ref: 1a751a59393ad696cdd7f6db882e3d0118e0b54e
dir: /sys/man/2/string/
.TH STRING 2 .SH NAME s_alloc, s_append, s_array, s_copy, s_error, s_free, s_incref, s_memappend, s_nappend, s_new, s_newalloc, s_parse, s_reset, s_restart, s_terminate, s_tolower, s_putc, s_unique, s_grow, s_read, s_read_line, s_getline \- extensible strings .SH SYNOPSIS .B #include <u.h> .br .B #include <libc.h> .br .B #include <String.h> .PP .B String* s_new(void) .br .B void s_free(String *s) .br .B String* s_newalloc(int n) .br .B String* s_array(char *p, int n) .br .B String* s_grow(String *s, int n) .PP .B void s_putc(String *s, int c) .br .B void s_terminate(String *s) .br .B String* s_reset(String *s) .br .B String* s_restart(String *s) .br .B String* s_append(String *s, char *p) .br .B String* s_nappend(String *s, char *p, int n) .br .B String* s_memappend(String *s, char *p, int n) .br .B String* s_copy(char *p) .br .B String* s_parse(String *s1, String *s2) .br .PP .B void s_tolower(String *s) .PP .B String* s_incref(String *s) .br .B String* s_unique(String *s) .PP .B #include <bio.h> .PP .B int s_read(Biobuf *b, String *s, int n) .br .B char* s_read_line(Biobuf *b, String *s) .br .B char* s_getline(Biobuf *b, String *s) .SH DESCRIPTION .PP These routines manipulate extensible strings. The basic type is .BR String , which points to an array of characters. The string maintains pointers to the beginning and end of the allocated array. In addition a finger pointer keeps track of where parsing will start (for .IR s_parse ) or new characters will be added (for .IR s_putc , .IR s_append , and .IR s_nappend ). The structure, and a few useful macros are: .sp .EX typedef struct String { Lock; char *base; /* base of String */ char *end; /* end of allocated space+1 */ char *ptr; /* ptr into String */ ... } String; #define s_to_c(s) ((s)->base) #define s_len(s) ((s)->ptr-(s)->base) #define s_clone(s) s_copy((s)->base) .EE .PP .I S_to_c is used when code needs a reference to the character array. Using .B s->base directly is frowned upon since it exposes too much of the implementation. .SS "allocation and freeing .PP A string must be allocated before it can be used. One normally does this using .IR s_new , giving the string an initial allocation of 128 bytes. If you know that the string will need to grow much longer, you can use .I s_newalloc instead, specifying the number of bytes in the initial allocation. .PP .I S_free causes both the string and its character array to be freed. .PP .I S_grow grows a string's allocation by a fixed amount. It is useful if you are reading directly into a string's character array but should be avoided if possible. .PP .I S_array is used to create a constant array, that is, one whose contents won't change. It points directly to the character array given as an argument. Tread lightly when using this call. .SS "Filling the string After its initial allocation, the string points to the beginning of an allocated array of characters starting with .SM NUL. .PP .I S_putc writes a character into the string at the pointer and advances the pointer to point after it. .PP .I S_terminate writes a .SM NUL at the pointer but doesn't advance it. .PP .I S_restart resets the pointer to the begining of the string but doesn't change the contents. .PP .I S_reset is equivalent to .I s_restart followed by .IR s_terminate . .PP .I S_append and .I s_nappend copy characters into the string at the pointer and advance the pointer. They also write a .SM NUL at the pointer without advancing the pointer beyond it. Both routines stop copying on encountering a .SM NUL. .I S_memappend is like .I s_nappend but doesn't stop at a .SM NUL. .PP If you know the initial character array to be copied into a string, you can allocate a string and copy in the bytes using .IR s_copy . This is the equivalent of a .I s_new followed by an .IR s_append . .PP .I S_parse copies the next white space terminated token from .I s1 to the end of .IR s2 . White space is defined as space, tab, and newline. Both single and double quoted strings are treated as a single token. The bounding quotes are not copied. There is no escape mechanism. .PP .I S_tolower converts all .SM ASCII characters in the string to lower case. .SS Multithreading .PP .I S_incref is used by multithreaded programs to avoid having the string memory released until the last user of the string performs an .IR s_free . .I S_unique returns a unique copy of the string: if the reference count it 1 it returns the string, otherwise it returns an .I s_clone of the string. .SS "Bio interaction .PP .I S_read reads the requested number of characters through a .I Biobuf into a string. The string is grown as necessary. An eof or error terminates the read. The number of bytes read is returned. The string is null terminated. .PP .I S_read_line reads up to and including the next newline and returns a pointer to the beginning of the bytes read. An eof or error terminates the read. The string is null terminated. .PP .I S_getline reads up to the next newline and returns a pointer to the beginning of the bytes read. Leading spaces and tabs and the trailing newline are all discarded. .I S_getline will recursively read through files included with .B #include and discard all other lines beginning with .BR # . .SH SOURCE .B /sys/src/libString .SH SEE ALSO .IR bio (2)