├── LICENSE
├── Makefile
├── README
└── jinja2htmlcompress.py
/LICENSE:
--------------------------------------------------------------------------------
1 | Copyright (c) 2011 by Armin Ronacher, see AUTHORS for more details.
2 |
3 | Some rights reserved.
4 |
5 | Redistribution and use in source and binary forms, with or without
6 | modification, are permitted provided that the following conditions are
7 | met:
8 |
9 | * Redistributions of source code must retain the above copyright
10 | notice, this list of conditions and the following disclaimer.
11 |
12 | * Redistributions in binary form must reproduce the above
13 | copyright notice, this list of conditions and the following
14 | disclaimer in the documentation and/or other materials provided
15 | with the distribution.
16 |
17 | * The names of the contributors may not be used to endorse or
18 | promote products derived from this software without specific
19 | prior written permission.
20 |
21 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 | "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 | LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24 | A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25 | OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26 | SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
27 | LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28 | DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29 | THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30 | (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
31 | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 |
--------------------------------------------------------------------------------
/Makefile:
--------------------------------------------------------------------------------
1 | .PHONY: test
2 |
3 | test:
4 | python jinja2htmlcompress.py
5 |
--------------------------------------------------------------------------------
/README:
--------------------------------------------------------------------------------
1 |
2 |
3 | -- jinja2-htmlcompress
4 |
5 | a Jinja2 extension that removes whitespace between HTML tags.
6 |
7 | Example usage:
8 |
9 | env = Environment(extensions=['jinja2htmlcompress.HTMLCompress'])
10 |
11 | How does it work? It throws away all whitespace between HTML tags
12 | it can find at runtime. It will however preserve pre, textarea, style
13 | and script tags because this kinda makes sense. In order to force
14 | whitespace you can use ``{{ " " }}``.
15 |
16 | Unlike filters that work at template runtime, this remotes whitespace
17 | at compile time and does not add an overhead in template execution.
18 |
19 | What if you only want to selective strip stuff?
20 |
21 | env = Environment(extensions=['jinja2htmlcompress.SelectiveHTMLCompress'])
22 |
23 | And then mark blocks with ``{% strip %}``:
24 |
25 | {% strip %} ... {% endstrip %}
26 |
27 |
--------------------------------------------------------------------------------
/jinja2htmlcompress.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | """
3 | jinja2htmlcompress
4 | ~~~~~~~~~~~~~~~~~~
5 |
6 | A Jinja2 extension that eliminates useless whitespace at template
7 | compilation time without extra overhead.
8 |
9 | :copyright: (c) 2011 by Armin Ronacher.
10 | :license: BSD, see LICENSE for more details.
11 | """
12 | import re
13 | from jinja2.ext import Extension
14 | from jinja2.lexer import Token, describe_token
15 | from jinja2 import TemplateSyntaxError
16 |
17 |
18 | _tag_re = re.compile(r'(?:<(/?)([a-zA-Z0-9_-]+)\s*|(>\s*))(?s)')
19 | _ws_normalize_re = re.compile(r'[ \t\r\n]+')
20 |
21 |
22 | class StreamProcessContext(object):
23 |
24 | def __init__(self, stream):
25 | self.stream = stream
26 | self.token = None
27 | self.stack = []
28 |
29 | def fail(self, message):
30 | raise TemplateSyntaxError(message, self.token.lineno,
31 | self.stream.name, self.stream.filename)
32 |
33 |
34 | def _make_dict_from_listing(listing):
35 | rv = {}
36 | for keys, value in listing:
37 | for key in keys:
38 | rv[key] = value
39 | return rv
40 |
41 |
42 | class HTMLCompress(Extension):
43 | isolated_elements = set(['script', 'style', 'noscript', 'textarea'])
44 | void_elements = set(['br', 'img', 'area', 'hr', 'param', 'input',
