/*=export_func ao_string_tokenize
*
* what: tokenize an input string
*
* arg: + char const* + string + string to be tokenized +
*
* ret_type: token_list_t*
* ret_desc: pointer to a structure that lists each token
*
* doc:
*
* This function will convert one input string into a list of strings.
* The list of strings is derived by separating the input based on
* white space separation. However, if the input contains either single
* or double quote characters, then the text after that character up to
* a matching quote will become the string in the list.
*
* The returned pointer should be deallocated with @code{free(3C)} when
* are done using the data. The data are placed in a single block of
* allocated memory. Do not deallocate individual token/strings.
*
* The structure pointed to will contain at least these two fields:
* @table @samp
* @item tkn_ct
* The number of tokens found in the input string.
* @item tok_list
* An array of @code{tkn_ct + 1} pointers to substring tokens, with
* the last pointer set to NULL.
* @end table
*
* There are two types of quoted strings: single quoted (@code{'}) and
* double quoted (@code{"}). Singly quoted strings are fairly raw in that
* escape characters (@code{\\}) are simply another character, except when
* preceding the following characters:
* @example
* @code{\\} double backslashes reduce to one
* @code{'} incorporates the single quote into the string
* @code{\n} suppresses both the backslash and newline character
* @end example
*
* Double quote strings are formed according to the rules of string
* constants in ANSI-C programs.
*
* example:
* @example
* #include <stdlib.h>
* int ix;
* token_list_t* ptl = ao_string_tokenize(some_string)
* for (ix = 0; ix < ptl->tkn_ct; ix++)
* do_something_with_tkn(ptl->tkn_list[ix]);
* free(ptl);
* @end example
* Note that everything is freed with the one call to @code{free(3C)}.
*
* err:
* NULL is returned and @code{errno} will be set to indicate the problem:
* @itemize @bullet
* @item
* @code{EINVAL} - There was an unterminated quoted string.
* @item
* @code{ENOENT} - The input string was empty.
* @item
* @code{ENOMEM} - There is not enough memory.
* @end itemize
=*/
token_list_t*
ao_string_tokenize(char const* str)
{
token_list_t* res = alloc_token_list(str);
ch_t* pzDest;
/*
* Now copy each token into the output buffer.
*/
if (res == NULL)
return res;
pzDest = (ch_t*)(res->tkn_list[0]);
res->tkn_ct = 0;
do {
res->tkn_list[ res->tkn_ct++ ] = pzDest;
for (;;) {
int ch = (ch_t)*str;
if (IS_WHITESPACE_CHAR(ch)) {
found_white_space:
str = SPN_WHITESPACE_CHARS(str+1);
break;
}
switch (ch) {
case '"':
copy_cooked(&pzDest, &str);
if (str == NULL) {
free(res);
errno = EINVAL;
return NULL;
}
if (IS_WHITESPACE_CHAR(*str))
goto found_white_space;
break;
case '\'':
copy_raw(&pzDest, &str);
if (str == NULL) {
free(res);
errno = EINVAL;
return NULL;
}
if (IS_WHITESPACE_CHAR(*str))
goto found_white_space;
break;
case NUL:
goto copy_done;
default:
str++;
*(pzDest++) = (unsigned char)ch;
}
} copy_done:;
/*
* NUL terminate the last token and see if we have any more tokens.
*/
*(pzDest++) = NUL;
} while (*str != NUL);
res->tkn_list[ res->tkn_ct ] = NULL;
return res;
}
/*=export_func ao_string_tokenize
*
* what: tokenize an input string
*
* arg: + char const* + string + string to be tokenized +
*
* ret_type: token_list_t*
* ret_desc: pointer to a structure that lists each token
*
* doc:
*
* This function will convert one input string into a list of strings.
* The list of strings is derived by separating the input based on
* white space separation. However, if the input contains either single
* or double quote characters, then the text after that character up to
* a matching quote will become the string in the list.
