u84dd\u84df\u84e0\u84e3\u84e5\u84e6\u8502"
+ "\u8511\u8537\u8539\u853a\u853c\u8570\u8572"
+ "\u8574\u85ae\u85af\u85d3\u85e4\u8616\u864f\u8651"
+ "\u865a\u866b\u866c\u866e\u867d\u867e\u867f"
+ "\u8680\u8681\u8682\u8695\u86ac\u86ca\u86ce\u86cf"
+ "\u86ee\u86f0\u86f1\u86f2\u86f3\u86f4\u8715"
+ "\u8717\u8737\u8747\u8748\u8749\u874e\u877c\u877e"
+ "\u8780\u87a8\u87cf\u8839\u8845\u8854\u8865"
+ "\u886c\u886e\u8884\u8885\u8886\u889c\u88ad\u88af"
+ "\u88c5\u88c6\u88c8\u88e2\u88e3\u88e4\u88e5"
+ "\u891b\u8934\u89c1\u89c2\u89c3\u89c4\u89c5\u89c6"
+ "\u89c7\u89c8\u89c9\u89ca\u89cb\u89cc\u89cd"
+ "\u89ce\u89cf\u89d0\u89d1\u89de\u89e6\u89ef\u8a1a"
+ "\u8a89\u8a8a\u8ba0\u8ba1\u8ba2\u8ba3\u8ba4"
+ "\u8ba5\u8ba6\u8ba7\u8ba8\u8ba9\u8baa\u8bab\u8bad"
+ "\u8bae\u8baf\u8bb0\u8bb1\u8bb2\u8bb3\u8bb4"
+ "\u8bb5\u8bb6\u8bb7\u8bb8\u8bb9\u8bba\u8bbb\u8bbc"
+ "\u8bbd\u8bbe\u8bbf\u8bc0\u8bc1\u8bc2\u8bc3"
+ "\u8bc4\u8bc5\u8bc6\u8bc7\u8bc8\u8bc9\u8bca\u8bcb"
+ "\u8bcc\u8bcd\u8bce\u8bcf\u8bd0\u8bd1\u8bd2"
+ "\u8bd3\u8bd4\u8bd5\u8bd6\u8bd7\u8bd8\u8bd9\u8bda"
+ "\u8bdb\u8bdc\u8bdd\u8bde\u8bdf\u8be0\u8be1"
+ "\u8be2\u8be3\u8be4\u8be5\u8be6\u8be7\u8be8\u8be9"
+ "\u8bea\u8beb\u8bec\u8bed\u8bee\u8bef\u8bf0"
+ "\u8bf1\u8bf2\u8bf3\u8bf4\u8bf5\u8bf6\u8bf7\u8bf8"
+ "\u8bf9\u8bfa\u8bfb\u8bfc\u8bfd\u8bfe\u8bff"
+ "\u8c00\u8c01\u8c02\u8c03\u8c04\u8c05\u8c06\u8c07"
+ "\u8c08\u8c0a\u8c0b\u8c0c\u8c0d\u8c0e\u8c0f"
+ "\u8c10\u8c11\u8c12\u8c13\u8c14\u8c15\u8c16\u8c17"
+ "\u8c18\u8c19\u8c1a\u8c1b\u8c1c\u8c1d\u8c1e"
+ "\u8c1f\u8c20\u8c21\u8c22\u8c23\u8c24\u8c25\u8c26"
+ "\u8c27\u8c28\u8c29\u8c2a\u8c2b\u8c2c\u8c2d"
+ "\u8c2e\u8c2f\u8c30\u8c31\u8c32\u8c33\u8c34\u8c35"
+ "\u8c36\u8c6e\u8d1d\u8d1e\u8d1f\u8d20\u8d21"
+ "\u8d22\u8d23\u8d24\u8d25\u8d26\u8d27\u8d28\u8d29"
+ "\u8d2a\u8d2b\u8d2c\u8d2d\u8d2e\u8d2f\u8d30"
+ "\u8d31\u8d32\u8d33\u8d34\u8d35\u8d36\u8d37\u8d38"
+ "\u8d39\u8d3a\u8d3b\u8d3c\u8d3d\u8d3e\u8d3f"
+ "\u8d40\u8d41\u8d42\u8d43\u8d44\u8d45\u8d46\u8d47"
+ "\u8d48\u8d49\u8d4a\u8d4b\u8d4c\u8d4d\u8d4e"
+ "\u8d4f\u8d50\u8d51\u8d52\u8d53\u8d54\u8d55\u8d56"
+ "\u8d57\u8d58\u8d59\u8d5a\u8d5b\u8d5c\u8d5d"
+ "\u8d5e\u8d5f\u8d60\u8d61\u8d62\u8d63\u8d6a\u8d75"
+ "\u8d76\u8d8b\u8db1\u8db8\u8dc3\u8dc4\u8dde"
+ "\u8df5\u8df6\u8df7\u8df8\u8df9\u8dfb\u8e0a\u8e0c"
+ "\u8e2a\u8e2c\u8e2f\u8e51\u8e52\u8e70\u8e7f"
+ "\u8e8f\u8e9c\u8eaf\u8f66\u8f67\u8f68\u8f69\u8f6a"
+ "\u8f6b\u8f6c\u8f6d\u8f6e\u8f6f\u8f70\u8f71"
+ "\u8f72\u8f73\u8f74\u8f75\u8f76\u8f77\u8f78\u8f79"
+ "\u8f7a\u8f7b\u8f7c\u8f7d\u8f7e\u8f7f\u8f80"
+ "\u8f81\u8f82\u8f83\u8f84\u8f85\u8f86\u8f87\u8f88"
+ "\u8f89\u8f8a\u8f8b\u8f8c\u8f8d\u8f8e\u8f8f"
+ "\u8f90\u8f91\u8f92\u8f93\u8f94\u8f95\u8f96\u8f97"
+ "\u8f98\u8f99\u8f9a\u8fa9\u8fab\u8fb9\u8fbd"
+ "\u8fbe\u8fc1\u8fc7\u8fc8\u8fd0\u8fd8\u8fd9\u8fdb"
+ "\u8fdc\u8fdd\u8fde\u8fdf\u8fe9\u8ff3\u8ff9"
+ "\u9002\u9009\u900a\u9012\u9026\u903b\u903e\u9057"
+ "\u9065\u9093\u909d\u90ac\u90ae\u90b9\u90ba"
+ "\u90bb\u90c1\u90cf\u90d0\u90d1\u90d3\u90e6\u90e7"
+ "\u90f8\u9142\u915d\u9166\u9171\u9178\u917d"
+ "\u917e\u917f\u91ca\u91cc\u9274\u92ae\u933e\u9485"
+ "\u9486\u9487\u9488\u9489\u948a\u948b\u948c"
+ "\u948d\u948e\u948f\u9490\u9491\u9492\u9493\u9494"
+ "\u9495\u9496\u9497\u9498\u9499\u949a\u949b"
+ "\u949c\u949d\u949e\u949f\u94a0\u94a1\u94a2\u94a3"
+ "\u94a4\u94a5\u94a6\u94a7\u94a8\u94a9\u94aa"
+ "\u94ab\u94ac\u94ad\u94ae\u94af\u94b0\u94b1\u94b2"
+ "\u94b3\u94b4\u94b5\u94b6\u94b7\u94b8\u94b9"
+ "\u94ba\u94bb\u94bc\u94bd\u94be\u94bf\u94c0\u94c1"
+ "\u94c2\u94c3\u94c4\u94c5\u94c6\u94c7\u94c8"
+ "\u94c9\u94ca\u94cb\u94cc\u94cd\u94ce\u94cf\u94d0"
+ "\u94d1\u94d2\u94d3\u94d4\u94d5\u94d6\u94d7"
+ "\u94d8\u94d9\u94da\u94db\u94dc\u94dd\u94de\u94df"
+ "\u94e0\u94e1\u94e2\u94e3\u94e4\u94e5\u94e6"
+ "\u94e7\u94e8\u94e9\u94ea\u94eb\u94ec\u94ed\u94ee"
+ "\u94ef\u94f0\u94f1\u94f2\u94f3\u94f4\u94f5"
