> There seems to be an inconsistency here. Can (c_start >= c_len) be
> relaxed to c_start > c_len?
Done. `substring' was a useful reference.
> It would be nice to document if it's an open, closed or half-
> open/closed range. E.g. see the documentation of 'substring':
Done.
> It seems a bit weird to support [start] and [end] for utf8->string but
> not for utf16->string and utf32->string.
I will gladly implement those too. I wanted feedback on the code before
I implemented all of them, which you provided, thank you. I still want
thoughts on the name of the new C function. If that is okay, then I can
implement the rest following the same name pattern.
>> + c_start = scm_to_size_t (start);
>
> This seems suboptimal because if start > SIZE_MAX,
> then this will throw an 'out-of-range' exception without attributing
> it to 'utf8->string' (untested).
Switched to scm_to_unsigned_integer, that does bounds checks. This is
what `substring' does.
The updated patch is attached.
~ Vijay
>From 61b4b444eec1a8825d54604cbcb5a68bcfa9cef5 Mon Sep 17 00:00:00 2001
From: Vijay Marupudi <vi...@vijaymarupudi.com>
Date: Thu, 20 Jan 2022 22:19:25 -0500
Subject: [PATCH] Enable utf8->string to take a range
Additionally, adds a scm_utf8_to_string_range function for access from
C. Behaves like substring.
* doc/ref/api-data.texi: Updated documentation to reflect new function
and range constraints
* libguile/bytevectors.c: Added new function.
* libguile/bytevectors.h: Added new function declaration.
* test-suite/tests/bytevectors.test: Added tests for exceptions and
behavior for edge cases
---
doc/ref/api-data.texi | 8 +++-
libguile/bytevectors.c | 66 ++++++++++++++++++++++++++-----
libguile/bytevectors.h | 1 +
test-suite/tests/bytevectors.test | 27 +++++++++++++
4 files changed, 91 insertions(+), 11 deletions(-)
diff --git a/doc/ref/api-data.texi b/doc/ref/api-data.texi
index b6c2c4d61..0206435d3 100644
--- a/doc/ref/api-data.texi
+++ b/doc/ref/api-data.texi
@@ -7139,16 +7139,22 @@ UTF-32 (aka. UCS-4) encoding of @var{str}. For UTF-16 and UTF-32,
it defaults to big endian.
@end deffn
-@deffn {Scheme Procedure} utf8->string utf
+@deffn {Scheme Procedure} utf8->string utf [start [end]]
@deffnx {Scheme Procedure} utf16->string utf [endianness]
@deffnx {Scheme Procedure} utf32->string utf [endianness]
@deffnx {C Function} scm_utf8_to_string (utf)
+@deffnx {C Function} scm_utf8_to_string_range (utf, start, end)
@deffnx {C Function} scm_utf16_to_string (utf, endianness)
@deffnx {C Function} scm_utf32_to_string (utf, endianness)
Return a newly allocated string that contains from the UTF-8-, UTF-16-,
or UTF-32-decoded contents of bytevector @var{utf}. For UTF-16 and UTF-32,
@var{endianness} should be the symbol @code{big} or @code{little}; when omitted,
it defaults to big endian.
+
+@var{start} and @var{end}, when provided, must be exact integers
+satisfying:
+
+0 <= @var{start} <= @var{end} <= @code{(bytevector-length @var{utf})}.
@end deffn
@node Bytevectors as Arrays
diff --git a/libguile/bytevectors.c b/libguile/bytevectors.c
index f42fbb427..3e128e667 100644
--- a/libguile/bytevectors.c
+++ b/libguile/bytevectors.c
@@ -2094,27 +2094,73 @@ SCM_DEFINE (scm_string_to_utf32, "string->utf32",
return (str);
-SCM_DEFINE (scm_utf8_to_string, "utf8->string",
- 1, 0, 0,
- (SCM utf),
- "Return a newly allocate string that contains from the UTF-8-"
- "encoded contents of bytevector @var{utf}.")
-#define FUNC_NAME s_scm_utf8_to_string
+static inline void
+validate_bytevector_range(const char* function_name, size_t len, size_t start, size_t end) {
+ if (SCM_UNLIKELY (start > len))
+ {
+ scm_out_of_range (function_name, scm_from_size_t(start));
+ }
+ if (SCM_UNLIKELY (end > len))
+ {
+ scm_out_of_range (function_name, scm_from_size_t(end));
+ }
+ if (SCM_UNLIKELY(end < start))
+ {
+ scm_out_of_range (function_name, scm_from_size_t(end));
+ }
+}
+
+
+SCM_DEFINE (scm_utf8_to_string_range, "utf8->string",
+ 1, 2, 0,
+ (SCM utf, SCM start, SCM end),
+ "Return a newly allocate string that contains from the UTF-8-"
+ "encoded contents of bytevector @var{utf}.")
