simple_text_extract 3.0.0 → 3.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 411c821b9a0f6ab4f5b95d0104786fbca88c42ab97fa4bd41e8443baae7c80a3
-  data.tar.gz: e6034b96a08ed5bea7abc61e0fb0c762e4c16c44a1e4d54adbc7eff2d9a8bcab
+  metadata.gz: 388ec404e856a47441f3bb3e23873d70eff4fabf86d96afcfeb6f7ad324e262d
+  data.tar.gz: 054f2cdb252b91ae14bdc678af1b75d433bfc6266d68ccace27ce4ec829c6484
 SHA512:
-  metadata.gz: 87d96e6217062b72e104ac1165475d3af497937532fe7f03364128086f6ab61d490d650d60030813783ba32c418bbab564455dc0659882724e6711d9a612cc4d
-  data.tar.gz: 645af90b82616a06805603d2417498890f6fbb53c0d2661934b9ec40d686550c97a42b5bbcc9cf8fe90c049367e45a2e8dd76af8f29d375d8f501beed5be4b16
+  metadata.gz: 5c5a9d4f02bd00f32495803f60b2552d084f204a39df5c239d29e9be2c04013ae44b865c805c750c3a52a51a5e9b93a358e97d386a351aa16460664e048bac61
+  data.tar.gz: f7bc4192659abaf6653f58c01b446e11e483dddad2efb91ebf077a88767346f50997d87ba8af5d4ab26e7ac2ed7bf6a4393fecf75b78b1968662a266e251a84e

data/CHANGELOG.md

@@ -1,4 +1,12 @@
-## 2.0.0 (2023-04-14)
+## 3.0.1 (2023-04-17)
+
+- Coerces filename in `SimpleTextExtract.supports?(filename:)` to string.
+
+## 3.0.1 (2023-04-17)
+
+- Fixes printing of Roo::Excelx::Cell::Empty for empty rows
+
+## 3.0.0 (2023-04-14)
 
 - [BREAKING CHANGE] Improves format of text extracts to better support post processing into sentences/rows. This will only cause issues if you have tests/code that relies on the specific format of whitespace characters in the resulting extracts. For example, the docx extract will now preserve newline characters.
 - Improves memory allocation for xlsx files using `Roo#each_row_streaming`

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (3.0.0)
+    simple_text_extract (3.0.2)
       roo (~> 2.10.0)
       rubyzip (~> 2.3.2)
       spreadsheet (~> 1.3.0)

data/lib/simple_text_extract/extract.rb

@@ -88,10 +88,13 @@ class SimpleTextExtract::Extract
 
       text = []
 
-      spreadsheet.sheets.each do |name|
-        text << name
+      spreadsheet.sheets.each_with_index do |name, i|
+        text << "# Sheet Index: #{i}"
+        text << "# Sheet Name: #{name}"
 
-        spreadsheet.sheet(name)&.each_row_streaming { |row| text << row.join(" ") }
+        spreadsheet.sheet(name)&.each_row_streaming do |row|
+          text << row.filter(&:present?).join(" ")
+        end
       end
 
       text.join("\n")

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "3.0.0"
+  VERSION = "3.0.2"
 end

data/lib/simple_text_extract.rb

@@ -13,7 +13,7 @@ module SimpleTextExtract
   end
 
   def self.supports?(filename: nil)
-    SUPPORTED_FILETYPES.include?(filename.split(".").last)
+    SUPPORTED_FILETYPES.include?(filename.to_s.split(".").last)
   end
 
   def self.missing_dependency?(command)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 3.0.0
+  version: 3.0.2
 platform: ruby
 authors:
 - Nick Weiland
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-04-14 00:00:00.000000000 Z
+date: 2023-04-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo