mechanize 2.8.0 → 2.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d7df2fdd2030e028d6107b3b54f94f788deba04b9615cb719ef2113291270d1c
-  data.tar.gz: ab12e971c446e5977662076f39711298b5311ef12fe54612855433e5e926fa46
+  metadata.gz: 53105ca453eb763c9cb80bea61508bbc08e500f96aceae911191490e4bb03af5
+  data.tar.gz: f5e0f84257bc299060775ce26d52b80d89153db95d3bfa98d8bfbdc1c3cb5fce
 SHA512:
-  metadata.gz: 50f065469eb756a860e5c02b6e2d31cd5f25e0da2db9c4e9dddd018a96fb8fe4bb209ffd70c0e51c777ede12245faff86568a9e9044dd006d61d3514cd35660c
-  data.tar.gz: 6db1eaffd62dc89449721ad9d06dbc5d0f8d15f24b49cf9be84a3f88dc1bd91a41e1774aef12bdc9933e3b8e0d5b0050cf4dbaa675db6131f7723b3713921630
+  metadata.gz: 4a55d7aedbc2e81ed13d073c6ff63b60fb4ad060c771589c0024abb3b02c55ee5be54fa5c44b60c78dc3d201e31358c1f9a4922befff223c5f68befb462a4a6a
+  data.tar.gz: cf5967ce52c29e352dc820d5fd943434d37fe279a2ae957531f88f96a23ce7b7c206066c236e5308b912c6757ca8e130e354d26f7dd90ed529522aa7cc8be24a

data/.github/workflows/ci-test.yml

@@ -14,7 +14,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        ruby-version: ["2.5", "2.6", "2.7", "3.0", "jruby"]
+        ruby-version: ["2.5", "2.6", "2.7", "3.0", "jruby", "truffleruby-head"]
 
     runs-on: ubuntu-latest
     steps:

data/CHANGELOG.md

@@ -1,19 +1,30 @@
 # Mechanize CHANGELOG
 
+## 2.8.1 / 2021-05-09
+
+### Fix
+
+* Gracefully handle parsing errors that contain an invalid byte sequence. Previously, if libxml2 registered a parsing error that itself contained invalid encoding, an exception might be raised. (#553)
+
+
 ## 2.8.0 / 2021-04-01
 
-* Requirements
-  * Mechanize now requires Ruby 2.5 or newer.
-  * Move from `ntlm-http` to `rubyntlm` gem. (#495, #574)
+### Requirements
 
-* New Features
-  * Page::Link#uri now handles non-ASCII `href`s. (#569) @terryyin
-  * FileConnection supports Windows drive letters (#483)
-  * Credential headers 'Authorization' and 'Cookie' are deleted on cross-origin redirects. (#538) @kyoshidajp
-  * ContentDispositionParser handles ISO8601 date headers, to be robust with websites that ignore RFC2183. (#554) @reitermarkus
+* Mechanize now requires Ruby 2.5 or newer.
+* Move from `ntlm-http` to `rubyntlm` gem. (#495, #574)
+
+### New Features
+
+* Page::Link#uri now handles non-ASCII `href`s. (#569) @terryyin
+* FileConnection supports Windows drive letters (#483)
+* Credential headers 'Authorization' and 'Cookie' are deleted on cross-origin redirects. (#538) @kyoshidajp
+* ContentDispositionParser handles ISO8601 date headers, to be robust with websites that ignore RFC2183. (#554) @reitermarkus
+
+### Bug fix
+
+* POST headers 'Content-Length', 'Content-MD5', and 'Content-Type' are deleted in a case-insensitive manner on redirects. Previously these headers were treated as case-sensitive.
 
-* Bug fix
-  * POST headers 'Content-Length', 'Content-MD5', and 'Content-Type' are deleted in a case-insensitive manner on redirects. Previously these headers were treated as case-sensitive.
 
 ## 2.7.7 / 2021-02-01
 
@@ -117,8 +128,7 @@
   * Mechanize::Agent#response_read will now raise a
     Mechanize::ResponseReadError instead of an EOFError and avoid losing
     requested content. #296.
-  * Depend on http-cookie, add backwards compatible deprecations.
-    #257 Akinori MUSHA.
+  * Depend on http-cookie, add backwards compatible deprecations. #257 Akinori MUSHA.
   * Added `Download#save!` for overwriting existing files. #300 Sean Kim.
 
