parsekit 0.1.2 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6ad6eb42fb7e96fa944f30245b2c7be51bf4ce1a0f7766749309676b225b17df
-  data.tar.gz: deb56ea394ac3fedc840e890e4d27de14585661233f19eeaae06baf7be1b1e90
+  metadata.gz: b32f09ec6af6545f7db84b9c6c6f10a27998d95b2305ec5f5a5bef4a80a2a717
+  data.tar.gz: 7b36ef18a14bd708ae885c5b101f822cf6cb088c1ba729b0398bd4d5522ab0fb
 SHA512:
-  metadata.gz: dc88b902dd12008a6936f4d62f5d4651544a3f463b725a15d385b919141e93873bd809436e6b9b008baa7b310d149becb2106a29ca103736f6525e09bef871d6
-  data.tar.gz: 9cbc5464a5cbe06a241d2253cde81da82c7eb75742654b7753c91a922acc87125f81a33c3e77d0d107a1435e8946a860e12388e44fa84dc887d9bb4bf9d2d3a2
+  metadata.gz: 2f5b479a90c550ea25c4a0a6f19afbb10aee5a51b14f7a27868857249605e6b72e045288eb2019805c8281d499d31b8d0597c96bea3c1cee87753430541116a1
+  data.tar.gz: a1ab174853194a4806e1c88606912005bc074b072893681c17e3e271339baadd401e7849ebc026305809507c7ca0b6d30584941c4a94f5619d339000df3e06dd

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 = "0.30"  # 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"
+  VERSION = "0.2.0"
 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

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: parsekit
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.0
 platform: ruby
 authors:
 - Chris Petersen
-autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-09-06 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -100,9 +99,7 @@ files:
 - ext/parsekit/src/lib.rs
 - ext/parsekit/src/parser.rs
 - lib/parsekit.rb
-- lib/parsekit/NATIVE_API.md
 - lib/parsekit/error.rb
-- lib/parsekit/parsekit.bundle
 - lib/parsekit/parser.rb
 - lib/parsekit/version.rb
 homepage: https://github.com/scientist-labs/parsekit
@@ -112,7 +109,6 @@ metadata:
   homepage_uri: https://github.com/scientist-labs/parsekit
   source_code_uri: https://github.com/scientist-labs/parsekit
   changelog_uri: https://github.com/scientist-labs/parsekit/blob/main/CHANGELOG.md
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -127,8 +123,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.3
-signing_key:
+rubygems_version: 3.6.9
 specification_version: 4
 summary: Ruby document parsing toolkit with PDF and OCR support
 test_files: []

data/lib/parsekit/NATIVE_API.md

@@ -1,125 +0,0 @@
-# ParseKit Native API Documentation
-
-This document describes the methods implemented in the Rust native extension for ParseKit::Parser.
-
-## Instance Methods
-
-### `initialize(options = {})`
-Initialize a new Parser instance with optional configuration.
-
-**Parameters:**
-- `options` [Hash] Configuration options
-  - `:encoding` [String] Input encoding (default: UTF-8)
-  - `:strict_mode` [Boolean] Enable strict parsing mode (default: false)
-  - `:max_depth` [Integer] Maximum nesting depth (default: 100)
-  - `:max_size` [Integer] Maximum file size in bytes (default: 100MB)
-
-### `parse(input)`
-Parse an input string (for text content).
-
-**Parameters:**
-- `input` [String] The input to parse
-
-**Returns:**
-- [String] The parsed result
-
-**Raises:**
-- `ArgumentError` If input is empty
-
-### `parse_file(path)`
-Parse a file (supports PDF, Office documents, text files, images with OCR).
-
-**Parameters:**
-- `path` [String] Path to the file to parse
-
-**Returns:**
-- [String] The extracted text content
-
-**Raises:**
-- `IOError` If file cannot be read
-- `RuntimeError` If parsing fails
-
-### `parse_bytes(data)`
-Parse binary data.
-
-**Parameters:**
-- `data` [Array<Integer>] Binary data as byte array
-
-**Returns:**
-- [String] The extracted text content
-
-**Raises:**
-- `ArgumentError` If data is empty
-- `RuntimeError` If parsing fails
-
-### `config`
-Get the current parser configuration.
-
-**Returns:**
-- [Hash] The parser configuration including encoding, strict_mode, max_depth, and max_size
-
-### `supports_file?(path)`
-Check if a file format is supported.
-
-**Parameters:**
-- `path` [String] File path to check
-
-**Returns:**
-- [Boolean] True if the file format is supported
-
-### `strict_mode?`
-Check if strict mode is enabled.
-
-**Returns:**
-- [Boolean] True if strict mode is enabled
-
-## Format-Specific Parsers
-
-These methods are also available but typically called internally via `parse_file` or `parse_bytes`:
-
-### `parse_pdf(data)`
-Parse PDF files using MuPDF (statically linked).
-
-### `parse_docx(data)`
-Parse Microsoft Word documents.
-
-### `parse_pptx(data)`
-Parse Microsoft PowerPoint presentations.
-
-### `parse_xlsx(data)`
-Parse Microsoft Excel spreadsheets.
-
-### `parse_json(data)`
-Parse and pretty-print JSON data.
-
-### `parse_xml(data)`
-Parse XML/HTML files and extract text content.
-
-### `parse_text(data)`
-Parse plain text files.
-
-### `ocr_image(data)`
-Perform OCR on images (PNG, JPEG, TIFF, BMP) using Tesseract.
-
-## Class Methods
-
-### `Parser.supported_formats`
-Get list of supported file formats.
-
-**Returns:**
-- [Array<String>] List of supported file extensions
-
-**Example:**
-```ruby
-ParseKit::Parser.supported_formats
-# => ["txt", "json", "xml", "html", "docx", "xlsx", "xls", "csv", "pdf", "png", "jpg", "jpeg", "tiff", "bmp", ...]
-```
-
-## Implementation Notes
-
-All these methods are implemented in Rust via the native extension. The Ruby layer (`lib/parsekit/parser.rb`) provides additional convenience methods and helpers that wrap these native methods.
-
-The native extension uses:
-- **MuPDF** for PDF parsing (statically linked)
-- **Tesseract** for OCR functionality (bundled)
-- **Various Rust crates** for Office document parsing (docx-rs, calamine, etc.)