[94] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * text_t.h -- a simple 16-bit charater string class
|
---|
| 4 | * Copyright (c) 1998 -- Rodger McNab
|
---|
| 5 | *
|
---|
| 6 | * This program is free software; you can redistribute it and/or modify
|
---|
| 7 | * it under the terms of the GNU General Public License as published by
|
---|
| 8 | * the Free Software Foundation; either version 2 of the License, or
|
---|
| 9 | * (at your option) any later version.
|
---|
| 10 | *
|
---|
| 11 | * This program is distributed in the hope that it will be useful,
|
---|
| 12 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 13 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 14 | * GNU General Public License for more details.
|
---|
| 15 | *
|
---|
| 16 | * You should have received a copy of the GNU General Public License
|
---|
| 17 | * along with this program; if not, write to the Free Software
|
---|
| 18 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 19 | *
|
---|
| 20 | * $Id: text_t.h 94 1999-01-04 03:32:21Z rjmcnab $
|
---|
| 21 | *
|
---|
| 22 | **************************************************************************/
|
---|
| 23 |
|
---|
| 24 |
|
---|
| 25 |
|
---|
| 26 | #ifndef TEXT_T_H
|
---|
| 27 | #define TEXT_T_H
|
---|
| 28 |
|
---|
| 29 | #ifndef USE_OBJECTSPACE
|
---|
| 30 | # include <vector>
|
---|
| 31 | # include <list>
|
---|
| 32 | # include <set>
|
---|
| 33 | #else
|
---|
| 34 | # include <ospace\std\vector>
|
---|
| 35 | # include <ospace\std\list>
|
---|
| 36 | # include <ospace\std\set>
|
---|
| 37 | #endif
|
---|
| 38 |
|
---|
| 39 | // use the standard namespace
|
---|
| 40 | #ifdef __GNUG__
|
---|
| 41 | // namespaces are broken in current version of gcc
|
---|
| 42 | #else
|
---|
| 43 | # ifndef USE_OBJECTSPACE
|
---|
| 44 | using namespace std;
|
---|
| 45 | # else
|
---|
| 46 | # ifndef OS_NO_NAMESPACE
|
---|
| 47 | using namespace ospace::std;
|
---|
| 48 | # endif
|
---|
| 49 | # endif
|
---|
| 50 | #endif
|
---|
| 51 |
|
---|
| 52 |
|
---|
| 53 | // class prototypes
|
---|
| 54 | class inconvertclass;
|
---|
| 55 | class outconvertclass;
|
---|
| 56 |
|
---|
| 57 |
|
---|
| 58 | typedef vector<unsigned short> usvector;
|
---|
| 59 |
|
---|
| 60 | // The class text_t can handle long strings which may contain
|
---|
| 61 | // null characters. It uses unsigned shorts to represent up to
|
---|
| 62 | // 64K character values.
|
---|
| 63 | class text_t {
|
---|
| 64 | public:
|
---|
| 65 | //type support for ucvector
|
---|
| 66 | typedef usvector::iterator iterator;
|
---|
| 67 | typedef usvector::const_iterator const_iterator;
|
---|
| 68 | typedef usvector::reference reference;
|
---|
| 69 | typedef usvector::const_reference const_reference;
|
---|
| 70 | typedef usvector::size_type size_type;
|
---|
| 71 | typedef usvector::difference_type difference_type;
|
---|
| 72 | typedef usvector::const_reverse_iterator const_reverse_iterator;
|
---|
| 73 | typedef usvector::reverse_iterator reverse_iterator;
|
---|
| 74 |
|
---|
| 75 | protected:
|
---|
| 76 | usvector text;
|
---|
| 77 | unsigned short encoding; // 0 = unicode, 1 = other
|
---|
| 78 |
|
---|
| 79 | public:
|
---|
| 80 | // constructors
|
---|
| 81 | text_t ();
|
---|
| 82 | text_t (int i);
|
---|
| 83 | text_t (char *s); // assumed to be a normal c string
|
---|
| 84 |
|
---|
