Patch from Darin Adler to restore Glib-1.2 handling of empty strings, and

Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>

        * glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
        Adler to restore Glib-1.2 handling of empty strings,
        and to fix off-by-one with @max_tokens. (#57663).
        Doc improvements.

        * tests/strfunc-test.c: Change tests to correspond to
        new behavior of g_strsplit().

ChangeLog

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-0

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-10

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-12

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-2

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-4

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-6

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

ChangeLog.pre-2-8

@@ -1,3 +1,13 @@
+Fri Aug 24 11:15:46 2001  Owen Taylor  <otaylor@redhat.com>
+
+	* glib/gstrfuncs.c docs/Changes-2.0.txt: Patch from Darin
+	Adler to restore Glib-1.2 handling of empty strings,
+	and to fix off-by-one with @max_tokens. (#57663).
+	Doc improvements.
+
+	* tests/strfunc-test.c: Change tests to correspond to
+	new behavior of g_strsplit().
+
 Thu Aug 23 11:09:58 2001  Owen Taylor  <otaylor@redhat.com>
 
 	* glib/ghash.c (g_hash_table_foreach_remove_or_steal): 

docs/Changes-2.0.txt

@@ -32,3 +32,11 @@
 * GDate now works in UTF-8, not in the current locale. If you
   want to use it with the encoding of the locale, you need
   to convert strings using g_locale_to_utf8 first.
+
+* g_strsplit() has been fixed to:
+
+  - include trailing empty tokens, rather than stripping them
+  - split into a maximum of @max_tokens tokens, rather than 
+    @max_tokens + 1
+
+  Code depending on either of these bugs will need to be fixed.

docs/reference/glib/tmpl/string_utils.sgml

@@ -358,20 +358,12 @@ nesting such as g_strup (g_strcanon (str)).
 
 <!-- ##### FUNCTION g_strsplit ##### -->
 <para>
-Splits a string into a maximum of @max_tokens pieces, using the given
-@delimiter. If @max_tokens is reached, the last piece contains the
-remainder of @string. If @string is an empty string, then the resulting
-string array has no elements.
 </para>
 
-@string: a string to split.
+@string: 
-@delimiter: a string which specifies the places at which to split the string.
+@delimiter: 
-The delimiter is not included in any of the resulting strings, unless
+@max_tokens: 
-max_tokens is reached.
+@Returns: 
-@max_tokens: the maximum number of pieces to split @string into. If this is
-less than 1, the string is split completely.
-@Returns: a newly-allocated NULL-terminated array of strings. Use g_strfreev()
-to free it.
 
 
 <!-- ##### FUNCTION g_strfreev ##### -->

glib/gstrfuncs.c

@@ -1566,6 +1566,29 @@ g_strchomp (gchar *string)
   return string;
 }
 
+/**
+ * g_strsplit:
+ * @string: a string to split.
+ * @delimiter: a string which specifies the places at which to split the string.
+ *     The delimiter is not included in any of the resulting strings, unless
+ *     max_tokens is reached.
+ * @max_tokens: the maximum number of pieces to split @string into. If this is
+ *              less than 1, the string is split completely.
+ * 
+ * Splits a string into a maximum of @max_tokens pieces, using the given
+ * @delimiter. If @max_tokens is reached, the remainder of @string is appended
+ * to the last token. 
+ *
+ * As a special case, the result of splitting the empty string "" is an empty
+ * vector, not a vector containing a single string. The reason for this
+ * special case is that being able to represent a empty vector is typically
+ * more useful than consistent handling of empty elements. If you do need
+ * to represent empty elements, you'll need to check for the empty string
+ * before calling g_strsplit().
+ * 
+ * Return value: a newly-allocated %NULL-terminated array of strings. Use g_strfreev()
+ *    to free it.
+ **/
 gchar**
 g_strsplit (const gchar *string,
 	    const gchar *delimiter,
@@ -1573,7 +1596,8 @@ g_strsplit (const gchar *string,
 {
   GSList *string_list = NULL, *slist;
   gchar **str_array, *s;
-  guint n = 1;
+  guint n = 0;
+  const gchar *remainder;
 
   g_return_val_if_fail (string != NULL, NULL);
   g_return_val_if_fail (delimiter != NULL, NULL);
@@ -1581,8 +1605,11 @@ g_strsplit (const gchar *string,
 
   if (max_tokens < 1)
     max_tokens = G_MAXINT;
+  else
+    --max_tokens;
 
-  s = strstr (string, delimiter);
+  remainder = string;
+  s = strstr (remainder, delimiter);
   if (s)
     {
       gsize delimiter_len = strlen (delimiter);   
@@ -1592,18 +1619,22 @@ g_strsplit (const gchar *string,
 	  gsize len;     
 	  gchar *new_string;
 
