admingit
/
Splunk_Deploiement
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

test_push_dashboards

Browse Source 
Pushed by: admin
License: RB02Z2FI66TO (Trial)
Timestamp: 2026-03-26T23:46:22.636894
masterdevtest
Splunk GitDeploy for Splunk 1 month ago
parent 6d5454448b
commit 24d19c99e3
483 changed files with 21 additions and 98463 deletions
Show Stats Download Patch File Download Diff File

0
apps/bitwarden_event_logs/README/script.conf.spec
Unescape View File

2
apps/bitwarden_event_logs/VERSION
Unescape View File

@ -1,2 +0,0 @@
2.1.0
2.1.0

54
apps/bitwarden_event_logs/app.manifest
Unescape View File

@ -1,54 +0,0 @@
{
"dependencies": null,
"incompatibleApps": null,
"info": {
"author": [
{
"company": "Bitwarden Inc.",
"email": "support@bitwarden.com",
"name": "Bitwarden Inc."
}
],
"classification": {
"categories": [],
"developmentStatus": null,
"intendedAudience": null
},
"commonInformationModels": null,
"description": "Bitwarden event logs integration into Splunk.",
"id": {
"group": null,
"name": "bitwarden_event_logs",
"version": "2.1.0"
},
"license": {
"name": null,
"text": null,
"uri": null
},
"privacyPolicy": {
"name": null,
"text": null,
"uri": null
},
"releaseDate": null,
"releaseNotes": {
"name": "README",
"text": "README.txt",
"uri": ""
},
"title": "Bitwarden Event Logs"
},
"inputGroups": null,
"platformRequirements": null,
"schemaVersion": "2.0.0",
"supportedDeployments": [
"_standalone",
"_distributed"
],
"targetWorkloads": [
"_search_heads",
"_indexers"
],
"tasks": null
}

0
apps/bitwarden_event_logs/appserver/static/setup/index.html
Unescape View File

0
apps/bitwarden_event_logs/appserver/static/setup/main.js
Unescape View File

0
apps/bitwarden_event_logs/appserver/static/setup/polyfills.js
Unescape View File

0
apps/bitwarden_event_logs/appserver/static/setup/runtime.js
Unescape View File

0
apps/bitwarden_event_logs/appserver/static/setup/scripts.js
Unescape View File

0
apps/bitwarden_event_logs/appserver/static/setup/styles.css
Unescape View File

0
apps/bitwarden_event_logs/bin/__init__.py
Unescape View File

BIN
apps/bitwarden_event_logs/bin/__pycache__/bitwarden_api.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/bin/__pycache__/config.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/bin/__pycache__/event_logs.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/bin/__pycache__/mappers.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/bin/__pycache__/models.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/bin/__pycache__/splunk_api.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/bin/__pycache__/utils.cpython-39.pyc
View File

Binary file not shown.

0
apps/bitwarden_event_logs/bin/bitwarden_api.py
Unescape View File

0
apps/bitwarden_event_logs/bin/bitwarden_event_logs.py
Unescape View File

0
apps/bitwarden_event_logs/bin/config.py
Unescape View File

0
apps/bitwarden_event_logs/bin/event_logs.py
Unescape View File

0
apps/bitwarden_event_logs/bin/mappers.py
Unescape View File

0
apps/bitwarden_event_logs/bin/models.py
Unescape View File

0
apps/bitwarden_event_logs/bin/splunk_api.py
Unescape View File

0
apps/bitwarden_event_logs/bin/utils.py
Unescape View File

0
apps/bitwarden_event_logs/default/app.conf
Unescape View File

6
apps/bitwarden_event_logs/default/collections.conf
Unescape View File

@ -1,6 +0,0 @@
[eventsapi]
enforceTypes = true
field.next_request.start = string
field.next_request.end = string
field.next_request.continuation_token = string
field.last_log_date = string

0
apps/bitwarden_event_logs/default/data/ui/nav/default.xml
Unescape View File

147
apps/bitwarden_event_logs/default/data/ui/views/authentication_events_dashboard.xml
Unescape View File

@ -1,147 +0,0 @@
<form version="1.1">
<label>Bitwarden Authentication Events</label>
<fieldset submitButton="false" autoRun="false">
<input type="time" token="timeframe">
<label>Timeframe</label>
<default>
<earliest>-24h@h</earliest>
<latest>now</latest>
</default>
</input>
<input type="dropdown" token="top_users_by">
<label>Top Users By</label>
<default>User Email</default>
<choice value="actingUserId">User ID</choice>
<choice value="actingUserEmail">User Email</choice>
<choice value="actingUserName">User Name</choice>
</input>
</fieldset>
<row>
<panel>
<map>
<title>Successful Log In Attempts</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" type=1000 | iplocation ipAddress | lookup geo_countries longitude as lon, latitude as lat | stats count by Country | geom geo_countries featureIdField=Country</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="drilldown">none</option>
<option name="mapping.choroplethLayer.colorBins">5</option>
<option name="mapping.choroplethLayer.colorMode">auto</option>
<option name="mapping.choroplethLayer.maximumColor">0x53a051</option>
<option name="mapping.map.center">(55.97,-40.69)</option>
<option name="mapping.map.zoom">3</option>
<option name="mapping.type">choropleth</option>
</map>
</panel>
</row>
<row>
<panel>
<chart>
<title>Authentication Events by Device</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" (type=1000 OR type=1001 OR type=1002 OR type=1003 OR type=1004 OR type=1005 OR type=1006 OR type=1008 OR type=1009) | timechart count by deviceName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">line</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
<panel>
<chart>
<title>Authentication Events by Type</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" (type=1000 OR type=1001 OR type=1002 OR type=1003 OR type=1004 OR type=1005 OR type=1006 OR type=1008 OR type=1009) | timechart count by typeName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">line</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<title>Authentication Events by Device</title>
<chart>
<title>Device</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" (type=1000 OR type=1001 OR type=1002 OR type=1003 OR type=1004 OR type=1005 OR type=1006 OR type=1008 OR type=1009) | stats count by deviceName</query>
<earliest>-24h@h</earliest>
<latest>now</latest>
</search>
<option name="charting.chart">pie</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
<panel>
<title>Authentication Events by Type</title>
<chart>
<title>Type</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" (type=1000 OR type=1001 OR type=1002 OR type=1003 OR type=1004 OR type=1005 OR type=1006 OR type=1008 OR type=1009) | stats count by typeName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">pie</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<chart>
<title>Top Failed Log In Attempts</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" (type=1005 OR type=1006) | stats count by $top_users_by$ | sort - count</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.axisLabelsX.majorLabelStyle.rotation">45</option>
<option name="charting.axisTitleX.text">Acting User</option>
<option name="charting.chart">column</option>
<option name="charting.chart.showDataLabels">all</option>
<option name="charting.chart.stackMode">default</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<chart>
<title>Top Successful Log In Attempts</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" type=1000 | stats count by $top_users_by$ | sort - count</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.axisLabelsX.majorLabelStyle.rotation">45</option>
<option name="charting.axisTitleX.text">Acting User</option>
<option name="charting.chart">column</option>
<option name="charting.chart.stackMode">default</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<event>
<title>Latest Authentication Events</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" (type=1000 OR type=1001 OR type=1002 OR type=1003 OR type=1004 OR type=1005 OR type=1006 OR type=1008 OR type=1009)
</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="list.drilldown">none</option>
</event>
</panel>
</row>
</form>

