Provide non-locale C/Scheme string conversion functions

* doc/ref/api-data.texi: document scm_to_stringn, scm_from_stringn,
  scm_to_latin1_stringn, and scm_from_latin1_stringn
* libguile/strings.h (scm_to_stringn): make public
  (scm_to_latin1_stringn): new declaration
  (scm_from_latin1_stringn): new declaration
* libguile/strings.c (scm_to_latin1_stringn): new function
  (scm_from_latin1_stringn): new function

diff --git a/doc/ref/api-data.texi b/doc/ref/api-data.texi
index 75e5e68..82982e9 100755 (executable)
--- a/doc/ref/api-data.texi
+++ b/doc/ref/api-data.texi
@@ -3969,6 +3969,74 @@ is larger than @var{max_len}, only @var{max_len} bytes have been
 stored and you probably need to try again with a larger buffer.
 @end deftypefn
 
+For most situations, string conversion should occur using the current
+locale, such as with the functions above.  But there may be cases where
+one wants to convert strings from a character encoding other than the
+locale's character encoding.  For these cases, the lower-level functions
+@code{scm_to_stringn} and @code{scm_from_stringn} are provided.  These
+functions should seldom be necessary if one is properly using locales.
+
+@deftp {C Type} scm_t_string_failed_conversion_handler
+This is an enumerated type that can take one of three values:
+@code{SCM_FAILED_CONVERSION_ERROR},
+@code{SCM_FAILED_CONVERSION_QUESTION_MARK}, and
+@code{SCM_FAILED_CONVERSION_ESCAPE_SEQUENCE}.  They are used to indicate
+a strategy for handling characters that cannot be converted to or from a
+given character encoding.  @code{SCM_FAILED_CONVERSION_ERROR} indicates
+that a conversion should throw an error if some characters cannot be
+converted.  @code{SCM_FAILED_CONVERSION_QUESTION_MARK} indicates that a
+conversion should replace unconvertable characters with the question
+mark character.  And, @code{SCM_FAILED_CONVERSION_ESCAPE_SEQUENCE}
+requests that a conversion should replace an unconvertable character
+with an escape sequence.
+
+While all three strategies apply when converting Scheme strings to C,
+only @code{SCM_FAILED_CONVERSION_ERROR} and
+@code{SCM_FAILED_CONVERSION_QUESTION_MARK} can be used when converting C
+strings to Scheme.
+@end deftp
+
+@deftypefn {C Function} char *scm_to_stringn (SCM str, size_t *lenp, const char *encoding, scm_t_string_failed_conversion_handler handler)
+This function returns a newly allocated C string from the Guile string
+@var{str}.  The length of the string will be returned in @var{lenp}.
+The character encoding of the C string is passed as the ASCII,
+null-terminated C string @var{encoding}.  The @var{handler} parameter
+gives a strategy for dealing with characters that cannot be converted
+into @var{encoding}.
+
+If @var{lenp} is NULL, this function will return a null-terminated C
+string.  It will throw an error if the string contains a null
+character.
+@end deftypefn
+
+@deftypefn {C Function} SCM scm_from_stringn (const char *str, size_t len, const char *encoding, scm_t_string_failed_conversion_handler handler)
+This function returns a scheme string from the C string @var{str}.  The
+length of the C string is input as @var{len}.  The encoding of the C
+string is passed as the ASCII, null-terminated C string @code{encoding}.
+The @var{handler} parameters suggests a strategy for dealing with
+unconvertable characters.
+@end deftypefn
+
+ISO-8859-1 is the most common 8-bit character encoding.  This encoding
+is also referred to as the Latin-1 encoding.  The following two
+conversion functions are provided to convert between Latin-1 C strings
+and Guile strings.
+
+@deftypefn {C Function} SCM scm_from_latin1_stringn (const char *str, size_t len)
+This function returns a scheme string from an ISO-8859-1-encoded C
+string @var{str} of length @var{len}.
+@end deftypefn
+
+@deftypefn {C function} char * scm_to_latin1_stringn (SCM str, size_t *lenp)
+This function returns a newly allocated, ISO-8859-1-encoded C string
+from the scheme string @var{str}.  An error will be thrown if the scheme
+string cannot be converted to the ISO-8859-1 encoding.  If @var{lenp} is
+@code{NULL}, the returned C string will be null terminated, and an error
+will be thrown if the C string would otherwise contain null
+characters. If @var{lenp} is not NULL, the length of the string is
+returned in @var{lenp}, and the string is not null terminated.
+@end deftypefn
+
 @node String Internals
 @subsubsection String Internals
 

