slaw 0.3.0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 30603c7c9387a2f1c2fc9d617f667b41824e0b68
-  data.tar.gz: 2b153cb4679f469f4b0b18e4ba8b6da239d69016
+  metadata.gz: d5870ba16d21c7e3577e3b03f4d361a0afc4f60f
+  data.tar.gz: 7ce6c9cdee52a9156a1b5a26b1a75a583bae80ab
 SHA512:
-  metadata.gz: a1fb11223dfbd14614eafaf1436e2b73c17fbdbc3fc0511f54492e3cab616c0a1db4f6ebdff0d0e56b498c23f3de1c8ce81ff7cd67e1784253dd6f22457976a2
-  data.tar.gz: 5d46d60e58c26cc44fef10a23f81de366361d538bfe35f649b6f6a81ea121ade63785d76d081fba26fc6413981ba831771f1c32aa5014bb8a02159122f3f40d5
+  metadata.gz: 24a30dd3aa44f5fa2416548d995fb52228a53c729b0f9834afe1af93c5623f9f22925e9fd939a6611f9b5869b2ed4531db95e059196d0738891c195e861fa42c
+  data.tar.gz: 7880f7ff8953864a056a35864a7c4d4a6a6d4573d755d1f1b8deb4b748e2c5e0d791e0926c837d97abc775aef67dc2c667018a05bb90438ac9964bb73a810683

data/README.md

@@ -70,7 +70,7 @@ extractor = Slaw::Extract::Extractor.new
 text = extractor.extract_from_pdf('/path/to/file.pdf')
 
 # parse the text into a XML and
-generator = Slaw::ZA::ByLawGenerator.new
+generator = Slaw::ZA::BylawGenerator.new
 bylaw = generator.generate_from_text(text)
 puts bylaw.to_xml(indent: 2)
 
@@ -125,7 +125,12 @@ between section titles before and after a section number:
     Definitions
     1. In this by-law, the following words ...
 
-This must be set by the user before parsing.
+This must be set by the user before parsing:
+
+```ruby
+generator = Slaw::ZA::BylawGenerator.new
+generator.parser.options = {section_number_after_title: true}
+```
 
 The parser does its best not to choke on input it doesn't understand, preferring a best effort
 to a completely accurate result. For example it may not be able to work out a section heading
@@ -157,6 +162,17 @@ apply layout rules with CSS.
 
 Slaw can render either an entire document like this, or just a portion of the XML tree.
 
+```ruby
+# render an entire document
+renderer = Slaw::Render::HTMLRenderer.new
+puts renderer.render(bylaw.doc, '/')
+
+# render the first section only
+puts renderer.render(bylaw.sections[0], '/')
+```
+
+For more information, see [/lib/slaw/render/html.rb](/lib/slaw/render/html.rb).
+
 ## Meta-data
 
 Acts and by-laws have metadata which it is not possible to get from their plain text representations,

data/lib/slaw.rb

@@ -17,6 +17,7 @@ require 'slaw/parse/builder'
 require 'slaw/parse/cleanser'
 require 'slaw/parse/error'
 
+require 'slaw/za/bylaw_generator'
 require 'slaw/extract/extractor'
 
 module Slaw

data/lib/slaw/parse/cleanser.rb

@@ -66,11 +66,17 @@ module Slaw
         s.gsub(/^.*Sabinet.*Government Printer.*$/i, '')\
          .gsub(/^.*Provincial Gazette \d+.*$/i, '')\
          .gsub(/^.*Provinsiale Koerant \d+.*$/i, '')\
+         .gsub(/^.*PROVINCIAL GAZETTE.*$/, '')\
+         .gsub(/^.*PROVINSIALE KOERANT.*$/, '')\
          .gsub(/^\s*\d+\s*$/, '')\
+         .gsub(/^.*This gazette is also available.*$/, '')\
         # get rid of date lines
          .gsub(/^\d+\s+\w+\s+\d+$/, '')\
         # get rid of page number lines
-         .gsub(/^\s*page \d+( of \d+)?\s*\n/i, '')
+         .gsub(/^\s*page \d+( of \d+)?\s*\n/i, '')\
+         .gsub(/^\s*\d*\s*No\. \d+$/, '')\
+        # get rid of lines with lots of ____ or ---- chars, they're usually pagebreaks
+         .gsub(/^.*[_-]{5}.*$/, '')
       end
 
