embedding images

1 files changed, 111 insertions, 0 deletions

diff --git a/builder/parser.py b/builder/parser.py
new file mode 100644
index 00000000..ea273556
--- /dev/null
+++ b/builder/parser.py
@@ -0,0 +1,111 @@
+import os
+import glob
+import mistune
+from paths import *
+
+renderer = mistune.Renderer(escape=False)
+markdown = mistune.Markdown(renderer=renderer)
+
+def fix_images(lines, s3_path):
+  real_lines = []
+  block = "\n\n".join(lines)
+  for line in block.split("\n"):
+    if "![" in line and "](http" not in line:
+      line = line.replace('](', '](' + s3_path)
+    real_lines.append(line)
+  return "\n".join(real_lines)
+
+def wide_section(line, s3_path):
+  lines = fix_images(lines, s3_path)
+  return "<section class='wide'>" + markdown(lines) + "</section>"
+
+def normal_section(lines, s3_path):
+  if len(lines):
+    lines = fix_images(lines, s3_path)
+    return "<section>" + markdown(lines) + "</section>"
+  return ""
+
+def parse_markdown(sections, s3_path):
+  groups = []
+  current_group = []
+  for section in sections:
+    if section.startswith('# '):
+      continue
+    if '![wide]' in section:
+      groups.append(normal_section(current_group, s3_path))
+      groups.append(wide_section([section], s3_path))
+      current_group = []
+    else:
+      current_group.append(section)
+  groups.append(normal_section(current_group, s3_path))
+  content = "".join(groups)
+  return content
+
+def read_metadata(fn):
+  with open(fn, "r") as file:
+    data = file.read()
+    data = data.replace("\n ", "\n")
+    if "\n" in data:
+      data = data.replace("\r", "")
+    else:
+      data = data.replace("\r", "\n")
+    sections = data.split("\n\n")
+  return parse_metadata(fn, sections)
+
+default_metadata = {
+  'status': 'published',
+  'title': 'Untitled Page',
+  'desc': '',
+  'slug': '',
+  'published': '2018-12-31',
+  'updated': '2018-12-31',
+  'authors': 'Adam Harvey',
+}
+
+def parse_metadata_section(metadata, section):
+  for line in section.split("\n"):
+    if ': ' not in line:
+      continue
+    key, value = line.split(': ', 1)
+    metadata[key.lower()] = value
+
+def parse_metadata(fn, sections):
+  found_meta = False
+  metadata = {}
+  valid_sections = []
+  for section in sections:
+    if not found_meta and ': ' in section:
+      found_meta = True
+      parse_metadata_section(metadata, section)
+      continue
+    if '-----' in section:
+      continue
+    if found_meta:
+      valid_sections.append(section)
+
+  if 'title' not in metadata:
+    print('warning: {} has no title'.format(fn))
+  for key in default_metadata:
+    if key not in metadata:
+      metadata[key] = default_metadata[key]
+  basename = os.path.basename(fn)
+  metadata['path'] = os.path.dirname(fn.replace(content_path, '')) + '/'
+  if basename == 'index.md':
+    metadata['url'] = metadata['path']
+  else:
+    metadata['url'] = metadata['path'] + basename.replace('.md', '') + '/'
+
+  if metadata['status'] == 'published|draft|private':
+    metadata['status'] = 'published'
+  metadata['authors'] = '<br>'.join(metadata['authors'].split(','))
+  return metadata, valid_sections
+
+def read_research_post_index():
+  posts = []
+  for fn in sorted(glob.glob(os.path.join(content_path, 'research/**/index.md'), recursive=True)):
+    metadata, valid_sections = read_metadata(fn)
+    if metadata is None or metadata['status'] == 'private' or metadata['status'] == 'draft':
+      continue
+    posts.append(metadata)
+  return posts
+