Compare commits
11 Commits
brotli-sna
...
disable-ap
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0e9ba9d72a | ||
|
|
f49464f451 | ||
|
|
bc6bde4062 | ||
|
|
2863167f45 | ||
|
|
ce3966c104 | ||
|
|
d5f574ca17 | ||
|
|
c96ece170a | ||
|
|
1fb90bbddc | ||
|
|
55b6ae86e8 | ||
|
|
66b892f770 | ||
|
|
3b80bb2f0e |
6
.github/workflows/containers.yml
vendored
6
.github/workflows/containers.yml
vendored
@@ -98,7 +98,8 @@ jobs:
|
||||
platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
|
||||
cache-from: type=local,src=/tmp/.buildx-cache
|
||||
cache-to: type=local,dest=/tmp/.buildx-cache
|
||||
provenance: false
|
||||
# Looks like this was disabled
|
||||
# provenance: false
|
||||
|
||||
# A new tagged release is required, which builds :tag and :latest
|
||||
- name: Build and push :tag
|
||||
@@ -117,7 +118,8 @@ jobs:
|
||||
platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
|
||||
cache-from: type=local,src=/tmp/.buildx-cache
|
||||
cache-to: type=local,dest=/tmp/.buildx-cache
|
||||
provenance: false
|
||||
# Looks like this was disabled
|
||||
# provenance: false
|
||||
|
||||
- name: Image digest
|
||||
run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
recursive-include changedetectionio/api *
|
||||
recursive-include changedetectionio/blueprint *
|
||||
recursive-include changedetectionio/model *
|
||||
recursive-include changedetectionio/processors *
|
||||
recursive-include changedetectionio/res *
|
||||
recursive-include changedetectionio/static *
|
||||
recursive-include changedetectionio/templates *
|
||||
|
||||
@@ -36,7 +36,7 @@ from flask import (
|
||||
from changedetectionio import html_tools
|
||||
from changedetectionio.api import api_v1
|
||||
|
||||
__version__ = '0.40.3'
|
||||
__version__ = '0.41.1'
|
||||
|
||||
datastore = None
|
||||
|
||||
@@ -340,8 +340,6 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
if len(dates) < 2:
|
||||
continue
|
||||
|
||||
prev_fname = watch.history[dates[-2]]
|
||||
|
||||
if not watch.viewed:
|
||||
# Re #239 - GUID needs to be individual for each event
|
||||
# @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
|
||||
@@ -362,9 +360,12 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
|
||||
watch_title = watch.get('title') if watch.get('title') else watch.get('url')
|
||||
fe.title(title=watch_title)
|
||||
latest_fname = watch.history[dates[-1]]
|
||||
|
||||
html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="<br>")
|
||||
html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
|
||||
newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
|
||||
include_equal=False,
|
||||
line_feed_sep="<br>")
|
||||
|
||||
fe.content(content="<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff),
|
||||
type='CDATA')
|
||||
|
||||
@@ -600,6 +601,16 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
if datastore.proxy_list is not None and form.data['proxy'] == '':
|
||||
extra_update_obj['proxy'] = None
|
||||
|
||||
# Unsetting all filter_text methods should make it go back to default
|
||||
# This particularly affects tests running
|
||||
if 'filter_text_added' in form.data and not form.data.get('filter_text_added') \
|
||||
and 'filter_text_replaced' in form.data and not form.data.get('filter_text_replaced') \
|
||||
and 'filter_text_removed' in form.data and not form.data.get('filter_text_removed'):
|
||||
extra_update_obj['filter_text_added'] = True
|
||||
extra_update_obj['filter_text_replaced'] = True
|
||||
extra_update_obj['filter_text_removed'] = True
|
||||
|
||||
|
||||
datastore.data['watching'][uuid].update(form.data)
|
||||
datastore.data['watching'][uuid].update(extra_update_obj)
|
||||
|
||||
@@ -847,28 +858,22 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
# Save the current newest history as the most recently viewed
|
||||
datastore.set_last_viewed(uuid, time.time())
|
||||
|
||||
newest_file = history[dates[-1]]
|
||||
|
||||
# Read as binary and force decode as UTF-8
|
||||
# Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
|
||||
try:
|
||||
with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
|
||||
newest_version_file_contents = f.read()
|
||||
newest_version_file_contents = watch.get_history_snapshot(dates[-1])
|
||||
except Exception as e:
|
||||
newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
|
||||
newest_version_file_contents = "Unable to read {}.\n".format(dates[-1])
|
||||
|
||||
previous_version = request.args.get('previous_version')
|
||||
try:
|
||||
previous_file = history[previous_version]
|
||||
except KeyError:
