newspaper_works_fixtures 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 02a902019c642f1b7211948001975e8bd636df81fa3da61064b3fcbea18440c6
-  data.tar.gz: fa8964c81494e85b92f8a8ba5267742d7235c52a6c4983f9a4116d5f81ad895e
+  metadata.gz: f9ba6498fb2a01749ad7c3d151d21ea1104840cdde8fb9027379f278522665e3
+  data.tar.gz: 6f223cf8bd3610ed00deb861989db8349b46c5e35736c4dfbdac0a1055e3ef8d
 SHA512:
-  metadata.gz: c6cd10271a654703b913aba2405a9fd4c27827312bab3f26aca80f5432c2cc2461122a43dee175b42bb031c8124a3064ec509ded6387a623685f4c2de5ce30be
-  data.tar.gz: 44e4895761568a68871df76c4f6da14b3ec4a6fb04fb4236296558f180eff10817377dc21280df5bbea1663934bdff00f019a0e33c1a90bb9a0e9ab1229270fe
+  metadata.gz: 51366b43d15d130e5cd02107964412f6d71319413014229619f666764ff5031d6df4b4a348963bd3c7d443310509e6c6b13cd7c1d6af8c3789ac0bded632a89f
+  data.tar.gz: 395e113f45e7d914197d6958f17e2e088efc93099a85b148adae6e3e6ae04b152d80a8183044bd4d447586d759ac2388c3023a58f29e5747e1cc5cb8de93f66e

data/README.md

@@ -61,6 +61,39 @@ files are included as well.
 
 11 image scans; 149 MB
 
+#### PDF and TIFF batch (Chicopee Weekly)
+```ruby
+# /path/to/gem/spec/fixtures/files/article_segmented/batch_deseret_news
+NewspaperWorksFixtures.pdf_batch
+NewspaperWorksFixtures.tiff_batch
+```
+These are two variants of four-page issues of Chicopee Weekly, via 
+[Digital Commonwealth](https://www.digitalcommonwealth.org/collections/commonwealth-oai:xd07gx07n).
+
+The PDF source materials are 400 ppi monochrome (CCITT group 4 compressed),
+with each PDF representing a single four page issue.  The file naming convention
+is as follows:
+
+- Publication directory named with Library of Congress Control Number (LCCN).
+
+- Inside publication directory are PDF files using naming convention of
+  `YYYYMMDDEE.pdf`, where:
+  - `YYYY` is four digit year.
+  - `MM` is month (zero padded).
+  - `DD` is day of month (zero padded).
+  - `EE` is edition number (zero padded).
+
+The TIFF batch likewise is one-bit "Group 4" compressed mononchrome images,
+and use a similar `YYYMMDDEE` naming convention:
+
+- Publication directory named with Library of Congress Control Number (LCCN).
+
+- Directly contained in publication directory are directories, one per issue,
+  using the `YYYYMMDDEE` naming convention/
+
+- Inside issue directories are TIFF files with lexically ordered filenames,
+  corresponding to page sequence order of that issue.
+
 #### Deseret News article segmented batch
 ```ruby
 # /path/to/gem/spec/fixtures/files/article_segmented/batch_deseret_news

data/lib/newspaper_works_fixtures.rb

@@ -31,4 +31,14 @@ module NewspaperWorksFixtures
   def self.article_segmented_batch_topaz_times
     File.join(file_fixtures, 'article_segmented', 'batch_topaz_times')
   end
+
+  # returns the PDF batch (single publication) for Chicopee Weekly
+  def self.pdf_batch
+    File.join(file_fixtures, 'pdf_batch', 'sn93059126')
+  end
+
+  # returns the TIFF batch (extracted from materials in PDF batch)
+  def self.tiff_batch
+    File.join(file_fixtures, 'tiff_batch', 'sn93059126')
+  end
 end

data/lib/newspaper_works_fixtures/version.rb

@@ -1,3 +1,3 @@
 module NewspaperWorksFixtures
-  VERSION = '0.2.0'.freeze
+  VERSION = '0.3.0'.freeze
 end

data/spec/fixtures/files/tiff_batch/README.md

@@ -0,0 +1,28 @@
+## Batch contents
+
+* A root directory named with the LCCN of the publication.
+
+* Contained in the publication directory, two four-page issues, each with
+  its own directory, named with the `YYYYMMDDEE` convention, where:
+    - `YYYY` represents the 4-digit year
+    - `MM` represents the 2-digit month
+    - `DD` represents the 2-digit day
+    - `EE` represents the 2-digit edition number (default is 01)
+
+* In each issue directory, page TIFF files are named in such a way that
+  lexical ordering is observed ("page1.tiff" is before "page2.tiff" in both
+  string evaluation and in human readability).
+
+### Batch details
+
+* _Contained herein are images created from like issue PDFs in `../pdf_batch`._
+
+* These page images were extracted via Ghostscript, with the following command
+syntax:
+
+```
+gs -dNOPAUSE -dBATCH -sDEVICE=tiffg4 -dTextAlphaBits=4 -sOutputFile=page%d.tiff -r400 -f $PDFFILE
+```
+
+* Like the PDF equivalents, containing one-bit monochrome CCITT "Group 4"
+  compressed images, these TIFF images use same compression and bit depth.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: newspaper_works_fixtures
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Sean Upton
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-06-28 00:00:00.000000000 Z
+date: 2019-09-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails
@@ -278,6 +278,15 @@ files:
 - spec/fixtures/files/pdf_batch/sn93059126/1856051001.pdf
 - spec/fixtures/files/pdf_batch/sn93059126/1856051701.pdf
 - spec/fixtures/files/pdf_batch/sn93059126/1856052401.pdf
+- spec/fixtures/files/tiff_batch/README.md
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page1.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page2.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page3.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page4.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page1.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page2.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page3.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page4.tiff
 homepage: https://github.com/marriott-library/newspaper_works_fixtures
 licenses:
 - Apache-2.0
@@ -298,7 +307,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.4
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: newspaper_works_fixtures is a Rails Engine gem providing file fixtures for
@@ -536,3 +545,12 @@ test_files:
 - spec/fixtures/files/pdf_batch/sn93059126/1856051001.pdf
 - spec/fixtures/files/pdf_batch/sn93059126/1856051701.pdf
 - spec/fixtures/files/pdf_batch/sn93059126/1856052401.pdf
+- spec/fixtures/files/tiff_batch/README.md
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page1.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page2.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page3.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1853060401/page4.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page1.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page2.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page3.tiff
+- spec/fixtures/files/tiff_batch/sn93059126/1856051001/page4.tiff