Merge branch 'master' of github.com:adamhrv/megapixels_dev

4 files changed, 122 insertions, 10 deletions

diff --git a/megapixels/app/settings/app_cfg.py b/megapixels/app/settings/app_cfg.py
index f6d0a7df..1eed1a41 100644
--- a/megapixels/app/settings/app_cfg.py
+++ b/megapixels/app/settings/app_cfg.py
@@ -169,6 +169,7 @@ DIR_SITE_INCLUDES = "../site/includes"
 DIR_SITE_USER_CONTENT = "../site/public/user_content"
 DIR_SITE_DATASETS = "../site/datasets/"
 DIR_SITE_FINAL_CITATIONS = "../site/datasets/final/"
+GOOGLE_ACCOUNT_CREDS_PATH = os.path.join("../", os.getenv("GOOGLE_ACCOUNT_CREDS_PATH"))
 
 # -----------------------------------------------------------------------------
 # Celery
diff --git a/megapixels/app/site/loader.py b/megapixels/app/site/loader.py
index 779f68ba..701c78b2 100644
--- a/megapixels/app/site/loader.py
+++ b/megapixels/app/site/loader.py
@@ -5,6 +5,9 @@ import glob
 import app.settings.app_cfg as cfg
 
 from app.utils.file_utils import load_json
+import app.utils.sheet_utils as sheet
+
+sidebar = sheet.fetch_google_lookup("sidebar", item_key="key")
 
 def read_metadata(fn):
   """
@@ -20,6 +23,12 @@ def read_metadata(fn):
     sections = data.split("\n\n")
   return parse_metadata(fn, sections)
 
+def domainFromUrl(url):
+  domain = url.split('/')[2].split('.')
+  if len(domain) > 2 and len(domain[-2]) == 2:
+    return ".".join(domain[-3:])
+  return ".".join(domain[-2:])
+
 
 default_metadata = {
   'status': 'published',
@@ -33,6 +42,18 @@ default_metadata = {
   'tagline': '',
 }
 
+sidebar_order = [
+  { 'key': 'published', 'title': 'Published' },
+  { 'key': 'images', 'title': 'Images' },
+  { 'key': 'videos', 'title': 'Videos' },
+  { 'key': 'identities', 'title': 'Identities' },
+  { 'key': 'purpose', 'title': 'Purpose' },
+  { 'key': 'created_by', 'title': 'Created by' },
+  { 'key': 'funded_by_short', 'title': 'Funded by' },
+  { 'key': 'size_gb', 'title': 'Download Size' },
+  { 'key': 'website', 'title': 'Website' },
+]
+
 def parse_metadata(fn, sections):
   """
   parse the metadata headers in a markdown file
@@ -87,8 +108,25 @@ def parse_metadata(fn, sections):
       print("Bad metadata? {}".format(dataset_path))
   elif 'datasets' in fn:
     print("/!\\ {} does not exist!".format(dataset_path))
+
+  if metadata['slug'] in sidebar:
+    sidebar_row = sidebar[metadata['slug']]
+    if sidebar_row:
+      metadata['sidebar'] = []
+      for item in sidebar_order:
+        key = item['key']
+        value = sidebar_row[key]
+        if value:
+          value = value.replace(' - ', ' – ')
+          if key == 'size_gb':
+            value += ' GB'
+          if key == 'website':
+            value = "<a href='" + value + "' target='_blank' rel='nofollow noopener'>" + domainFromUrl(value) + "</a>"
+          metadata['sidebar'].append({ 'value': value, 'title': item['title'], })
+
   if 'meta' not in metadata or not metadata['meta']: # dude
     metadata['meta'] = {}
+    metadata['sidebar'] = []
 