+ "\u94f6\u94f7\u94f8\u94f9\u94fa\u94fb\u94fc\u94fd"
+ "\u94fe\u94ff\u9500\u9501\u9502\u9503\u9504"
+ "\u9505\u9506\u9507\u9508\u9509\u950a\u950b\u950c"
+ "\u950d\u950e\u950f\u9510\u9511\u9512\u9513"
+ "\u9514\u9515\u9516\u9517\u9518\u9519\u951a\u951b"
+ "\u951c\u951d\u951e\u951f\u9520\u9521\u9522"
+ "\u9523\u9524\u9525\u9526\u9527\u9528\u9529\u952a"
+ "\u952b\u952c\u952d\u952e\u952f\u9530\u9531"
+ "\u9532\u9533\u9534\u9535\u9536\u9537\u9538\u9539"
+ "\u953b\u953c\u953d\u953e\u953f\u9540\u9541"
+ "\u9542\u9543\u9544\u9545\u9546\u9547\u9548\u9549"
+ "\u954a\u954b\u954c\u954d\u954e\u954f\u9550"
+ "\u9551\u9552\u9553\u9554\u9556\u9557\u9558\u9559"
+ "\u955a\u955b\u955c\u955d\u955e\u955f\u9560"
+ "\u9561\u9562\u9563\u9564\u9565\u9566\u9567\u9568"
+ "\u9569\u956a\u956b\u956c\u956d\u956e\u956f"
+ "\u9570\u9571\u9572\u9573\u9574\u9575\u9576\u957f"
+ "\u95e8\u95e9\u95ea\u95eb\u95ec\u95ed\u95ee"
+ "\u95ef\u95f0\u95f1\u95f2\u95f3\u95f4\u95f5\u95f6"
+ "\u95f7\u95f8\u95f9\u95fa\u95fb\u95fc\u95fd"
+ "\u95fe\u95ff\u9600\u9601\u9602\u9603\u9604\u9605"
+ "\u9606\u9607\u9608\u9609\u960a\u960b\u960c"
+ "\u960d\u960e\u960f\u9610\u9611\u9612\u9613\u9614"
+ "\u9615\u9616\u9617\u9618\u9619\u961a\u961b"
+ "\u961f\u9633\u9634\u9635\u9636\u9640\u9645\u9646"
+ "\u9647\u9648\u9649\u9655\u9667\u9668\u9669"
+ "\u968f\u9690\u96b6\u96bd\u96be\u96cf\u96e0\u96f3"
+ "\u96fe\u9701\u9721\u972d\u9753\u9759\u9765"
+ "\u9791\u9792\u97af\u97e6\u97e7\u97e8\u97e9\u97ea"
+ "\u97eb\u97ec\u97f5\u9875\u9876\u9877\u9878"
+ "\u9879\u987a\u987b\u987c\u987d\u987e\u987f\u9880"
+ "\u9881\u9882\u9883\u9884\u9885\u9886\u9887"
+ "\u9888\u9889\u988a\u988b\u988c\u988d\u988e\u988f"
+ "\u9890\u9891\u9892\u9893\u9894\u9895\u9896"
+ "\u9897\u9898\u9899\u989a\u989b\u989c\u989d\u989e"
+ "\u989f\u98a0\u98a1\u98a2\u98a4\u98a5\u98a6"
+ "\u98a7\u98ce\u98cf\u98d0\u98d1\u98d2\u98d3\u98d4"
+ "\u98d5\u98d6\u98d7\u98d8\u98d9\u98da\u98de"
+ "\u98e8\u990d\u9963\u9964\u9965\u9966\u9967\u9968"
+ "\u9969\u996a\u996b\u996c\u996d\u996e\u996f"
+ "\u9970\u9971\u9972\u9973\u9974\u9975\u9976\u9977"
+ "\u9978\u9979\u997a\u997b\u997c\u997d\u997e"
+ "\u997f\u9981\u9982\u9983\u9984\u9985\u9986\u9987"
+ "\u9988\u9989\u998a\u998b\u998c\u998d\u998e"
+ "\u998f\u9990\u9991\u9992\u9993\u9994\u9995\u9a6c"
+ "\u9a6d\u9a6e\u9a6f\u9a70\u9a71\u9a72\u9a73"
+ "\u9a74\u9a75\u9a76\u9a77\u9a78\u9a79\u9a7a\u9a7b"
+ "\u9a7c\u9a7d\u9a7e\u9a7f\u9a80\u9a81\u9a82"
+ "\u9a83\u9a84\u9a85\u9a86\u9a87\u9a88\u9a89\u9a8a"
+ "\u9a8b\u9a8c\u9a8d\u9a8e\u9a8f\u9a90\u9a91"
+ "\u9a92\u9a93\u9a94\u9a95\u9a96\u9a97\u9a98\u9a99"
+ "\u9a9a\u9a9b\u9a9c\u9a9d\u9a9e\u9a9f\u9aa0"
+ "\u9aa1\u9aa2\u9aa3\u9aa4\u9aa5\u9aa6\u9aa7\u9ac5"
+ "\u9acb\u9acc\u9b13\u9b47\u9b49\u9c7c\u9c7d"
+ "\u9c7e\u9c7f\u9c80\u9c81\u9c82\u9c83\u9c84\u9c85"
+ "\u9c86\u9c87\u9c88\u9c89\u9c8a\u9c8b\u9c8c"
+ "\u9c8d\u9c8e\u9c8f\u9c90\u9c91\u9c92\u9c93\u9c94"
+ "\u9c95\u9c96\u9c97\u9c98\u9c99\u9c9a\u9c9b"
+ "\u9c9c\u9c9d\u9c9e\u9c9f\u9ca0\u9ca1\u9ca2\u9ca3"
+ "\u9ca4\u9ca5\u9ca6\u9ca7\u9ca8\u9ca9\u9caa"
+ "\u9cab\u9cac\u9cad\u9cae\u9caf\u9cb0\u9cb1\u9cb2"
+ "\u9cb3\u9cb4\u9cb5\u9cb6\u9cb7\u9cb8\u9cb9"
+ "\u9cba\u9cbb\u9cbc\u9cbd\u9cbe\u9cbf\u9cc0\u9cc1"
+ "\u9cc2\u9cc3\u9cc4\u9cc5\u9cc6\u9cc7\u9cc8"
+ "\u9cc9\u9cca\u9ccb\u9ccc\u9ccd\u9cce\u9ccf\u9cd0"
+ "\u9cd1\u9cd2\u9cd3\u9cd4\u9cd5\u9cd6\u9cd7"
+ "\u9cd8\u9cd9\u9cda\u9cdb\u9cdc\u9cdd\u9cde\u9cdf"
+ "\u9ce0\u9ce1\u9ce2\u9ce3\u9e1f\u9e20\u9e21"
+ "\u9e22\u9e23\u9e24\u9e25\u9e26\u9e27\u9e28\u9e29"
+ "\u9e2a\u9e2b\u9e2c\u9e2d\u9e2e\u9e2f\u9e30"
+ "\u9e31\u9e32\u9e33\u9e34\u9e35\u9e36\u9e37\u9e38"
+ "\u9e39\u9e3a\u9e3b\u9e3c\u9e3d\u9e3e\u9e3f"
+ "\u9e40\u9e41\u9e42\u9e43\u9e44\u9e45\u9e46\u9e47"
+ "\u9e48\u9e49\u9e4a\u9e4b\u9e4c\u9e4d\u9e4e"
+ "\u9e4f\u9e50\u9e51\u9e52\u9e53\u9e54\u9e55\u9e56"
+ "\u9e57\u9e58\u9e59\u9e5a\u9e5b\u9e5c\u9e5d"
+ "\u9e5e\u9e5f\u9e60\u9e61\u9e62\u9e63\u9e64\u9e65"
