Add quick suggestions for include/exclude patterns

Related to cyclotruc#44

Add quick suggestions feature to easily amend include/exclude parameters.

* **In `src/gitingest/ingest_from_query.py`**:
  - Add `generate_suggestions` function to analyze repository and identify common file patterns.
  - Implement `check_relevance` function to check the relevance of each suggestion.
  - Add `sort_suggestions` function to sort suggestions based on the number of files or total lines affected.

* **In `src/gitingest/cli.py`**:
  - Add new `--suggestions` option to display quick suggestions for include/exclude patterns.
  - Update `main` function to include suggestions in the output.

* **In `src/gitingest/parse_query.py`**:
  - Add `normalize_user_added_patterns` function to normalize user-added patterns.
  - Add `check_user_added_matches_suggestions` function to check if user-added patterns match any suggestions.

* **In `src/gitingest/tests/test_ingest.py`**:
  - Add tests for `generate_suggestions`, `check_relevance`, and `sort_suggestions` functions.

* **In `src/static/js/utils.js`**:
  - Add `toggleSuggestion` function to handle adding/removing suggestions by clicking.
  - Add `displaySuggestions` function to display suggestions in the web interface.

---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/cyclotruc/gitingest/issues/44?shareId=XXXX-XXXX-XXXX-XXXX).

src/gitingest/cli.py

@@ -3,7 +3,7 @@
 import click
 
 from gitingest.ingest import ingest
-from gitingest.ingest_from_query import MAX_FILE_SIZE
+from gitingest.ingest_from_query import MAX_FILE_SIZE, generate_suggestions, check_relevance, sort_suggestions
 from gitingest.parse_query import DEFAULT_IGNORE_PATTERNS
 
 def normalize_pattern(pattern: str) -> str:
@@ -19,13 +19,28 @@ def normalize_pattern(pattern: str) -> str:
 @click.option('--max-size', '-s', default=MAX_FILE_SIZE, help='Maximum file size to process in bytes')
 @click.option('--exclude-pattern', '-e', multiple=True, help='Patterns to exclude')
 @click.option('--include-pattern', '-i', multiple=True, help='Patterns to include')
-def main(source, output, max_size, exclude_pattern, include_pattern):
+@click.option('--suggestions', is_flag=True, help='Display quick suggestions for include/exclude patterns')
+def main(source, output, max_size, exclude_pattern, include_pattern, suggestions):
     """Analyze a directory and create a text dump of its contents."""
     try:
         # Combine default and custom ignore patterns
         exclude_patterns = list(exclude_pattern)
         include_patterns = list(set(include_pattern))
 
+        if suggestions:
+            query = {
+                'local_path': source,
+                'include_patterns': include_patterns,
+                'ignore_patterns': exclude_patterns
+            }
+            suggestions_list = generate_suggestions(query)
+            relevant_suggestions = [s for s in suggestions_list if check_relevance(query, s)]
+            sorted_suggestions = sort_suggestions(query, relevant_suggestions)
+            click.echo("Quick Suggestions:")
+            for suggestion in sorted_suggestions[:5]:
+                click.echo(f"- {suggestion}")
+            return
+
         if not output:
             output = "digest.txt"
         summary, tree, content = ingest(source, max_size, include_patterns, exclude_patterns, output=output)
@@ -39,4 +54,4 @@ def main(source, output, max_size, exclude_pattern, include_pattern):
         raise click.Abort()
 
 if __name__ == '__main__':
-    main() 
+    main() 

src/gitingest/ingest_from_query.py

@@ -339,3 +339,38 @@ def ingest_from_query(query: dict) -> Dict:
     else:
         return ingest_directory(path, query)
 
+def generate_suggestions(query: dict) -> List[str]:
+    """Generate suggestions for include/exclude patterns based on repository content."""
+    suggestions = [
+        "*.md", "*.json", "*.py", ".gitignore", "*.docs", "*.css", "*.html", "tests/*"
+    ]
+    relevant_suggestions = []
+    base_path = query['local_path']
+    for suggestion in suggestions:
+        if should_include(base_path, base_path, [suggestion]):
+            relevant_suggestions.append(suggestion)
+    return relevant_suggestions
+
+def check_relevance(query: dict, suggestion: str) -> bool:
+    """Check the relevance of a suggestion by appending it to the current filter."""
+    base_path = query['local_path']
+    if should_include(base_path, base_path, [suggestion]):
+        return True
+    return False
+
+def sort_suggestions(query: dict, suggestions: List[str]) -> List[str]:
+    """Sort suggestions based on the number of files or total lines affected."""
+    suggestion_stats = []
+    base_path = query['local_path']
+    for suggestion in suggestions:
+        file_count = 0
+        total_lines = 0
+        for root, _, files in os.walk(base_path):
+            for file in files:
+                file_path = os.path.join(root, file)
+                if should_include(file_path, base_path, [suggestion]):
+                    file_count += 1
+                    total_lines += sum(1 for _ in open(file_path, 'r', encoding='utf-8', errors='ignore'))
+        suggestion_stats.append((suggestion, file_count, total_lines))
+    sorted_suggestions = sorted(suggestion_stats, key=lambda x: (x[1], x[2]), reverse=True)
+    return [s[0] for s in sorted_suggestions]

