Index: src/asmjs/asm-lexer.cc |
diff --git a/src/asmjs/asm-lexer.cc b/src/asmjs/asm-lexer.cc |
new file mode 100644 |
index 0000000000000000000000000000000000000000..3e49edd4bd71a33207f1d5f7e94e821e409dd7b2 |
--- /dev/null |
+++ b/src/asmjs/asm-lexer.cc |
@@ -0,0 +1,420 @@ |
+// Copyright 2017 the V8 project authors. All rights reserved. |
+// Use of this source code is governed by a BSD-style license that can be |
+// found in the LICENSE file. |
+ |
+#include "src/asmjs/asm-lexer.h" |
+ |
+#include <stdlib.h> |
+ |
+#include "src/objects.h" |
marja
2017/03/15 12:34:49
Why is objects.h needed?
bradn
2017/03/16 00:21:46
There was a Handle<String> used in scanner.h inlin
|
+#include "src/parsing/scanner-character-streams.h" |
vogelheim
2017/03/15 12:07:41
I don't see scanner-character-streams.h being used
bradn
2017/03/16 00:21:47
Dropped.
|
+#include "src/parsing/scanner.h" |
marja
2017/03/15 12:34:49
Hmm, you're still including scanner.h even though
bradn
2017/03/16 00:21:47
That was in the header.
This is needed here becaus
marja
2017/03/16 17:05:33
My orig. comment suggested moving the streams out
|
+ |
+namespace v8 { |
+namespace internal { |
+ |
+namespace { |
+// Cap number of identifiers to ensure we can assign both global and |
+// local ones a token id in the range of an int32_t. |
+static const int kMaxIdentifierCount = 0xf000000; |
+}; |
+ |
+AsmJsLexer::AsmJsLexer() |
+ : token_(0), |
+ preceding_token_(0), |
+ next_token_(0), |
+ rewind_(false), |
+ in_local_scope_(false), |
+ global_count_(0), |
+ double_value_(0.0), |
+ unsigned_value_(0), |
+ preceded_by_newline_(false) { |
+#define V(name, _junk1, _junk2, _junk3) property_names_[#name] = kToken_##name; |
+ STDLIB_MATH_FUNCTION_LIST(V) |
+ STDLIB_ARRAY_TYPE_LIST(V) |
+#undef V |
+#define V(name) property_names_[#name] = kToken_##name; |
+ STDLIB_MATH_VALUE_LIST(V) |
+ STDLIB_OTHER_LIST(V) |
+#undef V |
+#define V(name) global_names_[#name] = kToken_##name; |
+ KEYWORD_NAME_LIST(V) |
+#undef V |
+} |
+ |
+void AsmJsLexer::SetStream(std::unique_ptr<Utf16CharacterStream> stream) { |
+ stream_ = std::move(stream); |
+ Next(); |
+} |
+ |
+void AsmJsLexer::Next() { |
vogelheim
2017/03/15 12:07:40
I find this method much nicer to read now. Thanks.
bradn
2017/03/16 00:21:47
:-)
|
+ if (rewind_) { |
+ preceding_token_ = token_; |
+ token_ = next_token_; |
+ next_token_ = 0; |
+ rewind_ = false; |
+ return; |
+ } |
+ |
+ if (token_ == kEndOfInput || token_ == kParseError) { |
+ return; |
+ } |
+ |
+#if DEBUG |
+ if (FLAG_trace_asm_lexer) { |
+ if (Token() != 0) { |
vogelheim
2017/03/15 12:07:41
nitpick: No real problem here, but this logic is a
bradn
2017/03/16 00:21:47
Done.
