[lld] r295022 - Rename ScriptParser.{cpp,h} -> ScriptLexer.{cpp,h}.
Rui Ueyama via llvm-commits
llvm-commits at lists.llvm.org
Mon Feb 13 20:47:05 PST 2017
Author: ruiu
Date: Mon Feb 13 22:47:05 2017
New Revision: 295022
URL: http://llvm.org/viewvc/llvm-project?rev=295022&view=rev
Log:
Rename ScriptParser.{cpp,h} -> ScriptLexer.{cpp,h}.
These files contain a lexer, so the new names are better.
The parser is in LinkerScript.{cpp,h}.
Added:
lld/trunk/ELF/ScriptLexer.cpp
lld/trunk/ELF/ScriptLexer.h
Removed:
lld/trunk/ELF/ScriptParser.cpp
lld/trunk/ELF/ScriptParser.h
Modified:
lld/trunk/ELF/CMakeLists.txt
lld/trunk/ELF/LinkerScript.cpp
Modified: lld/trunk/ELF/CMakeLists.txt
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/CMakeLists.txt?rev=295022&r1=295021&r2=295022&view=diff
==============================================================================
--- lld/trunk/ELF/CMakeLists.txt (original)
+++ lld/trunk/ELF/CMakeLists.txt Mon Feb 13 22:47:05 2017
@@ -22,7 +22,7 @@ add_lld_library(lldELF
Mips.cpp
OutputSections.cpp
Relocations.cpp
- ScriptParser.cpp
+ ScriptLexer.cpp
Strings.cpp
SymbolTable.cpp
Symbols.cpp
Modified: lld/trunk/ELF/LinkerScript.cpp
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/LinkerScript.cpp?rev=295022&r1=295021&r2=295022&view=diff
==============================================================================
--- lld/trunk/ELF/LinkerScript.cpp (original)
+++ lld/trunk/ELF/LinkerScript.cpp Mon Feb 13 22:47:05 2017
@@ -17,7 +17,7 @@
#include "InputSection.h"
#include "Memory.h"
#include "OutputSections.h"
-#include "ScriptParser.h"
+#include "ScriptLexer.h"
#include "Strings.h"
#include "SymbolTable.h"
#include "Symbols.h"
@@ -1016,12 +1016,12 @@ size_t LinkerScript<ELFT>::getPhdrIndex(
return 0;
}
-class elf::ScriptParser final : public ScriptParserBase {
+class elf::ScriptParser final : public ScriptLexer {
typedef void (ScriptParser::*Handler)();
public:
ScriptParser(MemoryBufferRef MB)
- : ScriptParserBase(MB),
+ : ScriptLexer(MB),
IsUnderSysroot(isUnderSysroot(MB.getBufferIdentifier())) {}
void readLinkerScript();
Added: lld/trunk/ELF/ScriptLexer.cpp
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/ScriptLexer.cpp?rev=295022&view=auto
==============================================================================
--- lld/trunk/ELF/ScriptLexer.cpp (added)
+++ lld/trunk/ELF/ScriptLexer.cpp Mon Feb 13 22:47:05 2017
@@ -0,0 +1,203 @@
+//===- ScriptLexer.cpp ----------------------------------------------------===//
+//
+// The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the base parser class for linker script and dynamic
+// list.
+//
+//===----------------------------------------------------------------------===//
+
+#include "ScriptLexer.h"
+#include "Error.h"
+#include "llvm/ADT/Twine.h"
+
+using namespace llvm;
+using namespace lld;
+using namespace lld::elf;
+
+// Returns a whole line containing the current token.
+StringRef ScriptLexer::getLine() {
+ StringRef S = getCurrentMB().getBuffer();
+ StringRef Tok = Tokens[Pos - 1];
+
+ size_t Pos = S.rfind('\n', Tok.data() - S.data());
+ if (Pos != StringRef::npos)
+ S = S.substr(Pos + 1);
+ return S.substr(0, S.find_first_of("\r\n"));
+}
+
+// Returns 1-based line number of the current token.
+size_t ScriptLexer::getLineNumber() {
+ StringRef S = getCurrentMB().getBuffer();
+ StringRef Tok = Tokens[Pos - 1];
+ return S.substr(0, Tok.data() - S.data()).count('\n') + 1;
+}
+
+// Returns 0-based column number of the current token.
+size_t ScriptLexer::getColumnNumber() {
+ StringRef Tok = Tokens[Pos - 1];
+ return Tok.data() - getLine().data();
+}
+
+std::string ScriptLexer::getCurrentLocation() {
+ std::string Filename = getCurrentMB().getBufferIdentifier();
+ if (!Pos)
+ return Filename;
+ return (Filename + ":" + Twine(getLineNumber())).str();
+}
+
+ScriptLexer::ScriptLexer(MemoryBufferRef MB) { tokenize(MB); }
+
+// We don't want to record cascading errors. Keep only the first one.
