diff options
Diffstat (limited to 'include/ruby/internal/encoding/string.h')
| -rw-r--r-- | include/ruby/internal/encoding/string.h | 72 |
1 files changed, 55 insertions, 17 deletions
diff --git a/include/ruby/internal/encoding/string.h b/include/ruby/internal/encoding/string.h index 87226bec10..ea78cf23f3 100644 --- a/include/ruby/internal/encoding/string.h +++ b/include/ruby/internal/encoding/string.h @@ -25,11 +25,12 @@ #include "ruby/internal/value.h" #include "ruby/internal/encoding/encoding.h" #include "ruby/internal/attr/nonnull.h" +#include "ruby/internal/intern/string.h" /* rbimpl_strlen */ RBIMPL_SYMBOL_EXPORT_BEGIN() /** - * Identical to rb_enc_str_new(), except it additionally takes an encoding. + * Identical to rb_str_new(), except it additionally takes an encoding. * * @param[in] ptr A memory region of `len` bytes length. * @param[in] len Length of `ptr`, in bytes, not including the @@ -189,7 +190,7 @@ VALUE rb_enc_str_buf_cat(VALUE str, const char *ptr, long len, rb_encoding *enc) * In other languages, APIs like this one could be seen as the primitive * routines where encodings' "encode" feature are implemented. However in case * of Ruby this is not the primitive one. We directly manipulate encoded - * strings. Encoding conversion routines transocde an encoded string directly + * strings. Encoding conversion routines transcode an encoded string directly * to another one; not via a code point array. */ VALUE rb_enc_uint_chr(unsigned int code, rb_encoding *enc); @@ -263,6 +264,14 @@ VALUE rb_str_conv_enc(VALUE str, rb_encoding *from, rb_encoding *to); VALUE rb_str_conv_enc_opts(VALUE str, rb_encoding *from, rb_encoding *to, int ecflags, VALUE ecopts); /** + * @private + * + * This is an implementation detail of rb_enc_str_coderange(). Don't use this + * directly. + **/ +int rbimpl_enc_str_coderange_scan(VALUE str); + +/** * Scans the passed string to collect its code range. Because a Ruby's string * is mutable, its contents change from time to time; so does its code range. * A long-lived string tends to fall back to ::RUBY_ENC_CODERANGE_UNKNOWN. @@ -274,6 +283,27 @@ VALUE rb_str_conv_enc_opts(VALUE str, rb_encoding *from, rb_encoding *to, int ec int rb_enc_str_coderange(VALUE str); /** + * Scans the passed string to collect its code range. Because a Ruby's string + * is mutable, its contents change from time to time; so does its code range. + * A long-lived string tends to fall back to ::RUBY_ENC_CODERANGE_UNKNOWN. + * This API scans it and re-assigns a fine-grained code range constant. + * + * @param[out] str A string. + * @return An enum ::ruby_coderange_type. + */ +static inline int +rb_enc_str_coderange_inline(VALUE str) +{ + int cr = ENC_CODERANGE(str); + if (cr == ENC_CODERANGE_UNKNOWN) { + cr = rbimpl_enc_str_coderange_scan(str); + } + return cr; +} + +#define rb_enc_str_coderange rb_enc_str_coderange_inline + +/** * Scans the passed string until it finds something odd. Returns the number of * bytes scanned. As the name implies this is suitable for repeated call. One * of its application is `IO#readlines`. The method reads from its receiver's @@ -306,30 +336,38 @@ RBIMPL_ATTR_NONNULL(()) /** * Looks for the passed string in the passed buffer. * - * @param[in] x Buffer that potentially includes `y`. + * @param[in] x Query string. * @param[in] m Number of bytes of `x`. - * @param[in] y Query string. + * @param[in] y Buffer that potentially includes `x`. * @param[in] n Number of bytes of `y`. * @param[in] enc Encoding of both `x` and `y`. * @retval -1 Not found. - * @retval otherwise Found index in `x`. + * @retval otherwise Found index in `y`. * @note This API can match at a non-character-boundary. */ long rb_memsearch(const void *x, long m, const void *y, long n, rb_encoding *enc); /** @cond INTERNAL_MACRO */ -#ifdef HAVE_BUILTIN___BUILTIN_CONSTANT_P -#define rb_enc_str_new(str, len, enc) RB_GNUC_EXTENSION_BLOCK( \ - (__builtin_constant_p(str) && __builtin_constant_p(len)) ? \ - rb_enc_str_new_static((str), (len), (enc)) : \ - rb_enc_str_new((str), (len), (enc)) \ -) -#define rb_enc_str_new_cstr(str, enc) RB_GNUC_EXTENSION_BLOCK( \ - (__builtin_constant_p(str)) ? \ - rb_enc_str_new_static((str), (long)strlen(str), (enc)) : \ - rb_enc_str_new_cstr((str), (enc)) \ -) -#endif +RBIMPL_ATTR_NONNULL(()) +static inline VALUE +rbimpl_enc_str_new_cstr(const char *str, rb_encoding *enc) +{ + long len = rbimpl_strlen(str); + + return rb_enc_str_new_static(str, len, enc); +} + +#define rb_enc_str_new(str, len, enc) \ + ((RBIMPL_CONSTANT_P(str) && \ + RBIMPL_CONSTANT_P(len) ? \ + rb_enc_str_new_static: \ + rb_enc_str_new) ((str), (len), (enc))) + +#define rb_enc_str_new_cstr(str, enc) \ + ((RBIMPL_CONSTANT_P(str) ? \ + rbimpl_enc_str_new_cstr : \ + rb_enc_str_new_cstr) ((str), (enc))) + /** @endcond */ RBIMPL_SYMBOL_EXPORT_END() |