| 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 are |
| 25 # inserted into the <head> tag | 25 # 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 else: |
| 33 return orig_isBlockLevel(tag) | 33 return orig_isBlockLevel(tag) |
| 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 |
| 44 | 44 |
| 45 class AttributeParser(HTMLParser.HTMLParser): | 45 class AttributeParser(HTMLParser.HTMLParser): |
| 46 _string = None | 46 _string = None |
| 47 _inside_fixed = False | 47 _inside_fixed = False |
| 48 _fixed_strings = None | 48 _fixed_strings = None |
| 49 _attrs = None | 49 _attrs = None |
| 50 | 50 |
| 51 def __init__(self, whitelist): | 51 def __init__(self, whitelist): |
| 52 self._whitelist = whitelist | 52 self._whitelist = whitelist |
| 53 | 53 |
| 54 def parse(self, text, pagename): | 54 def parse(self, text, pagename): |
| 55 self.reset() | 55 self.reset() |
| 56 self._string = [] | 56 self._string = [] |
| 57 self._fixed_strings = [] | 57 self._fixed_strings = [] |
| 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), self._attrs, [''.join(s) for s in self
._fixed_strings] |
| 69 finally: | 69 finally: |
| 70 self._string = None | 70 self._string = None |
| 71 self._attrs = None | 71 self._attrs = None |
| 72 self._pagename = None | 72 self._pagename = None |
| 73 self._inside_fixed = False | 73 self._inside_fixed = False |
| 74 self._fixed_strings = None | 74 self._fixed_strings = None |
| 75 | 75 |
| 76 def handle_starttag(self, tag, attrs): | 76 def handle_starttag(self, tag, attrs): |
| 77 if self._inside_fixed: | 77 if self._inside_fixed: |
| 78 raise Exception("Unexpected HTML tag '%s' inside a fixed string on p
age %s" % (tag, self._pagename)) | 78 raise Exception("Unexpected HTML tag '%s' inside a fixed string on p
age %s" % (tag, self._pagename)) |
| 79 elif tag == "fix": | 79 elif tag == 'fix': |
| 80 self._inside_fixed = True | 80 self._inside_fixed = True |
| 81 self._fixed_strings.append([]) | 81 self._fixed_strings.append([]) |
| 82 elif tag in self._whitelist: | 82 elif tag in self._whitelist: |
| 83 self._attrs.setdefault(tag, []).append(attrs) | 83 self._attrs.setdefault(tag, []).append(attrs) |
| 84 self._string.append("<%s>" % tag) | 84 self._string.append('<%s>' % tag) |
| 85 else: | 85 else: |
| 86 raise Exception("Unexpected HTML tag '%s' in localizable string on p
age %s" % (tag, self._pagename)) | 86 raise Exception("Unexpected HTML tag '%s' in localizable string on p
age %s" % (tag, self._pagename)) |
| 87 | 87 |
| 88 def handle_endtag(self, tag): | 88 def handle_endtag(self, tag): |
| 89 if tag == "fix": | 89 if tag == 'fix': |
| 90 self._string.append("{%d}" % len(self._fixed_strings)) | 90 self._string.append('{%d}' % len(self._fixed_strings)) |
| 91 self._inside_fixed = False | 91 self._inside_fixed = False |
| 92 else: | 92 else: |
| 93 self._string.append("</%s>" % tag) | 93 self._string.append('</%s>' % tag) |
| 94 | 94 |
| 95 def _append_text(self, s): | 95 def _append_text(self, s): |
| 96 if self._inside_fixed: | 96 if self._inside_fixed: |
| 97 self._fixed_strings[-1].append(s) | 97 self._fixed_strings[-1].append(s) |
| 98 else: | 98 else: |
| 99 self._string.append(s) | 99 self._string.append(s) |
| 100 | 100 |
| 101 def handle_data(self, data): | 101 def handle_data(self, data): |
| 102 # Note: lack of escaping here is intentional. The result is a locale str
