Side by Side Diff: cms/utils.py
Issue 29590620:
Noissue - Refactor Converter.__init__ and __call__ (Closed)
Patch Set:
Created Oct. 27, 2017, 5:54 p.m.
| Left: | ||
| Right: |
Use n/p to move between diff chunks;
N/P to move between comments.
« cms/converters.py ('K')
|
« cms/converters.py ('k')
|
tests/expected_output/en/includer » ('j')
|
tests/test_site/includes/example.html » ('J')
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Hide Comments ('s')
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Hide Comments ('s')
| OLD | NEW |
|---|---|
| 1 # This file is part of the Adblock Plus web scripts, | 1 # This file is part of the Adblock Plus web scripts, |
| 2 # Copyright (C) 2006-present eyeo GmbH | 2 # Copyright (C) 2006-present eyeo GmbH |
| 3 # | 3 # |
| 4 # Adblock Plus is free software: you can redistribute it and/or modify | 4 # Adblock Plus is free software: you can redistribute it and/or modify |
| 5 # it under the terms of the GNU General Public License version 3 as | 5 # it under the terms of the GNU General Public License version 3 as |
| 6 # published by the Free Software Foundation. | 6 # published by the Free Software Foundation. |
| 7 # | 7 # |
| 8 # Adblock Plus is distributed in the hope that it will be useful, | 8 # Adblock Plus is distributed in the hope that it will be useful, |
| 9 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 9 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 # GNU General Public License for more details. | 11 # GNU General Public License for more details. |
| 12 # | 12 # |
| 13 # You should have received a copy of the GNU General Public License | 13 # You should have received a copy of the GNU General Public License |
| 14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. | 14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. |
| 15 | 15 |
| 16 from cms.converters import converters, TemplateConverter | 16 import re |
| 17 | |
| 18 __all__ = [ | |
| 19 'get_page_params', | |
| 20 'process_page', | |
| 21 'split_head_body', | |
| 22 'extract_page_metadata' | |
| 23 ] | |
| 24 | |
| 25 | |
| 26 def split_head_body(html): | |
|
Vasily Kuznetsov
2017/10/27 18:35:01
Maybe this function should be called `decapitate`.
mathias
2017/10/30 15:37:00
Funny, but no. The name is perfect, there's nothin
| |
| 27 """Split HTML page into head and remaining content. | |
| 28 | |
| 29 This is used to pass head and body of the page to the template as two | |
| 30 separate variables. | |
| 31 | |
| 32 Parameters | |
| 33 ---------- | |
| 34 html: str | |
| 35 Source HTML to split. | |
| 36 | |
| 37 Returns | |
| 38 ------- | |
| 39 (str, str) | |
| 40 Everything inside of <head> tags found in the page, | |
| 41 the rest of the page text with <head> tags removed. | |
| 42 | |
| 43 """ | |
| 44 head = [] | |
| 45 | |
| 46 def add_to_head(match): | |
| 47 head.append(match.group(1)) | |
| 48 return '' | |
| 49 | |
| 50 body = re.sub(r'<head>(.*?)</head>', add_to_head, html, flags=re.S) | |
| 51 return ''.join(head), body | |
| 52 | |
| 53 | |
| 54 def extract_page_metadata(source): | |
| 55 """Extract metadata variables from source text of the page. | |
| 56 | |
| 57 Parameters | |
| 58 ---------- | |
| 59 source: str | |
| 60 Source text of the page. | |
| 61 | |
| 62 Returns | |
| 63 ------- | |
| 64 (dict, str) | |
| 65 Metadata of the page, remaining source text without metadata. | |
| 66 | |
| 67 """ | |
| 68 metadata = {} | |
| 69 lines = source.splitlines(True) | |
| 70 for i, line in enumerate(lines): | |
| 71 if line.strip() in {'<!--', '-->'}: | |
| 72 lines[i] = '' | |
| 73 continue | |
| 74 if not re.search(r'^\s*[\w\-]+\s*=', line): | |
| 75 break | |
| 76 name, value = line.split('=', 1) | |
| 77 value = value.strip() | |
| 78 if value.startswith('[') and value.endswith(']'): | |
| 79 value = [element.strip() for element in value[1:-1].split(',')] | |
| 80 lines[i] = '\n' | |
| 81 metadata[name.strip()] = value | |
| 82 return metadata, ''.join(lines) | |
| 17 | 83 |
| 18 | 84 |
| 19 def get_page_params(source, locale, page, format=None, site_url_override=None, | 85 def get_page_params(source, locale, page, format=None, site_url_override=None, |
| 20 localized_string_callback=None): | 86 localized_string_callback=None): |
| 87 from cms.converters import converters | |
|
Vasily Kuznetsov
2017/10/27 18:35:02
It makes more sense to do contrived imports on thi
mathias
2017/10/30 15:37:00
Acknowledged.
