feedtxt 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3ae42d0a659477fb4d9c6c3f1e2816283a6c81ed
-  data.tar.gz: 34c181418101a9488cdf981b2b5808c0bcf2d488
+  metadata.gz: 08b6aa5f6093d99cc013764f924c5a1845b8b3f0
+  data.tar.gz: ae29161c8ffab020ca196d58dd55cdd0f823308c
 SHA512:
-  metadata.gz: 86d6e39f32a34d5f54a0c4e57e2810e1d5b481586e40a1610399eb4686605b5850d6669fa8427f4eed3950c420595b386712d89492e3cc7aece7df7c5848800b
-  data.tar.gz: 8e2d0e904b4dceeea9ae3ae45580cd9ad7d4f80ddfc78abd49f3c5044636063d7cebadfa19b0dd72d558501e43de64be7f43595c022ababfb03162a965c8b544
+  metadata.gz: fa7f505525df6950631f8789b44a52d8216573e52b32e6f452f6448c561adc4339ba5f760101e5451543945722d06bff9392655023d62c6242e7507772787814
+  data.tar.gz: 49dfd5b5c1f2747b47c0ef45bdb9580cae8ea745c0a3bc75fce88d5108415b15f92601d5b629bed7fbf75b4cc7bb8901ef1fad1c68e7a11b25c30b88eb3c35fd

data/Manifest.txt

@@ -3,4 +3,10 @@ Manifest.txt
 README.md
 Rakefile
 lib/feedtxt.rb
+lib/feedtxt/parser.rb
 lib/feedtxt/version.rb
+test/feeds/spec/example.yaml.txt
+test/feeds/spec/podcast.yaml.txt
+test/helper.rb
+test/test_version.rb
+test/test_yaml.rb