+#define FUNC_NAME s_scm_utf8_to_string_range
{
SCM str;
const char *c_utf;
- size_t c_utf_len = 0;
+ size_t c_start;
+ size_t c_end;
+ size_t c_len;
SCM_VALIDATE_BYTEVECTOR (1, utf);
-
- c_utf_len = SCM_BYTEVECTOR_LENGTH (utf);
c_utf = (char *) SCM_BYTEVECTOR_CONTENTS (utf);
- str = scm_from_utf8_stringn (c_utf, c_utf_len);
+ c_len = SCM_BYTEVECTOR_LENGTH(utf);
+ if (!scm_is_eq (start, SCM_UNDEFINED))
+ {
+ c_start = scm_to_unsigned_integer (start, 0, c_len);
+ }
+ else
+ {
+ c_start = 0;
+ }
+
+ if (!scm_is_eq (end, SCM_UNDEFINED))
+ {
+ c_end = scm_to_unsigned_integer (end, 0, c_len);
+ }
+ else
+ {
+ c_end = c_len;
+ }
+
+ validate_bytevector_range(FUNC_NAME, c_len, c_start, c_end);
+ str = scm_from_utf8_stringn (c_utf + c_start, c_end - c_start);
return (str);
}
#undef FUNC_NAME
+SCM
+scm_utf8_to_string(SCM utf)
+#define FUNC_NAME s_scm_utf8_to_string
+{
+ return scm_utf8_to_string_range(utf, SCM_UNDEFINED, SCM_UNDEFINED);
+}
+#undef FUNC_NAME
+
+
SCM_DEFINE (scm_utf16_to_string, "utf16->string",
1, 1, 0,
(SCM utf, SCM endianness),
diff --git a/libguile/bytevectors.h b/libguile/bytevectors.h
index 980d6e267..82a66ee5e 100644
--- a/libguile/bytevectors.h
+++ b/libguile/bytevectors.h
@@ -113,6 +113,7 @@ SCM_API SCM scm_string_to_utf8 (SCM);
SCM_API SCM scm_string_to_utf16 (SCM, SCM);
SCM_API SCM scm_string_to_utf32 (SCM, SCM);
SCM_API SCM scm_utf8_to_string (SCM);
+SCM_API SCM scm_utf8_to_string_range (SCM, SCM, SCM);
SCM_API SCM scm_utf16_to_string (SCM, SCM);
SCM_API SCM scm_utf32_to_string (SCM, SCM);
diff --git a/test-suite/tests/bytevectors.test b/test-suite/tests/bytevectors.test
index 732aadb3e..08719703a 100644
--- a/test-suite/tests/bytevectors.test
+++ b/test-suite/tests/bytevectors.test
@@ -558,6 +558,33 @@
exception:decoding-error
(utf8->string #vu8(104 105 239 191 50)))
+ (pass-if "utf8->string range: start provided"
+ (let* ((utf8 (string->utf8 "gnu guile"))
+ (str (utf8->string utf8 4)))
+ (string=? str "guile")))
+
+ (pass-if "utf8->string range: start and end provided"
+ (let* ((utf8 (string->utf8 "gnu guile"))
+ (str (utf8->string utf8 4 7)))
+ (string=? str "gui")))
+
+ (pass-if "utf8->string range: start = end = 0"
+ (let* ((utf8 (string->utf8 "gnu guile"))
+ (str (utf8->string utf8 0 0)))
+ (string=? str "")))
+
+ (pass-if-exception "utf8->string range: start > len"
+ exception:out-of-range
+ (let* ((utf8 (string->utf8 "four")))
+ ;; 4 as start is expected to return an empty string, in congruence
+ ;; with `substring'.
+ (utf8->string utf8 5)))
+
+ (pass-if-exception "utf8->string range: end < start"
+ exception:out-of-range
+ (let* ((utf8 (string->utf8 "gnu guile")))
+ (utf8->string utf8 1 0)))
+
(pass-if "utf16->string"
(let* ((utf16 (uint-list->bytevector (map char->integer
(string->list "hello, world"))
--
2.34.1
