bsky-parser 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 7aec83d0a4eabb6449e51290505c4497ea2f7b4e9f43c42d775ab573bd8e52c7
+  data.tar.gz: 5cef2aabe26ed6123550b7f6bb25d20266ab5e5f01caff8fd2973ec23146e574
+SHA512:
+  metadata.gz: 2bf88f931df9a6f9b664bb197afec3b51521bff88f612940f8f820d17a7b02bf412b3d83d0864dc412d4c6a241325f6a54dd24ac145118f37be79ed1decfb0fd
+  data.tar.gz: 3f197e06e7eaee4957c43cd693a076d8c5edd4e2943c61b5628f83f7e17a331ac9b10c8ab545bd6fccf8b6781b259dd326d75aec3d18877a3f2722d3bb8a8351

data/lib/bsky_parser.rb

@@ -0,0 +1,137 @@
+require "faraday"
+
+class BskyParser
+  class << self
+    BASE_URL = "https://bsky.social"
+
+    def parse(content)
+      parsed_content, mkdown_facets = process_markdown_links(content)
+
+      facets = mkdown_facets + tag_facets(parsed_content) + mention_facets(parsed_content) + url_facets(parsed_content)
+
+      [ parsed_content, facets]
+    end
+
+    private
+
+    def conn
+      @conn ||= Faraday.new(url: BASE_URL) do |f|
+        f.request :json
+      end
+    end
+
+    def tag_facets(content)
+      facets = []
+      tag_pattern = /#\S+/
+      matches = content.to_enum(:scan, tag_pattern).map { { tag: Regexp.last_match, indices: Regexp.last_match.offset(0) } }
+      matches.each do |match|
+        tag = match[:tag].to_s[1..-1] # Trim leading hashtag
+        indices = match[:indices]
+        facets << {
+          index: {
+            byteStart: indices[0],
+            byteEnd: indices[1]
+          },
+          features: [ {
+            "$type": "app.bsky.richtext.facet#tag",
+            tag: tag
+          } ]
+        }
+      end
+      facets
+    end
+
+    def mention_facets(content)
+      facets = []
+      # regex based on: https://atproto.com/specs/handle#handle-identifier-syntax
+      mention_pattern = /[$|\W](@([a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)/
+      matches = content.to_enum(:scan, mention_pattern).map { { handle: Regexp.last_match, indices: Regexp.last_match.offset(0) } }
+      matches.each do |match|
+        handle = match[:handle].to_s.strip[1..-1] # Trim leading @
+        indices = match[:indices]
+        resp = conn.get("/xrpc/com.atproto.identity.resolveHandle", { handle: handle })
+        handle_did = JSON.parse(resp.body)["did"]
+        facets << {
+          index: {
+            byteStart: indices[0],
+            byteEnd: indices[1]
+          },
+          features: [ {
+            "$type": "app.bsky.richtext.facet#mention",
+            did: handle_did
+          } ]
+        }
+      end
+      facets
+    end
+
+    def mkdown_links(content)
+      mkdown_links = []
+      url_pattern = /\[(?<text>[^\]]+)\]\((?<url>https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&\/\/=]*[-a-zA-Z0-9@%_\+~#\/\/=])?)\)/
+      matches = content.to_enum(:scan, url_pattern).map { Regexp.last_match }
+
+      mkdown_links = []
+      matches.each do |match|
+        mkdown_links << {
+          text: match[:text],
+          link: match[:url],
+          match: match.to_s
+        }
+      end
+      mkdown_links
+    end
+
+    def process_markdown_links(content)
+      facets = []
+      result_text = content.dup
+
+      links = mkdown_links(content)
+
+      links.reverse_each do |link|
+        start_pos = result_text.index(link[:match])
+
+        if start_pos
+          end_pos = start_pos + link[:match].length
+
+          facets << {
+            index: {
+              byteStart: start_pos,
+              byteEnd: start_pos + link[:text].length
+            },
+            features: [ {
+              "$type": "app.bsky.richtext.facet#link",
+              uri: link[:link]
+            } ]
+          }
+
+          result_text[start_pos...end_pos] = link[:text]
+        end
+      end
+
+      [ result_text, facets ]
+    end
+
+    def url_facets(content)
+      facets = []
+      # URL pattern from https://docs.bsky.app/docs/advanced-guides/post-richtext
+      url_pattern = /([$|\W])(https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&\/\/=]*[-a-zA-Z0-9@%_\+~#\/\/=])?)/
+      matches = content.to_enum(:scan, url_pattern).map { { url: Regexp.last_match, indices: Regexp.last_match.offset(0) } }
+      matches.each do |match|
+        url = match[:url].to_s[1..-1]
+        indices = match[:indices]
+        facets << {
+          index: {
+            byteStart: indices[0],
+            byteEnd: indices[1]
+          },
+          features: [ {
+            "$type": "app.bsky.richtext.facet#link",
+            uri: url
+          } ]
+        }
+      end
+      facets
+    end
+  end
+end
+

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: bsky-parser
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Jonathan Yeong
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2025-02-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: faraday
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.12.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.12.2
+description: 
+email: hey@jonathanyeong.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/bsky_parser.rb
+homepage: https://rubygems.org/gems/bsky_parser
+licenses:
+- MIT
+metadata:
+  source_code_uri: https://github.com/jonathanyeong/bsky-parser
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.3.6
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.22
+signing_key: 
+specification_version: 4
+summary: Parses text and generates Bluesky rich text facets
+test_files: []