Merge branch 'main' of github.com:HTTPArchive/almanac.httparchive.org…

… into production
HTTPArchive · Jan 17, 2021 · 39afac6 · 39afac6
2 parents 5eaaad9 + d18e78a
commit 39afac6
Show file tree

Hide file tree

Showing 74 changed files with 2,074 additions and 216 deletions.
diff --git a/README.md b/README.md
@@ -21,6 +21,7 @@ The Web Almanac is available in the original [English](https://almanac.httparchi
 - [Portuguese](https://almanac.httparchive.org/pt/)
 - [Russian](https://almanac.httparchive.org/ru/)
 - [Spanish](https://almanac.httparchive.org/es/)
+- [Ukrainian](https://almanac.httparchive.org/uk/)
 
 ## Contributing
 

diff --git a/sql/2020/05_Media/big_non_custom_metrics.sql b/sql/2020/05_Media/big_non_custom_metrics.sql
@@ -21,7 +21,7 @@ FROM (
     page,
     REGEXP_CONTAINS(body, r'(?i)<img[^><]*src=(?:\"|\')*data[:]image/(?:\"|\')*[^><]*>') AS has_img_data_uri,
     REGEXP_CONTAINS(body, r'(?i)<img[^><]*src=[^><]*>') AS has_img_src,
-    REGEXP_CONTAINS(body, r'(?i)<link[^><]*rel=(?:\"|\')*preconnect/(?:\"|\')*[^><]*>') AS rel_preconnect,
+    REGEXP_CONTAINS(body, r'(?i)<link[^><]*rel=(?:\"|\')*preconnect(?:\"|\')*[^><]*>') AS rel_preconnect,
     REGEXP_CONTAINS(body, r'(?i)<video[^><]*src=[^><]*>') AS has_video_src,
     REGEXP_CONTAINS(body, r'(?i)<video[^><]*>.*?<source[^><]*>.*?</video>') AS has_video_source,
     REGEXP_CONTAINS(body, r'(?i)<figure[^><]*>') AS has_figure,

