bsky-parser 1.0.1 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7fdc55d4d3f8e9870d3269b17fd625dae9531097fd23cd28baf2818369aa2e56
-  data.tar.gz: 2ac103361580b7e635be487f4711175c7a4c48d2882d6bf53ebca63617b44112
+  metadata.gz: 9644188145dd0c8339bac95a664eb8571b4e0491ecb4a6caecca335e8cbeeee7
+  data.tar.gz: d79bf56d7329841971cc3e2d1d5149216603d3bdd863212a048e96835c49de2f
 SHA512:
-  metadata.gz: 93856e7fbd30936e2174248771bd7311ac0199578a083ae19b5a389973a4e2edaaf4166fceb0419141362803c4fc2ea616a5d5e8b42e1235c4b17674f6d2fab3
-  data.tar.gz: 967011def1d229208d152f14006f394341bed0797c21629dba8f0d5442e75b98b1e454f9f4a093c7f41348e120a5a598fb529af69f8ca25768f38bc4079341ee
+  metadata.gz: 378e2e528768da19d162f68ffdbf0f48e4fd3d1f4a47fab457e6a643707314f9b4422b4210d169004c3d59661a839bfd6a8b68d44e2eaa4e963c779e103a40e3
+  data.tar.gz: f33448b0ac7a7cb653e020ddda3c3a67ff3d1fa0a48133bd4449567398298b3b8d4f3783b3eb32816abbf28a36aee30c4da040839e3430a63eda7f95c5b9239b

data/.rubocop.yml

@@ -1,5 +1,3 @@
-inherit_from: .rubocop_todo.yml
-
 AllCops:
   TargetRubyVersion: 3.3
   NewCops: enable
@@ -19,9 +17,13 @@ Style/FrozenStringLiteralComment:
 
 Metrics/MethodLength:
   Max: 20
+  Exclude:
+    - "test/**/*"
 
 Metrics/AbcSize:
   Max: 30
+  Exclude:
+    - 'test/**/*'
 
 Metrics/ClassLength:
   Enabled: true

data/CHANGELOG.md

@@ -0,0 +1,23 @@
+## [Unreleased]
+
+## [1.0.2] - 2025-02-25
+
+### Fixed
+
+- Fix tag facet regex. Previously, it would match this entire string: `#hello!`. Now it correctly matches `#hello` without the `!`.
+- Regex patterns for mentions, tags, and URL facets correctly match when they appear at the beginning of text without requiring a leading space. For example, `"#hello"` is now properly detected as a tag, while mid-word occurrences like `"hello#hello"` are still ignored.
+- URL facet has been fixed to not match if it occurs mid-word. E.g. `hellohttps://example.com` no longer matches.
+- Correctly handle indices to take into account of leading space with multiple matches.
+
+## [1.0.1] - 2025-02-19
+
+### Added
+- More files from bundle gem generator. Originally, I followed the rubygem guide which listed less files.
+- Added LICENSE
+
+### Fixed
+- Fixed Rubocop linting rule errors.
+
+## [1.0.0] - 2025-02-19
+
+- Initial Release.

data/README.md

@@ -1,8 +1,5 @@
 # Bsky Parser
 
-> [!WARNING]
-> API is stable but development is still in progress. Aka no tests yet!
-
 Gem that will parse text content and generate Bluesky rich text facets.
 
 Facets supported:

data/lib/bsky_parser/facets/base_facet.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module BskyParser
+  module Facets
+    class BaseFacet
+      def self.process(content)
+        new(content).process
+      end
+
+      attr_reader :content
+
+      def initialize(content)
+        @content = content
+      end
+
+      def process
+        raise NotImplementedError, "#{self.class} has not implemented method '#{__method__}'"
+      end
+    end
+  end
+end

data/lib/bsky_parser/facets/markdown_link_facet.rb

@@ -0,0 +1,79 @@
+# frozen_string_literal: true
+
+require_relative "base_facet"
+
+module BskyParser
+  module Facets
+    class MarkdownLinkFacet < BaseFacet
+      # Override class method to return both modified content and facets
+      def self.process(content)
+        new(content).process
+      end
+
+      def process
+        facets = []
+        result_text = content.dup
+        links = find_markdown_links
+
+        links.each do |link|
+          start_pos = result_text.index(link[:match])
+          next unless start_pos
+
+          end_pos = start_pos + link[:match].length
+
+          # Replace markdown syntax with just the text
+          result_text[start_pos...end_pos] = link[:text]
+
+          facets << {
+            index: {
+              byteStart: start_pos,
+              byteEnd: start_pos + link[:text].length
+            },
+            features: [{
+              "$type": "app.bsky.richtext.facet#link",
+              uri: link[:link]
+            }]
+          }
+        end
+
+        [result_text, facets]
+      end
+
+      private
+
+      def url_pattern
+        # This url pattern is different to  URL facet url patten because
+        # we don't want to mix named and numbered capture groups.
+        # Instead we convert the numbered to non-capturing groups `?:`
+        %r{
+          \[
+          (?<text>[^\]]+)                # The link text inside square brackets
+          \]
+          \(
+            (?<url>
+              https?://                     # http:// or https://
+              (?:www\.)?                    # Optional www.
+              [-a-zA-Z0-9@:%._\+~#=]{1,256} # Domain name
+              \.
+              [a-zA-Z0-9()]{1,6}            # TLD
+              \b
+              (?:[-a-zA-Z0-9()@:%_\+.~#?&/=]* # URL path, params, etc.
+              [-a-zA-Z0-9@%_\+~#/=])?
+            )
+          \)
+        }x
+      end
+
+      def find_markdown_links
+        content.to_enum(:scan, url_pattern).map do
+          match = Regexp.last_match
+          {
+            text: match[:text],
+            link: match[:url],
+            match: match.to_s
+          }
+        end
+      end
+    end
+  end
+end

