Side by Side Diff: cms/converters.py
Issue 29378736:
NoIssue - Improves converters.py PEP8 compliance (Closed)
Base URL: https://hg.adblockplus.org/cms
Patch Set:
Created March 8, 2017, 12:15 p.m.
| Left: | ||
| Right: |
Use n/p to move between diff chunks;
N/P to move between comments.
« no previous file with comments
|
« no previous file
|
tox.ini » ('j')
|
no next file with comments »
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) 2006-2016 Eyeo GmbH | 2 # Copyright (C) 2006-2016 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 import os | 16 import os |
| 17 import HTMLParser | 17 import HTMLParser |
| 18 import re | 18 import re |
| 19 | 19 |
| 20 import jinja2 | 20 import jinja2 |
| 21 import markdown | 21 import markdown |
| 22 | 22 |
| 23 | 23 |
| 24 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs are | 24 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs |
| 25 # inserted into the <head> tag | 25 # are inserted into the <head> tag |
| 26 orig_isBlockLevel = markdown.util.isBlockLevel | 26 orig_isBlockLevel = markdown.util.isBlockLevel |
| 27 | 27 |
| 28 | 28 |
| 29 def isBlockLevel(tag): | 29 def isBlockLevel(tag): |
| 30 if tag == 'head': | 30 if tag == 'head': |
| 31 return True | 31 return True |
| 32 else: | 32 return orig_isBlockLevel(tag) |
| 33 return orig_isBlockLevel(tag) | 33 |
| 34 markdown.util.isBlockLevel = isBlockLevel | 34 markdown.util.isBlockLevel = isBlockLevel |
| 35 | 35 |
| 36 html_escapes = { | 36 html_escapes = { |
| 37 '<': '<', | 37 '<': '<', |
| 38 '>': '>', | 38 '>': '>', |
| 39 '&': '&', | 39 '&': '&', |
| 40 '"': '"', | 40 '"': '"', |
| 41 "'": ''', | 41 "'": ''', |
| 42 } | 42 } |
| 43 | 43 |
| (...skipping 14 matching lines...) Expand all Loading... | |
| 58 self._inside_fixed = False | 58 self._inside_fixed = False |
| 59 self._attrs = {} | 59 self._attrs = {} |
| 60 self._pagename = pagename | 60 self._pagename = pagename |
| 61 | 61 |
| 62 # Force-escape ampersands, otherwise the parser will autocomplete bogus | 62 # Force-escape ampersands, otherwise the parser will autocomplete bogus |
| 63 # entities. | 63 # entities. |
| 64 text = re.sub(r'&(?!\S+;)', '&', text) | 64 text = re.sub(r'&(?!\S+;)', '&', text) |
| 65 | 65 |
| 66 try: | 66 try: |
| 67 self.feed(text) | 67 self.feed(text) |
| 68 return ''.join(self._string), self._attrs, [''.join(s) for s in self ._fixed_strings] | 68 return (''.join(self._string), |
| 69 self._attrs, [''.join(s) for s in self._fixed_strings]) | |
| 69 finally: | 70 finally: |
| 70 self._string = None | 71 self._string = None |
| 71 self._attrs = None | 72 self._attrs = None |
| 72 self._pagename = None | 73 self._pagename = None |
| 73 self._inside_fixed = False | 74 self._inside_fixed = False |
| 74 self._fixed_strings = None | 75 self._fixed_strings = None |
| 75 | 76 |
| 76 def handle_starttag(self, tag, attrs): | 77 def handle_starttag(self, tag, attrs): |
| 77 if self._inside_fixed: | 78 if self._inside_fixed: |
| 78 raise Exception("Unexpected HTML tag '%s' inside a fixed string on p age %s" % (tag, self._pagename)) | 79 raise Exception('Unexpected HTML tag "{}" inside a fixed string' |
|
Vasily Kuznetsov
2017/03/08 17:31:44
Do you think it's ok that we're changing the quote
Jon Sonesen
2017/03/08 17:51:57
Well, the otherway causes a style warning, however
Jon Sonesen
2017/03/08 17:55:25
whoops, I was wrong plz disregard XD
Vasily Kuznetsov
2017/03/09 12:33:27
Yeah, the logic is that if the string has single q
| |
| 79 elif tag == 'fix': | 80 'on page {}'.format(tag, self._pagename)) |
| 81 if tag == 'fix': | |
| 80 self._inside_fixed = True | 82 self._inside_fixed = True |
| 81 self._fixed_strings.append([]) | 83 self._fixed_strings.append([]) |
| 82 elif tag in self._whitelist: | 84 if tag in self._whitelist: |
| 83 self._attrs.setdefault(tag, []).append(attrs) | 85 self._attrs.setdefault(tag, []).append(attrs) |
| 84 self._string.append('<%s>' % tag) | 86 self._string.append('<{}>'.format(tag)) |