+ "\u9e66\u9e67\u9e68\u9e69\u9e6a\u9e6b\u9e6c"
+ "\u9e6d\u9e6f\u9e70\u9e71\u9e72\u9e73\u9e74\u9e7e"
+ "\u9ea6\u9eb8\u9ebb\u9ec4\u9ec9\u9ee1\u9ee9"
+ "\u9eea\u9efe\u9f0b\u9f0d\u9f17\u9f39\u9f50\u9f51"
+ "\u9f7f\u9f80\u9f81\u9f82\u9f83\u9f84\u9f85"
+ "\u9f86\u9f87\u9f88\u9f89\u9f8a\u9f8b\u9f8c\u9f99"
+ "\u9f9a\u9f9b\u9f9f]";
+ const std::string& hant_codepoints =
+ "[\u003b\u4e1f\u4e26\u4e82\u4e99\u4e9e\u4efd\u4f47"
+ "\u4f48\u4f54\u4f57\u4f75\u4f86\u4f96\u4fb6"
+ "\u4fb7\u4fc1\u4fc2\u4fd4\u4fe0\u4fec\u4ff1\u5000"
+ "\u5006\u5008\u5009\u500b\u5011\u5016\u5021"
+ "\u5023\u502b\u5049\u5074\u5075\u507d\u5091\u5096"
+ "\u5098\u5099\u50a2\u50ad\u50af\u50b3\u50b4"
+ "\u50b5\u50b7\u50be\u50c2\u50c5\u50c7\u50c9\u50cf"
+ "\u50d1\u50d5\u50de\u50e5\u50e8\u50f1\u50f9"
+ "\u5100\u5102\u5104\u5108\u5109\u5110\u5114\u5115"
+ "\u5118\u511f\u512a\u5132\u5137\u5138\u513a"
+ "\u513b\u513c\u5147\u514c\u5152\u5157\u5169\u518a"
+ "\u51aa\u51c8\u51cd\u51dc\u51f1\u5225\u522a"
+ "\u5244\u5247\u524b\u524e\u5257\u525b\u525d\u526e"
+ "\u5274\u5275\u5277\u5283\u5287\u5289\u528a"
+ "\u528c\u528d\u528f\u5291\u529a\u52c1\u52d5\u52d7"
+ "\u52d9\u52db\u52dd\u52de\u52e2\u52e9\u52f1"
+ "\u52f3\u52f5\u52f8\u52fb\u532d\u532f\u5331\u5340"
+ "\u5354\u5379\u537b\u5399\u53a0\u53ad\u53b2"
+ "\u53b4\u53c3\u53c4\u53e2\u540b\u5412\u5422\u5433"
+ "\u5436\u5442\u54b7\u54bc\u54e1\u5504\u551a"
+ "\u5538\u554f\u5553\u555e\u555f\u5562\u558e\u559a"
+ "\u55a8\u55aa\u55ab\u55ac\u55ae\u55b2\u55c6"
+ "\u55c7\u55ca\u55ce\u55da\u55e9\u55f6\u5606\u560d"
+ "\u5614\u5616\u5617\u561c\u5629\u562e\u562f"
+ "\u5630\u5635\u5638\u563d\u5653\u565a\u565d\u5660"
+ "\u5665\u5666\u566f\u5672\u5674\u5678\u5679"
+ "\u5680\u5687\u568c\u5690\u5695\u5699\u56a5\u56a6"
+ "\u56a8\u56ae\u56b2\u56b3\u56b4\u56b6\u56c0"
+ "\u56c1\u56c2\u56c5\u56c8\u56c9\u56cd\u56d1\u56d3"
+ "\u56ea\u5707\u570b\u570d\u5712\u5713\u5716"
+ "\u5718\u57b5\u57e1\u57f0\u57f7\u5805\u580a\u5816"
+ "\u581d\u582f\u5831\u5834\u584a\u584b\u584f"
+ "\u5852\u5857\u585a\u5862\u5864\u5875\u5879\u588a"
+ "\u589c\u58ae\u58b3\u58bb\u58be\u58c7\u58cb"
+ "\u58ce\u58d3\u58d8\u58d9\u58da\u58dc\u58de\u58df"
+ "\u58e0\u58e2\u58e9\u58ef\u58fa\u58fc\u58fd"
+ "\u5920\u5922\u5925\u593e\u5950\u5967\u5969\u596a"
+ "\u596c\u596e\u597c\u599d\u59ca\u59cd\u59e6"
+ "\u59ea\u5a1b\u5a41\u5a66\u5a6d\u5aa7\u5aaf\u5abc"
+ "\u5abd\u5acb\u5ad7\u5af5\u5afb\u5aff\u5b00"
+ "\u5b08\u5b0b\u5b0c\u5b19\u5b1d\u5b21\u5b24\u5b2a"
+ "\u5b30\u5b38\u5b43\u5b4c\u5b6b\u5b78\u5b7f"
+ "\u5bae\u5bdf\u5be2\u5be6\u5be7\u5be9\u5beb\u5bec"
+ "\u5bf5\u5bf6\u5c05\u5c07\u5c08\u5c0b\u5c0d"
+ "\u5c0e\u5c37\u5c46\u5c4d\u5c53\u5c5c\u5c62\u5c64"
+ "\u5c68\u5c6c\u5ca1\u5cf4\u5cf6\u5cfd\u5d0d"
+ "\u5d11\u5d17\u5d19\u5d22\u5d2c\u5d50\u5d81\u5d84"
+ "\u5d87\u5d94\u5d97\u5da0\u5da2\u5da7\u5dae"
+ "\u5db4\u5db8\u5dba\u5dbc\u5dbd\u5dcb\u5dd2\u5dd4"
+ "\u5dd6\u5df0\u5e25\u5e2b\u5e33\u5e36\u5e40"
+ "\u5e43\u5e57\u5e58\u5e5f\u5e63\u5e6b\u5e6c\u5e79"
+ "\u5e7e\u5eab\u5ec1\u5ec2\u5ec4\u5ec8\u5eda"
+ "\u5edd\u5edf\u5ee0\u5ee1\u5ee2\u5ee3\u5ee9\u5eec"
+ "\u5ef3\u5efb\u5f12\u5f14\u5f33\u5f35\u5f37"
+ "\u5f46\u5f48\u5f4c\u5f4e\u5f59\u5f5e\u5f65\u5f7f"
+ "\u5f8c\u5f91\u5f9e\u5fa0\u5fa9\u5fac\u5fb9"
+ "\u6035\u6046\u6065\u6085\u609e\u60b3\u60b5\u60b6"
+ "\u60bd\u60e1\u60f1\u60f2\u60fb\u611b\u611c"
+ "\u6128\u6134\u6137\u613e\u6144\u6147\u614b\u614d"
+ "\u6158\u615a\u615f\u6163\u6164\u616a\u616b"
+ "\u616e\u6173\u6176\u617c\u617e\u6182\u618a\u6190"
+ "\u6191\u6192\u619a\u61a4\u61ab\u61ae\u61b2"
+ "\u61b6\u61c3\u61c7\u61c9\u61cc\u61cd\u61de\u61df"
+ "\u61e3\u61e8\u61ee\u61f2\u61f6\u61f7\u61f8"
+ "\u61fa\u61fc\u61fe\u6200\u6207\u6214\u6227\u6229"
+ "\u6230\u6231\u6232\u6236\u62cb\u6329\u633e"
+ "\u6368\u636b\u6372\u6383\u6384\u6397\u6399\u639b"
+ "\u63a1\u63c0\u63da\u63db\u63ee\u6406\u640d"