45 | 'embed', 'col'])
46 | block_elements = set(['div', 'p', 'form', 'ul', 'ol', 'li', 'table', 'tr',
47 | 'tbody', 'thead', 'tfoot', 'tr', 'td', 'th', 'dl',
48 | 'dt', 'dd', 'blockquote', 'h1', 'h2', 'h3', 'h4',
49 | 'h5', 'h6', 'pre'])
50 | breaking_rules = _make_dict_from_listing([
51 | (['p'], set(['#block'])),
52 | (['li'], set(['li'])),
53 | (['td', 'th'], set(['td', 'th', 'tr', 'tbody', 'thead', 'tfoot'])),
54 | (['tr'], set(['tr', 'tbody', 'thead', 'tfoot'])),
55 | (['thead', 'tbody', 'tfoot'], set(['thead', 'tbody', 'tfoot'])),
56 | (['dd', 'dt'], set(['dl', 'dt', 'dd']))
57 | ])
58 |
59 | def is_isolated(self, stack):
60 | for tag in reversed(stack):
61 | if tag in self.isolated_elements:
62 | return True
63 | return False
64 |
65 | def is_breaking(self, tag, other_tag):
66 | breaking = self.breaking_rules.get(other_tag)
67 | return breaking and (tag in breaking or
68 | ('#block' in breaking and tag in self.block_elements))
69 |
70 | def enter_tag(self, tag, ctx):
71 | while ctx.stack and self.is_breaking(tag, ctx.stack[-1]):
72 | self.leave_tag(ctx.stack[-1], ctx)
73 | if tag not in self.void_elements:
74 | ctx.stack.append(tag)
75 |
76 | def leave_tag(self, tag, ctx):
77 | if not ctx.stack:
78 | ctx.fail('Tried to leave "%s" but something closed '
79 | 'it already' % tag)
80 | if tag == ctx.stack[-1]:
81 | ctx.stack.pop()
82 | return
83 | for idx, other_tag in enumerate(reversed(ctx.stack)):
84 | if other_tag == tag:
85 | for num in xrange(idx + 1):
86 | ctx.stack.pop()
87 | elif not self.breaking_rules.get(other_tag):
88 | break
89 |
90 | def normalize(self, ctx):
91 | pos = 0
92 | buffer = []
93 | def write_data(value):
94 | if not self.is_isolated(ctx.stack):
95 | value = _ws_normalize_re.sub(' ', value.strip())
96 | buffer.append(value)
97 |
98 | for match in _tag_re.finditer(ctx.token.value):
99 | closes, tag, sole = match.groups()
100 | preamble = ctx.token.value[pos:match.start()]
101 | write_data(preamble)
102 | if sole:
103 | write_data(sole)
104 | else:
105 | buffer.append(match.group())
106 | (closes and self.leave_tag or self.enter_tag)(tag, ctx)
107 | pos = match.end()
108 |
109 | write_data(ctx.token.value[pos:])
110 | return u''.join(buffer)
111 |
112 | def filter_stream(self, stream):
113 | ctx = StreamProcessContext(stream)
114 | for token in stream:
115 | if token.type != 'data':
116 | yield token
117 | continue
118 | ctx.token = token
119 | value = self.normalize(ctx)
120 | yield Token(token.lineno, 'data', value)
121 |
122 |
123 | class SelectiveHTMLCompress(HTMLCompress):
124 |
125 | def filter_stream(self, stream):
126 | ctx = StreamProcessContext(stream)
127 | strip_depth = 0
128 | while 1:
129 | if stream.current.type == 'block_begin':
130 | if stream.look().test('name:strip') or \
131 | stream.look().test('name:endstrip'):
132 | stream.skip()
133 | if stream.current.value == 'strip':
134 | strip_depth += 1
135 | else:
136 | strip_depth -= 1
137 | if strip_depth < 0:
138 | ctx.fail('Unexpected tag endstrip')
139 | stream.skip()
140 | if stream.current.type != 'block_end':
141 | ctx.fail('expected end of block, got %s' %
142 | describe_token(stream.current))
143 | stream.skip()
144 | if strip_depth > 0 and stream.current.type == 'data':
145 | ctx.token = stream.current
146 | value = self.normalize(ctx)
147 | yield Token(stream.current.lineno, 'data', value)
148 | else:
149 | yield stream.current
150 | stream.next()
151 |
152 |
153 | def test():
154 | from jinja2 import Environment
155 | env = Environment(extensions=[HTMLCompress])
156 | tmpl = env.from_string('''
157 |
158 |
159 | {{ title }}
160 |
161 |
166 |
167 | {{ title }}
Test Foo
168 | {{ title }}
169 |
170 |
171 | ''')
172 | print tmpl.render(title=42, href='index.html')
173 |
174 | env = Environment(extensions=[SelectiveHTMLCompress])
175 | tmpl = env.from_string('''
176 | Normal unchanged stuff
177 | {% strip %}Stripped test
178 | test {{ foo }}
179 | Normal again {{ foo }}
180 |
181 | Foo
Bar
182 | Baz
183 |
184 | Moep Test Moep
185 |
186 | {% endstrip %}
187 | ''')
188 | print tmpl.render(foo=42)
189 |
190 |
191 | if __name__ == '__main__':
192 | test()
193 |
--------------------------------------------------------------------------------