From 34d7df624c34f7b909da7db08dbcbf7d05de84af Mon Sep 17 00:00:00 2001
From: Kaz Kylheku <kaz@kylheku.com>
Date: Mon, 17 Nov 2014 07:13:18 -0800
Subject: * lib.c (split_str): If the separator string is empty, then unless
 opt_compat is 100 or less, provide a more consistent behavior, rather than
 splitting the string into characters. This latter behavior was never
 documented.

* txr.1: Documented.

* dep.mk: Updated.
---
 ChangeLog | 11 +++++++++++
 dep.mk    |  2 +-
 lib.c     | 25 ++++++++++++++++++++++++-
 txr.1     | 31 +++++++++++++++++++++++++++++++
 4 files changed, 67 insertions(+), 2 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 33590a1b..80681bd7 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,14 @@
+2014-11-17  Kaz Kylheku  <kaz@kylheku.com>
+
+	* lib.c (split_str): If the separator string is empty,
+	then unless opt_compat is 100 or less, provide a more
+	consistent behavior, rather than splitting the string
+	into characters. This latter behavior was never documented.
+
+	* txr.1: Documented.
+
+	* dep.mk: Updated.
+
 2014-11-15  Kaz Kylheku  <kaz@kylheku.com>
 
 	* lib.c (max2, min2): Use the less comparison function
diff --git a/dep.mk b/dep.mk
index bc7458e0..4fa08832 100644
--- a/dep.mk
+++ b/dep.mk
@@ -2,7 +2,7 @@
 ./lex.yy.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./gc.h $(top_srcdir)/./stream.h $(top_srcdir)/./utf8.h $(top_srcdir)/./signal.h $(top_srcdir)/./unwind.h $(top_srcdir)/./hash.h $(top_srcdir)/./parser.h $(top_srcdir)/./eval.h y.tab.h
 ./y.tab.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./signal.h $(top_srcdir)/./unwind.h $(top_srcdir)/./regex.h $(top_srcdir)/./utf8.h $(top_srcdir)/./match.h $(top_srcdir)/./hash.h $(top_srcdir)/./eval.h $(top_srcdir)/./stream.h $(top_srcdir)/./parser.h
 ./match.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./gc.h $(top_srcdir)/./signal.h $(top_srcdir)/./unwind.h $(top_srcdir)/./regex.h $(top_srcdir)/./stream.h $(top_srcdir)/./parser.h $(top_srcdir)/./txr.h $(top_srcdir)/./utf8.h $(top_srcdir)/./filter.h $(top_srcdir)/./hash.h $(top_srcdir)/./debug.h $(top_srcdir)/./eval.h $(top_srcdir)/./match.h
-./lib.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./gc.h $(top_srcdir)/./arith.h $(top_srcdir)/./rand.h $(top_srcdir)/./hash.h $(top_srcdir)/./signal.h $(top_srcdir)/./unwind.h $(top_srcdir)/./stream.h $(top_srcdir)/./utf8.h $(top_srcdir)/./filter.h $(top_srcdir)/./eval.h $(top_srcdir)/./sysif.h $(top_srcdir)/./regex.h
+./lib.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./gc.h $(top_srcdir)/./arith.h $(top_srcdir)/./rand.h $(top_srcdir)/./hash.h $(top_srcdir)/./signal.h $(top_srcdir)/./unwind.h $(top_srcdir)/./stream.h $(top_srcdir)/./utf8.h $(top_srcdir)/./filter.h $(top_srcdir)/./eval.h $(top_srcdir)/./sysif.h $(top_srcdir)/./regex.h $(top_srcdir)/./txr.h
 ./regex.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./parser.h $(top_srcdir)/./signal.h $(top_srcdir)/./unwind.h $(top_srcdir)/./stream.h $(top_srcdir)/./gc.h $(top_srcdir)/./regex.h $(top_srcdir)/./txr.h
 ./gc.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./stream.h $(top_srcdir)/./hash.h $(top_srcdir)/./txr.h $(top_srcdir)/./eval.h $(top_srcdir)/./gc.h $(top_srcdir)/./signal.h
 ./unwind.o: config.h $(top_srcdir)/./lib.h $(top_srcdir)/./gc.h $(top_srcdir)/./stream.h $(top_srcdir)/./txr.h $(top_srcdir)/./signal.h $(top_srcdir)/./eval.h $(top_srcdir)/./parser.h $(top_srcdir)/./unwind.h
diff --git a/lib.c b/lib.c
index 62d43b67..796a126c 100644
--- a/lib.c
+++ b/lib.c
@@ -57,6 +57,7 @@
 #include "eval.h"
 #include "sysif.h"
 #include "regex.h"
+#include "txr.h"
 
 #define max(a, b) ((a) > (b) ? (a) : (b))
 #define min(a, b) ((a) < (b) ? (a) : (b))
@@ -2778,7 +2779,29 @@ val split_str(val str, val sep)
     size_t len_sep = c_num(length_str(sep));
 
     if (len_sep == 0) {
-      return list_str(str);
+      if (opt_compat && opt_compat <= 100) {
+        return list_str(str);
+      } else {
+        const wchar_t *cstr = c_str(str);
+
+        if (*cstr) {
+          list_collect_decl (out, iter);
+
+          prot1(&str);
+
+          for (; *cstr; cstr++) {
+            val piece = mkustring(one);
+            init_str(piece, cstr);
+            iter = list_collect(iter, piece);
+          }
+
+          rel1(&str);
+
+          return out;
+        } else {
+          return cons(str, nil);
+        }
+      }
     } else {
       const wchar_t *cstr = c_str(str);
       const wchar_t *csep = c_str(sep);
diff --git a/txr.1 b/txr.1
index 409fe8a3..c4ae19d8 100644
--- a/txr.1
+++ b/txr.1
@@ -15874,6 +15874,15 @@ The string is broken into pieces
 according to the gaps left behind by the removed separators, and a list
 of the remaining pieces is returned.
 
+If
+.meta sep
+is the empty string, then the separator pieces removed from the
+string are considered to be the empty strings between its
+characters. In this case, if
+.meta string
+is of length one or zero, then it is considered to have no such pieces, and a
+list of one element is returned containing the original string.
+
 If a match for
 .meta sep
 is not found in the string at all, then the string is not
@@ -15895,6 +15904,17 @@ This operation is nondestructive:
 .meta string
 is not modified in any way.
 
+Note: To split a string into pieces of length one such that an empty string
+produces
+.code nil
+rather than
+.codn ("") ,
+use the
+.cblk
+.meti (tok-str < string #/./)
+.cble
+pattern.
+
 .coNP Function @ split-str-set
 .synb
 .mets (split-str-set < string << set )
@@ -26036,6 +26056,17 @@ can be emulated is \*(TX 97.
 Here are values which have a special meaning as arguments to the
 .code -C
 option, along with a description of what behaviors are affected:
+.IP 100
+Up to \*(TX 100, the
+.code split-str
+function had an undocumented behavior. When the
+.code sep
+argument was an empty string, it split the string into
+individual characters as if by calling
+.codn list-str .
+This behavior changed to the currently
+documented behavior starting in \*(TX 101.
+
 .IP 99
 Up to \*(TX 99, the substitution of TXR Lisp expressions in
 .code @(output)
-- 
cgit v1.2.3