iguvium 0.9.1 → 0.9.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 59643f281def94149de22d6b858f1f90f4b4b05289ef4f3ef13f146e4621f6c9
-  data.tar.gz: 7f10445415eadcc746b8d21050443595ecf127c7f6856a8b2962f8d072825447
+  metadata.gz: 8d6b546079935086775c26461dd4ea774d9f0474a4dcae211c71d01544536479
+  data.tar.gz: 8f96f1e0ae92923a268c3eee0431264f6d4324ed7e067e620ec376c1b7325917
 SHA512:
-  metadata.gz: 7d3899e42a5bcaa6359554ff96d803f4a09acdacbb53855887bdedfda9245604cf24054a3588508d58222cf4c7783d031b36bff9c6e3e0cac2476c6552a54dc4
-  data.tar.gz: 8b6011b52aa2232597d1dea4ef087d36d4713879a0a6c76aba3849337f348329357499e8a5d8c3ec9ace4346e64a058d5b6fd415626b6553dfa2f29f6d516278
+  metadata.gz: cdca6bd0a04ab1ba897cd9888acebecc5ee689ffb5c814b0ecce674e96fcbefbb8035c84b6d9eabf3192411153b2aaa43425771e37cd6736ac9dbe52fe4dc364
+  data.tar.gz: 82637dd89b1d3015503f7fff7ae198525a8a0fd0b0050b70285a57e27865e374620a4cc78c93027d650d20840eb9377171271b34bb4b1fc9b44a893ba738822e

data/.travis.yml

@@ -4,4 +4,5 @@ rvm:
   - 2.5.1
   - 2.4.5
   - 2.3.8
+  - 3.1.3
 before_install: gem install bundler && sudo apt-get install ghostscript

data/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 ## [Unreleased]
 
+## [0.9.2] - 2019-05-30
+### Fixed
+- Solving deprecated use of keyword arguments in method calls in Ruby 3
+- Matrix gem needs to be an explicit dependency as of Ruby 3.1.
+
 ## [0.9.1] - 2019-05-30
 ### Fixed
 - Rare `undefined method 'begin' for nil:NilClass` error fixed

data/README.md

@@ -110,6 +110,8 @@ just page text. The latter is useful in case of whitespace-separated fixed-width
 There are usually no actual tables in PDFs, only characters with coordinates,
 and some fancy lines. Human eye interprets this as a table. Iguvium behaves quite similarly. It prints PDF to an image file with GhostScript, then analyses the image.
 
+(Later clarification as per request. It only prints anything but text and images (-dFILTERTEXT -dFILTERIMAGE params of GhostScript, which lefts lines, curves, etc.) to analyze table structure. Text fields are extracted from pdf codepoints, if there are any. Trying to do otherwise would imply a full-blown OCR solution, something like FineReader. So with scanned image-only pdfs it is like an ideal unmatch: nothing is actually printed and there's no text to extract.)
+
 Long enough continuous edges are interpreted as possible cell borders. Gaussian blur is applied beforehand to get rid of possible inconsistencies and style features.
 
 Initially inspired by [camelot](https://github.com/socialcopsdev/camelot/) idea of image analysis to detect table structure. Besides this idea, is an independent work. Image recognition is written in Ruby, no OpenCV or other heavy computer vision libraries are used. Line detection algorithms are different too. The functionality of Camelot is significantly broader.

data/iguvium.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |spec|
   spec.name          = 'iguvium'
   spec.version       = Iguvium::VERSION
   spec.authors       = ['Dima Ermilov']
-  spec.email         = ['dima@scriptangle.com']
+  spec.email         = ['adworse@erlef.org']
 
   spec.summary       = 'Extract tables from PDF as a structured info'
   spec.description   = "Extract tables from PDF as a structured info. Uses ghostscript to print pdf \
@@ -33,8 +33,9 @@ to image, then recognizes table separators optically. No OpenCV or other heavy d
   spec.add_dependency 'oily_png', '~> 1.2'
   spec.add_dependency 'pdf-reader', '~> 2.1'
   spec.add_dependency 'slop', '~> 4.2'
+  spec.add_dependency 'matrix'
 
-  spec.add_development_dependency 'bundler', '~> 1.16'
+  spec.add_development_dependency 'bundler'
   spec.add_development_dependency 'rake', '~> 10.0'
   spec.add_development_dependency 'rspec', '~> 3.0'
 end

data/lib/iguvium/image.rb

@@ -15,7 +15,6 @@ module Iguvium
     #
     # @return [ChunkyPNG::Image]
     def self.read(path, pagenumber = 1, **opts)
-      puts path.shellescape
       rgb = path.gsub(/\.pdf$/, '.rgb')
       Iguvium.logger.info `#{opts[:gspath]} -dSAFER -dBATCH -dNOPAUSE -sDEVICE=pnggray -dGraphicsAlphaBits=4 \
     -r72 -dFirstPage=#{pagenumber} -dLastPage=#{pagenumber} \

data/lib/iguvium/page.rb

@@ -71,7 +71,7 @@ module Iguvium
     private
 
     def recognize!
-      image = Image.read(@path, @reader_page.number, @opts)
+      image = Image.read(@path, @reader_page.number, **@opts)
       recognized = CV.new(image).recognize
       @lines = recognized[:lines]
       @boxes = recognized[:boxes].reject { |box| box_empty?(box) }

data/lib/iguvium/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Iguvium
-  VERSION = '0.9.1'
+  VERSION = '0.9.2'
 end

data/lib/iguvium.rb

@@ -73,7 +73,7 @@ module Iguvium
         opts[:gspath] ||= gs_nix?
       end
 
-      PDF::Reader.new(path, opts).pages.map { |page| Page.new(page, path, opts) }
+      PDF::Reader.new(path, opts).pages.map { |page| Page.new(page, path, **opts) }
     end
 
     # Creates and gives access to Ruby Logger. Default [Logger::Level] is Logger::ERROR.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: iguvium
 version: !ruby/object:Gem::Version
-  version: 0.9.1
+  version: 0.9.2
 platform: ruby
 authors:
 - Dima Ermilov
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2019-05-30 00:00:00.000000000 Z
+date: 2022-12-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: convolver-light
@@ -66,20 +66,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '4.2'
+- !ruby/object:Gem::Dependency
+  name: matrix
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -112,7 +126,7 @@ description: Extract tables from PDF as a structured info. Uses ghostscript to p
   pdf to image, then recognizes table separators optically. No OpenCV or other heavy
   dependencies
 email:
-- dima@scriptangle.com
+- adworse@erlef.org
 executables:
 - iguvium
 extensions: []
@@ -142,7 +156,7 @@ homepage: https://github.com/adworse/iguvium
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -157,9 +171,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
-signing_key: 
+rubygems_version: 3.0.6
+signing_key:
 specification_version: 4
 summary: Extract tables from PDF as a structured info
 test_files: []