parsekit-bin 0.1.2.1 → 0.2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ee9084fa44aaac5c6ff89eae2c544b4210d05332fab6da0e3badbb0d6df360d8
-  data.tar.gz: 5f2317c0d8e691ad21540698535143faaac4560a2e187d60c6ab9f0e8f0a0861
+  metadata.gz: 70bc69e30ef452bec4a199f7b4e5bffbf69da408d01b2d833ea9fa48397d5bb8
+  data.tar.gz: 10b999903a9230199ee768b014f375f248814d3f973e9932c46cc88fb0fd8bd5
 SHA512:
-  metadata.gz: 951e90f083b0186008d823a8637e53e4ec7d91d52032886ee1952dbb4a53c621708e06a034a6c30834f888c9df089683b77129cd9a6db7848f58ad30041ae59a
-  data.tar.gz: 1ce0402e953b97d37266c00a65e022c44655bfd12048bc148a2e33aff377f848eabb3f6351e240e8169e22d3d3bd1222fb71ec639887f97453c6d22b74872416
+  metadata.gz: ab832cf15983e91300be2dc8472d70885a00f6a8821f0ac49539c115b60f7475b61fdbbe85a751a0ad1700d9cf2e008807de4433840703f984e99ceb9669c59f
+  data.tar.gz: 88b24994e1968d196d50dfcc812c89d0e23b35454bc3e04fb72b27598f84d2ea7f3a94de160e81de42b5b75fed70a0594ed0664390790a5ff3c5c7d9ff22a1e8

data/README.md

@@ -1,6 +1,6 @@
 <img src="/docs/assets/parsekit-wide.png" alt="parsekit" height="80px">
 
-[![Gem Version](https://badge.fury.io/rb/parsekit-bin.svg)](https://badge.fury.io/rb/parsekit-bin)
+[![Gem Version](https://badge.fury.io/rb/parsekit.svg)](https://badge.fury.io/rb/parsekit)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 Native Ruby bindings for the [parser-core](https://crates.io/crates/parser-core) Rust crate, providing high-performance document parsing and text extraction capabilities through Magnus. This gem wraps parser-core to extract text from PDFs, Office documents (DOCX, XLSX), images (with OCR), and more. Part of the ruby-nlp ecosystem.
@@ -19,7 +19,7 @@ Native Ruby bindings for the [parser-core](https://crates.io/crates/parser-core)
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'parsekit-bin'
+gem 'parsekit'
 ```
 
 And then execute:
@@ -29,7 +29,7 @@ And then execute:
 Or install it yourself as:
 
 ```bash
-gem install parsekit-bin
+gem install parsekit
 ```
 
 ### Requirements
@@ -158,7 +158,7 @@ By default, ParseKit bundles Tesseract for zero-dependency OCR support. Advanced
 
 **Using system Tesseract during installation:**
 ```bash
-gem install parsekit-bin -- --no-default-features
+gem install parsekit -- --no-default-features
 ```
 
 **For development with system Tesseract:**

data/ext/parsekit/Cargo.toml

@@ -14,14 +14,14 @@ name = "parsekit"
 magnus = { version = "0.8", features = ["rb-sys"] }
 # Document parsing - testing embedded C libraries
 # MuPDF builds from source and statically links
-mupdf = { version = "0.5", default-features = false, features = [] }
+mupdf = { version = "0.7", default-features = false, features = [] }
 # OCR - Using tesseract-rs for both system and bundled modes
-tesseract-rs = "0.1"  # Tesseract with optional bundling
+tesseract-rs = "0.2"  # Tesseract with optional bundling
 image = "0.25"  # Image processing library (match rusty-tesseract's version)
-calamine = "0.31"  # Excel parsing
+calamine = "0.35"  # Excel parsing
 docx-rs = "0.4"  # Word document parsing
-quick-xml = "0.38"  # XML parsing
-zip = "5.0"  # ZIP archive handling for PPTX
+quick-xml = "0.40"  # XML parsing
+zip = "8.2"  # ZIP archive handling for PPTX
 serde_json = "1.0"  # JSON parsing
 regex = "1.10"  # Text parsing
 encoding_rs = "0.8"  # Encoding detection

data/ext/parsekit/src/parser.rs

@@ -242,7 +242,7 @@ impl Parser {
             // Continue on page errors rather than failing entirely
             if let Ok(page) = doc.load_page(page_num) {
                 // Extract text from the page
-                if let Ok(text) = page.to_text() {
+                if let Ok(text) = page.to_text_page(mupdf::TextPageFlags::empty()).and_then(|tp| tp.to_text()) {
                     all_text.push_str(&text);
                     all_text.push('\n');
                 }

data/lib/parsekit/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ParseKit
-  VERSION = "0.1.2.1"
+  VERSION = "0.2.0.1"
 end

data/lib/parsekit.rb

@@ -2,9 +2,15 @@
 
 require_relative "parsekit/version"
 
-# Load the native extension
+# Load the compiled Rust extension. Precompiled (platform) gems install it into a
+# Ruby-ABI-versioned subdir (lib/parsekit/<major.minor>/parsekit.{so,bundle}) so a
+# single fat gem can carry a binary per Ruby version; source/dev builds place it flat
+# at lib/parsekit/parsekit.{so,bundle}. Try the versioned path first, fall back to the
+# flat one. Resolution goes through $LOAD_PATH (`require`, never `require_relative`)
+# because RubyGems installs native extensions outside the gem's lib/ dir.
 begin
-  require_relative "parsekit/parsekit"
+  RUBY_VERSION =~ /(\d+\.\d+)/
+  require "parsekit/#{Regexp.last_match(1)}/parsekit"
 rescue LoadError
   require "parsekit/parsekit"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: parsekit-bin
 version: !ruby/object:Gem::Version
-  version: 0.1.2.1
+  version: 0.2.0.1
 platform: ruby
 authors:
 - Chris Petersen
@@ -16,6 +16,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.129
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -23,6 +26,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.129
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -124,7 +130,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.3
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Ruby document parsing toolkit with PDF and OCR support
 test_files: []