Left: | ||
Right: |
LEFT | RIGHT |
---|---|
1 # coding: utf-8 | 1 # coding: utf-8 |
2 | 2 |
3 # This file is part of the Adblock Plus web scripts, | 3 # This file is part of the Adblock Plus web scripts, |
4 # Copyright (C) 2006-2015 Eyeo GmbH | 4 # Copyright (C) 2006-2015 Eyeo GmbH |
5 # | 5 # |
6 # Adblock Plus is free software: you can redistribute it and/or modify | 6 # Adblock Plus is free software: you can redistribute it and/or modify |
7 # it under the terms of the GNU General Public License version 3 as | 7 # it under the terms of the GNU General Public License version 3 as |
8 # published by the Free Software Foundation. | 8 # published by the Free Software Foundation. |
9 # | 9 # |
10 # Adblock Plus is distributed in the hope that it will be useful, | 10 # Adblock Plus is distributed in the hope that it will be useful, |
(...skipping 94 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
105 def handle_entityref(self, name): | 105 def handle_entityref(self, name): |
106 self._append_text(self.unescape("&%s;" % name)) | 106 self._append_text(self.unescape("&%s;" % name)) |
107 | 107 |
108 def handle_charref(self, name): | 108 def handle_charref(self, name): |
109 self._append_text(self.unescape("&#%s;" % name)) | 109 self._append_text(self.unescape("&#%s;" % name)) |
110 | 110 |
111 class Converter: | 111 class Converter: |
112 whitelist = {"a", "em", "strong", "code", "span"} | 112 whitelist = {"a", "em", "strong", "code", "span"} |
113 missing_translations = 0 | 113 missing_translations = 0 |
114 total_translations = 0 | 114 total_translations = 0 |
115 removed_line = '' | |
116 | 115 |
117 def __init__(self, params, key="pagedata"): | 116 def __init__(self, params, key="pagedata"): |
118 self._params = params | 117 self._params = params |
119 self._key = key | 118 self._key = key |
120 self._attribute_parser = AttributeParser(self.whitelist) | 119 self._attribute_parser = AttributeParser(self.whitelist) |
121 self._seen_defaults = {} | 120 self._seen_defaults = {} |
122 | 121 |
123 # Read in any parameters specified at the beginning of the file | 122 # Read in any parameters specified at the beginning of the file |
124 lines = params[key].splitlines(True) | 123 data, filename = params[key] |
124 lines = data.splitlines(True) | |
125 for i, line in enumerate(lines): | 125 for i, line in enumerate(lines): |
Sebastian Noack
2015/09/15 17:48:36
In order to prevent line numbers from being off we
| |
126 if not re.search(r"^\s*[\w\-]+\s*=", line): | 126 if not re.search(r"^\s*[\w\-]+\s*=", line): |
127 break | 127 break |
128 name, value = line.split("=", 1) | 128 name, value = line.split("=", 1) |
129 params[name.strip()] = value.strip() | 129 params[name.strip()] = value.strip() |
130 lines[i] = self.removed_line | 130 lines[i] = "\n" |
131 params[key] = "".join(lines) | 131 params[key] = ("".join(lines), filename) |
132 | 132 |
133 def localize_string(self, page, name, default, comment, localedata, escapes): | 133 def localize_string(self, page, name, default, comment, localedata, escapes): |
134 def escape(s): | 134 def escape(s): |
135 return re.sub(r".", | 135 return re.sub(r".", |
136 lambda match: escapes.get(match.group(0), match.group(0)), | 136 lambda match: escapes.get(match.group(0), match.group(0)), |
137 s, flags=re.S) | 137 s, flags=re.S) |
138 def re_escape(s): | 138 def re_escape(s): |
139 return re.escape(escape(s)) | 139 return re.escape(escape(s)) |
140 | 140 |
141 # Handle duplicated strings | 141 # Handle duplicated strings |
(...skipping 101 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
243 | 243 |
244 include_start_regex = '<' | 244 include_start_regex = '<' |
245 include_end_regex = '>' | 245 include_end_regex = '>' |
246 | 246 |
247 def resolve_includes(self, text): | 247 def resolve_includes(self, text): |
248 def resolve_include(match): | 248 def resolve_include(match): |
249 global converters | 249 global converters |
250 name = match.group(1) | 250 name = match.group(1) |
251 for format, converter_class in converters.iteritems(): | 251 for format, converter_class in converters.iteritems(): |
252 if self._params["source"].has_include(name, format): | 252 if self._params["source"].has_include(name, format): |
253 self._params["include"] = name | |
Sebastian Noack
2015/09/15 17:48:36
There seems to be no way to get the filename for i
| |
254 self._params["includedata"] = self._params["source"].read_include(name , format) | 253 self._params["includedata"] = self._params["source"].read_include(name , format) |
255 converter = converter_class(self._params, key="includedata") | 254 converter = converter_class(self._params, key="includedata") |
256 result = converter() | 255 result = converter() |
