X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FSupport%2FRegex.h;h=31b35ed0cad61f86712bb30b1f0a60559d6c7ea6;hb=b8e08438aa60d3269b942181bc643b48c345c10c;hp=4c4229eb57b10b508355ce77bc3ce816f2ba6cf3;hpb=48ba9ff3c44f33c65c26ecf5df306f4a428d2c26;p=oota-llvm.git diff --git a/include/llvm/Support/Regex.h b/include/llvm/Support/Regex.h index 4c4229eb57b..31b35ed0cad 100644 --- a/include/llvm/Support/Regex.h +++ b/include/llvm/Support/Regex.h @@ -7,57 +7,99 @@ // //===----------------------------------------------------------------------===// // -// This file implements a POSIX regular expression matcher. +// This file implements a POSIX regular expression matcher. Both Basic and +// Extended POSIX regular expressions (ERE) are supported. EREs were extended +// to support backreferences in matches. +// This implementation also supports matching strings with embedded NUL chars. // //===----------------------------------------------------------------------===// -#include "llvm/ADT/SmallVector.h" -#include "llvm/ADT/StringRef.h" +#ifndef LLVM_SUPPORT_REGEX_H +#define LLVM_SUPPORT_REGEX_H + +#include struct llvm_regex; + namespace llvm { + class StringRef; + template class SmallVectorImpl; + class Regex { public: enum { - /// Compile with support for subgroup matches, this is just to make - /// constructs like Regex("...", 0) more readable as Regex("...", Sub). - Sub=0, + NoFlags=0, /// Compile for matching that ignores upper/lower case distinctions. IgnoreCase=1, - /// Compile for matching that need only report success or failure, - /// not what was matched. - NoSub=2, /// Compile for newline-sensitive matching. With this flag '[^' bracket - /// expressions and '.' never match newline. A ^ anchor matches the - /// null string after any newline in the string in addition to its normal - /// function, and the $ anchor matches the null string before any + /// expressions and '.' never match newline. A ^ anchor matches the + /// null string after any newline in the string in addition to its normal + /// function, and the $ anchor matches the null string before any /// newline in the string in addition to its normal function. - Newline=4 + Newline=2, + /// By default, the POSIX extended regular expression (ERE) syntax is + /// assumed. Pass this flag to turn on basic regular expressions (BRE) + /// instead. + BasicRegex=4 }; - /// Compiles the given POSIX Extended Regular Expression \arg Regex. - /// This implementation supports regexes and matching strings with embedded - /// NUL characters. - Regex(const StringRef &Regex, unsigned Flags=NoSub); + /// Compiles the given regular expression \p Regex. + Regex(StringRef Regex, unsigned Flags = NoFlags); + Regex(const Regex &) = delete; + Regex &operator=(Regex regex) { + std::swap(preg, regex.preg); + std::swap(error, regex.error); + return *this; + } + Regex(Regex &®ex) { + preg = regex.preg; + error = regex.error; + regex.preg = nullptr; + } ~Regex(); /// isValid - returns the error encountered during regex compilation, or /// matching, if any. bool isValid(std::string &Error); - /// matches - Match the regex against a given \arg String. + /// getNumMatches - In a valid regex, return the number of parenthesized + /// matches it contains. The number filled in by match will include this + /// many entries plus one for the whole regex (as element 0). + unsigned getNumMatches() const; + + /// matches - Match the regex against a given \p String. /// - /// \param Matches - If given, on a succesful match this will be filled in - /// with references to the matched group expressions (inside \arg String), + /// \param Matches - If given, on a successful match this will be filled in + /// with references to the matched group expressions (inside \p String), /// the first group is always the entire pattern. - /// By default the regex is compiled with NoSub, which disables support for - /// Matches. - /// For this feature to be enabled you must construct the regex using - /// Regex("...", Regex::Sub) constructor. - bool match(const StringRef &String, SmallVectorImpl *Matches=0); + /// + /// This returns true on a successful match. + bool match(StringRef String, SmallVectorImpl *Matches = nullptr); + + /// sub - Return the result of replacing the first match of the regex in + /// \p String with the \p Repl string. Backreferences like "\0" in the + /// replacement string are replaced with the appropriate match substring. + /// + /// Note that the replacement string has backslash escaping performed on + /// it. Invalid backreferences are ignored (replaced by empty strings). + /// + /// \param Error If non-null, any errors in the substitution (invalid + /// backreferences, trailing backslashes) will be recorded as a non-empty + /// string. + std::string sub(StringRef Repl, StringRef String, + std::string *Error = nullptr); + + /// \brief If this function returns true, ^Str$ is an extended regular + /// expression that matches Str and only Str. + static bool isLiteralERE(StringRef Str); + + /// \brief Turn String into a regex by escaping its special characters. + static std::string escape(StringRef String); + private: struct llvm_regex *preg; int error; - bool sub; }; } + +#endif // LLVM_SUPPORT_REGEX_H