| 85 else: | 87 else: |
| 86 raise Exception("Unexpected HTML tag '%s' in localizable string on p age %s" % (tag, self._pagename)) | 88 raise Exception('Unexpected HTML tag "{}" inside a fixed string' |
| 89 'on page {}'.format(tag, self._pagename)) | |
| 87 | 90 |
| 88 def handle_endtag(self, tag): | 91 def handle_endtag(self, tag): |
| 89 if tag == 'fix': | 92 if tag == 'fix': |
| 90 self._string.append('{%d}' % len(self._fixed_strings)) | 93 self._string.append('{{{}}}'.format(self._fixed_strings)) |
| 91 self._inside_fixed = False | 94 self._inside_fixed = False |
| 92 else: | 95 else: |
| 93 self._string.append('</%s>' % tag) | 96 self._string.append('</{}>'.format(tag)) |
| 94 | 97 |
| 95 def _append_text(self, s): | 98 def _append_text(self, s): |
| 96 if self._inside_fixed: | 99 if self._inside_fixed: |
| 97 self._fixed_strings[-1].append(s) | 100 self._fixed_strings[-1].append(s) |
| 98 else: | 101 else: |
| 99 self._string.append(s) | 102 self._string.append(s) |
| 100 | 103 |
| 101 def handle_data(self, data): | 104 def handle_data(self, data): |
| 102 # Note: lack of escaping here is intentional. The result is a locale str ing, | 105 # Note: lack of escaping here is intentional. The result is a locale |
| 103 # HTML escaping is applied when this string is inserted into the documen t. | 106 # string, HTML escaping is applied when this string is inserted into |
| 107 # the document. | |
| 104 self._append_text(data) | 108 self._append_text(data) |
| 105 | 109 |
| 106 def handle_entityref(self, name): | 110 def handle_entityref(self, name): |
| 107 self._append_text(self.unescape('&%s;' % name)) | 111 self._append_text(self.unescape('&{};'.format(name))) |
| 108 | 112 |
| 109 def handle_charref(self, name): | 113 def handle_charref(self, name): |
| 110 self._append_text(self.unescape('&#%s;' % name)) | 114 self._append_text(self.unescape('&#{};'.format(name))) |
| 111 | 115 |
| 112 | 116 |
| 113 class Converter: | 117 class Converter: |
| 114 whitelist = {'a', 'em', 'sup', 'strong', 'code', 'span'} | 118 whitelist = {'a', 'em', 'sup', 'strong', 'code', 'span'} |
| 115 missing_translations = 0 | 119 missing_translations = 0 |
| 116 total_translations = 0 | 120 total_translations = 0 |
| 117 | 121 |
| 118 def __init__(self, params, key='pagedata'): | 122 def __init__(self, params, key='pagedata'): |
| 119 self._params = params | 123 self._params = params |
| 120 self._key = key | 124 self._key = key |
| 121 self._attribute_parser = AttributeParser(self.whitelist) | 125 self._attribute_parser = AttributeParser(self.whitelist) |
| 122 self._seen_defaults = {} | 126 self._seen_defaults = {} |
| 123 | 127 |
| 124 # Read in any parameters specified at the beginning of the file | 128 # Read in any parameters specified at the beginning of the file |
| 125 data, filename = params[key] | 129 data, filename = params[key] |
| 126 lines = data.splitlines(True) | 130 lines = data.splitlines(True) |
| 127 for i, line in enumerate(lines): | 131 for i, line in enumerate(lines): |
| 128 if not re.search(r'^\s*[\w\-]+\s*=', line): | 132 if not re.search(r'^\s*[\w\-]+\s*=', line): |
| 129 break | 133 break |
| 130 name, value = line.split('=', 1) | 134 name, value = line.split('=', 1) |
| 131 params[name.strip()] = value.strip() | 135 params[name.strip()] = value.strip() |
| 132 lines[i] = '\n' | 136 lines[i] = '\n' |
| 133 params[key] = (''.join(lines), filename) | 137 params[key] = (''.join(lines), filename) |
| 134 | 138 |
| 135 def localize_string(self, page, name, default, comment, localedata, escapes) : | 139 def localize_string( |
| 140 self, page, name, default, comment, localedata, escapes): | |
| 141 | |
| 136 def escape(s): | 142 def escape(s): |
| 137 return re.sub(r'.', | 143 return re.sub(r'.', |
|
Vasily Kuznetsov
2017/03/08 17:31:44
This is also kind of hard to read but more importa
Jon Sonesen
2017/03/08 17:51:57
I agree here, but assumed it would require an issu
Vasily Kuznetsov
2017/03/09 12:33:27
Yeah, you're right.
