#ifndef CST_UTIL_H
#define CST_UTIL_H

#include <stddef.h>
#include <stdint.h>

#ifdef __cplusplus
extern "C" {
#endif

typedef struct {
  char *buf;
  size_t len;
  size_t cap;
} cst_buf_t;

int cst_buf_append(cst_buf_t *b, const char *s, size_t n);
int cst_buf_puts(cst_buf_t *b, const char *s);
int cst_buf_printf(cst_buf_t *b, const char *fmt, ...);
void cst_buf_free(cst_buf_t *b);
/* Take ownership of the NUL-terminated buffer (never NULL on success). */
char *cst_buf_steal(cst_buf_t *b);

/* Largest n' <= n that does not split a UTF-8 sequence of s. */
size_t cst_utf8_floor(const char *s, size_t n);
/* Copy s[0..n) replacing invalid UTF-8 with '?'. malloc'd, NUL-terminated. */
char *cst_utf8_sanitize(const char *s, size_t n, size_t *out_len);
int cst_utf8_valid(const char *s, size_t n);

/* Re-chunks a byte stream so no piece ends inside a UTF-8 sequence: the
 * incomplete tail (at most 3 bytes) waits in the hold for the next feed. */
typedef struct {
  char b[4];
  size_t n;
} cst_utf8_hold_t;
/* Returns the complete prefix of hold+s[0..n) (malloc'd, NUL-terminated,
 * *out_len may be 0), or NULL on OOM. */
char *cst_utf8_hold_feed(cst_utf8_hold_t *h, const char *s, size_t n,
                         size_t *out_len);

/* Text files may start with a UTF-8 BOM (Windows editors): its length (0/3),
 * and an in-place strip of the NUL-terminated s (*len updated when given). */
size_t cst_bom_len(const char *s, size_t n);
void cst_strip_bom(char *s, size_t *len);
/* Line endings: "\r\n" -> "\n" in place (returns the new length); whether
 * every line of s ends in "\r\n" (and at least one does); and a malloc'd
 * copy of s with bare "\n" turned into "\r\n" when crlf, its BOM dropped and
 * a BOM added when bom. Edits keep a Windows file's style with these. */
size_t cst_crlf_to_lf(char *s, size_t n);
int cst_text_is_crlf(const char *s, size_t n);
char *cst_text_restyle(const char *s, size_t n, int crlf, int bom,
                       size_t *out_len);

/* fnmatch(3) without FNM_PATHNAME ('*' also crosses '/'): * ? [..] [!..]
 * [[:class:]] and backslash escapes over UTF-8 code points. Returns 0 on a
 * match. Always case-insensitive on Windows. */
#define CST_FNM_PERIOD 1   /* a leading '.' must be matched literally */
#define CST_FNM_CASEFOLD 2
int cst_fnmatch(const char *pat, const char *str, int flags);

uint64_t cst_fnv1a64(uint64_t h, const void *data, size_t n);
#define CST_FNV_INIT 1469598103934665603ULL

#ifdef __cplusplus
}
#endif

#endif