+ "\u6416\u6417\u6425\u6427\u6428\u6435\u6436\u643e"
+ "\u6440\u6451\u645c\u645f\u646f\u6473\u6476"
+ "\u647a\u647b\u6488\u648f\u6490\u6493\u649a\u649d"
+ "\u649f\u64a2\u64a3\u64a5\u64ab\u64b2\u64b3"
+ "\u64bb\u64be\u64bf\u64c1\u64c4\u64c7\u64ca\u64cb"
+ "\u64d3\u64d4\u64da\u64e0\u64e3\u64ec\u64ef"
+ "\u64f0\u64f1\u64f2\u64f4\u64f7\u64fa\u64fb\u64fc"
+ "\u64fe\u6504\u6506\u650f\u6514\u6516\u6519"
+ "\u651b\u651c\u651d\u6522\u6523\u6524\u652a\u652c"
+ "\u6557\u6558\u6575\u6578\u6582\u6583\u6595"
+ "\u65ac\u65b7\u65bc\u6607\u6642\u6649\u665d\u6688"
+ "\u6689\u6698\u66a2\u66ab\u66b1\u66c4\u66c6"
+ "\u66c7\u66c9\u66cf\u66d6\u66e0\u66e8\u66ec\u66f8"
+ "\u6703\u6727\u6756\u6771\u6792\u67f5\u687f"
+ "\u6894\u6898\u689d\u689f\u68b2\u68c4\u68d6\u68d7"
+ "\u68df\u68e7\u68f2\u68f6\u690f\u694a\u6953"
+ "\u6968\u696d\u6975\u6996\u69aa\u69ae\u69b2\u69bf"
+ "\u69cb\u69cd\u69d3\u69d6\u69e4\u69e7\u69e8"
+ "\u69f3\u6a01\u6a02\u6a05\u6a11\u6a13\u6a19\u6a1e"
+ "\u6a23\u6a38\u6a39\u6a3a\u6a48\u6a4b\u6a5f"
+ "\u6a62\u6a6b\u6a81\u6a89\u6a94\u6a9c\u6a9d\u6a9f"
+ "\u6aa2\u6aa3\u6aae\u6aaf\u6ab3\u6ab8\u6abb"
+ "\u6ad3\u6ada\u6adb\u6add\u6ade\u6adf\u6ae5\u6ae7"
+ "\u6ae8\u6aea\u6aeb\u6aec\u6af1\u6af3\u6af8"
+ "\u6afa\u6afb\u6b04\u6b0a\u6b0f\u6b12\u6b16\u6b1e"
+ "\u6b35\u6b3d\u6b4e\u6b50\u6b5b\u6b5f\u6b61"
+ "\u6b72\u6b77\u6b78\u6b7f\u6b98\u6b9e\u6ba4\u6ba8"
+ "\u6bab\u6bae\u6baf\u6bb0\u6bb2\u6bba\u6bbb"
+ "\u6bbc\u6bc0\u6bc6\u6bec\u6bff\u6c02\u6c08\u6c0c"
+ "\u6c23\u6c2b\u6c2c\u6c33\u6c39\u6c3e\u6c4e"
+ "\u6c59\u6c7a\u6c8d\u6c92\u6c96\u6cc1\u6d29\u6d36"
+ "\u6d79\u6d87\u6dbc\u6dd2\u6dda\u6de5\u6dea"
+ "\u6df5\u6df6\u6dfa\u6e19\u6e1b\u6e26\u6e2c\u6e3e"
+ "\u6e4a\u6e5e\u6e67\u6e6f\u6e88\u6e96\u6e9d"
+ "\u6eab\u6ebc\u6ec4\u6ec5\u6ecc\u6ece\u6eec\u6eef"
+ "\u6ef2\u6ef7\u6ef8\u6efb\u6efe\u6eff\u6f01"
+ "\u6f1a\u6f22\u6f23\u6f2c\u6f32\u6f35\u6f38\u6f3f"
+ "\u6f41\u6f51\u6f54\u6f59\u6f5b\u6f64\u6f6f"
+ "\u6f70\u6f77\u6f7f\u6f80\u6f86\u6f87\u6f97\u6fa0"
+ "\u6fa4\u6fa6\u6fa9\u6fae\u6fb1\u6fc1\u6fc3"
+ "\u6fd5\u6fd8\u6fdf\u6fe4\u6feb\u6fec\u6ff0\u6ff1"
+ "\u6ffa\u6ffc\u6ffe\u7005\u7006\u7007\u7009"
+ "\u700b\u700f\u7015\u7018\u701d\u701f\u7020\u7026"
+ "\u7027\u7028\u7030\u7032\u703e\u7043\u7044"
+ "\u7051\u7055\u7058\u705d\u7060\u7063\u7064\u7067"
+ "\u707d\u70ba\u70cf\u70f4\u7120\u7121\u7149"
+ "\u7152\u7159\u7162\u7165\u7169\u716c\u7171\u7185"
+ "\u7192\u7197\u71b1\u71b2\u71be\u71c1\u71c4"
+ "\u71c8\u71c9\u71d0\u71d2\u71d9\u71dc\u71df\u71e6"
+ "\u71ec\u71ed\u71f4\u71f6\u71fb\u71fc\u71fe"
+ "\u71ff\u720d\u7210\u721b\u722d\u7232\u723a\u723e"
+ "\u7240\u7246\u724b\u7258\u727d\u7296\u72a2"
+ "\u72a7\u72c0\u72f9\u72fd\u7319\u7336\u733b\u7341"
+ "\u7343\u7344\u7345\u734e\u7368\u736a\u736b"
+ "\u736e\u7370\u7371\u7372\u7375\u7377\u7378\u737a"
+ "\u737b\u737c\u7380\u73fe\u743a\u743f\u744b"
+ "\u7452\u7463\u7464\u7469\u746a\u746f\u7472\u7489"
+ "\u74a3\u74a6\u74ab\u74b0\u74bd\u74ca\u74cf"
+ "\u74d4\u74da\u750c\u7515\u751a\u7522\u7523\u755d"
+ "\u7562\u756b\u7570\u7576\u7587\u758a\u75c0"
+ "\u75d9\u75e0\u75fe\u7602\u760b\u760d\u7613\u761e"
+ "\u7621\u7627\u762e\u7632\u763a\u763b\u7642"
+ "\u7646\u7647\u7649\u7652\u7658\u765f\u7661\u7662"
+ "\u7664\u7665\u7667\u7669\u766c\u766d\u766e"
+ "\u7670\u7671\u7672\u767c\u7681\u769a\u76b0\u76b8"
+ "\u76ba\u76c3\u76dc\u76de\u76e1\u76e3\u76e4"
+ "\u76e7\u76ea\u7725\u773e\u774f\u775c\u775e\u776a"
+ "\u7787\u7798\u779c\u779e\u77ad\u77b6\u77bc"
+ "\u77d3\u77da\u77ef\u7802\u7832\u7843\u785c\u7864"
+ "\u7868\u786f\u78a9\u78ad\u78b3\u78b8\u78ba"
+ "\u78bc\u78d1\u78da\u78e3\u78e7\u78ef\u78fd\u7906"
+ "\u790e\u7919\u7921\u7926\u792a\u792b\u792c"
+ "\u792e\u7931\u7955\u797f\u798d\u798e\u7995\u79a1"
+ "\u79a6\u79aa\u79ae\u79b0\u79b1\u79bf\u79c8"
+ "\u7a05\u7a08\u7a0f\u7a1c\u7a1f\u7a2e\u7a31\u7a40"
+ "\u7a4c\u7a4d\u7a4e\u7a60\u7a61\u7a62\u7a69"
+ "\u7a6b\u7a6d\u7aa9\u7aaa\u7aae\u7aaf\u7ab5\u7ab6"
