bwkfanboy 1.4.1 → 2.0.0

data/lib/bwkfanboy/parser.rb

@@ -1,156 +0,0 @@
-require 'json'
-require 'date'
-
-require_relative 'utils'
-
-# :include: ../../doc/README.rdoc
-module Bwkfanboy
-
-  # :include: ../../doc/plugin.rdoc
-  class Parse
-    ENTRIES_MAX = 128
-
-    attr_reader :opt
-    
-    def initialize(opt = [])
-      @entries = []
-      @opt = opt
-    end
-
-    # Invokes #myparse & checks if it has grabbed something.
-    def parse(stream)
-      @entries = []
-      begin
-        myparse(stream)
-      rescue
-        @entries = []
-        Utils.errx(1, "parsing failed: #{$!}\n\nBacktrace:\n\n#{$!.backtrace.join("\n")}")
-      end
-      Utils.errx(1, "plugin return no output") if @entries.length == 0
-    end
-
-    def uri()
-      m = get_meta()
-      eval("\"#{m::URI}\"")
-    end
-
-    # Prints entries in 'key: value' formatted strings. Intended for
-    # debugging.
-    def dump()
-      @entries.each {|i|
-        puts "title    : " + i[:title]
-        puts "link     : " + i[:link]
-        puts "updated  : " + i[:updated]
-        puts "author   : " + i[:author]
-        puts "content  : " + i[:content]
-        puts ""
-      }
-    end
-    
-    def to_json()
-      # guess the time of the most recent entry
-      u = DateTime.parse() # January 1, 4713 BCE
-      @entries.each {|i|
-        t = DateTime.parse(i[:updated])
-        u = t if t > u
-      }
-      
-      m = get_meta()
-      uri = eval("\"#{m::URI}\"")
-      j = {
-        channel: {
-          updated: u,
-          id: uri,
-          author: Meta::NAME,   # just a placeholder
-          title: m::TITLE,
-          link: uri,
-          x_entries_content_type: m::CONTENT_TYPE
-        },
-        x_entries: @entries
-      }
-      Utils::cfg[:verbose] >= 1 ? JSON.pretty_generate(j) : JSON.generate(j)
-    end
-
-    # After loading a plugin, one can do basic validation of the
-    # plugin's class with the help of this method.
-    def check
-      m = get_meta()
-      begin
-        [:URI, :ENC, :VERSION, :COPYRIGHT, :TITLE, :CONTENT_TYPE].each {|i|
-          fail "#{m}::#{i} not defined or empty" if (! m.const_defined?(i) || m.const_get(i) =~ /^\s*$/)
-        }
-        
-        if m::URI =~ /#\{.+?\}/ && @opt.size == 0
-          fail 'additional options required'
-        end
-      rescue
-        Utils.errx(1, "incomplete plugin's instance: #{$!}")
-      end
-    end
-
-    # Prints plugin's meta information.
-    def dump_info()
-      m = get_meta()
-      puts "Version     : #{m::VERSION}"
-      puts "Copyright   : #{m::COPYRIGHT}"
-      puts "Title       : #{m::TITLE}"
-      puts "URI         : #{uri}"
-    end
-
-    protected
-
-    # This *must* be overridden in the child.
-    def myparse(stream)
-      raise "plugin isn't finished yet"
-    end
-
-    # Tries to parse _s_ as a date string. Return the result in ISO 8601
-    # format.
-    def date(s)
-      begin
-        DateTime.parse(clean(s)).iso8601()
-      rescue
-        Utils.vewarnx(2, "#{s} is unparsable; date is set to current")
-        DateTime.now().iso8601()
-      end
-    end
-
-    # will help you to check if there is a
-    def toobig?
-      return true if @entries.length >= ENTRIES_MAX
-      return false
-    end
-
-    def <<(t)
-      if toobig? then
-        Utils.warnx("reached max number of entries (#{ENTRIES_MAX})")
-        return @entries
-      end
-          
-      %w(updated author link).each { |i|
-        fail "unable to extract '#{i}'" if ! t.key?(i.to_sym) || t[i.to_sym] == nil || t[i.to_sym].empty?
-      }
-      %w(title content).each { |i|
-        fail "missing '#{i}'" if ! t.key?(i.to_sym) || t[i.to_sym] == nil
-      }
-      # a redundant check if user hasn't redefined date() method
-      if t[:updated] !~ /\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\+\d{2}:\d{2}/ then
-        fail "'#{t[:updated]}' isn't in iso8601 format"
-      end
-      @entries << t
-    end
-
-    private
-
-    def clean(s)
-      s.gsub(/\s+/, ' ').strip()
-    end
-
-    def get_meta()
-      Utils.errx(1, "incomplete plugin: no #{self.class}::Meta module") if (! defined?(self.class::Meta) || ! self.class::Meta.is_a?(Module))
-      self.class::Meta
-    end
-    
-  end # class
-
-end # module

