Refactor splits/2 using foreach syntax (remove private filter _nwise) (#3260)

This commit refactors `splits/2` implementation using `foreach` syntax
and reduces intermediate arrays. This refactoring removes an unnecessary
private (and undocumented) filter `_nwise` and closes #3148.

docs/content/manual/dev/manual.yml

@@ -2736,6 +2736,9 @@ sections:
           - program: 'splits(", *")'
             input: '"ab,cd,   ef, gh"'
             output: ['"ab"','"cd"','"ef"','"gh"']
+          - program: 'splits(",? *"; "n")'
+            input: '"ab,cd ef,  gh"'
+            output: ['"ab"','"cd"','"ef"','"gh"']
 
       - title: "`sub(regex; tostring)`, `sub(regex; tostring; flags)`"
         body: |

jq.1.prebuilt

@@ -3032,6 +3032,10 @@ These provide the same results as their \fBsplit\fR counterparts, but as a strea
 jq \'splits(", *")\'
    "ab,cd,   ef, gh"
 => "ab", "cd", "ef", "gh"
+
+jq \'splits(",? *"; "n")\'
+   "ab,cd ef,  gh"
+=> "ab", "cd", "ef", "gh"
 .
 .fi
 .

src/builtin.jq

@@ -98,26 +98,16 @@ def scan($re; $flags):
       else .string
       end;
 def scan($re): scan($re; null);
-#
+
-# If input is an array, then emit a stream of successive subarrays of length n (or less),
-# and similarly for strings.
-def _nwise($n):
-  def n: if length <= $n then . else .[0:$n] , (.[$n:] | n) end;
-  n;
-def _nwise(a; $n): a | _nwise($n);
-#
 # splits/1 produces a stream; split/1 is retained for backward compatibility.
-def splits($re; flags): . as $s
+def splits($re; $flags):
-#  # multiple occurrences of "g" are acceptable
+  .[foreach (match($re; $flags+"g"), null) as {$offset, $length}
-  | [ match($re; "g" + flags) | (.offset, .offset + .length) ]
+      (null; {start: .next, end: $offset, next: ($offset+$length)})];
-  | [0] + . +[$s|length]
-  | _nwise(2)
-  | $s[.[0]:.[1] ] ;
 def splits($re): splits($re; null);
-#
+
 # split emits an array for backward compatibility
-def split($re; flags): [ splits($re; flags) ];
+def split($re; $flags): [ splits($re; $flags) ];
-#
+
 # If s contains capture variables, then create a capture object and pipe it to s, bearing
 # in mind that s could be a stream
 def sub($re; s; $flags):
@@ -132,12 +122,12 @@ def sub($re; s; $flags):
             | .previous = ($edit | .offset + .length ) )
           | .result[] + $in[.previous:] )
       // $in;
-#
+
 def sub($re; s): sub($re; s; "");
-#
+
 def gsub($re; s; flags): sub($re; s; flags + "g");
 def gsub($re; s): sub($re; s; "g");
-#
+
 ########################################################################
 # generic iterator/generator
 def while(cond; update):

tests/manonig.test

@@ -64,6 +64,13 @@ splits(", *")
 "ef"
 "gh"
 
+splits(",? *"; "n")
+"ab,cd ef,  gh"
+"ab"
+"cd"
+"ef"
+"gh"
+
 sub("[^a-z]*(?<x>[a-z]+)"; "Z\(.x)"; "g")
 "123abc456def"
 "ZabcZdef"

tests/onig.test

@@ -192,8 +192,20 @@ sub("(?<x>.)"; "\(.x)!")
 "aB"
 ["AB","ab","cc"]
 
-# splits and _nwise
+# splits
 [splits("")]
 "ab"
 ["","a","b",""]
 
+[splits("c")]
+"ab"
+["ab"]
+
+[splits("a+"; "i")]
+"abAABBabA"
+["","b","BB","b",""]
+
+[splits("b+"; "i")]
+"abAABBabA"
+["a","AA","a","A"]
+