ing, | 102 # Note: lack of escaping here is intentional. The result is a locale str
ing, |
| 103 # HTML escaping is applied when this string is inserted into the documen
t. | 103 # HTML escaping is applied when this string is inserted into the documen
t. |
| 104 self._append_text(data) | 104 self._append_text(data) |
| 105 | 105 |
| 106 def handle_entityref(self, name): | 106 def handle_entityref(self, name): |
| 107 self._append_text(self.unescape("&%s;" % name)) | 107 self._append_text(self.unescape('&%s;' % name)) |
| 108 | 108 |
| 109 def handle_charref(self, name): | 109 def handle_charref(self, name): |
| 110 self._append_text(self.unescape("&#%s;" % name)) | 110 self._append_text(self.unescape('&#%s;' % name)) |
| 111 | 111 |
| 112 | 112 |
| 113 class Converter: | 113 class Converter: |
| 114 whitelist = {"a", "em", "sup", "strong", "code", "span"} | 114 whitelist = {'a', 'em', 'sup', 'strong', 'code', 'span'} |
| 115 missing_translations = 0 | 115 missing_translations = 0 |
| 116 total_translations = 0 | 116 total_translations = 0 |
| 117 | 117 |
| 118 def __init__(self, params, key="pagedata"): | 118 def __init__(self, params, key='pagedata'): |
| 119 self._params = params | 119 self._params = params |
| 120 self._key = key | 120 self._key = key |
| 121 self._attribute_parser = AttributeParser(self.whitelist) | 121 self._attribute_parser = AttributeParser(self.whitelist) |
| 122 self._seen_defaults = {} | 122 self._seen_defaults = {} |
| 123 | 123 |
| 124 # Read in any parameters specified at the beginning of the file | 124 # Read in any parameters specified at the beginning of the file |
| 125 data, filename = params[key] | 125 data, filename = params[key] |
| 126 lines = data.splitlines(True) | 126 lines = data.splitlines(True) |
| 127 for i, line in enumerate(lines): | 127 for i, line in enumerate(lines): |
| 128 if not re.search(r"^\s*[\w\-]+\s*=", line): | 128 if not re.search(r'^\s*[\w\-]+\s*=', line): |
| 129 break | 129 break |
| 130 name, value = line.split("=", 1) | 130 name, value = line.split('=', 1) |
| 131 params[name.strip()] = value.strip() | 131 params[name.strip()] = value.strip() |
| 132 lines[i] = "\n" | 132 lines[i] = '\n' |
| 133 params[key] = ("".join(lines), filename) | 133 params[key] = (''.join(lines), filename) |
| 134 | 134 |
| 135 def localize_string(self, page, name, default, comment, localedata, escapes)
: | 135 def localize_string(self, page, name, default, comment, localedata, escapes)
: |
| 136 def escape(s): | 136 def escape(s): |
| 137 return re.sub(r".", | 137 return re.sub(r'.', |
| 138 lambda match: escapes.get(match.group(0), match.group(
0)), | 138 lambda match: escapes.get(match.group(0), match.group(
0)), |
| 139 s, flags=re.S) | 139 s, flags=re.S) |
| 140 | 140 |
| 141 def re_escape(s): | 141 def re_escape(s): |
| 142 return re.escape(escape(s)) | 142 return re.escape(escape(s)) |
| 143 | 143 |
| 144 # Handle duplicated strings | 144 # Handle duplicated strings |
| 145 if default: | 145 if default: |
| 146 self._seen_defaults[(page, name)] = (default, comment) | 146 self._seen_defaults[(page, name)] = (default, comment) |
| 147 else: | 147 else: |
| 148 try: | 148 try: |
| 149 default, comment = self._seen_defaults[(page, name)] | 149 default, comment = self._seen_defaults[(page, name)] |
| 150 except KeyError: | 150 except KeyError: |
