liteparse-rb 0.1.13 → 0.1.14

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 53e2fa220141957960e80e01cadf273e8aa3e1f757f8acc8712bdc158264efcc
-  data.tar.gz: f24904a27aa45533c63a7e1d216a68229abcfa212d6df5b181af7dab97eb847e
+  metadata.gz: 840e257ec0149b7d40c9385ba934409200d047be40cd80be06dd4bef49b93bd6
+  data.tar.gz: 2e51b19e50155b48a126a746eeb233b633ca97cbaa80eec087e107be3914d27c
 SHA512:
-  metadata.gz: 74b57d39d1644196a2b3e5734908b148593a3c08b583dfaa362f00ba00570b70650b7f7710b9bb82b8f97b643941798a75b4010ce48739e8a08c046ff17cb9ff
-  data.tar.gz: 1cc2d8881244d759239d94bce1aa0260254d0b65ef1559a97bfdbd14cb84bad0b764f02226c14dc2e78c488bd6dd63388dd7ec0124c75a028fc2af441060d02d
+  metadata.gz: ef80a7427299914b237c053fbb365564ae56d76e847d6dbd5d23b3ec61af37562f073f99f54582e89d743647505b19c996b146ce4ef08e57ded9303210be9e6b
+  data.tar.gz: 483f25fb7098464be3594b5e762790a912147dd468f23cb0477d1c04e365c816784f6dde6de9aab3ae4bd3cc8cad5bab3e0644950126c387fe11bec6082e8fb8

data/Cargo.lock

@@ -16,7 +16,7 @@ checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
 dependencies = [
  "cfg-if",
  "cipher",
- "cpufeatures",
+ "cpufeatures 0.2.17",
 ]
 
 [[package]]
@@ -80,9 +80,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.102"
+version = "1.0.103"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
+checksum = "2a4385e2e34eb35d6b3efe798b9eb88096925d87726c0798709bf56d9ed84af3"
 
 [[package]]
 name = "arbitrary"
@@ -93,6 +93,18 @@ dependencies = [
  "derive_arbitrary",
 ]
 
+[[package]]
+name = "arrayref"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
+
+[[package]]
+name = "arrayvec"
+version = "0.7.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f02882884d3e1bc524fb12c79f107f6ad0e1cfd498c536ffb494301740995dfe"
+
 [[package]]
 name = "atomic-waker"
 version = "1.1.2"
@@ -157,6 +169,20 @@ version = "2.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4388bee8683e3d04af747c73422af53102d2bd24d9eadb6cbc100baef4b43f8"
 
+[[package]]
+name = "blake3"
+version = "1.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0aa83c34e62843d924f905e0f5c866eb1dd6545fc4d719e803d9ba6030371fce"
+dependencies = [
+ "arrayref",
+ "arrayvec",
+ "cc",
+ "cfg-if",
+ "constant_time_eq 0.4.2",
+ "cpufeatures 0.3.0",
+]
+
 [[package]]
 name = "block-buffer"
 version = "0.10.4"
@@ -351,6 +377,12 @@ version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7c74b8349d32d297c9134b8c88677813a227df8f779daa29bfc29c183fe3dca6"
 
+[[package]]
+name = "constant_time_eq"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d52eff69cd5e647efe296129160853a42795992097e8af39800e1060caeea9b"
+
 [[package]]
 name = "core-foundation"
 version = "0.9.4"
@@ -386,6 +418,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "cpufeatures"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b2a41393f66f16b0823bb79094d54ac5fbd34ab292ddafb9a0456ac9f87d201"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "crc"
 version = "3.4.0"
@@ -1121,9 +1162,9 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
 [[package]]
 name = "liteparse"
-version = "0.1.13"
+version = "0.1.14"
 dependencies = [
- "liteparse 2.2.0",
+ "liteparse 2.2.1",
  "liteparse-ruby",
  "magnus",
  "rb-sys",
@@ -1131,10 +1172,11 @@ dependencies = [
 
 [[package]]
 name = "liteparse"
-version = "2.2.0"
+version = "2.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "95c884d0aacf6f51bf93b5f870f18ed5f8188e8474b2d110a8acaf57821382ef"
+checksum = "292eab7b9f87ed43813072777fe318b2146c05ca8920a7afe047ca6f1900930b"
 dependencies = [
+ "blake3",
  "clap",
  "image",
  "infer",
@@ -1142,6 +1184,7 @@ dependencies = [
  "liteparse-pdfium-sys",
  "ordered-float",
  "reqwest 0.13.4",
+ "rmp",
  "serde",
  "serde_json",
  "tempfile",
@@ -1154,18 +1197,18 @@ dependencies = [
 
