stevedore-uploader 1.0.12-java → 1.0.13-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f11e36b9388530683b93423de8d0fabf3997d46b
-  data.tar.gz: 68f2bbe57091826e63a0a4de0a39afff43c70a7a
+  metadata.gz: bd37dc975bfda43876f38b9c55f258f0f3667704
+  data.tar.gz: 43d822366937414dc33ff300b45461ce8720405e
 SHA512:
-  metadata.gz: 57e658b3a6ee1147563861165e96ba9346befd3f72b986ace6c4c2cdf5c590e267faa889f8ab72beea8a3aabb8a0e08093001990df39fae4d436d9b18d9622cc
-  data.tar.gz: 298762fd18cd429f3057eb3684510c518b11a6379a2fe692c31791e41fc9c1f08c13f8f9aea21486d18546e584f6f314c50b4180d7d00af31b7d3250da18e1e1
+  metadata.gz: cf35c3b48af3928e4432d48196d49e7f08ac20acfb5eeef80b58365ee4036bf2936187e6247d948b3471670fc846ffbcee5b7d8d19e179ee2e4948fe252a397a
+  data.tar.gz: fbf1d8c9e26e519e5ac9ef09cb56344f2a6820bd55a7770474e51b2981ac1270362af5342213eea4e880acbf1250b08b1249a35cf0eec5733353ac34425f1e68

data/README.md

@@ -22,7 +22,7 @@ This project is in JRuby, so we can leverage the transformative enterprise stabi
 Command-Line Options
 --------------------
 ````
-Usage: upload_to_elasticsearch [options] target_(dir_or_csv)
+Usage: stevedore [options] target_(dir_or_csv)
     -h, --host=SERVER:PORT           The location of the ElasticSearch server
     -i, --index=NAME                 A name to use for the ES index (defaults to using the directory name)
     -s, --s3path=PATH                The path under your bucket where these files have been uploaded. (defaults to ES index)
@@ -41,23 +41,23 @@ Advanced Usage
 
 upload documents from your local disk
 ```
-bundle exec ruby bin/upload_to_elasticsearch.rb --index=INDEXNAMEx [--host=localhost:9200]  [--s3path=name-of-path-under-bucket] path/to/documents/to/parse
+bundle exec ruby bin/stevedore.rb --index=INDEXNAMEx [--host=localhost:9200]  [--s3path=name-of-path-under-bucket] path/to/documents/to/parse
 ```
 or from s3
 ```
-bundle exec ruby bin/upload_to_elasticsearch.rb --index=INDEXNAMEx [--host=localhost:9200]   s3://my-bucket/path/to/documents/to/parse
+bundle exec ruby bin/stevedore.rb --index=INDEXNAMEx [--host=localhost:9200]   s3://my-bucket/path/to/documents/to/parse
 ```
 
 if host isn't specified, we assume `localhost:9200`.
 
 e.g. 
 ```
-bundle exec ruby bin/upload_to_elasticsearch.rb --index=jrubytest --host=https://stevedore.elasticsearch.yourdomain.net/es/ ~/code/marco-rubios-emails/emls/ 
+bundle exec ruby bin/stevedore.rb --index=jrubytest --host=https://stevedore.elasticsearch.yourdomain.net/es/ ~/code/marco-rubios-emails/emls/ 
 ```
 
 you may also specify an s3:// location of documents to parse, instead of a local directory, e.g.
 ```
-bundle exec ruby bin/upload_to_elasticsearch.rb --index=jrubytest --host=https://stevedore.elasticsearch.yourdomain.net/es/ s3://int-data-dumps/marco-rubio-fire-drill
+bundle exec ruby bin/stevedore.rb --index=jrubytest --host=https://stevedore.elasticsearch.yourdomain.net/es/ s3://int-data-dumps/marco-rubio-fire-drill
 ```
 if you choose to process documents from S3, you should upload those documents using your choice of tool -- but `awscli` is a good choice. *Stevedore-Uploader does NOT upload documents to S3 on your behalf.
 

data/bin/{upload_to_elasticsearch.rb → stevedore.rb}

@@ -12,7 +12,7 @@ if __FILE__ == $0
   options = OpenStruct.new
   options.ocr = true
 
-  op = OptionParser.new("Usage: upload_to_elasticsearch [options] target_(dir_or_csv)") do |opts|
+  op = OptionParser.new("Usage: stevedore [options] target_(dir_or_csv)") do |opts|
     opts.on("-hSERVER:PORT", "--host=SERVER:PORT",
             "The location of the ElasticSearch server") do |host|
       options.host = host

data/lib/stevedore-uploader.rb

@@ -127,7 +127,7 @@ module Stevedore
         return nil
       end
       (Dir["#{pdf_basename}-*.png"] + Dir["#{pdf_basename}.png"]).sort_by{|png| (matchdata = png.match(/-\d+\.png/)).nil? ? 0 : matchdata[0].to_i }.each do |png|
-        ret = system('tesseract', png, png, "pdf", "")
+        ret = system('tesseract', png, png, "pdf", "", "quiet")
         if ret.nil?
           STDERR.puts "No tesseract (or not on path); skipping OCR"
           return nil
@@ -187,7 +187,7 @@ module Stevedore
       rescue StandardError, java.lang.NoClassDefFoundError, org.apache.tika.exception.TikaException => e
         STDERR.puts e.inspect
         STDERR.puts "#{e} #{e.message}: #{filename}"
-        STDERR.puts e.backtrace.join("\n") + "\n\n\n"
+        STDERR.puts e.backtrace.join("\n") + "\n\n\n" if e.backtrace
         # puts "\n"
         @errors << filename
         nil

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: stevedore-uploader
 version: !ruby/object:Gem::Version
-  version: 1.0.12
+  version: 1.0.13
 platform: java
 authors:
 - Jeremy B. Merrill
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2017-05-05 00:00:00.000000000 Z
+date: 2017-05-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -166,12 +166,13 @@ dependencies:
         version: 0.0.8
 description: TK
 email: jeremy.merrill@nytimes.com
-executables: []
+executables:
+- stevedore.rb
 extensions: []
 extra_rdoc_files: []
 files:
 - README.md
-- bin/upload_to_elasticsearch.rb
+- bin/stevedore.rb
 - lib/parsers/stevedore_blob.rb
 - lib/parsers/stevedore_csv_row.rb
 - lib/parsers/stevedore_email.rb