numUrls query (#60)

HTTPArchive · Aug 15, 2018 · 57db33e · 57db33e
1 parent 2fda19d
commit 57db33e
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 4 deletions.
diff --git a/sql/get_bigquery_dates.sh b/sql/get_bigquery_dates.sh
@@ -21,11 +21,11 @@
 # May be combined with the generateReports.sh script
 # to generate a histogram for each date. For example:
 #
-#   sql/getBigQueryDates.sh runs pages | \
-#     xargs -I date sql/generateReports.sh -h date
+#   sql/get_bigquery_dates.sh runs pages | \
+#     xargs -I date sql/generate_reports.sh -h date
 #
-#   sql/getBigQueryDates.sh runs pages | \
-#     xargs -I date sql/generateReport.sh -d date/cruxDcl.json
+#   sql/get_bigquery_dates.sh runs pages | \
+#     xargs -I date sql/generate_report.sh -d date/cruxDcl.json
 
 set -eo pipefail
 

diff --git a/sql/timeseries/numUrls.sql b/sql/timeseries/numUrls.sql
@@ -0,0 +1,15 @@
+#standardSQL
+SELECT
+  SUBSTR(_TABLE_SUFFIX, 0, 10) AS date,
+  UNIX_DATE(CAST(REPLACE(SUBSTR(_TABLE_SUFFIX, 0, 10), '_', '-') AS DATE)) * 1000 * 60 * 60 * 24 AS timestamp,
+  IF(ENDS_WITH(_TABLE_SUFFIX, 'desktop'), 'desktop', 'mobile') AS client,
+  COUNT(0) AS urls
+FROM
+  `httparchive.summary_pages.*`
+GROUP BY
+  date,
+  timestamp,
+  client
+ORDER BY
+  date DESC,
+  client