annotate include/llvm/Support/Regex.h @ 33:e4204d083e25

LLVM 3.5
author Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
date Thu, 12 Dec 2013 14:32:10 +0900
parents 95c75e76d11b
children 54457678186b
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
1 //===-- Regex.h - Regular Expression matcher implementation -*- C++ -*-----===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
2 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
3 // The LLVM Compiler Infrastructure
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
4 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
5 // This file is distributed under the University of Illinois Open Source
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
6 // License. See LICENSE.TXT for details.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
7 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
8 //===----------------------------------------------------------------------===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
9 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
10 // This file implements a POSIX regular expression matcher. Both Basic and
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
11 // Extended POSIX regular expressions (ERE) are supported. EREs were extended
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
12 // to support backreferences in matches.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
13 // This implementation also supports matching strings with embedded NUL chars.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
14 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
15 //===----------------------------------------------------------------------===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
16
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
17 #ifndef LLVM_SUPPORT_REGEX_H
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
18 #define LLVM_SUPPORT_REGEX_H
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
19
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
20 #include <string>
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
21
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
22 struct llvm_regex;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
23
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
24 namespace llvm {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
25 class StringRef;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
26 template<typename T> class SmallVectorImpl;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
27
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
28 class Regex {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
29 public:
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
30 enum {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
31 NoFlags=0,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
32 /// Compile for matching that ignores upper/lower case distinctions.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
33 IgnoreCase=1,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
34 /// Compile for newline-sensitive matching. With this flag '[^' bracket
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
35 /// expressions and '.' never match newline. A ^ anchor matches the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
36 /// null string after any newline in the string in addition to its normal
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
37 /// function, and the $ anchor matches the null string before any
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
38 /// newline in the string in addition to its normal function.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
39 Newline=2,
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
40 /// By default, the POSIX extended regular expression (ERE) syntax is
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
41 /// assumed. Pass this flag to turn on basic regular expressions (BRE)
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
42 /// instead.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
43 BasicRegex=4
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
44 };
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
45
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
46 /// Compiles the given regular expression \p Regex.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
47 Regex(StringRef Regex, unsigned Flags = NoFlags);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
48 ~Regex();
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
49
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
50 /// isValid - returns the error encountered during regex compilation, or
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
51 /// matching, if any.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
52 bool isValid(std::string &Error);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
53
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
54 /// getNumMatches - In a valid regex, return the number of parenthesized
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
55 /// matches it contains. The number filled in by match will include this
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
56 /// many entries plus one for the whole regex (as element 0).
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
57 unsigned getNumMatches() const;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
58
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
59 /// matches - Match the regex against a given \p String.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
60 ///
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
61 /// \param Matches - If given, on a successful match this will be filled in
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
62 /// with references to the matched group expressions (inside \p String),
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
63 /// the first group is always the entire pattern.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
64 ///
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
65 /// This returns true on a successful match.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
66 bool match(StringRef String, SmallVectorImpl<StringRef> *Matches = 0);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
67
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
68 /// sub - Return the result of replacing the first match of the regex in
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
69 /// \p String with the \p Repl string. Backreferences like "\0" in the
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
70 /// replacement string are replaced with the appropriate match substring.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
71 ///
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
72 /// Note that the replacement string has backslash escaping performed on
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
73 /// it. Invalid backreferences are ignored (replaced by empty strings).
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
74 ///
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
75 /// \param Error If non-null, any errors in the substitution (invalid
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
76 /// backreferences, trailing backslashes) will be recorded as a non-empty
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
77 /// string.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
78 std::string sub(StringRef Repl, StringRef String, std::string *Error = 0);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
79
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
80 /// \brief If this function returns true, ^Str$ is an extended regular
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
81 /// expression that matches Str and only Str.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
82 static bool isLiteralERE(StringRef Str);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
83
33
e4204d083e25 LLVM 3.5
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
84 /// \brief Turn String into a regex by escaping its special characters.
e4204d083e25 LLVM 3.5
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
85 static std::string escape(StringRef String);
e4204d083e25 LLVM 3.5
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
86
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
87 private:
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
88 struct llvm_regex *preg;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
89 int error;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
90 };
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
91 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
92
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
93 #endif // LLVM_SUPPORT_REGEX_H