|
||||
# Not present, use a default value, the second one in the sorted list.
|
||||
previous_file = history[dates[-2]]
|
||||
previous_timestamp = dates[-2]
|
||||
if previous_version:
|
||||
previous_timestamp = previous_version
|
||||
|
||||
try:
|
||||
with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
|
||||
previous_version_file_contents = f.read()
|
||||
previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
|
||||
except Exception as e:
|
||||
previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
|
||||
previous_version_file_contents = "Unable to read {}.\n".format(previous_timestamp)
|
||||
|
||||
|
||||
screenshot_url = watch.get_screenshot()
|
||||
@@ -948,37 +953,35 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
return output
|
||||
|
||||
timestamp = list(watch.history.keys())[-1]
|
||||
filename = watch.history[timestamp]
|
||||
try:
|
||||
with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
|
||||
tmp = f.readlines()
|
||||
tmp = watch.get_history_snapshot(timestamp).splitlines()
|
||||
|
||||
# Get what needs to be highlighted
|
||||
ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
|
||||
# Get what needs to be highlighted
|
||||
ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
|
||||
|
||||
# .readlines will keep the \n, but we will parse it here again, in the future tidy this up
|
||||
ignored_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
|
||||
wordlist=ignore_rules,
|
||||
mode='line numbers'
|
||||
)
|
||||
# .readlines will keep the \n, but we will parse it here again, in the future tidy this up
|
||||
ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
|
||||
wordlist=ignore_rules,
|
||||
mode='line numbers'
|
||||
)
|
||||
|
||||
trigger_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
|
||||
wordlist=watch['trigger_text'],
|
||||
mode='line numbers'
|
||||
)
|
||||
# Prepare the classes and lines used in the template
|
||||
i=0
|
||||
for l in tmp:
|
||||
classes=[]
|
||||
i+=1
|
||||
if i in ignored_line_numbers:
|
||||
classes.append('ignored')
|
||||
if i in trigger_line_numbers:
|
||||
classes.append('triggered')
|
||||
content.append({'line': l, 'classes': ' '.join(classes)})
|
||||
trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
|
||||
wordlist=watch['trigger_text'],
|
||||
mode='line numbers'
|
||||
)
|
||||
# Prepare the classes and lines used in the template
|
||||
i=0
|
||||
for l in tmp:
|
||||
classes=[]
|
||||
i+=1
|
||||
if i in ignored_line_numbers:
|
||||
classes.append('ignored')
|
||||
if i in trigger_line_numbers:
|
||||
classes.append('triggered')
|
||||
content.append({'line': l, 'classes': ' '.join(classes)})
|
||||
|
||||
except Exception as e:
|
||||
content.append({'line': "File doesnt exist or unable to read file {}".format(filename), 'classes': ''})
|
||||
content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
|
||||
|
||||
output = render_template("preview.html",
|
||||
content=content,
|
||||
|
||||
@@ -179,9 +179,7 @@ class WatchSingleHistory(Resource):
|
||||
if timestamp == 'latest':
|
||||
timestamp = list(watch.history.keys())[-1]
|
||||
|
||||
# @todo - Check for UTF-8 compatability
|
||||
with open(watch.history[timestamp], 'r') as f:
|
||||
content = f.read()
|
||||
content = watch.get_history_snapshot(timestamp)
|
||||
|
||||
response = make_response(content, 200)
|
||||
response.mimetype = "text/plain"
|
||||
|
||||
@@ -3,7 +3,8 @@ import apprise
|
||||
# Create our AppriseAsset and populate it with some of our new values:
|
||||
# https://github.com/caronc/apprise/wiki/Development_API#the-apprise-asset-object
|
||||
asset = apprise.AppriseAsset(
|
||||
image_url_logo='https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
|
||||
image_url_logo='https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png',
|
||||
async_mode=False # Maybe related to https://github.com/dgtlmoon/changedetection.io/issues/1486
|
||||
)
|
||||
|
||||
asset.app_id = "changedetection.io"
|
||||
|
||||
@@ -10,7 +10,7 @@ def same_slicer(l, a, b):
|
||||
return l[a:b]
|
||||
|
||||
# like .compare but a little different output
|
||||
def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True):
|
||||
def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True, include_replaced=True, include_change_type_prefix=True):
|
||||
cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
|
||||
|
||||
# @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
|
||||
@@ -19,33 +19,38 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
|
||||
g = before[alo:ahi]
|
||||
yield g
|
||||
elif include_removed and tag == 'delete':
|
||||
g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
|
||||
row_prefix = "(removed) " if include_change_type_prefix else ''
|
||||
g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
|
||||
yield g
|
||||
elif tag == 'replace':
|
||||
g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
|
||||
g += ["(into) " + i for i in same_slicer(after, blo, bhi)]
|
||||
elif include_replaced and tag == 'replace':
|
||||
row_prefix = "(changed) " if include_change_type_prefix else ''
|
||||
g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
|
||||
row_prefix = "(into) " if include_change_type_prefix else ''
|
||||
g += [row_prefix + i for i in same_slicer(after, blo, bhi)]
|
||||
yield g
|
||||
elif include_added and tag == 'insert':
|
||||
g = ["(added) " + i for i in same_slicer(after, blo, bhi)]
|
||||
row_prefix = "(added) " if include_change_type_prefix else ''
|
||||
g = [row_prefix + i for i in same_slicer(after, blo, bhi)]
|
||||