257 self.missing_translations += converter.missing_translations | 256 self.missing_translations += converter.missing_translations |
258 self.total_translations += converter.total_translations | 257 self.total_translations += converter.total_translations |
259 return result | 258 return result |
260 raise Exception("Failed to resolve include %s on page %s" % (name, self._p arams["page"])) | 259 raise Exception("Failed to resolve include %s on page %s" % (name, self._p arams["page"])) |
261 | 260 |
262 return re.sub( | 261 return re.sub( |
263 r'%s\?\s*include\s+([^\s<>"]+)\s*\?%s' % ( | 262 r'%s\?\s*include\s+([^\s<>"]+)\s*\?%s' % ( |
264 self.include_start_regex, | 263 self.include_start_regex, |
265 self.include_end_regex | 264 self.include_end_regex |
266 ), | 265 ), |
267 resolve_include, | 266 resolve_include, |
268 text | 267 text |
269 ) | 268 ) |
270 | 269 |
271 def __call__(self): | 270 def __call__(self): |
272 result = self.get_html(self._params[self._key]) | 271 result = self.get_html(*self._params[self._key]) |
273 result = self.resolve_includes(result) | 272 result = self.resolve_includes(result) |
274 if self._key == "pagedata": | 273 if self._key == "pagedata": |
275 head = [] | 274 head = [] |
276 def add_to_head(match): | 275 def add_to_head(match): |
277 head.append(match.group(1)) | 276 head.append(match.group(1)) |
278 return "" | 277 return "" |
279 body = re.sub(r"<head>(.*?)</head>", add_to_head, result, flags=re.S) | 278 body = re.sub(r"<head>(.*?)</head>", add_to_head, result, flags=re.S) |
280 return "".join(head), body | 279 return "".join(head), body |
281 else: | 280 else: |
282 return result | 281 return result |
283 | 282 |
284 class RawConverter(Converter): | 283 class RawConverter(Converter): |
285 def get_html(self, source): | 284 def get_html(self, source, filename): |
286 result = self.insert_localized_strings(source, html_escapes) | 285 result = self.insert_localized_strings(source, html_escapes) |
287 result = self.process_links(result) | 286 result = self.process_links(result) |
288 return result | 287 return result |
289 | 288 |
290 class MarkdownConverter(Converter): | 289 class MarkdownConverter(Converter): |
291 include_start_regex = r'(?:%s|%s)' % ( | 290 include_start_regex = r'(?:%s|%s)' % ( |
292 Converter.include_start_regex, | 291 Converter.include_start_regex, |
293 re.escape(jinja2.escape(Converter.include_start_regex)) | 292 re.escape(jinja2.escape(Converter.include_start_regex)) |
294 ) | 293 ) |
295 include_end_regex = r'(?:%s|%s)' % ( | 294 include_end_regex = r'(?:%s|%s)' % ( |
296 Converter.include_end_regex, | 295 Converter.include_end_regex, |
297 re.escape(jinja2.escape(Converter.include_end_regex)) | 296 re.escape(jinja2.escape(Converter.include_end_regex)) |
298 ) | 297 ) |
299 | 298 |
300 def get_html(self, source): | 299 def get_html(self, source, filename): |
301 def remove_unnecessary_entities(match): | 300 def remove_unnecessary_entities(match): |
302 char = unichr(int(match.group(1))) | 301 char = unichr(int(match.group(1))) |
303 if char in html_escapes: | 302 if char in html_escapes: |
304 return match.group(0) | 303 return match.group(0) |
305 else: | 304 else: |
306 return char | 305 return char |
307 | 306 |
308 escapes = {} | 307 escapes = {} |
309 for char in markdown.Markdown.ESCAPED_CHARS: | 308 for char in markdown.Markdown.ESCAPED_CHARS: |
310 escapes[char] = "&#" + str(ord(char)) + ";" | 309 escapes[char] = "&#" + str(ord(char)) + ";" |
311 for key, value in html_escapes.iteritems(): | 310 for key, value in html_escapes.iteritems(): |
312 escapes[key] = value | 311 escapes[key] = value |
313 | 312 |
314 md = markdown.Markdown(output="html5", extensions=["attr_list"]) | 313 md = markdown.Markdown(output="html5", extensions=["attr_list"]) |
315 md.preprocessors["html_block"].markdown_in_raw = True | 314 md.preprocessors["html_block"].markdown_in_raw = True |
316 | 315 |
317 def to_html(s): | 316 def to_html(s): |
318 return re.sub(r'</?p>', '', md.convert(s)) | 317 return re.sub(r'</?p>', '', md.convert(s)) |
319 | 318 |
320 result = self.insert_localized_strings(source, escapes, to_html) | 319 result = self.insert_localized_strings(source, escapes, to_html) |
321 result = md.convert(result) | 320 result = md.convert(result) |
322 result = re.sub(r"&#(\d+);", remove_unnecessary_entities, result) | 321 result = re.sub(r"&#(\d+);", remove_unnecessary_entities, result) |
323 result = self.process_links(result) | 322 result = self.process_links(result) |
324 return result | 323 return result |
325 | 324 |
325 class SourceTemplateLoader(jinja2.BaseLoader): | |
326 def __init__(self, source): | |
327 self.source = source | |
328 | |
329 def get_source(self, environment, template): | |
330 try: | |
331 result = self.source.read_file(template + ".tmpl") | |