diff --git a/sql/2020/16_Ecommerce/ecomm_covid_growth.sql b/sql/2020/16_Ecommerce/ecomm_covid_growth.sql
@@ -0,0 +1,60 @@
+#standardSQL
+# 13_03: Timeseries to show eCommerce growth acceleration due to Covid-19
+# Excluding apps which are not eCommerce platforms/vendors themselves but are used to identify eCommerce sites. These are signals added in Wappalyzer in 2020 to get better idea on % of eCommerce sites but these are not relevant for vendor % market share analysis
+SELECT
+  IF(ENDS_WITH(_TABLE_SUFFIX, '_desktop'), 'desktop', 'mobile') AS client,  
+  COUNT(DISTINCT url) AS freq,
+  total,
+  COUNT(DISTINCT url) / total AS pct,
+  2020 AS year,
+  LEFT(_TABLE_SUFFIX, 2) AS month,  
+FROM
+  `httparchive.technologies.2020_*`
+JOIN
+  (SELECT 
+      _TABLE_SUFFIX,
+      COUNT(DISTINCT url) AS total
+    FROM 
+      `httparchive.summary_pages.2020_*` 
+    GROUP BY 
+      _TABLE_SUFFIX)
+USING (_TABLE_SUFFIX)
+WHERE
+  category = 'Ecommerce'
+GROUP BY
+  client,
+  year,
+  month,
+  total 
+
+UNION ALL
+
+SELECT
+  IF(ENDS_WITH(_TABLE_SUFFIX, '_desktop'), 'desktop', 'mobile') AS client,  
+  COUNT(DISTINCT url) AS freq,
+  total,
+  COUNT(DISTINCT url) / total AS pct,
+  2019 AS year,
+  LEFT(_TABLE_SUFFIX, 2) AS month,  
+FROM
+  `httparchive.technologies.2019_*`
+JOIN
+  (SELECT 
+      _TABLE_SUFFIX,
+      COUNT(DISTINCT url) AS total
+    FROM 
+      `httparchive.summary_pages.2019_*` 
+    GROUP BY 
+      _TABLE_SUFFIX)
+USING (_TABLE_SUFFIX)
+WHERE
+  category = 'Ecommerce'
+GROUP BY
+  client,
+  year,
+  month,
+  total 
+
+ORDER BY
+  year DESC,
+  month DESC
diff --git a/sql/2020/16_Ecommerce/ecomm_vendors_covid_growth.sql b/sql/2020/16_Ecommerce/ecomm_vendors_covid_growth.sql
@@ -0,0 +1,38 @@
+#standardSQL
+# 13_04: Timeseries to show eCommerce vendors growth acceleration due to Covid-19
+# Excluding apps which are not eCommerce platforms/vendors themselves but are used to identify eCommerce sites. These are signals added in Wappalyzer in 2020 to get better idea on % of eCommerce sites but these are not relevant for vendor % market share analysis
+# Limiting to top 5000 records to continue further analysis in Google Sheets. Using HAVING clauses based on 'pct' results in missing data for certain months
+SELECT
+  IF(ENDS_WITH(_TABLE_SUFFIX, '_desktop'), 'desktop', 'mobile') AS client,  
+  app,
+  COUNT(DISTINCT url) AS freq,
+  total,
+  COUNT(DISTINCT url) / total AS pct,
+  LEFT(_TABLE_SUFFIX, 4) AS year,
+  SUBSTR(_TABLE_SUFFIX, 6, 2) AS month,  
+FROM
+  `httparchive.technologies.*`
+JOIN
+  (SELECT 
+      _TABLE_SUFFIX,
+      COUNT(DISTINCT url) AS total
+    FROM 
+      `httparchive.summary_pages.*` 
+    GROUP BY 
+      _TABLE_SUFFIX)
+USING (_TABLE_SUFFIX)
+WHERE
+  category = 'Ecommerce' AND 
+  (app != 'Cart Functionality' AND 
+   app != 'Google Analytics Enhanced eCommerce')
+GROUP BY
+  client,
+  app,
+  year,
+  month,
+  total 
+ORDER BY
+  pct DESC,
+  client DESC,
+  app DESC
+LIMIT 5000
diff --git a/src/config/2019.json b/src/config/2019.json
@@ -2,7 +2,7 @@
   "settings": [
     {
       "is_live": true,
-      "supported_languages": ["en","es","fr","hi","it","ja","nl","pt","ru","zh-CN","zh-TW"],
+      "supported_languages": ["en","es","fr","hi","it","ja","nl","pt","ru","uk","zh-CN","zh-TW"],
       "ebook_languages": ["en","ja"]
     }
   ],
@@ -695,6 +695,15 @@
       "github": "KJLarson",
       "twitter": "KaJLa47"
     },
+    "tymosh": {
+      "name": "Kate Tymoshkina",
+      "teams": [
+        "translators"
+      ],
+      "avatar_url": "https://avatars2.githubusercontent.com/u/25080897?v=4&s=200",
+      "github": "tymosh",
+      "linkedin": "tymosh"
+    },
     "khempenius": {
       "name": "Katie Hempenius",
       "teams": [

