feedtxt 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 08b6aa5f6093d99cc013764f924c5a1845b8b3f0
-  data.tar.gz: ae29161c8ffab020ca196d58dd55cdd0f823308c
+  metadata.gz: e298ca3389877938c8ded1a08b327480ebbf79f4
+  data.tar.gz: 1fbea9a04efc18cf21d6286092bb113e616ae20b
 SHA512:
-  metadata.gz: fa7f505525df6950631f8789b44a52d8216573e52b32e6f452f6448c561adc4339ba5f760101e5451543945722d06bff9392655023d62c6242e7507772787814
-  data.tar.gz: 49dfd5b5c1f2747b47c0ef45bdb9580cae8ea745c0a3bc75fce88d5108415b15f92601d5b629bed7fbf75b4cc7bb8901ef1fad1c68e7a11b25c30b88eb3c35fd
+  metadata.gz: f103a0b967f89c60a589622c899e03c9b17d05f4e7f726cba66d2712a82cbea07ee39c5319419f093bb8a6f321bbe8920669464c904623d145251917edc2293e
+  data.tar.gz: 4cdd5559ea35fe6b85e28d27fe461c884bd9e2689778b756ffc9b099bc15d6215648e329d3d862e876f976a4bad731639bfa334b374f58b89182bb748423c695

data/Manifest.txt

@@ -8,5 +8,5 @@ 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_scanner.rb
 test/test_yaml.rb

data/README.md

@@ -10,8 +10,8 @@
 
 ## Usage
 
-Use `Feedtxt::Parser.parse` to read / parse feeds in text (using the Feed.TXT)
-format.
+Use `Feedtxt.parse` to read / parse feeds in text using the Feed.TXT
+format also known as RSS (Really Simple Sharing) 5.0 ;-).
 The parse method will return an array:
 
 ```
@@ -52,7 +52,7 @@ Hello, world!
 <<<|
 TXT
 
-feed = Feedtxt::Parser.parse( text )
+feed = Feedtxt.parse( text )
 pp feed
 ```
 
@@ -148,7 +148,7 @@ He lives on [Bainbridge Island][3], a quick ferry ride from Seattle.
 <<<|  
 TXT
 