data/README.md

@@ -10,7 +10,197 @@
 
 ## Usage
 
-To be done.
+Use `Feedtxt::Parser.parse` to read / parse feeds in text (using the Feed.TXT)
+format.
+The parse method will return an array:
+
+```
+[ feed_metadata,
+  [
+    [ item_metadata, item_content ],
+    [ item_metadata, item_content ],
+    ...
+  ]
+]
+```
+
+- The 1st element is the feed metadata hash.
+- The 2nd element is the items array.
+  - The 1st element in an item array is the item metadata hash.
+  - The 2nd element in an item array is the item content.
+
+Easier to see it in action. Let's read in:
+
+``` ruby
+require 'feedtxt'
+
+text =<<TXT
+|>>>
+title:          "My Example Feed"
+home_page_url:  "https://example.org/"
+feed_url:       "https://example.org/feed.txt"
+</>
+id:  "2"
+url: "https://example.org/second-item"
+---
+This is a second item.
+</>
+id:  "1"
+url: "https://example.org/initial-post"
+---
+Hello, world!
+<<<|
+TXT
+
+feed = Feedtxt::Parser.parse( text )
+pp feed
+```
+
+resulting in:
+
+``` ruby
+[
+  {"title"        =>"My Example Feed",
+   "home_page_url"=>"https://example.org/",
+   "feed_url"     =>"https://example.org/feed.txt"
+  },
+  [[
+     {"id" =>"2",
+      "url"=>"https://example.org/second-item"
+     },
+     "This is a second item."
+   ],
+   [
+     {"id"=>"1",
+      "url"=>"https://example.org/initial-post"
+     },
+     "Hello, world!"
+  ]]
+]
+```
+
+and use like:
+
+``` ruby
+
+feed_metadata = feed[0]
+feed_items    = feed[1]
+
+feed_metadata[ 'title' ]
+# => "My Example Feed"
+feed_metadata[ 'feed_url' ]
+# => "https://example.org/feed.txt"
+
+item          = feed_items[0]   # or feed[1][0]
+item_metadata = item[0]         # or feed[1][0][0]
+item_content  = item[1]         # or feed[1][0][1]
+
+item_metadata[ 'id' ]
+# => "2"
+item_metadata[ 'url' ]
+# => "https://example.org/second-item"
+item_content
+# => "This is a second item."
+
+item          = feed_items[1]    # or feed[1][1]
+item_metadata = item[0]          # or feed[1][1][0]
+item_content  = item[1]          # or feed[1][1][1]
+
+item_metadata[ 'id' ]
+# => "1"
+item_metadata[ 'url' ]
+# => "https://example.org/initial-post"
+item_content
+# => "Hello, world!"
+...
+```
+
+Another example. Let's try a podcast:
+
+
+``` ruby
+text =<<TXT
+|>>>
+comment: "This is a podcast feed. You can add..."
+title:   "The Record"
+home_page_url: "http://therecord.co/"
+feed_url:      "http://therecord.co/feed.txt"
+</>
+id:        "http://therecord.co/chris-parrish"
+title:     "Special #1 - Chris Parrish"
+url:       "http://therecord.co/chris-parrish"
+summary:   "Brent interviews Chris Parrish, co-host of The Record and one-half of Aged & Distilled."
+published: 2014-05-09T14:04:00-07:00
+attachments:
+- url:           "http://therecord.co/downloads/The-Record-sp1e1-ChrisParrish.m4a"
+  mime_type:     "audio/x-m4a"
+  size_in_bytes: 89970236
+  duration_in_seconds: 6629
+---
+Chris has worked at [Adobe][1] and as a founder of Rogue Sheep, which won an Apple Design Award for Postage.
+Chris's new company is Aged & Distilled with Guy English - which shipped [Napkin](2),
+a Mac app for visual collaboration. Chris is also the co-host of The Record.
+He lives on [Bainbridge Island][3], a quick ferry ride from Seattle.
+
+[1]: http://adobe.com/
+[2]: http://aged-and-distilled.com/napkin/
+[3]: http://www.ci.bainbridge-isl.wa.us/
+<<<|  
+TXT
+
+feed = Feedtxt::Parser.parse( text )
+pp feed
+```
+
+resulting in:
+
+``` ruby
+[{"comment"=>"This is a podcast feed. You can add...",
+  "title"=>"The Record",
+  "home_page_url"=>"http://therecord.co/",
+  "feed_url"=>"http://therecord.co/feed.txt"
+ },
+ [
+   [{"id"=>"http://therecord.co/chris-parrish",
+     "title"=>"Special #1 - Chris Parrish",
+     "url"=>"http://therecord.co/chris-parrish",
+     "summary"=>"Brent interviews Chris Parrish, co-host of The Record and...",
+     "published"=>2014-05-09 23:04:00 +0200,
+     "attachments"=>
+      [{"url"=>"http://therecord.co/downloads/The-Record-sp1e1-ChrisParrish.m4a",
+        "mime_type"=>"audio/x-m4a",
+        "size_in_bytes"=>89970236,
+        "duration_in_seconds"=>6629}]
+     },
+     "Chris has worked at [Adobe][1] and as a founder of Rogue Sheep..."
+   ]
+ ]
+]
+```
+
+and use like:
+
+``` ruby
+feed_metadata = feed[0]
+feed_items    = feed[1]
+
+feed_metadata[ 'title' ]
+# => "The Record"
+feed_metadata[ 'feed_url' ]
+# => "http://therecord.co/feed.txt"
+
+item          = feed_items[0]  # or feed[1][0]
+item_metadata = item[0]        # or feed[1][0][0]
+item_content  = item[1]        # or feed[1][0][1]
+
+item_metadata[ 'title' ]
+# => "Special #1 - Chris Parrish"
+item_metadata[ 'url' ]
+# => "http://therecord.co/chris-parrish
+item_content
+# => "Chris has worked at [Adobe][1] and as a founder of Rogue Sheep..."
+...
+```
 
 
 ## License

data/lib/feedtxt.rb

@@ -16,6 +16,7 @@ require 'logutils'
 
 # our own code
 require 'feedtxt/version'  # let it always go first
+require 'feedtxt/parser'
 
 
 

