simple_text_extract 3.0.2 → 3.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 388ec404e856a47441f3bb3e23873d70eff4fabf86d96afcfeb6f7ad324e262d
-  data.tar.gz: 054f2cdb252b91ae14bdc678af1b75d433bfc6266d68ccace27ce4ec829c6484
+  metadata.gz: 1bcf42e8ea86d7b9bb1f14731cbf2219e5d2a3c9bca5288e0441776b9822a835
+  data.tar.gz: 3d17a5ec43537ea50c64b8b07237cd21125794084fa964a121267895b5ba5023
 SHA512:
-  metadata.gz: 5c5a9d4f02bd00f32495803f60b2552d084f204a39df5c239d29e9be2c04013ae44b865c805c750c3a52a51a5e9b93a358e97d386a351aa16460664e048bac61
-  data.tar.gz: f7bc4192659abaf6653f58c01b446e11e483dddad2efb91ebf077a88767346f50997d87ba8af5d4ab26e7ac2ed7bf6a4393fecf75b78b1968662a266e251a84e
+  metadata.gz: 7f452ddf56c6d464f4d16de10e4c934bd97b78e6adbedb43b163a5511881b81d466f3064e963410957b194420f74c0c6b554356b411f03845b37c417c845244f
+  data.tar.gz: be9d14077b31539fe14aec768cea5669958c922f0360eb8125e9289a8df61a36a6a2574b7ea1458eed010cf474ef80d70e7a601083016a0d968e37417c314c30

data/-

@@ -0,0 +1 @@
+Test

data/CHANGELOG.md

@@ -1,4 +1,8 @@
-## 3.0.1 (2023-04-17)
+## 3.0.3 (2023-04-27)
+
+- Add support for extracting text from tables in DOCX files.
+
+## 3.0.2 (2023-04-17)
 
 - Coerces filename in `SimpleTextExtract.supports?(filename:)` to string.
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (3.0.2)
+    simple_text_extract (3.0.4)
       roo (~> 2.10.0)
       rubyzip (~> 2.3.2)
       spreadsheet (~> 1.3.0)

data/lib/simple_text_extract/extract.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-class SimpleTextExtract::Extract
+class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
   def self.formatter(path)
     case path
     when /.zip$/i
@@ -28,7 +28,7 @@ class SimpleTextExtract::Extract
   end
 
   def to_s
-    @to_s ||= extract.to_s.gsub(/[^\S\n]+/, " ").gsub(/\s?\n\s+/, "\n").strip
+    @to_s ||= extract.to_s.scrub.gsub(/[^\S\n]+/, " ").gsub(/\s?\n\s+/, "\n").strip
   end
 
   private
@@ -133,6 +133,13 @@ class SimpleTextExtract::Extract
         doc.xpath("//w:document//w:body/w:p").each do |node|
           result << node.text
         end
+
+        doc.xpath("//w:document//w:body//w:tbl").each do |node|
+          node.xpath(".//w:tr").each do |row|
+            text = row.xpath("w:tc").map(&:text)
+            result << text.join(", ")
+          end
+        end
       end
 
       result.join("\n")

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "3.0.2"
+  VERSION = "3.0.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 3.0.2
+  version: 3.0.4
 platform: ruby
 authors:
 - Nick Weiland
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-04-18 00:00:00.000000000 Z
+date: 2023-06-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -59,6 +59,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- "-"
 - ".github/workflows/build.yml"
 - ".gitignore"
 - ".rubocop.yml"