 [[package]]
 name = "liteparse-pdfium"
-version = "1.2.0"
+version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "da32ff4cfed8ad099a7f4539b2765d5d74309f54deb0ca001b6331b530e2a9e8"
+checksum = "dbb04fb271230f7c13d97ce7f0261ecbcfd218272228c2d97b339482e60f9694"
 dependencies = [
  "liteparse-pdfium-sys",
 ]
 
 [[package]]
 name = "liteparse-pdfium-sys"
-version = "1.2.0"
+version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "be18655d558598f1caec00ec9534e2798db9176a9549924a7508689e5ce15f24"
+checksum = "a920d4b7bd4c75f0d2f47a93ef2b2b71348ab7bc14d6773f9c348549fa24d6d8"
 dependencies = [
  "flate2",
  "libloading",
@@ -1175,11 +1218,11 @@ dependencies = [
 
 [[package]]
 name = "liteparse-ruby"
-version = "0.1.13"
+version = "0.1.14"
 dependencies = [
  "anyhow",
  "image",
- "liteparse 2.2.0",
+ "liteparse 2.2.1",
  "liteparse-pdfium",
  "liteparse-pdfium-sys",
  "magnus",
@@ -1750,6 +1793,15 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "rmp"
+version = "0.8.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4ba8be72d372b2c9b35542551678538b562e7cf86c3315773cae48dfbfe7790c"
+dependencies = [
+ "num-traits",
+]
+
 [[package]]
 name = "rustc-hash"
 version = "2.1.2"
@@ -1982,7 +2034,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3bf829a2d51ab4a5ddf1352d8470c140cadc8301b2ae1789db023f01cedd6ba"
 dependencies = [
  "cfg-if",
- "cpufeatures",
+ "cpufeatures 0.2.17",
  "digest",
 ]
 
@@ -2970,7 +3022,7 @@ dependencies = [
  "aes",
  "arbitrary",
  "bzip2",
- "constant_time_eq",
+ "constant_time_eq 0.3.1",
  "crc32fast",
  "crossbeam-utils",
  "deflate64",

data/crates/liteparse-ruby/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "liteparse-ruby"
-version = "0.1.13"
+version = "0.1.14"
 edition.workspace = true
 license.workspace = true
 repository.workspace = true

data/crates/liteparse-ruby/src/lib.rs

@@ -10,12 +10,12 @@ use liteparse::config::{ImageMode, LiteParseConfig, OutputFormat};
 use liteparse::types::PdfInput;
 
 fn kwarg<T: magnus::TryConvert>(kwargs: &RHash, key: &str) -> Option<T> {
-    let sym = magnus::Symbol::new(key);
+    let sym = Ruby::get().unwrap().to_symbol(key);
     kwargs.get::<magnus::Symbol>(sym).and_then(|v| <T as magnus::TryConvert>::try_convert(v).ok())
 }
 
 fn kwarg_bool(kwargs: &RHash, key: &str) -> Option<bool> {
-    let sym = magnus::Symbol::new(key);
+    let sym = Ruby::get().unwrap().to_symbol(key);
     kwargs.get::<magnus::Symbol>(sym).and_then(|v| {
         use magnus::value::ReprValue;
         if v.is_nil() { None } else { Some(v.to_bool()) }

data/lib/liteparse/cli.rb

@@ -3,9 +3,18 @@ require_relative "../liteparse"
 module LiteParse
   # CLI support is handled by the native `lit` binary.
   # Run `lit --help` from the command line for usage.
+  #
+  # This module provides a programmatic entry point that delegates
+  # to the native CLI runner.
+  #
+  # @example
+  #   LiteParse::CLI.run(["parse", "document.pdf"])
   module CLI
     module_function
 
+    # Run the CLI with the given arguments.
+    # @param args [Array<String>] Command-line arguments (defaults to ARGV)
+    # @return [void]
     def run(args = ARGV)
       LiteParse.run_cli(args)
     rescue => e

