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 bool isHex(docstring const & str);
49 int hexToInt(docstring const & str);
51 /// is \p str pure ascii?
52 bool isAscii(docstring const & str);
54 /// is \p str pure ascii?
55 bool isAscii(std::string const & str);
58 * Changes the case of \p c to lowercase.
59 * Don't use this for non-ASCII characters, since it depends on the locale.
60 * This overloaded function is only implemented because the char_type variant
61 * would be used otherwise, and we assert in this function that \p c is in
64 char lowercase(char c);
67 * Changes the case of \p c to uppercase.
68 * Don't use this for non-ASCII characters, since it depends on the locale.
69 * This overloaded function is only implemented because the char_type variant
70 * would be used otherwise, and we assert in this function that \p c is in
73 char uppercase(char c);
75 /// Changes the case of \p c to lowercase.
76 /// Does not depend on the locale.
77 char_type lowercase(char_type c);
79 /// Changes the case of \p c to uppercase.
80 /// Does not depend on the locale.
81 char_type uppercase(char_type c);
83 /// same as lowercase(), but ignores locale
84 std::string const ascii_lowercase(std::string const &);
85 docstring const ascii_lowercase(docstring const &);
87 /// Changes the case of \p s to lowercase.
88 /// Does not depend on the locale.
89 docstring const lowercase(docstring const & s);
91 /// Changes the case of \p s to uppercase.
92 /// Does not depend on the locale.
93 docstring const uppercase(docstring const & s);
95 /// Does str start with c?
96 bool prefixIs(docstring const & str, char_type c);
98 /// Does str start with pre?
99 bool prefixIs(std::string const & str, std::string const & pre);
100 bool prefixIs(docstring const & str, docstring const & pre);
102 /// Does the string end with this char?
103 bool suffixIs(std::string const &, char);
104 bool suffixIs(docstring const &, char_type);
106 /// Does the string end with this suffix?
107 bool suffixIs(std::string const &, std::string const &);
108 bool suffixIs(docstring const &, docstring const &);
110 /// Is b contained in a?
111 inline bool contains(std::string const & a, std::string const & b)
113 return a.find(b) != std::string::npos;
116 inline bool contains(docstring const & a, docstring const & b)
118 return a.find(b) != docstring::npos;
121 inline bool contains(std::string const & a, char b)
123 return a.find(b) != std::string::npos;
126 inline bool contains(docstring const & a, char_type b)
128 return a.find(b) != docstring::npos;
132 bool containsOnly(std::string const &, std::string const &);
134 /** Extracts a token from this string at the nth delim.
135 Doesn't modify the original string. Similar to strtok.
138 token("a;bc;d", ';', 1) == "bc";
139 token("a;bc;d", ';', 2) == "d";
142 std::string const token(std::string const & a, char delim, int n);
144 docstring const token(docstring const & a, char_type delim, int n);
146 /** Search a token in this string using the delim.
147 Doesn't modify the original string. Returns -1 in case of
151 tokenPos("a;bc;d", ';', "bc") == 1;
152 tokenPos("a;bc;d", ';', "d") == 2;
155 int tokenPos(std::string const & a, char delim, std::string const & tok);
156 int tokenPos(docstring const & a, char_type delim, docstring const & tok);
159 /// Substitute all \a oldchar with \a newchar
160 std::string const subst(std::string const & a, char oldchar, char newchar);
162 /// Substitute all \a oldchar with \a newchar
163 docstring const subst(docstring const & a, char_type oldchar, char_type newchar);
165 /// substitutes all instances of \a oldstr with \a newstr
166 std::string const subst(std::string const & a,
167 std::string const & oldstr, std::string const & newstr);
169 /// substitutes all instances of \a oldstr with \a newstr
170 docstring const subst(docstring const & a,
171 docstring const & oldstr, docstring const & newstr);
173 /** Trims characters off the end and beginning of a string.
175 trim("ccabccc", "c") == "ab".
178 docstring const trim(docstring const & a, char const * p = " ");
180 /** Trims characters off the end and beginning of a string.
182 trim("ccabccc", "c") == "ab".
185 std::string const trim(std::string const & a, char const * p = " ");
187 /** Trims characters off the end of a string, removing any character
190 rtrim("abcde", "dec") == "ab".