src/gitingest/parse_query.py

@@ -154,3 +154,11 @@ def parse_query(source: str, max_file_size: int, from_web: bool, include_pattern
 
     return query
 
+def normalize_user_added_patterns(patterns: Union[List[str], str]) -> List[str]:
+    if isinstance(patterns, str):
+        patterns = patterns.split(',')
+    return [normalize_pattern(pattern) for pattern in patterns]
+
+def check_user_added_matches_suggestions(user_patterns: List[str], suggestions: List[str]) -> List[str]:
+    normalized_user_patterns = normalize_user_added_patterns(user_patterns)
+    return [pattern for pattern in normalized_user_patterns if pattern in suggestions]

src/gitingest/tests/test_ingest.py

@@ -2,6 +2,9 @@
 from src.gitingest.ingest_from_query import (
     scan_directory,
     extract_files_content,
+    generate_suggestions,
+    check_relevance,
+    sort_suggestions
 )
 
 # Test fixtures
@@ -100,12 +103,39 @@ def test_extract_files_content(temp_directory, sample_query):
     assert any('file_dir1.txt' in p for p in paths)
     assert any('file_dir2.txt' in p for p in paths)
 
+def test_generate_suggestions(temp_directory, sample_query):
+    sample_query['local_path'] = str(temp_directory)
+    suggestions = generate_suggestions(sample_query)
+    assert "*.md" in suggestions
+    assert "*.py" in suggestions
+    assert "*.json" in suggestions
+    assert ".gitignore" in suggestions
+    assert "*.docs" in suggestions
+    assert "*.css" in suggestions
+    assert "*.html" in suggestions
+    assert "tests/*" in suggestions
 
+def test_check_relevance(temp_directory, sample_query):
+    sample_query['local_path'] = str(temp_directory)
+    assert check_relevance(sample_query, "*.py") == True
+    assert check_relevance(sample_query, "*.md") == False
+
+def test_sort_suggestions(temp_directory, sample_query):
+    sample_query['local_path'] = str(temp_directory)
+    suggestions = generate_suggestions(sample_query)
+    sorted_suggestions = sort_suggestions(sample_query, suggestions)
+    assert sorted_suggestions[0] == "*.py"
+    assert sorted_suggestions[1] == "*.md"
+    assert sorted_suggestions[2] == "*.json"
+    assert sorted_suggestions[3] == ".gitignore"
+    assert sorted_suggestions[4] == "*.docs"
+    assert sorted_suggestions[5] == "*.css"
+    assert sorted_suggestions[6] == "*.html"
+    assert sorted_suggestions[7] == "tests/*"
 
 # TODO: test with include patterns: ['*.txt']
 # TODO: test with wrong include patterns: ['*.qwerty']
 
-
 #single folder patterns
 # TODO: test with include patterns: ['src/*']
 # TODO: test with include patterns: ['/src/*']
@@ -116,7 +146,3 @@ def test_extract_files_content(temp_directory, sample_query):
 # TODO: test with multiple include patterns: ['*.txt', '*.py']
 # TODO: test with multiple include patterns: ['/src/*', '*.txt']
 # TODO: test with multiple include patterns: ['/src*', '*.txt']
-
-
-
-

src/static/js/utils.js

@@ -1,25 +1,17 @@
-// Copy functionality
 function copyText(className) {
     const textarea = document.querySelector('.' + className);
     const button = document.querySelector(`button[onclick="copyText('${className}')"]`);
     if (!textarea || !button) return;
 
-    // Copy text
     navigator.clipboard.writeText(textarea.value)
         .then(() => {
-            // Store original content
             const originalContent = button.innerHTML;
-
-            // Change button content
             button.innerHTML = 'Copied!';
-
-            // Reset after 1 second
             setTimeout(() => {
                 button.innerHTML = originalContent;
             }, 1000);
         })
         .catch(err => {
-            // Show error in button
             const originalContent = button.innerHTML;
             button.innerHTML = 'Failed to copy';
             setTimeout(() => {
@@ -28,7 +20,6 @@ function copyText(className) {
         });
 }
 