data/lib/liteparse/parser.rb

@@ -5,9 +5,31 @@ module LiteParse
   # This file exists to mirror the Python wrapper structure and provide
   # a convenient require path.
   #
-  # Usage:
+  # @example Basic usage
   #   require "liteparse"
   #   parser = LiteParse::LiteParse.new(ocr_enabled: true)
   #   result = parser.parse("document.pdf")
   #   puts result.text
+
+  # @!method parse(input)
+  #   Parse a document from a file path.
+  #   @param input [String] Path to the document file (.pdf, .docx, .pptx, .xlsx, .html, image, etc.)
+  #   @return [LiteParse::ParseResult] Parsed document with pages, text, and images
+  #   @raise [RuntimeError] If parsing fails
+  #   @example
+  #     result = parser.parse("report.pdf")
+  #     result.pages.each { |page| puts page.text }
+
+  # @!method parse_bytes(data)
+  #   Parse a document from raw bytes.
+  #   @param data [String] Raw document bytes (binary string)
+  #   @return [LiteParse::ParseResult] Parsed document with pages, text, and images
+  #   @raise [RuntimeError] If parsing fails
+  #   @example
+  #     data = File.binread("report.pdf")
+  #     result = parser.parse_bytes(data)
+
+  # @!method config
+  #   Get the current parser configuration.
+  #   @return [LiteParse::Config] The active configuration
 end

data/lib/liteparse/types.rb

@@ -4,6 +4,104 @@ require_relative "liteparse/liteparse"
 # in the Rust extension. This file re-exports them for convenience.
 
 module LiteParse
+  # A single item of text with spatial position information.
+  # @!method text
+  #   @return [String] The text content of this item
+  # @!method x
+  #   @return [Float] Left edge X coordinate of the text bounding box
+  # @!method y
+  #   @return [Float] Top edge Y coordinate of the text bounding box
+  # @!method width
+  #   @return [Float] Width of the text bounding box
+  # @!method height
+  #   @return [Float] Height of the text bounding box
+  # @!method font_name
+  #   @return [String, nil] Name of the font used, if available
+  # @!method font_size
+  #   @return [Float, nil] Font size in points, if available
+  # @!method confidence
+  #   @return [Float, nil] OCR/text extraction confidence (0.0–1.0), if available
+  class TextItem; end
+
+  # A single parsed page from a document.
+  # @!method page_num
+  #   @return [Integer] 1-indexed page number
+  # @!method width
+  #   @return [Float] Page width in points
+  # @!method height
+  #   @return [Float] Page height in points
+  # @!method text
+  #   @return [String] Full concatenated text of this page
+  # @!method text_items
+  #   @return [Array<LiteParse::TextItem>] Individual text items with spatial information
+  class ParsedPage; end
+
+  # The complete result of parsing a document.
+  # @!method pages
+  #   @return [Array<LiteParse::ParsedPage>] All parsed pages
+  # @!method text
+  #   @return [String] Full concatenated text across all pages
+  # @!method images
+  #   @return [Array<LiteParse::ExtractedImage>] Images extracted from the document
+  # @!method num_pages
+  #   @return [Integer] Total number of pages parsed
+  # @!method get_page(page_num)
+  #   Retrieve a specific page by its 1-indexed page number.
+  #   @param page_num [Integer] 1-indexed page number
+  #   @return [LiteParse::ParsedPage, nil] The page, or nil if not found
+  class ParseResult; end
+
+  # An image extracted from a parsed document.
+  # @!method id
+  #   @return [String] Image identifier
+  # @!method page
+  #   @return [Integer] Page number where the image was found
+  # @!method format
+  #   @return [String] Image format (e.g. "png", "jpeg")
+  # @!method bytes
+  #   @return [String] Raw image bytes (binary string)
+  class ExtractedImage; end
+
+  # A screenshot of a document page rendered as an image.
+  # @!method page_num
+  #   @return [Integer] 1-indexed page number of the screenshot
+  # @!method width
+  #   @return [Integer] Width of the screenshot in pixels
+  # @!method height
+  #   @return [Integer] Height of the screenshot in pixels
+  # @!method image_bytes
+  #   @return [String] PNG image bytes (binary string)
+  class ScreenshotResult; end
+
+  # The current configuration of a LiteParse parser instance.
+  # @!method ocr_language
+  #   @return [String] Language used for OCR (e.g. "eng")
+  # @!method ocr_enabled
+  #   @return [Boolean] Whether OCR is enabled
+  # @!method ocr_server_url
+  #   @return [String, nil] External OCR server URL, if configured
+  # @!method ocr_server_headers
+  #   @return [Hash<String, String>, nil] Headers for OCR server requests
+  # @!method tessdata_path
+  #   @return [String, nil] Path to Tesseract tessdata directory
+  # @!method max_pages
+  #   @return [Integer] Maximum pages to parse
+  # @!method target_pages
+  #   @return [String, nil] Page range expression, if configured
+  # @!method dpi
+  #   @return [Float] Rendering DPI
+  # @!method output_format
+  #   @return [String] Output format: "json", "text", or "markdown"
+  # @!method preserve_very_small_text
+  #   @return [Boolean] Whether very small text is preserved
+  # @!method password
+  #   @return [String, nil] Document password, if set
+  # @!method quiet
+  #   @return [Boolean] Whether non-error output is suppressed
+  # @!method num_workers
+  #   @return [Integer] Number of worker threads
+  class Config; end
+
   # No additional Ruby wrapping needed — the native classes are registered
   # directly on the LiteParse module by the Rust init function.
 end