| 151 raise Exception("Text not yet defined for string %s on page %s"
% | 151 raise Exception('Text not yet defined for string %s on page %s'
% |
| 152 (name, page)) | 152 (name, page)) |
| 153 | 153 |
| 154 # Extract tag attributes from default string | 154 # Extract tag attributes from default string |
| 155 default, saved_attributes, fixed_strings = self._attribute_parser.parse(
default, self._params["page"]) | 155 default, saved_attributes, fixed_strings = self._attribute_parser.parse(
default, self._params['page']) |
| 156 | 156 |
| 157 # Get translation | 157 # Get translation |
| 158 locale = self._params["locale"] | 158 locale = self._params['locale'] |
| 159 if locale == self._params["defaultlocale"]: | 159 if locale == self._params['defaultlocale']: |
| 160 result = default | 160 result = default |
| 161 elif name in localedata: | 161 elif name in localedata: |
| 162 result = localedata[name].strip() | 162 result = localedata[name].strip() |
| 163 else: | 163 else: |
| 164 result = default | 164 result = default |
| 165 self.missing_translations += 1 | 165 self.missing_translations += 1 |
| 166 self.total_translations += 1 | 166 self.total_translations += 1 |
| 167 | 167 |
| 168 # Perform callback with the string if required, e.g. for the translation
s script | 168 # Perform callback with the string if required, e.g. for the translation
s script |
| 169 callback = self._params["localized_string_callback"] | 169 callback = self._params['localized_string_callback'] |
| 170 if callback: | 170 if callback: |
| 171 callback(page, locale, name, result, comment, fixed_strings) | 171 callback(page, locale, name, result, comment, fixed_strings) |
| 172 | 172 |
| 173 # Insert fixed strings | 173 # Insert fixed strings |
| 174 for i, fixed_string in enumerate(fixed_strings, 1): | 174 for i, fixed_string in enumerate(fixed_strings, 1): |
| 175 result = result.replace("{%d}" % i, fixed_string) | 175 result = result.replace('{%d}' % i, fixed_string) |
| 176 | 176 |
| 177 # Insert attributes | 177 # Insert attributes |
| 178 result = escape(result) | 178 result = escape(result) |
| 179 | 179 |
| 180 def stringify_attribute((name, value)): | 180 def stringify_attribute((name, value)): |
| 181 return '%s="%s"' % ( | 181 return '%s="%s"' % ( |
| 182 escape(name), | 182 escape(name), |
| 183 escape(self.insert_localized_strings(value, {})) | 183 escape(self.insert_localized_strings(value, {})) |
| 184 ) | 184 ) |
| 185 | 185 |
| 186 for tag in self.whitelist: | 186 for tag in self.whitelist: |
| 187 allowed_contents = "(?:[^<>]|%s)" % "|".join(( | 187 allowed_contents = '(?:[^<>]|%s)' % '|'.join(( |
| 188 "<(?:%s[^<>]*?|/%s)>" % (t, t) | 188 '<(?:%s[^<>]*?|/%s)>' % (t, t) |
| 189 for t in map(re.escape, self.whitelist - {tag}) | 189 for t in map(re.escape, self.whitelist - {tag}) |
| 190 )) | 190 )) |
| 191 saved = saved_attributes.get(tag, []) | 191 saved = saved_attributes.get(tag, []) |
| 192 for attrs in saved: | 192 for attrs in saved: |
| 193 attrs = map(stringify_attribute, attrs) | 193 attrs = map(stringify_attribute, attrs) |
| 194 result = re.sub( | 194 result = re.sub( |
| 195 r"%s(%s*?)%s" % (re_escape("<%s>" % tag), allowed_contents, | 195 r'%s(%s*?)%s' % (re_escape('<%s>' % tag), allowed_contents, |
| 196 re_escape("</%s>" % tag)), | 196 re_escape('</%s>' % tag)), |