 * Bug fix
@@ -147,13 +157,10 @@
   * Added iPad and Android user agents.  #277 by sambit, #278 by seansay.
 
 * Bug fix
-  * Mechanize#cert and Mechanize#key now return the values set by
-    #cert= and #key=. #244, #245 (Thanks, Robert Gogolok!)
-  * Mechanize no longer submits disabled form fields.  #276 by Bogdan Gusiev,
-    #279 by Ricardo Valeriano.
+  * Mechanize#cert and Mechanize#key now return the values set by #cert= and #key=. #244, #245 (Thanks, Robert Gogolok!)
+  * Mechanize no longer submits disabled form fields.  #276 by Bogdan Gusiev, #279 by Ricardo Valeriano.
   * Mechanize::File#save now behaves like Mechanize::Download#save in
-    that it will create the parent directory before saving.
-    #272, #280 by Ryan Kowalick
+    that it will create the parent directory before saving. #272, #280 by Ryan Kowalick
   * Ensure `application/xml` is registered as an XML parser in
     `PluggableParser`, not just `text/xml`. #266 James Gregory
   * Mechanize now writes cookiestxt with a prefixed dot for wildcard domain
@@ -173,8 +180,7 @@
     In mechanize 3 the old "Mac FireFox" user-agent alias will be removed.
     Pull request #231 by Gavin Miller.
   * Mechanize now authenticates using the raw challenge, not a reconstructed
-    one, to avoid dealing with quoting rules of RFC 2617.  Fixes failures in
-    #231 due to net-http-digest_auth 1.2.1
+    one, to avoid dealing with quoting rules of RFC 2617.  Fixes failures in #231 due to net-http-digest_auth 1.2.1
   * Fixed Content-Disposition parameter parser to be case insensitive. #233
   * Fixed redirection counting in following meta refresh. #240
 
@@ -205,8 +211,7 @@
     terminate chunked transfer-encoding properly.  Issue #116
   * Mechanize no longer raises an exception when multiple identical
     radiobuttons are checked.  Issue #214 by Matthias Guenther
-  * Fixed documentation for pre_connect_hooks and post_connect_hooks.  Issue
-    #226 by Robert Poor
+  * Fixed documentation for pre_connect_hooks and post_connect_hooks.  Issue #226 by Robert Poor
   * Worked around ruby 1.8 run with -Ku and ISO-8859-1 encoded characters in
     URIs.  Issue #228 by Stanislav O.Pogrebnyak
 
@@ -272,8 +277,7 @@
   * SSL parameters and proxy may now be set at any time.  Issue #194 by
     dsisnero.
   * Improved Mechanize::Page with #image_with and #images_with and
-    Mechanize::Page::Image various img element attribute accessors, #caption,
-    #extname, #mime_type and #fetch.  Pull request #173 by kitamomonga
+    Mechanize::Page::Image various img element attribute accessors, #caption, #extname, #mime_type and #fetch.  Pull request #173 by kitamomonga
   * Added MIME type parsing for content-types in Mechanize::PluggableParser
     for fine-grained parser choices.  Parsers will be chosen based on exact
     match, simplified type or media type in that order.  See
@@ -336,8 +340,7 @@
   * SSL connections will be verified against the system certificate store by
     default.
   * Added Mechanize#retry_change_requests to allow mechanize to retry POST and
-    other non-idempotent requests when you know it is safe to do so.  Issue
-    #123
+    other non-idempotent requests when you know it is safe to do so.  Issue #123
   * Mechanize can now stream files directly to disk without loading them into
     memory first through Mechanize::Download, a pluggable parser for
     downloading files.
@@ -352,8 +355,7 @@
       agent.pluggable_parser.default = Mechanize::Download
   * Added Mechanize#content_encoding_hooks which allow handling of
     non-standard content encodings like "agzip".  Patch #125 by kitamomonga
-  * Added dom_class to elements and the element matcher like dom_id.  Patch
-    #156 by Dan Hansen.
+  * Added dom_class to elements and the element matcher like dom_id.  Patch #156 by Dan Hansen.
   * Added support for the HTML5 keygen form element.  See
     http://dev.w3.org/html5/spec/Overview.html#the-keygen-element  Patch #157
     by Victor Costan.
@@ -402,8 +404,7 @@
   * The original Referer value persists on redirection.  Issue #150
   * Do not send a referer on a Refresh header based redirection.
   * Fixed encoding error in tests when LANG=C.  Patch #142 by jinschoi.
-  * The order of items in a form submission now match the DOM order.  Patch
-    #129 by kitamomonga
+  * The order of items in a form submission now match the DOM order.  Patch #129 by kitamomonga
   * Fixed proxy example in EXAMPLE.  Issue #146 by NielsKSchjoedt
 