data/lib/feedtxt/parser.rb

@@ -0,0 +1,91 @@
+# encoding: utf-8
+
+module Feedtxt
+
+
+class Parser
+
+  include LogUtils::Logging
+
+
+  ### convenience class/factory method
+  def self.parse( text, opts={} )
+    self.new( text ).parse
+  end
+
+  ### Note: lets keep/use same API as RSS::Parser for now
+  def initialize( text )
+    @text = text
+  end
+
+
+
+  FEED_BEGIN_RX = %r{^\|>>>$}
+  FEED_END_RX   = %r{^<<<\|$}
+  FEED_NEXT_RX  = %r{^</>$}       ## pass 1: split/break up blocks
+  FEED_META_RX  = %r{^---$}       ## pass 2: break up item into metadata and content block
+
+
+  def parse
+
+    ## find start marker e.g. |>>>
+    ##    todo: use regex - allow three or more >>>>>> or <<<<<<
+    ##    todo: allow spaces before and after
+
+
+    ## todo/fix:
+    ##    use index-like finder return posbeg and posend!!!
+    ##      regex is not fixed length/width; we need to know the length
+    ##   check what is the best way?  use regex match or something???
+
+    posbeg = @text.index( FEED_BEGIN_RX )
+    if posbeg.nil?
+      ## nothing found return empty array for now; return nil - why? why not?
+      puts "warn !!! no begin marker found e.g. |>>>"
+      return []
+    end
+
+    posend = @text.index( FEED_END_RX, posbeg )
+    if posend.nil?
+      ## nothing found return empty array for now; return nil - why? why not?
+      puts "warn !!! no end marker found e.g. <<<|"
+      return []
+    end
+
+    ## cutoff - get text between begin and end marker
+    buf = @text[ posbeg+4...posend ].strip
+    ## pp buf
+
+    ####
+    ## pass 1: split blocks by </>
+    ###    todo: allow   <<<</>>>>
+
+    blocks = buf.split( FEED_NEXT_RX )
+    ## pp blocks
+
+    ## 1st block is feed meta data
+    block1st = blocks.shift       ## get/remove 1st block from blocks
+    feed_metadata = YAML.load( block1st.strip )
+
+    feed_items = []
+    blocks.each do |block|
+      ###   note: do NOT use split e.g.--- is used by markdown
+      ##      only search for first --- to split (all others get ignored)
+      ##    todo: make three dashes --- (3) not hard-coded (allow more)
+      posmeta = block.index( FEED_META_RX )
+      item = []
+      item[0] = block[0...posmeta].strip
+      item[1] = block[posmeta+3..-1].strip
+
+      item_metadata = YAML.load( item[0] )
+      item_content  = item[1]
+
+      feed_items << [item_metadata, item_content]
+    end
+
+    [ feed_metadata, feed_items ]
+  end # method parse
+
+
+end  # class Parser
+end # module Feedtxt

data/lib/feedtxt/version.rb

@@ -3,8 +3,8 @@
 module Feedtxt
 
   MAJOR = 0
-  MINOR = 0
-  PATCH = 1
+  MINOR = 1
+  PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 
   def self.version

data/test/feeds/spec/example.yaml.txt

@@ -0,0 +1,15 @@
+|>>>
+title:          "My Example Feed"
+home_page_url:  "https://example.org/"
+feed_url:       "https://example.org/feed.txt"
+</>
+id:  "2"
+url: "https://example.org/second-item"
+---
+This is a second item.
+</>
+id:  "1"
+url: "https://example.org/initial-post"
+---
+Hello, world!
+<<<|

data/test/feeds/spec/podcast.yaml.txt

@@ -0,0 +1,26 @@
+|>>>
+comment: "This is a podcast feed. You can add this feed to your podcast client using the following URL: http://therecord.co/feed.json"
+title:   "The Record"
+home_page_url: "http://therecord.co/"
+feed_url:      "http://therecord.co/feed.txt"
+</>
+id:        "http://therecord.co/chris-parrish"
+title:     "Special #1 - Chris Parrish"
+url:       "http://therecord.co/chris-parrish"
+summary:   "Brent interviews Chris Parrish, co-host of The Record and one-half of Aged & Distilled."
+published: 2014-05-09T14:04:00-07:00
+attachments:
+- url:           "http://therecord.co/downloads/The-Record-sp1e1-ChrisParrish.m4a"
+  mime_type:     "audio/x-m4a"
+  size_in_bytes: 89970236
+  duration_in_seconds: 6629
+---
+Chris has worked at [Adobe][1] and as a founder of Rogue Sheep, which won an Apple Design Award for Postage.
+Chris's new company is Aged & Distilled with Guy English - which shipped [Napkin](2),
+a Mac app for visual collaboration. Chris is also the co-host of The Record.
+He lives on [Bainbridge Island][3], a quick ferry ride from Seattle.
+
+[1]: http://adobe.com/
+[2]: http://aged-and-distilled.com/napkin/
+[3]: http://www.ci.bainbridge-isl.wa.us/
+<<<|

