twitter_ebooks 3.0.8 → 3.0.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 76bdf6be758e91a56b4859679ea87f82bc77ff8a
-  data.tar.gz: e6a7cce43c71851d55ab214a01c0ce30afe0b45d
+  metadata.gz: 3f4312e16bb18ae646bbca7559d3044ecc7b00f7
+  data.tar.gz: 9fdcb9b3eb8cf9fc4449699ed20661a8b5ef8d2a
 SHA512:
-  metadata.gz: ed2d13e08bb0dbd4bb54b15f5c3d0d9037031300a54b251479e065f69c0850df819a64edc97b151bc967d3839cb9ac6337bf1a96440709f4c18ffbe0707b9fbc
-  data.tar.gz: dc979c49978d6d9e9fe474882c4c0bb8b2747658e7bb5f164df8051987281a1496ab14eb32d4c73f200df21f241acbed8cf0df4771e4d41666d851f359589e5c
+  metadata.gz: 39aee9bc75ffe627b24d1f6ae29f7bfd1c3093e3295dfebf5fdafb67b8ed649f417811112c5086f50449bb0a21ee899e7e3a5896e76a0de32a524da548e05a39
+  data.tar.gz: 8136aec89545928bd5a04dd94fd14c078752a913f098a32a6ee96fd2c065f9d03ed14dcdc32550ce17d9f3815aaaee20153b2e24f617903e34502faa85e19a3b

data/README.md

@@ -93,7 +93,7 @@ The underlying streaming and REST clients from the [twitter gem](https://github.
 
 ## Archiving accounts
 
-twitter\_ebooks comes with a syncing tool to download and then incrementally update a local json archive of a user's tweets.
+twitter\_ebooks comes with a syncing tool to download and then incrementally update a local json archive of a user's tweets (in this case, my good friend @0xabad1dea):
 
 ``` zsh
 ➜  ebooks archive 0xabad1dea corpus/0xabad1dea.json

data/bin/ebooks

@@ -114,6 +114,52 @@ STR
     log "Corpuses consumed to #{outpath}"
   end
 
+  HELP.jsonify = <<-STR
+    Usage: ebooks jsonify <tweets.csv> [tweets.csv2] [...]
+
+    Takes a csv twitter archive and converts it to json.
+  STR
+
+  def self.jsonify(paths)
+    if paths.empty?
+      log usage
+      exit
+    end
+
+    paths.each do |path|
+      name = File.basename(path).split('.')[0]
+      new_path = name + ".json"
+
+      tweets = []
+      id = nil
+      if path.split('.')[-1] == "csv" #from twitter archive
+        csv_archive = CSV.read(path, :headers=>:first_row)
+        tweets = csv_archive.map do |tweet|
+          { text: tweet['text'], id: tweet['tweet_id'] }
+        end
+      else
+        File.read(path).split("\n").each do |l|
+          if l.start_with?('# ')
+            id = l.split('# ')[-1]
+          else
+            tweet = { text: l }
+            if id
+              tweet[:id] = id
+              id = nil
+            end
+            tweets << tweet
+          end
+        end
+      end
+
+      File.open(new_path, 'w') do |f|
+        log "Writing #{tweets.length} tweets to #{new_path}"
+        f.write(JSON.pretty_generate(tweets))
+      end
+    end
+  end
+
+
   HELP.gen = <<-STR
     Usage: ebooks gen <model_path> [input]
 

data/lib/twitter_ebooks/model.rb

@@ -118,7 +118,7 @@ module Ebooks
           tweet[text_col]
         end
       else
-        log "Reading plaintext corpus from #{path}"
+        log "Reading plaintext corpus from #{path} (if this is a json or csv file, please rename the file with an extension and reconsume)"
         lines = content.split("\n")
       end
 

data/lib/twitter_ebooks/version.rb

@@ -1,3 +1,3 @@
 module Ebooks
-  VERSION = "3.0.8"
+  VERSION = "3.0.9"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: twitter_ebooks
 version: !ruby/object:Gem::Version
-  version: 3.0.8
+  version: 3.0.9
 platform: ruby
 authors:
 - Jaiden Mispy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-02-08 00:00:00.000000000 Z
+date: 2015-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec