gitingest 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 114b6d8e954843f88917f556760e7fab89753126cb5fd059ed6cfe55c8f2e6c6
-  data.tar.gz: 39873c0d14eff9d6e615f6e2f13e7e30331f0e97db1162b613047782a582ff6c
+  metadata.gz: c754bbf3a24a049ce269017c82ef90b295b0503cb05cc0e652c0101ce68df484
+  data.tar.gz: c3df8efb661ff08e0525da943062882a7a2b467302895f09cbb5dbab38383927
 SHA512:
-  metadata.gz: f35ffb41ddd9990cd1c2e8c4ad08018a5bdd63c8ec222bfce021ede2c67dfa9355fbc7f1102f014c555d0df46501877b01f2767aadf674896635bd7fa5bab355
-  data.tar.gz: e431693ee45cf65ab3c63931c5c4a69675ddafc8038f90cda3dfb7dacec7449f48a65a41bc12f56996f8e697f80d1a896243e97aa37c96085107491099dabc05
+  metadata.gz: 803d3a5bb7ca76c9f51a268d22d485c1455b8ba7ebbe16aa3c5af8eabd63fddef273810ec10fa682b7cf606094b30c1ce681468d2a48a190d546c81a6eb779ca
+  data.tar.gz: 6781db79ba3fce1c75f13e8587ceffe8e26d0da276c0c1bbf175f942a9e8e9f1b742884413aabcc6b719a2c010c4156e601aa4577b9604e6edcd7959c67447ec

data/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## [0.5.0] - 2025-03-10
+
+### Added
+- Added repository directory structure visualization with `--show-structure` / `-s` option
+- Created `DirectoryStructureBuilder` class to generate tree views of repositories
+- Added `generate_directory_structure` method to the Generator class
+- Added tests for directory structure visualization
+
+### Changed
+- Enhanced documentation with directory structure visualization examples
+- Updated CLI help with the new option
+
+---
+
 ## [0.4.0] - 2025-03-03
 
 ### Added

data/README.md

@@ -1,3 +1,6 @@
+[![Gem Version](https://badge.fury.io/rb/gitingest.svg?icon=si%3Arubygems)](https://badge.fury.io/rb/gitingest)
+![Gem Total Downloads](https://img.shields.io/gem/dt/gitingest?style=flat-square&link=https%3A%2F%2Frubygems.org%2Fgems%2Fgitingest)
+
 # Gitingest
 
 Gitingest is a Ruby gem that fetches files from a GitHub repository and generates a consolidated text prompt, which can be used as input for large language models, documentation generation, or other purposes.
@@ -45,6 +48,9 @@ gitingest --repository user/repo -T 4
 # Set thread pool shutdown timeout
 gitingest --repository user/repo -W 120
 
+# Show repository directory structure
+gitingest --repository user/repo -s
+
 # Combine threading options
 gitingest --repository user/repo -T 8 -W 90
 
@@ -62,12 +68,21 @@ gitingest --repository user/repo --verbose
 - `-o, --output FILE`: Output file for the prompt [Default: reponame_prompt.txt]
 - `-e, --exclude PATTERN`: File patterns to exclude (comma separated)
 - `-b, --branch BRANCH`: Repository branch [Default: main]
+- `-s, --show-structure`: Show repository directory structure instead of generating prompt
 - `-T, --threads COUNT`: Number of concurrent threads [Default: auto-detected]
 - `-W, --thread-timeout SECONDS`: Thread pool shutdown timeout [Default: 60]
 - `-q, --quiet`: Reduce logging to errors only
 - `-v, --verbose`: Increase logging verbosity
 - `-h, --help`: Show help message
 
