slaw 0.15.2 → 0.16.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ee90224965ffec0a5ecc89db6255f71a0c130985
-  data.tar.gz: db7f6af7264958130f57970af720b447bfea5955
+  metadata.gz: 27b008d695654755f54463b4aad7e409fdafc848
+  data.tar.gz: f5efa73340972f8a7b3544b6c1f9b7a407bca342
 SHA512:
-  metadata.gz: a7c52d0b2bc3ced5734e5ebd2c1bacc06cffd9c8d48ec9e7c5411c59f51622ce3eea70b2913b2c39de5f49eecebd15403447c28cda4b4c3ecccac0110ef8b436
-  data.tar.gz: de5f75e9033bac55ba54877e1730d2a12d973fef04c4f76c2ead30e78a9efdebd7908b065c0f307772318cf39e14d58afb978dc3a1c41a602311b46533b60546
+  metadata.gz: 14ed037256e022623d0d593bb1276e4dc669c2d3ce8dc0823e20c1e276b50e1509b62f30809db9d6c6bd8a3de56643f2d534f310f28161ef1a3fe15280466be6
+  data.tar.gz: 13b3c0757cb8c49ce28c8c0751831cb79f839d2e8a43459b3a0003339a3051d1edfc480fd936650a8acd3b08cf4a18763f13707df617e3d865b28a19f00bebb8

data/README.md

@@ -28,10 +28,10 @@ Or install it with:
 
     $ gem install slaw
 
-To run PDF extraction you will also need [xpdf](http://www.foolabs.com/xpdf/) and
+To run PDF extraction you will also need [poppler's pdftotext](https://poppler.freedesktop.org/).
 If you're on a Mac, you can use:
 
-    $ brew install xpdf
+    $ brew install poppler
 
 You may also need Ghostscript to remove password protection from PDF files. This is
 installed by default on most systems (including Mac). On Ubuntu you can use:
@@ -218,6 +218,10 @@ Akoma Ntoso `component` elements at the end of the XML document, with a name of
 
 ## Changelog
 
+### 0.16.0
+
+* Support --crop for PDFs. Requires [poppler](https://poppler.freedesktop.org/) pdftotex, not xpdf.
+
 ### 0.15.2
 
 * Update nokogiri to ~> 1.8.1

data/bin/slaw

@@ -22,6 +22,7 @@ class SlawCLI < Thor
   option :id_prefix, type: :string, desc: "Prefix to be used when generating ID elements when parsing a fragment."
   option :section_number_position, enum: ['before-title', 'after-title', 'guess'], desc: "Where do section titles come in relation to the section number? Default: before-title"
   option :reformat, type: :boolean, desc: "Reformat common formatting issues to make grammar matching better. Default: true for PDF files, false otherwise"
+  option :crop, type: :string, desc: "Crop box for PDF files, as 'left,top,width,height'."
   def parse(name)
     logging
 
@@ -32,6 +33,13 @@ class SlawCLI < Thor
     Slaw::Extract::Extractor.pdftotext_path = options[:pdftotext] if options[:pdftotext]
     extractor = Slaw::Extract::Extractor.new
 
+    if options[:crop]
+      extractor.cropbox = options[:crop].split(',').map(&:to_i)
+      if extractor.cropbox.length != 4
+        raise Thor::Error.new("--crop requires four comma-separated integers")
+      end
+    end
+
     case options[:input]
     when 'pdf'
       text = extractor.extract_from_pdf(name)

data/lib/slaw/extract/extractor.rb

@@ -17,6 +17,8 @@ module Slaw
 
       @@pdftotext_path = "pdftotext"
 
+      attr_accessor :cropbox
+
       # Extract text from a file.
       #
       # @param filename [String] filename to extract from
@@ -73,7 +75,14 @@ module Slaw
       #
       # @return [Array<String>] command and params to execute
       def pdf_to_text_cmd(filename)
-        [Extractor.pdftotext_path, "-enc", "UTF-8", filename, "-"]
+        cmd = [Extractor.pdftotext_path, "-enc", "UTF-8", "-nopgbrk"]
+
+        if @cropbox
+          # left, top, width, height
+          cmd += "-x -y -W -H".split.zip(@cropbox.map(&:to_s)).flatten
+        end
+
+        cmd + [filename, "-"]
       end
 
       def extract_from_text(filename)

data/lib/slaw/version.rb

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "0.15.2"
+  VERSION = "0.16.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 0.15.2
+  version: 0.16.0
 platform: ruby
 authors:
 - Greg Kempe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-12-22 00:00:00.000000000 Z
+date: 2018-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler