coelacanth 0.5.0 → 0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 06a629b2865e5c4be5508a92637b2824bce0922b2de1209cee7c8f358ea8b438
-  data.tar.gz: 43eac188f8c3d27e975753ff459c444d9ca49dc6e83aa8d067dca75b3223db87
+  metadata.gz: 94493e66b4aae51d1790f03eb89c95d2ec1861b9d150c1001bba7554a1b37ab7
+  data.tar.gz: acdd939524543ec62740e153774c44f5fcdee11d30a9bd5ca4e6bcabe2f65398
 SHA512:
-  metadata.gz: 4dc3c36802dce0be0e9deb9debdeccb5840bafa44a2613e6a59a270242b16f7f977d44b66a1e47472b9edf5a2a4026d057ffc91a490a776118dd493490e5ca9f
-  data.tar.gz: 3e558a85ab45b8f738be4c993413c279c7cb46bca7e44399e8fd40d1aa5e764b90865bbc51c7b38ad62be7501605e4f9d6edd3c0e8885ce8fe81830fda36d362
+  metadata.gz: 05b8789bd0bf8a23cb678b9f17349a403c0f1e7017903dea14ae13dbea1df1204a3a5cdd184c70e86e0d7366dce67cabbbd528846c2c498953088c1309830421
+  data.tar.gz: 047d1acabd38e890579947bd7311178ab0197089acd0185d5dbfa0628bbe6a5ad003c330e786c2d82d44fbada5b3ed13882178b50cba86c74ed2e2e12a527199

data/CHANGELOG.md

@@ -4,9 +4,11 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [v0.5.0] - 2025-11-08
-### :sparkles: New Features
-- [`d34ef32`](https://github.com/slidict/coelacanth/commit/d34ef32dbb969f7ef86dce6cd587c44a848ee32d) - add YouTube preprocessing support *(commit by [@yubele](https://github.com/yubele))*
-- [`2a566ad`](https://github.com/slidict/coelacanth/commit/2a566adeaaa5b813fded4b9ebd8ce8d90d43ee7c) - add morphological analysis for body markdown *(commit by [@yubele](https://github.com/yubele))*
+## [v0.6.1] - 2026-06-15
+### :bug: Bug Fixes
+- [`f387ef9`](https://github.com/slidict/coelacanth/commit/f387ef997e0c383458a4fd0384f74883fcb63f37) - Update gem-push.yml *(commit by [@abechan1](https://github.com/abechan1))*
 
-[v0.5.0]: https://github.com/slidict/coelacanth/compare/v0.4.3...v0.5.0
+### :wrench: Chores
+- [`4ad8456`](https://github.com/slidict/coelacanth/commit/4ad8456deba3aea4e6eea8836d6bdf728fbbdb70) - Bump version to 0.6.1 *(commit by [@abechan1](https://github.com/abechan1))*
+
+[v0.6.1]: https://github.com/slidict/coelacanth/compare/v0.6.0...v0.6.1

data/README.md

@@ -84,6 +84,20 @@ result[:screenshot] # => PNG screenshot as a binary string
 result[:response]   # => HTTP status, headers, and final URL
 ```
 
+# Plain-text morphology
+
+You can run the morphological analyzer without fetching a page by passing plain
+text:
+
+```ruby
+Coelacanth.morphological_analysis("これはテストです。 Testing morphology twice.")
+# => [
+#      { token: "testing morphology twice", score: 1.23, count: 2 },
+#      { token: "テスト", score: 1.02, count: 1 },
+#      ...
+#    ]
+```
+
 The returned hash includes:
 
 - `:extraction` – output from `Coelacanth::Extractor`, including title, Markdown body (`body_markdown`,
@@ -129,7 +143,7 @@ Runtime configuration is stored in `config/coelacanth.yml`. Environments inherit
 