*
* The returned pointer should be deallocated with @code{free(3C)} when
* are done using the data. The data are placed in a single block of
* allocated memory. Do not deallocate individual token/strings.
*
* The structure pointed to will contain at least these two fields:
* @table @samp
* @item tkn_ct
* The number of tokens found in the input string.
* @item tok_list
* An array of @code{tkn_ct + 1} pointers to substring tokens, with
* the last pointer set to NULL.
* @end table
*
* There are two types of quoted strings: single quoted (@code{'}) and
* double quoted (@code{"}). Singly quoted strings are fairly raw in that
* escape characters (@code{\\}) are simply another character, except when
* preceding the following characters:
* @example
* @code{\\} double backslashes reduce to one
* @code{'} incorporates the single quote into the string
* @code{\n} suppresses both the backslash and newline character
* @end example
*
* Double quote strings are formed according to the rules of string
* constants in ANSI-C programs.
*
* example:
* @example
* #include <stdlib.h>
* int ix;
* token_list_t* ptl = ao_string_tokenize( some_string )
* for (ix = 0; ix < ptl->tkn_ct; ix++)
* do_something_with_tkn( ptl->tkn_list[ix] );
* free( ptl );
* @end example
* Note that everything is freed with the one call to @code{free(3C)}.
*
* err:
* NULL is returned and @code{errno} will be set to indicate the problem:
* @itemize @bullet
* @item
* @code{EINVAL} - There was an unterminated quoted string.
* @item
* @code{ENOENT} - The input string was empty.
* @item
* @code{ENOMEM} - There is not enough memory.
* @end itemize
=*/
token_list_t*
ao_string_tokenize( char const* str )
{
int max_token_ct = 1; /* allow for trailing NUL on string */
token_list_t* res;
if (str == NULL) goto bogus_str;
/*
* Trim leading white space. Use "ENOENT" and a NULL return to indicate
* an empty string was passed.
*/
while (isspace( (ch_t)*str )) str++;
if (*str == NUL) {
bogus_str:
errno = ENOENT;
return NULL;
}
/*
* Take an approximate count of tokens. If no quoted strings are used,
* it will be accurate. If quoted strings are used, it will be a little
* high and we'll squander the space for a few extra pointers.
*/
{
cc_t* pz = (cc_t*)str;
do {
max_token_ct++;
while (! isspace( *++pz ))
if (*pz == NUL) goto found_nul;
while (isspace( *pz )) pz++;
} while (*pz != NUL);
found_nul:
;
}
res = malloc( sizeof(*res) + strlen(str) + (max_token_ct * sizeof(ch_t*)) );
if (res == NULL) {
errno = ENOMEM;
return res;
}
/*
* Now copy each token into the output buffer.
*/
{
ch_t* pzDest = (ch_t*)(res->tkn_list + (max_token_ct + 1));
res->tkn_ct = 0;
do {
res->tkn_list[ res->tkn_ct++ ] = pzDest;
for (;;) {
int ch = (ch_t)*str;
if (isspace( ch )) {
found_white_space:
while (isspace( (ch_t)*++str )) ;
break;
}
switch (ch) {
case '"':
copy_cooked( &pzDest, &str );
if (str == NULL) {
free(res);
errno = EINVAL;
return NULL;
}
if (isspace( (ch_t)*str ))
goto found_white_space;
break;
case '\'':
copy_raw( &pzDest, &str );
if (str == NULL) {
free(res);
errno = EINVAL;
return NULL;
}
if (isspace( (ch_t)*str ))
goto found_white_space;
break;
case NUL:
goto copy_done;
default:
str++;
*(pzDest++) = ch;
}
} copy_done:;
/*
* NUL terminate the last token and see if we have any more tokens.
*/
*(pzDest++) = NUL;
} while (*str != NUL);
res->tkn_list[ res->tkn_ct ] = NULL;
}
return res;
}