data/lib/bwkfanboy/plugins/bwk.rb

@@ -1,33 +0,0 @@
-# A simple plugin that parses the listing of bwk's articles from
-# dailyprincetonian.com.
-
-require 'nokogiri'
-
-class Page < Bwkfanboy::Parse
-  module Meta
-    URI = 'http://www.dailyprincetonian.com/advanced_search/?author=Brian+Kernighan'
-    URI_DEBUG = '/home/alex/lib/software/alex/bwkfanboy/test/semis/bwk.html'
-    ENC = 'UTF-8'
-    VERSION = 2
-    COPYRIGHT = "See bwkfanboy's LICENSE file"
-    TITLE = "Brian Kernighan's articles from Daily Princetonian"
-    CONTENT_TYPE = 'html'
-  end
-  
-  def myparse(stream)
-    url = "http://www.dailyprincetonian.com"
-
-    doc = Nokogiri::HTML(stream, nil, Meta::ENC)
-    doc.xpath("//div[@class='article_item']").each {|i|
-      t = clean(i.xpath("h2/a").children.text())
-      fail 'unable to extract link' if (link = clean(i.xpath("h2/a")[0].attributes['href'].value()).empty?)
-      link = clean(i.xpath("h2/a")[0].attributes['href'].value())
-      l = url + link + "print"
-      u = date(i.xpath("h2").children[1].text())
-      a = clean(i.xpath("div/span/a[1]").children.text())
-      c = clean(i.xpath("div[@class='summary']").text())
-      
-      self << { title: t, link: l, updated: u, author: a, content: c }
-    }
-  end
-end

data/lib/bwkfanboy/plugins/econlib.rb

@@ -1,34 +0,0 @@
-# This is a skeleton for a bwkfanboy 1.3.0 plugin.  To understand how
-# plugins work please read doc/plugins.rdoc file from bwkfanboy's
-# distribution.
-
-require 'nokogiri'
-
-class Page < Bwkfanboy::Parse
-  module Meta
-    URI = 'http://www.econlib.org/cgi-bin/searcharticles.pl?sortby=DD&query=ha*'
-    URI_DEBUG = '/home/alex/lib/software/alex/bwkfanboy/test/semis/econlib.html'
-    ENC = 'UTF-8'
-    VERSION = 1
-    COPYRIGHT = "See bwkfanboy's LICENSE file"
-    TITLE = "Latest articles from econlib.org"
-    CONTENT_TYPE = 'html'
-  end
-  
-  def myparse(stream)
-    baseurl = 'http://www.econlib.org'
-    
-    # read 'stream' IO object and parse it
-    doc = Nokogiri::HTML(stream, nil, Meta::ENC)
-    doc.xpath("//*[@id='divResults']//tr").each {|i|
-      t = clean(i.xpath("td[3]//a").text)
-      next if t == ""
-      l = baseurl + clean(i.xpath("td[3]//a")[0].attributes['href'].value)
-      u = date(i.xpath("td[4]").children.text)
-      a = clean(i.xpath("td[3]/div").children[2].text)
-      c = clean(i.xpath("td[4]").children[2].text)
-
-      self << { title: t, link: l, updated: u, author: a, content: c }
-    }
-  end
-end

data/lib/bwkfanboy/plugins/freebsd-ports-update.rb

@@ -1,76 +0,0 @@
-require 'digest/md5'
-
-class Page < Bwkfanboy::Parse
-  module Meta
-    URI = '/usr/ports/UPDATING'
-    URI_DEBUG = URI
-    ENC = 'ASCII'
-    VERSION = 3
-    COPYRIGHT = "See bwkfanboy's LICENSE file"
-    TITLE = "News from FreeBSD ports"
-    CONTENT_TYPE = 'text'
-  end
-
-  def myadd(ready, t, l, u, a, c)
-    return true if ! ready
-    return false if toobig?
-    self << { title: t, link: l, updated: u, author: a, content: c.rstrip } if ready
-    return true
-  end
-
-  def clean(t)
-    t = t[2..-1] if t[0] != "\t"
-    return '' if t == nil
-    return t
-  end
-  
-  def myparse(stream)
-    re_u = /^(\d{8}):$/
-    re_t1 = /^ {2}AFFECTS:\s+(.+)$/
-    re_t2 = /^\s+(.+)$/
-    re_a = /^ {2}AUTHORS?:\s+(.+)$/
-
-    ready = false
-    mode = nil
-    t = l = u = a = c = nil
-    while line = stream.gets
-      line.rstrip!
-
-      if line =~ re_u then
-        # add a new entry
-        break if ! myadd(ready, t, l, u, a, c)
-        ready = true
-        u = date($1)
-        l = $1                  # partial, see below
-        t = a = c = nil
-        next
-      end
-
-      if ready then
-        if line =~ re_t1 then
-          mode = 'title'
-          t = $1
-          c = clean($&) + "\n"
-          # link should be unique
-          l = "file://#{Meta::URI}\##{l}-#{Digest::MD5.hexdigest($1)}"
-        elsif line =~ re_a
-          mode = 'author'
-          a = $1
-          c += clean($&) + "\n"
-        elsif line =~ re_t2 && mode == 'title'
-          t += ' ' + $1
-          c += clean($&) + "\n"
-        else
-          # content
-          c += clean(line) + "\n"
-          mode = nil
-        end
-      end
-
-      # skipping the preamble
-    end
-
-    # add last entry
-    myadd(ready, t, l, u, a, c)
-  end
-end

