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
24 namespace libtextclassifier3 {
25
UncompressMakeRegexPattern(const UniLib & unilib,const flatbuffers::String * uncompressed_pattern,const CompressedBuffer * compressed_pattern,bool lazy_compile_regex,ZlibDecompressor * decompressor,std::string * result_pattern_text)26 std::unique_ptr<UniLib::RegexPattern> UncompressMakeRegexPattern(
27 const UniLib& unilib, const flatbuffers::String* uncompressed_pattern,
28 const CompressedBuffer* compressed_pattern, bool lazy_compile_regex,
29 ZlibDecompressor* decompressor, std::string* result_pattern_text) {
30 UnicodeText unicode_regex_pattern;
31 std::string decompressed_pattern;
32 if (compressed_pattern != nullptr &&
33 compressed_pattern->buffer() != nullptr) {
34 if (decompressor == nullptr ||
35 !decompressor->MaybeDecompress(compressed_pattern,
36 &decompressed_pattern)) {
37 TC3_LOG(ERROR) << "Cannot decompress pattern.";
38 return nullptr;
39 }
40 unicode_regex_pattern =
41 UTF8ToUnicodeText(decompressed_pattern.data(),
42 decompressed_pattern.size(), /*do_copy=*/false);
43 } else {
44 if (uncompressed_pattern == nullptr) {
45 TC3_LOG(ERROR) << "Cannot load uncompressed pattern.";
46 return nullptr;
47 }
48 unicode_regex_pattern =
49 UTF8ToUnicodeText(uncompressed_pattern->c_str(),
50 uncompressed_pattern->Length(), /*do_copy=*/false);
51 }
52
53 if (result_pattern_text != nullptr) {
54 *result_pattern_text = unicode_regex_pattern.ToUTF8String();
55 }
56
57 std::unique_ptr<UniLib::RegexPattern> regex_pattern;
58 if (lazy_compile_regex) {
59 regex_pattern = unilib.CreateLazyRegexPattern(unicode_regex_pattern);
60 } else {
61 regex_pattern = unilib.CreateRegexPattern(unicode_regex_pattern);
62 }
63
64 if (!regex_pattern) {
65 TC3_LOG(ERROR) << "Could not create pattern: "
66 << unicode_regex_pattern.ToUTF8String();
67 }
68 return regex_pattern;
69 }
70
71 } // namespace libtextclassifier3
72