+### Directory Structure Visualization
+
+```bash
+gitingest --repository user/repo --show-structure
+```
+
+This will display a tree view of the repository's structure:
+
 ### As a Library
 
 ```ruby
@@ -145,4 +160,4 @@ Inspired by [`cyclotruc/gitingest`](https://github.com/cyclotruc/gitingest).
 
 ## License
 
-The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/bin/gitingest

@@ -39,6 +39,10 @@ parser = OptionParser.new do |opts|
     options[:thread_timeout] = timeout
   end
 
+  opts.on("-s", "--show-structure", "Show repository directory structure") do
+    options[:show_structure] = true
+  end
+
   opts.on("-q", "--quiet", "Reduce logging to errors only") do
     options[:quiet] = true
   end
@@ -58,6 +62,7 @@ parser = OptionParser.new do |opts|
   opts.separator "  gitingest -r user/repo -t YOUR_TOKEN        # With GitHub token for private repositories"
   opts.separator "  gitingest -r user/repo -o custom_prompt.txt # Custom output file"
   opts.separator "  gitingest -r user/repo -T 8                 # Use 8 threads for processing"
+  opts.separator "  gitingest -r user/repo -s                   # Show repository directory structure"
 end
 
 begin

data/index.html

@@ -6,6 +6,7 @@
     <title>Gitingest - GitHub Repository Fetcher and Prompt Generator</title>
     <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/github-markdown-css/5.2.0/github-markdown.min.css">
     <style>
+        /* Styles remain the same */
         :root {
             --bg-color: #0d1117;
             --text-color: #c9d1d9;
@@ -176,7 +177,7 @@
         <div class="header">
             <div class="logo">G</div>
             <div>
-                <h1>Gitingest <span class="version-badge">v0.3.0</span></h1>
+                <h1>Gitingest <span class="version-badge">v0.5.0</span></h1>
                 <p>A Ruby gem that fetches files from a GitHub repository and generates a consolidated text prompt for LLMs</p>
             </div>
         </div>
@@ -213,6 +214,18 @@ gitingest --repository user/repo --branch develop
 # Exclude additional patterns
 gitingest --repository user/repo --exclude "*.md,docs/"
 
+# Show repository directory structure
+gitingest --repository user/repo -s
+
+# Control the number of threads
+gitingest --repository user/repo -T 4
+
+# Set thread pool shutdown timeout
+gitingest --repository user/repo -W 120
+
+# Combine threading options
+gitingest --repository user/repo -T 8 -W 90
+
 # Quiet mode
 gitingest --repository user/repo --quiet
 
@@ -226,19 +239,54 @@ gitingest --repository user/repo --verbose</code></pre>
             <li><code>-o, --output FILE</code>: Output file for the prompt [Default: reponame_prompt.txt]</li>
             <li><code>-e, --exclude PATTERN</code>: File patterns to exclude (comma separated)</li>
             <li><code>-b, --branch BRANCH</code>: Repository branch [Default: main]</li>
+            <li><code>-s, --show-structure</code>: Show repository directory structure</li>
+            <li><code>-T, --threads COUNT</code>: Number of concurrent threads [Default: auto-detected]</li>
+            <li><code>-W, --thread-timeout SECONDS</code>: Thread pool shutdown timeout [Default: 60]</li>
+            <li><code>-q, --quiet</code>: Reduce logging to errors only</li>
+            <li><code>-v, --verbose</code>: Increase logging verbosity</li>
             <li><code>-h, --help</code>: Show help message</li>
         </ul>
         
+        <h3>Directory Structure Visualization</h3>
+        <p>You can visualize the structure of a repository using the <code>--show-structure</code> option:</p>
+        <pre><code>gitingest --repository user/repo --show-structure</code></pre>
+        
+        <p>This will display a tree view of the repository's structure, for example:</p>
+        <pre><code>Directory structure:
+└── repo-name/
+    ├── README.md
+    ├── LICENSE
+    ├── lib/
+    │   ├── repo-name.rb
+    │   └── repo-name/
+    │       └── version.rb
+    ├── bin/
+    │   └── console
+    └── spec/
+        ├── spec_helper.rb
+        └── repo-name_spec.rb</code></pre>
+        
         <h3>As a Library</h3>
         <pre><code>require "gitingest"
 
-# Basic usage
+# Basic usage - write to a file
 generator = Gitingest::Generator.new(
   repository: "user/repo",
   token: "YOUR_GITHUB_TOKEN" # optional
 )
+
+# Run the full workflow (fetch repository and generate file)
 generator.run
 
+# OR generate file only (if you need the output path)
+output_path = generator.generate_file
+
+# Get content as a string (for in-memory processing)
+content = generator.generate_prompt
+
+# Generate and get repository directory structure
+structure = generator.generate_directory_structure
+
 # With custom options
 generator = Gitingest::Generator.new(
   repository: "user/repo",
@@ -246,26 +294,32 @@ generator = Gitingest::Generator.new(
   output_file: "my_prompt.txt",
   branch: "develop",
   exclude: ["*.md", "docs/"], 
-  quiet: true # or verbose: true
+  threads: 4,              # control concurrency
+  thread_timeout: 120,     # custom thread timeout
+  quiet: true,             # or verbose: true
+  show_structure: true     # show directory structure instead of generating prompt
 )
-generator.run
 
 # With custom logger
 custom_logger = Logger.new("gitingest.log")
 generator = Gitingest::Generator.new(
