From 792bec4c406949bab2abe39e56ef77515f494de8 Mon Sep 17 00:00:00 2001
From: Dmitriy Kazimirov <dmitriy.kazimirov@viorsan.com>
Date: Wed, 2 Apr 2025 05:00:15 +0000
Subject: [PATCH] logging docs + fixed generation of urls on back so we don't
have to do it on front.
---
plugin/search_books.js | 29 ++++++++++++---
readme.md | 11 +++++-
src/api/app.py | 68 +++++++++++++++++++++++++++++++++--
src/api/templates/files.html | 2 +-
src/api/templates/search.html | 2 +-
5 files changed, 103 insertions(+), 9 deletions(-)
diff --git a/plugin/search_books.js b/plugin/search_books.js
index 4ef6c16..cd5c75f 100644
--- a/plugin/search_books.js
+++ b/plugin/search_books.js
@@ -68,19 +68,40 @@ function search_books(params, userSettings) {
// Create properly encoded URL
let formattedUrl = '';
+ console.log(`Result: ${JSON.stringify(result)}`); // Debugging log
+ console.log(`Raw URL: ${result.raw_url}`); // Debugging log
+
if (result.raw_url) {
try {
// Split URL into parts and encode components separately
const url = new URL(result.raw_url);
- const pathParts = url.pathname.split('/').map(part =>
- encodeURIComponent(part).replace(/'/g, "%27")
+ console.log(`Raw URL: ${result.raw_url}`); // Debugging log
+ //const pathParts = url.pathname.split('/').map(part =>
+ // encodeURIComponent(part).replace(/'/g, "%27")
+ //);
+ const pathParts = url.pathname.split('/').map(part =>
+ encodeURIComponent(decodeURIComponent(part)) // fix double encoding
+ .replace(/'/g, "%27")
);
- const search = url.search ? '?' + encodeURIComponent(url.search.slice(1)) : '';
- formattedUrl = `${url.origin}${pathParts.join('/')}${search}`;
+ console.log(`Path parts: ${pathParts}`); // Debugging log
+
+
+ // Correct encoding of query params
+ //const search = url.search ? '?' + encodeURIComponent(url.search.slice(1)) : '';
+ const search = url.searchParams.toString(); // automatic encode of param
+ console.log(`Search params: ${search}`); // Debugging log
+ //formattedUrl = `${url.origin}${pathParts.join('/')}${search}`;
+ formattedUrl = `${url.origin}${pathParts.join('/')}${search ? `?${search}` : ''}`;
+ console.log(`Formatted URL: ${formattedUrl}`); // Debugging log
+
} catch (e) {
+ console.error('Error parsing URL:', e); // Debugging log
formattedUrl = result.raw_url; // Fallback to original if URL parsing fails
+ console.log(`Fallback URL: ${formattedUrl}`); // Debugging log
}
}
+
+
return `Book: ${result.file_path}\n` +
`Snippet: ${result.snippet}\n` +
diff --git a/readme.md b/readme.md
index 3d07cc8..fccd50f 100644
--- a/readme.md
+++ b/readme.md
@@ -103,10 +103,19 @@ docker-compose logs -f api
docker-compose down && docker-compose up -d --build
```
-Logs
+Logs (app)
```bash
docker logs booksearch_app -f
```
+Logs (elasticsearch)
+```bash
+ docker logs booksearch_elastic -f
+```
+Logs (both)
+```bash
+ docker-compose logs -f
+```
+
### Log Rotation
Configure Docker log rotation in `/etc/docker/daemon.json`:
diff --git a/src/api/app.py b/src/api/app.py
index f839b0f..957cab3 100644
--- a/src/api/app.py
+++ b/src/api/app.py
@@ -104,12 +104,14 @@ def search():
file_path = file_path[len("/books/"):]
url = f"{base_url}/{file_path}"
- raw_url = f"{base_url}/file/{file_path}?format=html"
-
+ raw_url_old = f"{base_url}/file/{file_path}?format=html"
+ raw_url = f"{base_url}/file_html/{file_path}"
+
search_results.append({
"file_path": file_path,
"url": url,
"raw_url": raw_url,
+ "raw_url_old": raw_url_old,
"snippet": snippet,
"score": hit['_score']
})
@@ -193,8 +195,70 @@ def list_files():
return jsonify({"error": str(e)}), 500
return render_template('files.html', error=str(e))
+@app.route('/file_html/<path:file_path>', methods=['GET'])
