Issue 5333 - Allow cms to generate relative pages

cms/bin/generate_static_pages.py

 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-present eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
 # along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
 
 import os
 import re
 import errno
 import codecs
 import ConfigParser
 import logging
+import lxml.html
+
 from argparse import ArgumentParser
 
 from cms.utils import get_page_params, process_page
 from cms.sources import create_source
 
 MIN_TRANSLATED = 0.3
 
 
-def generate_pages(repo, output_dir, revision):
+def generate_pages(repo, output_dir, revision, relative):
     known_files = set()
 
     def write_file(path_parts, contents, binary=False):
         encoding = None if binary else 'utf-8'
         outfile = os.path.join(output_dir, *path_parts)
         if outfile in known_files:
             logging.warning('File %s has multiple sources', outfile)
             return
         known_files.add(outfile)
 
@@ skipping 42 matching lines @@
         orig_has_locale = source.has_locale
 
         def has_locale(locale, page):
             page = get_locale_file(page)
             if (locale, page) in blacklist:
                 return False
             return orig_has_locale(locale, page)
         source.has_locale = has_locale
         source.resolve_link.cache_clear()
 
+        def rewrite_link(link):

[Vasily Kuznetsov, 2017/11/14 17:30:27]

This seems like it would work but the links would look nicer if we compact the
unnecessary pairs of `../some_path`, where the `some_path` part is the same in
the link and in the current page. Perhaps this is not first priority though and
is more of a cosmetic feature.

+            if link.startswith('/'):
+                if source.version:
+                    link += '?' + source.version
+                if relative:
+                    depth = len(page.split('/'))
+                    link = '/'.join(['..'] * depth) + link
+            return link
+
         # Second pass: actually generate pages this time
         for locale, page in pagelist:
             pagedata = process_page(source, locale, page)
 
-            # Make sure links to static files are versioned
-            pagedata = re.sub(r'(<script\s[^<>]*\bsrc="/[^"<>]+)', r'\1?%s' % source.version, pagedata)
-            pagedata = re.sub(r'(<link\s[^<>]*\bhref="/[^"<>]+)', r'\1?%s' % source.version, pagedata)
-            pagedata = re.sub(r'(<img\s[^<>]*\bsrc="/[^"<>]+)', r'\1?%s' % source.version, pagedata)
+            root = lxml.html.fromstring(pagedata).getroottree()
 
+            expr = '//img[@src|@srcset]|//script[@src]|//link[@href]|//a[@href]'
+            for elem in root.xpath(expr):
+                if 'srcset' in elem.attrib:
+                    srcset = []
+                    for src_zoom in elem.attrib['srcset'].split(', '):

[Vasily Kuznetsov, 2017/11/14 17:30:28]

Is the space after the comma mandatory? Otherwise we can't just split by ', ',
we need to split by comma.

+                        try:
+                            src, zoom = src_zoom.split(' ')
+                        except ValueError:
+                            src = src_zoom
+                            zoom = None
+                        res = rewrite_link(src)
+                        if zoom:
+                             res = res + ' ' + zoom
+                        srcset.append(res)
+
+                    elem.attrib['srcset'] = ', '.join(srcset)
+
+                for key in ['src', 'href']:
+                    if key in elem.attrib:
+                        elem.attrib[key] = rewrite_link(elem.attrib[key])
+
+            pagedata = lxml.html.tostring(root, encoding='unicode')
             write_file([locale] + page.split('/'), pagedata)
 
         for filename in source.list_localizable_files():
             for locale in locales:
                 if source.has_localizable_file(locale, filename):
                     filedata = source.read_localizable_file(locale, filename)
                     write_file([locale] + filename.split('/'), filedata, binary=True)
 
         for filename in source.list_static():
             write_file(filename.split('/'), source.read_static(filename), binary=True)
@@ skipping 10 matching lines @@
                     os.rmdir(path)
     remove_unknown(output_dir)
 
 
 if __name__ == '__main__':
     parser = ArgumentParser('Convert website source to static website')
     parser.add_argument('-r', '--rev',
                         help=('Specify which revision to generate from. '
                               'See "hg help revisions" for details.'),
                         default='default')
+    parser.add_argument('--relative', action='store_true', default=False)
     parser.add_argument('source', help="Path to website's repository")
     parser.add_argument('output', help='Path to desired output directory')
     args = parser.parse_args()
-    generate_pages(args.source, args.output, args.rev)
+    generate_pages(args.source, args.output, args.rev, args.relative)