+void ScriptLexer::setError(const Twine &Msg) {
+ if (Error)
+ return;
+ Error = true;
+
+ if (!Pos) {
+ error(getCurrentLocation() + ": " + Msg);
+ return;
+ }
+
+ std::string S = getCurrentLocation() + ": ";
+ error(S + Msg);
+ error(S + getLine());
+ error(S + std::string(getColumnNumber(), ' ') + "^");
+}
+
+// Split S into linker script tokens.
+void ScriptLexer::tokenize(MemoryBufferRef MB) {
+ std::vector<StringRef> Vec;
+ MBs.push_back(MB);
+ StringRef S = MB.getBuffer();
+ StringRef Begin = S;
+
+ for (;;) {
+ S = skipSpace(S);
+ if (S.empty())
+ break;
+
+ // Quoted token. Note that double-quote characters are parts of a token
+ // because, in a glob match context, only unquoted tokens are interpreted
+ // as glob patterns. Double-quoted tokens are literal patterns in that
+ // context.
+ if (S.startswith("\"")) {
+ size_t E = S.find("\"", 1);
+ if (E == StringRef::npos) {
+ StringRef Filename = MB.getBufferIdentifier();
+ size_t Lineno = Begin.substr(0, S.data() - Begin.data()).count('\n');
+ error(Filename + ":" + Twine(Lineno + 1) + ": unclosed quote");
+ return;
+ }
+
+ Vec.push_back(S.take_front(E + 1));
+ S = S.substr(E + 1);
+ continue;
+ }
+
+ // Unquoted token. This is more relaxed than tokens in C-like language,
+ // so that you can write "file-name.cpp" as one bare token, for example.
+ size_t Pos = S.find_first_not_of(
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+ "0123456789_.$/\\~=+[]*?-!<>^");
+
+ // A character that cannot start a word (which is usually a
+ // punctuation) forms a single character token.
+ if (Pos == 0)
+ Pos = 1;
+ Vec.push_back(S.substr(0, Pos));
+ S = S.substr(Pos);
+ }
+
+ Tokens.insert(Tokens.begin() + Pos, Vec.begin(), Vec.end());
+}
+
+// Skip leading whitespace characters or comments.
+StringRef ScriptLexer::skipSpace(StringRef S) {
+ for (;;) {
+ if (S.startswith("/*")) {
+ size_t E = S.find("*/", 2);
+ if (E == StringRef::npos) {
+ error("unclosed comment in a linker script");
+ return "";
+ }
+ S = S.substr(E + 2);
+ continue;
+ }
+ if (S.startswith("#")) {
+ size_t E = S.find('\n', 1);
+ if (E == StringRef::npos)
+ E = S.size() - 1;
+ S = S.substr(E + 1);
+ continue;
+ }
+ size_t Size = S.size();
+ S = S.ltrim();
+ if (S.size() == Size)
+ return S;
+ }
+}
+
+// An erroneous token is handled as if it were the last token before EOF.
+bool ScriptLexer::atEOF() { return Error || Tokens.size() == Pos; }
+
+StringRef ScriptLexer::next() {
+ if (Error)
+ return "";
+ if (atEOF()) {
+ setError("unexpected EOF");
+ return "";
+ }
+ return Tokens[Pos++];
+}
+
+StringRef ScriptLexer::peek(unsigned N) {
+ StringRef Tok;
+ for (unsigned I = 0; I <= N; ++I) {
+ Tok = next();
+ if (Error)
+ return "";
+ }
+ Pos = Pos - N - 1;
+ return Tok;
+}
+
+bool ScriptLexer::consume(StringRef Tok) {
+ if (peek() == Tok) {
+ skip();
+ return true;
+ }
+ return false;
+}
+
+void ScriptLexer::skip() { (void)next(); }
+
+void ScriptLexer::expect(StringRef Expect) {
+ if (Error)
+ return;
+ StringRef Tok = next();
+ if (Tok != Expect)
+ setError(Expect + " expected, but got " + Tok);
+}
+
+// Returns true if S encloses T.
+static bool encloses(StringRef S, StringRef T) {
+ return S.bytes_begin() <= T.bytes_begin() && T.bytes_end() <= S.bytes_end();
+}
+
+MemoryBufferRef ScriptLexer::getCurrentMB() {
+ // Find input buffer containing the current token.