| |
| 138 lambda match: escapes.get(match.group(0), match.group( 0)), | 144 lambda match: escapes.get(match.group(0), |
| 145 match.group(0)), | |
| 139 s, flags=re.S) | 146 s, flags=re.S) |
| 140 | 147 |
| 141 def re_escape(s): | 148 def re_escape(s): |
| 142 return re.escape(escape(s)) | 149 return re.escape(escape(s)) |
| 143 | 150 |
| 144 # Handle duplicated strings | 151 # Handle duplicated strings |
| 145 if default: | 152 if default: |
| 146 self._seen_defaults[(page, name)] = (default, comment) | 153 self._seen_defaults[(page, name)] = (default, comment) |
| 147 else: | 154 else: |
| 148 try: | 155 try: |
| 149 default, comment = self._seen_defaults[(page, name)] | 156 default, comment = self._seen_defaults[(page, name)] |
| 150 except KeyError: | 157 except KeyError: |
| 151 raise Exception('Text not yet defined for string %s on page %s' % | 158 raise Exception('Text not yet defined for string {} on page' |
| 152 (name, page)) | 159 '{}'.format(name, page)) |
| 153 | 160 |
| 154 # Extract tag attributes from default string | 161 # Extract tag attributes from default string |
| 155 default, saved_attributes, fixed_strings = self._attribute_parser.parse( default, self._params['page']) | 162 default, saved_attributes, fixed_strings = (self._attribute_parser |
|
Vasily Kuznetsov
2017/03/08 17:31:44
This looks kind of hard to read. How about this in
Jon Sonesen
2017/03/08 17:51:57
Yes that seems nicer, thank you!
| |
| 163 .parse(default, | |
| 164 self._params['page'] | |
| 165 )) | |
| 156 | 166 |
| 157 # Get translation | 167 # Get translation |
| 158 locale = self._params['locale'] | 168 locale = self._params['locale'] |
| 159 if locale == self._params['defaultlocale']: | 169 if locale == self._params['defaultlocale']: |
| 160 result = default | 170 result = default |
| 161 elif name in localedata: | 171 elif name in localedata: |
| 162 result = localedata[name].strip() | 172 result = localedata[name].strip() |
| 163 else: | 173 else: |
| 164 result = default | 174 result = default |
| 165 self.missing_translations += 1 | 175 self.missing_translations += 1 |
| 166 self.total_translations += 1 | 176 self.total_translations += 1 |
| 167 | 177 |
| 168 # Perform callback with the string if required, e.g. for the translation s script | 178 # Perform callback with the string if required, e.g. for the |
| 179 # translations script | |
| 169 callback = self._params['localized_string_callback'] | 180 callback = self._params['localized_string_callback'] |
| 170 if callback: | 181 if callback: |
| 171 callback(page, locale, name, result, comment, fixed_strings) | 182 callback(page, locale, name, result, comment, fixed_strings) |
| 172 | 183 |
| 173 # Insert fixed strings | 184 # Insert fixed strings |
| 174 for i, fixed_string in enumerate(fixed_strings, 1): | 185 for i, fixed_string in enumerate(fixed_strings, 1): |
| 175 result = result.replace('{%d}' % i, fixed_string) | 186 result = result.replace('{{{%d}}}'.format(i), fixed_string) |
| 176 | 187 |
| 177 # Insert attributes | 188 # Insert attributes |
| 178 result = escape(result) | 189 result = escape(result) |
| 179 | 190 |
| 180 def stringify_attribute((name, value)): | 191 def stringify_attribute((name, value)): |
| 181 return '%s="%s"' % ( | 192 return '{}="{}"'.format( |
| 182 escape(name), | 193 escape(name), |
| 183 escape(self.insert_localized_strings(value, {})) | 194 escape(self.insert_localized_strings(value, {})) |
