1 // Copyright 2016 PDFium Authors. All rights reserved. 2 // Use of this source code is governed by a BSD-style license that can be 3 // found in the LICENSE file. 4 5 #include "core/fpdfapi/parser/cpdf_simple_parser.h" 6 7 #include <string> 8 9 #include "core/fpdfapi/parser/fpdf_parser_utility.h" 10 #include "testing/gtest/include/gtest/gtest.h" 11 #include "testing/test_support.h" 12 13 TEST(SimpleParserTest, GetWord) { 14 static const pdfium::StrFuncTestData test_data[] = { 15 // Empty src string. 16 STR_IN_OUT_CASE("", ""), 17 // Content with whitespaces only. 18 STR_IN_OUT_CASE(" \t \0 \n", ""), 19 // Content with comments only. 20 STR_IN_OUT_CASE("%this is a test case\r\n%2nd line", ""), 21 // Mixed whitespaces and comments. 22 STR_IN_OUT_CASE(" \t \0%try()%haha\n %another line \aa", ""), 23 // Name. 24 STR_IN_OUT_CASE(" /Tester ", "/Tester"), 25 // String. 26 STR_IN_OUT_CASE("\t(nice day)!\n ", "(nice day)"), 27 // String with nested braces. 28 STR_IN_OUT_CASE("\t(It is a (long) day)!\n ", "(It is a (long) day)"), 29 // String with escaped chars. 30 STR_IN_OUT_CASE("\t(It is a \\(long\\) day!)hi\n ", 31 "(It is a \\(long\\) day!)"), 32 // Hex string. 33 STR_IN_OUT_CASE(" \n<4545acdfedertt>abc ", "<4545acdfedertt>"), 34 STR_IN_OUT_CASE(" \n<4545a<ed>ertt>abc ", "<4545a<ed>"), 35 // Dictionary. 36 STR_IN_OUT_CASE("<</oc 234 /color 2 3 R>>", "<<"), 37 STR_IN_OUT_CASE("\t\t<< /abc>>", "<<"), 38 // Handling ending delimiters. 39 STR_IN_OUT_CASE("> little bear", ">"), 40 STR_IN_OUT_CASE(") another bear", ")"), STR_IN_OUT_CASE(">> end ", ">>"), 41 // No ending delimiters. 42 STR_IN_OUT_CASE("(sdfgfgbcv", "(sdfgfgbcv"), 43 // Regular cases. 44 STR_IN_OUT_CASE("apple pear", "apple"), 45 STR_IN_OUT_CASE(" pi=3.1415 ", "pi=3.1415"), 46 STR_IN_OUT_CASE(" p t x c ", "p"), STR_IN_OUT_CASE(" pt\0xc ", "pt"), 47 STR_IN_OUT_CASE(" $^&&*\t\0sdff ", "$^&&*"), 48 STR_IN_OUT_CASE("\n\r+3.5656 -11.0", "+3.5656"), 49 }; 50 for (size_t i = 0; i < FX_ArraySize(test_data); ++i) { 51 const pdfium::StrFuncTestData& data = test_data[i]; 52 CPDF_SimpleParser parser(data.input, data.input_size); 53 ByteStringView word = parser.GetWord(); 54 EXPECT_EQ(data.expected_size, word.GetLength()) << " for case " << i; 55 if (data.expected_size != word.GetLength()) 56 continue; 57 EXPECT_EQ( 58 0, memcmp(data.expected, word.unterminated_c_str(), data.expected_size)) 59 << " for case " << i; 60 } 61 } 62 63 TEST(SimpleParserTest, FindTagParamFromStart) { 64 static const struct FindTagTestStruct { 65 const unsigned char* input; 66 unsigned int input_size; 67 const char* token; 68 int num_params; 69 bool result; 70 unsigned int result_pos; 71 } test_data[] = { 72 // Empty strings. 73 STR_IN_TEST_CASE("", "Tj", 1, false, 0), 74 STR_IN_TEST_CASE("", "", 1, false, 0), 75 // Empty token. 76 STR_IN_TEST_CASE(" T j", "", 1, false, 5), 77 // No parameter. 78 STR_IN_TEST_CASE("Tj", "Tj", 1, false, 2), 79 STR_IN_TEST_CASE("(Tj", "Tj", 1, false, 3), 80 // Partial token match. 81 STR_IN_TEST_CASE("\r12\t34 56 78Tj", "Tj", 1, false, 15), 82 // Regular cases with various parameters. 83 STR_IN_TEST_CASE("\r\0abd Tj", "Tj", 1, true, 0), 84 STR_IN_TEST_CASE("12 4 Tj 3 46 Tj", "Tj", 1, true, 2), 85 STR_IN_TEST_CASE("er^ 2 (34) (5667) Tj", "Tj", 2, true, 5), 86 STR_IN_TEST_CASE("<344> (232)\t343.4\n12 45 Tj", "Tj", 3, true, 11), 87 STR_IN_TEST_CASE("1 2 3 4 5 6 7 8 cm", "cm", 6, true, 3), 88 }; 89 for (size_t i = 0; i < FX_ArraySize(test_data); ++i) { 90 const FindTagTestStruct& data = test_data[i]; 91 CPDF_SimpleParser parser(data.input, data.input_size); 92 EXPECT_EQ(data.result, 93 parser.FindTagParamFromStart(data.token, data.num_params)) 94 << " for case " << i; 95 EXPECT_EQ(data.result_pos, parser.GetCurPos()) << " for case " << i; 96 } 97 } 98