 ```yaml
 development:
-  client: "ferrum" # Options: "ferrum", "screenshot_one"
+  client: "ferrum" # Options: "ferrum", "screenshot_one", "gotenberg"
   remote_client:
     ws_url: "ws://chrome:3000/chrome"
     timeout: 10
@@ -141,6 +155,13 @@ development:
       User-Agent: "<%= ENV.fetch("COELACANTH_REMOTE_CLIENT_USER_AGENT", "Coelacanth Chrome Extension") %>"
   screenshot_one:
     key: "<%= ENV.fetch("COELACANTH_SCREENSHOT_ONE_API_KEY", "your_screenshot_one_api_key_here") %>"
+  gotenberg:
+    url: "<%= ENV.fetch("COELACANTH_GOTENBERG_URL", "http://gotenberg:3000") %>"
+    open_timeout: 5
+    read_timeout: 30
+    wait_delay: "<%= ENV.fetch("COELACANTH_GOTENBERG_WAIT_DELAY", "") %>"
+    user_agent: "<%= ENV.fetch("COELACANTH_GOTENBERG_USER_AGENT", "") %>"
+    extra_http_headers:
   youtube:
     api_key: "<%= ENV.fetch("COELACANTH_YOUTUBE_API_KEY", "") %>"
   morphology:
@@ -157,6 +178,9 @@ development:
 - **Ferrum client** – Requires a running Chrome instance that exposes the DevTools protocol via WebSocket. Configure the URL,
   timeout, the network idle timeout, and any headers to inject.
 - **ScreenshotOne client** – Supply an API key to offload screenshot capture to [ScreenshotOne](https://screenshotone.com/).
+- **Gotenberg client** – Set `client: "gotenberg"` to capture screenshots through Gotenberg's Chromium URL screenshot
+  endpoint. Configure `gotenberg.url`, request timeouts, an optional `wait_delay`, an optional screenshot `user_agent`,
+  and optional `extra_http_headers`.
 - **Eyecatch image extraction** – Representative images are discovered automatically by checking Open Graph/Twitter metadata,
   Schema.org JSON-LD payloads, and high-signal `<img>` elements (hero/cover images, large dimensions, etc.). No manual XPath
   maintenance is required.
@@ -193,6 +217,9 @@ export COELACANTH_REMOTE_CLIENT_AUTHORIZATION="Bearer <token>"
 
