act_as_page_extractor 0.7.2 → 0.7.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6ba1988f27b631f295c69c6818f3a668273edfe528e3a07a7048c8e97b80cc91
-  data.tar.gz: 1e1465691d00b94cacd43473a540feeb307898441e895ca119e08425f8d74b69
+  metadata.gz: 150243f19490b089622edb3ca6e265347bcdadab21701de0865a63274b23fc8d
+  data.tar.gz: b3f0d0d90d3b035e4b4d9bee313f6084b46a8e686cc5c873ea5413ea3ab9cf50
 SHA512:
-  metadata.gz: 4593b3996ad378b94418b13152773b4838263a0258edc8a6858bb4d0fcffa501430643f4f871e8d07375967a401a1d2bd35c61c7a667d825e6708d285ef38625
-  data.tar.gz: 252e7852d92c45013b0a8d57cfb43cfc4a4091f219078611dca743f19453bce8ae3201004663b4d4f7ffa1a4e83171a5da9c4a0461bae9a05b91a1b1feeb0137
+  metadata.gz: 2cd0e7c24705e0eb3e646dba87343a06ac23fbaf16d2b1cacaf164046d096b2e65dc8a890bd923b2a59975ecfaacfd58e5e3ddcf61b8cf4610739b465c2af5b7
+  data.tar.gz: ab1e2e4e85117d9a4147ecdcd6ff32be761f3a7bbffee19b1041be8e0c9ea8d665f1358468e27549ab493d36b0fed05d2e2e06fdb7fccd1482b56defb459ac49

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    act_as_page_extractor (0.7.2)
+    act_as_page_extractor (0.7.3)
       activerecord (~> 7.0)
       amazing_print (~> 1)
       docsplit (~> 0)
@@ -40,18 +40,18 @@ GEM
     benchmark (0.4.1)
     bigdecimal (3.2.2)
     byebug (12.0.0)
-    concurrent-ruby (1.3.4)
+    concurrent-ruby (1.3.5)
     connection_pool (2.5.3)
-    diff-lcs (1.5.1)
+    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)
     logger (1.7.0)
-    minitest (5.25.1)
+    minitest (5.25.5)
     pdf-core (0.4.0)
     pdf-reader (1.4.1)
       Ascii85 (~> 1.0.0)
@@ -64,19 +64,19 @@ 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)
@@ -84,7 +84,7 @@ GEM
       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)

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 = "0.7.2"
+  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: 0.7.2
+  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