| 197 lambda match: r'<%s%s>%s</%s>' % ( | 197 lambda match: r'<%s%s>%s</%s>' % ( |
| 198 tag, | 198 tag, |
| 199 " " + " ".join(attrs) if attrs else "", | 199 ' ' + ' '.join(attrs) if attrs else '', |
| 200 match.group(1), | 200 match.group(1), |
| 201 tag | 201 tag |
| 202 ), | 202 ), |
| 203 result, 1, flags=re.S | 203 result, 1, flags=re.S |
| 204 ) | 204 ) |
| 205 result = re.sub( | 205 result = re.sub( |
| 206 r"%s(%s*?)%s" % (re_escape("<%s>" % tag), allowed_contents, | 206 r'%s(%s*?)%s' % (re_escape('<%s>' % tag), allowed_contents, |
| 207 re_escape("</%s>" % tag)), | 207 re_escape('</%s>' % tag)), |
| 208 r"<%s>\1</%s>" % (tag, tag), | 208 r'<%s>\1</%s>' % (tag, tag), |
| 209 result, flags=re.S | 209 result, flags=re.S |
| 210 ) | 210 ) |
| 211 return result | 211 return result |
| 212 | 212 |
| 213 def insert_localized_strings(self, text, escapes, to_html=lambda s: s): | 213 def insert_localized_strings(self, text, escapes, to_html=lambda s: s): |
| 214 def lookup_string(match): | 214 def lookup_string(match): |
| 215 name, comment, default = match.groups() | 215 name, comment, default = match.groups() |
| 216 if default: | 216 if default: |
| 217 default = to_html(default).strip() | 217 default = to_html(default).strip() |
| 218 return self.localize_string(self._params["page"], name, default, | 218 return self.localize_string(self._params['page'], name, default, |
| 219 comment, self._params["localedata"], esc
apes) | 219 comment, self._params['localedata'], esc
apes) |
| 220 | 220 |
| 221 return re.sub( | 221 return re.sub( |
| 222 r"{{\s*" | 222 r'{{\s*' |
| 223 r"([\w\-]+)" # String ID | 223 r'([\w\-]+)' # String ID |
| 224 r"(?:(?:\[(.*?)\])?" # Optional comment | 224 r'(?:(?:\[(.*?)\])?' # Optional comment |
| 225 r"\s+" | 225 r'\s+' |
| 226 r"((?:(?!{{).|" # Translatable text | 226 r'((?:(?!{{).|' # Translatable text |
| 227 r"{{(?:(?!}}).)*}}" # Nested translation | 227 r'{{(?:(?!}}).)*}}' # Nested translation |
| 228 r")*?)" | 228 r')*?)' |
| 229 r")?" | 229 r')?' |
| 230 r"}}", | 230 r'}}', |
| 231 lookup_string, | 231 lookup_string, |
| 232 text, | 232 text, |
| 233 flags=re.S | 233 flags=re.S |
| 234 ) | 234 ) |
| 235 | 235 |
| 236 def process_links(self, text): | 236 def process_links(self, text): |
| 237 def process_link(match): | 237 def process_link(match): |
| 238 pre, attr, url, post = match.groups() | 238 pre, attr, url, post = match.groups() |
| 239 url = jinja2.Markup(url).unescape() | 239 url = jinja2.Markup(url).unescape() |
| 240 | 240 |
| 241 locale, new_url = self._params["source"].resolve_link(url, self._par
ams["locale"]) | 241 locale, new_url = self._params['source'].resolve_link(url, self._par
ams['locale']) |
| 242 if new_url != None: | 242 if new_url != None: |
| 243 url = new_url | 243 url = new_url |
| 244 if attr == "href": | 244 if attr == 'href': |
| 245 post += ' hreflang="%s"' % jinja2.Markup.escape(locale) | 245 post += ' hreflang="%s"' % jinja2.Markup.escape(locale) |
| 246 | 246 |
| 247 return "".join((pre, jinja2.Markup.escape(url), post)) | 247 return ''.join((pre, jinja2.Markup.escape(url), post)) |
| 248 | 248 |
| 249 text = re.sub(r"(<a\s[^<>]*\b(href)=\")([^<>\"]+)(\")", process_link, te
xt) | 249 text = re.sub(r'(<a\s[^<>]*\b(href)=\")([^<>\"]+)(\")', process_link, te
xt) |
| 250 text = re.sub(r"(<img\s[^<>]*\b(src)=\")([^<>\"]+)(\")", process_link, t
