slaw 0.8.2 → 0.8.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ebc9c571ef0b0a1ef1bff4a209bac844df2d22a3
-  data.tar.gz: 6052a4641c800a8510ec02aeddc6653cb482a349
+  metadata.gz: 86252d91f002c7d21cc40838a6656943a705358a
+  data.tar.gz: c1f63cc236fc5dce297ffd3e08bbf2ea9eb4482c
 SHA512:
-  metadata.gz: d57425bab077cc85397b0c05bd2f68d187e64278f4758006d9679aa00ef002a519071a960e3703b1bd608b2ab4bccac544e3d7254869ea7f47840d4420e066d0
-  data.tar.gz: fe7372c0aee508e481d5c2665747030a1b26e11d00e912311424d79c6cf30438db81dbe4577ab14aae6efb99aaa8f33dc30d605c1691a9c48b632354c63d0817
+  metadata.gz: e0191f62145209f2d0506366011519fe634cd27d8a0bbb1e62fe3415ea7a4967ed9f5a84960305546834622051bcc97674e10261e71b5da57b88b73bb2b4c163
+  data.tar.gz: fe67681172b29cc3ec971276cfb1124984f27999f80af064665c0cd402e03c4b941da9ec2e85745be453f751057038068db2f627c2392e09b7b07a9671cf2c8a

data/README.md

@@ -216,6 +216,10 @@ Akoma Ntoso `component` elements at the end of the XML document, with a name of
 
 ## Changelog
 
+### 0.8.3
+
+* During cleanup, break lines on section titles that don't have a space after the number, eg: "New section title 4.(1) The content..."
+
 ### 0.8.2
 
 * Schedules can be empty (#10)

data/lib/slaw/parse/cleanser.rb

@@ -103,10 +103,10 @@ module Slaw
         # often we find a section title munged onto the same line as its first statement
         # eg:
         # foo bar. New section title 62. (1) For the purpose
-        s = s.gsub(/\. ([^.]+) (\d+\. \(1\) )/, ".\n" + '\1' + "\n" + '\2')
+        s = s.gsub(/\. ([^.]+) (\d+\. ?\(1\) )/, ".\n" + '\1' + "\n" + '\2')
 
         # New section title 62. (1) For the purpose
-        s = s.gsub(/(\w) (\d+\. \(1\) )/, '\1' + "\n" + '\2')
+        s = s.gsub(/(\w) (\d+\. ?\(1\) )/, '\1' + "\n" + '\2')
 
         # (1) foo; (2) bar
         # (1) foo. (2) bar

data/lib/slaw/version.rb

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "0.8.2"
+  VERSION = "0.8.3"
 end

data/spec/parse/cleanser_spec.rb

@@ -55,7 +55,9 @@ permit; and
 
     it 'should break lines at likely section titles' do
       subject.break_lines('foo bar. New section title 62. (1) For the purpose').should == "foo bar.\nNew section title\n62. (1) For the purpose"
+      subject.break_lines('foo bar. New section title 62.(1) For the purpose').should == "foo bar.\nNew section title\n62.(1) For the purpose"
       subject.break_lines('New section title 62. (1) For the purpose').should == "New section title\n62. (1) For the purpose"
+      subject.break_lines('New section title 62.(1) For the purpose').should == "New section title\n62.(1) For the purpose"
     end
 
     it 'should clean up wrapped definition lines after pdf' do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 0.8.2
+  version: 0.8.3
 platform: ruby
 authors:
 - Greg Kempe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-07 00:00:00.000000000 Z
+date: 2016-01-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler