parsekit-bin 0.2.0-aarch64-linux → 0.2.0.1-aarch64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 27014d56024d448eb983e947ed8a129d3ebbccadefc2d103eaaf706c8d62fd4d
-  data.tar.gz: 9141ece21e3784f8368245750f5aa60450c45b44385403ff2b667d9c6c0f54b6
+  metadata.gz: 2bf6239f703df75df420aed1aec9acdb7d22b9fc98bf575f2375836444fb07ba
+  data.tar.gz: 2304e3bfdf91e300836883be4933cbdf0980ccc69c0488c13926c4035a171a43
 SHA512:
-  metadata.gz: f21500372820fa38880e3e77184a3b3f0ef02e1b8e58a78c3a9fd42dedd39701c2a7270b8781a5dc8e8be7a321f500ed588f7f435f9583ffbfdb31355f692484
-  data.tar.gz: e068bd267501fc1bd2f6f545bca6a7cae51ad517867afa06dae0b6b2417ff9bd90621315fad72f6705344dcb5cc58fb780437b95bbab2763e83827c4d0acf2d4
+  metadata.gz: 640bbee023275973183d78c52b7ae3dda4334d1b568045beeaa6dee2f6f05bcdce3dac0f005fb810ece9f79ddc096abbfaf25b12c54dc58e1eef32602cb26b07
+  data.tar.gz: 00012caf0497df01d251bbf63645645df4441dc1e5360befca3ae2c94290d6da33912a46cbaa3e7a82eb40e723c36342d2f1d264a301ba56211345f597643ce5

data/README.md

@@ -1,6 +1,6 @@
 <img src="/docs/assets/parsekit-wide.png" alt="parsekit" height="80px">
 
-[![Gem Version](https://badge.fury.io/rb/parsekit-bin.svg)](https://badge.fury.io/rb/parsekit-bin)
+[![Gem Version](https://badge.fury.io/rb/parsekit.svg)](https://badge.fury.io/rb/parsekit)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 Native Ruby bindings for the [parser-core](https://crates.io/crates/parser-core) Rust crate, providing high-performance document parsing and text extraction capabilities through Magnus. This gem wraps parser-core to extract text from PDFs, Office documents (DOCX, XLSX), images (with OCR), and more. Part of the ruby-nlp ecosystem.
@@ -19,7 +19,7 @@ Native Ruby bindings for the [parser-core](https://crates.io/crates/parser-core)
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'parsekit-bin'
+gem 'parsekit'
 ```
 
 And then execute:
@@ -29,7 +29,7 @@ And then execute:
 Or install it yourself as:
 
 ```bash
-gem install parsekit-bin
+gem install parsekit
 ```
 
 ### Requirements
@@ -158,7 +158,7 @@ By default, ParseKit bundles Tesseract for zero-dependency OCR support. Advanced
 
 **Using system Tesseract during installation:**
 ```bash
-gem install parsekit-bin -- --no-default-features
+gem install parsekit -- --no-default-features
 ```
 
 **For development with system Tesseract:**

data/ext/parsekit/Cargo.toml

@@ -14,13 +14,13 @@ name = "parsekit"
 magnus = { version = "0.8", features = ["rb-sys"] }
 # Document parsing - testing embedded C libraries
 # MuPDF builds from source and statically links
-mupdf = { version = "0.8", default-features = false, features = [] }
+mupdf = { version = "0.7", default-features = false, features = [] }
 # OCR - Using tesseract-rs for both system and bundled modes
-tesseract-rs = "0.4"  # Tesseract with optional bundling
+tesseract-rs = "0.2"  # Tesseract with optional bundling
 image = "0.25"  # Image processing library (match rusty-tesseract's version)
-calamine = "0.36"  # Excel parsing
+calamine = "0.35"  # Excel parsing
 docx-rs = "0.4"  # Word document parsing
-quick-xml = "0.42"  # XML parsing
+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

data/ext/parsekit/src/parser.rs

@@ -390,23 +390,25 @@ impl Parser {
                     // Look for text elements (a:t or t)
                     let name = e.name();
                     let local_name_bytes = name.local_name();
-                    let local_name: &str = local_name_bytes.as_ref();
+                    let local_name = std::str::from_utf8(local_name_bytes.as_ref()).unwrap_or("");
                     if local_name == "t" {
                         in_text_element = true;
                     }
                 }
                 Ok(Event::Text(e)) => {
                     if in_text_element {
-                        let text_str = e.trim();
-                        if !text_str.is_empty() {
-                            text_parts.push(text_str.to_string());
+                        if let Ok(text) = e.decode() {
+                            let text_str = text.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: &str = local_name_bytes.as_ref();
+                    let local_name = std::str::from_utf8(local_name_bytes.as_ref()).unwrap_or("");
                     if local_name == "t" {
                         in_text_element = false;
                     }
@@ -473,7 +475,7 @@ impl Parser {
         loop {
             match reader.read_event_into(&mut buf) {
                 Ok(Event::Text(e)) => {
-                    txt.push_str(e.as_ref());
+                    txt.push_str(&e.decode().unwrap_or_default());
                     txt.push(' ');
                 }
                 Ok(Event::Eof) => break,

data/lib/parsekit/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ParseKit
-  VERSION = "0.2.0"
+  VERSION = "0.2.0.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: parsekit-bin
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.0.1
 platform: aarch64-linux
 authors:
 - Chris Petersen