+ assert(!MBs.empty());
+ if (!Pos)
+ return MBs[0];
+
+ for (MemoryBufferRef MB : MBs)
+ if (encloses(MB.getBuffer(), Tokens[Pos - 1]))
+ return MB;
+ llvm_unreachable("getCurrentMB: failed to find a token");
+}
Added: lld/trunk/ELF/ScriptLexer.h
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/ScriptLexer.h?rev=295022&view=auto
==============================================================================
--- lld/trunk/ELF/ScriptLexer.h (added)
+++ lld/trunk/ELF/ScriptLexer.h Mon Feb 13 22:47:05 2017
@@ -0,0 +1,53 @@
+//===- ScriptLexer.h --------------------------------------------*- C++ -*-===//
+//
+// The LLVM Linker
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLD_ELF_SCRIPT_LEXER_H
+#define LLD_ELF_SCRIPT_LEXER_H
+
+#include "lld/Core/LLVM.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include <utility>
+#include <vector>
+
+namespace lld {
+namespace elf {
+
+class ScriptLexer {
+public:
+ explicit ScriptLexer(MemoryBufferRef MB);
+
+ void setError(const Twine &Msg);
+ void tokenize(MemoryBufferRef MB);
+ static StringRef skipSpace(StringRef S);
+ bool atEOF();
+ StringRef next();
+ StringRef peek(unsigned N = 0);
+ void skip();
+ bool consume(StringRef Tok);
+ void expect(StringRef Expect);
+ std::string getCurrentLocation();
+
+ std::vector<MemoryBufferRef> MBs;
+ std::vector<StringRef> Tokens;
+ size_t Pos = 0;
+ bool Error = false;
+
+private:
+ StringRef getLine();
+ size_t getLineNumber();
+ size_t getColumnNumber();
+
+ MemoryBufferRef getCurrentMB();
+};
+
+} // namespace elf
+} // namespace lld
+
+#endif
Removed: lld/trunk/ELF/ScriptParser.cpp
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/ScriptParser.cpp?rev=295021&view=auto
==============================================================================
--- lld/trunk/ELF/ScriptParser.cpp (original)
+++ lld/trunk/ELF/ScriptParser.cpp (removed)
@@ -1,203 +0,0 @@
-//===- ScriptParser.cpp ---------------------------------------------------===//
-//
-// The LLVM Linker
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-// This file contains the base parser class for linker script and dynamic
-// list.
-//
-//===----------------------------------------------------------------------===//
-
-#include "ScriptParser.h"
-#include "Error.h"
-#include "llvm/ADT/Twine.h"
-
-using namespace llvm;
-using namespace lld;
-using namespace lld::elf;
-
-// Returns a whole line containing the current token.
-StringRef ScriptParserBase::getLine() {
- StringRef S = getCurrentMB().getBuffer();
- StringRef Tok = Tokens[Pos - 1];
-
- size_t Pos = S.rfind('\n', Tok.data() - S.data());
- if (Pos != StringRef::npos)
- S = S.substr(Pos + 1);
- return S.substr(0, S.find_first_of("\r\n"));
-}
-
-// Returns 1-based line number of the current token.
-size_t ScriptParserBase::getLineNumber() {
- StringRef S = getCurrentMB().getBuffer();
- StringRef Tok = Tokens[Pos - 1];
- return S.substr(0, Tok.data() - S.data()).count('\n') + 1;
-}
-
-// Returns 0-based column number of the current token.
-size_t ScriptParserBase::getColumnNumber() {
- StringRef Tok = Tokens[Pos - 1];
- return Tok.data() - getLine().data();
-}
-
-std::string ScriptParserBase::getCurrentLocation() {
- std::string Filename = getCurrentMB().getBufferIdentifier();
- if (!Pos)
- return Filename;
- return (Filename + ":" + Twine(getLineNumber())).str();
-}
-
-ScriptParserBase::ScriptParserBase(MemoryBufferRef MB) { tokenize(MB); }
-
-// We don't want to record cascading errors. Keep only the first one.
-void ScriptParserBase::setError(const Twine &Msg) {
- if (Error)
- return;
- Error = true;
-
- if (!Pos) {
- error(getCurrentLocation() + ": " + Msg);
- return;
- }
-
- std::string S = getCurrentLocation() + ": ";
- error(S + Msg);
- error(S + getLine());
- error(S + std::string(getColumnNumber(), ' ') + "^");
-}
-
-// Split S into linker script tokens.
-void ScriptParserBase::tokenize(MemoryBufferRef MB) {
- std::vector<StringRef> Vec;
- MBs.push_back(MB);
- StringRef S = MB.getBuffer();
- StringRef Begin = S;
-
- for (;;) {
- S = skipSpace(S);
- if (S.empty())
- break;
-
- // Quoted token. Note that double-quote characters are parts of a token
- // because, in a glob match context, only unquoted tokens are interpreted
- // as glob patterns. Double-quoted tokens are literal patterns in that
- // context.
