added truncation0.0.3

3 files changed, 101 insertions, 18 deletions

diff --git a/README.md b/README.md
index eb1f5a4..51c2f32 100644
--- a/README.md
+++ b/README.md
@@ -27,25 +27,53 @@ How to use
 =================
     from slugify import slugify
 
-    s = "This is a test ---"
-    r = slugify(s)
-    print r # => "this-is-a-test"
-
-    s = 'C\'est déjà l\'été.'
-    r = slugify(s)
-    print r # => "c-est-deja-lete"
-
-    s = 'Nín hǎo. Wǒ shì zhōng guó rén'
-    r = slugify(s)
-    print r # => "nin-hao-wo-shi-zhong-guo-ren"
+    txt = "This is a test ---"
+    r = slugify(txt)
+    self.assertEquals(r, "this-is-a-test")
+    
+    txt = "This -- is a ## test ---"
+    r = slugify(txt)
+    self.assertEquals(r, "this-is-a-test")
+    
+    txt = 'C\'est déjà l\'été.'
+    r = slugify(txt)
+    self.assertEquals(r, "cest-deja-lete")
 
-    s = '影師嗎'
-    r = slugify(s)
-    print r # => "ying-shi-ma"
+    txt = 'Nín hǎo. Wǒ shì zhōng guó rén'
+    r = slugify(txt)
+    self.assertEquals(r, "nin-hao-wo-shi-zhong-guo-ren")
 
     txt = 'Компьютер'
     r = slugify(txt)
-    print r # => "kompiuter"
+    self.assertEquals(r, "kompiuter")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt)
+    self.assertEquals(r, "jaja-lol-mememeoo-a")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt, max_length=9)
+    self.assertEquals(r, "jaja-lol")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt, max_length=15)
+    self.assertEquals(r, "jaja-lol-mememe")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt, max_length=50)
+    self.assertEquals(r, "jaja-lol-mememeoo-a")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt, max_length=15, word_boundary=True)
+    self.assertEquals(r, "jaja-lol-a")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt, max_length=19, word_boundary=True)
+    self.assertEquals(r, "jaja-lol-mememeoo")
+
+    txt = 'jaja---lol-méméméoo--a'
+    r = slugify(txt, max_length=20, word_boundary=True)
+    self.assertEquals(r, "jaja-lol-mememeoo-a")
 
 
 Running the tests
@@ -58,6 +86,10 @@ To run the tests against the current environment:
 Changelog
 =========
 
+0.0.3
+-----
+* Added the ability to truncate slugs + tests (viva Juan Riaza of Spain)
+
 0.0.2
 -----
 * Added more tests
@@ -71,7 +103,7 @@ Changelog
 License
 =======
 
-Copyright © Neekware Inc.
+Copyright © Val Neekman
 
 All rights reserved.
 
diff --git a/slugify/__init__.py b/slugify/__init__.py
index fe634bf..8d0295a 100644
--- a/slugify/__init__.py
+++ b/slugify/__init__.py
@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-__version__ = '0.0.2'
+__version__ = '0.0.3'
 
 __all__ = ['slugify']
 
@@ -23,7 +23,22 @@ REPLACE1_REXP = re.compile(r'[\']+')
 REPLACE2_REXP = re.compile(r'[^-a-z0-9]+')
 REMOVE_REXP = re.compile('-{2,}')
 
-def slugify(text, entities=True, decimal=True, hexadecimal=True):
+def smart_truncate(text, max_length=0, word_boundaries=False):
+    if not max_length or len(text) < max_length:
+        return text
+
+    if not word_boundaries:
+        return text[:max_length].strip('-')
+
+    truncated = ''
+    for i, word in enumerate(text.split('-')):
+        if not word: continue
+        if len(truncated) + len(word) + i <= max_length:
+            truncated += '{0}{1}'.format('-' if i else '', word)
+    return truncated.strip('-')
+
+
+def slugify(text, entities=True, decimal=True, hexadecimal=True, max_length=0, word_boundary=False):
     """ Make a slug from the given text """
 
     # text to unicode
@@ -64,4 +79,12 @@ def slugify(text, entities=True, decimal=True, hexadecimal=True):
     # remove redundant -
     text = REMOVE_REXP.sub('-', text).strip('-')
 
+    # smart truncate if requested
+    if max_length > 0:
+        text = smart_truncate(text, max_length, word_boundary)
+
     return text
+
+
+
+
diff --git a/test.py b/test.py
index e0697b5..c279a33 100644
--- a/test.py
+++ b/test.py
@@ -27,6 +27,34 @@ class TestSequenceFunctions(unittest.TestCase):
         r = slugify(txt)
         self.assertEquals(r, "kompiuter")
 
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt)
+        self.assertEquals(r, "jaja-lol-mememeoo-a")
+
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt, max_length=9)
+        self.assertEquals(r, "jaja-lol")
+
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt, max_length=15)
+        self.assertEquals(r, "jaja-lol-mememe")
+
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt, max_length=50)
+        self.assertEquals(r, "jaja-lol-mememeoo-a")
+
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt, max_length=15, word_boundary=True)
+        self.assertEquals(r, "jaja-lol-a")
+
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt, max_length=19, word_boundary=True)
+        self.assertEquals(r, "jaja-lol-mememeoo")
+
+        txt = 'jaja---lol-méméméoo--a'
+        r = slugify(txt, max_length=20, word_boundary=True)
+        self.assertEquals(r, "jaja-lol-mememeoo-a")
+
 if __name__ == '__main__':
     unittest.main()