+ "\u7aba\u7ac4\u7ac5\u7ac7\u7ac8\u7aca\u7aea"
+ "\u7af6\u7b46\u7b4d\u7b67\u7b74\u7b87\u7b8b\u7b8e"
+ "\u7b8f\u7b9d\u7bc0\u7bc4\u7bc9\u7bcb\u7bd4"
+ "\u7be4\u7be9\u7bf3\u7c00\u7c06\u7c0d\u7c1e\u7c21"
+ "\u7c23\u7c2b\u7c37\u7c39\u7c3d\u7c3e\u7c43"
+ "\u7c4c\u7c50\u7c59\u7c5c\u7c5f\u7c60\u7c64\u7c69"
+ "\u7c6a\u7c6c\u7c6e\u7c72\u7ca7\u7cb5\u7cdd"
+ "\u7cde\u7ce7\u7cf0\u7cf2\u7cf4\u7cf6\u7cf9\u7cfe"
+ "\u7d00\u7d02\u7d04\u7d05\u7d06\u7d07\u7d08"
+ "\u7d09\u7d0b\u7d0d\u7d10\u7d13\u7d14\u7d15\u7d16"
+ "\u7d17\u7d18\u7d19\u7d1a\u7d1b\u7d1c\u7d1d"
+ "\u7d21\u7d2c\u7d2e\u7d30\u7d31\u7d32\u7d33\u7d35"
+ "\u7d39\u7d3a\u7d3c\u7d3f\u7d40\u7d42\u7d43"
+ "\u7d44\u7d45\u7d46\u7d4e\u7d50\u7d55\u7d5b\u7d5d"
+ "\u7d5e\u7d61\u7d62\u7d66\u7d68\u7d70\u7d71"
+ "\u7d72\u7d73\u7d76\u7d79\u7d81\u7d83\u7d86\u7d88"
+ "\u7d89\u7d8c\u7d8f\u7d90\u7d91\u7d93\u7d9c"
+ "\u7d9e\u7da0\u7da2\u7da3\u7dab\u7dac\u7dad\u7daf"
+ "\u7db0\u7db1\u7db2\u7db3\u7db4\u7db5\u7db8"
+ "\u7db9\u7dba\u7dbb\u7dbd\u7dbe\u7dbf\u7dc4\u7dc7"
+ "\u7dca\u7dcb\u7dd1\u7dd2\u7dd3\u7dd4\u7dd7"
+ "\u7dd8\u7dd9\u7dda\u7ddd\u7dde\u7de0\u7de1\u7de3"
+ "\u7de6\u7de8\u7de9\u7dec\u7def\u7df1\u7df2"
+ "\u7df4\u7df6\u7df9\u7dfb\u7e08\u7e09\u7e0a\u7e0b"
+ "\u7e10\u7e11\u7e15\u7e17\u7e1b\u7e1d\u7e1e"
+ "\u7e1f\u7e23\u7e27\u7e2b\u7e2d\u7e2e\u7e31\u7e32"
+ "\u7e33\u7e34\u7e35\u7e36\u7e37\u7e39\u7e3d"
+ "\u7e3e\u7e43\u7e45\u7e46\u7e47\u7e52\u7e54\u7e55"
+ "\u7e5a\u7e5e\u7e61\u7e62\u7e69\u7e6a\u7e6b"
+ "\u7e6d\u7e6e\u7e6f\u7e70\u7e73\u7e78\u7e79\u7e7c"
+ "\u7e7d\u7e7e\u7e7f\u7e88\u7e8a\u7e8c\u7e8d"
+ "\u7e8f\u7e93\u7e94\u7e98\u7e9c\u7f3d\u7f48\u7f4c"
+ "\u7f4e\u7f63\u7f70\u7f75\u7f77\u7f85\u7f86"
+ "\u7f88\u7f8b\u7fa3\u7fa5\u7fa8\u7fa9\u7fb6\u7fd2"
+ "\u7feb\u7ff9\u7ffa\u802c\u802e\u8056\u805e"
+ "\u806f\u8070\u8072\u8073\u8075\u8076\u8077\u8079"
+ "\u807d\u807e\u8085\u8105\u8108\u811b\u8123"
+ "\u812b\u8139\u814e\u8156\u8161\u8166\u816b\u8173"
+ "\u8178\u8183\u819a\u81a0\u81a9\u81bd\u81be"
+ "\u81bf\u81c9\u81cd\u81cf\u81d8\u81da\u81df\u81e0"
+ "\u81e2\u81e5\u81e8\u81fa\u8207\u8208\u8209"
+ "\u820a\u8216\u8259\u8264\u8266\u826b\u8271\u8277"
+ "\u82bb\u8332\u834a\u8373\u838a\u8396\u83a2"
+ "\u83a7\u83d3\u83ef\u83f8\u8407\u840a\u842c\u8435"
+ "\u8449\u8452\u8464\u8466\u846f\u8477\u8490"
+ "\u8493\u8494\u849e\u84bc\u84c0\u84c6\u84cb\u84ee"
+ "\u84ef\u84fd\u8514\u851e\u8523\u8525\u8526"
+ "\u852d\u8534\u8541\u8546\u854e\u8552\u8553\u8555"
+ "\u8558\u8562\u8569\u856a\u856d\u8577\u8580"
+ "\u8588\u858a\u858c\u8591\u8594\u8598\u859f\u85a6"
+ "\u85a9\u85b0\u85b3\u85b4\u85ba\u85cd\u85ce"
+ "\u85dd\u85e5\u85ea\u85f4\u85f6\u85f7\u85f9\u85fa"
+ "\u8604\u8606\u8607\u860a\u860b\u861a\u861e"
+ "\u8622\u862d\u863a\u863f\u8646\u8655\u865b\u865c"
+ "\u865f\u8667\u866f\u86fa\u86fb\u8706\u8755"
+ "\u875f\u8766\u8768\u8778\u8784\u879e\u87a2\u87ae"
+ "\u87bb\u87bf\u87c4\u87c8\u87ce\u87e3\u87ec"
+ "\u87ef\u87f2\u87f6\u87fb\u8805\u8806\u880d\u8810"
+ "\u8811\u8814\u881f\u8823\u8827\u8828\u8831"
+ "\u8836\u883b\u8846\u884a\u8853\u8855\u885a\u885b"
+ "\u885d\u889e\u88b4\u88ca\u88cf\u88dc\u88dd"
+ "\u88e1\u88fd\u8907\u890c\u8918\u8932\u8933\u8938"
+ "\u893b\u8947\u894f\u8956\u895d\u8960\u8964"
+ "\u896a\u896c\u896f\u8972\u8988\u898b\u898e\u898f"
+ "\u8993\u8996\u8998\u89a1\u89a5\u89a6\u89aa"
+ "\u89ac\u89af\u89b2\u89b7\u89ba\u89bd\u89bf\u89c0"
+ "\u89f4\u89f6\u89f8\u8a01\u8a02\u8a03\u8a08"
+ "\u8a0a\u8a0c\u8a0e\u8a10\u8a12\u8a13\u8a15\u8a16"
+ "\u8a17\u8a18\u8a1b\u8a1d\u8a1f\u8a22\u8a23"
+ "\u8a25\u8a29\u8a2a\u8a2d\u8a31\u8a34\u8a36\u8a3a"
+ "\u8a3b\u8a3c\u8a41\u8a46\u8a4e\u8a50\u8a52"
+ "\u8a54\u8a55\u8a56\u8a57\u8a58\u8a5b\u8a5e\u8a60"
+ "\u8a61\u8a62\u8a63\u8a66\u8a69\u8a6b\u8a6c"
+ "\u8a6d\u8a6e\u8a70\u8a71\u8a72\u8a73\u8a75\u8a7c"
+ "\u8a7f\u8a84\u8a85\u8a86\u8a87\u8a8c\u8a8d"
+ "\u8a91\u8a92\u8a95\u8a98\u8a9a\u8a9e\u8aa0\u8aa1"
