Side by Side Diff: cms/converters.py
Issue 29495555:
Fixes 5343 - add global function: get_canonical_url (Closed)
Patch Set: Implement get_canonical_url (according to updated ticket)
Created July 28, 2017, 10:07 a.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
|
tests/expected_output/get_page_url@dynamic » ('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) 2006-2017 eyeo GmbH | 2 # Copyright (C) 2006-2017 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 __future__ import unicode_literals | 16 from __future__ import unicode_literals |
| 17 | 17 |
| 18 import os | 18 import os |
| 19 import HTMLParser | 19 import HTMLParser |
| 20 import re | 20 import re |
| 21 import urlparse | |
| 21 | 22 |
| 22 import jinja2 | 23 import jinja2 |
| 23 import markdown | 24 import markdown |
| 24 | 25 |
| 25 | 26 |
| 26 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs | 27 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs |
| 27 # are inserted into the <head> tag | 28 # are inserted into the <head> tag |
| 28 orig_isBlockLevel = markdown.util.isBlockLevel | 29 orig_isBlockLevel = markdown.util.isBlockLevel |
| 29 | 30 |
| 30 | 31 |
| (...skipping 358 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
| 389 'translate': self.translate, | 390 'translate': self.translate, |
| 390 'linkify': self.linkify, | 391 'linkify': self.linkify, |
| 391 'toclist': self.toclist, | 392 'toclist': self.toclist, |
| 392 } | 393 } |
| 393 | 394 |
| 394 globals = { | 395 globals = { |
| 395 'get_string': self.get_string, | 396 'get_string': self.get_string, |
| 396 'has_string': self.has_string, | 397 'has_string': self.has_string, |
| 397 'get_page_content': self.get_page_content, | 398 'get_page_content': self.get_page_content, |
| 398 'get_pages_metadata': self.get_pages_metadata, | 399 'get_pages_metadata': self.get_pages_metadata, |
| 400 'get_canonical_url': self.get_canonical_url, | |
| 399 } | 401 } |
| 400 | 402 |
| 401 for dirname, dictionary in [('filters', filters), | 403 for dirname, dictionary in [('filters', filters), |
| 402 ('globals', globals)]: | 404 ('globals', globals)]: |
| 403 for filename in self._params['source'].list_files(dirname): | 405 for filename in self._params['source'].list_files(dirname): |
| 404 root, ext = os.path.splitext(filename) | 406 root, ext = os.path.splitext(filename) |
| 405 if ext.lower() != '.py': | 407 if ext.lower() != '.py': |
| 406 continue | 408 continue |
| 407 | 409 |
| 408 path = os.path.join(dirname, filename) | 410 path = os.path.join(dirname, filename) |
| (...skipping 101 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
| 510 if isinstance(metadata[filter_name], list): | 512 if isinstance(metadata[filter_name], list): |
| 511 if isinstance(filter_value, basestring): | 513 if isinstance(filter_value, basestring): |
| 512 filter_value = [filter_value] | 514 filter_value = [filter_value] |
| 513 for option in filter_value: | 515 for option in filter_value: |
| 514 if str(option) not in metadata[filter_name]: | 516 if str(option) not in metadata[filter_name]: |
| 515 return False | 517 return False |
| 516 elif filter_value != metadata[filter_name]: | 518 elif filter_value != metadata[filter_name]: |
| 517 return False | 519 return False |
| 518 return True | 520 return True |
| 519 | 521 |
| 522 def get_canonical_url(self, page): | |
| 523 """Return canonical URL for the page (without locale code)""" | |
| 524 try: | |
| 525 base_url = self._params['site_url'] | |
| 526 except KeyError: | |
| 527 raise Exception('You must configure `siteurl` to use' | |
| 528 '`get_canonical_url()`') | |
| 529 | |
| 530 locale, page_url = self._params['source'].resolve_link( | |
| 531 page, self._params['locale'] | |
| 532 ) | |
| 533 # Remove the locale component that `resolve_link` adds at the | |
| 534 # beginning. | |
| 535 page_url = page_url[len(locale) + 1:] | |
| 536 return urlparse.urljoin(base_url, page_url) | |
| 537 | |
| 520 def toclist(self, content): | 538 def toclist(self, content): |
| 521 toc_re = r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h\1>' | 539 toc_re = r'<h(\d)\s[^<>]*\bid="([^<>"]+)"[^<>]*>(.*?)</h\1>' |
| 522 flat = [] | 540 flat = [] |
| 523 for match in re.finditer(toc_re, content, re.S): | 541 for match in re.finditer(toc_re, content, re.S): |
| 524 flat.append({ | 542 flat.append({ |
| 525 'level': int(match.group(1)), | 543 'level': int(match.group(1)), |
| 526 'anchor': jinja2.Markup(match.group(2)).unescape(), | 544 'anchor': jinja2.Markup(match.group(2)).unescape(), |
| 527 'title': jinja2.Markup(match.group(3)).unescape(), | 545 'title': jinja2.Markup(match.group(3)).unescape(), |
| 528 'subitems': [], | 546 'subitems': [], |
| 529 }) | 547 }) |
| 530 | 548 |
| 531 structured = [] | 549 structured = [] |
| 532 stack = [{'level': 0, 'subitems': structured}] | 550 stack = [{'level': 0, 'subitems': structured}] |
| 533 for item in flat: | 551 for item in flat: |
| 534 while stack[-1]['level'] >= item['level']: | 552 while stack[-1]['level'] >= item['level']: |
| 535 stack.pop() | 553 stack.pop() |
| 536 stack[-1]['subitems'].append(item) | 554 stack[-1]['subitems'].append(item) |
| 537 stack.append(item) | 555 stack.append(item) |
| 538 return structured | 556 return structured |
| 539 | 557 |
| 540 converters = { | 558 converters = { |
| 541 'html': RawConverter, | 559 'html': RawConverter, |
| 542 'md': MarkdownConverter, | 560 'md': MarkdownConverter, |
| 543 'tmpl': TemplateConverter, | 561 'tmpl': TemplateConverter, |
| 544 } | 562 } |
| OLD | NEW |
« no previous file with comments
|
« no previous file
|
tests/expected_output/get_page_url@dynamic » ('j')
|
no next file with comments »
