utf8.h

   1 #ifndef GIT_UTF8_H
   2 #define GIT_UTF8_H
   3
   4 typedef unsigned int ucs_char_t;  /* assuming 32bit int */
   5
   6 size_t display_mode_esc_sequence_len(const char *s);
   7 int utf8_width(const char **start, size_t *remainder_p);
   8 int utf8_strnwidth(const char *string, int len, int skip_ansi);
   9 int utf8_strwidth(const char *string);
  10 int is_utf8(const char *text);
  11 int is_encoding_utf8(const char *name);
  12 int same_encoding(const char *, const char *);
  13 __attribute__((format (printf, 2, 3)))
  14 int utf8_fprintf(FILE *, const char *, ...);
  15
  16 extern const char utf8_bom[];
  17 extern int skip_utf8_bom(char **, size_t);
  18
  19 void strbuf_add_wrapped_text(struct strbuf *buf,
  20                 const char *text, int indent, int indent2, int width);
  21 void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,
  22                              int indent, int indent2, int width);
  23 void strbuf_utf8_replace(struct strbuf *sb, int pos, int width,
  24                          const char *subst);
  25
  26 #ifndef NO_ICONV
  27 char *reencode_string_iconv(const char *in, size_t insz,
  28                             iconv_t conv, int *outsz);
  29 char *reencode_string_len(const char *in, int insz,
  30                           const char *out_encoding,
  31                           const char *in_encoding,
  32                           int *outsz);
  33 #else
  34 static inline char *reencode_string_len(const char *a, int b,
  35                                         const char *c, const char *d, int *e)
  36 { if (e) *e = 0; return NULL; }
  37 #endif
  38
  39 static inline char *reencode_string(const char *in,
  40                                     const char *out_encoding,
  41                                     const char *in_encoding)
  42 {
  43         return reencode_string_len(in, strlen(in),
  44                                    out_encoding, in_encoding,
  45                                    NULL);
  46 }
  47
  48 int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding);
  49
  50 /*
  51  * Returns true if the path would match ".git" after HFS case-folding.
  52  * The path should be NUL-terminated, but we will match variants of both ".git\0"
  53  * and ".git/..." (but _not_ ".../.git"). This makes it suitable for both fsck
  54  * and verify_path().
  55  */
  56 int is_hfs_dotgit(const char *path);
  57
  58 typedef enum {
  59         ALIGN_LEFT,
  60         ALIGN_MIDDLE,
  61         ALIGN_RIGHT
  62 } align_type;
  63
  64 /*
  65  * Align the string given and store it into a strbuf as per the
  66  * 'position' and 'width'. If the given string length is larger than
  67  * 'width' than then the input string is not truncated and no
  68  * alignment is done.
  69  */
  70 void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int width,
  71                        const char *s);
  72
  73 /*
  74  * If a data stream is declared as UTF-16BE or UTF-16LE, then a UTF-16
  75  * BOM must not be used [1]. The same applies for the UTF-32 equivalents.
  76  * The function returns true if this rule is violated.
  77  *
  78  * [1] http://unicode.org/faq/utf_bom.html#bom10
  79  */
  80 int has_prohibited_utf_bom(const char *enc, const char *data, size_t len);
  81
  82 /*
  83  * If the endianness is not defined in the encoding name, then we
  84  * require a BOM. The function returns true if a required BOM is missing.
  85  *
  86  * The Unicode standard instructs to assume big-endian if there in no
  87  * BOM for UTF-16/32 [1][2]. However, the W3C/WHATWG encoding standard
  88  * used in HTML5 recommends to assume little-endian to "deal with
  89  * deployed content" [3].
  90  *
  91  * Therefore, strictly requiring a BOM seems to be the safest option for
  92  * content in Git.
  93  *
  94  * [1] http://unicode.org/faq/utf_bom.html#gen6
  95  * [2] http://www.unicode.org/versions/Unicode10.0.0/ch03.pdf
  96  *     Section 3.10, D98, page 132
  97  * [3] https://encoding.spec.whatwg.org/#utf-16le
  98  */
  99 int is_missing_required_utf_bom(const char *enc, const char *data, size_t len);
 100
 101 #endif