+ "\u8aa3\u8aa4\u8aa5\u8aa6\u8aa8\u8aaa\u8aac"
+ "\u8ab0\u8ab2\u8ab6\u8ab9\u8abc\u8abe\u8abf\u8ac2"
+ "\u8ac4\u8ac7\u8ac9\u8acb\u8acd\u8acf\u8ad1"
+ "\u8ad2\u8ad6\u8ad7\u8adb\u8adc\u8add\u8ade\u8ae1"
+ "\u8ae2\u8ae4\u8ae6\u8ae7\u8aeb\u8aed\u8aee"
+ "\u8af1\u8af3\u8af6\u8af7\u8af8\u8afa\u8afc\u8afe"
+ "\u8b00\u8b01\u8b02\u8b04\u8b05\u8b0a\u8b0e"
+ "\u8b10\u8b14\u8b16\u8b17\u8b19\u8b1a\u8b1b\u8b1d"
+ "\u8b20\u8b21\u8b28\u8b2b\u8b2c\u8b2d\u8b33"
+ "\u8b39\u8b3e\u8b41\u8b45\u8b49\u8b4e\u8b4f\u8b56"
+ "\u8b58\u8b59\u8b5a\u8b5c\u8b5f\u8b6b\u8b6f"
+ "\u8b70\u8b74\u8b77\u8b78\u8b7d\u8b7e\u8b80\u8b8a"
+ "\u8b8c\u8b8e\u8b92\u8b93\u8b95\u8b96\u8b9a"
+ "\u8b9c\u8b9e\u8c48\u8c4e\u8c50\u8c54\u8c6c\u8c76"
+ "\u8c8d\u8c93\u8c99\u8c9d\u8c9e\u8c9f\u8ca0"
+ "\u8ca1\u8ca2\u8ca7\u8ca8\u8ca9\u8caa\u8cab\u8cac"
+ "\u8caf\u8cb0\u8cb2\u8cb3\u8cb4\u8cb6\u8cb7"
+ "\u8cb8\u8cba\u8cbb\u8cbc\u8cbd\u8cbf\u8cc0\u8cc1"
+ "\u8cc2\u8cc3\u8cc4\u8cc5\u8cc7\u8cc8\u8cca"
+ "\u8cd1\u8cd2\u8cd3\u8cd5\u8cd9\u8cda\u8cdc\u8cde"
+ "\u8ce0\u8ce1\u8ce2\u8ce3\u8ce4\u8ce6\u8ce7"
+ "\u8cea\u8ceb\u8cec\u8ced\u8cf0\u8cf4\u8cf5\u8cf8"
+ "\u8cfa\u8cfb\u8cfc\u8cfd\u8cfe\u8d04\u8d05"
+ "\u8d07\u8d08\u8d0a\u8d0b\u8d0d\u8d0f\u8d10\u8d13"
+ "\u8d14\u8d16\u8d17\u8d1b\u8d1c\u8d6c\u8d95"
+ "\u8d99\u8da8\u8db2\u8de1\u8de4\u8dfc\u8e10\u8e21"
+ "\u8e30\u8e34\u8e4c\u8e55\u8e5f\u8e63\u8e64"
+ "\u8e67\u8e7a\u8e82\u8e89\u8e8a\u8e8b\u8e8d\u8e91"
+ "\u8e92\u8e93\u8e95\u8e9a\u8ea1\u8ea5\u8ea6"
+ "\u8eaa\u8ec0\u8eca\u8ecb\u8ecc\u8ecd\u8ed1\u8ed2"
+ "\u8ed4\u8edb\u8edf\u8ee4\u8eeb\u8ef2\u8ef8"
+ "\u8ef9\u8efa\u8efb\u8efc\u8efe\u8f03\u8f05\u8f07"
+ "\u8f08\u8f09\u8f0a\u8f12\u8f13\u8f14\u8f15"
+ "\u8f1b\u8f1c\u8f1d\u8f1e\u8f1f\u8f25\u8f26\u8f29"
+ "\u8f2a\u8f2c\u8f2f\u8f33\u8f38\u8f3b\u8f3e"
+ "\u8f3f\u8f40\u8f42\u8f44\u8f45\u8f46\u8f49\u8f4d"
+ "\u8f4e\u8f54\u8f5d\u8f5f\u8f61\u8f62\u8f64"
+ "\u8fa6\u8fad\u8fae\u8faf\u8fb2\u8ff4\u9015\u9019"
+ "\u9023\u9031\u9032\u904a\u904b\u904e\u9054"
+ "\u9055\u9059\u905c\u905e\u9060\u9069\u906f\u9072"
+ "\u9077\u9078\u907a\u907c\u9081\u9084\u9087"
+ "\u908a\u908f\u9090\u90df\u90f5\u9106\u9109\u9112"
+ "\u9114\u9116\u9127\u912d\u9130\u9132\u9134"
+ "\u9136\u913a\u9147\u9148\u9165\u9183\u9196\u919c"
+ "\u919e\u91ab\u91ac\u91b1\u91bc\u91c0\u91c1"
+ "\u91c3\u91c5\u91cb\u91d0\u91d2\u91d3\u91d4\u91d5"
+ "\u91d7\u91d8\u91d9\u91dd\u91e3\u91e4\u91e6"
+ "\u91e7\u91e9\u91f5\u91f7\u91f9\u91fa\u9200\u9201"
+ "\u9203\u9204\u9208\u9209\u920d\u920e\u9210"
+ "\u9211\u9212\u9214\u9215\u921e\u9223\u9225\u9226"
+ "\u9227\u922e\u9230\u9233\u9234\u9237\u9238"
+ "\u9239\u923a\u923d\u923e\u923f\u9240\u9245\u9248"
+ "\u9249\u924b\u924d\u9251\u9255\u9257\u925a"
+ "\u925b\u925e\u9262\u9264\u9266\u926c\u926d\u9276"
+ "\u9278\u927a\u927b\u927f\u9283\u9285\u928d"
+ "\u9291\u9293\u9296\u9298\u929a\u929b\u929c\u92a0"
+ "\u92a3\u92a5\u92a6\u92a8\u92a9\u92aa\u92ab"
+ "\u92ac\u92b1\u92b2\u92b3\u92b7\u92b9\u92bb\u92bc"
+ "\u92c1\u92c3\u92c5\u92c7\u92cc\u92cf\u92d2"
+ "\u92d9\u92dd\u92df\u92e3\u92e4\u92e5\u92e6\u92e8"
+ "\u92e9\u92ea\u92ed\u92ee\u92ef\u92f0\u92f1"
+ "\u92f6\u92f8\u92fc\u9301\u9304\u9306\u9307\u9308"
+ "\u930f\u9310\u9312\u9315\u9318\u9319\u931a"
+ "\u931b\u931f\u9320\u9321\u9322\u9326\u9328\u9329"
+ "\u932b\u932e\u932f\u9332\u9333\u9336\u9338"
+ "\u9340\u9341\u9343\u9346\u9347\u9348\u934a\u934b"
+ "\u934d\u9354\u9358\u935a\u935b\u9360\u9364"
+ "\u9365\u9369\u936c\u9370\u9375\u9376\u937a\u937e"
+ "\u9382\u9384\u9387\u938a\u9394\u9396\u9397"
+ "\u9398\u939a\u939b\u93a1\u93a2\u93a3\u93a6\u93a7"
+ "\u93a9\u93aa\u93ac\u93ae\u93b0\u93b2\u93b3"
+ "\u93b5\u93b8\u93bf\u93c3\u93c7\u93c8\u93cc\u93cd"
+ "\u93d0\u93d1\u93d7\u93d8\u93dc\u93dd\u93de"
+ "\u93df\u93e1\u93e2\u93e4\u93e8\u93f0\u93f5\u93f7"
+ "\u93f9\u93fd\u9403\u940b\u9410\u9412\u9413"
+ "\u9414\u9418\u9419\u941d\u9420\u9426\u9427\u9428"
