[PATCH] Enable utf8->string to take a range

[Vijay Marupudi]

Hello,

Attached is a patch that allows `utf8->string' to take
additional parameters indicating the start and end indicies of the
bytevector that it is converting.

This preserves backwards compatibility by adding the new functionality
to an `scm_utf8_to_string_range' function (open to any alternative name
suggestions) and letting the old `scm_utf8_to_string' function call it.

For my work, I am currently handling bytevectors with large strings
embedded as part of the bytevector. This patch would reduce the need for
spurious allocations and copying to convert part of a bytevector to a
string using pure Scheme. It would also make R7RS compatibility easier,
since the current compatibility module involves copies to a fresh
bytevector.

For example, from module/scheme/base.scm

> (define (%subbytevector bv start end)
>   (define mlen (- end start))
>   (define out (make-bytevector mlen))
>   (bytevector-copy! bv start out 0 mlen)
>   out)
>
> (define (%subbytevector1 bv start)
>   (%subbytevector bv start (bytevector-length bv)))
>
> (define r7:utf8->string
>   (case-lambda*
>     ((bv) (utf8->string bv))
>     ((bv start #:optional (end (bytevector-length bv)))
>      (utf8->string (%subbytevector bv start end)))))


Would appreciate any thoughts and feedback.

~ Vijay

>From 695c2a6189458a292819df8fba659ea488dc0b4e Mon Sep 17 00:00:00 2001
From: Vijay Marupudi <vijay@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.
---
 doc/ref/api-data.texi  |  3 ++-
 libguile/bytevectors.c | 48 +++++++++++++++++++++++++++++++++++-------
 libguile/bytevectors.h |  1 +
 3 files changed, 43 insertions(+), 9 deletions(-)

diff --git a/doc/ref/api-data.texi b/doc/ref/api-data.texi
index b6c2c4d61..1bdd1f7ed 100644
--- a/doc/ref/api-data.texi
+++ b/doc/ref/api-data.texi
@@ -7139,10 +7139,11 @@ 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-,
diff --git a/libguile/bytevectors.c b/libguile/bytevectors.c
index f42fbb427..44a062257 100644
--- a/libguile/bytevectors.c
+++ b/libguile/bytevectors.c
@@ -2094,27 +2094,59 @@ SCM_DEFINE (scm_string_to_utf32, "string->utf32",
   return (str);
 
 
-SCM_DEFINE (scm_utf8_to_string, "utf8->string",
-           1, 0, 0,
-           (SCM utf),
+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
+#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 = 0;
+  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);
+  c_end = c_len;
+
+  if (!scm_is_eq (start, SCM_UNDEFINED))
+    {
+      c_start = scm_to_size_t (start);
+      if (SCM_UNLIKELY (c_start >= c_len))
+        {
+          scm_out_of_range (FUNC_NAME, start);
+        }
+
+      if (!scm_is_eq (end, SCM_UNDEFINED))
+       {
+         c_end = scm_to_size_t (end);
+         if (SCM_UNLIKELY (c_end > c_len))
+           scm_out_of_range (FUNC_NAME, end);
+       }
+    }
+
+  if (SCM_UNLIKELY(c_end < c_start)) {
+    scm_out_of_range (FUNC_NAME, 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);
 
-- 
2.34.1