History set max length number of snapshots

changedetectionio/blueprint/settings/templates/settings.html

@@ -59,6 +59,14 @@
                         {{ _('Set to') }} <strong>0</strong> {{ _('to disable') }}
                         </span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.history_snapshot_max_length, class="history_snapshot_max_length") }}
+                        <span class="pure-form-message-inline">{{ _('Limit collection of history snapshots for each watch to this number of history items.') }}
+                            <br>
+                        {{ _('Set to empty to disable / no limit') }}
+                        </span>
+                    </div>
+
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}

changedetectionio/blueprint/ui/templates/edit.html

@@ -115,6 +115,13 @@
                          {{ _('Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.') }}
                         </span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.history_snapshot_max_length, class="history_snapshot_max_length") }}
+                        <span class="pure-form-message-inline">{{ _('Limit collection of history snapshots for each watch to this number of history items.') }}
+                        <br>
+                        {{ _('Set to empty to use system settings default') }}
+                        </span>
+                    </div>
                     <div class="pure-control-group">
                         {{ render_ternary_field(form.use_page_title_in_list) }}
                     </div>

changedetectionio/forms.py

@@ -837,6 +837,8 @@ class processor_text_json_diff_form(commonSettingsForm):
     conditions = FieldList(FormField(ConditionFormRow), min_entries=1)  # Add rule logic here
     use_page_title_in_list = TernaryNoneBooleanField(_l('Use page <title> in list'), default=None)
 
+    history_snapshot_max_length = IntegerField(_l('Number of history items per watch to keep'), render_kw={"style": "width: 5em;"}, validators=[validators.Optional(), validators.NumberRange(min=2)])
+
     def extra_tab_content(self):
         return None
 
@@ -1034,6 +1036,8 @@ class globalSettingsApplicationForm(commonSettingsForm):
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,
                                                                                                      message=_l("Should contain zero or more attempts"))])
+
+    history_snapshot_max_length = IntegerField(_l('Number of history items per watch to keep'), render_kw={"style": "width: 5em;"}, validators=[validators.Optional(), validators.NumberRange(min=2)])
     ui = FormField(globalSettingsApplicationUIForm)
 
 

changedetectionio/model/App.py

@@ -46,6 +46,7 @@ class model(dict):
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
+                    'history_snapshot_max_length': None,
                     'ignore_whitespace': True,
                     'ignore_status_codes': False, #@todo implement, as ternary.
                     'ssim_threshold': '0.96',  # Default SSIM threshold for screenshot comparison

changedetectionio/model/Watch.py

@@ -1,3 +1,6 @@
+import gc
+from copy import copy
+
 from blinker import signal
 from changedetectionio.validate_url import is_safe_valid_url
 
@@ -13,7 +16,7 @@ from .. import jinja2_custom as safe_jinja
 from ..html_tools import TRANSLATE_WHITESPACE_TABLE
 
 FAVICON_RESAVE_THRESHOLD_SECONDS=86400
-BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024*20))
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -109,8 +112,13 @@ class model(watch_base):
         self.__datastore_path = kw.get('datastore_path')
         if kw.get('datastore_path'):
             del kw['datastore_path']
-            
+
+        self.__datastore=kw.get('__datastore')
+        if kw.get('__datastore'):
+            del kw['__datastore']
+
         super(model, self).__init__(*arg, **kw)
+
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
@@ -423,16 +431,49 @@ class model(watch_base):
         with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
             return f.read()
 