data/lib/bsky_parser/facets/mention_facet.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+require_relative "base_facet"
+
+module BskyParser
+  module Facets
+    class MentionFacet < BaseFacet
+      BASE_URL = "https://bsky.social"
+
+      def process
+        facets = []
+        # regex based on: https://atproto.com/specs/handle#handle-identifier-syntax
+        matches = content.to_enum(:scan, mention_pattern).map do
+          match = Regexp.last_match
+          start_offset = match[1]&.length || 0
+
+          {
+            handle: match[0],
+            indices: [match.begin(0) + start_offset, match.end(0)]
+          }
+        end
+
+        matches.each do |match|
+          handle = match[:handle].to_s.strip[1..] # Trim leading @
+          indices = match[:indices]
+          did = fetch_did(handle)
+          next if did.nil?
+
+          facets << build_facet(indices, did)
+        end
+        facets
+      end
+
+      private
+
+      def conn
+        @conn ||= Faraday.new(url: BASE_URL) do |f|
+          f.request :json
+        end
+      end
+
+      def fetch_did(handle)
+        resp = conn.get("/xrpc/com.atproto.identity.resolveHandle", { handle: handle })
+        JSON.parse(resp.body)["did"] if resp.success?
+      rescue Faraday::Error
+        # TODO: Introduce logging
+        nil
+      end
+
+      def mention_pattern
+        /(^|\s)(@([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])?)/
+      end
+
+      def build_facet(indices, handle_did)
+        {
+          index: {
+            byteStart: indices[0],
+            byteEnd: indices[1]
+          },
+          features: [{
+            "$type": "app.bsky.richtext.facet#mention",
+            did: handle_did
+          }]
+        }
+      end
+    end
+  end
+end

data/lib/bsky_parser/facets/tag_facet.rb

@@ -0,0 +1,48 @@
+# frozen_string_literal: true
+
+require_relative "base_facet"
+
+module BskyParser
+  module Facets
+    class TagFacet < BaseFacet
+      def process
+        facets = []
+        tag_pattern = /(^|\s)#[\w-]+/
+        matches = content.to_enum(:scan, tag_pattern).map do
+          match = Regexp.last_match
+          # If there's a space before the hashtag (match[1] contains a space),
+          # adjust the start position by adding 1
+          start_offset = match[1]&.length || 0
+
+          {
+            tag: match[0],
+            indices: [match.begin(0) + start_offset, match.end(0)]
+          }
+        end
+
+        matches.each do |match|
+          tag = match[:tag].to_s.lstrip[1..] # Trim leading space and hashtag
+          indices = match[:indices]
+          facets << build_facet(indices, tag)
+        end
+
+        facets
+      end
+
+      private
+
+      def build_facet(indices, tag)
+        {
+          index: {
+            byteStart: indices[0],
+            byteEnd: indices[1]
+          },
+          features: [{
+            "$type": "app.bsky.richtext.facet#tag",
+            tag: tag
+          }]
+        }
+      end
+    end
+  end
+end

data/lib/bsky_parser/facets/url_facet.rb

@@ -0,0 +1,61 @@
+# frozen_string_literal: true
+
+require_relative "base_facet"
+
+module BskyParser
+  module Facets
+    class URLFacet < BaseFacet
+      def process
+        facets = []
+
+        matches = content.to_enum(:scan, url_pattern).map do
+          match = Regexp.last_match
+          # Handles multiple urls
+          start_offset = match[1]&.length || 0
+
+          {
+            url: match[0],
+            indices: [match.begin(0) + start_offset, match.end(0)]
+          }
+        end
+
+        matches.each do |match|
+          url = match[:url].to_s.lstrip
+          indices = match[:indices]
+          facets << build_facet(indices, url)
+        end
+        facets
+      end
+
+      private
+
+      def url_pattern
+        # URI::RFC2396_PARSER.make_regexp has a complex regex with multiple capture groups
+        # Instead, use the URL pattern from https://docs.bsky.app/docs/advanced-guides/post-richtext
+        %r{
+          (^|\s)
+          (https?://
+            (www\.)?
+            [-a-zA-Z0-9@:%._\+~#=]{1,256}
+            \.
+            [a-zA-Z0-9()]{1,6}\b
+            ([-a-zA-Z0-9()@:%_\+.~#?&/=]*
+            [-a-zA-Z0-9@%_\+~#/=])?)
+        }x
+      end
+
+      def build_facet(indices, url)
+        {
+          index: {
+            byteStart: indices[0],
+            byteEnd: indices[1]
+          },
+          features: [{
+            "$type": "app.bsky.richtext.facet#link",
+            uri: url
+          }]
+        }
+      end
+    end
+  end
+end

