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"
27 /// Compare \p s and \p s2, ignoring the case.
28 /// Does not depend on the locale.
29 int compare_no_case(docstring const & s, docstring const & s2);
31 /// Compare \p s and \p s2, ignoring the case of ASCII characters only.
32 int compare_ascii_no_case(std::string const & s, std::string const & s2);
34 /// Compare \p s and \p s2, ignoring the case of ASCII characters only.
35 int compare_ascii_no_case(docstring const & s, docstring const & s2);
38 bool isStrInt(std::string const & str);
40 /// does the std::string represent an unsigned integer value ?
41 bool isStrUnsignedInt(std::string const & str);
44 bool isStrDbl(std::string const & str);
46 /// does the string contain a digit?
47 bool hasDigitASCII(docstring const & str);
49 bool isHexChar(char_type);
51 bool isHex(docstring const & str);
53 int hexToInt(docstring const & str);
55 /// is \p str pure ascii?
56 bool isAscii(docstring const & str);
58 /// is \p str pure ascii?
59 bool isAscii(std::string const & str);
62 * Changes the case of \p c to lowercase.
63 * Don't use this for non-ASCII characters, since it depends on the locale.
64 * This overloaded function is only implemented because the char_type variant
65 * would be used otherwise, and we assert in this function that \p c is in
68 char lowercase(char c);
71 * Changes the case of \p c to uppercase.
72 * Don't use this for non-ASCII characters, since it depends on the locale.
73 * This overloaded function is only implemented because the char_type variant
74 * would be used otherwise, and we assert in this function that \p c is in
77 char uppercase(char c);
79 /// Changes the case of \p c to lowercase.
80 /// Does not depend on the locale.
81 char_type lowercase(char_type c);
83 /// Changes the case of \p c to uppercase.
84 /// Does not depend on the locale.
85 char_type uppercase(char_type c);
87 /// Checks if the supplied character is lower-case
88 bool isLowerCase(char_type ch);
90 /// Checks if the supplied character is upper-case
91 bool isUpperCase(char_type ch);
93 /// same as lowercase(), but ignores locale
94 std::string const ascii_lowercase(std::string const &);
95 docstring const ascii_lowercase(docstring const &);
97 /// Changes the case of \p s to lowercase.
98 /// Does not depend on the locale.
99 docstring const lowercase(docstring const & s);
100 // Currently unused, but the code is there if needed.
101 // std::string const lowercase(std::string const & s);
103 /// Changes the case of \p s to uppercase.
104 /// Does not depend on the locale.
105 docstring const uppercase(docstring const & s);
107 /// Returns the superscript of \p c or \p c if no superscript exists.
108 /// Does not depend on the locale.
109 char_type superscript(char_type c);
111 /// Returns the subscript of \p c or \p c if no subscript exists.
112 /// Does not depend on the locale.
113 char_type subscript(char_type c);
115 /// Does str start with c?
116 bool prefixIs(docstring const & str, char_type c);
118 /// Does str start with pre?
119 bool prefixIs(std::string const & str, std::string const & pre);
120 bool prefixIs(docstring const & str, docstring const & pre);
122 /// Does the string end with this char?
123 bool suffixIs(std::string const &, char);
124 bool suffixIs(docstring const &, char_type);
126 /// Does the string end with this suffix?
127 bool suffixIs(std::string const &, std::string const &);
128 bool suffixIs(docstring const &, docstring const &);
130 /// Is b contained in a?
131 inline bool contains(std::string const & a, std::string const & b)
133 return a.find(b) != std::string::npos;
136 inline bool contains(docstring const & a, docstring const & b)
138 return a.find(b) != docstring::npos;
141 inline bool contains(std::string const & a, char b)
143 return a.find(b) != std::string::npos;
146 inline bool contains(docstring const & a, char_type b)
148 return a.find(b) != docstring::npos;
152 bool containsOnly(std::string const &, std::string const &);
154 /** Extracts a token from this string at the nth delim.
155 Doesn't modify the original string. Similar to strtok.
158 token("a;bc;d", ';', 1) == "bc";
159 token("a;bc;d", ';', 2) == "d";
162 std::string const token(std::string const & a, char delim, int n);
164 docstring const token(docstring const & a, char_type delim, int n);
166 /** Search a token in this string using the delim.
167 Doesn't modify the original string. Returns -1 in case of
171 tokenPos("a;bc;d", ';', "bc") == 1;
172 tokenPos("a;bc;d", ';', "d") == 2;
175 int tokenPos(std::string const & a, char delim, std::string const & tok);
176 int tokenPos(docstring const & a, char_type delim, docstring const & tok);
179 /// Substitute all \a oldchar with \a newchar
180 std::string const subst(std::string const & a, char oldchar, char newchar);
182 /// Substitute all \a oldchar with \a newchar
183 docstring const subst(docstring const & a, char_type oldchar, char_type newchar);
185 /// substitutes all instances of \a oldstr with \a newstr
186 std::string const subst(std::string const & a,
187 std::string const & oldstr, std::string const & newstr);
189 /// substitutes all instances of \a oldstr with \a newstr
190 docstring const subst(docstring const & a,
191 docstring const & oldstr, docstring const & newstr);
193 /// Count all occurences of char \a chr inside \a str
194 int count_char(std::string const & str, char chr);
196 /// Count all occurences of char \a chr inside \a str
197 int count_char(docstring const & str, docstring::value_type chr);
199 /** Trims characters off the end and beginning of a string.
