4 * This file is part of LyX, the document processor.
5 * Licence details can be found in the file COPYING.
7 * \author Lars Gullik Bjønnes
8 * \author Jean-Marc Lasgouttes
10 * Full author contact details are available in file CREDITS.
12 * A collection of string helper functions that works with string.
13 * Some of these would certainly benefit from a rewrite/optimization.
19 #include "support/docstring.h"
28 /// Compare \p s and \p s2, ignoring the case.
29 /// Does not depend on the locale.
30 int compare_no_case(docstring const & s, docstring const & s2);
32 /// Compare \p s and \p s2, ignoring the case of ASCII characters only.
33 int compare_ascii_no_case(std::string const & s, std::string const & s2);
35 /// Compare \p s and \p s2, ignoring the case of ASCII characters only.
36 int compare_ascii_no_case(docstring const & s, docstring const & s2);
39 bool isStrInt(std::string const & str);
41 /// does the std::string represent an unsigned integer value ?
42 bool isStrUnsignedInt(std::string const & str);
45 bool isStrDbl(std::string const & str);
47 /// does the string contain a digit?
48 bool hasDigit(docstring const & str);
50 bool isHex(docstring const & str);
52 int hexToInt(docstring const & str);
54 /// is \p str pure ascii?
55 bool isAscii(docstring const & str);
57 /// is \p str pure ascii?
58 bool isAscii(std::string const & str);
61 * Changes the case of \p c to lowercase.
62 * Don't use this for non-ASCII characters, since it depends on the locale.
63 * This overloaded function is only implemented because the char_type variant
64 * would be used otherwise, and we assert in this function that \p c is in
67 char lowercase(char c);
70 * Changes the case of \p c to uppercase.
71 * Don't use this for non-ASCII characters, since it depends on the locale.
72 * This overloaded function is only implemented because the char_type variant
73 * would be used otherwise, and we assert in this function that \p c is in
76 char uppercase(char c);
78 /// Changes the case of \p c to lowercase.
79 /// Does not depend on the locale.
80 char_type lowercase(char_type c);
82 /// Changes the case of \p c to uppercase.
83 /// Does not depend on the locale.
84 char_type uppercase(char_type c);
86 /// Checks if the supplied character is lower-case
87 bool isLowerCase(char_type ch);
89 /// Checks if the supplied character is upper-case
90 bool isUpperCase(char_type ch);
92 /// same as lowercase(), but ignores locale
93 std::string const ascii_lowercase(std::string const &);
94 docstring const ascii_lowercase(docstring const &);
96 /// Changes the case of \p s to lowercase.
97 /// Does not depend on the locale.
98 docstring const lowercase(docstring const & s);
100 /// Changes the case of \p s to uppercase.
101 /// Does not depend on the locale.
102 docstring const uppercase(docstring const & s);
104 /// Returns the superscript of \p c or \p c if no superscript exists.
105 /// Does not depend on the locale.
106 char_type superscript(char_type c);
108 /// Returns the subscript of \p c or \p c if no subscript exists.
109 /// Does not depend on the locale.
110 char_type subscript(char_type c);
112 /// Does str start with c?
113 bool prefixIs(docstring const & str, char_type c);
115 /// Does str start with pre?
116 bool prefixIs(std::string const & str, std::string const & pre);
117 bool prefixIs(docstring const & str, docstring const & pre);
119 /// Does the string end with this char?
120 bool suffixIs(std::string const &, char);
121 bool suffixIs(docstring const &, char_type);
123 /// Does the string end with this suffix?
124 bool suffixIs(std::string const &, std::string const &);
125 bool suffixIs(docstring const &, docstring const &);
127 /// Is b contained in a?
128 inline bool contains(std::string const & a, std::string const & b)
130 return a.find(b) != std::string::npos;
133 inline bool contains(docstring const & a, docstring const & b)
135 return a.find(b) != docstring::npos;
138 inline bool contains(std::string const & a, char b)
140 return a.find(b) != std::string::npos;
143 inline bool contains(docstring const & a, char_type b)
145 return a.find(b) != docstring::npos;
149 bool containsOnly(std::string const &, std::string const &);
151 /** Extracts a token from this string at the nth delim.
152 Doesn't modify the original string. Similar to strtok.
155 token("a;bc;d", ';', 1) == "bc";
156 token("a;bc;d", ';', 2) == "d";
159 std::string const token(std::string const & a, char delim, int n);
161 docstring const token(docstring const & a, char_type delim, int n);
163 /** Search a token in this string using the delim.
164 Doesn't modify the original string. Returns -1 in case of
168 tokenPos("a;bc;d", ';', "bc") == 1;
169 tokenPos("a;bc;d", ';', "d") == 2;
172 int tokenPos(std::string const & a, char delim, std::string const & tok);
173 int tokenPos(docstring const & a, char_type delim, docstring const & tok);
176 /// Substitute all \a oldchar with \a newchar
177 std::string const subst(std::string const & a, char oldchar, char newchar);
179 /// Substitute all \a oldchar with \a newchar
180 docstring const subst(docstring const & a, char_type oldchar, char_type newchar);
182 /// substitutes all instances of \a oldstr with \a newstr
183 std::string const subst(std::string const & a,
184 std::string const & oldstr, std::string const & newstr);
186 /// substitutes all instances of \a oldstr with \a newstr
187 docstring const subst(docstring const & a,
188 docstring const & oldstr, docstring const & newstr);
190 /// Count all occurences of char \a chr inside \a str
191 int count_char(docstring const & str, docstring::value_type chr);
193 /** Trims characters off the end and beginning of a string.