yield g
|
||||
|
||||
# only_differences - only return info about the differences, no context
|
||||
# line_feed_sep could be "<br>" or "<li>" or "\n" etc
|
||||
def render_diff(previous_file, newest_file, include_equal=False, include_removed=True, include_added=True, line_feed_sep="\n"):
|
||||
with open(newest_file, 'r') as f:
|
||||
newest_version_file_contents = f.read()
|
||||
newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
|
||||
def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True):
|
||||
|
||||
if previous_file:
|
||||
with open(previous_file, 'r') as f:
|
||||
previous_version_file_contents = f.read()
|
||||
newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
|
||||
|
||||
if previous_version_file_contents:
|
||||
previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
|
||||
else:
|
||||
previous_version_file_contents = ""
|
||||
|
||||
rendered_diff = customSequenceMatcher(previous_version_file_contents,
|
||||
newest_version_file_contents,
|
||||
include_equal, include_removed, include_added)
|
||||
rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
|
||||
after=newest_version_file_contents,
|
||||
include_equal=include_equal,
|
||||
include_removed=include_removed,
|
||||
include_added=include_added,
|
||||
include_replaced=include_replaced,
|
||||
include_change_type_prefix=include_change_type_prefix)
|
||||
|
||||
# Recursively join lists
|
||||
f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])
|
||||
|
||||
@@ -399,13 +399,19 @@ class watchForm(commonSettingsForm):
|
||||
body = TextAreaField('Request body', [validators.Optional()])
|
||||
method = SelectField('Request method', choices=valid_method, default=default_method)
|
||||
ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
|
||||
check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
|
||||
check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
|
||||
|
||||
filter_text_added = BooleanField('Added lines', default=True)
|
||||
filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
|
||||
filter_text_removed = BooleanField('Removed lines', default=True)
|
||||
|
||||
# @todo this class could be moved to its own text_json_diff_watchForm and this goes to restock_diff_Watchform perhaps
|
||||
in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
|
||||
|
||||
trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
|
||||
if os.getenv("PLAYWRIGHT_DRIVER_URL"):
|
||||
browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
|
||||
text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
|
||||
text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
|
||||
webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
|
||||
|
||||
save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
|
||||
|
||||
@@ -287,3 +287,18 @@ def workarounds_for_obfuscations(content):
|
||||
content = re.sub('<!--\s+-->', '', content)
|
||||
|
||||
return content
|
||||
|
||||
|
||||
def get_triggered_text(content, trigger_text):
|
||||
triggered_text = []
|
||||
result = strip_ignore_text(content=content,
|
||||
wordlist=trigger_text,
|
||||
mode="line numbers")
|
||||
|
||||
i = 1
|
||||
for p in content.splitlines():
|
||||
if i in result:
|
||||
triggered_text.append(p)
|
||||
i += 1
|
||||
|
||||
return triggered_text
|
||||
|
||||
@@ -26,6 +26,9 @@ base_config = {
|
||||
'fetch_backend': 'system', # plaintext, playwright etc
|
||||
'processor': 'text_json_diff', # could be restock_diff or others from .processors
|
||||
'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
|
||||
'filter_text_added': True,
|
||||
'filter_text_replaced': True,
|
||||
'filter_text_removed': True,
|
||||
'has_ldjson_price_data': None,
|
||||
'track_ldjson_price_data': None,
|
||||
'headers': {}, # Extra headers to send
|
||||
@@ -241,9 +244,32 @@ class model(dict):
|
||||
bump = self.history
|
||||
return self.__newest_history_key
|
||||
|
||||
def get_history_snapshot(self, timestamp):
|
||||
import brotli
|
||||
filepath = self.history[timestamp]
|
||||
|
||||
# See if a brotli versions exists and switch to that
|
||||
if not filepath.endswith('.br') and os.path.isfile(f"{filepath}.br"):
|
||||
filepath = f"{filepath}.br"
|
||||
|
||||
# OR in the backup case that the .br does not exist, but the plain one does
|
||||
if filepath.endswith('.br') and not os.path.isfile(filepath):
|
||||
if os.path.isfile(filepath.replace('.br', '')):
|
||||
filepath = filepath.replace('.br', '')
|
||||
|
||||
if filepath.endswith('.br'):
|
||||
# Brotli doesnt have a fileheader to detect it, so we rely on filename
|
||||
# https://www.rfc-editor.org/rfc/rfc7932
|
||||
with open(filepath, 'rb') as f:
|
||||
return(brotli.decompress(f.read()).decode('utf-8'))
|
||||
|
||||
with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
|
||||
return f.read()
|
||||
|
||||
# Save some text file to the appropriate path and bump the history
|
||||
# result_obj from fetch_site_status.run()
|
||||
def save_history_text(self, contents, timestamp, snapshot_id):
|
||||
import brotli
|
||||
|
||||
self.ensure_data_dir_exists()
|
||||
|
||||
@@ -252,16 +278,21 @@ class model(dict):
|
||||
if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
|
||||
time.sleep(timestamp - self.__newest_history_key)
|
||||
|
||||
snapshot_fname = f"{snapshot_id}.txt"
|
||||
threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
|
||||
skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
|
||||
|
||||
# Only write if it does not exist, this is so that we dont bother re-saving the same data by checksum under different filenames.