| 85 | void setencoding (unsigned short theencoding) {encoding=theencoding;};
|
---|
| 86 | unsigned short getencoding () {return encoding;};
|
---|
| 87 |
|
---|
| 88 | // basic container support
|
---|
| 89 | iterator begin () {return text.begin();}
|
---|
| 90 | const_iterator begin () const {return text.begin();}
|
---|
| 91 | iterator end () {return text.end();}
|
---|
| 92 | const_iterator end () const {return text.end();}
|
---|
| 93 |
|
---|
| 94 | void erase(iterator pos) {text.erase(pos);}
|
---|
| 95 | void erase(iterator first, iterator last) {text.erase(first, last);}
|
---|
| 96 | void push_back(unsigned short c) {text.push_back(c);}
|
---|
| 97 | void pop_back() {text.pop_back();}
|
---|
| 98 | text_t &operator=(const text_t &x) {text=x.text; encoding=x.encoding; return *this;}
|
---|
| 99 | reference operator[](size_type n) {return text[n];};
|
---|
| 100 | const_reference operator[](size_type n) const {return text[n];};
|
---|
| 101 |
|
---|
| 102 | bool empty () const {return text.empty();}
|
---|
| 103 | size_type size() const {return text.size();}
|
---|
| 104 | friend bool operator!=(const text_t& x, const text_t& y);
|
---|
| 105 | friend bool operator==(const text_t& x, const text_t& y);
|
---|
| 106 | friend bool operator<(const text_t& x, const text_t& y);
|
---|
| 107 | friend bool operator>(const text_t& x, const text_t& y);
|
---|
| 108 |
|
---|
| 109 | // added functionality
|
---|
| 110 | void clear () {text.erase(text.begin(),text.end());}
|
---|
| 111 | void append (const text_t &t);
|
---|
| 112 | void appendrange (iterator first, iterator last);
|
---|
| 113 | void appendrange (const_iterator first, const_iterator last);
|
---|
| 114 | text_t &operator+= (const text_t &t) {append(t);return *this;}
|
---|
| 115 |
|
---|
| 116 | // support for integers
|
---|
| 117 | void appendint (int i);
|
---|
| 118 | void setint (int i) {clear();appendint(i);}
|
---|
| 119 | text_t &operator=(int i) {setint (i);return *this;}
|
---|
| 120 | text_t &operator+= (int i) {appendint(i);return *this;}
|
---|
| 121 | int getint ();
|
---|
| 122 |
|
---|
| 123 | // support for arrays of chars
|
---|
| 124 | void appendcarr (char *s, size_type len);
|
---|
| 125 | void setcarr (char *s, size_type len) {clear();appendcarr(s,len);}
|
---|
| 126 |
|
---|
| 127 | // support for null-terminated C strings
|
---|
| 128 | void appendcstr (char *s);
|
---|
| 129 | void setcstr (char *s) {clear();appendcstr(s);}
|
---|
| 130 | text_t &operator= (char *s) {setcstr(s);return *this;} // c string
|
---|
| 131 | text_t &operator+= (char *s) {appendcstr(s);return *this;} // c string
|
---|
| 132 |
|
---|
| 133 | // strings returned from getcarr and getcstr become the callers
|
---|
| 134 | // responsibility and should be deallocated with "delete"
|
---|
| 135 | char *getcarr(size_type &len) const;
|
---|
| 136 | char *getcstr() const;
|
---|
| 137 | };
|
---|
| 138 |
|
---|
| 139 |
|
---|
| 140 | inline text_t operator+(const text_t &t1, const text_t &t2)
|
---|
| 141 | {
|
---|
| 142 | text_t tnew = t1;
|
---|
| 143 | tnew.append(t2);
|
---|
| 144 | return tnew;
|
---|
| 145 | }
|
---|
| 146 |
|
---|
| 147 | inline text_t operator+(const text_t &t1, int i1)
|
---|
| 148 | {
|
---|
| 149 | text_t tnew = t1;
|
---|
| 150 | tnew.appendint(i1);
|
---|
| 151 | return tnew;
|
---|
| 152 | }
|
---|
| 153 |
|
---|
