chupa-text-decomposer-html 1.0.4 → 1.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d18136db785fa061ef0bea3f17f8826a1ff55ed5020a591926e1700b91b9df38
-  data.tar.gz: 2c173149ac68d34756944ce98caa32f1dbc5bba4f86dab0461505bb90a5d406f
+  metadata.gz: 8011fcf3e4474139ed2b25cb2119ba4c1e2f757933ee2a9f2df6d50803d0ffb8
+  data.tar.gz: '0198e6902575d462b1384f98c75de279ba82b391a70ee58638788a4c302f142c'
 SHA512:
-  metadata.gz: 692141e0ed3d3d92729de8c47d62fa78ad6bc571070d293cdd8a7865e2d2366d82d68ef83121300dd92a82193b3db3ca83b7865ad6e0212c7e1b26e698830b13
-  data.tar.gz: 061e659f770c63f304cc7b697b6f3c512ea0c975eac35d55a9de9ad434820f056477275e4a240e058a42ace0187b1240290050bf83984049593003e309694411
+  metadata.gz: d891df99acd083ac16e6a03659317257e3bee19dda9b25bf6d0219f9c76a8b7504c1b786d2051fc2529b7c6318fba76b1a96b9b1788b034adc914223a0665e57
+  data.tar.gz: 0dc3fb7c8362f442d6b23763c94fc2dce72c8a88f754e6ed533558eda960a93b0d32de23878476f49e7a7d2bd90d86ecb598e88aed3367509d44ab00cf532336

data/Rakefile

@@ -1,6 +1,6 @@
-# -*- mode: ruby; coding: utf-8 -*-
+# -*- ruby -*-
 #
-# Copyright (C) 2013-2017  Kouhei Sutou <kou@clear-code.com>
+# Copyright (C) 2013-2026  Sutou Kouhei <kou@clear-code.com>
 #
 # This library is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -46,3 +46,13 @@ desc "Run tests"
 task :test do
   ruby("test/run-test.rb")
 end
+
+release_task = Rake.application["release"]
+# We use Trusted Publishing.
+release_task.prerequisites.delete("build")
+release_task.prerequisites.delete("release:rubygem_push")
+release_task_comment = release_task.comment
+if release_task_comment
+  release_task.clear_comments
+  release_task.comment = release_task_comment.gsub(/ and build.*$/, "")
+end

data/chupa-text-decomposer-html.gemspec

@@ -22,7 +22,7 @@ end
 
 Gem::Specification.new do |spec|
   spec.name = "chupa-text-decomposer-html"
-  spec.version = "1.0.4"
+  spec.version = "1.0.6"
   spec.homepage = "https://github.com/ranguba/chupa-text-decomposer-html"
   spec.authors = ["Kouhei Sutou"]
   spec.email = ["kou@clear-code.com"]

data/doc/text/news.md

@@ -1,5 +1,19 @@
 # News
 
+## 1.0.6: 2026-11-12
+
+### Fixes
+
+  * Fixed a bug that `Encoding::CompatibilityError` is raised on
+    detecting target with ASCII incompatible encoding body such as
+    ISO-2022-JP.
+
+## 1.0.5: 2024-09-22
+
+### Fixes
+
+  * Fixed typos.
+
 ## 1.0.4: 2024-09-22
 
 ### Improvements

data/lib/chupa-text/decomposers/html.rb

@@ -1,4 +1,4 @@
-# Copyright (C) 2013-2024  Sutou Kouhei <kou@clear-code.com>
+# Copyright (C) 2013-2026  Sutou Kouhei <kou@clear-code.com>
 #
 # This library is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -37,8 +37,11 @@ module ChupaText
         body = data.body
         return false if body.nil?
 
-        return true if body.start_with?("<!DOCTYPE html ")
-        return true if body.start_with?("<html")
+        # Compare as bytes because body may use an ASCII incompatible
+        # encoding such as ISO-2022-JP.
+        head = body.byteslice(0, 15).b
+        return true if head.start_with?("<!DOCTYPE html ")
+        return true if head.start_with?("<html")
 
         false
       end
@@ -108,8 +111,8 @@ module ChupaText
         candidates = [
           Encoding::EUC_JP,
           Encoding::WINDOWS_31J,
-          Encoding::UTF16_BE,
-          Encoding::UTF16_LE,
+          Encoding::UTF_16BE,
+          Encoding::UTF_16LE,
         ]
         candidates.each do |candidate|
           begin

data/test/test-html.rb

@@ -1,4 +1,4 @@
-# Copyright (C) 2013-2024  Sutou Kouhei <kou@clear-code.com>
+# Copyright (C) 2013-2026  Sutou Kouhei <kou@clear-code.com>
 #
 # This library is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -121,6 +121,26 @@ class TestHTML < Test::Unit::TestCase
           @decomposer.target?(create_data("<html"))
         end
       end
+
+      def test_iso_2022_jp
+        body = "<html><body>こんにちは</body></html>".encode("ISO-2022-JP")
+        assert do
+          @decomposer.target?(create_data(body))
+        end
+      end
+
+      def test_utf_16le
+        body = "<html><body>Hello</body></html>".encode("UTF-16LE")
+        assert do
+          not @decomposer.target?(create_data(body))
+        end
+      end
+
+      def test_text
+        assert do
+          not @decomposer.target?(create_data("Hello"))
+        end
+      end
     end
   end
 

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: chupa-text-decomposer-html
 version: !ruby/object:Gem::Version
-  version: 1.0.4
+  version: 1.0.6
 platform: ruby
 authors:
 - Kouhei Sutou
 bindir: bin
 cert_chain: []
-date: 2024-09-22 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: chupa-text
@@ -76,7 +76,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.0.dev
+rubygems_version: 4.0.20
 specification_version: 4
 summary: This is a ChupaText decomposer plugin for to extract text and meta-data from
   HTML.