 ## 2.0.1 / 2011-06-28
@@ -471,8 +472,7 @@ Mechanize is now under the MIT license
   * Mechanize now implements session cookies.  GH #78
   * Mechanize now implements deflate decoding.  GH #40
   * Mechanize now allows a certificate and key to be passed directly.  GH #71
-  * Mechanize::Form::MultiSelectList now implements #option_with and
-    #options_with.  GH #42
+  * Mechanize::Form::MultiSelectList now implements #option_with and #options_with.  GH #42
   * Add Mechanize::Page::Link#rel and #rel?(kind) to read and test the rel
     attribute.
   * Add Mechanize::Page#canonical_uri to read a </tt><link

data/README.md

@@ -74,6 +74,4 @@ Thank you to Michael Neumann for starting the Ruby version. Thanks to everyone w
 
 ## License
 
-This library is distributed under the MIT license. Please see the [LICENSE](http://docs.seattlerb.org/mechanize/LICENSE_rdoc.html) file.
-
-
+This library is distributed under the MIT license. Please see [LICENSE.txt](https://github.com/sparklemotion/mechanize/blob/main/LICENSE.txt).

data/lib/mechanize/page.rb

@@ -104,9 +104,9 @@ class Mechanize::Page < Mechanize::File
     parser = self.parser unless parser
     return false if parser.errors.empty?
     parser.errors.any? do |error|
-      error.message =~ /(indicate\ encoding)|
-                        (Invalid\ char)|
-                        (input\ conversion\ failed)/x
+      error.message.scrub =~ /(indicate\ encoding)|
+                              (Invalid\ char)|
+                              (input\ conversion\ failed)/x
     end
   end
 

data/lib/mechanize/version.rb

@@ -1,4 +1,4 @@
 # frozen_string_literal: true
 class Mechanize
-  VERSION = "2.8.0"
+  VERSION = "2.8.1"
 end

data/mechanize.gemspec

@@ -7,7 +7,7 @@ require 'mechanize/version'
 Gem::Specification.new do |spec|
   spec.name = "mechanize"
   spec.version = Mechanize::VERSION
-  spec.homepage = "http://docs.seattlerb.org/mechanize/"
+  spec.homepage = "https://github.com/sparklemotion/mechanize"
   spec.summary = 'The Mechanize library is used for automating interaction with websites'
   spec.description =
     [

data/test/test_mechanize_page_encoding.rb

@@ -183,5 +183,27 @@ class TestMechanizePageEncoding < Mechanize::TestCase
     assert_equal Encoding::UTF_8, result.text.encoding
   end
 
-end
+  def test_parser_error_message_containing_encoding_errors
+    # https://github.com/sparklemotion/mechanize/issues/553
+    body = <<~EOF
+      <html>
+      <body>
+      <!--
+      ## メモ
+      処理の一般化, 二重ループ, 多重ループ
+      wzxhzdk:25
+      -->
+    EOF
+    page = util_page body
 
+    # this should not raise an "invalid byte sequence in UTF-8" error while processing parsing errors
+    page.search("body")
+
+    # let's assert on the setup: a libxml2-returned parsing error itself contains an invalid character
+    assert(error = page.parser.errors.find { |e| e.message.include?("Comment not terminated") })
+    exception = assert_raises(ArgumentError) do
+      error.message =~ /any regex just to trigger encoding error/
+    end
+    assert_includes(exception.message, "invalid byte sequence in UTF-8")
+  end unless RUBY_ENGINE == 'jruby' # this is a libxml2-specific condition
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mechanize
 version: !ruby/object:Gem::Version
-  version: 2.8.0
+  version: 2.8.1
 platform: ruby
 authors:
 - Eric Hodel
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-04-01 00:00:00.000000000 Z
+date: 2021-05-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -474,7 +474,7 @@ files:
 - test/test_mechanize_util.rb
 - test/test_mechanize_xml_file.rb
 - test/test_multi_select.rb
-homepage: http://docs.seattlerb.org/mechanize/
+homepage: https://github.com/sparklemotion/mechanize
 licenses:
 - MIT
 metadata: {}