act_as_page_extractor 0.7.1 → 0.7.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4a11b311c9575aace2a74e468f35b062c6e444d58e6f62caed99b70bab60703b
-  data.tar.gz: 9c463a553f4e3490110f46626d2c4c6c0f124b2522c63ef0e7db2acc856b12a2
+  metadata.gz: 150243f19490b089622edb3ca6e265347bcdadab21701de0865a63274b23fc8d
+  data.tar.gz: b3f0d0d90d3b035e4b4d9bee313f6084b46a8e686cc5c873ea5413ea3ab9cf50
 SHA512:
-  metadata.gz: 4db62f37880a270dfe39dcedf5a537b2e5699633709348a030ae2274218478493c994099d38e7ff21729bdf543e681c66b818d2bc321b6b49f1478fa348d00c7
-  data.tar.gz: e2df6c4f723418d1098b0d0afac87fef847b50a87a766198e13ee42b8ff2cf4fac5e2788f09a7105ee13dbec4d84bfaf5084f9bcae7ad127915ab08d652f9deb
+  metadata.gz: 2cd0e7c24705e0eb3e646dba87343a06ac23fbaf16d2b1cacaf164046d096b2e65dc8a890bd923b2a59975ecfaacfd58e5e3ddcf61b8cf4610739b465c2af5b7
+  data.tar.gz: ab1e2e4e85117d9a4147ecdcd6ff32be761f3a7bbffee19b1041be8e0c9ea8d665f1358468e27549ab493d36b0fed05d2e2e06fdb7fccd1482b56defb459ac49

data/Gemfile.lock

@@ -1,8 +1,8 @@
 PATH
   remote: .
   specs:
-    act_as_page_extractor (0.7.1)
-      activerecord (~> 6.0)
+    act_as_page_extractor (0.7.3)
+      activerecord (~> 7.0)
       amazing_print (~> 1)
       docsplit (~> 0)
       filesize (~> 0)
@@ -15,30 +15,43 @@ GEM
   remote: https://rubygems.org/
   specs:
     Ascii85 (1.0.3)
-    activemodel (6.1.7.8)
-      activesupport (= 6.1.7.8)
-    activerecord (6.1.7.8)
-      activemodel (= 6.1.7.8)
-      activesupport (= 6.1.7.8)
-    activesupport (6.1.7.8)
-      concurrent-ruby (~> 1.0, >= 1.0.2)
+    activemodel (7.2.2.2)
+      activesupport (= 7.2.2.2)
+    activerecord (7.2.2.2)
+      activemodel (= 7.2.2.2)
+      activesupport (= 7.2.2.2)
+      timeout (>= 0.4.0)
+    activesupport (7.2.2.2)
+      base64
+      benchmark (>= 0.3)
+      bigdecimal
+      concurrent-ruby (~> 1.0, >= 1.3.1)
+      connection_pool (>= 2.2.5)
+      drb
       i18n (>= 1.6, < 2)
+      logger (>= 1.4.2)
       minitest (>= 5.1)
-      tzinfo (~> 2.0)
-      zeitwerk (~> 2.3)
+      securerandom (>= 0.3)
+      tzinfo (~> 2.0, >= 2.0.5)
     afm (0.2.2)
     amazing_print (1.8.1)
     awesome_print (1.9.2)
+    base64 (0.3.0)
+    benchmark (0.4.1)
+    bigdecimal (3.2.2)
     byebug (12.0.0)
-    concurrent-ruby (1.3.4)
-    diff-lcs (1.5.1)
+    concurrent-ruby (1.3.5)
+    connection_pool (2.5.3)
+    diff-lcs (1.6.2)
     docile (1.4.1)
     docsplit (0.7.6)
+    drb (2.2.3)
     filesize (0.2.0)
     hashery (2.1.2)
-    i18n (1.14.5)
+    i18n (1.14.7)
       concurrent-ruby (~> 1.0)
-    minitest (5.25.1)
+    logger (1.7.0)
+    minitest (5.25.5)
     pdf-core (0.4.0)
     pdf-reader (1.4.1)
       Ascii85 (~> 1.0.0)
@@ -51,34 +64,35 @@ GEM
       pdf-core (~> 0.4.0)
       ttfunk (~> 1.4.0)
     rake (12.3.3)
-    rspec (3.13.0)
+    rspec (3.13.1)
       rspec-core (~> 3.13.0)
       rspec-expectations (~> 3.13.0)
       rspec-mocks (~> 3.13.0)
-    rspec-core (3.13.0)
+    rspec-core (3.13.5)
       rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.2)
+    rspec-expectations (3.13.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.1)
+    rspec-mocks (3.13.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-support (3.13.1)
+    rspec-support (3.13.5)
     ruby-rc4 (0.1.5)
     rubyzip (1.3.0)
+    securerandom (0.4.1)
     simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.12.3)
+    simplecov-html (0.13.2)
     simplecov_json_formatter (0.1.4)
+    timeout (0.4.3)
     total_compressor (0.1.11)
       awesome_print (~> 1.1, >= 1.1.0)
       rubyzip (~> 1.2, >= 1.2.2)
     ttfunk (1.4.0)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
-    zeitwerk (2.6.17)
 
