parsekit-bin 0.2.0 → 0.2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7973f2a8c97f073189e80eca0d519c35d083a7b7f49fec5711c1244daf26a792
-  data.tar.gz: 1d51beb427c9f2b2e9556c2c6ce6863573c58c517dad4395fd41102fb4c98a61
+  metadata.gz: 70bc69e30ef452bec4a199f7b4e5bffbf69da408d01b2d833ea9fa48397d5bb8
+  data.tar.gz: 10b999903a9230199ee768b014f375f248814d3f973e9932c46cc88fb0fd8bd5
 SHA512:
-  metadata.gz: 50dfe8c91a81e5a48a064af1d6ff0f888d6862b82822e602d6ab2a1394fffd20b0509a82253dee9a8df98d1d35313c535254b0a7cce701ff17c1d9e5cb99e608
-  data.tar.gz: 92f85aa149a75c7b469511ceffc5c341540a5bf311015ae2a5c846b52f8b56d6b4056c6bb2a6675c18c4421dd2e80e2c77061d718bdabc1ee540933dcea11c76
+  metadata.gz: ab832cf15983e91300be2dc8472d70885a00f6a8821f0ac49539c115b60f7475b61fdbbe85a751a0ad1700d9cf2e008807de4433840703f984e99ceb9669c59f
+  data.tar.gz: 88b24994e1968d196d50dfcc812c89d0e23b35454bc3e04fb72b27598f84d2ea7f3a94de160e81de42b5b75fed70a0594ed0664390790a5ff3c5c7d9ff22a1e8

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: ruby
 authors:
 - Chris Petersen