+ "\u942b\u942e\u9432\u9433\u9435\u9436\u9438"
+ "\u943a\u943f\u9444\u944a\u944c\u9451\u9452\u9454"
+ "\u9455\u945e\u9460\u9463\u9465\u946d\u9470"
+ "\u9471\u9472\u9477\u9479\u947c\u947d\u947e\u947f"
+ "\u9481\u9577\u9580\u9582\u9583\u9586\u9588"
+ "\u9589\u958b\u958c\u958e\u958f\u9591\u9592\u9593"
+ "\u9594\u9598\u95a1\u95a2\u95a3\u95a5\u95a7"
+ "\u95a8\u95a9\u95ab\u95ac\u95ad\u95b1\u95b2\u95b6"
+ "\u95b9\u95bb\u95bc\u95bd\u95be\u95bf\u95c3"
+ "\u95c6\u95c7\u95c8\u95ca\u95cb\u95cc\u95cd\u95d0"
+ "\u95d2\u95d3\u95d4\u95d5\u95d6\u95d8\u95dc"
+ "\u95de\u95e0\u95e1\u95e2\u95e4\u95e5\u9628\u962a"
+ "\u9658\u965d\u965e\u9663\u9670\u9673\u9678"
+ "\u967d\u9684\u9689\u968a\u968e\u9695\u969b\u96a8"
+ "\u96aa\u96b1\u96b4\u96b8\u96bb\u96cb\u96d6"
+ "\u96d9\u96db\u96dc\u96de\u96e2\u96e3\u96f2\u96fb"
+ "\u9711\u9722\u9727\u973d\u9742\u9744\u9748"
+ "\u975a\u975c\u9766\u9768\u9777\u9780\u978f\u979d"
+ "\u97a6\u97bd\u97c1\u97c3\u97c6\u97c9\u97cb"
+ "\u97cc\u97cd\u97d3\u97d9\u97dc\u97de\u97ee\u97fb"
+ "\u97ff\u9801\u9802\u9803\u9805\u9806\u9807"
+ "\u9808\u980a\u980c\u980e\u980f\u9810\u9811\u9812"
+ "\u9813\u9817\u9818\u981c\u9821\u9824\u9826"
+ "\u982d\u982e\u9830\u9832\u9834\u9837\u9838\u9839"
+ "\u983b\u983d\u9846\u984c\u984d\u984e\u984f"
+ "\u9852\u9853\u9854\u9858\u9859\u985b\u985e\u9862"
+ "\u9865\u9867\u986b\u986c\u986f\u9870\u9871"
+ "\u9873\u9874\u98a8\u98ad\u98ae\u98af\u98b1\u98b3"
+ "\u98b6\u98b8\u98ba\u98bb\u98bc\u98c0\u98c4"
+ "\u98c6\u98c8\u98db\u98e0\u98e2\u98e3\u98e5\u98e9"
+ "\u98ea\u98eb\u98ed\u98ef\u98f2\u98f4\u98fc"
+ "\u98fd\u98fe\u98ff\u9903\u9904\u9905\u9909\u990a"
+ "\u990c\u990e\u990f\u9911\u9912\u9913\u9915"
+ "\u9916\u9918\u991a\u991b\u991c\u991e\u9921\u9928"
+ "\u992c\u9931\u9933\u9935\u9936\u9937\u993a"
+ "\u993c\u993d\u993e\u993f\u9941\u9943\u9945\u9948"
+ "\u9949\u994a\u994b\u994c\u9951\u9952\u9957"
+ "\u995c\u995e\u9962\u99ac\u99ad\u99ae\u99b1\u99b3"
+ "\u99b4\u99b9\u99c1\u99d0\u99d1\u99d2\u99d4"
+ "\u99d5\u99d8\u99d9\u99db\u99dd\u99df\u99e1\u99e2"
+ "\u99ed\u99f0\u99f1\u99f8\u99ff\u9a01\u9a02"
+ "\u9a05\u9a0c\u9a0d\u9a0e\u9a0f\u9a16\u9a19\u9a24"
+ "\u9a27\u9a2b\u9a2d\u9a2e\u9a30\u9a36\u9a37"
+ "\u9a38\u9a3e\u9a40\u9a41\u9a42\u9a43\u9a44\u9a45"
+ "\u9a4a\u9a4c\u9a4d\u9a4f\u9a55\u9a57\u9a5a"
+ "\u9a5b\u9a5f\u9a62\u9a64\u9a65\u9a66\u9a6a\u9a6b"
+ "\u9aaf\u9acf\u9ad2\u9ad4\u9ad5\u9ad6\u9b00"
+ "\u9b06\u9b0d\u9b1a\u9b22\u9b25\u9b27\u9b28\u9b29"
+ "\u9b2d\u9b2e\u9b31\u9b4e\u9b58\u9b5a\u9b5b"
+ "\u9b62\u9b68\u9b6f\u9b74\u9b77\u9b7a\u9b81\u9b83"
+ "\u9b8a\u9b8b\u9b8d\u9b8e\u9b90\u9b91\u9b92"
+ "\u9b93\u9b9a\u9b9c\u9b9d\u9b9e\u9ba6\u9baa\u9bab"
+ "\u9bad\u9bae\u9bb3\u9bb6\u9bba\u9bc0\u9bc1"
+ "\u9bc7\u9bc9\u9bca\u9bd2\u9bd4\u9bd5\u9bd6\u9bdb"
+ "\u9bdd\u9be1\u9be2\u9be4\u9be7\u9be8\u9bea"
+ "\u9beb\u9bf0\u9bf4\u9bf7\u9bfd\u9bff\u9c01\u9c02"
+ "\u9c03\u9c08\u9c09\u9c0d\u9c0f\u9c10\u9c12"
+ "\u9c13\u9c1c\u9c1f\u9c20\u9c23\u9c25\u9c28\u9c29"
+ "\u9c2d\u9c2e\u9c31\u9c32\u9c33\u9c35\u9c37"
+ "\u9c39\u9c3a\u9c3b\u9c3c\u9c3e\u9c42\u9c45\u9c48"
+ "\u9c49\u9c52\u9c54\u9c56\u9c57\u9c58\u9c5d"
+ "\u9c5f\u9c60\u9c63\u9c64\u9c67\u9c68\u9c6d\u9c6f"
+ "\u9c77\u9c78\u9c7a\u9ce5\u9ce7\u9ce9\u9cec"
+ "\u9cf2\u9cf3\u9cf4\u9cf6\u9cfe\u9d06\u9d07\u9d09"
+ "\u9d12\u9d15\u9d1b\u9d1d\u9d1e\u9d1f\u9d23"
+ "\u9d26\u9d28\u9d2f\u9d30\u9d34\u9d37\u9d3b\u9d3f"
+ "\u9d41\u9d42\u9d43\u9d50\u9d51\u9d52\u9d53"
+ "\u9d5c\u9d5d\u9d60\u9d61\u9d6a\u9d6c\u9d6e\u9d6f"
+ "\u9d72\u9d77\u9d7e\u9d84\u9d87\u9d89\u9d8a"
+ "\u9d93\u9d96\u9d98\u9d9a\u9da1\u9da5\u9da9\u9daa"
+ "\u9dac\u9daf\u9db2\u9db4\u9db9\u9dba\u9dbb"
+ "\u9dbc\u9dc0\u9dc1\u9dc2\u9dc4\u9dc8\u9dca\u9dd3"
+ "\u9dd6\u9dd7\u9dd9\u9dda\u9de5\u9de6\u9deb"
+ "\u9def\u9df2\u9df3\u9df8\u9df9\u9dfa\u9dfd\u9dff"
+ "\u9e02\u9e07\u9e0c\u9e0f\u9e15\u9e18\u9e1a"
+ "\u9e1b\u9e1d\u9e1e\u9e75\u9e79\u9e7a\u9e7c\u9e7d"