ext) | 250 text = re.sub(r'(<img\s[^<>]*\b(src)=\")([^<>\"]+)(\")', process_link, t
ext) |
| 251 return text | 251 return text |
| 252 | 252 |
| 253 include_start_regex = '<' | 253 include_start_regex = '<' |
| 254 include_end_regex = '>' | 254 include_end_regex = '>' |
| 255 | 255 |
| 256 def resolve_includes(self, text): | 256 def resolve_includes(self, text): |
| 257 def resolve_include(match): | 257 def resolve_include(match): |
| 258 global converters | 258 global converters |
| 259 name = match.group(1) | 259 name = match.group(1) |
| 260 for format, converter_class in converters.iteritems(): | 260 for format, converter_class in converters.iteritems(): |
| 261 if self._params["source"].has_include(name, format): | 261 if self._params['source'].has_include(name, format): |
| 262 self._params["includedata"] = self._params["source"].read_in
clude(name, format) | 262 self._params['includedata'] = self._params['source'].read_in
clude(name, format) |
| 263 converter = converter_class(self._params, key="includedata") | 263 converter = converter_class(self._params, key='includedata') |
| 264 result = converter() | 264 result = converter() |
| 265 self.missing_translations += converter.missing_translations | 265 self.missing_translations += converter.missing_translations |
| 266 self.total_translations += converter.total_translations | 266 self.total_translations += converter.total_translations |
| 267 return result | 267 return result |
| 268 raise Exception("Failed to resolve include %s on page %s" % (name, s
elf._params["page"])) | 268 raise Exception('Failed to resolve include %s on page %s' % (name, s
elf._params['page'])) |
| 269 | 269 |
| 270 return re.sub( | 270 return re.sub( |
| 271 r'%s\?\s*include\s+([^\s<>"]+)\s*\?%s' % ( | 271 r'%s\?\s*include\s+([^\s<>"]+)\s*\?%s' % ( |
| 272 self.include_start_regex, | 272 self.include_start_regex, |
| 273 self.include_end_regex | 273 self.include_end_regex |
| 274 ), | 274 ), |
| 275 resolve_include, | 275 resolve_include, |
| 276 text | 276 text |
| 277 ) | 277 ) |
| 278 | 278 |
| 279 def __call__(self): | 279 def __call__(self): |
| 280 result = self.get_html(*self._params[self._key]) | 280 result = self.get_html(*self._params[self._key]) |
| 281 result = self.resolve_includes(result) | 281 result = self.resolve_includes(result) |
| 282 if self._key == "pagedata": | 282 if self._key == 'pagedata': |
| 283 head = [] | 283 head = [] |
| 284 | 284 |
| 285 def add_to_head(match): | 285 def add_to_head(match): |
| 286 head.append(match.group(1)) | 286 head.append(match.group(1)) |
| 287 return "" | 287 return '' |
| 288 body = re.sub(r"<head>(.*?)</head>", add_to_head, result, flags=re.S
) | 288 body = re.sub(r'<head>(.*?)</head>', add_to_head, result, flags=re.S
) |
| 289 return "".join(head), body | 289 return ''.join(head), body |
| 290 else: | 290 else: |
| 291 return result | 291 return result |
| 292 | 292 |
| 293 | 293 |
| 294 class RawConverter(Converter): | 294 class RawConverter(Converter): |
| 295 def get_html(self, source, filename): | 295 def get_html(self, source, filename): |
| 296 result = self.insert_localized_strings(source, html_escapes) | 296 result = self.insert_localized_strings(source, html_escapes) |
| 297 result = self.process_links(result) | 297 result = self.process_links(result) |
| 298 return result | 298 return result |
