Issue 4687 - Add Context Function get_pages_metadata to Test Site

tests/test_site/globals/get_pages_metadata.py

Index: tests/test_site/globals/get_pages_metadata.py
===================================================================
new file mode 100644
--- /dev/null
+++ b/tests/test_site/globals/get_pages_metadata.py
@@ -0,0 +1,44 @@
+import re
+from jinja2 import contextfunction
+
+
+@contextfunction
+def get_pages_metadata(context, filters=None):
+    if not isinstance(filters, dict) and filters:
+        raise TypeError('Filters are not a dictionary')
+
+    return_data = []
+    for page_name, _format in context['source'].list_pages():
+        data, filename = context['source'].read_page(page_name, _format)
+        page_data = parse_page_metadata(data, page_name)
+
+        if filter_metadata(filters, page_data) is True:
+            return_data.append(page_data)
+
+    return return_data
+
+
+def parse_page_metadata(data, page):
+    page_metadata = {'page': page}
+    lines = data.splitlines(True)
+    for i, line in enumerate(lines):
+        if not re.search(r'^\s*[\w\-]+\s*=', line):
+            break
+        name, value = line.split('=', 1)
+        value = value.strip(' ').strip('\n')

[Vasily Kuznetsov, 2017/03/08 17:07:41]

Can we just strip everything? Or is there a special reason you want to leave
tabs and exotic whitespace in there?

[Jon Sonesen, 2017/03/08 17:47:17]

Nah, we should just strip everything, will do

+        if value.startswith('['):

[Vasily Kuznetsov, 2017/03/08 17:07:41]

Maybe add "and value.endswith(']')" here to be a bit more careful?

[Jon Sonesen, 2017/03/08 17:47:16]

Agreed.

+            value = value[1:-1].split(',')

[Vasily Kuznetsov, 2017/03/08 17:07:41]

We should probably filter the split value through strip again to remove the
whitespace that could be around commas.

[Jon Sonesen, 2017/03/08 17:47:16]

no problem :)

+        page_metadata[name.strip()] = value
+    return page_metadata
+
+
+def filter_metadata(filters, metadata):
+    if filters is None:
+        return True
+    for filter_name, filter_value in filters.items():
+        if filter_name not in metadata:
+            return False
+        for option in filter_value.split(','):
+            if option not in metadata[filter_name]:
+                return False
+    return True