From 634502e7246f8850ad6c649b79ae9f072f45baf4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Hugo=20H=C3=B6rnquist?= <hugo@lysator.liu.se>
Date: Mon, 11 Sep 2023 17:54:35 +0200
Subject: Introduce stream-split-by.

This procedure isn't currently used, but as noted is really useful for
grouping a character stream into a word stream, which is a later commit
will use for it for justifying posibly infinite streams of text.
---
 doc/ref/guile/srfi-41.texi   | 20 ++++++++++++++++++++
 module/srfi/srfi-41/util.scm | 15 ++++++++++++++-
 tests/test/srfi-41-util.scm  | 20 ++++++++++++++++++++
 3 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/doc/ref/guile/srfi-41.texi b/doc/ref/guile/srfi-41.texi
index 310751ec..d8020ecc 100644
--- a/doc/ref/guile/srfi-41.texi
+++ b/doc/ref/guile/srfi-41.texi
@@ -73,6 +73,26 @@ times.
 stream cons, but eval arguments beforehand.
 @end defun
 
+@defun stream-split-by pred strm
+Chunks the content of @var{strm} into lists, breaking on @var{pred}.
+If the end of the stream is reached, the remaining objects
+are put into a final chunk.
+
+Can for example be used to split a stream of characters into a stream
+of words.
+
+@lisp
+(stream-split-by (lambda (c) (char=? c #\space))
+                 (-> "This is a short test"
+                     string->list list->stream))
+⇒ #<stream (#\T #\h #\i #\s #\space)
+           (#\i #\s #\space)
+           (#\a #\space)
+           (#\s #\h #\o #\r #\t #\space)
+           (#\t #\e #\s #\t)>
+@end lisp
+@end defun
+
 @defun stream-timeslice-limit stream timeslice
 Wrap a stream in time limits. Each element has at most @var{timeslice}
 seconds to produce a value, otherwise the stream ends. Useful for finding the
diff --git a/module/srfi/srfi-41/util.scm b/module/srfi/srfi-41/util.scm
index cecbb3b3..1571cc4c 100644
--- a/module/srfi/srfi-41/util.scm
+++ b/module/srfi/srfi-41/util.scm
@@ -18,7 +18,8 @@
            stream-partition
            stream-split
            stream-paginate
-           stream-timeslice-limit))
+           stream-timeslice-limit
+           stream-split-by))
 
 (define (stream-car+cdr stream)
   (values (stream-car stream)
@@ -146,3 +147,15 @@
           (stream-timeslice-limit (stream-cdr strm) timeslice)))
    (lambda _ stream-null)))
 
+
+(define-stream (stream-split-by pred strm)
+  (let loop ((accumulated '())
+             (strm strm))
+    (stream-match strm
+      (() (if (null? accumulated)
+              stream-null
+              (stream (reverse accumulated))))
+      ((x . xs) (pred x)
+       (stream-cons (reverse (cons x accumulated)) (loop '()  xs)))
+      ((x . xs)
+       (loop (cons x accumulated) xs)))))
diff --git a/tests/test/srfi-41-util.scm b/tests/test/srfi-41-util.scm
index ff0e3cce..9a753b03 100644
--- a/tests/test/srfi-41-util.scm
+++ b/tests/test/srfi-41-util.scm
@@ -8,6 +8,7 @@
   :use-module (srfi srfi-88)
   :use-module (srfi srfi-41 util)
   :use-module (srfi srfi-41)
+  :use-module ((srfi srfi-1) :select (circular-list))
   :use-module ((ice-9 sandbox) :select (call-with-time-limit)))
 
 (test-equal "Finite stream"
@@ -86,3 +87,22 @@
     (test-equal "time limited stream"
       '(1 2 3)
       (stream->list strm))))
+
+
+(test-group "stream-split-by"
+  (let ((hello-chars-stream (stream-unfold
+                             car
+                             (const #t)
+                             cdr
+                             (apply circular-list
+                                    (string->list "Hello ")))))
+    (test-equal "Check that test list looks as expected"
+      (string->list "Hello Hell")
+      (stream->list 10 hello-chars-stream))
+    (test-equal "Check that it splits correctly"
+      '("Hello " "Hello " "Hello ")
+      (stream->list
+       3
+       (stream-map list->string
+                   (stream-split-by (lambda (c) (char=? c #\space))
+                                    hello-chars-stream))))))
-- 
cgit v1.2.3