DPLA upload metrics breakdown by hub

SQL

SELECT
  REPLACE(
    REPLACE(
      REPLACE(cl_to, "_", " "),
      "Media contributed by the ",
      ""
    ),
    "Media contributed by ",
    ""
  ) AS "Institution",
  COUNT(img_name) AS "File count",
  COUNT(
    DISTINCT REGEXP_REPLACE(
      REGEXP_REPLACE(img_name, '^.*DPLA_-_', ''),
      '[\.|_].*$',
      ''
    )
  ) AS "Item count",
  ROUND(SUM(img_size /(1 < < 30))) AS "Size (GB)"
FROM
  page
  JOIN image ON page_title = img_name
  JOIN categorylinks ON page_id = cl_from
WHERE
  cl_to = "Media_contributed_by_Digital_Commonwealth"
  OR cl_to = "Media_contributed_by_Digital_Library_of_Georgia"
  OR cl_to = "Media_contributed_by_Indiana_Memory"
  OR cl_to = "Media_contributed_by_Minnesota_Digital_Library"
  OR cl_to = "Media_contributed_by_North_Carolina_Digital_Heritage_Center"
  OR cl_to = "Media_contributed_by_the_National_Archives_and_Records_Administration_via_DPLA"
  OR cl_to = "Media_contributed_by_the_Ohio_Digital_Network"
  OR cl_to = "Media_contributed_by_the_Plains_to_Peaks_Collective"
  OR cl_to = "Media_contributed_by_The_Portal_to_Texas_History"
  OR cl_to = "Media_contributed_by_the_Digital_Public_Library_of_America"
GROUP BY(cl_to)
ORDER BY(COUNT(img_name)) DESC
SQL

Checking query status...