| 184 ) | 195 ) |
| 185 | 196 |
| 186 for tag in self.whitelist: | 197 for tag in self.whitelist: |
| 187 allowed_contents = '(?:[^<>]|%s)' % '|'.join(( | 198 allowed_contents = '(?:[^<>]|{})'.format('|').join(( |
| 188 '<(?:%s[^<>]*?|/%s)>' % (t, t) | 199 '<(?:{}[^<>]*?|/{})>'.format(t, t) |
| 189 for t in map(re.escape, self.whitelist - {tag}) | 200 for t in map(re.escape, self.whitelist - {tag}) |
| 190 )) | 201 )) |
| 191 saved = saved_attributes.get(tag, []) | 202 saved = saved_attributes.get(tag, []) |
| 192 for attrs in saved: | 203 for attrs in saved: |
| 193 attrs = map(stringify_attribute, attrs) | 204 attrs = map(stringify_attribute, attrs) |
| 194 result = re.sub( | 205 result = re.sub( |
| 195 r'%s(%s*?)%s' % (re_escape('<%s>' % tag), allowed_contents, | 206 r'{}({}*?){}'.format(re_escape('<{}>'.format(tag)), |
| 196 re_escape('</%s>' % tag)), | 207 allowed_contents, |
| 197 lambda match: r'<%s%s>%s</%s>' % ( | 208 re_escape('</{}>'.format(tag))), |
| 209 lambda match: r'<{}{}>{}</{}>'.format( | |
| 198 tag, | 210 tag, |
| 199 ' ' + ' '.join(attrs) if attrs else '', | 211 ' ' + ' '.join(attrs) if attrs else '', |
| 200 match.group(1), | 212 match.group(1), |
| 201 tag | 213 tag |
| 202 ), | 214 ), |
| 203 result, 1, flags=re.S | 215 result, 1, flags=re.S |
| 204 ) | 216 ) |
| 205 result = re.sub( | 217 result = re.sub( |
| 206 r'%s(%s*?)%s' % (re_escape('<%s>' % tag), allowed_contents, | 218 r'{}({}*?){}'.format(re_escape('<{}>'.format(tag)), |
| 207 re_escape('</%s>' % tag)), | 219 allowed_contents, |
| 208 r'<%s>\1</%s>' % (tag, tag), | 220 re_escape('</{}>'.format(tag))), |
| 221 r'<{}>\1</{}>'.format(tag, tag), | |
| 209 result, flags=re.S | 222 result, flags=re.S |
| 210 ) | 223 ) |
| 211 return result | 224 return result |
| 212 | 225 |
| 213 def insert_localized_strings(self, text, escapes, to_html=lambda s: s): | 226 def insert_localized_strings(self, text, escapes, to_html=lambda s: s): |
| 214 def lookup_string(match): | 227 def lookup_string(match): |
| 215 name, comment, default = match.groups() | 228 name, comment, default = match.groups() |
| 216 if default: | 229 if default: |
| 217 default = to_html(default).strip() | 230 default = to_html(default).strip() |
| 218 return self.localize_string(self._params['page'], name, default, | 231 return self.localize_string(self._params['page'], name, default, |
| 219 comment, self._params['localedata'], esc apes) | 232 comment, self._params['localedata'], |
| 233 escapes) | |
| 220 | 234 |
| 221 return re.sub( | 235 return re.sub( |
| 222 r'{{\s*' | 236 r'{{\s*' |
| 223 r'([\w\-]+)' # String ID | 237 r'([\w\-]+)' # String ID |
| 224 r'(?:(?:\[(.*?)\])?' # Optional comment | 238 r'(?:(?:\[(.*?)\])?' # Optional comment |
| 225 r'\s+' | 239 r'\s+' |
| 226 r'((?:(?!{{).|' # Translatable text | 240 r'((?:(?!{{).|' # Translatable text |
| 227 r'{{(?:(?!}}).)*}}' # Nested translation | 241 r'{{(?:(?!}}).)*}}' # Nested translation |
| 228 r')*?)' | 242 r')*?)' |
| 229 r')?' | 243 r')?' |
| 230 r'}}', | 244 r'}}', |
| 231 lookup_string, | 245 lookup_string, |
| 232 text, | 246 text, |
| 233 flags=re.S | 247 flags=re.S |
| 234 ) | 248 ) |
| 235 | 249 |
| 236 def process_links(self, text): | 250 def process_links(self, text): |
| 237 def process_link(match): | 251 def process_link(match): |
| 238 pre, attr, url, post = match.groups() | 252 pre, attr, url, post = match.groups() |
