Changeset 5608

Timestamp:

07/04/07 04:28:29 (1 year ago)

Author:

mtredinnick

Message:

unicode: Added unicode-aware slugify filter (in Python) and better non-ASCII
handling for the Javascript slug creator in admin. Can never be perfect here,
but this is more tolerant in many cases. Fixed #4365. Thanks, Bill de hÓra,
Baptiste, orestis@orestis.gr, Ahmet and Jonas for contributions to this.

Files:

• django/branches/unicode/django/contrib/admin/media/js/urlify.js (modified) (3 diffs)
• django/branches/unicode/django/template/defaultfilters.py (modified) (1 diff)
• django/branches/unicode/tests/regressiontests/defaultfilters/tests.py (modified) (1 diff)

django/branches/unicode/django/contrib/admin/media/js/urlify.js

@@ +1 @@
+var LATIN_MAP =
+{
+    'À': 'A', 'Á': 'A', 'Â': 'A', 'Ã': 'A', 'Ä': 'A', 'Ã
+': 'A', 'Æ': 'AE', 'Ç':
+    'C', 'È': 'E', 'É': 'E', 'Ê': 'E', 'Ë': 'E', 'Ì': 'I', 'Í': 'I', 'Î': 'I',
+    'Ï': 'I', 'Ð': 'D', 'Ñ': 'N', 'Ò': 'O', 'Ó': 'O', 'Ô': 'O', 'Õ': 'O', 'Ö':
+    'O', 'Ø': 'O', 'Ù': 'U', 'Ú': 'U', 'Û': 'U', 'Ü': 'U', 'Ý': 'Y', 'Þ': 'TH',
+    'ß': 'ss', 'à ':'a', 'á':'a', 'â': 'a', 'ã': 'a', 'À': 'a', 'Ã¥': 'a', 'Ê':
+    'ae', 'ç': 'c', 'Ú': 'e', 'é': 'e', 'ê': 'e', 'ë': 'e', 'ì': 'i', 'í': 'i',
+    'î': 'i', 'ï': 'i', 'ð': 'o', 'ñ': 'n', 'ò': 'o', 'ó': 'o', 'Î': 'o', 'õ':
+    'o', 'ö': 'o', 'Þ': 'o', 'ù': 'u', 'ú': 'u', 'û': 'u', 'Ì': 'u', 'Ü': 'y',
+    'ß': 'th', 'ÿ': 'y',
+}
+var LATIN_SYMBOLS_MAP =
+{
+    '©':'(c)',
+}
+var GREEK_MAP =
+{
+    'α':'a', 'β':'b', 'γ':'g', 'Ύ':'d', 'ε':'e', 'ζ':'z', 'η':'h', 'Ξ':'8',
+    'ι':'i', 'κ':'k', 'λ':'l', 'ÎŒ':'m', 'Îœ':'n', 'Ο':'3', 'ο':'o', 'π':'p',
+    'ρ':'r', 'σ':'s', 'τ':'t', 'Ï
+':'y', 'φ':'f', 'χ':'x', 'ψ':'ps', 'ω':'w',
+    'ά':'a', 'έ':'e', 'ί':'i', 'ό':'o', 'ύ':'y', 'ή':'h', 'ώ':'w', 'ς':'s',
+    'ϊ':'i', 'ΰ':'y', 'ϋ':'y', 'ΐ':'i',
+    'Α':'A', 'Β':'B', 'Γ':'G', 'Δ':'D', 'Ε':'E', 'Ζ':'Z', 'Η':'H', 'Θ':'8',
+    'Ι':'I', 'Κ':'K', 'Λ':'L', 'Μ':'M', 'Ν':'N', 'Ξ':'3', 'Ο':'O', 'Π':'P',
+    'Ρ':'R', 'Σ':'S', '΀':'T', 'Υ':'Y', 'Ί':'F', 'Χ':'X', 'Κ':'PS', 'Ω':'W',
+    'Ά':'A', 'Έ':'E', 'Ί':'I', 'Ό':'O', 'Ύ':'Y', 'Ή':'H', 'Ώ':'W', 'Ϊ':'I',
+    'Ϋ':'Y'
+}
+var TURKISH_MAP = {
+    'ş':'s', 'Ş':'S', 'ı':'i', 'Ä°':'I', 'ç':'c', 'Ç':'C', 'ÃŒ':'u', 'Ü':'U',
+    'ö':'o', 'Ö':'O', 'ğ':'g', 'Ğ':'G',
+}
+// var RUSSIAN_MAP =
+// {
+// }
+
+var ALL_DOWNCODE_MAPS=new Array()
+ALL_DOWNCODE_MAPS[0]=LATIN_MAP
+ALL_DOWNCODE_MAPS[1]=LATIN_SYMBOLS_MAP