- if (S.startswith("\"")) {
- size_t E = S.find("\"", 1);
- if (E == StringRef::npos) {
- StringRef Filename = MB.getBufferIdentifier();
- size_t Lineno = Begin.substr(0, S.data() - Begin.data()).count('\n');
- error(Filename + ":" + Twine(Lineno + 1) + ": unclosed quote");
- return;
- }
-
- Vec.push_back(S.take_front(E + 1));
- S = S.substr(E + 1);
- continue;
- }
-
- // Unquoted token. This is more relaxed than tokens in C-like language,
- // so that you can write "file-name.cpp" as one bare token, for example.
- size_t Pos = S.find_first_not_of(
- "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
- "0123456789_.$/\\~=+[]*?-!<>^");
-
- // A character that cannot start a word (which is usually a
- // punctuation) forms a single character token.
- if (Pos == 0)
- Pos = 1;
- Vec.push_back(S.substr(0, Pos));
- S = S.substr(Pos);
- }
-
- Tokens.insert(Tokens.begin() + Pos, Vec.begin(), Vec.end());
-}
-
-// Skip leading whitespace characters or comments.
-StringRef ScriptParserBase::skipSpace(StringRef S) {
- for (;;) {
- if (S.startswith("/*")) {
- size_t E = S.find("*/", 2);
- if (E == StringRef::npos) {
- error("unclosed comment in a linker script");
- return "";
- }
- S = S.substr(E + 2);
- continue;
- }
- if (S.startswith("#")) {
- size_t E = S.find('\n', 1);
- if (E == StringRef::npos)
- E = S.size() - 1;
- S = S.substr(E + 1);
- continue;
- }
- size_t Size = S.size();
- S = S.ltrim();
- if (S.size() == Size)
- return S;
- }
-}
-
-// An erroneous token is handled as if it were the last token before EOF.
-bool ScriptParserBase::atEOF() { return Error || Tokens.size() == Pos; }
-
-StringRef ScriptParserBase::next() {
- if (Error)
- return "";
- if (atEOF()) {
- setError("unexpected EOF");
- return "";
- }
- return Tokens[Pos++];
-}
-
-StringRef ScriptParserBase::peek(unsigned N) {
- StringRef Tok;
- for (unsigned I = 0; I <= N; ++I) {
- Tok = next();
- if (Error)
- return "";
- }
- Pos = Pos - N - 1;
- return Tok;
-}
-
-bool ScriptParserBase::consume(StringRef Tok) {
- if (peek() == Tok) {
- skip();
- return true;
- }
- return false;
-}
-
-void ScriptParserBase::skip() { (void)next(); }
-
-void ScriptParserBase::expect(StringRef Expect) {
- if (Error)
- return;
- StringRef Tok = next();
- if (Tok != Expect)
- setError(Expect + " expected, but got " + Tok);
-}
-
-// Returns true if S encloses T.
-static bool encloses(StringRef S, StringRef T) {
- return S.bytes_begin() <= T.bytes_begin() && T.bytes_end() <= S.bytes_end();
-}
-
-MemoryBufferRef ScriptParserBase::getCurrentMB() {
- // Find input buffer containing the current token.
- assert(!MBs.empty());
- if (!Pos)
- return MBs[0];
-
- for (MemoryBufferRef MB : MBs)
- if (encloses(MB.getBuffer(), Tokens[Pos - 1]))
- return MB;
- llvm_unreachable("getCurrentMB: failed to find a token");
-}
Removed: lld/trunk/ELF/ScriptParser.h
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/ScriptParser.h?rev=295021&view=auto
==============================================================================
--- lld/trunk/ELF/ScriptParser.h (original)
+++ lld/trunk/ELF/ScriptParser.h (removed)
@@ -1,53 +0,0 @@
-//===- ScriptParser.h -------------------------------------------*- C++ -*-===//
-//
-// The LLVM Linker
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef LLD_ELF_SCRIPT_PARSER_H
-#define LLD_ELF_SCRIPT_PARSER_H
-
-#include "lld/Core/LLVM.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/Support/MemoryBuffer.h"
-#include <utility>
-#include <vector>
-
-namespace lld {
-namespace elf {
-
-class ScriptParserBase {
-public:
- explicit ScriptParserBase(MemoryBufferRef MB);
-
- void setError(const Twine &Msg);
- void tokenize(MemoryBufferRef MB);
- static StringRef skipSpace(StringRef S);
- bool atEOF();
- StringRef next();
- StringRef peek(unsigned N = 0);
- void skip();
- bool consume(StringRef Tok);
- void expect(StringRef Expect);
- std::string getCurrentLocation();
-
- std::vector<MemoryBufferRef> MBs;
- std::vector<StringRef> Tokens;
- size_t Pos = 0;
- bool Error = false;
-
-private:
- StringRef getLine();
- size_t getLineNumber();
- size_t getColumnNumber();
-
- MemoryBufferRef getCurrentMB();
-};
-
-} // namespace elf
-} // namespace lld
-
-#endif
More information about the llvm-commits
mailing list