iguvium 0.8.0 → 0.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 50748a9a17471a1f0f58a108ee632344cafad4c0ee6ab6096dbdb297c53b1381
-  data.tar.gz: 6e676513f8aaee937f2dbb28316452a0dcd38f850afdc31a5ef6685200189814
+  metadata.gz: f3c9f4727d6069408bb795a4754c1b3f7098a997b7b6b47a9e114c4c04602f17
+  data.tar.gz: f7490d4f57e2e845740713cddff88fd558070f7ab4481598bf08fc504c33802c
 SHA512:
-  metadata.gz: 4b0c5fc257ae4e8b667f0611f708e744c806de1f319e016e42df3553273c0cda445fe23f29e76ed8ef980eaf4680c21ecd7dccdf4602b721e5731981eace3097
-  data.tar.gz: 563368859fa3684b8baa54f25e788c91f76d46c71b56bfa271fd9d6db2b9e6f74ad4d5937488b42c5f0912fdcc77e09432c214fde7d5c76dca85884e594912cf
+  metadata.gz: b973456ea806aef36d4b8328ae2740f624e31bf169d4861d0c6e095133a2fe33e41780e11830c4f891b2d72204873e20225575130e59f5ab55fe6e496a9c0c45
+  data.tar.gz: 218edd15c127f9d705759d1f32dbedbcd68615d1c4d77d4ca8e63b0d0d12801c759444cc4d4967c81e3cc4d88b4a90fb76792794d69b29a25395561bc78eaf0e

data/README.md

@@ -60,6 +60,10 @@ And then execute:
 Or install it yourself as:
 
     $ gem install iguvium
+    
+If you're not a developer and have a Mac, you maybe have default Ruby installation and no development tools installed.
+
+In this case, run `xcode-select --install` beforehand, and after that install Iguvium as admin: `sudo gem install iguvium` 
 
 ## Usage
 
@@ -85,10 +89,12 @@ iguvium filename.pdf [options]
     -p, --pages     page numbers, comma-separated, no spaces
     -i, --images    use pictures in pdf (usually a bad idea)
     -n, --newlines  keep newlines
+    -t, --text      extract full page text instead of tables
     --verbose       verbose output
 ```
 
-Given a filename, it generates CSV files for the tables detected 
+Given a filename, it generates CSV files for the tables detected or, with `-t` option, 
+just page text. The latter is useful in case of whitespace-separated fixed-width tables.  
 
 ## Implementation details
 There are usually no actual tables in PDFs, only characters with coordinates,

data/exe/iguvium

@@ -9,6 +9,7 @@ opts = Slop.parse { |o|
   o.array '-p', '--pages', 'page numbers, comma-separated, no spaces'
   o.bool '-i', '--images', 'use pictures in pdf (usually a bad idea)'
   o.bool '-n', '--newlines', 'keep newlines'
+  o.bool '-t', '--text', 'extract full page text instead of tables'
   o.bool '--verbose', 'verbose output'
   o.on '--version', 'print the version' do
     puts Iguvium::VERSION
@@ -36,6 +37,17 @@ page_numbers = pages.count.times.to_a if page_numbers.empty?
 # puts page_numbers.inspect
 # puts opts.to_hash.inspect
 
+if opts[:text]
+  page_numbers.each do |number|
+    print "Extracting page #{number + 1}... "
+    txt = pages[number].text
+    txt_file = "#{path.gsub(/\.pdf$/, '')}_page_#{number + 1}.txt"
+    puts "Saving #{File.expand_path txt_file}"
+    File.write txt_file, txt
+  end
+  exit
+end
+
 page_numbers.each do |number|
   print "Extracting page #{number + 1}... "
   tables = pages[number].extract_tables!(images: opts[:images])
@@ -45,7 +57,7 @@ page_numbers.each do |number|
     csv = table.to_a(newlines: opts[:newlines]).map(&:to_csv).join
     next if csv.empty?
     csv_file = "#{path.gsub(/\.pdf$/, '')}_page_#{number + 1}_table_#{i}.csv"
-    puts "Saving #{File.expand_path(csv_file, __dir__)}"
+    puts "Saving #{File.expand_path csv_file}"
     File.write csv_file, csv
   end
 end

data/lib/iguvium/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Iguvium
-  VERSION = '0.8.0'
+  VERSION = '0.8.1'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: iguvium
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.8.1
 platform: ruby
 authors:
 - Dima Ermilov
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-11-19 00:00:00.000000000 Z
+date: 2018-11-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pdf-reader