From e0dbcc3a6455d990c0a0ecde74e279e8f3b53843 Mon Sep 17 00:00:00 2001
From: Kaz Kylheku <kaz@kylheku.com>
Date: Wed, 26 Oct 2016 20:19:42 -0700
Subject: Fix tok-str semantics once again.

The problem is that when the regular expression
is capable of matching empty strings, tok-str
will extract an empty token immediately following
a non-empty token. For instance (tok-str "a,b" /[^,]*/)
extracts ("a" "" "b") instead of just ("a" "b").
This is a poor behavior and the way to fix it is to
impose a rule that an empty token must not be extracted
immediately at the ending position of a previous token.
Only a non-empty token can be consecutive to a token.

* lib.c (tok_str): Rewrite the logic of the loop,
using the prev_empty flag to suppress empty tokens
which immediately follow non-empty tokens. The
addition of 1 to the position when the token is empty
to skip a character is done at the bottom of the loop
and a new last_end variable keeps track of the end position
of the last extracted token for the purposes of extracting
the keep-between area if keep_sep is true. The old loop
is preserved intact and enabled by compatibility.

* tests/015/split.tl: Multiple empty-regex test cases for
tok-str updated.

* txr.1: Updated tok-str documentation and also added
a note between the conditions under which split-str and
tok-str, invoked with keep-sep true, produce equivalent
output. Added compatibility notes.
---
 tests/015/split.tl | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'tests/015')

diff --git a/tests/015/split.tl b/tests/015/split.tl
index 30a8e01c..ae77a642 100644
--- a/tests/015/split.tl
+++ b/tests/015/split.tl
@@ -123,34 +123,34 @@
   (split-str "abcacabcac" #/ab?/ t) ("" "ab" "c" "a" "c" "ab" "c" "a" "c"))
 
 (mtest
-  (tok-str "" #//) nil
-  (tok-str "a" #//) nil
+  (tok-str "" #//) ("")
+  (tok-str "a" #//) ("" "")
   (tok-str "" #/a/) nil
   (tok-str "a" #/a/) ("a"))
 
 (mtest
-  (tok-str "" #// t) ("")
-  (tok-str "a" #// t) ("a")
+  (tok-str "" #// t) ("" "" "")
+  (tok-str "a" #// t) ("" "" "a" "" "")
   (tok-str "" #/a/ t) ("")
   (tok-str "a" #/a/ t) ("" "a" ""))
 
 (mtest
-  (tok-str "ab" #//) ("")
+  (tok-str "ab" #//) ("" "" "")
   (tok-str "ab" #/a/) ("a")
   (tok-str "ab" #/b/) ("b")
   (tok-str "ab" #/ab/) ("ab")
   (tok-str "ab" #/abc/) nil)
 
 (mtest
-  (tok-str "ab" #// t) ("a" "" "b")
+  (tok-str "ab" #// t) ("" "" "a" "" "b" "" "")
   (tok-str "ab" #/a/ t) ("" "a" "b")
   (tok-str "ab" #/b/ t) ("a" "b" "")
   (tok-str "ab" #/ab/ t) ("" "ab" "")
   (tok-str "ab" #/abc/ t) ("ab"))
 
 (mtest
-  (tok-str "abc" #//) ("" "")
-  (tok-str "abc" #// t) ("a" "" "b" "" "c"))
+  (tok-str "abc" #//) ("" "" "" "")
+  (tok-str "abc" #// t) ("" "" "a" "" "b" "" "c" "" ""))
 
 (mtest
   (tok-str "abc" #/a/) ("a")
-- 
cgit v1.2.3