| 299 | 299 |
| (...skipping 11 matching lines...) Expand all Loading... |
| 311 def get_html(self, source, filename): | 311 def get_html(self, source, filename): |
| 312 def remove_unnecessary_entities(match): | 312 def remove_unnecessary_entities(match): |
| 313 char = unichr(int(match.group(1))) | 313 char = unichr(int(match.group(1))) |
| 314 if char in html_escapes: | 314 if char in html_escapes: |
| 315 return match.group(0) | 315 return match.group(0) |
| 316 else: | 316 else: |
| 317 return char | 317 return char |
| 318 | 318 |
| 319 escapes = {} | 319 escapes = {} |
| 320 for char in markdown.Markdown.ESCAPED_CHARS: | 320 for char in markdown.Markdown.ESCAPED_CHARS: |
| 321 escapes[char] = "&#" + str(ord(char)) + ";" | 321 escapes[char] = '&#' + str(ord(char)) + ';' |
| 322 for key, value in html_escapes.iteritems(): | 322 for key, value in html_escapes.iteritems(): |
| 323 escapes[key] = value | 323 escapes[key] = value |
| 324 | 324 |
| 325 md = markdown.Markdown(output="html5", extensions=["extra"]) | 325 md = markdown.Markdown(output='html5', extensions=['extra']) |
| 326 md.preprocessors["html_block"].markdown_in_raw = True | 326 md.preprocessors['html_block'].markdown_in_raw = True |
| 327 | 327 |
| 328 def to_html(s): | 328 def to_html(s): |
| 329 return re.sub(r'</?p>', '', md.convert(s)) | 329 return re.sub(r'</?p>', '', md.convert(s)) |
| 330 | 330 |
| 331 result = self.insert_localized_strings(source, escapes, to_html) | 331 result = self.insert_localized_strings(source, escapes, to_html) |
| 332 result = md.convert(result) | 332 result = md.convert(result) |
| 333 result = re.sub(r"&#(\d+);", remove_unnecessary_entities, result) | 333 result = re.sub(r'&#(\d+);', remove_unnecessary_entities, result) |
| 334 result = self.process_links(result) | 334 result = self.process_links(result) |
| 335 return result | 335 return result |
| 336 | 336 |
| 337 | 337 |
| 338 class SourceTemplateLoader(jinja2.BaseLoader): | 338 class SourceTemplateLoader(jinja2.BaseLoader): |
| 339 def __init__(self, source): | 339 def __init__(self, source): |
| 340 self.source = source | 340 self.source = source |
| 341 | 341 |
| 342 def get_source(self, environment, template): | 342 def get_source(self, environment, template): |
| 343 try: | 343 try: |
| 344 result = self.source.read_file(template + ".tmpl") | 344 result = self.source.read_file(template + '.tmpl') |
| 345 except Exception: | 345 except Exception: |
| 346 raise jinja2.TemplateNotFound(template) | 346 raise jinja2.TemplateNotFound(template) |
| 347 return result + (None,) | 347 return result + (None,) |
| 348 | 348 |
| 349 | 349 |
| 350 class TemplateConverter(Converter): | 350 class TemplateConverter(Converter): |
| 351 def __init__(self, *args, **kwargs): | 351 def __init__(self, *args, **kwargs): |
| 352 Converter.__init__(self, *args, **kwargs) | 352 Converter.__init__(self, *args, **kwargs) |
| 353 | 353 |
| 354 filters = { | 354 filters = { |
| 355 "translate": self.translate, | 355 'translate': self.translate, |
| 356 "linkify": self.linkify, | 356 'linkify': self.linkify, |
| 357 "toclist": self.toclist, | 357 'toclist': self.toclist, |
| 358 } | 358 } |
| 359 | 359 |
| 360 globals = { | 360 globals = { |
| 361 "get_string": self.get_string, | 361 'get_string': self.get_string, |
| 362 "get_page_content": self.get_page_content, | 362 'get_page_content': self.get_page_content, |