diff --git a/src/config/2020.json b/src/config/2020.json
@@ -2,7 +2,7 @@
   "settings": [
     {
       "is_live": true,
-      "supported_languages": ["en","es","fr","hi","it","ja","nl","pt","ru","zh-CN","zh-TW"],
+      "supported_languages": ["en","es","fr","hi","it","ja","nl","pt","ru","uk","zh-CN","zh-TW"],
       "ebook_languages": ["en"]
     }
   ],
@@ -39,8 +39,7 @@
           "part": "I",
           "chapter": "5",
           "title": "Media",
-          "slug": "media",
-          "todo": true
+          "slug": "media"
         },
         {
           "part": "I",
@@ -118,8 +117,7 @@
           "part": "III",
           "chapter": "16",
           "title": "Ecommerce",
-          "slug": "ecommerce",
-          "todo": true
+          "slug": "ecommerce"
         },
         {
           "part": "III",
@@ -232,6 +230,16 @@
       "website": "https://AhmadAwais.com",
       "github": "ahmadawais",
       "twitter": "MrAhmadAwais"
+    } ,
+    "alankent": {
+      "name": "Alan Kent",
+      "teams": [
+        "reviewers"
+      ],
+      "avatar_url": "https://avatars0.githubusercontent.com/u/5702163?v=4&s=200",
+      "website": "https://alankent.me",
+      "github": "alankent",
+      "twitter": "akent99"
     },
     "amedina": {
       "name": "Alberto Medina",
@@ -351,7 +359,9 @@
       ],
       "avatar_url": "https://avatars1.githubusercontent.com/u/6849494?v=4&s=200",
       "website": "https://benseymour.com",
-      "github": "bseymour"
+      "github": "bseymour",
+      "twitter": "bseymour",
+      "linkedin": "benseymour"
     },
     "bharatagsrwal": {
       "name": "Bharat Agarwal",
@@ -515,14 +525,6 @@
       "github": "dougsillars",
       "twitter": "dougsillars"
     },
-    "drewzboto": {
-      "name": "Drewz",
-      "teams": [
-        "reviewers"
-      ],
-      "avatar_url": "https://avatars2.githubusercontent.com/u/1111351?v=4&s=200",
-      "github": "drewzboto"
-    },
     "dsadhanala": {
       "name": "Durga Prasad Sadhanala",
       "teams": [
@@ -571,6 +573,16 @@
       "github": "ericwbailey",
       "twitter": "ericwbailey"
     },
+    "eeeps": {
+      "name": "Eric Portis",
+      "teams": [
+        "authors"
+      ],
+      "avatar_url": "https://avatars1.githubusercontent.com/u/3441390?v=4&s=200",
+      "website": "https://ericportis.com/",
+      "github": "eeeps",
+      "twitter": "etportis"
+    },
     "estelle": {
       "name": "Estelle Weyl",
       "teams": [
@@ -685,7 +697,7 @@
     "jrharalson": {
       "name": "Jason Haralson",
       "teams": [
-        "reviewers",
+        "authors",
         "analysts"
       ],
       "avatar_url": "https://avatars1.githubusercontent.com/u/7421844?v=4&s=200",
@@ -757,6 +769,15 @@
       "github": "thefoxis",
       "twitter": "fox"
     },
+    "tymosh": {
+      "name": "Kate Tymoshkina",
+      "teams": [
+        "translators"
+      ],
+      "avatar_url": "https://avatars2.githubusercontent.com/u/25080897?v=4&s=200",
+      "github": "tymosh",
+      "linkedin": "tymosh"
+    },
     "khempenius": {
       "name": "Katie Hempenius",
       "teams": [
@@ -955,6 +976,16 @@
       "github": "natedame",
       "twitter": "seonate"
     },
+    "Navaneeth-akam": {
+      "name": "Navaneeth Krishna M P",
+      "teams": [
+        "reviewers"
+       ],
+      "avatar_url": "https://avatars1.githubusercontent.com/u/69532755?s=200&v=4",
+      "website": "http://www.nparthas.com/",
+      "github": "Navaneeth-akam",
+      "twitter": "Navanee55755217"
+    },
     "phacks": {
       "name": "Nicolas Goutay",
       "teams": [
@@ -1155,7 +1186,8 @@
     "rockeynebhwani": {
       "name": "Rockey Nebhwani",
       "teams": [
-        "authors"
+        "authors",
+        "analysts"
       ],
       "avatar_url": "https://avatars1.githubusercontent.com/u/1718757?v=4&s=200",
       "github": "rockeynebhwani",
@@ -1293,7 +1325,7 @@
         "authors"
       ],
       "avatar_url": "https://avatars1.githubusercontent.com/u/2042718?v=4&s=200",
-      "website": "https://www.fullstacktraining.com",
+      "website": "https://tamas.io",
       "github": "tpiros",
       "twitter": "tpiros"
     },