| 239 url = jinja2.Markup(url).unescape() | 253 url = jinja2.Markup(url).unescape() |
| 240 | 254 |
| 241 locale, new_url = self._params['source'].resolve_link(url, self._par ams['locale']) | 255 locale, new_url = self._params['source']\ |
|
Vasily Kuznetsov
2017/03/08 17:31:44
PEP8 discourages line continuation with backslashe
Jon Sonesen
2017/03/08 17:51:57
oh yeah, I though i replaced all the back slashes
| |
| 242 if new_url != None: | 256 .resolve_link(url, self._params['locale']) |
| 257 if new_url is not None: | |
| 243 url = new_url | 258 url = new_url |
| 244 if attr == 'href': | 259 if attr == 'href': |
| 245 post += ' hreflang="%s"' % jinja2.Markup.escape(locale) | 260 post += ' hreflang="{}"'\ |
|
Vasily Kuznetsov
2017/03/08 17:31:44
Maybe we can use continuation with parentheses ins
Jon Sonesen
2017/03/08 17:51:57
yesh
| |
| 261 .format(jinja2.Markup.escape(locale)) | |
| 246 | 262 |
| 247 return ''.join((pre, jinja2.Markup.escape(url), post)) | 263 return ''.join((pre, jinja2.Markup.escape(url), post)) |
| 248 | 264 |
| 249 text = re.sub(r'(<a\s[^<>]*\b(href)=\")([^<>\"]+)(\")', process_link, te xt) | 265 text = re.sub(r'(<a\s[^<>]*\b(href)=\")([^<>\"]+)(\")', |
| 250 text = re.sub(r'(<img\s[^<>]*\b(src)=\")([^<>\"]+)(\")', process_link, t ext) | 266 process_link, text) |
| 267 text = re.sub(r'(<img\s[^<>]*\b(src)=\")([^<>\"]+)(\")', | |
| 268 process_link, text) | |
| 251 return text | 269 return text |
| 252 | 270 |
| 253 include_start_regex = '<' | 271 include_start_regex = '<' |
| 254 include_end_regex = '>' | 272 include_end_regex = '>' |
| 255 | 273 |
| 256 def resolve_includes(self, text): | 274 def resolve_includes(self, text): |
| 257 def resolve_include(match): | 275 def resolve_include(match): |
| 258 global converters | |
| 259 name = match.group(1) | 276 name = match.group(1) |
| 260 for format, converter_class in converters.iteritems(): | 277 for format_, converter_class in converters.iteritems(): |
| 261 if self._params['source'].has_include(name, format): | 278 if self._params['source'].has_include(name, format_): |
| 262 self._params['includedata'] = self._params['source'].read_in clude(name, format) | 279 self._params['includedata'] = self._params['source']\ |
| 263 converter = converter_class(self._params, key='includedata') | 280 .read_include(name, format) |
| 281 converter = converter_class(self._params, | |
| 282 key='includedata') | |
| 264 result = converter() | 283 result = converter() |
| 265 self.missing_translations += converter.missing_translations | 284 self.missing_translations += converter.missing_translations |
| 266 self.total_translations += converter.total_translations | 285 self.total_translations += converter.total_translations |
| 267 return result | 286 return result |
| 268 raise Exception('Failed to resolve include %s on page %s' % (name, s elf._params['page'])) | 287 raise Exception('Failed to resolve include {}' |
| 288 'on page {}'.format(name, self._params['page'])) | |
| 269 | 289 |
| 270 return re.sub( | 290 return re.sub( |
| 271 r'%s\?\s*include\s+([^\s<>"]+)\s*\?%s' % ( | 291 r'{}\?\s*include\s+([^\s<>"]+)\s*\?{}'.format( |
| 272 self.include_start_regex, | 292 self.include_start_regex, |
| 273 self.include_end_regex | 293 self.include_end_regex |
| 274 ), | 294 ), |
| 275 resolve_include, | 295 resolve_include, |
| 276 text | 296 text |
| 277 ) | 297 ) |
| 278 | 298 |
| 279 def __call__(self): | 299 def __call__(self): |