   repository: "user/repo",
   logger: custom_logger
-)
-generator.run</code></pre>
+)</code></pre>
         
         <h2>Features</h2>
         <ul>
             <li>Fetches all files from a GitHub repository based on the given branch</li>
             <li>Automatically excludes common binary files and system files by default</li>
             <li>Allows custom exclusion patterns for specific file extensions or directories</li>
-            <li>Uses concurrent processing for faster downloads</li>
-            <li>Handles GitHub API rate limiting with automatic retry</li>
+            <li>Uses concurrent processing with configurable thread count for faster downloads</li>
+            <li>Shows real-time progress with visual bar, ETA, and processing rate</li>
+            <li>Handles GitHub API rate limiting with automatic retry and exponential backoff</li>
+            <li>Optimizes memory usage with buffered writes and thread-local buffers</li>
+            <li>Intelligently prioritizes files for better thread distribution</li>
             <li>Generates a clean, formatted output file with file paths and content</li>
+            <li>Provides both file-based and string-based output options</li>
+            <li>Visualizes repository directory structure in a tree format</li>
         </ul>
         
         <h2>Default Exclusion Patterns</h2>
@@ -290,6 +344,52 @@ generator.run</code></pre>
         <div class="changelog">
             <h2>Changelog</h2>
             
+            <div class="changelog-item">
+                <div>
+                    <span class="changelog-version">v0.5.0</span>
+                    <span class="changelog-date">- March 4, 2025</span>
+                </div>
+                <ul class="changelog-list">
+                    <li>Added repository directory structure visualization with <code>--show-structure</code> option</li>
+                    <li>Created <code>DirectoryStructureBuilder</code> class to generate tree views of repositories</li>
+                    <li>Added <code>generate_directory_structure</code> method to the Generator class</li>
+                    <li>Added tests for the directory structure visualization</li>
+                    <li>Updated documentation with directory structure visualization examples</li>
+                </ul>
+            </div>
+            
+            <div class="changelog-item">
+                <div>
+                    <span class="changelog-version">v0.4.0</span>
+                    <span class="changelog-date">- March 4, 2025</span>
+                </div>
+                <ul class="changelog-list">
+                    <li>Added <code>generate_prompt</code> method for in-memory content generation without file I/O</li>
+                    <li>Integrated visual progress bar with file processing rate reporting</li>
+                    <li>Added human-readable time formatting for progress estimates</li>
+                    <li>Enhanced test coverage for multithreaded operations</li>
+                    <li>Refactored <code>process_content_to_output</code> for better code reuse</li>
+                    <li>Improved thread management to handle various error conditions gracefully</li>
+                    <li>Fixed thread pool shutdown issues and race conditions</li>
+                </ul>
+            </div>
+            
+            <div class="changelog-item">
+                <div>
+                    <span class="changelog-version">v0.3.1</span>
+                    <span class="changelog-date">- March 3, 2025</span>
+                </div>
+                <ul class="changelog-list">
+                    <li>Introduced configurable threading options with <code>:threads</code> and <code>:thread_timeout</code></li>
+                    <li>Implemented thread-local buffers to reduce mutex contention during file processing</li>
+                    <li>Added exponential backoff with jitter for rate-limited API requests</li>
+                    <li>Improved progress indicator with estimated time remaining</li>
+                    <li>Increased <code>BUFFER_SIZE</code> from 100 to 250 to reduce I/O operations</li>
+                    <li>Optimized file exclusion check using a combined regex for faster matching</li>
+                    <li>Improved thread pool efficiency by prioritizing smaller files first</li>
+                </ul>
+            </div>
+            
             <div class="changelog-item">
                 <div>
                     <span class="changelog-version">v0.3.0</span>
@@ -298,7 +398,7 @@ generator.run</code></pre>
                 <ul class="changelog-list">
                     <li>Added <code>faraday-retry</code> gem dependency for better API rate limit handling</li>
                     <li>Implemented thread-safe buffer management with mutex locks</li>
-                    <li>Added new <code>ProgressIndicator</code> class for better CLI progress reporting (showing percentages)</li>
+                    <li>Added new <code>ProgressIndicator</code> class for better CLI progress reporting</li>
                     <li>Improved memory efficiency with configurable buffer size</li>
                     <li>Enhanced code organization with dedicated methods for file content formatting</li>