1
apps/bitwarden_event_logs/default/data/ui/views/configuration.xml
Unescape View File

@ -2,3 +2,4 @@
<view template="bitwarden_event_logs:/templates/base.html" type="html" isDashboard="False"> <view template="bitwarden_event_logs:/templates/base.html" type="html" isDashboard="False">
<label>Configuration</label> <label>Configuration</label>
</view> </view>
#test

126
apps/bitwarden_event_logs/default/data/ui/views/organization_events_dashboard.xml
Unescape View File

@ -1,126 +0,0 @@
<form version="1.1">
<label>Bitwarden Organization Events</label>
<fieldset submitButton="false" autoRun="false">
<input type="time" token="timeframe">
<label>Timeframe</label>
<default>
<earliest>-24h@h</earliest>
<latest>now</latest>
</default>
</input>
<input type="dropdown" token="top_users_by">
<label>Top Users By</label>
<default>User Email</default>
<choice value="actingUserId">User ID</choice>
<choice value="actingUserEmail">User Email</choice>
<choice value="actingUserName">User Name</choice>
</input>
</fieldset>
<row>
<panel>
<map>
<title>Organization Events</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]> | iplocation ipAddress | lookup geo_countries longitude as lon, latitude as lat | stats count by Country | geom geo_countries featureIdField=Country</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="drilldown">none</option>
<option name="mapping.choroplethLayer.colorBins">5</option>
<option name="mapping.choroplethLayer.colorMode">auto</option>
<option name="mapping.choroplethLayer.maximumColor">0x53a051</option>
<option name="mapping.map.center">(55.97,-40.69)</option>
<option name="mapping.map.zoom">3</option>
<option name="mapping.type">choropleth</option>
<option name="refresh.display">progressbar</option>
</map>
</panel>
</row>
<row>
<panel>
<chart>
<title>Organization Events by Device</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]> | timechart count by deviceName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">line</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
<panel>
<chart>
<title>Organization Events by Type</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]> | timechart count by typeName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>&gt;</search>
<option name="charting.chart">line</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<title>Organization Events by Device</title>
<chart>
<title>Device</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]> | stats count by deviceName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">pie</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
<panel>
<title>Organization Events by Type</title>
<chart>
<title>Type</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]> | stats count by typeName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">pie</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<chart>
<title>Top Organization Event Users</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]> | stats count by $top_users_by$ | sort - count</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.axisLabelsX.majorLabelStyle.rotation">90</option>
<option name="charting.axisTitleX.text">Acting User</option>
<option name="charting.chart">column</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<event>
<title>Latest Organization Events</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1300 AND type<1800)]]></query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="list.drilldown">none</option>
</event>
</panel>
</row>
</form>

13
apps/bitwarden_event_logs/default/data/ui/views/setup_page_dashboard.xml
Unescape View File

@ -1,13 +0,0 @@
<dashboard isDashboard="false"
script="setup/runtime.js,setup/polyfills.js,setup/scripts.js,setup/main.js"
stylesheet="setup/styles.css"
version="1.1">
<label>Setup</label>
<row>
<panel>
<html>
<div id="app-root"></div>
</html>
</panel>
</row>
</dashboard>

127
apps/bitwarden_event_logs/default/data/ui/views/vault_item_events_dashboard.xml
Unescape View File

@ -1,127 +0,0 @@
<form version="1.1">
<label>Bitwarden Vault Item Events</label>
<fieldset submitButton="false" autoRun="false">
<input type="time" token="timeframe">
<label>Timeframe</label>
<default>
<earliest>-24h@h</earliest>
<latest>now</latest>
</default>
</input>
<input type="dropdown" token="top_users_by">
<label>Top Users By</label>
<default>User Email</default>
<choice value="actingUserId">User ID</choice>
<choice value="actingUserEmail">User Email</choice>
<choice value="actingUserName">User Name</choice>
</input>
</fieldset>
<row>
<panel>
<map>
<title>Vault Item Events</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]> | iplocation ipAddress | lookup geo_countries longitude as lon, latitude as lat | stats count by Country | geom geo_countries featureIdField=Country</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="drilldown">none</option>
<option name="mapping.choroplethLayer.colorBins">5</option>
<option name="mapping.choroplethLayer.colorMode">auto</option>
<option name="mapping.choroplethLayer.maximumColor">0x53a051</option>
<option name="mapping.map.center">(55.97,-40.69)</option>
<option name="mapping.map.zoom">3</option>
<option name="mapping.type">choropleth</option>
<option name="refresh.display">progressbar</option>
</map>
</panel>
</row>
<row>
<panel>
<chart>
<title>Vault Item Events by Device</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]> | timechart count by deviceName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">line</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
<panel>
<chart>
<title>Vault Item Events by Type</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]> | timechart count by typeName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>&gt;</search>
<option name="charting.chart">line</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<title>Vault Item Events by Device</title>
<chart>
<title>Device</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]> | stats count by deviceName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">pie</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
<panel>
<title>Vault Item Events by Type</title>
<chart>
<title>Type</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]> | stats count by typeName</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.chart">pie</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<chart>
<title>Top Vault Item Event Users</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]> | stats count by $top_users_by$ | sort - count</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="charting.axisLabelsX.majorLabelStyle.rotation">90</option>
<option name="charting.axisTitleX.text">Acting User</option>
<option name="charting.chart">column</option>
<option name="charting.drilldown">none</option>
<option name="refresh.display">progressbar</option>
</chart>
</panel>
</row>
<row>
<panel>
<event>
<title>Latest Vault Item Events</title>
<search>
<query>`bitwarden_event_logs_index` sourcetype="bitwarden:events" <![CDATA[(type>=1100 AND type<1200)]]>
</query>
<earliest>$timeframe.earliest$</earliest>
<latest>$timeframe.latest$</latest>
</search>
<option name="list.drilldown">none</option>
</event>
</panel>
</row>
</form>

6
apps/bitwarden_event_logs/default/inputs.conf
Unescape View File

@ -1,6 +0,0 @@
[script://$SPLUNK_HOME/etc/apps/bitwarden_event_logs/bin/bitwarden_event_logs.py]
interval = 60
sourcetype = bitwarden:events
index = main
passAuth = splunk-system-user
python.version = python3