   return metadata, valid_sections
 
diff --git a/megapixels/app/site/parser.py b/megapixels/app/site/parser.py
index 06c45f41..dc2a09f2 100644
--- a/megapixels/app/site/parser.py
+++ b/megapixels/app/site/parser.py
@@ -55,7 +55,7 @@ def parse_markdown(metadata, sections, s3_path, skip_h1=False):
     elif '### statistics' in section.lower() or '### sidebar' in section.lower():
       if len(current_group):
         groups.append(format_section(current_group, s3_path))
-      current_group = []
+      current_group = [format_include("{% include 'sidebar.html' %}", metadata)]
       if 'sidebar' not in section.lower():
         current_group.append(section)
       in_stats = True
@@ -267,15 +267,6 @@ def format_include(section, metadata):
   include_fn = section.strip().strip('\n').strip().strip('{%').strip().strip('%}').strip()
   include_fn = include_fn.strip('include').strip().strip('"').strip().strip("'").strip()
   return includes_env.get_template(include_fn).render(metadata=metadata)
-  # include_dir = cfg.DIR_SITE_INCLUDES
-  # try:
-  #   includes_env.get_template(fp_html)
-  #   with open(join(include_dir, fp_html), 'r') as fp:
-  #     html = fp.read().replace('\n', '')
-  #   return html
-  # except Exception as e:
-  #   print(f'Error parsing include: {e}')
-  #   return ''
 
 def format_applet(section, s3_path):
   """
diff --git a/megapixels/app/utils/sheet_utils.py b/megapixels/app/utils/sheet_utils.py
new file mode 100644
index 00000000..85f979c6
--- /dev/null
+++ b/megapixels/app/utils/sheet_utils.py
@@ -0,0 +1,82 @@
+import os
+import gspread
+from oauth2client.service_account import ServiceAccountCredentials
+
+from app.settings import app_cfg as cfg
+
+def fetch_spreadsheet():
+  """Open the Google Spreadsheet, which contains the individual worksheets"""
+  scope = ['https://spreadsheets.google.com/feeds', 'https://www.googleapis.com/auth/drive']
+  path = os.path.dirname(os.path.abspath(__file__))
+  credentials = ServiceAccountCredentials.from_json_keyfile_name(cfg.GOOGLE_ACCOUNT_CREDS_PATH, scope)
+  docid = "1denb7TjYsN9igHyvYah7fQ0daABW32Z30lwV7QrDJQc"
+  client = gspread.authorize(credentials)
+  spreadsheet = client.open_by_key(docid)
+  return spreadsheet
+
+def fetch_worksheet(name):
+  """Get a reference to a particular "worksheet" from the Google Spreadsheet"""
+  spreadsheet = fetch_spreadsheet()
+  return spreadsheet.worksheet(name)
+
+def fetch_google_sheet(name):
+  """Get all the values from a particular worksheet as a list of lists.
+  Returns:
+  :keys - the first row of the document
+  :lines - a list of lists with the rest of the rows"""
+  rows = fetch_worksheet(name).get_all_values()
+  keys = rows[0]
+  lines = rows[1:]
+  return keys, lines
+
+def fetch_google_sheet_objects(name):
+  """Get all the values from a worksheet as a list of dictionaries"""
+  keys, rows = fetch_google_sheet(name)
+  recs = []
+  for row in rows:
+    rec = {}
+    for index, key in enumerate(keys):
+      rec[key] = row[index]
+    recs.append(rec)
+  return recs
+
+def fetch_google_lookup(name, item_key='key'):
+  """Get all the values from a worksheet as a dictionary of dictionaries.
+  Specify which field you want to use as the dictionary key."""
+  keys, rows = fetch_google_sheet(name)
+  lookup = {}
+  for row in rows:
+    rec = {}
+    for index, key in enumerate(keys):
+      rec[key] = row[index]
+    lookup[rec[item_key]] = rec
+  return lookup
+
+def fetch_verified_paper_lookup():
+  """Fetch a lookup keyed by dataset, where each dataset points to a hash of valid or invalid papers..."""
+  keys, rows = fetch_google_sheet('verifications')
+  verified_lookup = {}
+  for row in rows:
+    rec = {}
+    for index, key in enumerate(keys):
+      rec[key] = row[index]
+    if rec['dataset'] not in verified_lookup:
+      verified_lookup[rec['dataset']] = {}
+    if str(rec['uses_dataset']) == '1':
+      verified_lookup[rec['dataset']][rec['paper_id']] = rec
+  return verified_lookup
+
+def update_or_append_worksheet(name, form):
+  """Update a row if it exists, create it if it doesn't"""
+  worksheet = fetch_worksheet(name)
+  keys = worksheet.row_values(1)
+  row = [ form[key] if key in form else '' for key in keys ]
+  try:
+    cell = worksheet.find(form['paper_id'])
+  except:
+    cell = None
+  if cell:
+    for i, item in enumerate(row):
+      worksheet.update_cell(cell.row, i+1, item)
+  else:
+    worksheet.append_row(row)