simple_text_extract 3.0.5 → 3.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 48a3c8805698e6f4af386789e4b4f11e9a3e38425bb1c2ce467ec7cefa99f2ba
-  data.tar.gz: f66a75c47984d63cf41b4f09f8c874f94da1f2928dddf268b4aac5ce48413f85
+  metadata.gz: bad3e0fab883d324b24e9a06cacdceed53de65e51489be88557a3dcdc5bf39b6
+  data.tar.gz: 2c8b53df878e404f90ca65eacae7ce25bc1663de7f138bed7c8ee744b13ee456
 SHA512:
-  metadata.gz: 5c8a892a0916945062f298c1b78728f62962ccca8404c9aabc7724db73b0806f00c1074bac7e13a94d390c7b67d19b7f5398ef96ea6ef41439ea66ba4bf78d3b
-  data.tar.gz: f0de6277f88c6debeaaac4bea385b3ba6e4d9180f53e5a2cef288ce5f80a30e92f67ad7e46c08aa908fb5ee30ccaffb1aaf0ea5ac4560cb2aa8262c8a610ce05
+  metadata.gz: a2e1d6659ddfd9cf3252afc481db1077499ecfab0b4602b52555d6f5f18a29b7a7bbeb671009a0505be547a5ad553accbebf037df3f5a4aec1f9673fc4ff0069
+  data.tar.gz: c3363629bf98d6fd55ac380830c2b7721903361a021e0ee10c5ddf33566be27199dda7e569cdc6821110a2200d3804d62f85d936a99165b58584df52c955afe1

data/.github/workflows/{build.yml → test.yml}

@@ -1,14 +1,20 @@
 name: build
-on: [push, pull_request]
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
 jobs:
   build:
     strategy:
       fail-fast: false
       matrix:
         include:
-          - ruby: 3.2
+          - ruby: 3.3
             gemfile: Gemfile
-          - ruby: 3.1
+          - ruby: 3.2
             gemfile: Gemfile
     runs-on: ubuntu-latest
     env:

data/.ruby-version

@@ -1 +1 @@
-3.2.2
+3.3.4

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 3.0.6 (2024-07-12)
+
+- Stop depending on Active::Support (#present?)
+
 ## 3.0.3 (2023-04-27)
 
 - Add support for extracting text from tables in DOCX files.

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    simple_text_extract (3.0.5)
+    simple_text_extract (3.0.7)
       roo (~> 2.10.0)
       rubyzip (~> 2.3.2)
       spreadsheet (~> 1.3.0)
@@ -10,54 +10,56 @@ GEM
   remote: https://rubygems.org/
   specs:
     ast (2.4.2)
-    base64 (0.1.1)
+    bigdecimal (3.1.8)
     coderay (1.1.3)
-    json (2.6.3)
+    json (2.7.2)
     language_server-protocol (3.17.0.3)
-    memory_profiler (1.0.1)
-    method_source (1.0.0)
-    minitest (5.20.0)
-    mocha (2.1.0)
+    memory_profiler (1.0.2)
+    method_source (1.1.0)
+    minitest (5.24.1)
+    mocha (2.4.0)
       ruby2_keywords (>= 0.0.5)
-    nokogiri (1.15.4-arm64-darwin)
+    nokogiri (1.16.6-arm64-darwin)
       racc (~> 1.4)
-    nokogiri (1.15.4-x86_64-linux)
+    nokogiri (1.16.6-x86_64-linux)
       racc (~> 1.4)
-    parallel (1.23.0)
-    parser (3.2.2.4)
+    parallel (1.25.1)
+    parser (3.3.4.0)
       ast (~> 2.4.1)
       racc
     pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    racc (1.7.1)
+    racc (1.8.0)
     rainbow (3.1.1)
-    rake (13.0.6)
-    regexp_parser (2.8.2)
-    rexml (3.2.6)
-    roo (2.10.0)
+    rake (13.2.1)
+    regexp_parser (2.9.2)
+    rexml (3.3.1)
+      strscan
+    roo (2.10.1)
       nokogiri (~> 1)
       rubyzip (>= 1.3.0, < 3.0.0)
-    rubocop (1.57.1)
-      base64 (~> 0.1.1)
+    rubocop (1.65.0)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.2.2.4)
+      parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
+      regexp_parser (>= 2.4, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.28.1, < 2.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.29.0)
-      parser (>= 3.2.1.0)
-    ruby-ole (1.2.12.2)
+    rubocop-ast (1.31.3)
+      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 (1.3.0)
+    spreadsheet (1.3.1)
+      bigdecimal
       ruby-ole
+    strscan (3.1.0)
     unicode-display_width (2.5.0)
 
 PLATFORMS
@@ -75,4 +77,4 @@ DEPENDENCIES
   simple_text_extract!
 
 BUNDLED WITH
-   2.4.10
+   2.5.11

data/lib/simple_text_extract/extract.rb

@@ -78,7 +78,7 @@ class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
     def pdf_extract
       return nil if SimpleTextExtract.missing_dependency?("pdftotext")
 
-      `pdftotext #{Shellwords.escape(file.path)} -`
+      `pdftotext #{Shellwords.escape(file.path)} - 2>/dev/null`
     end
 
     def xlsx_extract
@@ -93,7 +93,7 @@ class SimpleTextExtract::Extract # rubocop:disable Metrics/ClassLength
         text << "# Sheet Name: #{name}"
 
         spreadsheet.sheet(name)&.each_row_streaming do |row|
-          text << row.filter(&:present?).join(" ")
+          text << row.map(&:to_s).join(" ")
         end
       end
 

data/lib/simple_text_extract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleTextExtract
-  VERSION = "3.0.5"
+  VERSION = "3.0.7"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_text_extract
 version: !ruby/object:Gem::Version
-  version: 3.0.5
+  version: 3.0.7
 platform: ruby
 authors:
 - Nick Weiland
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-10-23 00:00:00.000000000 Z
+date: 2024-07-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -60,7 +60,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - "-"
-- ".github/workflows/build.yml"
+- ".github/workflows/test.yml"
 - ".gitignore"
 - ".rubocop.yml"
 - ".ruby-version"
@@ -97,7 +97,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements:
 - antiword
 - pdftotext/poppler
-rubygems_version: 3.4.10
+rubygems_version: 3.5.15
 signing_key:
 specification_version: 4
 summary: Extract text from various file types before resorting to an OCR solution.