-feed = Feedtxt::Parser.parse( text )
+feed = Feedtxt.parse( text )
 pp feed
 ```
 

data/Rakefile

@@ -5,7 +5,7 @@ Hoe.spec 'feedtxt' do
 
   self.version = Feedtxt::VERSION
 
-  self.summary = "feedtxt - reads Feed.TXT - feeds in text (unicode) - publish & share posts, articles, podcasts, 'n' more"
+  self.summary = "feedtxt - reads Feed.TXT a.k.a. RSS (Really Simple Sharing) 5.0 ;-) - feeds in text (unicode) - publish & share posts, articles, podcasts, 'n' more"
   self.description = summary
 
   self.urls    = ['https://github.com/feedtxt/feedtxt']

data/lib/feedtxt.rb

@@ -3,6 +3,7 @@
 
 # core and stdlibs
 
+require 'strscan'    ## StringScanner
 require 'json'
 require 'yaml'
 require 'date'
@@ -10,6 +11,7 @@ require 'time'
 require 'pp'
 
 
+
 # 3rd party gems/libs
 require 'logutils'
 
@@ -21,5 +23,16 @@ require 'feedtxt/parser'
 
 
 
+##  add shortcut / alias e.g.
+##   lets you use:
+##    Feedtxt.parse  instead of Feedtxt::Parser.parse
+module Feedtxt
+  def self.parse( text, opts={} )
+    Parser.parse( text,  )
+  end
+end
+
+
+
 # say hello
 puts Feedtxt.banner     if $DEBUG || (defined?($RUBYLIBS_DEBUG) && $RUBYLIBS_DEBUG)

data/lib/feedtxt/parser.rb

@@ -20,47 +20,56 @@ class Parser
 
 
 
-  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
+  ## note:
+  ##   regex excape  pipe: | to \|
+  ##   \\ needs to get escaped twice e.g. (\\ becomes \)
+  ##  e.g. |>>>  or |>>>>>
+  FEED_BEGIN = %{^[ ]*\\|>>>+[ ]*$}    ## note: allow leading n trailing spaces; allow 3 or more brackets
+  ##  e.g. <<<| or <<<<<<|
+  FEED_END   = %{^[ ]*<<<+\\|[ ]*$}    ## note: allow leading n trailing spaces; allow 3 or more brackets
+
+  ## e.g.</>  or <<</>>>
+  FEED_NEXT  = %{^[ ]*<+/>+[ ]*$}       ## pass 1: split/break up blocks
+  ## e.g. --- or -----
+  FEED_META  = %{^[ ]*---+[ ]*$}       ## 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
+    ##    use regex - allow three or more >>>>>> or <<<<<<
+    ##    allow spaces before and after
 
+    s = StringScanner.new( @text )
 
-    ## 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???
+    prolog = s.scan_until( /(?=#{FEED_BEGIN})/ )
+    ## pp prolog
 
-    posbeg = @text.index( FEED_BEGIN_RX )
-    if posbeg.nil?
+    feed_begin = s.scan( /#{FEED_BEGIN}/ )
+    if feed_begin.empty?    ## use blank? why? why not??
       ## 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?
+
+    buf =  s.scan_until( /(?=#{FEED_END})/ )
+    buf = buf.strip    # remove leading and trailing whitespace
+
+    feed_end = s.scan( /#{FEED_END}/ )
+    if feed_end.empty?   ## use blank? why? why not??
       ## 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   <<<</>>>>
+    ###    note: allows   <<<</>>>>
 
-    blocks = buf.split( FEED_NEXT_RX )
+    blocks = buf.split( /#{FEED_NEXT}/ )
     ## pp blocks
 
     ## 1st block is feed meta data
@@ -72,13 +81,17 @@ class Parser
       ###   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]
+      s2 = StringScanner.new( block )
+
+      item_metadata = s2.scan_until( /(?=#{FEED_META})/ )
+      item_metadata = item_metadata.strip    # remove leading and trailing whitespace
+      item_metadata = YAML.load( item_metadata )   ## convert to hash with yaml
+
+      feed_meta = s2.scan( /#{FEED_META}/ )
+
+      item_content = s2.rest
+      item_content = item_content.strip     # remove leading and trailing whitespace
 
       feed_items << [item_metadata, item_content]
     end
@@ -88,4 +101,5 @@ class Parser
 
 
 end  # class Parser
+
 end # module Feedtxt

data/lib/feedtxt/version.rb

@@ -3,7 +3,7 @@
 module Feedtxt
 
   MAJOR = 0
-  MINOR = 1
+  MINOR = 2
   PATCH = 0
   VERSION = [MAJOR,MINOR,PATCH].join('.')
 

data/test/test_scanner.rb

@@ -0,0 +1,56 @@
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_scanner.rb
+#  or better
+#     rake test
+
+require 'helper'
+
+
+class TestScanner < MiniTest::Test
+
+  ## note:
+  ##   regex excape  pipe: | to \|
+  ##   note: \\ needs to get escaped twice e.g. (\\ becomes \)
+  FEED_BEGIN = %{^[ ]*\\|>>>+[ ]*$}
+  FEED_END   = %{^[ ]*<<<+\\|[ ]*$}
+
+  def test_scan
+
+text =<<TXT
+bla bla bla
+|>>>
+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
+
+    s = StringScanner.new( text )
+
+    prolog = s.scan_until( /(?=#{FEED_BEGIN})/ )
+    pp prolog
+
+    feed_begin = s.scan( /#{FEED_BEGIN}/ )
+    assert_equal '|>>>', feed_begin
+
+    body =  s.scan_until( /(?=#{FEED_END})/ )
+    pp body
+
+    feed_end = s.scan( /#{FEED_END}/ )
+    assert_equal '<<<|', feed_end
+
+    assert true
+  end
+
+end # class TestScanner

data/test/test_yaml.rb

@@ -14,11 +14,6 @@ class TestYaml < MiniTest::Test
     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/",
@@ -32,8 +27,8 @@ class TestYaml < MiniTest::Test
        "Hello, world!"
     ]]]
 
-
-    assert_equal exp, feed
+    assert_equal exp, Feedtxt::Parser.parse( text )
+    assert_equal exp, Feedtxt.parse( text )     ## try shortcut alias too
   end
 
   def test_podcast
@@ -41,11 +36,6 @@ class TestYaml < MiniTest::Test
     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",
@@ -65,7 +55,8 @@ class TestYaml < MiniTest::Test
        "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
+    assert_equal exp, Feedtxt::Parser.parse( text )
+    assert_equal exp, Feedtxt.parse( text )   ## try shortcut alias too
   end
 
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: feedtxt
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Gerald Bauer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-06-11 00:00:00.000000000 Z
+date: 2017-06-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc
@@ -38,8 +38,8 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.15'
-description: feedtxt - reads Feed.TXT - feeds in text (unicode) - publish & share
-  posts, articles, podcasts, 'n' more
+description: feedtxt - reads Feed.TXT a.k.a. RSS (Really Simple Sharing) 5.0 ;-) -
+  feeds in text (unicode) - publish & share posts, articles, podcasts, 'n' more
 email: wwwmake@googlegroups.com
 executables: []
 extensions: []
@@ -58,7 +58,7 @@ files:
 - test/feeds/spec/example.yaml.txt
 - test/feeds/spec/podcast.yaml.txt
 - test/helper.rb
-- test/test_version.rb
+- test/test_scanner.rb
 - test/test_yaml.rb
 homepage: https://github.com/feedtxt/feedtxt
 licenses:
@@ -85,6 +85,6 @@ rubyforge_project:
 rubygems_version: 2.6.7
 signing_key: 
 specification_version: 4
-summary: feedtxt - reads Feed.TXT - feeds in text (unicode) - publish & share posts,
-  articles, podcasts, 'n' more
+summary: feedtxt - reads Feed.TXT a.k.a. RSS (Really Simple Sharing) 5.0 ;-) - feeds
+  in text (unicode) - publish & share posts, articles, podcasts, 'n' more
 test_files: []

data/test/test_version.rb

@@ -1,19 +0,0 @@
-###
-#  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