 export COELACANTH_REMOTE_CLIENT_USER_AGENT="Coelacanth Chrome Extension"
 export COELACANTH_SCREENSHOT_ONE_API_KEY="your_screenshot_one_api_key_here"
+export COELACANTH_GOTENBERG_URL="http://gotenberg:3000"
+export COELACANTH_GOTENBERG_WAIT_DELAY="2s"
+export COELACANTH_GOTENBERG_USER_AGENT="Coelacanth Chrome Extension"
 export COELACANTH_YOUTUBE_API_KEY="your_youtube_data_api_key"
 ```
 
@@ -216,6 +243,10 @@ YouTube, so non-video pages continue to behave as before.
 When using Docker Compose, you can create a `.env` file or export the variables in your environment so the `app` service picks
 them up automatically.
 
+Docker Compose also starts a `gotenberg` service and passes `COELACANTH_GOTENBERG_URL` to the `app` service by default.
+To try that path locally, set `client: "gotenberg"` in `config/coelacanth.yml` or export the equivalent environment-specific
+configuration before running the app container.
+
 If you are working inside Docker, make sure the `UID` environment variable matches your host user by exporting it in your shell
 startup file:
 

data/compose.yml

@@ -1,25 +1,34 @@
-networks:
-  app-tier:
-    driver: bridge
-services:
-  app:
+networks:
+  app-tier:
+    driver: bridge
+services:
+  app:
     environment:
       - UID=${UID}
       - COELACANTH_REMOTE_CLIENT_AUTHORIZATION=${COELACANTH_REMOTE_CLIENT_AUTHORIZATION:-}
       - COELACANTH_REMOTE_CLIENT_USER_AGENT=${COELACANTH_REMOTE_CLIENT_USER_AGENT:-}
       - COELACANTH_SCREENSHOT_ONE_API_KEY=${COELACANTH_SCREENSHOT_ONE_API_KEY:-}
-    tty: true
-    stdin_open: true
-    build:
-      context: .
-      dockerfile: Dockerfile
-    volumes:
-      - ./:/app:cached
-    working_dir: /app
-    command: bash
-    networks:
-      - app-tier
-  chrome:
-    image: browserless/chrome:latest
-    networks:
-      - app-tier
+      - COELACANTH_GOTENBERG_URL=${COELACANTH_GOTENBERG_URL:-http://gotenberg:3000}
+      - COELACANTH_GOTENBERG_WAIT_DELAY=${COELACANTH_GOTENBERG_WAIT_DELAY:-}
+      - COELACANTH_GOTENBERG_USER_AGENT=${COELACANTH_GOTENBERG_USER_AGENT:-}
+    tty: true
+    stdin_open: true
+    build:
+      context: .
+      dockerfile: Dockerfile
+    volumes:
+      - ./:/app:cached
+    working_dir: /app
+    command: bash
+    depends_on:
+      - gotenberg
+    networks:
+      - app-tier
+  chrome:
+    image: browserless/chrome:latest
+    networks:
+      - app-tier
+  gotenberg:
+    image: gotenberg/gotenberg:8
+    networks:
+      - app-tier

data/config/coelacanth.yml

@@ -1,5 +1,5 @@
 development: &development
-  client: "ferrum" # Options: "ferrum", "screenshot_one"
+  client: "ferrum" # Options: "ferrum", "screenshot_one", "gotenberg"
   remote_client:
     ws_url: "ws://chrome:3000/chrome"
     timeout: 10 # seconds
@@ -11,6 +11,13 @@ development: &development
       User-Agent: "<%= ENV.fetch("COELACANTH_REMOTE_CLIENT_USER_AGENT", "Coelacanth Chrome Extension") %>"
   screenshot_one:
     key: "<%= ENV.fetch("COELACANTH_SCREENSHOT_ONE_API_KEY", "your_screenshot_one_api_key_here") %>"
+  gotenberg:
+    url: "<%= ENV.fetch("COELACANTH_GOTENBERG_URL", "http://gotenberg:3000") %>"
+    open_timeout: 5
+    read_timeout: 30
+    wait_delay: "<%= ENV.fetch("COELACANTH_GOTENBERG_WAIT_DELAY", "") %>"
+    user_agent: "<%= ENV.fetch("COELACANTH_GOTENBERG_USER_AGENT", "") %>"
+    extra_http_headers:
   youtube:
     api_key: "<%= ENV.fetch("COELACANTH_YOUTUBE_API_KEY", "") %>"
   morphology:

data/lib/coelacanth/client/ferrum.rb

@@ -5,8 +5,8 @@ require "ferrum"
 module Coelacanth::Client
   # Coelacanth::Client
   class Ferrum < Coelacanth::Client::Base
-    def initialize(url)
-      super(url)
+    def initialize(url, config = Coelacanth.config)
+      super(url, config)
       remote_client.goto(url)
     end
 

data/lib/coelacanth/client/gotenberg.rb

@@ -0,0 +1,89 @@
+# frozen_string_literal: true
+
+require "json"
+require "net/http"
+require "uri"
+
+require_relative "../http"
+
+module Coelacanth::Client
+  # Client for capturing screenshots through a Gotenberg Chromium service.
+  class Gotenberg < Coelacanth::Client::Base
+    SCREENSHOT_URL_PATH = "/forms/chromium/screenshot/url"
+
+    def get_response
+      uri = URI.parse(@url)
+      response = Coelacanth::HTTP.get_response(
+        uri,
+        open_timeout: Coelacanth::HTTP::DEFAULT_OPEN_TIMEOUT,