|
||||
dest = os.path.join(self.watch_data_dir, snapshot_fname)
|
||||
if not os.path.exists(dest):
|
||||
# in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
|
||||
# most sites are utf-8 and some are even broken utf-8
|
||||
with open(dest, 'wb') as f:
|
||||
f.write(contents)
|
||||
f.close()
|
||||
if not skip_brotli and len(contents) > threshold:
|
||||
snapshot_fname = f"{snapshot_id}.txt.br"
|
||||
dest = os.path.join(self.watch_data_dir, snapshot_fname)
|
||||
if not os.path.exists(dest):
|
||||
with open(dest, 'wb') as f:
|
||||
f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
|
||||
else:
|
||||
snapshot_fname = f"{snapshot_id}.txt"
|
||||
dest = os.path.join(self.watch_data_dir, snapshot_fname)
|
||||
if not os.path.exists(dest):
|
||||
with open(dest, 'wb') as f:
|
||||
f.write(contents)
|
||||
|
||||
# Append to index
|
||||
# @todo check last char was \n
|
||||
@@ -298,7 +329,8 @@ class model(dict):
|
||||
# Compare each lines (set) against each history text file (set) looking for something new..
|
||||
existing_history = set({})
|
||||
for k, v in self.history.items():
|
||||
alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
|
||||
content = self.get_history_snapshot(k)
|
||||
alist = set([line.strip().lower() for line in content.splitlines()])
|
||||
existing_history = existing_history.union(alist)
|
||||
|
||||
# Check that everything in local_lines(new stuff) already exists in existing_history - it should
|
||||
@@ -359,6 +391,7 @@ class model(dict):
|
||||
return fname
|
||||
return False
|
||||
|
||||
|
||||
def pause(self):
|
||||
self['paused'] = True
|
||||
|
||||
@@ -388,8 +421,8 @@ class model(dict):
|
||||
# self.history will be keyed with the full path
|
||||
for k, fname in self.history.items():
|
||||
if os.path.isfile(fname):
|
||||
with open(fname, "r") as f:
|
||||
contents = f.read()
|
||||
if True:
|
||||
contents = self.get_history_snapshot(k)
|
||||
res = re.findall(regex, contents, re.MULTILINE)
|
||||
if res:
|
||||
if not csv_writer:
|
||||
@@ -425,3 +458,38 @@ class model(dict):
|
||||
# Return list of tags, stripped and lowercase, used for searching
|
||||
def all_tags(self):
|
||||
return [s.strip().lower() for s in self.get('tag','').split(',')]
|
||||
|
||||
def has_special_diff_filter_options_set(self):
|
||||
|
||||
# All False - nothing would be done, so act like it's not processable
|
||||
if not self.get('filter_text_added', True) and not self.get('filter_text_replaced', True) and not self.get('filter_text_removed', True):
|
||||
return False
|
||||
|
||||
# Or one is set
|
||||
if not self.get('filter_text_added', True) or not self.get('filter_text_replaced', True) or not self.get('filter_text_removed', True):
|
||||
return True
|
||||
|
||||
# None is set
|
||||
return False
|
||||
|
||||
|
||||
def get_last_fetched_before_filters(self):
|
||||
import brotli
|
||||
filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
|
||||
|
||||
if not os.path.isfile(filepath):
|
||||
# If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
|
||||
dates = list(self.history.keys())
|
||||
if len(dates):
|
||||
return self.get_history_snapshot(dates[-1])
|
||||
else:
|
||||
return ''
|
||||
|
||||
with open(filepath, 'rb') as f:
|
||||
return(brotli.decompress(f.read()).decode('utf-8'))
|
||||
|
||||
def save_last_fetched_before_filters(self, contents):
|
||||
import brotli
|
||||
filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
|
||||
with open(filepath, 'wb') as f:
|
||||
f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
|
||||
|
||||
@@ -5,17 +5,18 @@ import json
|
||||
|
||||
valid_tokens = {
|
||||
'base_url': '',
|
||||
'watch_url': '',
|
||||
'watch_uuid': '',
|
||||
'watch_title': '',
|
||||
'watch_tag': '',
|
||||
'current_snapshot': '',
|
||||
'diff': '',
|
||||
'diff_added': '',
|
||||
'diff_removed': '',
|
||||
'diff_full': '',
|
||||
'diff_removed': '',
|
||||
'diff_url': '',
|
||||
'preview_url': '',
|
||||
'current_snapshot': ''
|
||||
'triggered_text': '',
|
||||
'watch_tag': '',
|
||||
'watch_title': '',
|
||||
'watch_url': '',
|
||||
'watch_uuid': '',
|
||||
}
|
||||
|
||||
default_notification_format_for_watch = 'System default'
|
||||
@@ -211,17 +212,18 @@ def create_notification_parameters(n_object, datastore):
|
||||
tokens.update(
|
||||
{
|
||||
'base_url': base_url if base_url is not None else '',
|
||||
'watch_url': watch_url,
|
||||
'watch_uuid': uuid,
|
||||
'watch_title': watch_title if watch_title is not None else '',
|
||||
'watch_tag': watch_tag if watch_tag is not None else '',
|
||||
'diff_url': diff_url,
|
||||
'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else '',
|
||||
'diff': n_object.get('diff', ''), # Null default in the case we use a test
|
||||
'diff_added': n_object.get('diff_added', ''), # Null default in the case we use a test
|
||||
'diff_removed': n_object.get('diff_removed', ''), # Null default in the case we use a test
|
||||
'diff_full': n_object.get('diff_full', ''), # Null default in the case we use a test
|
||||
'diff_removed': n_object.get('diff_removed', ''), # Null default in the case we use a test
|
||||
'diff_url': diff_url,
|
||||
'preview_url': preview_url,
|
||||
'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
|
||||
'triggered_text': n_object.get('triggered_text', ''),
|
||||
'watch_tag': watch_tag if watch_tag is not None else '',
|
||||
'watch_title': watch_title if watch_title is not None else '',
|
||||
'watch_url': watch_url,
|
||||
'watch_uuid': uuid,
|
||||
})
|
||||
|
||||
return tokens
|
||||
|
||||
@@ -9,7 +9,7 @@ from copy import deepcopy
|
||||
|
||||
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
|
||||
|
||||
name = 'Re-stock detection'
|
||||
name = 'Re-stock detection for single product pages'
|
||||
description = 'Detects if the product goes back to in-stock'
|
||||
|
||||
class perform_site_check(difference_detection_processor):
|
||||
|
||||
@@ -279,6 +279,34 @@ class perform_site_check(difference_detection_processor):
