Merge pull request #6 from miki725/minify

Minify
miki725 · Nov 22, 2017 · 8b1cdd5 · 8b1cdd5
2 parents 9134304 + 0990d64
commit 8b1cdd5
Show file tree

Hide file tree

Showing 5 changed files with 24 additions and 14 deletions.
diff --git a/HISTORY.rst b/HISTORY.rst
@@ -3,13 +3,19 @@
 History
 -------
 
+0.1.2 (2017-11-22)
+~~~~~~~~~~~~~~~~~~
+
+* Fixed: Not removing all spaces between html tags.
+  Sometimes spaces matter for formatting.
+  For example ``<strong>Hello</strong> <i>World</i>`` cannot be minified any further.
+
 0.1.1 (2016-09-26)
 ~~~~~~~~~~~~~~~~~~
 
 * Fixed: Cache properties now allow to set cache value via ``foo = bar``
   syntax when cache descriptor has ``as_property == True``
 
-
 0.1.0 (2015-11-26)
 ~~~~~~~~~~~~~~~~~~
 

diff --git a/django_auxilium/__init__.py b/django_auxilium/__init__.py
@@ -1,2 +1,2 @@
-__version__ = '0.1.1'
+__version__ = '0.1.2'
 __author__ = 'Miroslav Shubernetskiy'
diff --git a/django_auxilium/utils/html.py b/django_auxilium/utils/html.py
@@ -2,7 +2,6 @@
 import re
 
 import six
-from django.utils.html import strip_spaces_between_tags
 from six.moves.html_entities import name2codepoint
 from six.moves.html_parser import HTMLParser
 
@@ -11,6 +10,7 @@
 
 EXCLUDE_TAGS = ('textarea', 'pre', 'code', 'script',)
 RE_WHITESPACE = re.compile(r'\s{2,}|\n')
+RE_SPACE_BETWEEN_TAGS = re.compile(r'>(?:\s{2,}|\n)<')
 RE_EXCLUDE_TAGS = re.compile(
     """(               # group for results to be included in re.split
           <(?:{0})     # match beginning of one of exclude tags
@@ -27,10 +27,11 @@ def simple_minify(html):
     """
     Minify HTML with very simple algorithm.
 
-    This function tries to minify HTML by stripping all spaces between all html tags
-    (e.g. ``</div>    <div>`` -> ``</div><div>``). This step is accomplished by using
-    Django's ``strip_spaces_between_tags`` method. In addition to that, this function
-    replaces all whitespace (more then two consecutive whitespace characters or new line)
+    This function tries to minify HTML by stripping most spaces between all html tags
+    (e.g. ``</div>    <div>`` -> ``</div> <div>``). Note that not all spaces are removed
+    since sometimes that can adjust rendered HTML (e.g. ``<strong>Hello</strong> <i></i>``).
+    In addition to that, this function replaces all whitespace
+    (more then two consecutive whitespace characters or new line)
     with a space character except inside excluded tags such as ``pre`` or ``textarea``.
 
     **Though process**:
@@ -54,8 +55,7 @@ def simple_minify(html):
        appended to final HTML since as explained above, they are guaranteed
        to be content of excluded tags hence do not require minification.
     #. All even indexed elements are minified by stripping whitespace between
-       tags by using Django's ``strip_spaces_between_tags`` and redundant
-       whitespace is stripped in general via simple regex.
+       tags and redundant whitespace is stripped in general via simple regex.
 
     You can notice that the process does not involve parsing HTML since that
     usually adds some overhead (e.g. using beautiful soup). By using 2 regex
@@ -65,7 +65,8 @@ def simple_minify(html):
     html = ''
     for i, component in enumerate(components):
         if i % 2 == 0:
-            component = strip_spaces_between_tags(component.strip())
+            component = component.strip()
+            component = RE_SPACE_BETWEEN_TAGS.sub('> <', component)
             component = RE_WHITESPACE.sub(' ', component)
             html += component
         else:

diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -5,9 +5,10 @@ django-formtools
 flake8
 importanize
 mock
-pytest>=2.9
+pdbpp
 pytest-cov
 pytest-django
+pytest>=2.9
 python-magic
 sphinx
 sphinx-autobuild

diff --git a/tests/utils/test_html.py b/tests/utils/test_html.py
@@ -18,6 +18,8 @@
     </script>
 </head>
 <body>
+    <strong>Hello</strong> <i>World</i>
+    <strong>Hello</strong><i>Mars</i>
     <div>Content Here</div>
     <textarea>
 Input
@@ -42,11 +44,11 @@
 </html>
 """
 
-MINIFY_EXPECTED = """<html><head><title>Minify Test</title><script>
+MINIFY_EXPECTED = """<html> <head> <title>Minify Test</title><script>
         (function() {
             console.log('hello world');
         })();
-    </script></head><body><div>Content Here</div><textarea>
+    </script></head> <body> <strong>Hello</strong> <i>World</i> <strong>Hello</strong><i>Mars</i> <div>Content Here</div><textarea>
 Input
 Here
   123
@@ -61,7 +63,7 @@
         (function() {
             console.log('inside body script');
         })();
-    </script></body></html>"""
+    </script></body> </html>"""
 
 
 EXTRACT_INPUT = """