simple_text_extract 3.0.7 → 3.0.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bad3e0fab883d324b24e9a06cacdceed53de65e51489be88557a3dcdc5bf39b6
-  data.tar.gz: 2c8b53df878e404f90ca65eacae7ce25bc1663de7f138bed7c8ee744b13ee456
+  metadata.gz: b19c5d7467780a0ccb69fb18e29eb81c9acb7e16caf39a93ddeedaf325d541bd
+  data.tar.gz: 942c5a13853805d7e66feacf997e5a9181e69ea309a880916ca08653c0e3e8bd
 SHA512:
-  metadata.gz: a2e1d6659ddfd9cf3252afc481db1077499ecfab0b4602b52555d6f5f18a29b7a7bbeb671009a0505be547a5ad553accbebf037df3f5a4aec1f9673fc4ff0069
-  data.tar.gz: c3363629bf98d6fd55ac380830c2b7721903361a021e0ee10c5ddf33566be27199dda7e569cdc6821110a2200d3804d62f85d936a99165b58584df52c955afe1
+  metadata.gz: 42303612565dbfe9f23f699c3e554fb9509bbf7165e24d5b4b1fbea3f0ffe0bcd9f8723ac39861341f978b734ab671d17f6aa5a530e6fcf47dddfbe6e796acd1
+  data.tar.gz: c07deca30b24a70fef2baf7967bcfb411d4a60bdd24c624ce0a328e83be4ed558dca2628f468fa27b9d66e5e317413539d15d7b1bb551a8ec987d80eb69723a6

data/.rubocop.yml

@@ -111,5 +111,8 @@ Lint/MissingSuper:
 Lint/ConstantDefinitionInBlock:
   Enabled: false
 
+Lint/SuppressedException:
+  Enabled: false
+
 Style/SingleArgumentDig:
   Enabled: false

data/Gemfile.lock

@@ -1,7 +1,9 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (3.0.7)
+    simple_text_extract (3.0.9)
+      base64
+      csv
       roo (~> 2.10.0)
       rubyzip (~> 2.3.2)
       spreadsheet (~> 1.3.0)
@@ -10,61 +12,62 @@ GEM
   remote: https://rubygems.org/
   specs:
     ast (2.4.2)
-    bigdecimal (3.1.8)
+    base64 (0.2.0)
+    bigdecimal (3.1.9)
     coderay (1.1.3)
-    json (2.7.2)
+    csv (3.3.2)
+    json (2.9.1)
     language_server-protocol (3.17.0.3)
-    memory_profiler (1.0.2)
+    memory_profiler (1.1.0)
     method_source (1.1.0)
-    minitest (5.24.1)
-    mocha (2.4.0)
+    minitest (5.25.4)
+    mocha (2.7.1)
       ruby2_keywords (>= 0.0.5)
-    nokogiri (1.16.6-arm64-darwin)
+    nokogiri (1.18.1-arm64-darwin)
       racc (~> 1.4)
-    nokogiri (1.16.6-x86_64-linux)
+    nokogiri (1.18.1-x86_64-linux-gnu)
       racc (~> 1.4)
-    parallel (1.25.1)
-    parser (3.3.4.0)
+    parallel (1.26.3)
+    parser (3.3.6.0)
       ast (~> 2.4.1)
       racc
-    pry (0.14.2)
+    pry (0.15.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    racc (1.8.0)
+    racc (1.8.1)
     rainbow (3.1.1)
     rake (13.2.1)
-    regexp_parser (2.9.2)
-    rexml (3.3.1)
-      strscan
+    regexp_parser (2.10.0)
     roo (2.10.1)
       nokogiri (~> 1)
       rubyzip (>= 1.3.0, < 3.0.0)
-    rubocop (1.65.0)
+    rubocop (1.69.2)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 2.4, < 3.0)
-      rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.31.1, < 2.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.36.2, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.31.3)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.37.0)
       parser (>= 3.3.1.0)
     ruby-ole (1.2.13.1)
     ruby-progressbar (1.13.0)
     ruby2_keywords (0.0.5)
     rubyzip (2.3.2)
-    spreadsheet (1.3.1)
+    spreadsheet (1.3.3)
       bigdecimal
       ruby-ole
-    strscan (3.1.0)
-    unicode-display_width (2.5.0)
+    unicode-display_width (3.1.3)
+      unicode-emoji (~> 4.0, >= 4.0.4)
+    unicode-emoji (4.0.4)
 