| 280 result = self.get_html(*self._params[self._key]) | 300 result = self.get_html(*self._params[self._key]) |
| 281 result = self.resolve_includes(result) | 301 result = self.resolve_includes(result) |
| 282 if self._key == 'pagedata': | 302 if self._key == 'pagedata': |
| 283 head = [] | 303 head = [] |
| 284 | 304 |
| 285 def add_to_head(match): | 305 def add_to_head(match): |
| 286 head.append(match.group(1)) | 306 head.append(match.group(1)) |
| 287 return '' | 307 return '' |
| 288 body = re.sub(r'<head>(.*?)</head>', add_to_head, result, flags=re.S ) | 308 body = re.sub(r'<head>(.*?)</head>', add_to_head, result, |
| 309 flags=re.S) | |
| 289 return ''.join(head), body | 310 return ''.join(head), body |
| 290 else: | 311 return result |
| 291 return result | |
| 292 | 312 |
| 293 | 313 |
| 294 class RawConverter(Converter): | 314 class RawConverter(Converter): |
| 295 def get_html(self, source, filename): | 315 def get_html(self, source, filename): |
| 296 result = self.insert_localized_strings(source, html_escapes) | 316 result = self.insert_localized_strings(source, html_escapes) |
| 297 result = self.process_links(result) | 317 result = self.process_links(result) |
| 298 return result | 318 return result |
| 299 | 319 |
| 300 | 320 |
| 301 class MarkdownConverter(Converter): | 321 class MarkdownConverter(Converter): |
| 302 include_start_regex = r'(?:%s|%s)' % ( | 322 include_start_regex = r'(?:{}|{})'.format( |
| 303 Converter.include_start_regex, | 323 Converter.include_start_regex, |
| 304 re.escape(jinja2.escape(Converter.include_start_regex)) | 324 re.escape(jinja2.escape(Converter.include_start_regex)) |
| 305 ) | 325 ) |
| 306 include_end_regex = r'(?:%s|%s)' % ( | 326 include_end_regex = r'(?:{}|{})'.format( |
| 307 Converter.include_end_regex, | 327 Converter.include_end_regex, |
| 308 re.escape(jinja2.escape(Converter.include_end_regex)) | 328 re.escape(jinja2.escape(Converter.include_end_regex)) |
| 309 ) | 329 ) |
| 310 | 330 |
| 311 def get_html(self, source, filename): | 331 def get_html(self, source, filename): |
| 312 def remove_unnecessary_entities(match): | 332 def remove_unnecessary_entities(match): |
| 313 char = unichr(int(match.group(1))) | 333 char = unichr(int(match.group(1))) |
| 314 if char in html_escapes: | 334 if char in html_escapes: |
| 315 return match.group(0) | 335 return match.group(0) |
| 316 else: | 336 return char |
| 317 return char | |
| 318 | 337 |
| 319 escapes = {} | 338 escapes = {} |
| 320 md = markdown.Markdown(output='html5', extensions=['extra']) | 339 md = markdown.Markdown(output='html5', extensions=['extra']) |
| 321 for char in md.ESCAPED_CHARS: | 340 for char in md.ESCAPED_CHARS: |
| 322 escapes[char] = '&#' + str(ord(char)) + ';' | 341 escapes[char] = '&#{};'.format(str(ord(char))) |
| 323 for key, value in html_escapes.iteritems(): | 342 for key, value in html_escapes.iteritems(): |
| 324 escapes[key] = value | 343 escapes[key] = value |
| 325 | 344 |
| 326 md.preprocessors['html_block'].markdown_in_raw = True | 345 md.preprocessors['html_block'].markdown_in_raw = True |
| 327 | 346 |
| 328 def to_html(s): | 347 def to_html(s): |
| 329 return re.sub(r'</?p>', '', md.convert(s)) | 348 return re.sub(r'</?p>', '', md.convert(s)) |
| 330 | 349 |
| 331 result = self.insert_localized_strings(source, escapes, to_html) | 350 result = self.insert_localized_strings(source, escapes, to_html) |
| 332 result = md.convert(result) | 351 result = md.convert(result) |