-	  len = s - string;
+	  len = s - remainder;
 	  new_string = g_new (gchar, len + 1);
-	  strncpy (new_string, string, len);
+	  strncpy (new_string, remainder, len);
 	  new_string[len] = 0;
 	  string_list = g_slist_prepend (string_list, new_string);
 	  n++;
-	  string = s + delimiter_len;
+	  remainder = s + delimiter_len;
-	  s = strstr (string, delimiter);
+	  s = strstr (remainder, delimiter);
 	}
       while (--max_tokens && s);
     }
-  string_list = g_slist_prepend (string_list, g_strdup (string));
+  if (*string)
+    {
+      n++;
+      string_list = g_slist_prepend (string_list, g_strdup (remainder));
+    }
 
   str_array = g_new (gchar*, n + 1);
 

tests/strfunc-test.c

@@ -145,7 +145,7 @@ main (int   argc,
   TEST (NULL, strcmp (g_strrstr_len ("FooBarFooBarFoo", 14, "BarFoo"),
 		      "BarFooBarFoo") == 0);
 
-  TEST (NULL, strv_check (g_strsplit ("", ",", 0), "", NULL));
+  TEST (NULL, strv_check (g_strsplit ("", ",", 0), NULL));
   TEST (NULL, strv_check (g_strsplit ("x", ",", 0), "x", NULL));
   TEST (NULL, strv_check (g_strsplit ("x,y", ",", 0), "x", "y", NULL));
   TEST (NULL, strv_check (g_strsplit ("x,y,", ",", 0), "x", "y", "", NULL));
@@ -158,18 +158,18 @@ main (int   argc,
   TEST (NULL, strv_check (g_strsplit (",,x,,y,,z,,", ",", 0), "", "", "x", "", "y", "", "z", "", "", NULL));
   TEST (NULL, strv_check (g_strsplit (",,x,,y,,z,,", ",,", 0), "", "x", "y", "z", "", NULL));
 
-  TEST (NULL, strv_check (g_strsplit ("", ",", 2), "", NULL));
+  TEST (NULL, strv_check (g_strsplit ("", ",", 2), NULL));
   TEST (NULL, strv_check (g_strsplit ("x", ",", 2), "x", NULL));
   TEST (NULL, strv_check (g_strsplit ("x,y", ",", 2), "x", "y", NULL));
-  TEST (NULL, strv_check (g_strsplit ("x,y,", ",", 2), "x", "y", "", NULL));
+  TEST (NULL, strv_check (g_strsplit ("x,y,", ",", 2), "x", "y,", NULL));
-  TEST (NULL, strv_check (g_strsplit (",x,y", ",", 2), "", "x", "y", NULL));
+  TEST (NULL, strv_check (g_strsplit (",x,y", ",", 2), "", "x,y", NULL));
-  TEST (NULL, strv_check (g_strsplit (",x,y,", ",", 2), "", "x", "y,", NULL));
+  TEST (NULL, strv_check (g_strsplit (",x,y,", ",", 2), "", "x,y,", NULL));
-  TEST (NULL, strv_check (g_strsplit ("x,y,z", ",", 2), "x", "y", "z", NULL));
+  TEST (NULL, strv_check (g_strsplit ("x,y,z", ",", 2), "x", "y,z", NULL));
-  TEST (NULL, strv_check (g_strsplit ("x,y,z,", ",", 2), "x", "y", "z,", NULL));
+  TEST (NULL, strv_check (g_strsplit ("x,y,z,", ",", 2), "x", "y,z,", NULL));
-  TEST (NULL, strv_check (g_strsplit (",x,y,z", ",", 2), "", "x", "y,z", NULL));
+  TEST (NULL, strv_check (g_strsplit (",x,y,z", ",", 2), "", "x,y,z", NULL));
-  TEST (NULL, strv_check (g_strsplit (",x,y,z,", ",", 2), "", "x", "y,z,", NULL));
+  TEST (NULL, strv_check (g_strsplit (",x,y,z,", ",", 2), "", "x,y,z,", NULL));
-  TEST (NULL, strv_check (g_strsplit (",,x,,y,,z,,", ",", 2), "", "", "x,,y,,z,,", NULL));
+  TEST (NULL, strv_check (g_strsplit (",,x,,y,,z,,", ",", 2), "", ",x,,y,,z,,", NULL));
-  TEST (NULL, strv_check (g_strsplit (",,x,,y,,z,,", ",,", 2), "", "x", "y,,z,,", NULL));
+  TEST (NULL, strv_check (g_strsplit (",,x,,y,,z,,", ",,", 2), "", "x,,y,,z,,", NULL));
 
   g_print ("\n");