       # Get rid of whitespace at the end of lines and at the start and end of the 
@@ -118,6 +124,9 @@ module Slaw
         # "foo" means ...; "bar" means
         s = s.gsub(/; (["”“][^"”“]+?["”“] means)/, ";\n\\1")
 
+        # CHAPTER 4 PARKING METER PARKING GROUNDS Place of parking
+        s = s.gsub(/([A-Z0-9 ]{5,}) ([A-Z][a-z ]{5,})/, "\\1\n\\2")
+
         s
       end
 

data/lib/slaw/version.rb

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "0.3.0"
+  VERSION = "0.3.1"
 end

data/spec/parse/cleanser_spec.rb

@@ -61,6 +61,10 @@ permit; and
     it 'should clean up wrapped definition lines after pdf' do
       subject.break_lines('“agricultural holding” means a portion of land not less than 0.8 hectares in extent used solely or mainly for the purpose of agriculture, horticulture or for breeding or keeping domesticated animals, poultry or bees; “approved” means as approved by the Council; “bund wall” means a containment wall surrounding an above ground storage tank, constructed of an impervious material and designed to contain 110% of the contents of the tank; “certificate of fitness” means a certificate contemplated in section 20; “certificate of registration” means a certificate contemplated in section 35;').should == "“agricultural holding” means a portion of land not less than 0.8 hectares in extent used solely or mainly for the purpose of agriculture, horticulture or for breeding or keeping domesticated animals, poultry or bees;\n“approved” means as approved by the Council;\n“bund wall” means a containment wall surrounding an above ground storage tank, constructed of an impervious material and designed to contain 110% of the contents of the tank;\n“certificate of fitness” means a certificate contemplated in section 20;\n“certificate of registration” means a certificate contemplated in section 35;"
     end
+
+    it 'should break at CAPCASE TO Normal Case' do
+      subject.break_lines('CHAPTER 3 PARKING METER PARKING GROUNDS Place of parking 7. No person may park or cause or permit to be parked any vehicle or allow a vehicle to be or remain in a parking meter parking ground otherwise than in a parking bay.').should == "CHAPTER 3 PARKING METER PARKING GROUNDS\nPlace of parking 7. No person may park or cause or permit to be parked any vehicle or allow a vehicle to be or remain in a parking meter parking ground otherwise than in a parking bay."
+    end
   end
 
   describe '#strip_toc' do
@@ -125,4 +129,12 @@ Definitions and interpretation
 1. (1) In this Chapter, unless the context otherwise indicates-"
     end
   end
+
+  describe '#remove_boilerplate' do
+    it 'should handle no toc' do
+      s = "(2)The provisions of section 12 (1) (a), (b), (d) and (g) and section 12(2), (3), (4) and (5), read with the necessary changes, apply to the taking into custody of cats.\nClaiming of impounded dogs and cats\n_____________________________________________________________________________________________ ___________ By-laws relating to Dogs and Cats for Promulgation\n14. (1) Any person may claim an impounded dog or cat if he or she –\n(a) satisfies the poundmaster that he or she is the owner or is otherwise entitled to the custody of the dog or cat concerned;"
+
+      subject.remove_boilerplate(s).should == "(2)The provisions of section 12 (1) (a), (b), (d) and (g) and section 12(2), (3), (4) and (5), read with the necessary changes, apply to the taking into custody of cats.\nClaiming of impounded dogs and cats\n\n14. (1) Any person may claim an impounded dog or cat if he or she –\n(a) satisfies the poundmaster that he or she is the owner or is otherwise entitled to the custody of the dog or cat concerned;"
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors:
 - Greg Kempe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-23 00:00:00.000000000 Z
+date: 2014-11-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler