Pull Lexer's CharInfo table out for general use throughout Clang.

Rewriting the same predicates over and over again is bad for code size and
code maintainence. Using the functions in <ctype.h> is generally unsafe
unless they are specified to be locale-independent (i.e. only isdigit and
isxdigit).

The next commit will try to clean up uses of <ctype.h> functions within Clang.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@174765 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 162 insertions, 0 deletions

diff --git a/include/clang/Basic/CharInfo.h b/include/clang/Basic/CharInfo.h
new file mode 100644
index 0000000000..f9b7b7311d
--- /dev/null
+++ b/include/clang/Basic/CharInfo.h
@@ -0,0 +1,162 @@
+//===--- clang/Basic/CharInfo.h - Classifying ASCII Characters ------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef CLANG_BASIC_CHARINFO_H
+#define CLANG_BASIC_CHARINFO_H
+
+#include "llvm/Support/Compiler.h"
+#include "llvm/Support/DataTypes.h"
+
+namespace clang {
+namespace charinfo {
+  extern const uint16_t InfoTable[256];
+
+  enum {
+    CHAR_HORZ_WS  = 0x0001,  // '\t', '\f', '\v'.  Note, no '\0'
+    CHAR_VERT_WS  = 0x0002,  // '\r', '\n'
+    CHAR_SPACE    = 0x0004,  // ' '
+    CHAR_DIGIT    = 0x0008,  // 0-9
+    CHAR_XLETTER  = 0x0010,  // a-f,A-F
+    CHAR_UPPER    = 0x0020,  // A-Z
+    CHAR_LOWER    = 0x0040,  // a-z
+    CHAR_UNDER    = 0x0080,  // _
+    CHAR_PERIOD   = 0x0100,  // .
+    CHAR_RAWDEL   = 0x0200,  // {}[]#<>%:;?*+-/^&|~!=,"'
+    CHAR_PUNCT    = 0x0400   // `$@()
+  };
+
+  enum {
+    CHAR_XUPPER = CHAR_XLETTER | CHAR_UPPER,
+    CHAR_XLOWER = CHAR_XLETTER | CHAR_LOWER
+  };
+} // end namespace charinfo
+
+/// Returns true if this is an ASCII character.
+LLVM_READNONE static inline bool isASCII(char c) {
+  return static_cast<unsigned char>(c) <= 127;
+}
+
+/// Returns true if this is a valid first character of a C identifier,
+/// which is [a-zA-Z_].
+LLVM_READONLY static inline bool isIdentifierHead(unsigned char c,
+                                                  bool AllowDollar = false) {
+  using namespace charinfo;
+  if (InfoTable[c] & (CHAR_UPPER|CHAR_LOWER|CHAR_UNDER))
+    return true;
+  return AllowDollar && c == '$';
+}
+
+/// Returns true if this is a body character of a C identifier,
+/// which is [a-zA-Z0-9_].
+LLVM_READONLY static inline bool isIdentifierBody(unsigned char c,
+                                                  bool AllowDollar = false) {
+  using namespace charinfo;
+  if (InfoTable[c] & (CHAR_UPPER|CHAR_LOWER|CHAR_DIGIT|CHAR_UNDER))
+    return true;
+  return AllowDollar && c == '$';
+}
+
+/// Returns true if this character is horizontal ASCII whitespace:
+/// ' ', '\\t', '\\f', '\\v'.
+///
+/// Note that this returns false for '\\0'.
+LLVM_READONLY static inline bool isHorizontalWhitespace(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_HORZ_WS|CHAR_SPACE)) != 0;
+}
+
+/// Returns true if this character is vertical ASCII whitespace: '\\n', '\\r'.
+///
+/// Note that this returns false for '\\0'.
+LLVM_READONLY static inline bool isVerticalWhitespace(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & CHAR_VERT_WS) != 0;
+}
+
+/// Return true if this character is horizontal or vertical ASCII whitespace:
+/// ' ', '\\t', '\\f', '\\v', '\\n', '\\r'.
+///
+/// Note that this returns false for '\\0'.
+LLVM_READONLY static inline bool isWhitespace(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_HORZ_WS|CHAR_VERT_WS|CHAR_SPACE)) != 0;
+}
+
+/// Return true if this character is an ASCII digit: [0-9]
+LLVM_READONLY static inline bool isDigit(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & CHAR_DIGIT) != 0;
+}
+
+/// Return true if this character is a lowercase ASCII letter: [a-z]
+LLVM_READONLY static inline bool isLowercase(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & CHAR_LOWER) != 0;
+}
+
+/// Return true if this character is an uppercase ASCII letter: [A-Z]
+LLVM_READONLY static inline bool isUppercase(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & CHAR_UPPER) != 0;
+}
+
+/// Return true if this character is an ASCII letter: [a-zA-Z]
+LLVM_READONLY static inline bool isLetter(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_UPPER|CHAR_LOWER)) != 0;
+}
+
+/// Return true if this character is an ASCII letter or digit: [a-zA-Z0-9]
+LLVM_READONLY static inline bool isAlphanumeric(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_DIGIT|CHAR_UPPER|CHAR_LOWER)) != 0;
+}
+
+/// Return true if this character is an ASCII hex digit: [0-9a-fA-F]
+LLVM_READONLY static inline bool isHexDigit(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_DIGIT|CHAR_XLETTER)) != 0;
+    return true;
+}
+
+/// Return true if this character is an ASCII punctuation character.
+///
+/// Note that '_' is both a punctuation character and an identifier character!
+LLVM_READONLY static inline bool isPunctuation(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_UNDER|CHAR_PERIOD|CHAR_RAWDEL|CHAR_PUNCT)) != 0;
+}
+
+/// Return true if this character is an ASCII printable character; that is, a
+/// character that should take exactly one column to print in a fixed-width
+/// terminal.
+LLVM_READONLY static inline bool isPrintable(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_UPPER|CHAR_LOWER|CHAR_PERIOD|CHAR_PUNCT|
+                          CHAR_DIGIT|CHAR_UNDER|CHAR_RAWDEL|CHAR_SPACE)) != 0;
+}
+
+/// Return true if this is the body character of a C preprocessing number,
+/// which is [a-zA-Z0-9_.].
+LLVM_READONLY static inline bool isPreprocessingNumberBody(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] &
+          (CHAR_UPPER|CHAR_LOWER|CHAR_DIGIT|CHAR_UNDER|CHAR_PERIOD)) != 0;
+}
+
+/// Return true if this is the body character of a C++ raw string delimiter.
+LLVM_READONLY static inline bool isRawStringDelimBody(unsigned char c) {
+  using namespace charinfo;
+  return (InfoTable[c] & (CHAR_UPPER|CHAR_LOWER|CHAR_PERIOD|
+                          CHAR_DIGIT|CHAR_UNDER|CHAR_RAWDEL)) != 0;
+}
+
+} // end namespace clang
+
+#endif