|
+ if (Token() == kDouble) { |
+ PrintF("%lf ", AsDouble()); |
+ } else if (Token() == kUnsigned) { |
+ PrintF("%" PRIu64 " ", AsUnsigned()); |
+ } else { |
+ std::string name = Name(Token()); |
+ PrintF("%s ", name.c_str()); |
+ } |
+ } |
+ } |
+#endif |
+ |
+ preceded_by_newline_ = false; |
+ preceding_token_ = token_; |
+ for (;;) { |
+ uc32 ch = stream_->Advance(); |
+ switch (ch) { |
+ case ' ': |
+ case '\t': |
+ case '\n': |
+ case '\r': |
+ // Ignore whitespace, track when we've passed a newline for optional |
+ // semicolon support. |
+ if (ch == '\n') { |
vogelheim
2017/03/15 12:07:41
nitpick: This is weird. If you have a switch-case
bradn
2017/03/16 00:21:46
Hah, yeah good point (missed that in the refactor)
|
+ preceded_by_newline_ = true; |
+ } |
+ break; |
+ |
+ case kEndOfInput: |
+ token_ = kEndOfInput; |
+ return; |
+ |
+ case '\'': |
+ case '"': |
+ ConsumeString(ch); |
+ return; |
+ |
+ case '/': |
+ ch = stream_->Advance(); |
+ if (ch == '/') { |
+ ConsumeCComment(); |
+ } else if (ch == '*') { |
+ ConsumeCPPComment(); |
+ } else { |
+ stream_->Back(); |
+ token_ = '/'; |
+ return; |
+ } |
+ // Breaks out of switch, but loops again (i.e. the case when we parsed |
+ // a comment, but need to continue to look for the next token). |
+ break; |
+ |
+ case '<': |
+ case '>': |
+ case '=': |
+ case '!': |
+ ConsumeCompareOrShift(ch); |
+ return; |
+ |
+ default: |
+ if (IsIdentifierStart(ch)) { |
+ ConsumeIdentifier(ch); |
+ } else if (IsNumberStart(ch)) { |
+ ConsumeNumber(ch); |
+ } else if (ch >= 32 && ch < 127) { |
vogelheim
2017/03/15 12:07:41
[Not sure this is an issue, but... ]
How many of
bradn
2017/03/16 00:21:47
Listed out the single char ones.
|
+ // Use fixed token IDs for ASCII. |
+ token_ = ch; |
+ } else { |
+ // TODO(bradnelson): Support unicode (probably via UnicodeCache). |
+ token_ = kParseError; |
+ } |
+ return; |
+ } |
+ } |
+} |
+ |
+void AsmJsLexer::Rewind() { |
+ DCHECK(!rewind_); |
+ next_token_ = token_; |
+ token_ = preceding_token_; |
+ preceding_token_ = 0; |
+ rewind_ = true; |
+ preceded_by_newline_ = false; |
+ identifier_string_.clear(); |
+} |
+ |
+void AsmJsLexer::ResetLocals() { local_names_.clear(); } |
+ |
+#if DEBUG |
+// Only used for debugging. |
+std::string AsmJsLexer::Name(token_t token) const { |
+ // TODO(bradnelson): Make thread safe. |
+ if (token >= 32 && token < 127) { |
+ return std::string(1, static_cast<char>(token)); |
+ } |
+ for (auto& i : local_names_) { |
+ if (i.second == token) { |
+ return i.first.c_str(); |
Karl
2017/03/15 15:04:13
Why not just:
return i.first;
bradn
2017/03/16 00:21:46
Done.
|
+ } |
+ } |
+ for (auto& i : global_names_) { |
+ if (i.second == token) { |
+ return i.first.c_str(); |
Karl
2017/03/15 15:04:13
Same here.
bradn
2017/03/16 00:21:47
Done.
|
+ } |
+ } |
+ for (auto& i : property_names_) { |
+ if (i.second == token) { |
+ return i.first.c_str(); |
Karl
2017/03/15 15:04:13
Same here.
bradn
2017/03/16 00:21:46
Done.
|
+ } |
+ } |
+ switch (token) { |
+#define V(rawname, name) \ |
+ case kToken_##name: \ |
+ return rawname; |
+ LONG_SYMBOL_NAME_LIST(V) |
+#undef V |
+ default: |
+ break; |
+ } |
+ if (token == kUnsigned) { |
vogelheim
2017/03/15 12:07:40
Why not handle all of these inside the switch righ
bradn
2017/03/16 00:21:46
Done.
|
+ return "{unsigned value}"; |
+ } else if (token == kDouble) { |
+ return "{double value}"; |
+ } else if (token == kParseError) { |
+ return "{parse error}"; |
+ } else if (token == kEndOfInput) { |
+ return "{end of input}"; |
+ } |
+ UNREACHABLE(); |
+ return "{unreachable}"; |
+} |
+#endif |
+ |
+int AsmJsLexer::GetPosition() const { return static_cast<int>(stream_->pos()); } |
vogelheim
2017/03/15 12:07:40
Does this work if rewind_ is set? If not, maybe ad
bradn
2017/03/16 00:21:46
Done.