|
||||
# Re #340 - return the content before the 'ignore text' was applied
|
||||
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
|
||||
|
||||
|
||||
# @todo whitespace coming from missing rtrim()?
|
||||
# stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
|
||||
# Rewrite's the processing text based on only what diff result they want to see
|
||||
if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
|
||||
# Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
|
||||
from .. import diff
|
||||
# needs to not include (added) etc or it may get used twice
|
||||
# Replace the processed text with the preferred result
|
||||
rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
|
||||
newest_version_file_contents=stripped_text_from_html,
|
||||
include_equal=False, # not the same lines
|
||||
include_added=watch.get('filter_text_added', True),
|
||||
include_removed=watch.get('filter_text_removed', True),
|
||||
include_replaced=watch.get('filter_text_replaced', True),
|
||||
line_feed_sep="\n",
|
||||
include_change_type_prefix=False)
|
||||
|
||||
watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
|
||||
|
||||
if not rendered_diff and stripped_text_from_html:
|
||||
# We had some content, but no differences were found
|
||||
# Store our new file as the MD5 so it will trigger in the future
|
||||
c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
|
||||
return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
|
||||
else:
|
||||
stripped_text_from_html = rendered_diff
|
||||
|
||||
# Treat pages with no renderable text content as a change? No by default
|
||||
empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
|
||||
if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
|
||||
@@ -337,6 +365,7 @@ class perform_site_check(difference_detection_processor):
|
||||
blocked = True
|
||||
# Filter and trigger works the same, so reuse it
|
||||
# It should return the line numbers that match
|
||||
# Unblock flow if the trigger was found (some text remained after stripped what didnt match)
|
||||
result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
|
||||
wordlist=trigger_text,
|
||||
mode="line numbers")
|
||||
|
||||
@@ -18,6 +18,7 @@ function isItemInStock() {
|
||||
'nicht lieferbar',
|
||||
'nicht zur verfügung',
|
||||
'no disponible temporalmente',
|
||||
'not available',
|
||||
'not in stock',
|
||||
'out of stock',
|
||||
'out-of-stock',
|
||||
|
||||
@@ -28,3 +28,11 @@ pytest tests/test_notification.py
|
||||
# Re-run with HIDE_REFERER set - could affect login
|
||||
export HIDE_REFERER=True
|
||||
pytest tests/test_access_control.py
|
||||
|
||||
# Re-run a few tests that will trigger brotli based storage
|
||||
export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
|
||||
pytest tests/test_access_control.py
|
||||
pytest tests/test_notification.py
|
||||
pytest tests/test_backend.py
|
||||
pytest tests/test_rss.py
|
||||
pytest tests/test_unique_lines.py
|
||||
@@ -893,6 +893,21 @@ body.full-width {
|
||||
font-size: .875em;
|
||||
}
|
||||
}
|
||||
.text-filtering {
|
||||
h3 {
|
||||
margin-top: 0;
|
||||
}
|
||||
border: 1px solid #ccc;
|
||||
padding: 1rem;
|
||||
border-radius: 5px;
|
||||
margin-bottom: 1rem;
|
||||
fieldset:last-of-type {
|
||||
padding-bottom: 0;
|
||||
.pure-control-group {
|
||||
padding-bottom: 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ul {
|
||||
@@ -1053,12 +1068,15 @@ ul {
|
||||
color: #fff;
|
||||
ul {
|
||||
padding: 0.3rem;
|
||||
|
||||
li {
|
||||
list-style: none;
|
||||
}
|
||||
list-style: none;
|
||||
font-size: 0.8rem;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
.restock-label {
|
||||
&.in-stock {
|
||||
background-color: var(--color-background-button-green);
|
||||
|
||||
@@ -872,6 +872,17 @@ body.full-width .edit-form {
|
||||
color: var(--color-text-input-description); }
|
||||
.edit-form .pure-form-message-inline code {
|
||||
font-size: .875em; }
|
||||
.edit-form .text-filtering {
|
||||
border: 1px solid #ccc;
|
||||
padding: 1rem;
|
||||
border-radius: 5px;
|
||||
margin-bottom: 1rem; }
|
||||
.edit-form .text-filtering h3 {
|
||||
margin-top: 0; }
|
||||
.edit-form .text-filtering fieldset:last-of-type {
|
||||
padding-bottom: 0; }
|
||||
.edit-form .text-filtering fieldset:last-of-type .pure-control-group {
|
||||
padding-bottom: 0; }
|
||||
|
||||
ul {
|
||||
padding-left: 1em;
|
||||
@@ -989,7 +1000,8 @@ ul {
|
||||
#quick-watch-processor-type ul {
|
||||
padding: 0.3rem; }
|
||||
#quick-watch-processor-type ul li {
|
||||
list-style: none; }
|
||||
list-style: none;
|
||||
font-size: 0.8rem; }
|
||||
|
||||
.restock-label {
|
||||
padding: 3px;
|
||||
|
||||
@@ -17,6 +17,7 @@
|
||||
<li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
|
||||
<li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
|
||||
<li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
|
||||
<li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="notifications-wrapper">
|
||||
@@ -103,6 +104,10 @@
|
||||
<td>The current snapshot value, useful when combined with JSON or CSS filters
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{triggered_text}}' }}</code></td>
|
||||
<td>Text that tripped the trigger from filters</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<div class="pure-form-message-inline">
|
||||
|
||||
@@ -244,12 +244,6 @@ User-Agent: wonderbra 1.0") }}