332 except Exception: | |
333 raise jinja2.TemplateNotFound(template) | |
334 return result + (None,) | |
335 | |
326 class TemplateConverter(Converter): | 336 class TemplateConverter(Converter): |
327 removed_line = "{#\n#}" | |
328 | |
329 def __init__(self, *args, **kwargs): | 337 def __init__(self, *args, **kwargs): |
330 Converter.__init__(self, *args, **kwargs) | 338 Converter.__init__(self, *args, **kwargs) |
331 | 339 |
332 filters = { | 340 filters = { |
333 "translate": self.translate, | 341 "translate": self.translate, |
334 "linkify": self.linkify, | 342 "linkify": self.linkify, |
335 "toclist": self.toclist, | 343 "toclist": self.toclist, |
336 } | 344 } |
337 | 345 |
338 globals = { | 346 globals = { |
339 "get_string": self.get_string, | 347 "get_string": self.get_string, |
340 "get_page_content": self.get_page_content, | 348 "get_page_content": self.get_page_content, |
341 } | 349 } |
342 | 350 |
343 for dirname, dictionary in [("filters", filters), ("globals", globals)]: | 351 for dirname, dictionary in [("filters", filters), ("globals", globals)]: |
344 for filename in self._params["source"].list_files(dirname): | 352 for filename in self._params["source"].list_files(dirname): |
345 root, ext = os.path.splitext(filename) | 353 root, ext = os.path.splitext(filename) |
346 if ext.lower() != ".py": | 354 if ext.lower() != ".py": |
347 continue | 355 continue |
348 | 356 |
349 path = "%s/%s" % (dirname, filename) | 357 path = "%s/%s" % (dirname, filename) |
358 namespace = self._params["source"].exec_file(path) | |
359 | |
350 name = os.path.basename(root) | 360 name = os.path.basename(root) |
351 dictionary[name] = self._params["source"].import_symbol(path, name) | 361 try: |
352 | 362 dictionary[name] = namespace[name] |
353 self._env = jinja2.Environment(loader=self._params["source"].get_template_lo ader(), autoescape=True) | 363 except KeyError: |
364 raise Exception("Expected symbol %r not found in %r" % (name, path)) | |
365 | |
366 self._env = jinja2.Environment(loader=SourceTemplateLoader(self._params["sou rce"]), autoescape=True) | |
354 self._env.filters.update(filters) | 367 self._env.filters.update(filters) |
355 self._env.globals.update(globals) | 368 self._env.globals.update(globals) |
356 | 369 |
357 def get_template_filename(self): | 370 def get_html(self, source, filename): |
358 source = self._params["source"] | |
Sebastian Noack
2015/09/15 17:48:36
And here is where the problematic part starts. I d
| |
359 if hasattr(source, "get_path"): | |
360 if self._key == "pagedata": | |
361 return source.get_path(source.page_filename(self._params["page"], "tmpl" )) | |
362 if self._key == "includedata": | |
363 return source.get_path(source.include_filename(self._params["include"], "tmpl")) | |
364 if self._key == "templatedata": | |
365 return source.get_path(source.template_filename(self._params["template"] )) | |
366 | |
367 def get_html(self, source): | |
368 env = self._env | 371 env = self._env |
369 code = env.compile(source, None, self.get_template_filename()) | 372 code = env.compile(source, None, filename) |
Sebastian Noack
2015/09/15 17:48:36
There are two ways to make the template aware of t
| |
370 template = env.template_class.from_code(env, code, env.globals) | 373 template = jinja2.Template.from_code(env, code, env.globals) |
371 | 374 |
372 try: | 375 try: |
373 module = template.make_module(self._params) | 376 module = template.make_module(self._params) |
374 except Exception: | 377 except Exception: |
375 env.handle_exception() | 378 env.handle_exception() |
Sebastian Noack
2015/09/15 17:48:36
Note that this is necessary because as opposed to
| |
376 | 379 |
377 for key, value in module.__dict__.iteritems(): | 380 for key, value in module.__dict__.iteritems(): |
378 if not key.startswith("_"): | 381 if not key.startswith("_"): |
379 self._params[key] = value | 382 self._params[key] = value |
380 | 383 |
381 result = unicode(module) | 384 result = unicode(module) |
382 result = self.process_links(result) | 385 result = self.process_links(result) |
383 return result | 386 return result |
384 | 387 |
385 def translate(self, default, name, comment=None): | 388 def translate(self, default, name, comment=None): |
(...skipping 48 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
434 stack.pop() | 437 stack.pop() |
435 stack[-1]["subitems"].append(item) | 438 stack[-1]["subitems"].append(item) |
436 stack.append(item) | 439 stack.append(item) |
437 return structured | 440 return structured |
438 | 441 |
439 converters = { | 442 converters = { |
440 "html": RawConverter, | 443 "html": RawConverter, |
441 "md": MarkdownConverter, | 444 "md": MarkdownConverter, |
442 "tmpl": TemplateConverter, | 445 "tmpl": TemplateConverter, |
443 } | 446 } |
LEFT | RIGHT |