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 "tokenizer.h"
18
19 #include <string>
20 #include <vector>
21
22 #include <gtest/gtest.h>
23
24 namespace android {
25 namespace init {
26
27 namespace {
28
RunTest(const std::string & data,const std::vector<std::vector<std::string>> & expected_tokens)29 void RunTest(const std::string& data, const std::vector<std::vector<std::string>>& expected_tokens) {
30 auto data_copy = std::string{data};
31 data_copy.push_back('\n');
32 data_copy.push_back('\0');
33
34 parse_state state;
35 state.line = 0;
36 state.ptr = data_copy.data();
37 state.nexttoken = 0;
38
39 std::vector<std::string> current_line;
40 std::vector<std::vector<std::string>> tokens;
41
42 while (true) {
43 switch (next_token(&state)) {
44 case T_EOF:
45 EXPECT_EQ(expected_tokens, tokens) << data;
46 return;
47 case T_NEWLINE:
48 tokens.emplace_back(std::move(current_line));
49 current_line.clear();
50 break;
51 case T_TEXT:
52 current_line.emplace_back(state.text);
53 break;
54 }
55 }
56 }
57
58 } // namespace
59
TEST(tokenizer,null)60 TEST(tokenizer, null) {
61 RunTest("", {{}});
62 }
63
TEST(tokenizer,simple_oneline)64 TEST(tokenizer, simple_oneline) {
65 RunTest("one two\tthree\rfour", {{"one", "two", "three", "four"}});
66 }
67
TEST(tokenizer,simple_multiline)68 TEST(tokenizer, simple_multiline) {
69 RunTest("1 2 3\n4 5 6\n7 8 9", {{"1", "2", "3"}, {"4", "5", "6"}, {"7", "8", "9"}});
70 }
71
TEST(tokenizer,preceding_space)72 TEST(tokenizer, preceding_space) {
73 // Preceding spaces are ignored.
74 RunTest(" 1 2 3\n\t\t\t\t4 5 6\n\r\r\r\r7 8 9",
75 {{"1", "2", "3"}, {"4", "5", "6"}, {"7", "8", "9"}});
76 }
77
TEST(tokenizer,comments)78 TEST(tokenizer, comments) {
79 // Entirely commented lines still produce a T_NEWLINE token for tracking line count.
80 RunTest("1 2 3\n#4 5 6\n7 8 9", {{"1", "2", "3"}, {}, {"7", "8", "9"}});
81
82 RunTest("#1 2 3\n4 5 6\n7 8 9", {{}, {"4", "5", "6"}, {"7", "8", "9"}});
83
84 RunTest("1 2 3\n4 5 6\n#7 8 9", {{"1", "2", "3"}, {"4", "5", "6"}, {}});
85
86 RunTest("1 2 #3\n4 #5 6\n#7 8 9", {{"1", "2"}, {"4"}, {}});
87 }
88
TEST(tokenizer,control_chars)89 TEST(tokenizer, control_chars) {
90 // Literal \n, \r, \t, and \\ produce the control characters \n, \r, \t, and \\ respectively.
91 // Literal \? produces ? for all other character '?'
92
93 RunTest(R"(1 token\ntoken 2)", {{"1", "token\ntoken", "2"}});
94 RunTest(R"(1 token\rtoken 2)", {{"1", "token\rtoken", "2"}});
95 RunTest(R"(1 token\ttoken 2)", {{"1", "token\ttoken", "2"}});
96 RunTest(R"(1 token\\token 2)", {{"1", "token\\token", "2"}});
97 RunTest(R"(1 token\btoken 2)", {{"1", "tokenbtoken", "2"}});
98
99 RunTest(R"(1 token\n 2)", {{"1", "token\n", "2"}});
100 RunTest(R"(1 token\r 2)", {{"1", "token\r", "2"}});
101 RunTest(R"(1 token\t 2)", {{"1", "token\t", "2"}});
102 RunTest(R"(1 token\\ 2)", {{"1", "token\\", "2"}});
103 RunTest(R"(1 token\b 2)", {{"1", "tokenb", "2"}});
104
105 RunTest(R"(1 \ntoken 2)", {{"1", "\ntoken", "2"}});
106 RunTest(R"(1 \rtoken 2)", {{"1", "\rtoken", "2"}});
107 RunTest(R"(1 \ttoken 2)", {{"1", "\ttoken", "2"}});
108 RunTest(R"(1 \\token 2)", {{"1", "\\token", "2"}});
109 RunTest(R"(1 \btoken 2)", {{"1", "btoken", "2"}});
110
111 RunTest(R"(1 \n 2)", {{"1", "\n", "2"}});
112 RunTest(R"(1 \r 2)", {{"1", "\r", "2"}});
113 RunTest(R"(1 \t 2)", {{"1", "\t", "2"}});
114 RunTest(R"(1 \\ 2)", {{"1", "\\", "2"}});
115 RunTest(R"(1 \b 2)", {{"1", "b", "2"}});
116 }
117
TEST(tokenizer,cr_lf)118 TEST(tokenizer, cr_lf) {
119 // \ before \n, \r, or \r\n is interpreted as a line continuation
120 // Extra whitespace on the next line is eaten, except \r unlike in the above tests.
121
122 RunTest("lf\\\ncont", {{"lfcont"}});
123 RunTest("lf\\\n \t\t\t\tcont", {{"lfcont"}});
124
125 RunTest("crlf\\\r\ncont", {{"crlfcont"}});
126 RunTest("crlf\\\r\n \t\t\t\tcont", {{"crlfcont"}});
127
128 RunTest("cr\\\rcont", {{"crcont"}});
129
130 RunTest("lfspace \\\ncont", {{"lfspace", "cont"}});
131 RunTest("lfspace \\\n \t\t\t\tcont", {{"lfspace", "cont"}});
132
133 RunTest("crlfspace \\\r\ncont", {{"crlfspace", "cont"}});
134 RunTest("crlfspace \\\r\n \t\t\t\tcont", {{"crlfspace", "cont"}});
135
136 RunTest("crspace \\\rcont", {{"crspace", "cont"}});
137 }
138
TEST(tokenizer,quoted)139 TEST(tokenizer, quoted) {
140 RunTest("\"quoted simple string\"", {{"quoted simple string"}});
141
142 // Unterminated quotes just return T_EOF without any T_NEWLINE.
143 RunTest("\"unterminated quoted string", {});
144
145 RunTest("\"1 2 3\"\n \"unterminated quoted string", {{"1 2 3"}});
146
147 // Escaping quotes is not allowed and are treated as an unterminated quoted string.
148 RunTest("\"quoted escaped quote\\\"\"", {});
149 RunTest("\"quoted escaped\\\" quote\"", {});
150 RunTest("\"\\\"quoted escaped quote\"", {});
151
152 RunTest("\"quoted control characters \\n \\r \\t \\\\ \\b \\\r \\\n \r \n\"",
153 {{"quoted control characters \\n \\r \\t \\\\ \\b \\\r \\\n \r \n"}});
154
155 RunTest("\"quoted simple string\" \"second quoted string\"",
156 {{"quoted simple string", "second quoted string"}});
157
158 RunTest("\"# comment quoted string\"", {{"# comment quoted string"}});
159
160 RunTest("\"Adjacent \"\"quoted strings\"", {{"Adjacent quoted strings"}});
161 }
162
163 } // namespace init
164 } // namespace android
165