From 8ba00dd9f12f59f67be88175f25b0109f2039a61 Mon Sep 17 00:00:00 2001
From: Justin Mayer <entroP@gmail.com>
Date: Wed, 15 Apr 2020 20:42:21 +0200
Subject: [PATCH] Preserve category case in importer

Adds a `preserve_case` parameter to the `slugify()` function and uses it
to preserve capital letters in category names when using the Pelican
importer.
---
 pelican/tests/test_importer.py  | 6 +++---
 pelican/tests/test_utils.py     | 6 ++++++
 pelican/tools/pelican_import.py | 6 ++++--
 pelican/utils.py                | 5 +++--
 4 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/pelican/tests/test_importer.py b/pelican/tests/test_importer.py
index 1a6ce404..f7346b9a 100644
--- a/pelican/tests/test_importer.py
+++ b/pelican/tests/test_importer.py
@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
 
 import locale
 import os
@@ -138,7 +138,7 @@ class TestWordpressXmlImporter(unittest.TestCase):
         index = 0
         for post in test_posts:
             name = post[2]
-            category = slugify(post[5][0], regex_subs=subs)
+            category = slugify(post[5][0], regex_subs=subs, preserve_case=True)
             name += '.md'
             filename = os.path.join(category, name)
             out_name = fnames[index]
@@ -215,7 +215,7 @@ class TestWordpressXmlImporter(unittest.TestCase):
         for post in test_posts:
             name = post[2]
             kind = post[8]
-            category = slugify(post[5][0], regex_subs=subs)
+            category = slugify(post[5][0], regex_subs=subs, preserve_case=True)
             name += '.md'
             filename = os.path.join(kind, category, name)
             out_name = fnames[index]
diff --git a/pelican/tests/test_utils.py b/pelican/tests/test_utils.py
index ad90a78e..3a8c4bd8 100644
--- a/pelican/tests/test_utils.py
+++ b/pelican/tests/test_utils.py
@@ -122,6 +122,12 @@ class TestUtils(LoggedTestCase):
         for value, expected in samples:
             self.assertEqual(utils.slugify(value, regex_subs=subs), expected)
 
+        self.assertEqual(utils.slugify('Cat', regex_subs=subs), 'cat')
+        self.assertEqual(
+            utils.slugify('Cat', regex_subs=subs, preserve_case=False), 'cat')
+        self.assertEqual(
+            utils.slugify('Cat', regex_subs=subs, preserve_case=True), 'Cat')
+
     def test_slugify_substitute(self):
 
         samples = (('C++ is based on C', 'cpp-is-based-on-c'),
diff --git a/pelican/tools/pelican_import.py b/pelican/tools/pelican_import.py
index 335f1953..bb3b8fc3 100755
--- a/pelican/tools/pelican_import.py
+++ b/pelican/tools/pelican_import.py
@@ -634,7 +634,8 @@ def get_out_filename(output_path, filename, ext, kind,
             typename = ''
             kind = 'article'
         if dircat and (len(categories) > 0):
-            catname = slugify(categories[0], regex_subs=slug_subs)
+            catname = slugify(
+                categories[0], regex_subs=slug_subs, preserve_case=True)
         else:
             catname = ''
         out_filename = os.path.join(output_path, typename,
@@ -643,7 +644,8 @@ def get_out_filename(output_path, filename, ext, kind,
             os.makedirs(os.path.join(output_path, typename, catname))
     # option to put files in directories with categories names
     elif dircat and (len(categories) > 0):
-        catname = slugify(categories[0], regex_subs=slug_subs)
+        catname = slugify(
+            categories[0], regex_subs=slug_subs, preserve_case=True)
         out_filename = os.path.join(output_path, catname, filename + ext)
         if not os.path.isdir(os.path.join(output_path, catname)):
             os.mkdir(os.path.join(output_path, catname))
diff --git a/pelican/utils.py b/pelican/utils.py
index 4b5b7134..b1536de8 100644
--- a/pelican/utils.py
+++ b/pelican/utils.py
@@ -222,7 +222,7 @@ def pelican_open(filename, mode='r', strip_crs=(sys.platform == 'win32')):
     yield content
 
 
-def slugify(value, regex_subs=()):
+def slugify(value, regex_subs=(), preserve_case=False):
     """
     Normalizes string, converts to lowercase, removes non-alpha characters,
     and converts spaces to hyphens.
@@ -245,7 +245,8 @@ def slugify(value, regex_subs=()):
         value = re.sub(src, dst, value, flags=re.IGNORECASE)
 
     # convert to lowercase
-    value = value.lower()
+    if not preserve_case:
+        value = value.lower()
 
     # we want only ASCII chars
     value = value.encode('ascii', 'ignore').strip()