jekyll-stats 0.2.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab21769c8de5f9ff18a6ad985b0a0240dbf00c29be751b3f0aee27f8c313a257
-  data.tar.gz: '071349d927967afb2c9164d9382a56175d9aa106d818ac267d32930169aca4e7'
+  metadata.gz: 5c9845c1c909307a6ee955d23c51412d24c1a12789d7144a817f8ac619bdaa91
+  data.tar.gz: ec4fdcf95f6b96fca65dac435e0edd307fff6c5ac7ea416e44bb473a0ee29d85
 SHA512:
-  metadata.gz: c1f4bc991fa3230b0e0c3d5c0a471495738a0a853021ba257cc5501cf6748fb8ed567892b0005f5166071c3a2e2aab398380b83fbcb90a11819d2896583957ce
-  data.tar.gz: de7e7fc767997a55e345f63df9214fc46501790ff9a3f7fba3ee166968f43ce40ec1fec8ed8f4002a4c39a3c5de95ab6bc06307ecb3881fc19b191466b0fc28c
+  metadata.gz: b88c1fb528e0fa65d53c7d22a3580a875b40b18d74f418128457c8faaa8b3bce8fa323e675ae5c64f06d19933cdb85731d3d8218016559c4f35a2b0d79ef4066
+  data.tar.gz: 279c44108897e9686dba753f11aadb8947bdc1fb95ae466ff8bbc5f306364689168ea476ab2cd1500982c4e92e03c62a9d814f6ba91f2599b4d52dea6dd6a494

data/CHANGELOG.md

@@ -1,5 +1,16 @@
 ## [Unreleased]
 
+## [0.4.0] - 2026-08-30
+
+- Add `external_links` to stats: total, unique, and per-domain counts of outbound links
+- Each domain entry includes `posts` (distinct source posts) so single-post link lists are visible
+
+## [0.3.0] - 2026-08-30
+
+- Add `internal_links` to stats: posts ranked by inbound links from other posts
+- Source posts can be excluded by tag via `jekyll-stats.link_source_exclude_tags` in `_config.yml`
+- `--json` no longer prints "Loading site..." to stdout, so output pipes cleanly to `jq`
+
 ## [0.2.0] - 2026-01-03
 