diff --git a/libguile/strings.c b/libguile/strings.c
index 52dfb53..68fa25c 100644 (file)
--- a/libguile/strings.c
+++ b/libguile/strings.c
@@ -1501,6 +1501,12 @@ scm_from_stringn (const char *str, size_t len, const char *encoding,
   return res;
 }
 
+SCM
+scm_from_latin1_stringn (const char *str, size_t len)
+{
+  return scm_from_stringn (str, len, NULL, SCM_FAILED_CONVERSION_ERROR);
+}
+
 SCM
 scm_from_locale_stringn (const char *str, size_t len)
 {
@@ -1697,6 +1703,11 @@ unistring_escapes_to_r6rs_escapes (char **bufp, size_t *lenp)
   memcpy (before, after, j);
 }
 
+char *
+scm_to_latin1_stringn (SCM str, size_t *lenp)
+{
+  return scm_to_stringn (str, lenp, NULL, SCM_FAILED_CONVERSION_ERROR);
+}
 
 char *
 scm_to_locale_stringn (SCM str, size_t *lenp)

diff --git a/libguile/strings.h b/libguile/strings.h
index 734ac62..4b120e0 100644 (file)
--- a/libguile/strings.h
+++ b/libguile/strings.h
@@ -113,10 +113,8 @@ SCM_API SCM scm_substring_shared (SCM str, SCM start, SCM end);
 SCM_API SCM scm_substring_copy (SCM str, SCM start, SCM end);
 SCM_API SCM scm_string_append (SCM args);
 
-SCM_API SCM scm_from_stringn (const char *str, size_t len, 
-                                     const char *encoding,
-                                     scm_t_string_failed_conversion_handler 
-                                     handler);
+SCM_API SCM scm_from_stringn (const char *str, size_t len, const char *encoding,
+                              scm_t_string_failed_conversion_handler handler);
 SCM_API SCM scm_c_make_string (size_t len, SCM chr);
 SCM_API size_t scm_c_string_length (SCM str);
 SCM_API size_t scm_c_symbol_length (SCM sym);
@@ -128,17 +126,17 @@ SCM_API SCM scm_c_substring_shared (SCM str, size_t start, size_t end);
 SCM_API SCM scm_c_substring_copy (SCM str, size_t start, size_t end);
 
 SCM_API int scm_is_string (SCM x);
+SCM_API SCM scm_from_latin1_stringn (const char *str, size_t len);
 SCM_API SCM scm_from_locale_string (const char *str);
 SCM_API SCM scm_from_locale_stringn (const char *str, size_t len);
 SCM_INTERNAL SCM scm_i_from_utf8_string (const scm_t_uint8 *str);
 SCM_API SCM scm_take_locale_string (char *str);
 SCM_API SCM scm_take_locale_stringn (char *str, size_t len);
+SCM_API char *scm_to_latin1_stringn (SCM str, size_t *lenp);
 SCM_API char *scm_to_locale_string (SCM str);
 SCM_API char *scm_to_locale_stringn (SCM str, size_t *lenp);
-SCM_INTERNAL char *scm_to_stringn (SCM str, size_t *lenp, 
-                                   const char *encoding,
-                                   scm_t_string_failed_conversion_handler
-                                   handler);
+SCM_API char *scm_to_stringn (SCM str, size_t *lenp, const char *encoding,
+                              scm_t_string_failed_conversion_handler handler);
 SCM_INTERNAL scm_t_uint8 *scm_i_to_utf8_string (SCM str);
 SCM_API size_t scm_to_locale_stringbuf (SCM str, char *buf, size_t max_len);
 
@@ -215,6 +213,8 @@ SCM_API SCM scm_sys_symbol_dump (SCM);
 SCM_API SCM scm_sys_stringbuf_hist (void);
 #endif
 
+
+
 /* deprecated stuff */
 
 #if SCM_ENABLE_DEPRECATED