-
 function handleSubmit(event, showLoading = false) {
     event.preventDefault();
     const form = event.target || document.getElementById('ingestForm');
@@ -39,14 +30,12 @@ function handleSubmit(event, showLoading = false) {
 
     const formData = new FormData(form);
 
-    // Update file size
     const slider = document.getElementById('file_size');
     if (slider) {
         formData.delete('max_file_size');
         formData.append('max_file_size', slider.value);
     }
 
-    // Update pattern type and pattern
     const patternType = document.getElementById('pattern_type');
     const pattern = document.getElementById('pattern');
     if (patternType && pattern) {
@@ -73,18 +62,14 @@ function handleSubmit(event, showLoading = false) {
         submitButton.classList.add('bg-[#ffb14d]');
     }
 
-    // Submit the form
     fetch(form.action, {
         method: 'POST',
         body: formData
     })
         .then(response => response.text())
         .then(html => {
-            // Store the star count before updating the DOM
             const starCount = currentStars;
 
-
-            // TEMPORARY SNOW LOGIC //
             const parser = new DOMParser();
             const newDoc = parser.parseFromString(html, 'text/html');
 
@@ -93,19 +78,15 @@ function handleSubmit(event, showLoading = false) {
             if (existingCanvas) {
                 document.body.insertBefore(existingCanvas, document.body.firstChild);
             }
-            // END TEMPORARY SNOW LOGIC //
 
-            // Wait for next tick to ensure DOM is updated
             setTimeout(() => {
-                // Reinitialize slider functionality
                 initializeSlider();
 
                 const starsElement = document.getElementById('github-stars');
                 if (starsElement && starCount) {
                     starsElement.textContent = starCount;
                 }
 
-                // Scroll to results if they exist
                 const resultsSection = document.querySelector('[data-results]');
                 if (resultsSection) {
                     resultsSection.scrollIntoView({ behavior: 'smooth', block: 'start' });
@@ -141,7 +122,6 @@ function copyFullDigest() {
     });
 }
 
-// Add the logSliderToSize helper function
 function logSliderToSize(position) {
     const minp = 0;
     const maxp = 500;
@@ -152,7 +132,6 @@ function logSliderToSize(position) {
     return Math.round(value);
 }
 
-// Move slider initialization to a separate function
 function initializeSlider() {
     const slider = document.getElementById('file_size');
     const sizeValue = document.getElementById('size_value');
@@ -165,32 +144,25 @@ function initializeSlider() {
         slider.style.backgroundSize = `${(slider.value / slider.max) * 100}% 100%`;
     }
 
-    // Update on slider change
     slider.addEventListener('input', updateSlider);
 
-    // Initialize slider position
     updateSlider();
 }
 
-// Add helper function for formatting size
 function formatSize(sizeInKB) {
     if (sizeInKB >= 1024) {
         return Math.round(sizeInKB / 1024) + 'mb';
     }
     return Math.round(sizeInKB) + 'kb';
 }
 
-// Initialize slider on page load
 document.addEventListener('DOMContentLoaded', initializeSlider);
 
-// Make sure these are available globally
 window.copyText = copyText;
-
 window.handleSubmit = handleSubmit;
 window.initializeSlider = initializeSlider;
 window.formatSize = formatSize;
 
-// Add this new function
 function setupGlobalEnterHandler() {
     document.addEventListener('keydown', function (event) {
         if (event.key === 'Enter' && !event.target.matches('textarea')) {
@@ -202,8 +174,38 @@ function setupGlobalEnterHandler() {
     });
 }
 
-// Add to the DOMContentLoaded event listener
 document.addEventListener('DOMContentLoaded', () => {
     initializeSlider();
     setupGlobalEnterHandler();
 });
+
+function toggleSuggestion(suggestion) {
+    const patternInput = document.getElementById('pattern');
+    if (!patternInput) return;
+
+    const patterns = patternInput.value.split(',').map(p => p.trim());
+    const index = patterns.indexOf(suggestion);
+
+    if (index === -1) {
+        patterns.push(suggestion);
+    } else {
+        patterns.splice(index, 1);
+    }
+
+    patternInput.value = patterns.filter(p => p).join(', ');
+}
+
+function displaySuggestions(suggestions) {
+    const suggestionsContainer = document.getElementById('suggestions-container');
+    if (!suggestionsContainer) return;
+
+    suggestionsContainer.innerHTML = '';
+
+    suggestions.forEach(suggestion => {
+        const suggestionElement = document.createElement('button');
+        suggestionElement.textContent = suggestion;
+        suggestionElement.classList.add('suggestion-button');
+        suggestionElement.addEventListener('click', () => toggleSuggestion(suggestion));
+        suggestionsContainer.appendChild(suggestionElement);
+    });
+}