diff options
Diffstat (limited to 'manual/string.texi')
| -rw-r--r-- | manual/string.texi | 118 |
1 files changed, 105 insertions, 13 deletions
diff --git a/manual/string.texi b/manual/string.texi index af95925a14..cb9f5412f8 100644 --- a/manual/string.texi +++ b/manual/string.texi @@ -890,6 +890,9 @@ specifying a null character as the value of the @var{c} argument. @comment BSD @deftypefun {char *} index (const char *@var{string}, int @var{c}) @code{index} is another name for @code{strchr}; they are exactly the same. +New code should always use @code{strchr} since this name is defined in +@w{ISO C} while @code{index} is a BSD invention which never was available +on @w{System V} derived systems. @end deftypefun @comment string.h @@ -910,6 +913,9 @@ strrchr ("hello, world", 'l') @comment BSD @deftypefun {char *} rindex (const char *@var{string}, int @var{c}) @code{rindex} is another name for @code{strrchr}; they are exactly the same. +New code should always use @code{strrchr} since this name is defined in +@w{ISO C} while @code{rindex} is a BSD invention which never was available +on @w{System V} derived systems. @end deftypefun @comment string.h @@ -1067,13 +1073,14 @@ Here is a simple example showing the use of @code{strtok}. @dots{} -char string[] = "words separated by spaces -- and, punctuation!"; +const char string[] = "words separated by spaces -- and, punctuation!"; const char delimiters[] = " .,;:!-"; -char *token; +char *token, *cp; @dots{} -token = strtok (string, delimiters); /* token => "words" */ +cp = strdupa (string); /* Make writable copy. */ +token = strtok (cp, delimiters); /* token => "words" */ token = strtok (NULL, delimiters); /* token => "separated" */ token = strtok (NULL, delimiters); /* token => "by" */ token = strtok (NULL, delimiters); /* token => "spaces" */ @@ -1097,7 +1104,7 @@ pointer. Calling @code{strtok_r} with a null pointer for @var{newstring} and leaving @var{save_ptr} between the calls unchanged does the job without limiting reentrancy. -This function was proposed for POSIX.1b and can be found on many systems +This function is defined in POSIX-1 and can be found on many systems which support multi-threading. @end deftypefun @@ -1123,14 +1130,14 @@ Here is how the above example looks like when @code{strsep} is used. @dots{} -char string[] = "words separated by spaces -- and, punctuation!"; +const char string[] = "words separated by spaces -- and, punctuation!"; const char delimiters[] = " .,;:!-"; char *running; char *token; @dots{} -running = string; +running = strdupa (string); token = strsep (&running, delimiters); /* token => "words" */ token = strsep (&running, delimiters); /* token => "separated" */ token = strsep (&running, delimiters); /* token => "by" */ @@ -1180,13 +1187,66 @@ The function returns a pointer to a static buffer which contains the string representing of the encoding of @var{n}. To encoded a series of bytes the use should append the new string to the destination buffer. @emph{Warning:} Since a static buffer is used this function should not -be used in multi-threaded programs. There is no thread-safe alternatice +be used in multi-threaded programs. There is no thread-safe alternative to this function in the C library. @end deftypefun +Alone the @code{l64a} function is not usable. To encode arbitrary +sequences of bytes one needs some more code and this could look like +this: + +@smallexample +char * +encode (const void *buf, size_t len) +@{ + /* @r{We know in advance how long the buffer has to be.} */ + unsigned char *in = (unsigned char *) buf; + char *out = malloc (6 + ((len + 3) / 4) * 6 + 1); + char *cp = out; + + /* @r{Encode the length.} */ + memcpy (cp, l64a (len), 6); + cp += 6; + + while (len > 3) + @{ + unsigned long int n = *in++; + n = (n << 8) | *in++; + n = (n << 8) | *in++; + n = (n << 8) | *in++; + len -= 4; + /* @r{Using `htonl' is necessary so that the data can be} + @r{decoded even on machines with different byte order.