 PLATFORMS
   arm64-darwin-21
   arm64-darwin-23
+  arm64-darwin-24
   x86_64-linux
 
 DEPENDENCIES

data/lib/simple_text_extract/extract.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require "open3"
+
 class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
   def self.formatter(path)
     case path
@@ -78,7 +80,13 @@ class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
     def pdf_extract
       return nil if SimpleTextExtract.missing_dependency?("pdftotext")
 
-      `pdftotext #{Shellwords.escape(file.path)} - 2>/dev/null`
+      stdout, stderr, status = Open3.capture3("pdftotext #{Shellwords.escape(file.path)} -")
+      if status.success?
+        stdout
+      else
+        warn "pdftotext failed: #{stderr}"
+        nil
+      end
     end
 
     def xlsx_extract
@@ -87,13 +95,14 @@ class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
       spreadsheet = Roo::Spreadsheet.open(file, only_visible_sheets: true)
 
       text = []
-
       spreadsheet.sheets.each_with_index do |name, i|
         text << "# Sheet Index: #{i}"
         text << "# Sheet Name: #{name}"
 
         spreadsheet.sheet(name)&.each_row_streaming do |row|
-          text << row.map(&:to_s).join(" ")
+          text << row.map do |cell|
+            cell.value.to_s
+          end.join(" ")
         end
       end
 
@@ -116,7 +125,13 @@ class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
     def doc_extract
       return nil if SimpleTextExtract.missing_dependency?("antiword")
 
-      `antiword #{Shellwords.escape(file.path)}`
+      stdout, stderr, status = Open3.capture3("antiword #{Shellwords.escape(file.path)}")
+      if status.success?
+        stdout
+      else
+        warn "antiword failed: #{stderr}"
+        nil
+      end
     end
 
     def docx_extract

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "3.0.7"
+  VERSION = "3.0.9"
 end

data/simple_text_extract.gemspec

@@ -27,6 +27,8 @@ Gem::Specification.new do |spec|
   spec.requirements << "pdftotext/poppler"
 
   spec.add_dependency "roo", "~> 2.10.0"
-  spec.add_dependency "spreadsheet", "~> 1.3.0"
   spec.add_dependency "rubyzip", "~> 2.3.2"
+  spec.add_dependency "spreadsheet", "~> 1.3.0"
+  spec.add_dependency "base64"
+  spec.add_dependency "csv"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 3.0.7
+  version: 3.0.9
 platform: ruby
 authors:
 - Nick Weiland
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-07-12 00:00:00.000000000 Z
+date: 2024-12-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 2.10.0
+- !ruby/object:Gem::Dependency
+  name: rubyzip
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.3.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.3.2
 - !ruby/object:Gem::Dependency
   name: spreadsheet
   requirement: !ruby/object:Gem::Requirement
@@ -39,19 +53,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 1.3.0
 - !ruby/object:Gem::Dependency
-  name: rubyzip
+  name: base64
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.2
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.2
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: csv
+  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'
 description: Extract text from various file types before resorting to an OCR solution.
 email:
 - nickweiland@gmail.com
@@ -97,7 +125,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements:
 - antiword
 - pdftotext/poppler
-rubygems_version: 3.5.15
+rubygems_version: 3.5.21
 signing_key:
 specification_version: 4
 summary: Extract text from various file types before resorting to an OCR solution.