open-uri-cached 0.0.5 → 2.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 349b8c42b059c7fd2cf0284c5df387559ba97ddccea7e4c1b9fe0f93f030af1b
+  data.tar.gz: bf8e5c09b35ccd42f04a37d791340e9532892380eacea4e8d7657ab301a1894c
+SHA512:
+  metadata.gz: c66cd1f8fc5a320ece25968fb8651100dd2011b4eadb3ee5c99c24273e192f423a78b3f00019366ff8ca6e8b960ddd90024a92603bb942fea6289321290b6295
+  data.tar.gz: bb4bbcfdd49782212169c7372156455f725de04ae56c451eb20427fb3da4e82bf306b61b7b4347fabb945c64ece16e66b70bf426a3bc10feee96c688b22f3681

data/README.md

@@ -0,0 +1,32 @@
+# OpenURI with caching
+
+Carelessly make OpenURI requests without getting hate mail.
+
+## Usage
+
+Require the library
+
+```ruby
+    require 'open-uri/cached'
+    open('http://www.someone-that-hates-being-scraped.com').read
+```
+
+## Configuring
+
+If you're not super pumped about reading files from `/tmp`, you can configure the cache path:
+
+```ruby
+  OpenURI::Cache.cache_path = '/tmp/open-uri'
+```
+
+## Invalidating
+
+They say cache invalidation is hard, but not really:
+
+```ruby
+  # Invalidate a single URL
+  OpenURI::Cache.invalidate('https://example.com/')
+
+  # Invalidate everything
+  OpenURI::Cache.invalidate_all!
+```

data/lib/open-uri/cached.rb

@@ -1,5 +1,7 @@
-require 'open-uri'
 require 'digest/sha1'
+require 'fileutils'
+require 'open-uri'
+require 'securerandom'
 require 'yaml'
 
 module OpenURI
@@ -22,7 +24,7 @@ module OpenURI
   end
 
   class Cache
-    @cache_path = "/tmp/open-uri-#{Process.uid}"
+    @cache_path = "/tmp/open-uri-#{SecureRandom.uuid}"
 
     class << self
       attr_accessor :cache_path
@@ -36,9 +38,9 @@ module OpenURI
         # TODO: head request to determine last_modified vs file modtime
 
         # Read metadata, if it exists
-        meta = YAML::load(File.read("#{filename}.meta")) if File.exists?("#{filename}.meta")
+        meta = YAML.unsafe_load(File.read("#{filename}.meta")) if File.exist?("#{filename}.meta")
 
-        f = File.exists?(filename) ? StringIO.new(File.open(filename, "rb") { |f| f.read }) : nil
+        f = File.exist?(filename) ? StringIO.new(File.open(filename, "rb") { |fd| fd.read }) : nil
 
         # Add meta accessors
         if meta && f
@@ -111,6 +113,11 @@ module OpenURI
         false
       end
 
+      # Invalidate all caches we know about
+      def invalidate_all!
+        FileUtils.rm_r(@cache_path, force: true, secure: true)
+      end
+
       protected
         def filename_from_url(url)
           uri = URI.parse(url) # TODO: rescue here?
@@ -124,7 +131,7 @@ module OpenURI
             full.push(dir)
             dir = full.join('/')
             next if dir.to_s == ''
-            Dir.mkdir(dir) unless File.exists?(dir)
+            Dir.mkdir(dir) unless File.exist?(dir)
           end
         end
     end

metadata

@@ -1,66 +1,71 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: open-uri-cached
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 0
-  - 5
-  version: 0.0.5
+version: !ruby/object:Gem::Version
+  version: 2.0.0
 platform: ruby
-authors: 
+authors:
 - Danial Pearce
-autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2012-01-08 00:00:00 +11:00
-default_executable: 
-dependencies: []
-
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.10'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.14'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.14'
 description: OpenURI with transparent disk caching
-email: rubygems@tigris.id.au
+email: danial.pearce@gmail.com
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
-- README.markdown
+files:
 - LICENSE
+- README.md
 - lib/open-uri/cached.rb
-has_rdoc: true
-homepage: http://github.com/tigris/open-uri-cached
+homepage: https://github.com/tigris/open-uri-cached
 licenses: []
-
-post_install_message: 
+metadata: {}
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
-rubyforge_project: 
-rubygems_version: 1.3.7
-signing_key: 
-specification_version: 3
-summary: Do a lot of site scraping but take lots of attempts at parsing the content before reaching your end result? This gem is for you. But wait, there's more... Ok, no there isn't.
+rubygems_version: 3.6.9
+specification_version: 4
+summary: Do a lot of site scraping but take lots of attempts at parsing the content
+  before reaching your end result? This gem is for you. But wait, there's more...
+  Ok, no there isn't.
 test_files: []
-

data/README.markdown

@@ -1,14 +0,0 @@
-# OpenURI with caching
-
-Carelessly make OpenURI requests without getting hate mail.
-
-## Usage
-
-Require the library
-
-    require 'open-uri/cached'
-    open('http://www.someone-that-hates-being-scraped.com').read
-
-## Configuring
-
-OpenURI::Cache.cache_path = '/tmp/open-uri'