parsekit-bin 0.1.2-arm64-darwin-23 → 0.2.0-arm64-darwin-23

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 36b8db867913082e0cbf900c570fd8de4825cb0ef8fdb2d2405445fa53caf090
-  data.tar.gz: 9d0a9fed6c39ee65dca39a867f306d746ea806d7f194bcf85e738a1506e5d758
+  metadata.gz: 3829c5724ef17010e882645be9d1a3e41e3759505b19822da82298a207586501
+  data.tar.gz: 80c44bfdddb47f3420005c1a2d77da7d6239a920e2bbed1d4c66b6418033e81b
 SHA512:
-  metadata.gz: 88c970ce8aec1b36ff41d2759412bd38ebf1bbd02b24d18f186db08a1eed8654af66231e9baa076d50f5636f50c076630a994e8c7d05b404a594931f6e4c5d21
-  data.tar.gz: b7ca8f826136e35b4d62594121d37ba4f0e9843179a503e737b5fec41b26f99e7f149ed3a158628b338e14628139986bb29e3209c6ffe0ab160853a2d3e4f604
+  metadata.gz: 87a3fb103a507c0306a0224f3e45fcf44e229af1b662890e72b46035f9d527aba0587b8c6bac209cdadfc9f2708db1753f2f2ea8d9fdc5e3f9eedc461136445b
+  data.tar.gz: 6c49bafb9e66c30ae2ce5107df9cd0ea4c9c6658d5c73518171057712d631d8fcc903a6075258820220df5a91c24d85eb53b04df37769ff1438c55f4e4d6bfa7

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 = "0.8", default-features = false, features = [] }
 # OCR - Using tesseract-rs for both system and bundled modes
-tesseract-rs = "0.1"  # Tesseract with optional bundling
+tesseract-rs = "0.4"  # Tesseract with optional bundling
 image = "0.25"  # Image processing library (match rusty-tesseract's version)
-calamine = "0.31"  # Excel parsing
+calamine = "0.36"  # 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 = "0.42"  # 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');
                 }
@@ -390,25 +390,23 @@ impl Parser {
                     // Look for text elements (a:t or t)
                     let name = e.name();
                     let local_name_bytes = name.local_name();
-                    let local_name = std::str::from_utf8(local_name_bytes.as_ref()).unwrap_or("");
+                    let local_name: &str = local_name_bytes.as_ref();
                     if local_name == "t" {
                         in_text_element = true;
                     }
                 }
                 Ok(Event::Text(e)) => {
                     if in_text_element {
-                        if let Ok(text) = e.decode() {
-                            let text_str = text.trim();
-                            if !text_str.is_empty() {
-                                text_parts.push(text_str.to_string());
-                            }
+                        let text_str = e.trim();
+                        if !text_str.is_empty() {
+                            text_parts.push(text_str.to_string());
                         }
                     }
                 }
                 Ok(Event::End(ref e)) => {
                     let name = e.name();
                     let local_name_bytes = name.local_name();
-                    let local_name = std::str::from_utf8(local_name_bytes.as_ref()).unwrap_or("");
+                    let local_name: &str = local_name_bytes.as_ref();
                     if local_name == "t" {
                         in_text_element = false;
                     }
@@ -475,7 +473,7 @@ impl Parser {
         loop {
             match reader.read_event_into(&mut buf) {
                 Ok(Event::Text(e)) => {
-                    txt.push_str(&e.decode().unwrap_or_default());
+                    txt.push_str(e.as_ref());
                     txt.push(' ');
                 }
                 Ok(Event::Eof) => break,

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

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: parsekit-bin
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.0
 platform: arm64-darwin-23
 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
@@ -117,17 +123,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.4'
+      version: '4.0'
   - - "<"
     - !ruby/object:Gem::Version
-      version: 3.5.dev
+      version: 4.1.dev
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.9
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Ruby document parsing toolkit with PDF and OCR support
 test_files: []