data/lib/bwkfanboy/plugins/inc.rb

@@ -1,37 +0,0 @@
-# Requires 1 option: an author's name, for example 'jason-fried'.
-
-require 'nokogiri'
-
-class Page < Bwkfanboy::Parse
-  module Meta
-    URI = 'http://www.inc.com/author/#{opt[0]}'
-    URI_DEBUG = '/home/alex/lib/software/alex/bwkfanboy/test/semis/inc.html'
-    ENC = 'UTF-8'
-    VERSION = 1
-    COPYRIGHT = 'See bwkfanboy\'s LICENSE file'
-    TITLE = "Articles (per-user) from inc.com"
-    CONTENT_TYPE = 'html'
-  end
-  
-  def myparse(stream)
-    profile = opt[0]
-    
-    # read 'stream' IO object and parse it
-    doc = Nokogiri::HTML(stream, nil, Meta::ENC)
-    doc.xpath("//div[@id='articleriver']/div/div").each {|i|
-      t = clean(i.xpath("h3").text)
-      l = clean(i.xpath("h3/a")[0].attributes['href'].value)
-      
-      next if (u = i.xpath("div[@class='byline']/span")).size == 0
-      u = date(u.text)
-      
-      a = clean(i.xpath("div[@class='byline']/a").text)
-      
-      c = i.xpath("p[@class='summary']")
-      c.xpath("a").remove
-      c = c.inner_html(encoding: Meta::ENC)
-      
-      self << { title: t, link: l, updated: u, author: a, content: c }
-    }
-  end
-end

data/lib/bwkfanboy/schema.js

@@ -1,39 +0,0 @@
-{
-    "type": "object",
-    "properties": {
-		"channel": {
-			"type": "object",
-			"properties": {
-				"updated": {
-					"type": "string",
-					"format": "date-time"
-				},
-				"id": { "type": "string" },
-				"author": { "type": "string" },
-				"title": { "type": "string" },
-				"link": { "type": "string" },
-				"x_entries_content_type": {
-					"type": "string",
-					"enum": ["text", "html", "xhtml"]
-				}
-			}
-		},
-		"x_entries": {
-			"type": "array",
-			"minItems": 1,
-			"items": {
-				"type": "object",
-				"properties": {
-					"title": { "type": "string" },
-					"link": { "type": "string" },
-					"updated": {
-						"type": "string",
-						"format": "date-time"
-					},
-					"author": { "type": "string" },
-					"content": { "type": "string" }
-				}
-			}
-		}
-	}
-}

data/test/popen4.sh

@@ -1,4 +0,0 @@
-#!/bin/sh
-echo this is stdin
-echo this is stderr 1>&2
-exit 32

data/test/rake_git.rb

@@ -1,36 +0,0 @@
-#!/usr/bin/env ruby
-# -*-ruby-*-
-# :erb:
-
-# This is a helper for your Rakefile. Read the comments for each
-# function.
-
-require 'git'
-require 'pp'
-
-# Return a list of files in a git repository _repdir_.
-#
-# Add this to your gem spec:
-#
-# spec = Gem::Specification.new {|i|
-#   i.files = git_ls('.')
-# }
-#
-# What it does is just collecting the list of the files from the git
-# repository. The idea is to use that list for the gem spec. No more
-# missing or redundant files in gems!
-def git_ls(repdir, ignore_some = true)
-  ignore = ['/?\.gitignore$']
-
-  r = []
-  g = Git.open repdir
-  g.ls_files.each {|i, v|
-    next if ignore_some && ignore.index {|ign| i.match(/#{ign}/) }
-    r << i
-  }
-  r
-end
-
-pp git_ls('.') if __FILE__ == $0
-
-# Don't remove this: falsework/0.2.2/naive/2010-12-26T04:50:00+02:00

data/test/semis/Rakefile

@@ -1,35 +0,0 @@
-# -*-ruby-*-
-
-require 'open-uri'
-
-LINKS = 'links.txt'
-
-desc "fetch pages found in #{LINKS} file; (filter with 't=page')"
-task :default do
-  if ENV['t'] =~ /^\s*$/ || !ENV.key?('t') then ENV['t'] = '.*' end
-
-  stng = false
-  File.open(LINKS) { |fp|
-    n = 0
-    while line = fp.gets
-      n += 1
-      next if (line =~ /^\s*#/ || line =~ /^\s*$/)
-      a = line.split
-      fail "invalid line #{n}" if a.length != 2
-      next if (a[0] !~ Regexp::new(ENV['t']))
-
-      rm(a[0], force: true)
-      printf "fetching '#{a[1]}'... "
-      open(a[1]) {|remote|
-        open(a[0], 'w+') {|out| out.puts remote.read }
-        stng = true
-      }
-      puts 'OK'
-    end
-  }
-
-  if !stng
-    STDERR.puts 'No matching fetch targets found.'
-    exit 1
-  end
-end