Shimeng (Simon) Wang | 8a31eba | 2010-12-06 19:01:33 -0800 | [diff] [blame^] | 1 | // Copyright 2010 the V8 project authors. All rights reserved. |
| 2 | // Redistribution and use in source and binary forms, with or without |
| 3 | // modification, are permitted provided that the following conditions are |
| 4 | // met: |
| 5 | // |
| 6 | // * Redistributions of source code must retain the above copyright |
| 7 | // notice, this list of conditions and the following disclaimer. |
| 8 | // * Redistributions in binary form must reproduce the above |
| 9 | // copyright notice, this list of conditions and the following |
| 10 | // disclaimer in the documentation and/or other materials provided |
| 11 | // with the distribution. |
| 12 | // * Neither the name of Google Inc. nor the names of its |
| 13 | // contributors may be used to endorse or promote products derived |
| 14 | // from this software without specific prior written permission. |
| 15 | // |
| 16 | // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 17 | // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 18 | // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 19 | // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 20 | // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 21 | // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 22 | // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 23 | // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 24 | // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 25 | // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 26 | // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 27 | |
| 28 | #include <stdarg.h> |
| 29 | #include "../include/v8stdint.h" |
| 30 | #include "globals.h" |
| 31 | #include "checks.h" |
| 32 | #include "allocation.h" |
| 33 | #include "utils.h" |
| 34 | #include "list.h" |
| 35 | #include "smart-pointer.h" |
| 36 | #include "scanner-base.h" |
| 37 | #include "preparse-data.h" |
| 38 | #include "preparser.h" |
| 39 | |
| 40 | enum ResultCode { kSuccess = 0, kErrorReading = 1, kErrorWriting = 2 }; |
| 41 | |
| 42 | namespace v8 { |
| 43 | namespace internal { |
| 44 | |
| 45 | // THIS FILE IS PROOF-OF-CONCEPT ONLY. |
| 46 | // The final goal is a stand-alone preparser library. |
| 47 | |
| 48 | // UTF16Buffer based on an UTF-8 string in memory. |
| 49 | class UTF8UTF16Buffer : public UTF16Buffer { |
| 50 | public: |
| 51 | UTF8UTF16Buffer(uint8_t* buffer, size_t length) |
| 52 | : UTF16Buffer(), |
| 53 | buffer_(buffer), |
| 54 | offset_(0), |
| 55 | end_offset_(static_cast<int>(length)) { } |
| 56 | |
| 57 | virtual void PushBack(uc32 ch) { |
| 58 | // Pushback assumes that the character pushed back is the |
| 59 | // one that was most recently read, and jumps back in the |
| 60 | // UTF-8 stream by the length of that character's encoding. |
| 61 | offset_ -= unibrow::Utf8::Length(ch); |
| 62 | pos_--; |
| 63 | #ifdef DEBUG |
| 64 | int tmp = 0; |
| 65 | ASSERT_EQ(ch, unibrow::Utf8::ValueOf(buffer_ + offset_, |
| 66 | end_offset_ - offset_, |
| 67 | &tmp); |
| 68 | #endif |
| 69 | } |
| 70 | |
| 71 | virtual uc32 Advance() { |
| 72 | if (offset_ == end_offset_) return -1; |
| 73 | uint8_t first_char = buffer_[offset_]; |
| 74 | if (first_char <= unibrow::Utf8::kMaxOneByteChar) { |
| 75 | pos_++; |
| 76 | offset_++; |
| 77 | return static_cast<uc32>(first_char); |
| 78 | } |
| 79 | unibrow::uchar codepoint = |
| 80 | unibrow::Utf8::CalculateValue(buffer_ + offset_, |
| 81 | end_offset_ - offset_, |
| 82 | &offset_); |
| 83 | pos_++; |
| 84 | return static_cast<uc32>(codepoint); |
| 85 | } |
| 86 | |
| 87 | virtual void SeekForward(int pos) { |
| 88 | while (pos_ < pos) { |
| 89 | uint8_t first_byte = buffer_[offset_++]; |
| 90 | while (first_byte & 0x80u && offset_ < end_offset_) { |
| 91 | offset_++; |
| 92 | first_byte <<= 1; |
| 93 | } |
| 94 | pos_++; |
| 95 | } |
| 96 | } |
| 97 | |
| 98 | private: |
| 99 | const uint8_t* buffer_; |
| 100 | unsigned offset_; |
| 101 | unsigned end_offset_; |
| 102 | }; |
| 103 | |
| 104 | |
| 105 | class StandAloneJavaScriptScanner : public JavaScriptScanner { |