 - Add `--tags` / `-t` option to filter stats by tags

data/README.md

@@ -81,10 +81,39 @@ The `--save` flag writes `_data/stats.json` with this structure:
   "posts_by_day_of_week": { "monday": 23, "tuesday": 18, "wednesday": 15, "thursday": 20, "friday": 22, "saturday": 14, "sunday": 15 },
   "tags": [{ "name": "ruby", "count": 34 }, { "name": "opensource", "count": 28 }],
   "categories": [{ "name": "code", "count": 45 }, { "name": "cars", "count": 32 }],
+  "internal_links": [
+    { "url": "/2024/01/foo", "title": "Foo", "inbound_count": 7, "inbound_from": ["/2024/03/bar", "/2024/06/baz"] }
+  ],
+  "external_links": {
+    "total": 4637,
+    "unique": 3723,
+    "domains": [
+      { "host": "github.com", "count": 1380, "posts": 172 },
+      { "host": "en.wikipedia.org", "count": 94, "posts": 61 }
+    ]
+  },
   "drafts_count": 3
 }
 ```
 
+### Internal links
+
+`internal_links` lists posts ranked by how many other posts link to them. It matches markdown and `<a href>` links that point at another post's URL, either as a root-relative path or an absolute URL under your site's `url:`. Self-links and duplicate links from the same source post are ignored.
+
+To stop link-list style posts (year in review, roundups) inflating the counts, exclude them as sources by tag in `_config.yml`:
+
+```yaml
+jekyll-stats:
+  link_source_exclude_tags:
+    - roundup
+```
+
+Excluded posts still appear as targets; they just don't contribute outbound links.
+
+### External links
+
+`external_links` counts outbound `http(s)` links to hosts other than your site's `url:`. `total` is raw link occurrences, `unique` is distinct URLs, and each `domains` entry has `count` (distinct URLs at that host) and `posts` (distinct source posts). A high `count` with a low `posts` means one or two posts account for most links to that host. The same `link_source_exclude_tags` config applies.
+
 ## Building a Stats Page
 
 After running `jekyll stats --save`, create a stats page using Liquid:

data/lib/jekyll-stats/command.rb

@@ -25,6 +25,7 @@ module JekyllStats
       end
 
       def process(options)
+        Jekyll.logger.log_level = :error if options["json"]
         options = configuration_from_options(options)
         site = Jekyll::Site.new(options)
 

data/lib/jekyll-stats/formatter.rb

@@ -34,6 +34,16 @@ module JekyllStats
         lines << categories_line
       end
 
+      if stats[:internal_links].any?
+        lines << ""
+        lines << most_linked_posts
+      end
+
+      if stats[:external_links][:domains].any?
+        lines << ""
+        lines << top_external_domains
+      end
+
       if stats[:drafts_count].positive?
         lines << ""
         lines << "Drafts: #{stats[:drafts_count]}"
@@ -99,6 +109,24 @@ module JekyllStats
       "Categories:\n  #{cat_strs.join(" | ")}"
     end
 
+    def most_linked_posts
+      links = stats[:internal_links].first(5)
+      lines = ["Most Linked Posts:"]
+      links.each do |l|
+        lines << "  #{l[:inbound_count].to_s.rjust(2)}  #{truncate(l[:title], 50)}"
+      end
+      lines.join("\n")
+    end
+
+    def top_external_domains
+      ext = stats[:external_links]
+      lines = ["External Links: #{format_number(ext[:total])} (#{format_number(ext[:unique])} unique, #{ext[:domains].size} hosts)"]
+      ext[:domains].first(5).each do |d|
+        lines << "  #{d[:count].to_s.rjust(4)}  #{d[:host]} (#{d[:posts]} posts)"
+      end
+      lines.join("\n")
+    end
+
     def format_number(n)
       n.to_s.reverse.gsub(/(\d{3})(?=\d)/, '\\1,').reverse
     end

data/lib/jekyll-stats/stats_calculator.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require "uri"
+
 module JekyllStats
   class StatsCalculator
     WORDS_PER_MINUTE = 200
@@ -40,6 +42,8 @@ module JekyllStats
         posts_by_day_of_week: posts_by_day_of_week(posts),
         tags: tag_counts(posts),
         categories: category_counts(posts),
+        internal_links: internal_links(posts),
+        external_links: external_links(posts),
         drafts_count: drafts_count
       }
     end
@@ -147,6 +151,74 @@ module JekyllStats
             .map { |name, count| { name: name, count: count } }
     end
 
+    def internal_links(posts)
+      by_url = posts.each_with_object({}) { |p, h| h[normalize_url(p.url)] = p }
+      exclude = Array(site.config.dig("jekyll-stats", "link_source_exclude_tags")).map { |t| normalize_tag(t) }
+      site_url = site.config["url"].to_s
+
+      inbound = Hash.new { |h, k| h[k] = [] }
+      posts.each do |post|
+        post_tags = (post.data["tags"] || []).map { |t| normalize_tag(t) }
+        next if exclude.any? && (exclude & post_tags).any?
+
+        post.content.to_s.scan(%r{(?:\]\(|<a\s[^>]*href=["'])([^"'\s)]+)}i).flatten.each do |href|
+          href = href.delete_prefix(site_url) unless site_url.empty?
+          next unless href.start_with?("/")
+
+          target = by_url[normalize_url(href)]
+          next unless target
+          next if target == post
+
+          inbound[target] << post
+        end
+      end
+
+      inbound.map { |target, sources|
+        {
+          url: target.url,
+          title: target.data["title"] || "(untitled)",
+          inbound_count: sources.uniq.size,
+          inbound_from: sources.uniq.map(&:url).sort
+        }
+      }.sort_by { |r| [-r[:inbound_count], r[:url]] }
+    end
+
+    def external_links(posts)
+      exclude = Array(site.config.dig("jekyll-stats", "link_source_exclude_tags")).map { |t| normalize_tag(t) }
+      site_host = (URI.parse(site.config["url"].to_s).host rescue nil)
+
+      urls = []
+      posts.each do |post|
+        post_tags = (post.data["tags"] || []).map { |t| normalize_tag(t) }
+        next if exclude.any? && (exclude & post_tags).any?
+
+        post.content.to_s.scan(%r{(?:\]\(|<a\s[^>]*href=["'])(https?://[^"'\s)]+)}i).flatten.each do |href|
+          host = URI.parse(href).host rescue nil
+          next if host.nil?
+          next if site_host && host == site_host
+
+          urls << [href, host, post]
+        end
+      end
+
+      unique = urls.uniq { |u, _, _| u }
+      domains = urls.group_by { |_, h, _| h }
+                    .map { |host, us|
+                      {
+                        host: host,
+                        count: us.map { |u, _, _| u }.uniq.size,
+                        posts: us.map { |_, _, p| p }.uniq.size
+                      }
+                    }
+                    .sort_by { |d| [-d[:count], d[:host]] }
+
+      { total: urls.size, unique: unique.size, domains: domains }
+    end
+
+    def normalize_url(url)
+      url.sub(/[#?].*\z/, "").sub(%r{/index\.html\z}, "").chomp(".html").chomp("/")
+    end
+
     def drafts_count
       return 0 unless site.respond_to?(:drafts) && site.drafts
 
@@ -171,6 +243,8 @@ module JekyllStats
         posts_by_day_of_week: %w[sunday monday tuesday wednesday thursday friday saturday].each_with_object({}) { |d, h| h[d] = 0 },
         tags: [],
         categories: [],
+        internal_links: [],
+        external_links: { total: 0, unique: 0, domains: [] },
         drafts_count: 0
       }
     end

data/lib/jekyll-stats/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module JekyllStats
-  VERSION = "0.2.0"
+  VERSION = "0.4.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jekyll-stats
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Andrew Nesbitt
@@ -77,7 +77,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.1
+rubygems_version: 4.0.17
 specification_version: 4
 summary: Jekyll plugin that generates site statistics
 test_files: []