|
+ |
+void AsmJsLexer::Seek(int pos) { |
+ stream_->Seek(pos); |
+ preceding_token_ = 0; |
+ token_ = 0; |
+ next_token_ = 0; |
+ rewind_ = false; |
+ Next(); |
+} |
+ |
+void AsmJsLexer::ConsumeIdentifier(uc32 ch) { |
+ // Consume characters while still part of the identifier. |
+ identifier_string_ = ""; |
vogelheim
2017/03/15 12:07:41
identifier_string_.clear();
(STL is bizarre, but.
bradn
2017/03/16 00:21:46
Yep. Done.
|
+ while (IsIdentifierPart(ch)) { |
+ identifier_string_ += ch; |
+ ch = stream_->Advance(); |
+ } |
+ // Go back one for next time. |
+ stream_->Back(); |
+ |
+ // Decode what the identifier means. |
+ if (preceding_token_ == '.') { |
+ auto i = property_names_.find(identifier_string_); |
+ if (i != property_names_.end()) { |
+ token_ = i->second; |
+ return; |
+ } |
+ } else { |
+ { |
+ auto i = local_names_.find(identifier_string_); |
+ if (i != local_names_.end()) { |
+ token_ = i->second; |
+ return; |
+ } |
+ } |
+ if (!in_local_scope_) { |
+ auto i = global_names_.find(identifier_string_); |
+ if (i != global_names_.end()) { |
+ token_ = i->second; |
+ return; |
+ } |
+ } |
+ } |
+ if (preceding_token_ == '.') { |
+ CHECK(global_count_ < kMaxIdentifierCount); |
+ token_ = kGlobalsStart + global_count_++; |
+ property_names_[identifier_string_] = token_; |
+ } else if (in_local_scope_) { |
+ CHECK(local_names_.size() < kMaxIdentifierCount); |
+ token_ = kLocalsStart - static_cast<token_t>(local_names_.size()); |
+ local_names_[identifier_string_] = token_; |
+ } else { |
+ CHECK(global_count_ < kMaxIdentifierCount); |
+ token_ = kGlobalsStart + global_count_++; |
+ global_names_[identifier_string_] = token_; |
+ } |
+} |
+ |
+void AsmJsLexer::ConsumeNumber(uc32 ch) { |
+ std::string number; |
+ number = ch; |
+ bool has_dot = ch == '.'; |
+ for (;;) { |
+ ch = stream_->Advance(); |
+ if ((ch >= '0' && ch <= '9') || (ch >= 'a' && ch <= 'f') || |
+ (ch >= 'A' && ch <= 'F') || ch == '.' || ch == 'x' || |
+ ((ch == '-' || ch == '+') && (number[number.size() - 1] == 'e' || |
+ number[number.size() - 1] == 'E'))) { |
+ // TODO(bradnelson): Test weird cases ending in -. |
+ if (ch == '.') { |
+ has_dot = true; |
+ } |
+ number += ch; |
+ } else { |
+ break; |
+ } |
+ } |
+ stream_->Back(); |
+ // Special case the most common number. |
+ if (number == "0") { |
+ unsigned_value_ = 0; |
+ token_ = kUnsigned; |
+ return; |
+ } |
+ // Pick out dot. |
+ if (number == ".") { |
+ token_ = '.'; |
+ return; |
+ } |
+ // Decode numbers. |
+ // TODO(bradnelson): Replace strto* with shared code with scanner.cc |
+ char* end; |
+ if (has_dot) { |
+ double_value_ = strtod(number.c_str(), &end); |
+ token_ = kDouble; |
+ } else { |
+ if (number.size() > 2 && number[0] == '0' && number[1] == 'x') { |
+ // Decode 0x* as hex. |
+ unsigned_value_ = strtoul(number.c_str() + 2, &end, 16); |
+ } else if (number.size() > 1 && number[0] == '0') { |
+ // Decode 0* as octal. |
+ unsigned_value_ = strtoul(number.c_str() + 1, &end, 8); |
+ } else { |
+ // Decode the rest as double. |
+ // This can come up in asm.js as for example 1e2 is used to encode 100. |
