/usr/include/wvstreams/wvstrutils.h is in libwvstreams-dev 4.6.1-2build1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 | /* -*- Mode: C++ -*-
* Worldvisions Weaver Software:
* Copyright (C) 1997-2002 Net Integration Technologies, Inc.
*
* Various little string functions...
*
* FIXME: and some other assorted crap that belongs anywhere but here.
*/
#ifndef __WVSTRUTILS_H
#define __WVSTRUTILS_H
#include <sys/types.h> // for off_t
#include <time.h>
#include <ctype.h>
#include "wvstring.h"
#include "wvstringlist.h"
#include "wvhex.h"
#ifndef _WIN32
#include "wvregex.h"
#endif
/** \file
* Various little string functions
*/
/**
* Add character c to the end of a string after removing
* terminating carriage returns/linefeeds if any.
*
* You need a buffer that's at least one character bigger than the
* current length of the string, including the terminating NULL.
*/
char *terminate_string(char *string, char c);
/**
* Trims whitespace from the beginning and end of the character string,
* including carriage return / linefeed characters. Modifies the string
* in place. Returns the new first character of the string, which points
* either at 'string' itself or some character contained therein.
*
* string is allowed to be NULL; returns NULL in that case.
*/
char *trim_string(char *string);
/**
* Similar to above, but trims the string starting at the first occurrence of
* c.
*/
char *trim_string(char *string, char c);
/**
* return the string formed by concatenating string 'a' and string 'b' with
* the 'sep' character between them. For example,
* spacecat("xx", "yy", ";");
* returns "xx;yy", and
* spacecat("xx;;", "yy", ";")
* returns "xx;;;yy", and
* spacecat("xx;;", "yy", ";", true)
* returns "xx;yy".
*
* This function is much faster than the more obvious WvString("%s;%s", a, b),
* so it's useful when you're producing a *lot* of string data.
*/
WvString spacecat(WvStringParm a, WvStringParm b, char sep = ' ',
bool onesep = false);
/**
* Replaces all whitespace characters in the string with non-breaking spaces
* ( ) for use with web stuff.
*/
char *non_breaking(const char *string);
/**
* Replace all instances of c1 with c2 for the first 'length' characters in
* 'string'. Ignores terminating NULL, so make sure you set 'length' correctly.
*/
void replace_char(void *string, char c1, char c2, int length);
/**
* Snip off the first part of 'haystack' if it consists of 'needle'.
*/
char *snip_string(char *haystack, char *needle);
#ifndef _WIN32
/**
* In-place modify a character string so that all contained letters are
* in lower case. Returns 'string'.
*/
char *strlwr(char *string);
/**
* In-place modify a character string so that all contained letters are
* in upper case. Returns 'string'.
*/
char *strupr(char *string);
#endif
/** Returns true if all characters in 'string' are isalnum() (alphanumeric). */
bool is_word(const char *string);
/**
* Produce a hexadecimal dump of the data buffer in 'buf' of length 'len'.
* It is formatted with 16 bytes per line; each line has an address offset,
* hex representation, and printable representation.
*
* This is used mostly for debugging purposes. You can send the returned
* WvString object directly to a WvLog or any other WvStream for output.
*/
WvString hexdump_buffer(const void *buf, size_t len, bool charRep = true);
/**
* Returns true if 'c' is a newline or carriage return character.
* Increases code readability a bit.
*/
bool isnewline(char c);
/**
* Converts escaped characters (things like %20 etc.) from web URLS
* into their normal ASCII representations. If you happen to be
* decoding PEM encoded stuff, or anything that has + signs in it that
* you don't want encoded as spaces, then set no_space to true, and
* it should "just work" for you.
*/
WvString url_decode(WvStringParm str, bool no_space = false);
/**
* Converts all those pesky spaces, colons, and other nasties into nice
* unreadable Quasi-Unicode codes. The 'unsafe' parameter is a list of
* characters that are unsafe and should be escaped. If unspecified,
* all characters which are not part of the uric character class defined
* in RFC 2396 will be escaped. Note: The '%' character is always escaped, as
* otherwise the string would not be decodable.
