feat: Add retained formats functionality for auto-conversion

Implements ability to keep original book formats after conversion to target format.
Users can now select which formats to retain via CWA settings UI.

Features:
- New auto_convert_retained_formats setting with checkbox grid UI
- Automatic conflict prevention (target format always retained)
- Database migration support for backward compatibility
- Enhanced ingest processor with robust format addition logic

Credit to @angelicadvocate for original implementation concept in PR #284.

Fixes edge cases including race conditions, UI state handling, and iteration safety.

Author: crocodilestick

CONTRIBUTORS

@@ -1,7 +1,7 @@
 CONTRIBUTORS
 
 This file is automatically generated. DO NOT EDIT MANUALLY.
-Generated on: 2025-09-12T19:09:48.157596Z
+Generated on: 2025-09-12T19:34:33.644775Z
 
 Upstream project: https://github.com/janeczku/calibre-web
 Fork project (Calibre-Web Automated, since 2024): https://github.com/crocodilestick/calibre-web-automated

cps/cwa_functions.py

@@ -222,14 +222,15 @@ def set_cwa_settings():
     for format in ignorable_formats:
         string_settings.append(f"ignore_ingest_{format}")
         string_settings.append(f"ignore_convert_{format}")
+        string_settings.append(f"convert_retained_{format}")
 
     if request.method == 'POST':
         if request.form['submit_button'] == "Submit":
-            result = {"auto_convert_ignored_formats":[], "auto_ingest_ignored_formats":[]}
+            result = {"auto_convert_ignored_formats":[], "auto_ingest_ignored_formats":[], "auto_convert_retained_formats":[]}
             # set boolean_settings
             for setting in boolean_settings:
                 value = request.form.get(setting)
-                if value == None:
+                if value is None:
                     value = 0
                 else:
                     value = 1
@@ -238,18 +239,20 @@ def set_cwa_settings():
             for setting in string_settings:
                 value = request.form.get(setting)
                 if setting[:14] == "ignore_convert":
-                    if value == None:
-                        continue
-                    else:
+                    if value is not None:
                         result["auto_convert_ignored_formats"].append(value)
-                        continue
+                    continue
                 elif setting[:13] == "ignore_ingest":
-                    if value == None:
-                        continue
-                    else:
+                    if value is not None:
                         result["auto_ingest_ignored_formats"].append(value)
-                        continue
-                elif setting == "auto_convert_target_format" and value == None:
+                    continue
+                elif setting.startswith("convert_retained"):
+                    if value is not None:
+                        result["auto_convert_retained_formats"].append(value)
+                    continue
+                elif setting == "auto_convert_target_format":
+                    if value is None:
+                        value = cwa_db.cwa_settings['auto_convert_target_format']
                     value = cwa_db.cwa_settings['auto_convert_target_format']
 
                 result |= {setting:value}
@@ -260,6 +263,15 @@ def set_cwa_settings():
             if result['auto_convert_target_format'] in result['auto_ingest_ignored_formats']:
                 result['auto_ingest_ignored_formats'].remove(result['auto_convert_target_format'])
 
+            # Prevent retaining of ignored ingest formats (create a copy to avoid modification during iteration)
+            for ignored_format in result['auto_ingest_ignored_formats'][:]:
+                if ignored_format in result['auto_convert_retained_formats']:
+                    result['auto_convert_retained_formats'].remove(ignored_format)
+
+            # Force target format to be retained (ensure it's not already there to avoid duplicates)
+            if result['auto_convert_target_format'] not in result['auto_convert_retained_formats']:
+                result['auto_convert_retained_formats'].append(result['auto_convert_target_format'])
+
             # Handle integer settings
             for setting in integer_settings:
                 value = request.form.get(setting)

cps/templates/cwa_settings.html

@@ -429,6 +429,35 @@ <h4 class="settings-section-header">{{_('CWA Auto-Convert - Ignored Formats')}}<
       </div>
     </div>
 
+    <div class="settings-container">
+      <h4 class="settings-section-header">{{_('CWA Auto-Convert - Retained Formats')}}</h4>
+      <p class="cwa-settings-explanation settings-explanation">
+        {{_('The formats selected here will always be added to the library, even after they have been converted to the target format. However, if the format is in the "CWA Auto-Ingest - Ignored Formats" list, it will not be imported. Note that the target format is always retained.')}}
+      </p>
+      <div style="max-width: 90rem; padding-left: 30px;">
+        {% for format in ignorable_formats -%}
+          <label for="convert_retained_{{ format }}" style="width: 75px; padding-right: 6px; display: inline-block !important;">
+            {% if format in cwa_settings.get('auto_convert_retained_formats', []) or format == cwa_settings['auto_convert_target_format'] %}
+              {% if format in cwa_settings['auto_ingest_ignored_formats'] %}
+                <input type="checkbox" id="convert_retained_{{ format }}" name="convert_retained_{{ format }}" value="{{ format }}" disabled style="vertical-align: middle; accent-color: var(--color-secondary); display: inline-block !important;">
+              {% elif format == cwa_settings['auto_convert_target_format'] %}
+                <input type="checkbox" id="convert_retained_{{ format }}" name="convert_retained_{{ format }}" value="{{ format }}" checked disabled style="vertical-align: middle; accent-color: var(--color-secondary); display: inline-block !important;" title="Target format is always retained">
+              {% else %}
+                <input type="checkbox" id="convert_retained_{{ format }}" name="convert_retained_{{ format }}" value="{{ format }}" checked style="vertical-align: middle; accent-color: var(--color-secondary); display: inline-block !important;">
+              {% endif %}
+            {% else %}
+              {% if format in cwa_settings['auto_ingest_ignored_formats'] %}
+                <input type="checkbox" id="convert_retained_{{ format }}" name="convert_retained_{{ format }}" value="{{ format }}" disabled style="vertical-align: middle; accent-color: var(--color-secondary); display: inline-block !important;">
+              {% else %}
+                <input type="checkbox" id="convert_retained_{{ format }}" name="convert_retained_{{ format }}" value="{{ format }}" style="vertical-align: middle; accent-color: var(--color-secondary); display: inline-block !important;">
+              {% endif %}
+            {% endif %}
+            <span style="padding-left: 4px; vertical-align: middle;">{{ format }}</span>
+          </label>
+        {% endfor %}
+      </div>
+    </div>
+
     <div class="settings-container">
       <h4 class="settings-section-header">{{_('CWA Auto-Ingest - Ignored Formats')}}</h4>
       <p class="cwa-settings-explanation settings-explanation">