| 154 | inline text_t operator+(const text_t &t1, char *s1)
|
---|
| 155 | {
|
---|
| 156 | text_t tnew = t1;
|
---|
| 157 | tnew.appendcstr(s1);
|
---|
| 158 | return tnew;
|
---|
| 159 | }
|
---|
| 160 |
|
---|
| 161 |
|
---|
| 162 | inline bool operator!=(const text_t& x, const text_t& y)
|
---|
| 163 | {
|
---|
| 164 | return (x.text != y.text);
|
---|
| 165 | }
|
---|
| 166 |
|
---|
| 167 | inline bool operator==(const text_t& x, const text_t& y)
|
---|
| 168 | {
|
---|
| 169 | return (x.text == y.text);
|
---|
| 170 | }
|
---|
| 171 |
|
---|
| 172 | inline bool operator<(const text_t& x, const text_t& y)
|
---|
| 173 | {
|
---|
| 174 | return (x.text < y.text);
|
---|
| 175 | }
|
---|
| 176 |
|
---|
| 177 | inline bool operator>(const text_t& x, const text_t& y)
|
---|
| 178 | {
|
---|
| 179 | return (x.text > y.text);
|
---|
| 180 | }
|
---|
| 181 |
|
---|
| 182 |
|
---|
| 183 | struct eqtext_t
|
---|
| 184 | {
|
---|
| 185 | bool operator()(const text_t t1, const text_t t2) const
|
---|
| 186 | { return t1 == t2; }
|
---|
| 187 | };
|
---|
| 188 |
|
---|
| 189 | struct lttext_t
|
---|
| 190 | {
|
---|
| 191 | bool operator()(const text_t t1, const text_t t2) const
|
---|
| 192 | { return t1 < t2; }
|
---|
| 193 | };
|
---|
| 194 |
|
---|
| 195 |
|
---|
| 196 | // frequently used derived types
|
---|
| 197 | typedef set<text_t,lttext_t> text_tset;
|
---|
| 198 | typedef list<text_t> text_tlist; // more efficient for insertions/deletions
|
---|
| 199 | typedef vector<text_t> text_tarray; // more space efficient than text_tlist
|
---|
| 200 |
|
---|
| 201 |
|
---|
| 202 | // general functions which work on text_ts
|
---|
| 203 |
|
---|
| 204 | // find a character within a range
|
---|
| 205 | text_t::const_iterator findchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 206 | unsigned short c);
|
---|
| 207 | text_t::iterator findchar (text_t::iterator first, text_t::iterator last,
|
---|
| 208 | unsigned short c);
|
---|
| 209 |
|
---|
| 210 | // get a string up to the next delimiter (which is skipped)
|
---|
| 211 | text_t::const_iterator getdelimitstr (text_t::const_iterator first,
|
---|
| 212 | text_t::const_iterator last,
|
---|
| 213 | unsigned short c, text_t &outstr);
|
---|
| 214 | text_t::iterator getdelimitstr (text_t::iterator first, text_t::iterator last,
|
---|
| 215 | unsigned short c, text_t &outstr);
|
---|
| 216 |
|
---|
| 217 | // split a string with a character
|
---|
| 218 | void splitchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 219 | unsigned short c, text_tlist &outlist);
|
---|
| 220 | void splitchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 221 | unsigned short c, text_tarray &outlist);
|
---|
| 222 |
|
---|
| 223 | // join a string using a character
|
---|
| 224 | void joinchar (const text_tlist &inlist, unsigned short c, text_t &outtext);
|
---|
| 225 | void joinchar (const text_tarray &inlist, unsigned short c, text_t &outtext);
|
---|
| 226 |
|
---|
| 227 | // count the occurances of a character within a range
|
---|
| 228 | int countchar (text_t::const_iterator first, text_t::const_iterator last,
|
---|
| 229 | unsigned short c);
|
---|
| 230 |
|
---|
| 231 |
|
---|
| 232 |
|
---|
| 233 |
|
---|
| 234 |
|
---|
| 235 |
|
---|
| 236 |
|
---|
| 237 |
|
---|
| 238 | // conversion classes used for getting information in to and out of
|
---|
| 239 | // the text_t class.