193 std::string const rtrim(std::string const & a, char const * p = " ");
194 docstring const rtrim(docstring const & a, char const * p = " ");
196 /** Trims characters off the beginning of a string.
198 ("abbabcdef", "ab") = "cdef"
201 std::string const ltrim(std::string const & a, char const * p = " ");
202 docstring const ltrim(docstring const & a, char const * p = " ");
204 /** Splits the string given in the first argument at the first occurence
205 of the third argumnent, delim.
206 What precedes delim is returned in the second argument, piece; this
207 will be the whole of the string if no delimiter is found.
208 The return value is what follows delim, if anything. So the return
209 value is the null string if no delimiter is found.
213 ret = split(s1, s2, ';') -> ret = "bc", s2 == "a"
216 std::string const split(std::string const & a, std::string & piece, char delim);
217 docstring const split(docstring const & a, docstring & piece, char_type delim);
219 /// Same as split but does not return a piece
220 std::string const split(std::string const & a, char delim);
222 /// Same as split but uses the last delim.
223 std::string const rsplit(std::string const & a, std::string & piece, char delim);
224 docstring const rsplit(docstring const & a, char_type delim);
226 /// Escapes non ASCII chars and other problematic characters that cause
227 /// problems in latex labels.
228 docstring const escape(docstring const & lab);
230 /// Word-wraps the provided docstring, returning a line-broken string
231 /// of width no wider than width, with the string broken at spaces.
232 /// If the string cannot be broken appropriately, it returns something
233 /// with "..." at the end, again no wider than width.
234 /// We assume here that str does not contain newlines.
235 /// If indent is positive, then the first line is indented that many
236 /// spaces. If it is negative, then successive lines are indented, as
237 /// if the first line were "outdented".
238 docstring wrap(docstring const & str, int const indent = 0,
239 size_t const width = 80);
241 /// Like the preceding, except it is intended to operate on strings
242 /// that may contain embedded newlines.
243 /// \param numlines Don't return more than numlines lines. If numlines
244 /// is 0, we return everything.
245 docstring wrapParas(docstring const & str, int const indent = 0,
246 size_t const width = 80, size_t const maxlines = 10);
248 /// gives a vector of stringparts which have the delimiter delim
249 /// If \p keepempty is true, empty strings will be pushed to the vector as well
250 std::vector<std::string> const getVectorFromString(std::string const & str,
251 std::string const & delim = std::string(","),
252 bool keepempty = false);
253 std::vector<docstring> const getVectorFromString(docstring const & str,
254 docstring const & delim = from_ascii(","), bool keepempty = false);
256 /// the same vice versa
257 std::string const getStringFromVector(std::vector<std::string> const & vec,
258 std::string const & delim = std::string(","));
259 docstring const getStringFromVector(std::vector<docstring> const & vec,
260 docstring const & delim = from_ascii(","));
262 /// Search \p search_token in \p str and return the position if it is
263 /// found, else -1. The last item in \p str must be "".
264 int findToken(char const * const str[], std::string const & search_token);
266 template <class Arg1>
267 docstring bformat(docstring const & fmt, Arg1);
269 template <class Arg1, class Arg2>
270 docstring bformat(docstring const & fmt, Arg1, Arg2);
272 template <class Arg1, class Arg2, class Arg3>
273 docstring bformat(docstring const & fmt, Arg1, Arg2, Arg3);
275 template <class Arg1, class Arg2, class Arg3, class Arg4>
276 docstring bformat(docstring const & fmt, Arg1, Arg2, Arg3, Arg4);
279 template<> docstring bformat(docstring const & fmt, int arg1);
280 template<> docstring bformat(docstring const & fmt, long arg1);
281 template<> docstring bformat(docstring const & fmt, unsigned int arg1);
282 template<> docstring bformat(docstring const & fmt, docstring arg1);
283 template<> docstring bformat(docstring const & fmt, char * arg1);
284 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2);
285 template<> docstring bformat(docstring const & fmt, char const * arg1, docstring arg2);
286 template<> docstring bformat(docstring const & fmt, int arg1, int arg2);
287 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3);
288 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3, docstring arg4);
291 } // namespace support