+ALL_DOWNCODE_MAPS[2]=GREEK_MAP
+ALL_DOWNCODE_MAPS[3]=TURKISH_MAP
+//ALL_DOWNCODE_MAPS[4]=RUSSIAN_MAP
+
+var Downcoder = new Object();
+Downcoder.Initialize = function()
+{
+    if (Downcoder.map) // already made
+        return ;
+    Downcoder.map ={}
+    Downcoder.chars = '' ;
+    for(var i in ALL_DOWNCODE_MAPS)
+    {
+        var lookup = ALL_DOWNCODE_MAPS[i]
+        for (var c in lookup)
+        {
+            Downcoder.map[c] = lookup[c] ;
+            Downcoder.chars += c ;
+        }
+     }
+    Downcoder.regex = new RegExp('[' + Downcoder.chars + ']|[^' + Downcoder.chars + ']+','g') ;
+}
+
+downcode= function( slug )
+{
+    Downcoder.Initialize() ;
+    var downcoded =""
+    var pieces = slug.match(Downcoder.regex);
+    if(pieces)
+    {
+        for (var i = 0 ; i < pieces.length ; i++)
+        {
+            if (pieces[i].length == 1)
+            {
+                var mapped = Downcoder.map[pieces[i]] ;
+                if (mapped != null)
+                {
+                    downcoded+=mapped;
+                    continue ;
+                }
+            }
+            downcoded+=pieces[i];
+        }
+    }
+    else
+    {
+        downcoded = slug;
+    }
+    return downcoded;
+}
+
+
-function URLify(s, num_chars) {
-    // changes, e.g., "Petty theft" to "petty_theft"
-    // remove all these words from the string before urlifying
+    s = downcode(s);
-    removelist = ["a", "an", "as", "at", "before", "but", "by", "for", "from",
-                  "is", "in", "into", "like", "of", "off", "on", "onto", "per",
@@ -8 +103 @@
-    r = new RegExp('\\b(' + removelist.join('|') + ')\\b', 'gi');
-    s = s.replace(r, '');
+    // if downcode doesn't hit, the char will be stripped here
-    s = s.replace(/[^-\w\s]/g, '');  // remove unneeded chars
-    s = s.replace(/^\s+|\s+$/g, ''); // trim leading/trailing spaces
@@ -14 +110 @@
-    return s.substring(0, num_chars);// trim to first num_chars chars
-}
+

django/branches/unicode/django/template/defaultfilters.py

@@ -116 +116 @@
-
-def slugify(value):
-
-
-
-
+
+
+
+
+
+
+
-    return re.sub('[-\s]+', '-', value)
-slugify = stringfilter(slugify)

django/branches/unicode/tests/regressiontests/defaultfilters/tests.py

@@ -68 +68 @@
-u'jack-jill-like-numbers-123-and-4-and-silly-characters'
-
+>>> slugify(u"Un \xe9l\xe9phant \xe0 l'or\xe9e du bois")
+u'un-elephant-a-loree-du-bois'
+
->>> stringformat(1, u'03d')
-u'001'