-    def _write_atomic(self, dest, data):
+    def _write_atomic(self, dest, data, mode='wb'):
         """Write data atomically to dest using a temp file"""
-        if not os.path.exists(dest):
-            import tempfile
-            with tempfile.NamedTemporaryFile('wb', delete=False, dir=self.watch_data_dir) as tmp:
-                tmp.write(data)
-                tmp.flush()
-                os.fsync(tmp.fileno())
-                tmp_path = tmp.name
-            os.replace(tmp_path, dest)
+        import tempfile
+        with tempfile.NamedTemporaryFile(mode, delete=False, dir=self.watch_data_dir) as tmp:
+            tmp.write(data)
+            tmp.flush()
+            os.fsync(tmp.fileno())
+            tmp_path = tmp.name
+        os.replace(tmp_path, dest)
+
+    def history_trim(self, newest_n_items):
+        from pathlib import Path
+
+        # Sort by timestamp (key)
+        sorted_items = sorted(self.history.items(), key=lambda x: int(x[0]))
+
+        keep_part = dict(sorted_items[-newest_n_items:])
+        delete_part = dict(sorted_items[:-newest_n_items])
+        logger.info( f"[{self.get('uuid')}] Trimming history to most recent {newest_n_items} items, keeping {len(keep_part)} items deleting {len(delete_part)} items.")
+
+        if delete_part:
+            for item in delete_part.items():
+                try:
+                    Path(item[1]).unlink(missing_ok=True)
+                except Exception as e:
+                    logger.critical(f"{str(e)}")
+                finally:
+                    logger.debug(f"[{self.get('uuid')}] Deleted {item[1]} history snapshot")
+        try:
+            dest = os.path.join(self.watch_data_dir, self.history_index_filename)
+            output = "\r\n".join(
+                f"{k},{Path(v).name}"
+                for k, v in keep_part.items()
+            )+"\r\n"
+            self._write_atomic(dest=dest, data=output, mode='w')
+        except Exception as e:
+            logger.critical(f"{str(e)}")
+        finally:
+            logger.debug(f"[{self.get('uuid')}] Updated history index {dest}")
+
+        # reimport
+        bump = self.history
+        gc.collect()
 
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
@@ -441,7 +482,6 @@ class model(watch_base):
         logger.trace(f"{self.get('uuid')} - Updating {self.history_index_filename} with timestamp {timestamp}")
 
         self.ensure_data_dir_exists()
-
         skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
 
         # Binary data - detect file type and save without compression
@@ -501,6 +541,16 @@ class model(watch_base):
         self.__newest_history_key = timestamp
         self.__history_n += 1
 
+
+        maxlen = (
+                self.get('history_snapshot_max_length')
+                or self.__datastore['settings']['application'].get('history_snapshot_max_length')
+        )
+
+        if self.__history_n > maxlen: # AND history len greater than...
+            self.history_trim(newest_n_items=maxlen)
+
+
         # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
         return snapshot_fname
 

changedetectionio/model/__init__.py

@@ -32,6 +32,7 @@ class watch_base(dict):
             'filter_text_replaced': True,
             'follow_price_changes': True,
             'has_ldjson_price_data': None,
+            'history_snapshot_max_length': None,
             'headers': {},  # Extra headers to send
             'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
             'ignore_status_codes': None,

changedetectionio/store/__init__.py

@@ -9,18 +9,14 @@ from flask import (
 )
 from flask_babel import gettext
 
-from ..blueprint.rss import RSS_CONTENT_FORMAT_DEFAULT
-from ..html_tools import TRANSLATE_WHITESPACE_TABLE
-from ..model import App, Watch, USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
-from copy import deepcopy, copy
+from ..model import App, Watch
+from copy import deepcopy
 from os import path, unlink
-from threading import Lock
 import json
 import os
 import re
 import secrets
 import sys
-import threading
 import time
 import uuid as uuid_builder
 from loguru import logger
@@ -35,7 +31,6 @@ except ImportError:
     HAS_ORJSON = False
 
 from ..processors import get_custom_watch_obj_for_processor
-from ..processors.restock_diff import Restock
 
 # Import the base class and helpers
 from .file_saving_datastore import FileSavingDataStore, load_all_watches, save_watch_atomic, save_json_atomic
@@ -308,7 +303,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         if entity.get('processor') != 'text_json_diff':
             logger.trace(f"Loading Watch object '{watch_class.__module__}.{watch_class.__name__}' for UUID {uuid}")
 
-        entity = watch_class(datastore_path=self.datastore_path, default=entity)
+        entity = watch_class(datastore_path=self.datastore_path, __datastore=self.__data, default=entity)
         return entity
 
     # ============================================================================