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
<fieldset>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.check_unique_lines) }}
|
||||
<span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
|
||||
</div>
|
||||
</fieldset>
|
||||
<div class="pure-control-group">
|
||||
{% set field = render_field(form.include_filters,
|
||||
rows=5,
|
||||
@@ -287,37 +281,39 @@ xpath://body/div/span[contains(@class, 'example-class')]",
|
||||
href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
|
||||
</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.subtractive_selectors, rows=5, placeholder="header
|
||||
<fieldset class="pure-control-group">
|
||||
{{ render_field(form.subtractive_selectors, rows=5, placeholder="header
|
||||
footer
|
||||
nav
|
||||
.stockticker") }}
|
||||
<span class="pure-form-message-inline">
|
||||
<span class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li> Remove HTML element(s) by CSS selector before text conversion. </li>
|
||||
<li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
|
||||
</ul>
|
||||
</span>
|
||||
</div>
|
||||
<fieldset class="pure-group">
|
||||
{{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
|
||||
/some.regex\d{2}/ for case-INsensitive regex
|
||||
") }}
|
||||
<span class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
|
||||
<li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
|
||||
<li>Changing this will affect the comparison checksum which may trigger an alert</li>
|
||||
<li>Use the preview/show current tab to see ignores</li>
|
||||
</ul>
|
||||
</span>
|
||||
</fieldset>
|
||||
<div class="text-filtering">
|
||||
<fieldset class="pure-group" id="text-filtering-type-options">
|
||||
<h3>Text filtering</h3>
|
||||
Limit trigger/ignore/block/extract to;<br>
|
||||
{{ render_checkbox_field(form.filter_text_added) }}
|
||||
{{ render_checkbox_field(form.filter_text_replaced) }}
|
||||
{{ render_checkbox_field(form.filter_text_removed) }}
|
||||
<span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
|
||||
<span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
|
||||
<span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
|
||||
</fieldset>
|
||||
|
||||
</fieldset>
|
||||
<fieldset class="pure-control-group">
|
||||
{{ render_checkbox_field(form.check_unique_lines) }}
|
||||
<span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
|
||||
</fieldset>
|
||||
<fieldset>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.trigger_text, rows=5, placeholder="Some text to wait for in a line
|
||||
/some.regex\d{2}/ for case-INsensitive regex
|
||||
") }}
|
||||
") }}
|
||||
<span class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li>Text to wait for before triggering a change/notification, all text and regex are tested <i>case-insensitive</i>.</li>
|
||||
@@ -328,6 +324,21 @@ nav
|
||||
</span>
|
||||
</div>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group">
|
||||
{{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
|
||||
/some.regex\d{2}/ for case-INsensitive regex
|
||||
") }}
|
||||
<span class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
|
||||
<li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
|
||||
<li>Changing this will affect the comparison checksum which may trigger an alert</li>
|
||||
<li>Use the preview/show current tab to see ignores</li>
|
||||
</ul>
|
||||
</span>
|
||||
|
||||
</fieldset>
|
||||
|
||||
<fieldset>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
|
||||
@@ -362,6 +373,7 @@ Unavailable") }}
|
||||
</span>
|
||||
</div>
|
||||
</fieldset>
|
||||
</div>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
|
||||
176
changedetectionio/tests/test_add_replace_remove_filter.py
Normal file
176
changedetectionio/tests/test_add_replace_remove_filter.py
Normal file
@@ -0,0 +1,176 @@
|
||||
#!/usr/bin/python3
|
||||
|
||||
import time
|
||||
from flask import url_for
|
||||
from .util import live_server_setup
|
||||
from changedetectionio import html_tools
|
||||
|
||||
|
||||
def set_original(excluding=None, add_line=None):
|
||||
test_return_data = """<html>
|
||||
<body>
|
||||
<p>Some initial text</p>
|
||||
<p>So let's see what happens.</p>
|
||||
<p>and a new line!</p>
|
||||
<p>The golden line</p>
|
||||
<p>A BREAK TO MAKE THE TOP LINE STAY AS "REMOVED" OR IT WILL GET COUNTED AS "CHANGED INTO"</p>
|
||||
<p>Something irrelevant</p>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
if add_line:
|
||||
c=test_return_data.splitlines()
|
||||
c.insert(5, add_line)
|
||||
test_return_data = "\n".join(c)
|
||||
|
||||
if excluding:
|
||||
output = ""
|
||||
for i in test_return_data.splitlines():
|
||||
if not excluding in i:
|
||||
output += f"{i}\n"
|
||||
|
||||
test_return_data = output
|
||||
|
||||
with open("test-datastore/endpoint-content.txt", "w") as f:
|
||||
f.write(test_return_data)
|
||||
|
||||
def test_setup(client, live_server):
|
||||
live_server_setup(live_server)
|
||||
|
||||
def test_check_removed_line_contains_trigger(client, live_server):
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
# Give the endpoint time to spin up
|
||||
time.sleep(1)
|
||||
set_original()
|
||||
# Add our URL to the import page
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
res = client.post(
|
||||
url_for("import_page"),
|
||||
data={"urls": test_url},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"1 Imported" in res.data