| 363 } | 363 } |
| 364 | 364 |
| 365 for dirname, dictionary in [("filters", filters), ("globals", globals)]: | 365 for dirname, dictionary in [('filters', filters), ('globals', globals)]: |
| 366 for filename in self._params["source"].list_files(dirname): | 366 for filename in self._params['source'].list_files(dirname): |
| 367 root, ext = os.path.splitext(filename) | 367 root, ext = os.path.splitext(filename) |
| 368 if ext.lower() != ".py": | 368 if ext.lower() != '.py': |
| 369 continue | 369 continue |
| 370 | 370 |
| 371 path = "%s/%s" % (dirname, filename) | 371 path = '%s/%s' % (dirname, filename) |
| 372 namespace = self._params["source"].exec_file(path) | 372 namespace = self._params['source'].exec_file(path) |
| 373 | 373 |
| 374 name = os.path.basename(root) | 374 name = os.path.basename(root) |
| 375 try: | 375 try: |
| 376 dictionary[name] = namespace[name] | 376 dictionary[name] = namespace[name] |
| 377 except KeyError: | 377 except KeyError: |
| 378 raise Exception("Expected symbol %r not found in %r" % (name
, path)) | 378 raise Exception('Expected symbol %r not found in %r' % (name
, path)) |
| 379 | 379 |
| 380 self._env = jinja2.Environment(loader=SourceTemplateLoader(self._params[
"source"]), autoescape=True) | 380 self._env = jinja2.Environment(loader=SourceTemplateLoader(self._params[
'source']), autoescape=True) |
| 381 self._env.filters.update(filters) | 381 self._env.filters.update(filters) |
| 382 self._env.globals.update(globals) | 382 self._env.globals.update(globals) |
| 383 | 383 |
| 384 def get_html(self, source, filename): | 384 def get_html(self, source, filename): |
| 385 env = self._env | 385 env = self._env |
| 386 code = env.compile(source, None, filename) | 386 code = env.compile(source, None, filename) |
| 387 template = jinja2.Template.from_code(env, code, env.globals) | 387 template = jinja2.Template.from_code(env, code, env.globals) |
| 388 | 388 |
| 389 try: | 389 try: |
| 390 module = template.make_module(self._params) | 390 module = template.make_module(self._params) |
| 391 except Exception: | 391 except Exception: |
| 392 env.handle_exception() | 392 env.handle_exception() |
| 393 | 393 |
| 394 for key, value in module.__dict__.iteritems(): | 394 for key, value in module.__dict__.iteritems(): |
| 395 if not key.startswith("_"): | 395 if not key.startswith('_'): |
| 396 self._params[key] = value | 396 self._params[key] = value |
| 397 | 397 |
| 398 result = unicode(module) | 398 result = unicode(module) |
| 399 result = self.process_links(result) | 399 result = self.process_links(result) |
| 400 return result | 400 return result |
| 401 | 401 |
| 402 def translate(self, default, name, comment=None): | 402 def translate(self, default, name, comment=None): |
| 403 return jinja2.Markup(self.localize_string( | 403 return jinja2.Markup(self.localize_string( |
| 404 self._params["page"], name, default, comment, | 404 self._params['page'], name, default, comment, |
| 405 self._params["localedata"], html_escapes | 405 self._params['localedata'], html_escapes |
| 406 )) | 406 )) |
| 407 | 407 |
| 408 def get_string(self, name, page=None): | 408 def get_string(self, name, page=None): |
| 409 if page is None: | 409 if page is None: |
| 410 page = self._params["page"] | 410 page = self._params['page'] |
| 411 | 411 |