| (...skipping 22 matching lines...) Expand all Loading... | |
| 355 'translate': self.translate, | 374 'translate': self.translate, |
| 356 'linkify': self.linkify, | 375 'linkify': self.linkify, |
| 357 'toclist': self.toclist, | 376 'toclist': self.toclist, |
| 358 } | 377 } |
| 359 | 378 |
| 360 globals = { | 379 globals = { |
| 361 'get_string': self.get_string, | 380 'get_string': self.get_string, |
| 362 'get_page_content': self.get_page_content, | 381 'get_page_content': self.get_page_content, |
| 363 } | 382 } |
| 364 | 383 |
| 365 for dirname, dictionary in [('filters', filters), ('globals', globals)]: | 384 for dirname, dictionary in [('filters', filters), |
| 385 ('globals', globals)]: | |
| 366 for filename in self._params['source'].list_files(dirname): | 386 for filename in self._params['source'].list_files(dirname): |
| 367 root, ext = os.path.splitext(filename) | 387 root, ext = os.path.splitext(filename) |
| 368 if ext.lower() != '.py': | 388 if ext.lower() != '.py': |
| 369 continue | 389 continue |
| 370 | 390 |
| 371 path = '%s/%s' % (dirname, filename) | 391 path = os.path.join(dirname, filename) |
| 372 namespace = self._params['source'].exec_file(path) | 392 namespace = self._params['source'].exec_file(path) |
| 373 | 393 |
| 374 name = os.path.basename(root) | 394 name = os.path.basename(root) |
| 375 try: | 395 try: |
| 376 dictionary[name] = namespace[name] | 396 dictionary[name] = namespace[name] |
| 377 except KeyError: | 397 except KeyError: |
| 378 raise Exception('Expected symbol %r not found in %r' % (name , path)) | 398 raise Exception('Expected symbol {} not found' |
| 399 'in {}'.format(name, path)) | |
| 379 | 400 |
| 380 self._env = jinja2.Environment(loader=SourceTemplateLoader(self._params[ 'source']), autoescape=True) | 401 self._env = jinja2.Environment( |
| 402 loader=SourceTemplateLoader(self._params['source']), | |
| 403 autoescape=True) | |
| 381 self._env.filters.update(filters) | 404 self._env.filters.update(filters) |
| 382 self._env.globals.update(globals) | 405 self._env.globals.update(globals) |
| 383 | 406 |
| 384 def get_html(self, source, filename): | 407 def get_html(self, source, filename): |
| 385 env = self._env | 408 env = self._env |
| 386 code = env.compile(source, None, filename) | 409 code = env.compile(source, None, filename) |
| 387 template = jinja2.Template.from_code(env, code, env.globals) | 410 template = jinja2.Template.from_code(env, code, env.globals) |
| 388 | 411 |
| 389 try: | 412 try: |
| 390 module = template.make_module(self._params) | 413 module = template.make_module(self._params) |
| (...skipping 11 matching lines...) Expand all Loading... | |
| 402 def translate(self, default, name, comment=None): | 425 def translate(self, default, name, comment=None): |
| 403 return jinja2.Markup(self.localize_string( | 426 return jinja2.Markup(self.localize_string( |
| 404 self._params['page'], name, default, comment, | 427 self._params['page'], name, default, comment, |
| 405 self._params['localedata'], html_escapes | 428 self._params['localedata'], html_escapes |
| 406 )) | 429 )) |
| 407 | 430 |
| 408 def get_string(self, name, page=None): | 431 def get_string(self, name, page=None): |
| 409 if page is None: | 432 if page is None: |
| 410 page = self._params['page'] | 433 page = self._params['page'] |
| 411 | 434 |