2
apps/bitwarden_event_logs/default/macros.conf
Unescape View File

@ -1,2 +0,0 @@
[bitwarden_event_logs_index]
definition=index=*

138
apps/bitwarden_event_logs/default/props.conf
Unescape View File

@ -1,138 +0,0 @@
[bitwarden:events]
LINE_BREAKER = ([\r\n])
SHOULD_LINEMERGE = false
TRUNCATE = 5000
KV_MODE = json
FIELDALIAS-alias_1 = ipAddress AS src
FIELDALIAS-alias_2 = date AS timestamp
EVAL-typeName = coalesce(case(\
type==1000,"User_LoggedIn",\
type==1001,"User_ChangedPassword",\
type==1002,"User_Updated2fa",\
type==1003,"User_Disabled2fa",\
type==1004,"User_Recovered2fa",\
type==1005,"User_FailedLogIn",\
type==1006,"User_FailedLogIn2fa",\
type==1007,"User_ClientExportedVault",\
type==1008,"User_UpdatedTempPassword",\
type==1009,"User_MigratedKeyToKeyConnector",\
type==1010,"User_RequestedDeviceApproval",\
type==1011,"User_TdeOffboardingPasswordSet",\
type==1100,"Cipher_Created",\
type==1101,"Cipher_Updated",\
type==1102,"Cipher_Deleted",\
type==1103,"Cipher_AttachmentCreated",\
type==1104,"Cipher_AttachmentDeleted",\
type==1105,"Cipher_Shared",\
type==1106,"Cipher_UpdatedCollections",\
type==1107,"Cipher_ClientViewed",\
type==1108,"Cipher_ClientToggledPasswordVisible",\
type==1109,"Cipher_ClientToggledHiddenFieldVisible",\
type==1110,"Cipher_ClientToggledCardCodeVisible",\
type==1111,"Cipher_ClientCopiedPassword",\
type==1112,"Cipher_ClientCopiedHiddenField",\
type==1113,"Cipher_ClientCopiedCardCode",\
type==1114,"Cipher_ClientAutofilled",\
type==1115,"Cipher_SoftDeleted",\
type==1116,"Cipher_Restored",\
type==1117,"Cipher_ClientToggledCardNumberVisible",\
type==1300,"Collection_Created",\
type==1301,"Collection_Updated",\
type==1302,"Collection_Deleted",\
type==1400,"Group_Created",\
type==1401,"Group_Updated",\
type==1402,"Group_Deleted",\
type==1500,"OrganizationUser_Invited",\
type==1501,"OrganizationUser_Confirmed",\
type==1502,"OrganizationUser_Updated",\
type==1503,"OrganizationUser_Removed",\
type==1504,"OrganizationUser_UpdatedGroups",\
type==1505,"OrganizationUser_UnlinkedSso",\
type==1506,"OrganizationUser_ResetPassword_Enroll",\
type==1507,"OrganizationUser_ResetPassword_Withdraw",\
type==1508,"OrganizationUser_AdminResetPassword",\
type==1509,"OrganizationUser_ResetSsoLink",\
type==1510,"OrganizationUser_FirstSsoLogin",\
type==1511,"OrganizationUser_Revoked",\
type==1512,"OrganizationUser_Restored",\
type==1513,"OrganizationUser_ApprovedAuthRequest",\
type==1514,"OrganizationUser_RejectedAuthRequest",\
type==1515,"OrganizationUser_Deleted",\
type==1516,"OrganizationUser_Left",\
type==1517,"OrganizationUser_AutomaticallyConfirmed",\
type==1600,"Organization_Updated",\
type==1601,"Organization_PurgedVault",\
type==1602,"Organization_ClientExportedVault",\
type==1603,"Organization_VaultAccessed",\
type==1604,"Organization_EnabledSso",\
type==1605,"Organization_DisabledSso",\
type==1606,"Organization_EnabledKeyConnector",\
type==1607,"Organization_DisabledKeyConnector",\
type==1608,"Organization_SponsorshipsSynced",\
type==1609,"Organization_CollectionManagement_Updated",\
type==1610,"Organization_CollectionManagement_LimitCollectionCreationEnabled",\
type==1611,"Organization_CollectionManagement_LimitCollectionCreationDisabled",\
type==1612,"Organization_CollectionManagement_LimitCollectionDeletionEnabled",\
type==1613,"Organization_CollectionManagement_LimitCollectionDeletionDisabled",\
type==1614,"Organization_CollectionManagement_LimitItemDeletionEnabled",\
type==1615,"Organization_CollectionManagement_LimitItemDeletionDisabled",\
type==1616,"Organization_CollectionManagement_AllowAdminAccessToAllCollectionItemsEnabled",\
type==1617,"Organization_CollectionManagement_AllowAdminAccessToAllCollectionItemsDisabled",\
type==1620,"Organization_AutoConfirmEnabled_Admin",\
type==1621,"Organization_AutoConfirmDisabled_Admin",\
type==1622,"Organization_AutoConfirmEnabled_Portal",\
type==1623,"Organization_AutoConfirmDisabled_Portal",\
type==1700,"Policy_Updated",\
type==1800,"ProviderUser_Invited",\
type==1801,"ProviderUser_Confirmed",\
type==1802,"ProviderUser_Updated",\
type==1803,"ProviderUser_Removed",\
type==1900,"ProviderOrganization_Created",\
type==1901,"ProviderOrganization_Added",\
type==1902,"ProviderOrganization_Removed",\
type==1903,"ProviderOrganization_VaultAccessed",\
type==2000,"OrganizationDomain_Added",\
type==2001,"OrganizationDomain_Removed",\
type==2002,"OrganizationDomain_Verified",\
type==2003,"OrganizationDomain_NotVerified",\
type==2100,"Secret_Retrieved",\
type==2101,"Secret_Created",\
type==2102,"Secret_Edited",\
type==2103,"Secret_Deleted",\
type==2104,"Secret_Permanently_Deleted",\
type==2105,"Secret_Restored",\
type==2200,"Project_Retrieved",\
type==2201,"Project_Created",\
type==2202,"Project_Edited",\
type==2203,"Project_Deleted"\
), type)
EVAL-deviceName = coalesce(case(device==0,"Android",\
device==1,"iOS",\
device==2,"Chrome Extension",\
device==3,"Firefox Extension",\
device==4,"Opera Extension",\
device==5,"Edge Extension",\
device==6,"Windows Desktop",\
device==7,"macOS Desktop",\
device==8,"Linux Desktop",\
device==9,"Chrome Browser",\
device==10,"Firefox Browser",\
device==11,"Opera Browser",\
device==12,"Edge Browser",\
device==13,"IEBrowser",\
device==14,"Unknown Browser",\
device==15,"Android Amazon",\
device==16,"UWP",\
device==17,"Safari Browser",\
device==18,"Vivaldi Browser",\
device==19,"Vivaldi Extension",\
device==20,"Safari Extension",\
device==21,"SDK",\
device==22,"Server",\
device==23,"Windows CLI",\
device==24,"MacOs CLI",\
device==25,"Linux CLI",\
device==26,"DuckDuckGo"\
), device)
TIME_PREFIX = "date":"
TIME_FORMAT = %Y-%m-%dT%H:%M:%S.%6N%Z

4
apps/bitwarden_event_logs/default/script.conf
Unescape View File

@ -1,4 +0,0 @@
[config]
apiUrl=https://api.bitwarden.com
identityUrl=https://identity.bitwarden.com
loggingLevel=INFO

3
apps/bitwarden_event_logs/default/server.conf
Unescape View File

@ -1,3 +0,0 @@
[shclustering]
conf_replication_include.script = true

1
apps/bitwarden_event_logs/lib/PySocks-1.7.1.dist-info/INSTALLER
Unescape View File

@ -1 +0,0 @@
pip

22
apps/bitwarden_event_logs/lib/PySocks-1.7.1.dist-info/LICENSE
Unescape View File

@ -1,22 +0,0 @@
Copyright 2006 Dan-Haim. All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. Neither the name of Dan Haim nor the names of his contributors may be used
to endorse or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY DAN HAIM "AS IS" AND ANY EXPRESS OR IMPLIED
WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
EVENT SHALL DAN HAIM OR HIS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA
OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMANGE.