201 trim("ccabccc", "c") == "ab".
204 docstring const trim(docstring const & a, char const * p = " ");
206 /** Trims characters off the end and beginning of a string.
208 trim("ccabccc", "c") == "ab".
211 std::string const trim(std::string const & a, char const * p = " ");
213 /** Trims characters off the end of a string, removing any character
216 rtrim("abcde", "dec") == "ab".
219 std::string const rtrim(std::string const & a, char const * p = " ");
220 docstring const rtrim(docstring const & a, char const * p = " ");
222 /** Trims characters off the beginning of a string.
224 ("abbabcdef", "ab") = "cdef"
227 std::string const ltrim(std::string const & a, char const * p = " ");
228 docstring const ltrim(docstring const & a, char const * p = " ");
230 /** Splits the string given in the first argument at the first occurence
231 of the third argument, delim.
232 What precedes delim is returned in the second argument, piece; this
233 will be the whole of the string if no delimiter is found.
234 The return value is what follows delim, if anything. So the return
235 value is the null string if no delimiter is found.
236 'a' and 'piece' must be different variables.
240 ret = split(s1, s2, ';') -> ret = "bc", s2 == "a"
243 std::string const split(std::string const & a, std::string & piece, char delim);
244 docstring const split(docstring const & a, docstring & piece, char_type delim);
246 /// Same as split but does not return a piece
247 std::string const split(std::string const & a, char delim);
249 /// Same as split but uses the last delim.
250 std::string const rsplit(std::string const & a, std::string & piece, char delim);
251 docstring const rsplit(docstring const & a, docstring & piece, char_type delim);
252 docstring const rsplit(docstring const & a, char_type delim);
254 /// Escapes non ASCII chars and other problematic characters that cause
255 /// problems in latex labels.
256 docstring const escape(docstring const & lab);
258 /// Word-wraps the provided docstring, returning a line-broken string
259 /// of width no wider than width, with the string broken at spaces.
260 /// If the string cannot be broken appropriately, it returns something
261 /// with "..." at the end, again no wider than width.
262 /// We assume here that str does not contain newlines.
263 /// If indent is positive, then the first line is indented that many
264 /// spaces. If it is negative, then successive lines are indented, as
265 /// if the first line were "outdented".
266 docstring wrap(docstring const & str, int const indent = 0,
267 size_t const width = 80);
269 /// Like the preceding, except it is intended to operate on strings
270 /// that may contain embedded newlines.
271 /// \param numlines Don't return more than numlines lines. If numlines
272 /// is 0, we return everything.
273 docstring wrapParas(docstring const & str, int const indent = 0,
274 size_t const width = 80, size_t const maxlines = 10);
276 /// gives a vector of stringparts which have the delimiter delim
277 /// If \p keepempty is true, empty strings will be pushed to the vector as well
278 std::vector<std::string> const getVectorFromString(std::string const & str,
279 std::string const & delim = std::string(","),
280 bool keepempty = false);
281 std::vector<docstring> const getVectorFromString(docstring const & str,
282 docstring const & delim = from_ascii(","), bool keepempty = false);
284 /// the same vice versa
285 std::string const getStringFromVector(std::vector<std::string> const & vec,
286 std::string const & delim = std::string(","));
287 docstring const getStringFromVector(std::vector<docstring> const & vec,
288 docstring const & delim = from_ascii(","));
290 /// Search \p search_token in \p str and return the position if it is
291 /// found, else -1. The last item in \p str must be "".
292 int findToken(char const * const str[], std::string const & search_token);
294 template <class Arg1>
295 docstring bformat(docstring const & fmt, Arg1);
297 template <class Arg1, class Arg2>
298 docstring bformat(docstring const & fmt, Arg1, Arg2);
300 template <class Arg1, class Arg2, class Arg3>
301 docstring bformat(docstring const & fmt, Arg1, Arg2, Arg3);
303 template <class Arg1, class Arg2, class Arg3, class Arg4>
304 docstring bformat(docstring const & fmt, Arg1, Arg2, Arg3, Arg4);
307 template<> docstring bformat(docstring const & fmt, int arg1);
308 template<> docstring bformat(docstring const & fmt, long arg1);
309 template<> docstring bformat(docstring const & fmt, unsigned int arg1);
310 template<> docstring bformat(docstring const & fmt, docstring arg1);
311 template<> docstring bformat(docstring const & fmt, char * arg1);
312 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2);
313 template<> docstring bformat(docstring const & fmt, docstring arg1, int arg2);
314 template<> docstring bformat(docstring const & fmt, char const * arg1, docstring arg2);
315 template<> docstring bformat(docstring const & fmt, int arg1, int arg2);
316 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3);
317 template<> docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3, docstring arg4);
320 } // namespace support