+ "\u9e97\u9ea4\u9ea5\u9ea9\u9eaf\u9eb5\u9ebc"
+ "\u9ebd\u9ec3\u9ecc\u9ede\u9ee8\u9ef2\u9ef4\u9ef6"
+ "\u9ef7\u9efd\u9eff\u9f07\u9f08\u9f09\u9f15"
+ "\u9f34\u9f4a\u9f4b\u9f4e\u9f4f\u9f52\u9f54\u9f55"
+ "\u9f57\u9f59\u9f5c\u9f5f\u9f60\u9f61\u9f63"
+ "\u9f66\u9f67\u9f69\u9f6a\u9f6c\u9f72\u9f76\u9f77"
+ "\u9f8d\u9f8e\u9f90\u9f94\u9f95\u9f9c]";
+
+ // Create UnicodeSets for zh-Hans and zh-Hant for later reference.
+ UErrorCode status = U_ZERO_ERROR;
+ hans_set_.reset(new icu::UnicodeSet(
+ icu::UnicodeString::fromUTF8(hans_codepoints), status));
+ DVLOG(1) << u_errorName(status);
+ hant_set_.reset(new icu::UnicodeSet(
+ icu::UnicodeString::fromUTF8(hant_codepoints), status));
+ DVLOG(1) << u_errorName(status);
+
+ // Make these sets immutable. This keeps the class threadsafe and
+ // makes certain operations on these sets faster.
+ hans_set_->freeze();
+ hant_set_->freeze();
}
bool ChineseScriptClassifier::IsInitialized() const {
- return hans2hant_ && hant2hans_;
+ return hans_set_ && hant_set_;
}
ChineseScriptClassifier::~ChineseScriptClassifier() {}
@@ -61,56 +786,21 @@ std::string ChineseScriptClassifier::Classify(const std::string& input) const {
base::IsUnicodeWhitespace),
input_subset.end());
- // Convert two copies of the input to icu::UnicodeString. Two copies are
- // necessary because transliteration happens in place only.
- icu::UnicodeString original_input =
+ // Convert the input to icu::UnicodeString so we can iterate over codepoints.
+ icu::UnicodeString input_codepoints =
icu::UnicodeString::fromUTF8(input_subset);
- icu::UnicodeString hant_input = icu::UnicodeString::fromUTF8(input_subset);
- icu::UnicodeString hans_input = icu::UnicodeString::fromUTF8(input_subset);
-
- // Get the zh-Hant version of this input.
- hans2hant_->transliterate(hant_input);
- // Get the zh-Hans version of this input.
- hant2hans_->transliterate(hans_input);
-
- // Debugging only: show the input, the Hant version, and the Hans version.
- if (VLOG_IS_ON(1)) {
- std::string hant_string;
- std::string hans_string;
- hans_input.toUTF8String(hans_string);
- hant_input.toUTF8String(hant_string);
- DVLOG(1) << "Original input:\n" << input_subset;
- DVLOG(1) << "zh-Hant output:\n" << hant_string;
- DVLOG(1) << "zh-Hans output:\n" << hans_string;
- }
// Count matches between the original input chars and the Hant and Hans
// versions of the input.
int hant_count = 0;
int hans_count = 0;
- // Iterate over all chars in the original input and compute matches between
- // the Hant version and the Hans version.
- //
- // All segments (original, Hant, and Hans) should have the same length, but
- // in case of some corner case or bug in which they turn out not to be,
- // we compute the minimum length we are allowed to traverse.
- const int min_length =
- std::min(original_input.length(),
- std::min(hans_input.length(), hant_input.length()));
- for (int index = 0; index < min_length; ++index) {
- const auto original_char = original_input.charAt(index);
- const auto hans_char = hans_input.charAt(index);
- const auto hant_char = hant_input.charAt(index);
- if (hans_char == hant_char) {
- continue;
- } else if (original_char == hans_char) {
- // Hans-specific char found.
+ for (int index = 0; index < input_codepoints.length(); ++index) {
+ const auto codepoint = input_codepoints.charAt(index);
+ if (hans_set_->contains(codepoint))
++hans_count;
- } else if (original_char == hant_char) {
- // Hant-specific char found.
+ if (hant_set_->contains(codepoint))
++hant_count;
- }
}
DVLOG(1) << "Found " << hans_count << " zh-Hans chars in input";
DVLOG(1) << "Found " << hant_count << " zh-Hant chars in input";
« no previous file with comments | « components/translate/core/language_detection/chinese_script_classifier.h ('k') | no next file » | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698