321
apps/bitwarden_event_logs/lib/PySocks-1.7.1.dist-info/METADATA
Unescape View File

@ -1,321 +0,0 @@
Metadata-Version: 2.1
Name: PySocks
Version: 1.7.1
Summary: A Python SOCKS client module. See https://github.com/Anorov/PySocks for more information.
Home-page: https://github.com/Anorov/PySocks
Author: Anorov
Author-email: anorov.vorona@gmail.com
License: BSD
Keywords: socks,proxy
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.4
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*
Description-Content-Type: text/markdown
PySocks
=======
PySocks lets you send traffic through SOCKS and HTTP proxy servers. It is a modern fork of [SocksiPy](http://socksipy.sourceforge.net/) with bug fixes and extra features.
Acts as a drop-in replacement to the socket module. Seamlessly configure SOCKS proxies for any socket object by calling `socket_object.set_proxy()`.
----------------
Features
========
* SOCKS proxy client for Python 2.7 and 3.4+
* TCP supported
* UDP mostly supported (issues may occur in some edge cases)
* HTTP proxy client included but not supported or recommended (you should use urllib2's or requests' own HTTP proxy interface)
* urllib2 handler included. `pip install` / `setup.py install` will automatically install the `sockshandler` module.
Installation
============
pip install PySocks
Or download the tarball / `git clone` and...
python setup.py install
These will install both the `socks` and `sockshandler` modules.
Alternatively, include just `socks.py` in your project.
--------------------------------------------
*Warning:* PySocks/SocksiPy only supports HTTP proxies that use CONNECT tunneling. Certain HTTP proxies may not work with this library. If you wish to use HTTP (not SOCKS) proxies, it is recommended that you rely on your HTTP client's native proxy support (`proxies` dict for `requests`, or `urllib2.ProxyHandler` for `urllib2`) instead.
--------------------------------------------
Usage
=====
## socks.socksocket ##
import socks
s = socks.socksocket() # Same API as socket.socket in the standard lib
s.set_proxy(socks.SOCKS5, "localhost") # SOCKS4 and SOCKS5 use port 1080 by default
# Or
s.set_proxy(socks.SOCKS4, "localhost", 4444)
# Or
s.set_proxy(socks.HTTP, "5.5.5.5", 8888)
# Can be treated identical to a regular socket object
s.connect(("www.somesite.com", 80))
s.sendall("GET / HTTP/1.1 ...")
print s.recv(4096)
## Monkeypatching ##
To monkeypatch the entire standard library with a single default proxy:
import urllib2
import socket
import socks
socks.set_default_proxy(socks.SOCKS5, "localhost")
socket.socket = socks.socksocket
urllib2.urlopen("http://www.somesite.com/") # All requests will pass through the SOCKS proxy
Note that monkeypatching may not work for all standard modules or for all third party modules, and generally isn't recommended. Monkeypatching is usually an anti-pattern in Python.
## urllib2 Handler ##
Example use case with the `sockshandler` urllib2 handler. Note that you must import both `socks` and `sockshandler`, as the handler is its own module separate from PySocks. The module is included in the PyPI package.
import urllib2
import socks
from sockshandler import SocksiPyHandler
opener = urllib2.build_opener(SocksiPyHandler(socks.SOCKS5, "127.0.0.1", 9050))
print opener.open("http://www.somesite.com/") # All requests made by the opener will pass through the SOCKS proxy
--------------------------------------------
Original SocksiPy README attached below, amended to reflect API changes.
--------------------------------------------
SocksiPy
A Python SOCKS module.
(C) 2006 Dan-Haim. All rights reserved.
See LICENSE file for details.
*WHAT IS A SOCKS PROXY?*
A SOCKS proxy is a proxy server at the TCP level. In other words, it acts as
a tunnel, relaying all traffic going through it without modifying it.
SOCKS proxies can be used to relay traffic using any network protocol that
uses TCP.
*WHAT IS SOCKSIPY?*
This Python module allows you to create TCP connections through a SOCKS
proxy without any special effort.
It also supports relaying UDP packets with a SOCKS5 proxy.
*PROXY COMPATIBILITY*
SocksiPy is compatible with three different types of proxies:
1. SOCKS Version 4 (SOCKS4), including the SOCKS4a extension.
2. SOCKS Version 5 (SOCKS5).
3. HTTP Proxies which support tunneling using the CONNECT method.
*SYSTEM REQUIREMENTS*
Being written in Python, SocksiPy can run on any platform that has a Python
interpreter and TCP/IP support.
This module has been tested with Python 2.3 and should work with greater versions
just as well.
INSTALLATION
-------------
Simply copy the file "socks.py" to your Python's `lib/site-packages` directory,
and you're ready to go. [Editor's note: it is better to use `python setup.py install` for PySocks]
USAGE
------
First load the socks module with the command:
>>> import socks
>>>
The socks module provides a class called `socksocket`, which is the base to all of the module's functionality.
The `socksocket` object has the same initialization parameters as the normal socket
object to ensure maximal compatibility, however it should be noted that `socksocket` will only function with family being `AF_INET` and
type being either `SOCK_STREAM` or `SOCK_DGRAM`.
Generally, it is best to initialize the `socksocket` object with no parameters
>>> s = socks.socksocket()
>>>
The `socksocket` object has an interface which is very similiar to socket's (in fact
the `socksocket` class is derived from socket) with a few extra methods.
To select the proxy server you would like to use, use the `set_proxy` method, whose
syntax is:
set_proxy(proxy_type, addr[, port[, rdns[, username[, password]]]])
Explanation of the parameters:
`proxy_type` - The type of the proxy server. This can be one of three possible
choices: `PROXY_TYPE_SOCKS4`, `PROXY_TYPE_SOCKS5` and `PROXY_TYPE_HTTP` for SOCKS4,
SOCKS5 and HTTP servers respectively. `SOCKS4`, `SOCKS5`, and `HTTP` are all aliases, respectively.
`addr` - The IP address or DNS name of the proxy server.
`port` - The port of the proxy server. Defaults to 1080 for socks and 8080 for http.
`rdns` - This is a boolean flag than modifies the behavior regarding DNS resolving.
If it is set to True, DNS resolving will be preformed remotely, on the server.
If it is set to False, DNS resolving will be preformed locally. Please note that
setting this to True with SOCKS4 servers actually use an extension to the protocol,
called SOCKS4a, which may not be supported on all servers (SOCKS5 and http servers
always support DNS). The default is True.
`username` - For SOCKS5 servers, this allows simple username / password authentication
with the server. For SOCKS4 servers, this parameter will be sent as the userid.
This parameter is ignored if an HTTP server is being used. If it is not provided,
authentication will not be used (servers may accept unauthenticated requests).
`password` - This parameter is valid only for SOCKS5 servers and specifies the
respective password for the username provided.
Example of usage:
>>> s.set_proxy(socks.SOCKS5, "socks.example.com") # uses default port 1080
>>> s.set_proxy(socks.SOCKS4, "socks.test.com", 1081)
After the set_proxy method has been called, simply call the connect method with the
traditional parameters to establish a connection through the proxy:
>>> s.connect(("www.sourceforge.net", 80))
>>>
Connection will take a bit longer to allow negotiation with the proxy server.
Please note that calling connect without calling `set_proxy` earlier will connect
without a proxy (just like a regular socket).
Errors: Any errors in the connection process will trigger exceptions. The exception
may either be generated by the underlying socket layer or may be custom module
exceptions, whose details follow:
class `ProxyError` - This is a base exception class. It is not raised directly but
rather all other exception classes raised by this module are derived from it.
This allows an easy way to catch all proxy-related errors. It descends from `IOError`.
All `ProxyError` exceptions have an attribute `socket_err`, which will contain either a
caught `socket.error` exception, or `None` if there wasn't any.
class `GeneralProxyError` - When thrown, it indicates a problem which does not fall
into another category.
* `Sent invalid data` - This error means that unexpected data has been received from
the server. The most common reason is that the server specified as the proxy is
not really a SOCKS4/SOCKS5/HTTP proxy, or maybe the proxy type specified is wrong.
* `Connection closed unexpectedly` - The proxy server unexpectedly closed the connection.
This may indicate that the proxy server is experiencing network or software problems.
* `Bad proxy type` - This will be raised if the type of the proxy supplied to the
set_proxy function was not one of `SOCKS4`/`SOCKS5`/`HTTP`.
* `Bad input` - This will be raised if the `connect()` method is called with bad input
parameters.
class `SOCKS5AuthError` - This indicates that the connection through a SOCKS5 server
failed due to an authentication problem.
* `Authentication is required` - This will happen if you use a SOCKS5 server which
requires authentication without providing a username / password at all.
* `All offered authentication methods were rejected` - This will happen if the proxy
requires a special authentication method which is not supported by this module.
* `Unknown username or invalid password` - Self descriptive.
class `SOCKS5Error` - This will be raised for SOCKS5 errors which are not related to
authentication.
The parameter is a tuple containing a code, as given by the server,
and a description of the
error. The possible errors, according to the RFC, are:
* `0x01` - General SOCKS server failure - If for any reason the proxy server is unable to
fulfill your request (internal server error).
* `0x02` - connection not allowed by ruleset - If the address you're trying to connect to
is blacklisted on the server or requires authentication.
* `0x03` - Network unreachable - The target could not be contacted. A router on the network
had replied with a destination net unreachable error.
* `0x04` - Host unreachable - The target could not be contacted. A router on the network
had replied with a destination host unreachable error.
* `0x05` - Connection refused - The target server has actively refused the connection
(the requested port is closed).
* `0x06` - TTL expired - The TTL value of the SYN packet from the proxy to the target server
has expired. This usually means that there are network problems causing the packet
to be caught in a router-to-router "ping-pong".
* `0x07` - Command not supported - For instance if the server does not support UDP.
* `0x08` - Address type not supported - The client has provided an invalid address type.
When using this module, this error should not occur.
class `SOCKS4Error` - This will be raised for SOCKS4 errors. The parameter is a tuple
containing a code and a description of the error, as given by the server. The
possible error, according to the specification are:
* `0x5B` - Request rejected or failed - Will be raised in the event of an failure for any
reason other then the two mentioned next.
* `0x5C` - request rejected because SOCKS server cannot connect to identd on the client -
The Socks server had tried an ident lookup on your computer and has failed. In this
case you should run an identd server and/or configure your firewall to allow incoming
connections to local port 113 from the remote server.
* `0x5D` - request rejected because the client program and identd report different user-ids -
The Socks server had performed an ident lookup on your computer and has received a
different userid than the one you have provided. Change your userid (through the
username parameter of the set_proxy method) to match and try again.
class `HTTPError` - This will be raised for HTTP errors. The message will contain
the HTTP status code and provided error message.
After establishing the connection, the object behaves like a standard socket.
Methods like `makefile()` and `settimeout()` should behave just like regular sockets.
Call the `close()` method to close the connection.
In addition to the `socksocket` class, an additional function worth mentioning is the
`set_default_proxy` function. The parameters are the same as the `set_proxy` method.
This function will set default proxy settings for newly created `socksocket` objects,
in which the proxy settings haven't been changed via the `set_proxy` method.
This is quite useful if you wish to force 3rd party modules to use a SOCKS proxy,
by overriding the socket object.
For example:
>>> socks.set_default_proxy(socks.SOCKS5, "socks.example.com")
>>> socket.socket = socks.socksocket
>>> urllib.urlopen("http://www.sourceforge.net/")
PROBLEMS
---------
Please open a GitHub issue at https://github.com/Anorov/PySocks