} */ + memcpy (cp, l64a (htonl (n)), 6); + cp += 6; + @} + if (len > 0) + @{ + unsigned long int n = *in++; + if (--len > 0) + @{ + n = (n << 8) | *in++; + if (--len > 0) + n = (n << 8) | *in; + @} + memcpy (cp, l64a (htonl (n)), 6); + cp += 6; + @} + *cp = '\0'; + return out; +@} +@end smallexample + +It is strange that the library does not provide the complete +functionality needed but so be it. There are some other encoding +methods which are much more widely used (UU encoding, Base64 encoding). +Generally, it is better to use one of these encodings. + To decode data produced with @code{l64a} the following function should be used. +@comment stdlib.h +@comment XPG @deftypefun {long int} a64l (const char *@var{string}) The parameter @var{string} should contain a string which was produced by a call to @code{l64a}. The function processes the next 6 characters and @@ -1205,17 +1265,17 @@ characters. @node Argz and Envz Vectors @section Argz and Envz Vectors -@cindex argz vectors +@cindex argz vectors (string vectors) @cindex string vectors, null-character separated @cindex argument vectors, null-character separated @dfn{argz vectors} are vectors of strings in a contiguous block of memory, each element separated from its neighbors by null-characters (@code{'\0'}). -@cindex envz vectors +@cindex envz vectors (environment vectors) @cindex environment vectors, null-character separated @dfn{Envz vectors} are an extension of argz vectors where each element is a -name-value pair, separated by a @code{'='} character (as in a unix +name-value pair, separated by a @code{'='} character (as in a Unix environment). @menu @@ -1247,13 +1307,17 @@ allocation error occurs. @pindex argz.h These functions are declared in the standard include file @file{argz.h}. +@comment argz.h +@comment GNU @deftypefun {error_t} argz_create (char *const @var{argv}[], char **@var{argz}, size_t *@var{argz_len}) -The @code{argz_create} function converts the unix-style argument vector +The @code{argz_create} function converts the Unix-style argument vector @var{argv} (a vector of pointers to normal C strings, terminated by @code{(char *)0}; @pxref{Program Arguments}) into an argz vector with the same elements, which is returned in @var{argz} and @var{argz_len}. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {error_t} argz_create_sep (const char *@var{string}, int @var{sep}, char **@var{argz}, size_t *@var{argz_len}) The @code{argz_create_sep} function converts the null-terminated string @var{string} into an argz vector (returned in @var{argz} and @@ -1261,14 +1325,18 @@ The @code{argz_create_sep} function converts the null-terminated string character @var{sep}. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {size_t} argz_count (const char *@var{argz}, size_t @var{arg_len}) Returns the number of elements in the argz vector @var{argz} and @var{argz_len}. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {void} argz_extract (char *@var{argz}, size_t @var{argz_len}, char **@var{argv}) The @code{argz_extract} function converts the argz vector @var{argz} and -@var{argz_len} into a unix-style argument vector stored in @var{argv}, +@var{argz_len} into a Unix-style argument vector stored in @var{argv}, by putting pointers to every element in @var{argz} into successive positions in @var{argv}, followed by a terminator of @code{0}. @var{Argv} must be pre-allocated with enough space to hold all the @@ -1281,6 +1349,8 @@ still active. This function is useful for passing the elements in @var{argz} to an exec function (@pxref{Executing a File}). @end deftypefun +@comment argz.h +@comment GNU @deftypefun {void} argz_stringify (char *@var{argz}, size_t @var{len}, int @var{sep}) The @code{argz_stringify} converts @var{argz} into a normal string with the elements separated by the character @var{sep}, by replacing each @@ -1289,20 +1359,26 @@ string) with @var{sep}. This is handy for printing @var{argz} in a readable manner. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {error_t} argz_add (char **@var{argz}, size_t *@var{argz_len}, const char *@var{str}) The @code{argz_add} function adds the string @var{str} to the end of the argz vector @code{*@var{argz}}, and updates @code{*@var{argz}} and @code{*@var{argz_len}} accordingly. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {error_t} argz_add_sep (char **@var{argz}, size_t *@var{argz_len}, const char *@var{str}, int @var{delim}) The @code{argz_add_sep} function is similar to @code{argz_add}, but @var{str} is split into separate elements in the result at occurances of the character @var{delim}. This is useful, for instance, for -adding the components of a unix search path to an argz vector, by using +adding the components of a Unix search path to an argz vector, by using a value of @code{':'} for @var{delim}. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {error_t} argz_append (char **@var{argz}, size_t *@var{argz_len}, const char *@var{buf}, size_t @var{buf_len}) The @code{argz_append} function appends @var{buf_len} bytes starting at @var{buf} to the argz vector @code{*@var{argz}}, reallocating @@ -1310,6 +1386,8 @@ The @code{argz_append} function appends @var{buf_len} bytes starting at @code{*@var{argz_len}}. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {error_t} argz_delete (char **@var{argz}, size_t *@var{argz_len}, char *@var{entry}) If @var{entry} points to the beginning of one of the elements in the argz vector @code{*@var{argz}}, the @code{argz_delete} function will @@ -1319,6 +1397,8 @@ destructive argz functions usually reallocate their argz argument, pointers into argz vectors such as @var{entry} will then become invalid. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {error_t} argz_insert (char **@var{argz}, size_t *@var{argz_len}, char *@var{before}, const char *@var{entry}) The @code{argz_insert} function inserts the string @var{entry} into the argz vector @code{*@var{argz}} at a point just before the existing @@ -1330,6 +1410,8 @@ is @code{0}, @var{entry} is added to the end instead (as if by @var{before} will result in @var{entry} being inserted at the beginning. @end deftypefun +@comment argz.h +@comment GNU @deftypefun {char *} argz_next (char *@var{argz}, size_t @var{argz_len}, const char *@var{entry}) The @code{argz_next} function provides a convenient way of iterating over the elements in the argz vector @var{argz}. It returns a pointer @@ -1387,6 +1469,8 @@ fail) have a return type of @code{error_t}, and return either @code{0} or @pindex envz.h These functions are declared in the standard include file @file{envz.h}. +@comment envz.h +@comment GNU @deftypefun {char *} envz_entry (const char *@var{envz}, size_t @var{envz_len}, const char *@var{name}) The @code{envz_entry} function finds the entry in @var{envz} with the name @var{name}, and returns a pointer to the whole entry---that is, the argz @@ -1394,6 +1478,8 @@ element which begins with @var{name} followed by a @code{'='} character. If there is no entry with that name, @code{0} is returned. @end deftypefun +@comment envz.h +@comment GNU @deftypefun {char *} envz_get (const char *@var{envz}, size_t @var{envz_len}, const char *@var{name}) The @code{envz_get} function finds the entry in @var{envz} with the name @var{name} (like @code{envz_entry}), and returns a pointer to the value @@ -1401,6 +1487,8 @@ portion of that entry (following the @code{'='}). If there is no entry with that name (or only a null entry), @code{0} is returned. @end deftypefun +@comment envz.h +@comment GNU @deftypefun {error_t} envz_add (char **@var{envz}, size_t *@var{envz_len}, const char *@var{name}, const char *@var{value}) The @code{envz_add} function adds an entry to @code{*@var{envz}} (updating @code{*@var{envz}} and @code{*@var{envz_len}}) with the name @@ -1410,6 +1498,8 @@ already exists in @var{envz}, it is removed first. If @var{value} is (mentioned above). @end deftypefun +@comment envz.h +@comment GNU @deftypefun {error_t} envz_merge (char **@var{envz}, size_t *@var{envz_len}, const char *@var{envz2}, size_t @var{envz2_len}, int @var{override}) The @code{envz_merge} function adds each entry in @var{envz2} to @var{envz}, as if with @code{envz_add}, updating @code{*@var{envz}} and @@ -1421,6 +1511,8 @@ entry in @var{envz} can prevent an entry of the same name in @var{envz2} from being added to @var{envz}, if @var{override} is false. @end deftypefun +@comment envz.h +@comment GNU @deftypefun {void} envz_strip (char **@var{envz}, size_t *@var{envz_len}) The @code{envz_strip} function removes any null entries from @var{envz}, updating @code{*@var{envz}} and @code{*@var{envz_len}}. |