|
||||
|
||||
# Give the thread time to pick it up
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
|
||||
# Goto the edit page, add our ignore text
|
||||
# Add our URL to the import page
|
||||
res = client.post(
|
||||
url_for("edit_page", uuid="first"),
|
||||
data={"trigger_text": 'The golden line',
|
||||
"url": test_url,
|
||||
'fetch_backend': "html_requests",
|
||||
'filter_text_removed': 'y'},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"Updated watch." in res.data
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
set_original(excluding='Something irrelevant')
|
||||
|
||||
# A line thats not the trigger should not trigger anything
|
||||
res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
assert b'1 watches queued for rechecking.' in res.data
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' not in res.data
|
||||
|
||||
# The trigger line is REMOVED, this should trigger
|
||||
set_original(excluding='The golden line')
|
||||
client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' in res.data
|
||||
|
||||
|
||||
# Now add it back, and we should not get a trigger
|
||||
client.get(url_for("mark_all_viewed"), follow_redirects=True)
|
||||
set_original(excluding=None)
|
||||
client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' not in res.data
|
||||
|
||||
# Remove it again, and we should get a trigger
|
||||
set_original(excluding='The golden line')
|
||||
client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' in res.data
|
||||
|
||||
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
|
||||
assert b'Deleted' in res.data
|
||||
|
||||
|
||||
def test_check_add_line_contains_trigger(client, live_server):
|
||||
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
# Give the endpoint time to spin up
|
||||
time.sleep(1)
|
||||
test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://') + "?xxx={{ watch_url }}"
|
||||
|
||||
res = client.post(
|
||||
url_for("settings_page"),
|
||||
data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
|
||||
"application-notification_body": 'triggered text was -{{triggered_text}}-',
|
||||
# https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
|
||||
"application-notification_urls": test_notification_url,
|
||||
"application-minutes_between_check": 180,
|
||||
"application-fetch_backend": "html_requests"
|
||||
},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b'Settings updated' in res.data
|
||||
|
||||
set_original()
|
||||
# Add our URL to the import page
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
res = client.post(
|
||||
url_for("import_page"),
|
||||
data={"urls": test_url},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"1 Imported" in res.data
|
||||
|
||||
# Give the thread time to pick it up
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
|
||||
# Goto the edit page, add our ignore text
|
||||
# Add our URL to the import page
|
||||
res = client.post(
|
||||
url_for("edit_page", uuid="first"),
|
||||
data={"trigger_text": 'Oh yes please',
|
||||
"url": test_url,
|
||||
'fetch_backend': "html_requests",
|
||||
'filter_text_removed': '',
|
||||
'filter_text_added': 'y'},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"Updated watch." in res.data
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
set_original(excluding='Something irrelevant')
|
||||
|
||||
# A line thats not the trigger should not trigger anything
|
||||
res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
assert b'1 watches queued for rechecking.' in res.data
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' not in res.data
|
||||
|
||||
# The trigger line is ADDED, this should trigger
|
||||
set_original(add_line='<p>Oh yes please</p>')
|
||||
client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' in res.data
|
||||
|
||||
with open("test-datastore/notification.txt", 'r') as f:
|
||||
response= f.read()
|
||||
assert '-Oh yes please-' in response
|
||||
|
||||
|
||||
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
|
||||
assert b'Deleted' in res.data
|
||||
@@ -87,7 +87,10 @@ def test_check_block_changedetection_text_NOT_present(client, live_server):
|
||||
# Add our URL to the import page
|
||||
res = client.post(
|
||||
url_for("edit_page", uuid="first"),
|
||||
data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
|
||||
data={"text_should_not_be_present": ignore_text,
|
||||
"url": test_url,
|
||||
'fetch_backend': "html_requests"
|
||||
},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"Updated watch." in res.data
|
||||
@@ -129,7 +132,6 @@ def test_check_block_changedetection_text_NOT_present(client, live_server):
|
||||
set_modified_response_minus_block_text()
|
||||
client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' in res.data
|
||||
|
||||
|
||||
@@ -198,8 +198,8 @@ def test_check_json_without_filter(client, live_server):
|
||||
)
|
||||
|
||||
# Should still see '"html": "<b>"'
|
||||
assert b'"<b>' in res.data
|
||||
assert res.data.count(b'{\n') >= 2
|
||||
assert b'"html": "<b>"' in res.data
|
||||
assert res.data.count(b'{') >= 2
|
||||
|
||||
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
|
||||
assert b'Deleted' in res.data
|
||||
|
||||
@@ -94,7 +94,6 @@ def test_unique_lines_functionality(client, live_server):
|
||||
res = client.get(url_for("index"))