data/test/helper.rb

@@ -0,0 +1,23 @@
+## $:.unshift(File.dirname(__FILE__))
+
+
+## minitest setup
+
+require 'minitest/autorun'
+
+require 'logutils'
+require 'textutils'
+
+
+## our own code
+require 'feedtxt'
+
+
+
+LogUtils::Logger.root.level = :debug
+
+
+def read_text( name )
+  text = File.read( "#{Feedtxt.root}/test/feeds/#{name}.txt" )
+  text
+end

data/test/test_version.rb

@@ -0,0 +1,19 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_version.rb
+#  or better
+#     rake test
+
+require 'helper'
+
+
+class TestVersion < MiniTest::Test
+
+  def test_version
+
+    puts "Feedtxt: #{Feedtxt::VERSION}"
+
+    assert true
+  end
+
+end # class TestVersion

data/test/test_yaml.rb

@@ -0,0 +1,72 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_yaml.rb
+#  or better
+#     rake test
+
+require 'helper'
+
+
+class TestYaml < MiniTest::Test
+
+  def test_example
+
+    text = read_text( 'spec/example.yaml' )
+    pp text
+
+    feed = Feedtxt::Parser.parse( text )
+    pp feed
+
+    ## pp feed.to_json
+
+    exp = [
+      {"title"=>"My Example Feed",
+  "home_page_url"=>"https://example.org/",
+  "feed_url"=>"https://example.org/feed.txt"},
+    [[
+      {"id"=>"2", "url"=>"https://example.org/second-item"},
+       "This is a second item."
+     ],
+     [
+       {"id"=>"1", "url"=>"https://example.org/initial-post"},
+       "Hello, world!"
+    ]]]
+
+
+    assert_equal exp, feed
+  end
+
+  def test_podcast
+
+    text = read_text( 'spec/podcast.yaml' )
+    pp text
+
+    feed = Feedtxt::Parser.parse( text )
+    pp feed
+
+    ## pp feed.to_json
+
+    exp =[{"comment"=>
+   "This is a podcast feed. You can add this feed to your podcast client using the following URL: http://therecord.co/feed.json",
+  "title"=>"The Record",
+  "home_page_url"=>"http://therecord.co/",
+  "feed_url"=>"http://therecord.co/feed.txt"},
+ [[{"id"=>"http://therecord.co/chris-parrish",
+    "title"=>"Special #1 - Chris Parrish",
+    "url"=>"http://therecord.co/chris-parrish",
+    "summary"=>
+     "Brent interviews Chris Parrish, co-host of The Record and one-half of Aged & Distilled.",
+    "published"=>DateTime.new( 2014, 5, 9, 23, 4, 0, '+02'),
+    "attachments"=>
+     [{"url"=>
+        "http://therecord.co/downloads/The-Record-sp1e1-ChrisParrish.m4a",
+       "mime_type"=>"audio/x-m4a",
+       "size_in_bytes"=>89970236,
+       "duration_in_seconds"=>6629}]},
+   "Chris has worked at [Adobe][1] and as a founder of Rogue Sheep, which won an Apple Design Award for Postage.\nChris's new company is Aged & Distilled with Guy English - which shipped [Napkin](2),\na Mac app for visual collaboration. Chris is also the co-host of The Record.\nHe lives on [Bainbridge Island][3], a quick ferry ride from Seattle.\n\n[1]: http://adobe.com/\n[2]: http://aged-and-distilled.com/napkin/\n[3]: http://www.ci.bainbridge-isl.wa.us/"]]]
+
+    assert_equal exp, feed
+  end
+
+
+end # class TestYaml

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: feedtxt
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Gerald Bauer
@@ -53,7 +53,13 @@ files:
 - README.md
 - Rakefile
 - lib/feedtxt.rb
+- lib/feedtxt/parser.rb
 - lib/feedtxt/version.rb
+- test/feeds/spec/example.yaml.txt
+- test/feeds/spec/podcast.yaml.txt
+- test/helper.rb
+- test/test_version.rb
+- test/test_yaml.rb
 homepage: https://github.com/feedtxt/feedtxt
 licenses:
 - Public Domain