9
apps/bitwarden_event_logs/lib/PySocks-1.7.1.dist-info/RECORD
Unescape View File

@ -1,9 +0,0 @@
PySocks-1.7.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
PySocks-1.7.1.dist-info/LICENSE,sha256=cCfiFOAU63i3rcwc7aWspxOnn8T2oMUsnaWz5wfm_-k,1401
PySocks-1.7.1.dist-info/METADATA,sha256=zbQMizjPOOP4DhEiEX24XXjNrYuIxF9UGUpN0uFDB6Y,13235
PySocks-1.7.1.dist-info/RECORD,,
PySocks-1.7.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
PySocks-1.7.1.dist-info/WHEEL,sha256=t_MpApv386-8PVts2R6wsTifdIn0vbUDTVv61IbqFC8,92
PySocks-1.7.1.dist-info/top_level.txt,sha256=TKSOIfCFBoK9EY8FBYbYqC3PWd3--G15ph9n8-QHPDk,19
socks.py,sha256=xOYn27t9IGrbTBzWsUUuPa0YBuplgiUykzkOB5V5iFY,31086
sockshandler.py,sha256=2SYGj-pwt1kjgLoZAmyeaEXCeZDWRmfVS_QG6kErGtY,3966

0
apps/bitwarden_event_logs/lib/PySocks-1.7.1.dist-info/REQUESTED
Unescape View File

5
apps/bitwarden_event_logs/lib/PySocks-1.7.1.dist-info/WHEEL
Unescape View File

@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.33.3)
Root-Is-Purelib: true
Tag: py3-none-any

BIN
apps/bitwarden_event_logs/lib/__pycache__/six.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/__pycache__/socks.cpython-39.pyc
View File

Binary file not shown.