|
||||
assert b'unviewed' not in res.data
|
||||
|
||||
|
||||
# Now set the content which contains the new text and re-ordered existing text
|
||||
set_modified_with_trigger_text_response()
|
||||
client.get(url_for("form_watch_checknow"), follow_redirects=True)
|
||||
|
||||
@@ -13,21 +13,37 @@ class TestDiffBuilder(unittest.TestCase):
|
||||
|
||||
def test_expected_diff_output(self):
|
||||
base_dir = os.path.dirname(__file__)
|
||||
output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after.txt")
|
||||
with open(base_dir + "/test-content/before.txt", 'r') as f:
|
||||
previous_version_file_contents = f.read()
|
||||
|
||||
with open(base_dir + "/test-content/after.txt", 'r') as f:
|
||||
newest_version_file_contents = f.read()
|
||||
|
||||
output = diff.render_diff(previous_version_file_contents=previous_version_file_contents,
|
||||
newest_version_file_contents=newest_version_file_contents)
|
||||
|
||||
output = output.split("\n")
|
||||
|
||||
|
||||
self.assertIn('(changed) ok', output)
|
||||
self.assertIn('(into) xok', output)
|
||||
self.assertIn('(into) next-x-ok', output)
|
||||
self.assertIn('(added) and something new', output)
|
||||
|
||||
|
||||
output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after-2.txt")
|
||||
with open(base_dir + "/test-content/after-2.txt", 'r') as f:
|
||||
newest_version_file_contents = f.read()
|
||||
output = diff.render_diff(previous_version_file_contents, newest_version_file_contents)
|
||||
output = output.split("\n")
|
||||
self.assertIn('(removed) for having learned computerese,', output)
|
||||
self.assertIn('(removed) I continue to examine bits, bytes and words', output)
|
||||
|
||||
#diff_removed
|
||||
output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after.txt", include_equal=False, include_removed=True, include_added=False)
|
||||
with open(base_dir + "/test-content/before.txt", 'r') as f:
|
||||
previous_version_file_contents = f.read()
|
||||
|
||||
with open(base_dir + "/test-content/after.txt", 'r') as f:
|
||||
newest_version_file_contents = f.read()
|
||||
output = diff.render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=False)
|
||||
output = output.split("\n")
|
||||
self.assertIn('(changed) ok', output)
|
||||
self.assertIn('(into) xok', output)
|
||||
@@ -35,7 +51,9 @@ class TestDiffBuilder(unittest.TestCase):
|
||||
self.assertNotIn('(added) and something new', output)
|
||||
|
||||
#diff_removed
|
||||
output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after-2.txt", include_equal=False, include_removed=True, include_added=False)
|
||||
with open(base_dir + "/test-content/after-2.txt", 'r') as f:
|
||||
newest_version_file_contents = f.read()
|
||||
output = diff.render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=False)
|
||||
output = output.split("\n")
|
||||
self.assertIn('(removed) for having learned computerese,', output)
|
||||
self.assertIn('(removed) I continue to examine bits, bytes and words', output)
|
||||
|
||||
@@ -69,18 +69,28 @@ class update_worker(threading.Thread):
|
||||
else:
|
||||
line_feed_sep = "\n"
|
||||
|
||||
with open(watch_history[dates[-1]], 'rb') as f:
|
||||
snapshot_contents = f.read()
|
||||
# Add text that was triggered
|
||||
snapshot_contents = watch.get_history_snapshot(dates[-1])
|
||||
trigger_text = watch.get('trigger_text', [])
|
||||
triggered_text = ''
|
||||
|
||||
if len(trigger_text):
|
||||
from . import html_tools
|
||||
triggered_text = html_tools.get_triggered_text(content=snapshot_contents, trigger_text=trigger_text)
|
||||
if triggered_text:
|
||||
triggered_text = line_feed_sep.join(triggered_text)
|
||||
|
||||
|
||||
n_object.update({
|
||||
'watch_url': watch['url'],
|
||||
'uuid': watch_uuid,
|
||||
'current_snapshot': snapshot_contents,
|
||||
'diff': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), line_feed_sep=line_feed_sep),
|
||||
'diff_added': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_removed=False, line_feed_sep=line_feed_sep),
|
||||
'diff_full': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_equal=True, line_feed_sep=line_feed_sep),
|
||||
'diff_removed': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_added=False, line_feed_sep=line_feed_sep),
|
||||
'screenshot': watch.get_screenshot() if watch.get('notification_screenshot') else None,
|
||||
'current_snapshot': snapshot_contents.decode('utf-8'),
|
||||
'diff': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], line_feed_sep=line_feed_sep),
|
||||
'diff_added': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], include_removed=False, line_feed_sep=line_feed_sep),
|
||||
'diff_removed': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], include_added=False, line_feed_sep=line_feed_sep),
|
||||
'diff_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], include_equal=True, line_feed_sep=line_feed_sep)
|
||||
'triggered_text': triggered_text,
|
||||
'uuid': watch_uuid,
|
||||
'watch_url': watch['url'],
|
||||
})
|
||||
logging.info (">> SENDING NOTIFICATION")
|
||||
self.notification_q.put(n_object)
|
||||
@@ -323,6 +333,7 @@ class update_worker(threading.Thread):
|
||||
|
||||
self.cleanup_error_artifacts(uuid)
|
||||
|
||||
#
|
||||
# Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
|
||||
if process_changedetection_results:
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user