data/lib/bsky_parser/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module BskyParser
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
 end

data/lib/bsky_parser.rb

@@ -1,145 +1,25 @@
 # frozen_string_literal: true
 
 require_relative "bsky_parser/version"
+require_relative "bsky_parser/facets/markdown_link_facet"
+require_relative "bsky_parser/facets/tag_facet"
+require_relative "bsky_parser/facets/url_facet"
+require_relative "bsky_parser/facets/mention_facet"
 
 require "faraday"
 
 module BskyParser
   class << self
-    BASE_URL = "https://bsky.social"
-
     def parse(content)
-      parsed_content, mkdown_facets = process_markdown_links(content)
+      parsed_content, mkdown_facets = Facets::MarkdownLinkFacet.process(content)
 
-      facets = mkdown_facets + tag_facets(parsed_content) + mention_facets(parsed_content) + url_facets(parsed_content)
+      facets =
+        mkdown_facets +
+        Facets::TagFacet.process(parsed_content) +
+        Facets::MentionFacet.process(parsed_content) +
+        Facets::URLFacet.process(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 do
-        { tag: Regexp.last_match, indices: Regexp.last_match.offset(0) }
-      end
-      matches.each do |match|
-        tag = match[:tag].to_s[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 do
-        { handle: Regexp.last_match, indices: Regexp.last_match.offset(0) }
-      end
-      matches.each do |match|
-        handle = match[:handle].to_s.strip[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)
-      url_pattern = %r{\[(?<text>[^\]]+)\]\((?<url>https?://(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&/=]*[-a-zA-Z0-9@%_\+~#/=])?)\)}
-      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])
-
-        next unless start_pos
-
-        end_pos = start_pos + link[:match].length
-
-        facets << {
-          index: {
-            byteStart: start_pos,
-            byteEnd: start_pos + link[:text].length
-          },
-          features: [{
-            "$type": "app.bsky.richtext.facet#link",
-            uri: link[:link]
-          }]
-        }
-
-        result_text[start_pos...end_pos] = link[:text]
-      end
-
-      [result_text, facets]
-    end
-
-    def url_facets(content)
-      facets = []
-      # URL pattern from https://docs.bsky.app/docs/advanced-guides/post-richtext
-      url_pattern = %r{([$|\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 do
-        { url: Regexp.last_match, indices: Regexp.last_match.offset(0) }
-      end
-      matches.each do |match|
-        url = match[:url].to_s[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

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bsky-parser
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Jonathan Yeong
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2025-02-19 00:00:00.000000000 Z
+date: 2025-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday
@@ -32,12 +32,17 @@ extra_rdoc_files: []
 files:
 - ".devcontainer/devcontainer.json"
 - ".rubocop.yml"
-- ".rubocop_todo.yml"
+- CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - LICENSE
 - README.md
 - Rakefile
 - lib/bsky_parser.rb
+- lib/bsky_parser/facets/base_facet.rb
+- lib/bsky_parser/facets/markdown_link_facet.rb
+- lib/bsky_parser/facets/mention_facet.rb
+- lib/bsky_parser/facets/tag_facet.rb
+- lib/bsky_parser/facets/url_facet.rb
 - lib/bsky_parser/version.rb
 - sig/bsky_parser.rbs
 homepage: https://github.com/jonathanyeong/bsky-parser

data/.rubocop_todo.yml

@@ -1,31 +0,0 @@
-# This configuration was generated by
-# `rubocop --auto-gen-config`
-# on 2025-02-19 04:07:09 UTC using RuboCop version 1.72.2.
-# The point is for the user to remove these configuration records
-# one by one as the offenses are removed from the code base.
-# Note that changes in the inspected code, or installation of new
-# versions of RuboCop, may require this file to be generated again.
-
-# Offense count: 1
-Lint/MixedRegexpCaptureTypes:
-  Exclude:
-    - 'lib/bsky_parser.rb'
-
-# Offense count: 1
-# Configuration parameters: CountComments, Max, CountAsOne, AllowedMethods, AllowedPatterns.
-Metrics/MethodLength:
-  Exclude:
-    - 'lib/bsky_parser.rb'
-
-# Offense count: 1
-# This cop supports unsafe autocorrection (--autocorrect-all).
-Style/MapIntoArray:
-  Exclude:
-    - 'lib/bsky_parser.rb'
-
-# Offense count: 3
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
-# URISchemes: http, https
-Layout/LineLength:
-  Max: 175