6
apps/bitwarden_event_logs/lib/bin/normalizer
Unescape View File

@ -1,6 +0,0 @@
#!/home/runner/.cache/pypoetry/virtualenvs/bitwarden-event-logs-tER4sFWd-py3.9/bin/python3
import sys
from charset_normalizer.cli import cli_detect
if __name__ == '__main__':
sys.argv[0] = sys.argv[0].removesuffix('.exe')
sys.exit(cli_detect())

1
apps/bitwarden_event_logs/lib/certifi-2025.11.12.dist-info/INSTALLER
Unescape View File

@ -1 +0,0 @@
pip

78
apps/bitwarden_event_logs/lib/certifi-2025.11.12.dist-info/METADATA
Unescape View File

@ -1,78 +0,0 @@
Metadata-Version: 2.4
Name: certifi
Version: 2025.11.12
Summary: Python package for providing Mozilla's CA Bundle.
Home-page: https://github.com/certifi/python-certifi
Author: Kenneth Reitz
Author-email: me@kennethreitz.com
License: MPL-2.0
Project-URL: Source, https://github.com/certifi/python-certifi
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
Classifier: Natural Language :: English
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Python: >=3.7
License-File: LICENSE
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-python
Dynamic: summary
Certifi: Python SSL Certificates
================================
Certifi provides Mozilla's carefully curated collection of Root Certificates for
validating the trustworthiness of SSL certificates while verifying the identity
of TLS hosts. It has been extracted from the `Requests`_ project.
Installation
------------
``certifi`` is available on PyPI. Simply install it with ``pip``::
$ pip install certifi
Usage
-----
To reference the installed certificate authority (CA) bundle, you can use the
built-in function::
>>> import certifi
>>> certifi.where()
'/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
Or from the command line::
$ python -m certifi
/usr/local/lib/python3.7/site-packages/certifi/cacert.pem
Enjoy!
.. _`Requests`: https://requests.readthedocs.io/en/master/
Addition/Removal of Certificates
--------------------------------
Certifi does not support any addition/removal or other modification of the
CA trust store content. This project is intended to provide a reliable and
highly portable root of trust to python deployments. Look to upstream projects
for methods to use alternate trust.

12
apps/bitwarden_event_logs/lib/certifi-2025.11.12.dist-info/RECORD
Unescape View File

@ -1,12 +0,0 @@
certifi-2025.11.12.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
certifi-2025.11.12.dist-info/METADATA,sha256=_JprGu_1lWSdHlruRBKcorXnrfvBDhvX_6KRr8HQbLc,2475
certifi-2025.11.12.dist-info/RECORD,,
certifi-2025.11.12.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
certifi-2025.11.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
certifi-2025.11.12.dist-info/licenses/LICENSE,sha256=6TcW2mucDVpKHfYP5pWzcPBpVgPSH2-D8FPkLPwQyvc,989
certifi-2025.11.12.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
certifi/__init__.py,sha256=1BRSxNMnZW7CZ2oJtYWLoJgfHfcB9i273exwiPwfjJM,94
certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
certifi/cacert.pem,sha256=oa1dZD4hxDtb7XTH4IkdzbWPavUcis4eTwINZUqlKhY,283932
certifi/core.py,sha256=XFXycndG5pf37ayeF8N32HUuDafsyhkVMbO4BAPWHa0,3394
certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

0
apps/bitwarden_event_logs/lib/certifi-2025.11.12.dist-info/REQUESTED
Unescape View File

5
apps/bitwarden_event_logs/lib/certifi-2025.11.12.dist-info/WHEEL
Unescape View File

@ -1,5 +0,0 @@
Wheel-Version: 1.0
Generator: setuptools (80.9.0)
Root-Is-Purelib: true
Tag: py3-none-any

20
apps/bitwarden_event_logs/lib/certifi-2025.11.12.dist-info/licenses/LICENSE
Unescape View File

@ -1,20 +0,0 @@
This package contains a modified version of ca-bundle.crt:
ca-bundle.crt -- Bundle of CA Root Certificates
This is a bundle of X.509 certificates of public Certificate Authorities
(CA). These were automatically extracted from Mozilla's root certificates
file (certdata.txt). This file can be found in the mozilla source tree:
https://hg.mozilla.org/mozilla-central/file/tip/security/nss/lib/ckfw/builtins/certdata.txt
It contains the certificates in PEM format and therefore
can be directly used with curl / libcurl / php_curl, or with
an Apache+mod_ssl webserver for SSL client authentication.
Just configure this file as the SSLCACertificateFile.#
***** BEGIN LICENSE BLOCK *****
This Source Code Form is subject to the terms of the Mozilla Public License,
v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
one at http://mozilla.org/MPL/2.0/.
***** END LICENSE BLOCK *****
@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

4
apps/bitwarden_event_logs/lib/certifi/__init__.py
Unescape View File

@ -1,4 +0,0 @@
from .core import contents, where
__all__ = ["contents", "where"]
__version__ = "2025.11.12"

12
apps/bitwarden_event_logs/lib/certifi/__main__.py
Unescape View File

@ -1,12 +0,0 @@
import argparse
from certifi import contents, where
parser = argparse.ArgumentParser()
parser.add_argument("-c", "--contents", action="store_true")
args = parser.parse_args()
if args.contents:
print(contents())
else:
print(where())

BIN
apps/bitwarden_event_logs/lib/certifi/__pycache__/__init__.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/certifi/__pycache__/core.cpython-39.pyc
View File

Binary file not shown.

4678
apps/bitwarden_event_logs/lib/certifi/cacert.pem
View File

File diff suppressed because it is too large Load Diff

83
apps/bitwarden_event_logs/lib/certifi/core.py
Unescape View File

@ -1,83 +0,0 @@
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem or its contents.
"""
import sys
import atexit
def exit_cacert_ctx() -> None:
_CACERT_CTX.__exit__(None, None, None) # type: ignore[union-attr]
if sys.version_info >= (3, 11):
from importlib.resources import as_file, files
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the file
# in cases where we're inside of a zipimport situation until someone
# actually calls where(), but we don't want to re-extract the file
# on every call of where(), so we'll do it once then store it in a
# global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you to
# manage the cleanup of this file, so it doesn't actually return a
# path, it returns a context manager that will give you the path
# when you enter it and will do any cleanup when you leave it. In
# the common case of not needing a temporary file, it will just
# return the file system location and the __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = as_file(files("certifi").joinpath("cacert.pem"))
_CACERT_PATH = str(_CACERT_CTX.__enter__())
atexit.register(exit_cacert_ctx)
return _CACERT_PATH
def contents() -> str:
return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
else:
from importlib.resources import path as get_path, read_text
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the
# file in cases where we're inside of a zipimport situation until
# someone actually calls where(), but we don't want to re-extract
# the file on every call of where(), so we'll do it once then store
# it in a global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you
# to manage the cleanup of this file, so it doesn't actually
# return a path, it returns a context manager that will give
# you the path when you enter it and will do any cleanup when
# you leave it. In the common case of not needing a temporary
# file, it will just return the file system location and the
# __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = get_path("certifi", "cacert.pem")
_CACERT_PATH = str(_CACERT_CTX.__enter__())
atexit.register(exit_cacert_ctx)
return _CACERT_PATH
def contents() -> str:
return read_text("certifi", "cacert.pem", encoding="ascii")