*/
WvString url_encode(WvStringParm str, WvStringParm unsafe = "");
/**
* Returns the difference between to dates in a human readable format
*/
WvString diff_dates(time_t t1, time_t t2);
/**
* Returns an RFC822-compatible date made out of _when, or, if _when < 0, out of
* the current time.
*/
WvString rfc822_date(time_t _when = -1);
/** Returns an RFC1123-compatible date made out of _when */
WvString rfc1123_date(time_t _when);
/** Return the local date (TZ applied) out of _when */
WvString local_date(time_t _when = -1);
/** Return the local time (in format of ISO 8601) out of _when */
WvString intl_time(time_t _when = -1);
/** Return the local date (in format of ISO 8601) out of _when */
WvString intl_date(time_t _when = -1);
/** Return the local date and time (in format of ISO 8601) out of _when */
WvString intl_datetime(time_t _when = -1);
time_t intl_gmtoff(time_t t);
#ifndef _WIN32
/**
* Similar to crypt(), but this randomly selects its own salt.
* This function is defined in strcrypt.cc. It chooses to use the DES
* engine.
*/
WvString passwd_crypt(const char *str);
#endif
/**
* Similar to crypt(), but this randomly selects its own salt.
* This function is defined in strcrypt.cc. It chooses to use the MD5
* engine.
*/
WvString passwd_md5(const char *str);
/**
* Returns a string with a backslash in front of every non alphanumeric
* character in s1.
*/
WvString backslash_escape(WvStringParm s1);
/** How many times does 'c' occur in "s"? */
int strcount(WvStringParm s, const char c);
/**
* Example: encode_hostname_as_DN("www.fizzle.com")
* will result in dc=www,dc=fizzle,dc=com,cn=www.fizzle.com
*/
WvString encode_hostname_as_DN(WvStringParm hostname);
/**
* Given a hostname, turn it into a "nice" one. It has to start with a
* letter/number, END with a letter/number, have underscores converted to
* hyphens, and have no more than one hyphen in a row. If we can't do this
* and have any sort of answer, return "UNKNOWN".
*/
WvString nice_hostname(WvStringParm name);
/**
* Take a full path/file name and splits it up into respective pathname and
* filename. This can also be useful for splitting the toplevel directory off a
* path.
*/
WvString getfilename(WvStringParm fullname);
WvString getdirname(WvStringParm fullname);
/*
* Possible rounding methods for numbers -- remember from school?
*/
enum RoundingMethod
{
ROUND_DOWN,
ROUND_DOWN_AT_POINT_FIVE,
ROUND_UP_AT_POINT_FIVE,
ROUND_UP
};
/**
* Given a number of blocks and a blocksize (default==1 byte), return a
* WvString containing a human-readable representation of blocks*blocksize.
* This function uses SI prefixes.
*/
WvString sizetoa(unsigned long long blocks, unsigned long blocksize = 1,
RoundingMethod rounding_method = ROUND_UP_AT_POINT_FIVE);
/**
* Given a size in kilobyes, return a human readable size.
* This function uses SI prefixes (1 MB = 1 000 KB = 1 000 000 B).
*/
WvString sizektoa(unsigned long long kbytes,
RoundingMethod rounding_method = ROUND_UP_AT_POINT_FIVE);
/**
* Given a number of blocks and a blocksize (default==1 byte), return a
* WvString containing a human-readable representation of blocks*blocksize.
* This function uses IEC prefixes.
*/
WvString sizeitoa(unsigned long long blocks, unsigned long blocksize = 1,
RoundingMethod rounding_method = ROUND_UP_AT_POINT_FIVE);
/**
* Given a size in kilobytes, return a human readable size.
* This function uses IEC prefixes.
*/
WvString sizekitoa(unsigned long long kbytes,
RoundingMethod rounding_method = ROUND_UP_AT_POINT_FIVE);
/** Given a number of seconds, returns a formatted human-readable string
* saying how long the period is.
*/
WvString secondstoa(unsigned int total_seconds);
/**
* Finds a string in an array and returns its index.
* Returns -1 if not found.
*/
int lookup(const char *str, const char * const *table,
bool case_sensitive = false);
/**
* Splits a string and adds each substring to a collection.