| 412 localedata = self._params["source"].read_locale(self._params["locale"],
page) | 412 localedata = self._params['source'].read_locale(self._params['locale'],
page) |
| 413 default = localedata[name] | 413 default = localedata[name] |
| 414 return jinja2.Markup(self.localize_string( | 414 return jinja2.Markup(self.localize_string( |
| 415 page, name, default, "", localedata, html_escapes | 415 page, name, default, '', localedata, html_escapes |
| 416 )) | 416 )) |
| 417 | 417 |
| 418 def get_page_content(self, page, locale=None): | 418 def get_page_content(self, page, locale=None): |
| 419 from cms.utils import get_page_params | 419 from cms.utils import get_page_params |
| 420 | 420 |
| 421 if locale is None: | 421 if locale is None: |
| 422 locale = self._params["locale"] | 422 locale = self._params['locale'] |
| 423 return get_page_params(self._params["source"], locale, page) | 423 return get_page_params(self._params['source'], locale, page) |
| 424 | 424 |
| 425 def linkify(self, page, locale=None, **attrs): | 425 def linkify(self, page, locale=None, **attrs): |
| 426 if locale is None: | 426 if locale is None: |
| 427 locale = self._params["locale"] | 427 locale = self._params['locale'] |
| 428 | 428 |
| 429 locale, url = self._params["source"].resolve_link(page, locale) | 429 locale, url = self._params['source'].resolve_link(page, locale) |
| 430 return jinja2.Markup('<a%s>' % ''.join( | 430 return jinja2.Markup('<a%s>' % ''.join( |
| 431 ' %s="%s"' % (name, jinja2.escape(value)) for name, value in [ | 431 ' %s="%s"' % (name, jinja2.escape(value)) for name, value in [ |
| 432 ('href', url), | 432 ('href', url), |
| 433 ('hreflang', locale) | 433 ('hreflang', locale) |
| 434 ] + attrs.items() | 434 ] + attrs.items() |
| 435 )) | 435 )) |
| 436 | 436 |
| 437 def toclist(self, content): | 437 def toclist(self, content): |
| 438 flat = [] | 438 flat = [] |
| 439 for match in re.finditer(r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h
\1>', content, re.S): | 439 for match in re.finditer(r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h
\1>', content, re.S): |
| 440 flat.append({ | 440 flat.append({ |
| 441 "level": int(match.group(1)), | 441 'level': int(match.group(1)), |
| 442 "anchor": jinja2.Markup(match.group(2)).unescape(), | 442 'anchor': jinja2.Markup(match.group(2)).unescape(), |
| 443 "title": jinja2.Markup(match.group(3)).unescape(), | 443 'title': jinja2.Markup(match.group(3)).unescape(), |
| 444 "subitems": [], | 444 'subitems': [], |
| 445 }) | 445 }) |
| 446 | 446 |
| 447 structured = [] | 447 structured = [] |
| 448 stack = [{"level": 0, "subitems": structured}] | 448 stack = [{'level': 0, 'subitems': structured}] |
| 449 for item in flat: | 449 for item in flat: |
| 450 while stack[-1]["level"] >= item["level"]: | 450 while stack[-1]['level'] >= item['level']: |
| 451 stack.pop() | 451 stack.pop() |
| 452 stack[-1]["subitems"].append(item) | 452 stack[-1]['subitems'].append(item) |
| 453 stack.append(item) | 453 stack.append(item) |
| 454 return structured | 454 return structured |
| 455 | 455 |
| 456 converters = { | 456 converters = { |
| 457 "html": RawConverter, | 457 'html': RawConverter, |
| 458 "md": MarkdownConverter, | 458 'md': MarkdownConverter, |
| 459 "tmpl": TemplateConverter, | 459 'tmpl': TemplateConverter, |
| 460 } | 460 } |
| OLD | NEW |