]>
Commit | Line | Data |
---|---|---|
f4ada568 | 1 | ///////////////////////////////////////////////////////////////////////////// |
7c968cee VZ |
2 | // Name: wx/tokenzr.h |
3 | // Purpose: String tokenizer - a C++ replacement for strtok(3) | |
f4ada568 | 4 | // Author: Guilhem Lavaux |
1e6feb95 | 5 | // Modified by: (or rather rewritten by) Vadim Zeitlin |
f4ada568 GL |
6 | // Created: 04/22/98 |
7 | // RCS-ID: $Id$ | |
8 | // Copyright: (c) Guilhem Lavaux | |
9 | // Licence: wxWindows licence | |
10 | ///////////////////////////////////////////////////////////////////////////// | |
11 | ||
12 | #ifndef _WX_TOKENZRH | |
13 | #define _WX_TOKENZRH | |
14 | ||
12028905 | 15 | #if defined(__GNUG__) && !defined(NO_GCC_PRAGMA) |
2224580a | 16 | #pragma interface "tokenzr.h" |
f4ada568 GL |
17 | #endif |
18 | ||
19 | #include "wx/object.h" | |
20 | #include "wx/string.h" | |
df5168c4 | 21 | #include "wx/arrstr.h" |
bbf8fc53 | 22 | |
7c968cee VZ |
23 | // ---------------------------------------------------------------------------- |
24 | // constants | |
25 | // ---------------------------------------------------------------------------- | |
26 | ||
bbf8fc53 VZ |
27 | // default: delimiters are usual white space characters |
28 | #define wxDEFAULT_DELIMITERS (_T(" \t\r\n")) | |
f4ada568 | 29 | |
7c968cee VZ |
30 | // wxStringTokenizer mode flags which determine its behaviour |
31 | enum wxStringTokenizerMode | |
32 | { | |
33 | wxTOKEN_INVALID = -1, // set by def ctor until SetString() is called | |
34 | wxTOKEN_DEFAULT, // strtok() for whitespace delims, RET_EMPTY else | |
35 | wxTOKEN_RET_EMPTY, // return empty token in the middle of the string | |
36 | wxTOKEN_RET_EMPTY_ALL, // return trailing empty tokens too | |
37 | wxTOKEN_RET_DELIMS, // return the delim with token (implies RET_EMPTY) | |
38 | wxTOKEN_STRTOK // behave exactly like strtok(3) | |
39 | }; | |
40 | ||
41 | // ---------------------------------------------------------------------------- | |
42 | // wxStringTokenizer: replaces infamous strtok() and has some other features | |
43 | // ---------------------------------------------------------------------------- | |
44 | ||
bddd7a8d | 45 | class WXDLLIMPEXP_BASE wxStringTokenizer : public wxObject |
85833f5c | 46 | { |
f4ada568 | 47 | public: |
7c968cee VZ |
48 | // ctors and initializers |
49 | // default ctor, call SetString() later | |
50 | wxStringTokenizer() { m_mode = wxTOKEN_INVALID; } | |
51 | // ctor which gives us the string | |
52 | wxStringTokenizer(const wxString& str, | |
bbf8fc53 | 53 | const wxString& delims = wxDEFAULT_DELIMITERS, |
7c968cee VZ |
54 | wxStringTokenizerMode mode = wxTOKEN_DEFAULT); |
55 | ||
56 | // args are same as for the non default ctor above | |
57 | void SetString(const wxString& str, | |
bbf8fc53 | 58 | const wxString& delims = wxDEFAULT_DELIMITERS, |
7c968cee VZ |
59 | wxStringTokenizerMode mode = wxTOKEN_DEFAULT); |
60 | ||
61 | // reinitialize the tokenizer with the same delimiters/mode | |
62 | void Reinit(const wxString& str); | |
85833f5c | 63 | |
7c968cee VZ |
64 | // tokens access |
65 | // count them | |
bbf8fc53 | 66 | size_t CountTokens() const; |
7c968cee VZ |
67 | // did we reach the end of the string? |
68 | bool HasMoreTokens() const; | |
69 | // get the next token, will return empty string if !HasMoreTokens() | |
bbf8fc53 | 70 | wxString GetNextToken(); |
85833f5c | 71 | |
7c968cee VZ |
72 | // get current tokenizer state |
73 | // returns the part of the string which remains to tokenize (*not* the | |
74 | // initial string) | |
bbf8fc53 | 75 | wxString GetString() const { return m_string; } |
85833f5c | 76 | |
7c968cee VZ |
77 | // returns the current position (i.e. one index after the last |
78 | // returned token or 0 if GetNextToken() has never been called) in the | |
79 | // original string | |
bbf8fc53 | 80 | size_t GetPosition() const { return m_pos; } |
dbdb39b2 | 81 | |
7c968cee VZ |
82 | // misc |
83 | // get the current mode - can be different from the one passed to the | |
84 | // ctor if it was wxTOKEN_DEFAULT | |
85 | wxStringTokenizerMode GetMode() const { return m_mode; } | |
86 | ||
87 | // backwards compatibility section from now on | |
88 | // ------------------------------------------- | |
89 | ||
bbf8fc53 VZ |
90 | // for compatibility only, use GetNextToken() instead |
91 | wxString NextToken() { return GetNextToken(); } | |
85833f5c | 92 | |
7c968cee VZ |
93 | // compatibility only, don't use |
94 | void SetString(const wxString& to_tokenize, | |
95 | const wxString& delims, | |
06b466c7 | 96 | bool WXUNUSED(ret_delim)) |
7c968cee VZ |
97 | { |
98 | SetString(to_tokenize, delims, wxTOKEN_RET_DELIMS); | |
99 | } | |
100 | ||
101 | wxStringTokenizer(const wxString& to_tokenize, | |
102 | const wxString& delims, | |
103 | bool ret_delim) | |
104 | { | |
105 | SetString(to_tokenize, delims, ret_delim); | |
106 | } | |
107 | ||
2224580a | 108 | protected: |
7c968cee VZ |
109 | bool IsOk() const { return m_mode != wxTOKEN_INVALID; } |
110 | ||
bbf8fc53 VZ |
111 | wxString m_string, // the (rest of) string to tokenize |
112 | m_delims; // all delimiters | |
113 | ||
114 | size_t m_pos; // the position in the original string | |
115 | ||
7c968cee VZ |
116 | wxStringTokenizerMode m_mode; // see wxTOKEN_XXX values |
117 | ||
118 | bool m_hasMore; // do we have more (possible empty) tokens? | |
f4ada568 GL |
119 | }; |
120 | ||
1e6feb95 VZ |
121 | // ---------------------------------------------------------------------------- |
122 | // convenience function which returns all tokens at once | |
123 | // ---------------------------------------------------------------------------- | |
124 | ||
125 | // the function takes the same parameters as wxStringTokenizer ctor and returns | |
126 | // the array containing all tokens | |
bddd7a8d | 127 | wxArrayString WXDLLIMPEXP_BASE |
1e6feb95 VZ |
128 | wxStringTokenize(const wxString& str, |
129 | const wxString& delims = wxDEFAULT_DELIMITERS, | |
130 | wxStringTokenizerMode mode = wxTOKEN_DEFAULT); | |
131 | ||
85833f5c | 132 | #endif // _WX_TOKENZRH |