* coll : the collection of strings to add to
* _s : the string to split
* splitchars : the set of delimiter characters
* limit : the maximum number of elements to split
*/
template<class StringCollection>
void strcoll_split(StringCollection &coll, WvStringParm _s,
const char *splitchars = " \t", int limit = 0)
{
WvString s(_s);
char *sptr = s.edit(), *eptr, oldc;
// Simple if statement to catch (and add) empty (but not NULL) strings.
if (sptr && !*sptr )
{
WvString *emptyString = new WvString("");
coll.add(emptyString, true);
}
// Needed to catch delimeters at the beginning of the string.
bool firstrun = true;
while (sptr && *sptr)
{
--limit;
if (firstrun)
{
firstrun = false;
}
else
{
sptr += strspn(sptr, splitchars);
}
if (limit)
{
eptr = sptr + strcspn(sptr, splitchars);
}
else
{
eptr = sptr + strlen(sptr);
}
oldc = *eptr;
*eptr = 0;
WvString *newstr = new WvString(sptr);
coll.add(newstr, true);
*eptr = oldc;
sptr = eptr;
}
}
/**
* Splits a string and adds each substring to a collection.
* this behaves differently in that it actually delimits the
* pieces as fields and returns them, it doesn't treat multiple
* delimeters as one and skip them.
*
* ie., parm1::parm2 -> 'parm1','','parm2' when delimited with ':'
*
* coll : the collection of strings to add to
* _s : the string to split
* splitchars : the set of delimiter characters
* limit : the maximum number of elements to split
*/
template<class StringCollection>
void strcoll_splitstrict(StringCollection &coll, WvStringParm _s,
const char *splitchars = " \t", int limit = 0)
{
WvString s(_s);
char *cur = s.edit();
if (!cur) return;
for (;;)
{
--limit;
if (!limit)
{
coll.add(new WvString(cur), true);
break;
}
int len = strcspn(cur, splitchars);
char tmp = cur[len];
cur[len] = 0;
coll.add(new WvString(cur), true);
cur[len] = tmp;
if (!cur[len]) break;
cur += len + 1;
}
}
#ifndef _WIN32 // don't have regex on win32
/**
* Splits a string and adds each substring to a collection.
* coll : the collection of strings to add to
* _s : the string to split
* splitchars : the set of delimiter characters
* limit : the maximum number of elements to split
*/
template<class StringCollection>
void strcoll_split(StringCollection &coll, WvStringParm s,
const WvRegex ®ex, int limit = 0)
{
int start = 0;
int match_start, match_end;
int count = 0;
while ((limit == 0 || count < limit)
&& regex.continuable_match(&s[start], match_start, match_end)
&& match_end > 0)
{
WvString *substr = new WvString;
int len = match_start;
substr->setsize(len+1);
memcpy(substr->edit(), &s[start], len);
substr->edit()[len] = '\0';
coll.add(substr, true);
start += match_end;
++count;
}
if (limit == 0 || count < limit)
{
WvString *last = new WvString(&s[start]);
last->unique();
coll.add(last, true);
}
}
#endif
/**
* Concatenates all strings in a collection and returns the result.
* coll : the collection of strings to read from
* joinchars : the delimiter string to insert between strings
*/
template<class StringCollection>
WvString strcoll_join(const StringCollection &coll,
const char *joinchars = " \t")
{
size_t joinlen = strlen(joinchars);
size_t totlen = 1;
typename StringCollection::Iter s(
const_cast<StringCollection&>(coll));
for (s.rewind(); s.next(); )
{
if (s->cstr())
totlen += strlen(s->cstr());
totlen += joinlen;
}
totlen -= joinlen; // no join chars at tail
WvString total;
total.setsize(totlen);
char *te = total.edit();
te[0] = 0;
bool first = true;
for (s.rewind(); s.next(); )
{
if (first)
first = false;
else
strcat(te, joinchars);
if (s->cstr())
strcat(te, s->cstr());
}
return total;
}
/**
* Replace any instances of "a" with "b" in "s". Kind of like sed, only
* much dumber.
