release 1.2.6, case sensitive slug support1.2.6

7 files changed, 38 insertions, 9 deletions

diff --git a/.vscode/settings.json b/.vscode/settings.json
new file mode 100644
index 0000000..20d15cb
--- /dev/null
+++ b/.vscode/settings.json
@@ -0,0 +1,3 @@
+{
+  "python.linting.pylintEnabled": false
+}
\ No newline at end of file
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3ccebfe..84f3436 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,3 +1,6 @@
+## 1.2.6
+  - Add support for case sensitive slugs (@s-m-e)
+
 ## 1.2.5
   - Add support for using text-unidecode (@bolkedebruin)
   - Switch to pycodestyle instead of pep8
diff --git a/README.rst b/README.rst
index 9604965..dbdeb52 100644
--- a/README.rst
+++ b/README.rst
@@ -162,6 +162,10 @@ How to use
     r = slugify(txt, stopwords=['the', 'in', 'a', 'hurry'])
     self.assertEqual(r, 'quick-brown-fox-jumps-over-lazy-dog')
 
+    txt = 'thIs Has a stopword Stopword'
+    r = slugify(txt, stopwords=['Stopword'], lowercase=False)
+    self.assertEqual(r, 'thIs-Has-a-stopword')
+
     txt = 'foo & bar'
     r = slugify(txt)
     self.assertEqual(r, 'foo-bar')
@@ -176,6 +180,8 @@ How to use
     r = slugify(txt, separator='_', regex_pattern=regex_pattern)
     self.assertNotEqual(r, "_this_is_a_test_")
 
+For more examples, have a look at the (`TEST`_) file.
+
 Running the tests
 -----------------
 
@@ -189,7 +195,7 @@ To run the tests against the current environment:
 License
 -------
 
-Released under a (`MIT`_) license.
+Released under a (`TEST`_) license.
 
 **Note:**
 
@@ -222,3 +228,4 @@ X.Y.Z Version
 
 .. _MIT: https://github.com/un33k/python-slugify/blob/master/LICENSE
 
+.. _TEST: https://github.com/un33k/python-slugify/blob/master/test.py
diff --git a/pycodestyle.sh b/pycodestyle.sh
index ab6766e..cd6122d 100755
--- a/pycodestyle.sh
+++ b/pycodestyle.sh
@@ -7,5 +7,7 @@
 #  -- E261 at least two spaces before inline comment
 #  -- E225 missing whitespace around operator
 #  -- E501 line too long
+# Ignoring warning codes
+#  -- W605 invalid escape sequence '\d'
 
-pycodestyle --ignore=E128,E261,E225,E501 slugify test.py setup.py
+pycodestyle --ignore=E128,E261,E225,E501,W605 slugify test.py setup.py
diff --git a/slugify/__init__.py b/slugify/__init__.py
index 02393a1..1a02a3e 100644
--- a/slugify/__init__.py
+++ b/slugify/__init__.py
@@ -3,4 +3,4 @@ from .slugify import *
 
 __author__ = 'Val Neekman @ Neekware Inc. [@vneekman]'
 __description__ = 'A Python slugify application that also handles Unicode'
-__version__ = '1.2.5'
+__version__ = '1.2.6'
diff --git a/slugify/slugify.py b/slugify/slugify.py
index 99afb7f..192bbd3 100644
--- a/slugify/slugify.py
+++ b/slugify/slugify.py
@@ -26,6 +26,7 @@ DECIMAL_PATTERN = re.compile('&#(\d+);')
 HEX_PATTERN = re.compile('&#x([\da-fA-F]+);')
 QUOTE_PATTERN = re.compile(r'[\']+')
 ALLOWED_CHARS_PATTERN = re.compile(r'[^-a-z0-9]+')
+ALLOWED_CHARS_PATTERN_WITH_UPPERCASE = re.compile(r'[^-a-zA-Z0-9]+')
 DUPLICATE_DASH_PATTERN = re.compile('-{2,}')
 NUMBERS_PATTERN = re.compile('(?<=\d),(?=\d)')
 DEFAULT_SEPARATOR = '-'
@@ -74,7 +75,7 @@ def smart_truncate(string, max_length=0, word_boundaries=False, separator=' ', s
 
 
 def slugify(text, entities=True, decimal=True, hexadecimal=True, max_length=0, word_boundary=False,
-            separator=DEFAULT_SEPARATOR, save_order=False, stopwords=(), regex_pattern=None):
+            separator=DEFAULT_SEPARATOR, save_order=False, stopwords=(), regex_pattern=None, lowercase=True):
     """
     Make a slug from the given text.
     :param text (str): initial text
@@ -87,6 +88,7 @@ def slugify(text, entities=True, decimal=True, hexadecimal=True, max_length=0, w
     :param separator (str): separator between words
     :param stopwords (iterable): words to discount
     :param regex_pattern (str): regex pattern for allowed characters
+    :param lowercase (bool): activate case sensitivity by setting it to False
     :return (str):
     """
 
@@ -127,8 +129,9 @@ def slugify(text, entities=True, decimal=True, hexadecimal=True, max_length=0, w
     if sys.version_info < (3,):
         text = text.encode('ascii', 'ignore')
 
-    # make the text lowercase
-    text = text.lower()
+    # make the text lowercase (optional)
+    if lowercase:
+        text = text.lower()
 
     # remove generated quotes -- post-process
     text = QUOTE_PATTERN.sub('', text)
@@ -137,7 +140,10 @@ def slugify(text, entities=True, decimal=True, hexadecimal=True, max_length=0, w
     text = NUMBERS_PATTERN.sub('', text)
 
     # replace all other unwanted characters
-    pattern = regex_pattern or ALLOWED_CHARS_PATTERN
+    if lowercase:
+        pattern = regex_pattern or ALLOWED_CHARS_PATTERN
+    else:
+        pattern = regex_pattern or ALLOWED_CHARS_PATTERN_WITH_UPPERCASE
     text = re.sub(pattern, DEFAULT_SEPARATOR, text)
 
     # remove redundant
@@ -145,8 +151,11 @@ def slugify(text, entities=True, decimal=True, hexadecimal=True, max_length=0, w
 
     # remove stopwords
     if stopwords:
-        stopwords_lower = [s.lower() for s in stopwords]
-        words = [w for w in text.split(DEFAULT_SEPARATOR) if w not in stopwords_lower]
+        if lowercase:
+            stopwords_lower = [s.lower() for s in stopwords]
+            words = [w for w in text.split(DEFAULT_SEPARATOR) if w not in stopwords_lower]
+        else:
+            words = [w for w in text.split(DEFAULT_SEPARATOR) if w not in stopwords]
         text = DEFAULT_SEPARATOR.join(words)
 
     # smart truncate if requested
diff --git a/test.py b/test.py
index 3d37a0b..9ff9ec0 100644
--- a/test.py
+++ b/test.py
@@ -113,6 +113,11 @@ class TestSlugification(unittest.TestCase):
         r = slugify(txt, stopwords=['stopword'])
         self.assertEqual(r, 'this-has-a')
 
+    def test_stopword_removal_casesensitive(self):
+        txt = 'thIs Has a stopword Stopword'
+        r = slugify(txt, stopwords=['Stopword'], lowercase=False)
+        self.assertEqual(r, 'thIs-Has-a-stopword')
+
     def test_multiple_stopword_occurances(self):
         txt = 'the quick brown fox jumps over the lazy dog'
         r = slugify(txt, stopwords=['the'])