parsekit 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6ad6eb42fb7e96fa944f30245b2c7be51bf4ce1a0f7766749309676b225b17df
-  data.tar.gz: deb56ea394ac3fedc840e890e4d27de14585661233f19eeaae06baf7be1b1e90
+  metadata.gz: ee11d59d78b4a2d0d837233b464f3bc84c934659826fe879953b2c1caa56521a
+  data.tar.gz: b3829363b1821c19d51d86beb494b83a30e0f875e847a7b439a6ed27a993cb26
 SHA512:
-  metadata.gz: dc88b902dd12008a6936f4d62f5d4651544a3f463b725a15d385b919141e93873bd809436e6b9b008baa7b310d149becb2106a29ca103736f6525e09bef871d6
-  data.tar.gz: 9cbc5464a5cbe06a241d2253cde81da82c7eb75742654b7753c91a922acc87125f81a33c3e77d0d107a1435e8946a860e12388e44fa84dc887d9bb4bf9d2d3a2
+  metadata.gz: dddee73ead9421e822a25d97b8fc32ac852c6cc4b8729ae77308b304544738f53e3f6313f124eaf01e4a0bee0e28f2066d411dc00fe324ec47133a0ab9dc4445
+  data.tar.gz: 724666245f2fe62df854b034deb6db3b1db0fcd55f58a257e6929d0946fa1c88ec3e8644b59a0c3930dbc82608ff113d5a2d5a782b6e30f0e40678f1ed5edb43

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 = "0.6", default-features = false, features = [] }
 # OCR - Using tesseract-rs for both system and bundled modes
 tesseract-rs = "0.1"  # Tesseract with optional bundling
 image = "0.25"  # Image processing library (match rusty-tesseract's version)
-calamine = "0.30"  # Excel parsing
+calamine = "0.34"  # 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 = "0.39"  # 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 = "0.1.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: parsekit
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Chris Petersen
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-09-06 00:00:00.000000000 Z
+date: 2026-03-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -100,9 +100,7 @@ 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
@@ -127,7 +125,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.3
+rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
 summary: Ruby document parsing toolkit with PDF and OCR support

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.)