 PLATFORMS
   x86_64-linux

data/act_as_page_extractor.gemspec

@@ -24,7 +24,7 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'rspec',     '~> 0'
   spec.add_development_dependency 'simplecov', '~> 0'
 
-  spec.add_runtime_dependency 'activerecord',     '~> 6.0'
+  spec.add_runtime_dependency 'activerecord',     '~> 7.0'
   spec.add_runtime_dependency 'amazing_print',    '~> 1'
   spec.add_runtime_dependency 'docsplit',         '~> 0'                  # API for OpenOffice jodconverter (any to pdf)
   spec.add_runtime_dependency 'pdf_utils',        '~> 0'                  # getting text from pdf

data/lib/act_as_page_extractor/modules/validating.rb

@@ -5,7 +5,7 @@ module ActAsPageExtractor
 
   def validate_size
     mb = 2**20
-    valid = File.size(@copy_document_path) <= 1*mb
+    valid = File.size(@copy_document_path) <= 20*mb
 
     unless valid
       @page_extraction_state = EXTRACTING_STATES[:error_filesize]

data/lib/act_as_page_extractor/version.rb

@@ -1,5 +1,5 @@
 # :nocov:
 module ActAsPageExtractor
-  VERSION = "0.7.1"
+  VERSION = "0.7.3"
 end
 # :nocov:

data/spec/act_as_page_extractor_spec.rb

@@ -1,5 +1,6 @@
 require 'spec_helper'
 require 'act_as_page_extractor'
+require 'tmpdir'
 
 describe ActAsPageExtractor do
   context 'correct extraction' do
@@ -21,9 +22,9 @@ describe ActAsPageExtractor do
         ActAsPageExtractor.start_extraction
         expect(book.page_extraction_state).to eq ActAsPageExtractor::EXTRACTING_STATES[:extracted]
         expect(ExtractedPage.array.count).to eq 4
-        expect(ExtractedPage.array[0][:page]).to match /on a tall column, stood the statue of the Happy Prince/
-        unless document.match /pdf/
-          expect(book.pdf_path).to match /pdf/
+        expect(ExtractedPage.array[0][:page]).to match(/on a tall column, stood the statue of the Happy Prince/)
+        unless document.match(/pdf/)
+          expect(book.pdf_path).to match(/pdf/)
           expect(book.remove_files.count).to eq 1
           expect(book.pages_extraction_errors).to be_empty
         end
@@ -79,5 +80,48 @@ describe ActAsPageExtractor do
         expect(book.pages_extraction_errors).to match(error_msg)
       end
     end
+
+    context 'when file is less than 20MB' do
+      let(:filename) { 'normal_file.txt' }
+      let(:tmp_dir) { File.expand_path("../test/", __dir__) }
+      let(:document) { File.join(tmp_dir, filename) }
+
+      before { build_file(tmp_dir, document, size_mb: 3) }
+
+      after { File.delete(document) if File.exist?(document) }
+
+      it 'converts without errors' do
+        book = Book.new({ doc_path: filename })
+        allow(Book).to receive_message_chain('where') { [book] }
+        ActAsPageExtractor.start_extraction
+        expect(book.page_extraction_state).to eq ActAsPageExtractor::EXTRACTING_STATES[:extracted]
+        expect(book.pages_extraction_errors).to eq ""
+      end
+    end
+
+    context 'when file is larger than 20MB' do
+      let(:filename) { 'large_file.txt' }
+      let(:tmp_dir) { File.expand_path("../test/", __dir__) }
+      let(:document) { File.join(tmp_dir, filename) }
+
+      before { build_file(tmp_dir, document, size_mb: 22) }
+
+      after { File.delete(document) if File.exist?(document) }
+
+      it 'sets error_filesize state and logs error' do
+        book = Book.new({ doc_path: filename })
+        allow(Book).to receive_message_chain('where') { [book] }
+        ActAsPageExtractor.start_extraction
+        expect(book.page_extraction_state).to eq ActAsPageExtractor::EXTRACTING_STATES[:error_filesize]
+        expect(book.pages_extraction_errors).to match('error_filesize')
+      end
+    end
+  end
+end
+
+def build_file(dir, file, size_mb:)
+  FileUtils.mkdir_p(dir)
+  File.open(file, "w") do |f|
+    size_mb.times { f.write("a " * 1024 * 512) }
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: act_as_page_extractor
 version: !ruby/object:Gem::Version
-  version: 0.7.1
+  version: 0.7.3
 platform: ruby
 authors:
 - PhlowerTeam
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-08-23 00:00:00.000000000 Z
+date: 2025-08-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -98,14 +98,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '6.0'
+        version: '7.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '6.0'
+        version: '7.0'
 - !ruby/object:Gem::Dependency
   name: amazing_print
   requirement: !ruby/object:Gem::Requirement