|
---|
| 240 |
|
---|
| 241 | class convertclass
|
---|
| 242 | {
|
---|
| 243 | public:
|
---|
| 244 | enum status_t {finished, stopped, unfinished};
|
---|
| 245 |
|
---|
| 246 | convertclass ();
|
---|
| 247 | virtual void reset ();
|
---|
| 248 | };
|
---|
| 249 |
|
---|
| 250 |
|
---|
| 251 |
|
---|
| 252 | // convert from a char stream to the text_t class
|
---|
| 253 | // the default version assumes the input is a ascii
|
---|
| 254 | // character array
|
---|
| 255 | class inconvertclass : public convertclass
|
---|
| 256 | {
|
---|
| 257 | public:
|
---|
| 258 | inconvertclass ();
|
---|
| 259 | void reset ();
|
---|
| 260 | void setinput (char *thestart, size_t thelen);
|
---|
| 261 |
|
---|
| 262 | // output will be cleared before the conversion
|
---|
| 263 | virtual void convert (text_t &output, status_t &status);
|
---|
| 264 |
|
---|
| 265 | // will treat the text_t as a 8-bit string and convert
|
---|
| 266 | // it to a 16-bit string using the about convert method.
|
---|
| 267 | text_t convert (const text_t &t);
|
---|
| 268 |
|
---|
| 269 | protected:
|
---|
| 270 | char *start;
|
---|
| 271 | size_t len;
|
---|
| 272 | };
|
---|
| 273 |
|
---|
| 274 | // to get something which will do the conversion
|
---|
| 275 | // to ascii declare a (non global!) instance like
|
---|
| 276 | // this
|
---|
| 277 | // inconvertclass ascii2text_t;
|
---|
| 278 |
|
---|
| 279 |
|
---|
| 280 | // Convert from a text_t class to a char stream
|
---|
| 281 | // This default version assumes the output is a ascii
|
---|
| 282 | // character array. If you set the output stream you
|
---|
| 283 | // can use this class to output to a stream using the
|
---|
| 284 | // << operator. The << operator can also be conveniently
|
---|
| 285 | // used to set the output stream by doing something like
|
---|
| 286 | //
|
---|
| 287 | // cout << text_t2ascii << textstr << anothertextstr;
|
---|
| 288 | //
|
---|
| 289 | // this class assumes that the input text doesn't change
|
---|
| 290 | // while the conversion takes place
|
---|
| 291 | class outconvertclass : public convertclass
|
---|
| 292 | {
|
---|
| 293 | public:
|
---|
| 294 | outconvertclass ();
|
---|
| 295 | void reset ();
|
---|
| 296 | void setinput (text_t *theinput);
|
---|
| 297 | // note that convert does not null-terminate the
|
---|
| 298 | // output array of characters
|
---|
| 299 | virtual void convert (char *output, size_t maxlen,
|
---|
| 300 | size_t &len, status_t &status);
|
---|
| 301 |
|
---|
| 302 | // will convert the 16-bit string to a 8-bit stream
|
---|
| 303 | // and place the result in a text_t. This method uses
|
---|
| 304 | // the above convert function.
|
---|
| 305 | text_t convert (const text_t &t);
|
---|
| 306 |
|
---|
| 307 | void setostream (ostream *theouts);
|
---|
| 308 | ostream *getostream ();
|
---|
| 309 |
|
---|
| 310 | protected:
|
---|
| 311 | text_t *input;
|
---|
| 312 | text_t::iterator texthere; // only valid if input is valid
|
---|
| 313 |
|
---|
| 314 | ostream *outs;
|
---|
| 315 | };
|
---|
| 316 |
|
---|
| 317 | // to get something which will do the conversion
|
---|
| 318 | // to text_t declare a (non global!) instance like
|
---|
| 319 | // this
|
---|
| 320 | // outconvertclass text_t2ascii;
|
---|
| 321 |
|
---|
| 322 |
|
---|
| 323 | // stream operators for the output class
|
---|
| 324 | outconvertclass &operator<< (ostream &theouts, outconvertclass &outconverter);
|
---|
| 325 | outconvertclass &operator<< (outconvertclass &outconverter, const text_t &t);
|
---|
| 326 |
|
---|
| 327 |
|
---|
| 328 | #endif
|
---|