195 trim("ccabccc", "c") == "ab".
198 docstring const trim(docstring const & a, char const * p = " ");
200 /** Trims characters off the end and beginning of a string.
202 trim("ccabccc", "c") == "ab".
205 std::string const trim(std::string const & a, char const * p = " ");
207 /** Trims characters off the end of a string, removing any character
210 rtrim("abcde", "dec") == "ab".
213 std::string const rtrim(std::string const & a, char const * p = " ");
214 docstring const rtrim(docstring const & a, char const * p = " ");
216 /** Trims characters off the beginning of a string.
218 ("abbabcdef", "ab") = "cdef"
221 std::string const ltrim(std::string const & a, char const * p = " ");
222 docstring const ltrim(docstring const & a, char const * p = " ");
224 /** Splits the string given in the first argument at the first occurence
225 of the third argument, delim.
226 What precedes delim is returned in the second argument, piece; this
227 will be the whole of the string if no delimiter is found.
228 The return value is what follows delim, if anything. So the return
229 value is the null string if no delimiter is found.
233 ret = split(s1, s2, ';') -> ret = "bc", s2 == "a"
236 std::string const split(std::string const & a, std::string & piece, char delim);
237 docstring const split(docstring const & a, docstring & piece, char_type delim);
239 /// Same as split but does not return a piece
240 std::string const split(std::string const & a, char delim);
242 /// Same as split but uses the last delim.
243 std::string const rsplit(std::string const & a, std::string & piece, char delim);
244 docstring const rsplit(docstring const & a, char_type delim);
246 /// Escapes non ASCII chars and other problematic characters that cause
247 /// problems in latex labels.
248 docstring const escape(docstring const & lab);
250 /// Word-wraps the provided docstring, returning a line-broken string
251 /// of width no wider than width, with the string broken at spaces.
252 /// If the string cannot be broken appropriately, it returns something
253 /// with "..." at the end, again no wider than width.
254 /// We assume here that str does not contain newlines.
255 /// If indent is positive, then the first line is indented that many
256 /// spaces. If it is negative, then successive lines are indented, as
257 /// if the first line were "outdented".
258 docstring wrap(docstring const & str, int const indent = 0,
259 size_t const width = 80);
261 /// Like the preceding, except it is intended to operate on strings
262 /// that may contain embedded newlines.
263 /// \param numlines Don't return more than numlines lines. If numlines
264 /// is 0, we return everything.
265 docstring wrapParas(docstring const & str, int const indent = 0,
266 size_t const width = 80, size_t const maxlines = 10);
268 /// gives a vector of stringparts which have the delimiter delim
269 /// If \p keepempty is true, empty strings will be pushed to the vector as well
270 std::vector<std::string> const getVectorFromString(std::string const & str,
271 std::string const & delim = std::string(","),
272 bool keepempty = false);
273 std::vector<docstring> const getVectorFromString(docstring const & str,
274 docstring const & delim = from_ascii(","), bool keepempty = false);
276 /// the same vice versa
277 std::string const getStringFromVector(std::vector<std::string> const & vec,
278 std::string const & delim = std::string(","));
279 docstring const getStringFromVector(std::vector<docstring> const & vec,
280 docstring const & delim = from_ascii(","));
282 /// Search \p search_token in \p str and return the position if it is
283 /// found, else -1. The last item in \p str must be "".
284 int findToken(char const * const str[], std::string const & search_token);
286 template <class Arg1>
287 docstring bformat(docstring const & fmt, Arg1);
289 template <class Arg1, class Arg2>
290 docstring bformat(docstring const & fmt, Arg1, Arg2);
292 template <class Arg1, class Arg2, class Arg3>
293 docstring bformat(docstring const & fmt, Arg1, Arg2, Arg3);
295 template <class Arg1, class Arg2, class Arg3, class Arg4>
296 docstring bformat(docstring const & fmt, Arg1, Arg2, Arg3, Arg4);
299 template<> docstring bformat(docstring const & fmt, int arg1);
300 template<> docstring bformat(docstring const & fmt, long arg1);
301 template<> docstring bformat(docstring const & fmt, unsigned int arg1);
302 template<> docstring bformat(docstring const & fmt, docstring arg1);
303 template<> docstring bformat(docstring const & fmt, char * arg1);
304 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2);
305 template<> docstring bformat(docstring const & fmt, docstring arg1, int arg2);
306 template<> docstring bformat(docstring const & fmt, char const * arg1, docstring arg2);
307 template<> docstring bformat(docstring const & fmt, int arg1, int arg2);
308 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3);
309 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3, docstring arg4);
312 } // namespace support