0
apps/bitwarden_event_logs/lib/certifi/py.typed
Unescape View File

1
apps/bitwarden_event_logs/lib/charset_normalizer-3.4.4.dist-info/INSTALLER
Unescape View File

@ -1 +0,0 @@
pip

764
apps/bitwarden_event_logs/lib/charset_normalizer-3.4.4.dist-info/METADATA
Unescape View File

@ -1,764 +0,0 @@
Metadata-Version: 2.4
Name: charset-normalizer
Version: 3.4.4
Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
Author-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
Maintainer-email: "Ahmed R. TAHRI" <tahri.ahmed@proton.me>
License: MIT
Project-URL: Changelog, https://github.com/jawah/charset_normalizer/blob/master/CHANGELOG.md
Project-URL: Documentation, https://charset-normalizer.readthedocs.io/
Project-URL: Code, https://github.com/jawah/charset_normalizer
Project-URL: Issue tracker, https://github.com/jawah/charset_normalizer/issues
Keywords: encoding,charset,charset-detector,detector,normalization,unicode,chardet,detect
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Typing :: Typed
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode-backport
Dynamic: license-file
<h1 align="center">Charset Detection, for Everyone 👋</h1>
<p align="center">
<sup>The Real First Universal Charset Detector</sup><br>
<a href="https://pypi.org/project/charset-normalizer">
<img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
</a>
<a href="https://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://static.pepy.tech/badge/charset-normalizer/month" />
</a>
<a href="https://bestpractices.coreinfrastructure.org/projects/7297">
<img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
</a>
</p>
<p align="center">
<sup><i>Featured Packages</i></sup><br>
<a href="https://github.com/jawah/niquests">
<img alt="Static Badge" src="https://img.shields.io/badge/Niquests-Most_Advanced_HTTP_Client-cyan">
</a>
<a href="https://github.com/jawah/wassima">
<img alt="Static Badge" src="https://img.shields.io/badge/Wassima-Certifi_Replacement-cyan">
</a>
</p>
<p align="center">
<sup><i>In other language (unofficial port - by the community)</i></sup><br>
<a href="https://github.com/nickspring/charset-normalizer-rs">
<img alt="Static Badge" src="https://img.shields.io/badge/Rust-red">
</a>
</p>
> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
> I'm trying to resolve the issue by taking a new approach.
> All IANA character set names for which the Python core library provides codecs are supported.
<p align="center">
>>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
</p>
This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
| Feature | [Chardet](https://github.com/chardet/chardet) | Charset Normalizer | [cChardet](https://github.com/PyYoshi/cChardet) |
|--------------------------------------------------|:---------------------------------------------:|:--------------------------------------------------------------------------------------------------:|:-----------------------------------------------:|
| `Fast` | ❌ | ✅ | ✅ |
| `Universal**` | ❌ | ✅ | ❌ |
| `Reliable` **without** distinguishable standards | ❌ | ✅ | ✅ |
| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
| `License` | LGPL-2.1<br>_restrictive_ | MIT | MPL-1.1<br>_restrictive_ |
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ❌ | ✅ | N/A |
| `UnicodeDecodeError Safety` | ❌ | ✅ | ❌ |
| `Whl Size (min)` | 193.6 kB | 42 kB | ~200 kB |
| `Supported Encoding` | 33 | 🎉 [99](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) | 40 |
<p align="center">
<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
</p>
*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br>
## ⚡ Performance
This package offer better performance than its counterpart Chardet. Here are some numbers.
| Package | Accuracy | Mean per file (ms) | File per sec (est) |
|-----------------------------------------------|:--------:|:------------------:|:------------------:|
| [chardet](https://github.com/chardet/chardet) | 86 % | 63 ms | 16 file/sec |
| charset-normalizer | **98 %** | **10 ms** | 100 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
|-----------------------------------------------|:---------------:|:---------------:|:---------------:|
| [chardet](https://github.com/chardet/chardet) | 265 ms | 71 ms | 7 ms |
| charset-normalizer | 100 ms | 50 ms | 5 ms |
_updated as of december 2024 using CPython 3.12_
Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
> And yes, these results might change at any time. The dataset can be updated to include more files.
> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
> Keep in mind that the stats are generous and that Chardet accuracy vs our is measured using Chardet initial capability
> (e.g. Supported Encoding) Challenge-them if you want.
## ✨ Installation
Using pip:
```sh
pip install charset-normalizer -U
```
## 🚀 Basic Usage
### CLI
This package comes with a CLI.
```
usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
file [file ...]
The Real First Universal Charset Detector. Discover originating encoding used
on text file. Normalize text to unicode.
positional arguments:
files File(s) to be analysed
optional arguments:
-h, --help show this help message and exit
-v, --verbose Display complementary information about file if any.
Stdout will contain logs about the detection process.
-a, --with-alternative
Output complementary possibilities if any. Top-level
JSON WILL be a list.
-n, --normalize Permit to normalize input file. If not set, program
does not write anything.
-m, --minimal Only output the charset detected to STDOUT. Disabling
JSON output.
-r, --replace Replace file when trying to normalize it instead of
creating a new one.
-f, --force Replace file without asking if you are sure, use this
flag with caution.
-t THRESHOLD, --threshold THRESHOLD
Define a custom maximum amount of chaos allowed in
decoded content. 0. <= chaos <= 1.
--version Show version information and exit.
```
```bash
normalizer ./data/sample.1.fr.srt
```
or
```bash
python -m charset_normalizer ./data/sample.1.fr.srt
```
🎉 Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
```json
{
"path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
"encoding": "cp1252",
"encoding_aliases": [
"1252",
"windows_1252"
],
"alternative_encodings": [
"cp1254",
"cp1256",
"cp1258",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
"mbcs"
],
"language": "French",
"alphabets": [
"Basic Latin",
"Latin-1 Supplement"
],
"has_sig_or_bom": false,
"chaos": 0.149,
"coherence": 97.152,
"unicode_path": null,
"is_preferred": true
}
```
### Python
*Just print out normalized text*
```python
from charset_normalizer import from_path
results = from_path('./my_subtitle.srt')
print(str(results.best()))
```
*Upgrade your code without effort*
```python
from charset_normalizer import detect
```
The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
## 😇 Why
When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
reliable alternative using a completely different method. Also! I never back down on a good challenge!
I **don't care** about the **originating charset** encoding, because **two different tables** can
produce **two identical rendered string.**
What I want is to get readable text, the best I can.
In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair Unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
## 🍰 How
- Discard all charset encoding table that could not fit the binary content.
- Measure noise, or the mess once opened (by chunks) with a corresponding charset encoding.
- Extract matches with the lowest mess detected.
- Additionally, we measure coherence / probe for a language.
**Wait a minute**, what is noise/mess and coherence according to **YOU ?**
*Noise :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
**I established** some ground rules about **what is obvious** when **it seems like** a mess (aka. defining noise in rendered text).
I know that my interpretation of what is noise is probably incomplete, feel free to contribute in order to
improve or rewrite it.
*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