                     <li>Added comprehensive method documentation and parameter descriptions</li>
@@ -323,26 +423,6 @@ generator.run</code></pre>
                     <li>Enforced a 1000 file limit to prevent memory overload</li>
                 </ul>
             </div>
-            
-            <div class="changelog-item">
-                <div>
-                    <span class="changelog-version">v0.1.0</span>
-                    <span class="changelog-date">- March 2, 2025</span>
-                </div>
-                <ul class="changelog-list">
-                    <li>Initial release of Gitingest</li>
-                    <li>Core functionality to fetch and process GitHub repository files</li>
-                    <li>Command-line interface for easy interaction</li>
-                    <li>Smart file filtering with default exclusions for common non-code files</li>
-                    <li>Concurrent processing for improved performance</li>
-                    <li>Custom exclude patterns support</li>
-                    <li>GitHub authentication via access tokens</li>
-                    <li>Automatic rate limit handling with retry mechanism</li>
-                    <li>Repository prompt generation with file separation markers</li>
-                    <li>Support for custom branch selection</li>
-                    <li>Custom output file naming options</li>
-                </ul>
-            </div>
         </div>
         
         <h2>Contributing</h2>
@@ -357,7 +437,7 @@ generator.run</code></pre>
     
     <footer>
         <p>© 2025 David Santangelo</p>
-        <p>Last updated: March 2, 2025</p>
+        <p>Last updated: March 4, 2025</p>
     </footer>
 </body>
 </html>

data/lib/gitingest/generator.rb

@@ -96,6 +96,7 @@ module Gitingest
     # @option options [Logger] :logger Custom logger instance
     # @option options [Integer] :threads Number of threads to use (default: auto-detected)
     # @option options [Integer] :thread_timeout Seconds to wait for thread pool shutdown (default: 60)
+    # @option options [Boolean] :show_structure Show repository directory structure (default: false)
     def initialize(options = {})
       @options = options
       @repo_files = []
@@ -109,6 +110,12 @@ module Gitingest
     # Main execution method for command line
     def run
       fetch_repository_contents
+
+      if @options[:show_structure]
+        puts generate_directory_structure
+        return
+      end
+
       generate_file
     end
 
@@ -144,6 +151,21 @@ module Gitingest
       result
     end
 
+    # Generate a textual representation of the repository's directory structure
+    #
+    # @return [String] The directory structure as a formatted string
+    def generate_directory_structure
+      fetch_repository_contents if @repo_files.empty?
+
+      @logger.info "Generating directory structure for #{@options[:repository]}"
+
+      repo_name = @options[:repository].split("/").last
+      structure = DirectoryStructureBuilder.new(repo_name, @repo_files).build
+
+      @logger.info "\n"
+      structure
+    end
+
     private
 
     # Set up logging based on verbosity options
@@ -169,6 +191,7 @@ module Gitingest
       @options[:exclude] ||= []
       @options[:threads] ||= DEFAULT_THREAD_COUNT
       @options[:thread_timeout] ||= DEFAULT_THREAD_TIMEOUT
+      @options[:show_structure] ||= false
       @excluded_patterns = DEFAULT_EXCLUDES + @options[:exclude]
     end
 
@@ -441,4 +464,57 @@ module Gitingest
       end
     end
   end
+
+  # Helper class to build directory structure visualization
+  class DirectoryStructureBuilder
+    def initialize(root_name, files)
+      @root_name = root_name
+      @files = files.map(&:path)
+    end
+
+    def build
+      tree = { @root_name => {} }
+
+      @files.sort.each do |path|
+        parts = path.split("/")
+        current = tree[@root_name]
+
+        parts.each do |part|
+          if part == parts.last
+            current[part] = nil
+          else
+            current[part] ||= {}
+            current = current[part]
+          end
+        end
+      end
+
+      output = ["Directory structure:"]
+      render_tree(tree, "", output)
+      output.join("\n")
+    end
+
+    private
+
+    def render_tree(tree, prefix, output)
+      return if tree.nil?
+
+      tree.keys.each_with_index do |key, index|
+        is_last = index == tree.keys.size - 1
+        current_prefix = prefix
+
+        if prefix.empty?
+          output << "└── #{key}/"
+          current_prefix = "    "
+        else
+          connector = is_last ? "└── " : "├── "
+          item = tree[key].is_a?(Hash) ? "#{key}/" : key
+          output << "#{prefix}#{connector}#{item}"
+          current_prefix = prefix + (is_last ? "    " : "│   ")
+        end
+
+        render_tree(tree[key], current_prefix, output) if tree[key].is_a?(Hash)
+      end
+    end
+  end
 end

data/lib/gitingest/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Gitingest
-  VERSION = "0.4.0"
+  VERSION = "0.5.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gitingest
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Davide Santangelo
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-03-03 00:00:00.000000000 Z
+date: 2025-03-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: concurrent-ruby