data/lib/liteparse/version.rb

@@ -1,3 +1,4 @@
 module LiteParse
-  VERSION = "0.1.13"
+  # Current version of liteparse-rb.
+  VERSION = "0.1.14"
 end

data/lib/liteparse.rb

@@ -2,9 +2,46 @@ require_relative "liteparse/version"
 require_relative "liteparse/liteparse"
 
 module LiteParse
+  # Generic error raised by LiteParse operations.
   class Error < StandardError; end
 end
 
+# YARD declarations for methods defined in the Rust extension.
+# These are invisible to YARD, so we declare them with @!method.
+class LiteParse::LiteParse
+  # @!method self.new(**kwargs)
+  #   Create a new LiteParse parser instance.
+  #   @param kwargs [Hash] Keyword arguments for parser configuration
+  #   @option kwargs [String] :ocr_language ("eng") Language for OCR
+  #   @option kwargs [Boolean] :ocr_enabled (true) Enable OCR
+  #   @option kwargs [String, nil] :ocr_server_url URL of an external OCR server
+  #   @option kwargs [Hash<String, String>, nil] :ocr_server_headers Headers for OCR server requests
+  #   @option kwargs [String, nil] :tessdata_path Path to Tesseract tessdata directory
+  #   @option kwargs [Integer] :max_pages (1000) Maximum pages to parse
+  #   @option kwargs [String, nil] :target_pages Page range expression (e.g. "1-5,7")
+  #   @option kwargs [Float] :dpi (150.0) Rendering DPI
+  #   @option kwargs [String] :output_format ("json") Output format: "json", "text", or "markdown"
+  #   @option kwargs [Boolean] :preserve_very_small_text (false) Preserve tiny text
+  #   @option kwargs [String, nil] :password Password for encrypted documents
+  #   @option kwargs [Boolean] :quiet (false) Suppress non-error output
+  #   @option kwargs [Integer] :num_workers Number of worker threads (auto-detected)
+  #   @option kwargs [String] :image_mode ("placeholder") Image mode: "placeholder", "embed", or "off"
+  #   @option kwargs [Boolean] :extract_links (false) Extract hyperlinks
+  #   @return [LiteParse::LiteParse]
+  #   @example
+  #     parser = LiteParse::LiteParse.new(ocr_enabled: true, dpi: 200)
+
+  # @!method screenshot(input, page_numbers: nil)
+  #   Take screenshots of document pages.
+  #   @param input [String] Path to the document file
+  #   @param page_numbers [Array<Integer>, nil] Specific page numbers (1-indexed) to screenshot. nil = all pages.
+  #   @return [Array<LiteParse::ScreenshotResult>] Screenshot results with image bytes
+  #   @example
+  #     parser = LiteParse::LiteParse.new
+  #     screenshots = parser.screenshot("document.pdf", page_numbers: [1, 3])
+  #     screenshots.each { |s| File.write("page_#{s.page_num}.png", s.image_bytes) }
+end
+
 # Wrap native new to accept 0 args (the Rust constructor expects 1 positional arg).
 LiteParse::LiteParse.singleton_class.alias_method :native_new, :new
 LiteParse::LiteParse.define_singleton_method(:new) do |**kwargs|

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: liteparse-rb
 version: !ruby/object:Gem::Version
-  version: 0.1.13
+  version: 0.1.14
 platform: ruby
 authors:
 - Evan Mattiza
@@ -23,6 +23,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
+- !ruby/object:Gem::Dependency
+  name: yard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
 description: Ruby bindings for LiteParse — an open-source document parser that extracts
   text with spatial layout information, bounding boxes, OCR support, and more.
 executables: []
@@ -49,6 +63,7 @@ licenses:
 metadata:
   homepage_uri: https://github.com/emattiza/liteparse-rb
   source_code_uri: https://github.com/emattiza/liteparse-rb
+  documentation_uri: https://rubydoc.info/gems/liteparse-rb
 rdoc_options: []
 require_paths:
 - lib