+ double_value_ = strtod(number.c_str(), &end); |
+ unsigned_value_ = static_cast<uint32_t>(double_value_); |
+ } |
+ token_ = kUnsigned; |
+ } |
+ // Check if string to number conversion didn't consume all the characters. |
+ // This happens if the character filter let through something invalid |
+ // like: 0123ef for example. |
+ // TODO(bradnelson): Check if this happens often enough to be a perf problem. |
+ if (end != number.c_str() + number.size()) { |
+ // If things didn't parse fully, but start with a '.', back out the other |
+ // characters and emit the '.' token. |
+ if (number[0] == '.') { |
+ for (size_t k = 1; k < number.size(); ++k) { |
+ stream_->Back(); |
+ } |
+ token_ = '.'; |
+ return; |
+ } |
+ // Anything else that doesn't parse is an error. |
+ token_ = kParseError; |
+ return; |
+ } |
+} |
+ |
+void AsmJsLexer::ConsumeCComment() { |
+ for (;;) { |
+ uc32 ch = stream_->Advance(); |
+ if (ch == '\n' || ch == kEndOfInput) { |
+ break; |
+ } |
+ } |
+} |
+ |
+void AsmJsLexer::ConsumeCPPComment() { |
+ for (;;) { |
+ uc32 ch = stream_->Advance(); |
+ if (ch == '*') { |
vogelheim
2017/03/15 12:07:41
Your choice, but I think this if-branch would be a
bradn
2017/03/16 00:21:46
Ah, yeah, that's better.
Done.
|
+ ch = stream_->Advance(); |
+ if (ch == '/') { |
+ break; |
+ } |
+ if (ch == '*') { |
+ stream_->Back(); |
+ } |
+ } else if (ch == kEndOfInput) { |
vogelheim
2017/03/15 12:07:40
I think this potentially swallows a syntax error w
bradn
2017/03/16 00:21:46
Ah, yes.
Fixed and added a test.
|
+ break; |
+ } |
+ } |
+} |
+ |
+void AsmJsLexer::ConsumeString(uc32 quote) { |
+ // Only string allowed is 'use asm' / "use asm". |
+ const char* expected = "use asm"; |
+ for (; *expected != '\0'; ++expected) { |
+ if (stream_->Advance() != *expected) { |
+ token_ = kParseError; |
+ return; |
+ } |
+ } |
+ if (stream_->Advance() != quote) { |
+ token_ = kParseError; |
+ return; |
+ } |
+ token_ = kToken_UseAsm; |
+} |
+ |
+void AsmJsLexer::ConsumeCompareOrShift(uc32 ch) { |
+ uc32 next_ch = stream_->Advance(); |
+ if (next_ch == '=') { |
+ switch (ch) { |
+ case '<': |
+ token_ = kToken_LE; |
+ break; |
+ case '>': |
+ token_ = kToken_GE; |
+ break; |
+ case '=': |
+ token_ = kToken_EQ; |
+ break; |
+ case '!': |
+ token_ = kToken_NE; |
+ break; |
+ default: |
+ UNREACHABLE(); |
+ } |
+ } else if (ch == '<' && next_ch == '<') { |
+ token_ = kToken_SHL; |
+ } else if (ch == '>' && next_ch == '>') { |
+ if (stream_->Advance() == '>') { |
+ token_ = kToken_SHR; |
+ } else { |
+ token_ = kToken_SAR; |
+ stream_->Back(); |
+ } |
+ } else { |
+ stream_->Back(); |
+ token_ = ch; |
+ } |
+} |
+ |
+bool AsmJsLexer::IsIdentifierStart(uc32 ch) { |
+ return (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z') || ch == '_' || |
+ ch == '$'; |
+} |
+ |
+bool AsmJsLexer::IsIdentifierPart(uc32 ch) { |
+ return IsIdentifierStart(ch) || (ch >= '0' && ch <= '9'); |
+} |
+ |
+bool AsmJsLexer::IsNumberStart(uc32 ch) { |
+ return ch == '.' || (ch >= '0' && ch <= '9'); |
+} |
+ |
+} // namespace internal |
+} // namespace v8 |