scripts/cwa_db.py

@@ -245,7 +245,7 @@ def get_cwa_settings(self) -> dict:
     def update_cwa_settings(self, result) -> None:
         """Sets settings using POST request from set_cwa_settings()"""
         for setting in result.keys():
-            if setting == "auto_convert_ignored_formats" or setting == "auto_ingest_ignored_formats":
+            if setting == "auto_convert_ignored_formats" or setting == "auto_ingest_ignored_formats" or setting == "auto_convert_retained_formats":
                 result[setting] = ','.join(result[setting])
 
             # Use parameterized queries to safely handle non-English characters and quotes

scripts/cwa_schema.sql

@@ -42,6 +42,7 @@ CREATE TABLE IF NOT EXISTS cwa_settings(
     auto_convert_target_format TEXT DEFAULT "epub" NOT NULL,
     auto_convert_ignored_formats TEXT DEFAULT "" NOT NULL,
     auto_ingest_ignored_formats TEXT DEFAULT "" NOT NULL,
+    auto_convert_retained_formats TEXT DEFAULT "" NOT NULL,
     auto_ingest_automerge TEXT DEFAULT "new_record" NOT NULL,
     ingest_timeout_minutes INTEGER DEFAULT 15 NOT NULL,
     auto_metadata_enforcement SMALLINT DEFAULT 1 NOT NULL,

scripts/ingest_processor.py

@@ -123,6 +123,9 @@ def __init__(self, filepath: str):
                 self.ingest_ignored_formats.append(tmp_ext)
 
         self.convert_ignored_formats = self.cwa_settings['auto_convert_ignored_formats']
+        self.convert_retained_formats = self.cwa_settings.get('auto_convert_retained_formats', [])
+        if isinstance(self.convert_retained_formats, str):
+            self.convert_retained_formats = self.convert_retained_formats.split(',') if self.convert_retained_formats else []
         self.is_kindle_epub_fixer = self.cwa_settings['kindle_epub_fixer']
 
         # Formats
@@ -712,6 +715,35 @@ def main(filepath=sys.argv[1]):
 
             if convert_successful: # If previous conversion process was successful, remove tmp files and import into library
                 nbp.add_book_to_library(converted_filepath) # type: ignore
+                
+                # If the original format should be retained, also add it as an additional format
+                if nbp.input_format in nbp.convert_retained_formats and nbp.input_format not in nbp.ingest_ignored_formats:
+                    print(f"[ingest-processor]: Retaining original format ({nbp.input_format}) for {nbp.filename}...", flush=True)
+                    # Find the book that was just added to get its ID
+                    try:
+                        calibre_db_path = os.path.join(nbp.library_dir, 'metadata.db')
+                        with sqlite3.connect(calibre_db_path, timeout=30) as con:
+                            cur = con.cursor()
+                            # Get the most recently added book - use title/author for more reliable matching
+                            # in case of concurrent ingests
+                            cur.execute("""
+                                SELECT id FROM books 
+                                WHERE path = (SELECT path FROM books ORDER BY timestamp DESC LIMIT 1)
+                                ORDER BY timestamp DESC LIMIT 1
+                            """)
+                            result = cur.fetchone()
+                            
+                        if result:
+                            book_id = result[0]
+                            # Verify the original file still exists before trying to add it
+                            if os.path.exists(filepath) and os.path.getsize(filepath) > 0:
+                                nbp.add_format_to_book(book_id, filepath)
+                            else:
+                                print(f"[ingest-processor] Original file no longer exists or is empty, cannot retain format: {filepath}", flush=True)
+                        else:
+                            print(f"[ingest-processor] Could not find book ID to add retained format for: {nbp.filename}", flush=True)
+                    except Exception as e:
+                        print(f"[ingest-processor] Error adding retained format: {e}", flush=True)
 
         elif nbp.can_convert and not nbp.auto_convert_on: # Books not in target format but Auto-Converter is off so files are imported anyway
             print(f"\n[ingest-processor]: {nbp.filename} not in target format but CWA Auto-Convert is deactivated so importing the file anyway...", flush=True)