1 /*
2 * Copyright (C) 2018 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17 #include "utils/zlib/zlib_regex.h"
18
19 #include <memory>
20
21 #include "utils/base/logging.h"
22 #include "utils/flatbuffers.h"
23 #include "utils/utf8/unicodetext.h"
24
25 namespace libtextclassifier3 {
26
UncompressMakeRegexPattern(const UniLib & unilib,const flatbuffers::String * uncompressed_pattern,const CompressedBuffer * compressed_pattern,bool lazy_compile_regex,ZlibDecompressor * decompressor,std::string * result_pattern_text)27 std::unique_ptr<UniLib::RegexPattern> UncompressMakeRegexPattern(
28 const UniLib& unilib, const flatbuffers::String* uncompressed_pattern,
29 const CompressedBuffer* compressed_pattern, bool lazy_compile_regex,
30 ZlibDecompressor* decompressor, std::string* result_pattern_text) {
31 UnicodeText unicode_regex_pattern;
32 std::string decompressed_pattern;
33 if (compressed_pattern != nullptr &&
34 compressed_pattern->buffer() != nullptr) {
35 if (decompressor == nullptr ||
36 !decompressor->MaybeDecompress(compressed_pattern,
37 &decompressed_pattern)) {
38 TC3_LOG(ERROR) << "Cannot decompress pattern.";
39 return nullptr;
40 }
41 unicode_regex_pattern =
42 UTF8ToUnicodeText(decompressed_pattern.data(),
43 decompressed_pattern.size(), /*do_copy=*/false);
44 } else {
45 if (uncompressed_pattern == nullptr) {
46 TC3_LOG(ERROR) << "Cannot load uncompressed pattern.";
47 return nullptr;
48 }
49 unicode_regex_pattern =
50 UTF8ToUnicodeText(uncompressed_pattern->c_str(),
51 uncompressed_pattern->Length(), /*do_copy=*/false);
52 }
53
54 if (result_pattern_text != nullptr) {
55 *result_pattern_text = unicode_regex_pattern.ToUTF8String();
56 }
57
58 std::unique_ptr<UniLib::RegexPattern> regex_pattern;
59 if (lazy_compile_regex) {
60 regex_pattern = unilib.CreateLazyRegexPattern(unicode_regex_pattern);
61 } else {
62 regex_pattern = unilib.CreateRegexPattern(unicode_regex_pattern);
63 }
64
65 if (!regex_pattern) {
66 TC3_LOG(ERROR) << "Could not create pattern: "
67 << unicode_regex_pattern.ToUTF8String();
68 }
69 return regex_pattern;
70 }
71
72 } // namespace libtextclassifier3
73