| 106 | public: |
| 107 | void Initialize(UTF16Buffer* source) { |
| 108 | source_ = source; |
| 109 | literal_flags_ = kLiteralString | kLiteralIdentifier; |
| 110 | Init(); |
| 111 | // Skip initial whitespace allowing HTML comment ends just like |
| 112 | // after a newline and scan first token. |
| 113 | has_line_terminator_before_next_ = true; |
| 114 | SkipWhiteSpace(); |
| 115 | Scan(); |
| 116 | } |
| 117 | }; |
| 118 | |
| 119 | |
| 120 | // Write a number to dest in network byte order. |
| 121 | void WriteUInt32(FILE* dest, uint32_t value, bool* ok) { |
| 122 | for (int i = 3; i >= 0; i--) { |
| 123 | uint8_t byte = static_cast<uint8_t>(value >> (i << 3)); |
| 124 | int result = fputc(byte, dest); |
| 125 | if (result == EOF) { |
| 126 | *ok = false; |
| 127 | return; |
| 128 | } |
| 129 | } |
| 130 | } |
| 131 | |
| 132 | // Read number from FILE* in network byte order. |
| 133 | uint32_t ReadUInt32(FILE* source, bool* ok) { |
| 134 | uint32_t n = 0; |
| 135 | for (int i = 0; i < 4; i++) { |
| 136 | int c = fgetc(source); |
| 137 | if (c == EOF) { |
| 138 | *ok = false; |
| 139 | return 0; |
| 140 | } |
| 141 | n = (n << 8) + static_cast<uint32_t>(c); |
| 142 | } |
| 143 | return n; |
| 144 | } |
| 145 | |
| 146 | |
| 147 | bool ReadBuffer(FILE* source, void* buffer, size_t length) { |
| 148 | size_t actually_read = fread(buffer, 1, length, stdin); |
| 149 | return (actually_read == length); |
| 150 | } |
| 151 | |
| 152 | |
| 153 | bool WriteBuffer(FILE* dest, void* buffer, size_t length) { |
| 154 | size_t actually_written = fwrite(buffer, 1, length, dest); |
| 155 | return (actually_written == length); |
| 156 | } |
| 157 | |
| 158 | // Preparse stdin and output result on stdout. |
| 159 | int PreParseIO() { |
| 160 | fprintf(stderr, "LOG: Enter parsing loop\n"); |
| 161 | bool ok = true; |
| 162 | uint32_t length = ReadUInt32(stdin, &ok); |
| 163 | if (!ok) return kErrorReading; |
| 164 | SmartPointer<byte> buffer(NewArray<byte>(length)); |
| 165 | if (!ReadBuffer(stdin, *buffer, length)) { |
| 166 | return kErrorReading; |
| 167 | } |
| 168 | UTF8UTF16Buffer input_buffer(*buffer, static_cast<size_t>(length)); |
| 169 | StandAloneJavaScriptScanner scanner; |
| 170 | scanner.Initialize(&input_buffer); |
| 171 | CompleteParserRecorder recorder; |
| 172 | preparser::PreParser preparser; |
| 173 | |
| 174 | if (!preparser.PreParseProgram(&scanner, &recorder, true)) { |
| 175 | if (scanner.stack_overflow()) { |
| 176 | // Report stack overflow error/no-preparser-data. |
| 177 | WriteUInt32(stdout, 0, &ok); |
| 178 | if (!ok) return kErrorWriting; |
| 179 | return 0; |
| 180 | } |
| 181 | } |
| 182 | Vector<unsigned> pre_data = recorder.ExtractData(); |
| 183 | |
| 184 | uint32_t size = static_cast<uint32_t>(pre_data.length() * sizeof(uint32_t)); |
| 185 | WriteUInt32(stdout, size, &ok); |
| 186 | if (!ok) return kErrorWriting; |
| 187 | if (!WriteBuffer(stdout, |
| 188 | reinterpret_cast<byte*>(pre_data.start()), |
| 189 | size)) { |
| 190 | return kErrorWriting; |
| 191 | } |
| 192 | return 0; |
| 193 | } |
| 194 | |
| 195 | // Functions declared by allocation.h |
| 196 | |
| 197 | void FatalProcessOutOfMemory(const char* location) { |
| 198 | V8_Fatal("", 0, location); |
| 199 | } |
| 200 | |
| 201 | bool EnableSlowAsserts() { return true; } |
| 202 | |
| 203 | } } // namespace v8::internal |
| 204 | |
| 205 | |
| 206 | int main(int argc, char* argv[]) { |
| 207 | int status = 0; |
| 208 | do { |
| 209 | status = v8::internal::PreParseIO(); |
| 210 | } while (status == 0); |
| 211 | fprintf(stderr, "EXIT: Failure %d\n", status); |
| 212 | return EXIT_FAILURE; |
| 213 | } |
| 214 | |
| 215 | |
| 216 | // Fatal error handling declared by checks.h. |
| 217 | |
| 218 | extern "C" void V8_Fatal(const char* file, int line, const char* format, ...) { |
| 219 | fflush(stdout); |
| 220 | fflush(stderr); |
| 221 | va_list arguments; |
| 222 | va_start(arguments, format); |
| 223 | vfprintf(stderr, format, arguments); |
| 224 | va_end(arguments); |
| 225 | fputs("\n#\n\n", stderr); |
| 226 | exit(EXIT_FAILURE); |
| 227 | } |