parsekit-bin 0.1.2-x86_64-linux → 0.2.0-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 69a24c82104c0c2666fe0b8efc32efd31ecf1a9c14ec9f428176c36e36b144e2
-  data.tar.gz: 0c72a460ddb050b3f8ef3ddef81323bb5ddcd64bfe5b83ea7f2b5489319e6394
+  metadata.gz: 074bdac0c52226852cbc5771830851d85f3f812abe703e94b3f8babb97587840
+  data.tar.gz: 38b638d1cdbfae3b09dbaf5a105171dcb575d444133bb94e5829affc4d83b66b
 SHA512:
-  metadata.gz: 122103c50beb01a232aba35d1a4a2bbc90c48d30bf01334a573bbf5d5f97122404176a9d809e8e79e38b60590916765d2b88f6bdbade816365f4589d98e10a58
-  data.tar.gz: 6e099842b8612c467d774cf5f60126db1159c6e6f370027aa7529a68517ded425bbfebc8b96929cbeffad9c644655295fcbcb164d31e6ade696a057b5a733823
+  metadata.gz: 54b590b41ae482f1408c4203b3130f93b29b0e6167e3279ccc8db6f9d0679e519e84bb7d79fadeb4bde5f0a74892bf6cf45834b64a59fbf60d1b2bc33f1c93de
+  data.tar.gz: fa7b38b35c781b52f4c82aef8c39833f89304fd61b5c7898e09d28fe11d236ad576b35b91a11846b6941e6583d5f53420edf85f4451403ad1e5d8330e6f2299c

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: x86_64-linux
 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: []