+def get_file_html(file_path):
+ """Serve the HTML version of the file"""
+ # Ensure the file path is within the /books directory
+ books_dir = "/books"
+ # TODO: remove this logic from regular erv
+
+ # Decode URL-encoded path and normalize
+ decoded_path = unquote(file_path)
+ # Remove any leading slashes or duplicate 'books/' segments
+ decoded_path = decoded_path.lstrip('/')
+ if decoded_path.startswith('books/'):
+ decoded_path = decoded_path[6:]
+
+ # Join paths safely
+ full_path = os.path.normpath(os.path.join(books_dir, decoded_path))
+
+ # Validate the path is within the books directory
+ if not os.path.abspath(full_path).startswith(os.path.abspath(books_dir)):
+ return jsonify({"error": "Access denied: File path outside of books directory"}), 403
+
+ try:
+ # Handle EPUB files
+ if file_path.lower().endswith('.epub'):
+ # Convert EPUB to HTML
+ try:
+ book = epub.read_epub(full_path)
+ html_content = []
+ for item in book.get_items():
+ if item.get_type() == ebooklib.ITEM_DOCUMENT:
+ content = item.get_content()
+ if content:
+ soup = BeautifulSoup(content, 'html.parser')
+ # Preserve basic formatting tags
+ for tag in soup.find_all():
+ if tag.name not in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'br', 'div', 'span', 'strong', 'em', 'b', 'i', 'ul', 'ol', 'li']:
+ tag.unwrap()
+ html_content.append(str(soup))
+ except Exception as e:
+ logging.error(f"Error processing EPUB {full_path}: {str(e)}")
+ return jsonify({"error": f"Failed to process EPUB: {str(e)}"}), 500
+ return render_template('text_file.html',
+ file_path=file_path,
+ content='<hr>'.join(html_content),
+ is_html=True)
+
+ # Handle regular text files
+ with open(full_path, 'r', encoding='utf-8', errors='ignore') as f:
+ content = f.read()
+
+ # If it's an API request or the Accept header doesn't include HTML, return plain text
+ if request.headers.get('Accept') == 'application/json' or 'text/html' not in request.headers.get('Accept', ''):
+ return content, 200, {'Content-Type': 'text/plain; charset=utf-8'}
+
+ # Otherwise, render a simple HTML page with the content
+ return render_template('text_file.html', file_path=file_path, content=content)
+ except Exception as e:
+ return jsonify({"error": str(e)}), 404
+
+
+
@app.route('/file/<path:file_path>', methods=['GET'])
def get_file(file_path):
+ """Serve the file with proper headers"""
# Ensure the file path is within the /books directory
books_dir = "/books"
diff --git a/src/api/templates/files.html b/src/api/templates/files.html
index e89a227..e759e81 100644
--- a/src/api/templates/files.html
+++ b/src/api/templates/files.html
@@ -115,7 +115,7 @@
<span class="file-name">
<a href="/file/{{ file.path }}">
{% if file.path.endswith('.epub') %}
- <br><a href="/file/{{ file.path }}?format=html" class="plain-view-link">(View as HTML)</a>
+ <br><a href="/file_html/{{ file.path }}" class="plain-view-link">(View as HTML)</a>
{% endif %}
{% if file.title != file.name %}
<span class="book-title">{{ file.title }}</span>
diff --git a/src/api/templates/search.html b/src/api/templates/search.html
index 604cfeb..4ed9576 100644
--- a/src/api/templates/search.html
+++ b/src/api/templates/search.html
@@ -37,7 +37,7 @@
<div class="file-actions">
<a href="/file/{{ result.file_path.replace('/books/', '') }}" class="file-action">View Full File</a>
<span class="action-separator">|</span>
- <a href="/file/{{ result.file_path.replace('/books/', '') }}?format=html" class="file-action">View as HTML</a>
+ <a href="/file_html/{{ result.file_path.replace('/books/', '') }}" class="file-action">View as HTML</a>
</div>
</div>
{% endfor %}