| 412 localedata = self._params['source'].read_locale(self._params['locale'], page) | 435 localedata = self._params['source'].read_locale(self._params['locale'], |
| 436 page) | |
| 413 default = localedata[name] | 437 default = localedata[name] |
| 414 return jinja2.Markup(self.localize_string( | 438 return jinja2.Markup(self.localize_string( |
| 415 page, name, default, '', localedata, html_escapes | 439 page, name, default, '', localedata, html_escapes |
| 416 )) | 440 )) |
| 417 | 441 |
| 418 def get_page_content(self, page, locale=None): | 442 def get_page_content(self, page, locale=None): |
| 419 from cms.utils import get_page_params | 443 from cms.utils import get_page_params |
| 420 | 444 |
| 421 if locale is None: | 445 if locale is None: |
| 422 locale = self._params['locale'] | 446 locale = self._params['locale'] |
| 423 return get_page_params(self._params['source'], locale, page) | 447 return get_page_params(self._params['source'], locale, page) |
| 424 | 448 |
| 425 def linkify(self, page, locale=None, **attrs): | 449 def linkify(self, page, locale=None, **attrs): |
| 426 if locale is None: | 450 if locale is None: |
| 427 locale = self._params['locale'] | 451 locale = self._params['locale'] |
| 428 | 452 |
| 429 locale, url = self._params['source'].resolve_link(page, locale) | 453 locale, url = self._params['source'].resolve_link(page, locale) |
| 430 return jinja2.Markup('<a%s>' % ''.join( | 454 return jinja2.Markup('<a{}>'.format(''.join( |
| 431 ' %s="%s"' % (name, jinja2.escape(value)) for name, value in [ | 455 ' {}="{}"'.format(name, jinja2.escape(value)) for name, value in [ |
| 432 ('href', url), | 456 ('href', url), |
| 433 ('hreflang', locale) | 457 ('hreflang', locale) |
| 434 ] + attrs.items() | 458 ] + attrs.items() |
| 435 )) | 459 ))) |
| 436 | 460 |
| 437 def toclist(self, content): | 461 def toclist(self, content): |
| 462 toc_re = r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h\1>' | |
| 438 flat = [] | 463 flat = [] |
| 439 for match in re.finditer(r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h \1>', content, re.S): | 464 for match in re.finditer(toc_re, content, re.S): |
| 440 flat.append({ | 465 flat.append({ |
| 441 'level': int(match.group(1)), | 466 'level': int(match.group(1)), |
| 442 'anchor': jinja2.Markup(match.group(2)).unescape(), | 467 'anchor': jinja2.Markup(match.group(2)).unescape(), |
| 443 'title': jinja2.Markup(match.group(3)).unescape(), | 468 'title': jinja2.Markup(match.group(3)).unescape(), |
| 444 'subitems': [], | 469 'subitems': [], |
| 445 }) | 470 }) |
| 446 | 471 |
| 447 structured = [] | 472 structured = [] |
| 448 stack = [{'level': 0, 'subitems': structured}] | 473 stack = [{'level': 0, 'subitems': structured}] |
| 449 for item in flat: | 474 for item in flat: |
| 450 while stack[-1]['level'] >= item['level']: | 475 while stack[-1]['level'] >= item['level']: |
| 451 stack.pop() | 476 stack.pop() |
| 452 stack[-1]['subitems'].append(item) | 477 stack[-1]['subitems'].append(item) |
| 453 stack.append(item) | 478 stack.append(item) |
| 454 return structured | 479 return structured |
| 455 | 480 |
| 456 converters = { | 481 converters = { |
| 457 'html': RawConverter, | 482 'html': RawConverter, |
| 458 'md': MarkdownConverter, | 483 'md': MarkdownConverter, |
| 459 'tmpl': TemplateConverter, | 484 'tmpl': TemplateConverter, |
| 460 } | 485 } |
| OLD | NEW |
« no previous file with comments
|
« no previous file
|
tox.ini » ('j')
|
no next file with comments »