*/
WvString strreplace(WvStringParm s, WvStringParm a, WvStringParm b);
/** Replace any consecutive instances of character c with a single one */
WvString undupe(WvStringParm s, char c);
/** Do gethostname() without a fixed-length buffer */
WvString hostname();
/** Get the fqdn of the local host, using gethostbyname() and gethostname() */
WvString fqdomainname();
/** Get the current working directory without a fixed-length buffer */
WvString wvgetcwd();
/**
* Inserts SI-style spacing into a number
* (eg passing 9876543210 returns "9 876 543 210")
*/
WvString metriculate(const off_t i);
/**
* Returns everything in line (exclusively) after a.
* If a is not in line, "" is returned.
*/
WvString afterstr(WvStringParm line, WvStringParm a);
/**
* Returns everything in line (exclusively) before 'a'.
* If a is not in line, line is returned.
*/
WvString beforestr(WvStringParm line, WvStringParm a);
/**
* Returns the string of length len starting at pos in line.
* Error checking prevents seg fault.
* If pos > line.len()-1 return ""
* if pos+len > line.len() simply return from pos to end of line
*/
WvString substr(WvString line, unsigned int pos, unsigned int len);
/**
* Removes any trailing punctuation ('.', '?', or '!') from the line, and
* returns it in a new string. Does not modify line.
*/
WvString depunctuate(WvStringParm line);
// Converts a string in decimal to an arbitrary numeric type
template<class T>
bool wvstring_to_num(WvStringParm str, T &n)
{
bool neg = false;
n = 0;
for (const char *p = str; *p; ++p)
{
if (isdigit(*p))
{
n = n * T(10) + T(*p - '0');
}
else if ((const char *)str == p
&& *p == '-')
{
neg = true;
}
else return false;
}
if (neg)
n = -n;
return true;
}
/*
* Before using the C-style string escaping functions below, please consider
* using the functions in wvtclstring.h instead; they usualy lead to much more
* human readable and manageable results, and allow representation of
* lists of strings.
*/
struct CStrExtraEscape
{
char ch;
const char *esc;
};
extern const CStrExtraEscape CSTR_TCLSTR_ESCAPES[];
/// Converts data into a C-style string constant.
//
// If data is NULL, returns WvString::null; otherwise, returns an allocated
// WvString containing the C-style string constant that represents the data.
//
// All printable characters including space except " and \ are represented with
// escaping.
//
// The usual C escapes are performed, such as \n, \r, \", \\ and \0.
//
// All other characters are escaped in uppercase hex form, eg. \x9E
//
// The extra_escapes parameter allows for additional characters beyond
// the usual ones escaped in C; setting it to CSTR_TCLSTR_ESCAPES will
// escape { and } as \< and \>, which allows the resulting strings to be
// TCL-string coded without ridiculous double-escaping.
//
WvString cstr_escape(const void *data, size_t size,
const CStrExtraEscape extra_escapes[] = NULL);
/// Converts a C-style string constant into data.
//
// This function does *not* include the trailing null that a C compiler would --
// if you want this null, put \0 at the end of the C-style string
//
// If cstr is correctly formatted and max_size is large enough for the
// resulting data, returns true and size will equal the size of the
// resulting data. If data is not NULL it will contain this data.
//
// If cstr is correctly formatted but max_size is too small for the resulting
// data, returns false and size will equal the minimum value of min_size
// for this function to have returned true. If data is non-NULL it will
// contain the first max_size bytes of resulting data.
//
// If cstr is incorrectly formatted, returns false and size will equal 0.
//
// This functions works just as well on multiple, whitespace-separated
// C-style strings as well. This allows you to concatenate strings produced
// by cstr_escape, and the result of cstr_unescape will be the data blocks
// concatenated together. This implies that the empty string corresponds
// to a valid data block of length zero; however, a null string still returns
// an error.
//
// The extra_escapes parameter must match that used in the call to
// cstr_escape used to produce the escaped strings.
//
bool cstr_unescape(WvStringParm cstr, void *data, size_t max_size, size_t &size,
const CStrExtraEscape extra_escapes[] = NULL);
static inline bool is_int(const char *str)
{
if (!str)
return false;
if (*str == '-')
++str;
if (!*str)
return false;
while (*str)
if (!isdigit(*str++))
return false;
return true;
}
/// Converts a pointer into a string, like glibc's %p formatter would
/// do.
WvString ptr2str(void* ptr);
#endif // __WVSTRUTILS_H
|