| |
| 88 | |
| 21 # Guess page format if omitted, but default to Markdown for friendlier excep tions | 89 # Guess page format if omitted, but default to Markdown for friendlier excep tions |
| 22 if format is None: | 90 if format is None: |
| 23 for format in converters.iterkeys(): | 91 for format in converters.iterkeys(): |
| 24 if source.has_page(page, format): | 92 if source.has_page(page, format): |
| 25 break | 93 break |
| 26 else: | 94 else: |
| 27 format = 'md' | 95 format = 'md' |
| 28 | 96 |
| 29 params = { | 97 params = { |
| 30 'source': source, | 98 'source': source, |
| 31 'template': 'default', | 99 'template': 'default', |
| 32 'locale': locale, | 100 'locale': locale, |
| 33 'page': page, | 101 'page': page, |
| 34 'pagedata': source.read_page(page, format), | |
| 35 'config': source.read_config(), | 102 'config': source.read_config(), |
| 36 'localized_string_callback': localized_string_callback, | 103 'localized_string_callback': localized_string_callback, |
| 37 } | 104 } |
| 38 | 105 |
| 39 localefile = page | 106 localefile = page |
| 40 if params['config'].has_option('locale_overrides', page): | 107 if params['config'].has_option('locale_overrides', page): |
| 41 localefile = params['config'].get('locale_overrides', page) | 108 localefile = params['config'].get('locale_overrides', page) |
| 42 params['localedata'] = source.read_locale(params['locale'], localefile) | 109 params['localedata'] = source.read_locale(params['locale'], localefile) |
| 43 | 110 |
| 44 if params['config'].has_option('general', 'siteurl'): | 111 if params['config'].has_option('general', 'siteurl'): |
| 45 if site_url_override: | 112 if site_url_override: |
| 46 params['site_url'] = site_url_override | 113 params['site_url'] = site_url_override |
| 47 else: | 114 else: |
| 48 params['site_url'] = params['config'].get('general', 'siteurl') | 115 params['site_url'] = params['config'].get('general', 'siteurl') |
| 49 | 116 |
| 50 try: | 117 data, filename = source.read_page(page, format) |
|
Vasily Kuznetsov
2017/10/27 18:35:01
This was done in the constructor of `Converter` be
mathias
2017/10/30 15:37:00
Acknowledged.
| |
| 51 converter_class = converters[format] | 118 metadata, body = extract_page_metadata(data) |
| 52 except KeyError: | 119 params['pagedata'] = body, filename |
| 53 raise Exception('Page %s uses unknown format %s' % (page, format)) | 120 params.update(metadata) |
| 54 | 121 |
| 55 converter = converter_class(params) | |
| 56 | |
| 57 # Note: The converter might change some parameters so we can only read in | |
| 58 # template data here. | |
| 59 params['templatedata'] = source.read_template(params['template']) | 122 params['templatedata'] = source.read_template(params['template']) |
| 60 | 123 |
| 61 defaultlocale = params['config'].get('general', 'defaultlocale') | 124 defaultlocale = params['config'].get('general', 'defaultlocale') |
| 62 params['defaultlocale'] = defaultlocale | 125 params['defaultlocale'] = defaultlocale |
| 63 | 126 |
| 64 locales = [ | 127 locales = [ |
| 65 l | 128 l |
| 66 for l in source.list_locales() | 129 for l in source.list_locales() |
| 67 if source.has_locale(l, localefile) | 130 if source.has_locale(l, localefile) |
| 68 ] | 131 ] |
| 69 if defaultlocale not in locales: | 132 if defaultlocale not in locales: |
| 70 locales.append(defaultlocale) | 133 locales.append(defaultlocale) |
| 71 locales.sort() | 134 locales.sort() |
| 72 params['available_locales'] = locales | 135 params['available_locales'] = locales |
| 73 | 136 |
| 74 params['head'], params['body'] = converter() | 137 try: |
|
Vasily Kuznetsov
2017/10/27 18:35:02
Lines 137-143 should probably be in `converters.py
mathias
2017/10/30 15:37:00
Acknowledged.
| |
| 138 converter_class = converters[format] | |
| 139 converter = converter_class(body, filename, params) | |
|
mathias
2017/10/30 15:37:00
This line should not be part of this try-block any
Vasily Kuznetsov
2017/11/07 17:08:29
Done.
| |
| 140 except KeyError: | |
| 141 raise Exception('Page %s uses unknown format %s' % (page, format)) | |
| 142 | |
| 143 converted = converter() | |
| 144 params['head'], params['body'] = split_head_body(converted) | |
| 145 | |
| 75 if converter.total_translations > 0: | 146 if converter.total_translations > 0: |
| 76 params['translation_ratio'] = ( | 147 params['translation_ratio'] = ( |
| 77 1 - float(converter.missing_translations) / converter.total_translat ions | 148 1 - float(converter.missing_translations) / converter.total_translat ions |
| 78 ) | 149 ) |
| 79 else: | 150 else: |
| 80 params['translation_ratio'] = 1 | 151 params['translation_ratio'] = 1 |
| 81 | 152 |
| 82 return params | 153 return params |
| 83 | 154 |
| 84 | 155 |
| 85 def process_page(source, locale, page, format=None, site_url_override=None, | 156 def process_page(source, locale, page, format=None, site_url_override=None, |
| 86 localized_string_callback=None): | 157 localized_string_callback=None): |
| 87 return TemplateConverter( | 158 from cms.converters import TemplateConverter |
| 88 get_page_params(source, locale, page, format, | 159 |
| 89 site_url_override, localized_string_callback), | 160 params = get_page_params(source, locale, page, format, site_url_override, |
| 90 key='templatedata' | 161 localized_string_callback) |
| 91 )() | 162 return TemplateConverter(*params['templatedata'], params=params)() |
| OLD | NEW |
« cms/converters.py ('K')
|
« cms/converters.py ('k')
|
tests/expected_output/en/includer » ('j')
|
tests/test_site/includes/example.html » ('J')
