Issue 4488 - Add support for JSON page front matter

cms/utils.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 re
+import json
 
 __all__ = [
     'get_page_params',
     'process_page',
     'split_head_body',
     'extract_page_metadata'
 ]
 
 
 def split_head_body(html):
@@ skipping 31 matching lines @@
     ----------
     source: str
         Source text of the page.
 
     Returns
     -------
     (dict, str)
         Metadata of the page, remaining source text without metadata.
 
     """
-    metadata = {}
-    lines = source.splitlines(True)
-    for i, line in enumerate(lines):
-        if line.strip() in {'<!--', '-->'}:
-            lines[i] = ''
-            continue
-        if not re.search(r'^\s*[\w\-]+\s*=', line):
-            break
-        name, value = line.split('=', 1)
-        value = value.strip()
-        if value.startswith('[') and value.endswith(']'):
-            value = [element.strip() for element in value[1:-1].split(',')]
-        lines[i] = '\n'
-        metadata[name.strip()] = value
-    return metadata, ''.join(lines)
+    m = re.search(r'^\s*<!--\s*(.*?)-->', source, re.S)
+    text = m.group(1) if m else source
+
+    decoder = json.JSONDecoder()
+    try:
+        metadata, length = decoder.raw_decode(text)
+    except ValueError:
+        metadata = None
+
+    if not isinstance(metadata, dict):
+        metadata = {}
+        length = 0
+        for line in text.splitlines(True):
+            if not re.search(r'^\s*[\w\-]+\s*=', line):
+                break
+            name, value = line.split('=', 1)
+            value = value.strip()
+            if value.startswith('[') and value.endswith(']'):
+                value = [element.strip() for element in value[1:-1].split(',')]
+            metadata[name.strip()] = value
+            length += len(line)
+
+    # Need to preserve line numbers for jinja2 tracebacks

[Sebastian Noack, 2018/03/31 22:07:36]

This comment is slightly out of place here. Perhaps move it inside the block.
Otherwise it looks like that the check in the next line is related to preserving
line numbers too (which it is not).

[rosie, 2018/04/18 02:35:32]

Done.

+    if length > 0:
+        cutoff = m.end() if m else length
+        source = '\n' * source.count('\n', 0, cutoff) + source[cutoff:]
+    return metadata, source
 
 
 def get_page_params(source, locale, page, format=None, site_url_override=None,
                     localized_string_callback=None):
     from cms.converters import converters
 
     # Guess page format if omitted, but default to Markdown for friendlier exceptions
     if format is None:
         for format in converters.iterkeys():
             if source.has_page(page, format):
@@ skipping 60 matching lines @@
     return params
 
 
 def process_page(source, locale, page, format=None, site_url_override=None,
                  localized_string_callback=None):
     from cms.converters import TemplateConverter
 
     params = get_page_params(source, locale, page, format, site_url_override,
                              localized_string_callback)
     return TemplateConverter(*params['templatedata'], params=params)()