+        read_timeout: Coelacanth::HTTP::DEFAULT_READ_TIMEOUT
+      )
+      @origin_response = response
+      @status_code = response.code.to_i
+
+      return response.body if response.is_a?(Net::HTTPSuccess)
+
+      Coelacanth::HTTP.raise_http_error(uri, response)
+    end
+
+    def get_screenshot
+      response = Net::HTTP.start(
+        endpoint_uri.host,
+        endpoint_uri.port,
+        use_ssl: endpoint_uri.scheme == "https",
+        open_timeout: open_timeout,
+        read_timeout: read_timeout
+      ) do |http|
+        http.request(screenshot_request)
+      end
+
+      return response.body if response.is_a?(Net::HTTPSuccess)
+
+      raise "Failed to fetch screenshot from Gotenberg: #{response.code} #{response.message}"
+    rescue Net::OpenTimeout, Net::ReadTimeout, Timeout::Error => e
+      raise Coelacanth::TimeoutError, "Gotenberg screenshot request timed out: #{e.message}"
+    end
+
+    private
+
+    def screenshot_request
+      request = Net::HTTP::Post.new(endpoint_uri)
+      request.set_form(gotenberg_form_fields, "multipart/form-data")
+      request
+    end
+
+    def gotenberg_form_fields
+      fields = [["url", @url]]
+      wait_delay = @config.read("gotenberg.wait_delay")
+      user_agent = @config.read("gotenberg.user_agent")
+      extra_http_headers = @config.read("gotenberg.extra_http_headers")
+
+      fields << ["waitDelay", wait_delay] if present?(wait_delay)
+      fields << ["userAgent", user_agent] if present?(user_agent)
+      if extra_http_headers && extra_http_headers.any?
+        fields << ["extraHttpHeaders", extra_http_headers.to_json]
+      end
+      fields
+    end
+
+    def endpoint_uri
+      @endpoint_uri ||= URI.join(base_url, SCREENSHOT_URL_PATH)
+    end
+
+    def base_url
+      @config.read("gotenberg.url") || "http://localhost:3000"
+    end
+
+    def open_timeout
+      @config.read("gotenberg.open_timeout") || Coelacanth::HTTP::DEFAULT_OPEN_TIMEOUT
+    end
+
+    def read_timeout
+      @config.read("gotenberg.read_timeout") || 30
+    end
+
+    def present?(value)
+      !value.nil? && value.to_s.strip != ""
+    end
+  end
+end

data/lib/coelacanth/extractor/morphological_analyzer.rb

@@ -64,6 +64,10 @@ module Coelacanth
         @config = config
       end
 
+      def call_text(text, title: nil)
+        call(node: nil, title: title, markdown: text)
+      end
+
       def call(node:, title:, markdown:)
         stats = Hash.new do |hash, key|
           hash[key] = {

data/lib/coelacanth/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Coelacanth
-  VERSION = "0.5.0"
+  VERSION = "0.6.1"
 end

data/lib/coelacanth.rb

@@ -4,6 +4,7 @@ require "net/http"
 require_relative "coelacanth/configure"
 require_relative "coelacanth/client/base"
 require_relative "coelacanth/client/ferrum"
+require_relative "coelacanth/client/gotenberg"
 require_relative "coelacanth/client/screenshot_one"
 require_relative "coelacanth/dom"
 require_relative "coelacanth/extractor"
@@ -21,7 +22,7 @@ module Coelacanth
   class RobotsDisallowedError < StandardError; end
 
   def self.analyze(url)
-    client_class = config.read("client") == "screenshot_one" ? Client::ScreenshotOne : Client::Ferrum
+    client_class = client_class_for(config.read("client"))
     @client = client_class.new(url)
     regular_url = Redirect.new.resolve_redirect(url)
     response = begin
@@ -47,7 +48,24 @@ module Coelacanth
     }
   end
 
+  def self.client_class_for(client_name)
+    case client_name
+    when "screenshot_one"
+      Client::ScreenshotOne
+    when "gotenberg"
+      Client::Gotenberg
+    else
+      Client::Ferrum
+    end
+  end
+
   def self.config
     @config ||= Configure.new
   end
+
+  def self.morphological_analysis(text, title: nil)
+    Extractor::MorphologicalAnalyzer
+      .new(config: config)
+      .call_text(text, title: title)
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: coelacanth
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.1
 platform: ruby
 authors:
 - Yusuke
@@ -33,6 +33,7 @@ files:
 - lib/coelacanth.rb
 - lib/coelacanth/client/base.rb
 - lib/coelacanth/client/ferrum.rb
+- lib/coelacanth/client/gotenberg.rb
 - lib/coelacanth/client/screenshot_one.rb
 - lib/coelacanth/configure.rb
 - lib/coelacanth/dom.rb