## ⚡ Known limitations
- Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
- Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
## ⚠️ About Python EOLs
**If you are running:**
- Python >=2.7,<3.5: Unsupported
- Python 3.5: charset-normalizer < 2.1
- Python 3.6: charset-normalizer < 3.1
- Python 3.7: charset-normalizer < 4.0
Upgrade your Python interpreter as soon as possible.
## 👤 Contributing
Contributions, issues and feature requests are very much welcome.<br />
Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
## 📝 License
Copyright © [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)
## 💼 For Enterprise
Professional support for charset-normalizer is available as part of the [Tidelift
Subscription][1]. Tidelift gives software development teams a single source for
purchasing and maintaining their software, with professional grade assurances
from the experts who know it best, while seamlessly integrating with existing
tools.
[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/7297/badge)](https://www.bestpractices.dev/projects/7297)
# Changelog
All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [3.4.4](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.4) (2025-10-13)
### Changed
- Bound `setuptools` to a specific constraint `setuptools>=68,<=81`.
- Raised upper bound of mypyc for the optional pre-built extension to v1.18.2
### Removed
- `setuptools-scm` as a build dependency.
### Misc
- Enforced hashes in `dev-requirements.txt` and created `ci-requirements.txt` for security purposes.
- Additional pre-built wheels for riscv64, s390x, and armv7l architectures.
- Restore ` multiple.intoto.jsonl` in GitHub releases in addition to individual attestation file per wheel.
## [3.4.3](https://github.com/Ousret/charset_normalizer/compare/3.4.2...3.4.3) (2025-08-09)
### Changed
- mypy(c) is no longer a required dependency at build time if `CHARSET_NORMALIZER_USE_MYPYC` isn't set to `1`. (#595) (#583)
- automatically lower confidence on small bytes samples that are not Unicode in `detect` output legacy function. (#391)
### Added
- Custom build backend to overcome inability to mark mypy as an optional dependency in the build phase.
- Support for Python 3.14
### Fixed
- sdist archive contained useless directories.
- automatically fallback on valid UTF-16 or UTF-32 even if the md says it's noisy. (#633)
### Misc
- SBOM are automatically published to the relevant GitHub release to comply with regulatory changes.
Each published wheel comes with its SBOM. We choose CycloneDX as the format.
- Prebuilt optimized wheel are no longer distributed by default for CPython 3.7 due to a change in cibuildwheel.
## [3.4.2](https://github.com/Ousret/charset_normalizer/compare/3.4.1...3.4.2) (2025-05-02)
### Fixed
- Addressed the DeprecationWarning in our CLI regarding `argparse.FileType` by backporting the target class into the package. (#591)
- Improved the overall reliability of the detector with CJK Ideographs. (#605) (#587)
### Changed
- Optional mypyc compilation upgraded to version 1.15 for Python >= 3.8
## [3.4.1](https://github.com/Ousret/charset_normalizer/compare/3.4.0...3.4.1) (2024-12-24)
### Changed
- Project metadata are now stored using `pyproject.toml` instead of `setup.cfg` using setuptools as the build backend.
- Enforce annotation delayed loading for a simpler and consistent types in the project.
- Optional mypyc compilation upgraded to version 1.14 for Python >= 3.8
### Added
- pre-commit configuration.
- noxfile.
### Removed
- `build-requirements.txt` as per using `pyproject.toml` native build configuration.
- `bin/integration.py` and `bin/serve.py` in favor of downstream integration test (see noxfile).
- `setup.cfg` in favor of `pyproject.toml` metadata configuration.
- Unused `utils.range_scan` function.
### Fixed
- Converting content to Unicode bytes may insert `utf_8` instead of preferred `utf-8`. (#572)
- Deprecation warning "'count' is passed as positional argument" when converting to Unicode bytes on Python 3.13+
## [3.4.0](https://github.com/Ousret/charset_normalizer/compare/3.3.2...3.4.0) (2024-10-08)
### Added
- Argument `--no-preemptive` in the CLI to prevent the detector to search for hints.
- Support for Python 3.13 (#512)
### Fixed
- Relax the TypeError exception thrown when trying to compare a CharsetMatch with anything else than a CharsetMatch.
- Improved the general reliability of the detector based on user feedbacks. (#520) (#509) (#498) (#407) (#537)
- Declared charset in content (preemptive detection) not changed when converting to utf-8 bytes. (#381)
## [3.3.2](https://github.com/Ousret/charset_normalizer/compare/3.3.1...3.3.2) (2023-10-31)
### Fixed
- Unintentional memory usage regression when using large payload that match several encoding (#376)
- Regression on some detection case showcased in the documentation (#371)
### Added
- Noise (md) probe that identify malformed arabic representation due to the presence of letters in isolated form (credit to my wife)
## [3.3.1](https://github.com/Ousret/charset_normalizer/compare/3.3.0...3.3.1) (2023-10-22)
### Changed
- Optional mypyc compilation upgraded to version 1.6.1 for Python >= 3.8
- Improved the general detection reliability based on reports from the community
## [3.3.0](https://github.com/Ousret/charset_normalizer/compare/3.2.0...3.3.0) (2023-09-30)
### Added
- Allow to execute the CLI (e.g. normalizer) through `python -m charset_normalizer.cli` or `python -m charset_normalizer`
- Support for 9 forgotten encoding that are supported by Python but unlisted in `encoding.aliases` as they have no alias (#323)
### Removed
- (internal) Redundant utils.is_ascii function and unused function is_private_use_only
- (internal) charset_normalizer.assets is moved inside charset_normalizer.constant
### Changed
- (internal) Unicode code blocks in constants are updated using the latest v15.0.0 definition to improve detection
- Optional mypyc compilation upgraded to version 1.5.1 for Python >= 3.8
### Fixed
- Unable to properly sort CharsetMatch when both chaos/noise and coherence were close due to an unreachable condition in \_\_lt\_\_ (#350)
## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
### Changed
- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
- Minor improvement over the global detection reliability
### Added
- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
- Explicit support for Python 3.12
### Fixed
- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
### Added
- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
### Removed
- Support for Python 3.6 (PR #260)
### Changed
- Optional speedup provided by mypy/c 1.0.1
## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
### Fixed
- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
### Changed
- Speedup provided by mypy/c 0.990 on Python >= 3.7
## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
- Sphinx warnings when generating the documentation
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
### Added
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Removed
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
### Fixed
- Sphinx warnings when generating the documentation
## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
### Changed
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Removed
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
### Deprecated
- Function `normalize` scheduled for removal in 3.0
### Changed
- Removed useless call to decode in fn is_unprintable (#206)
### Fixed
- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
### Added
- Output the Unicode table version when running the CLI with `--version` (PR #194)
### Changed
- Re-use decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
### Fixed
- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
### Removed
- Support for Python 3.5 (PR #192)
### Deprecated
- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
### Fixed
- ASCII miss-detection on rare cases (PR #170)
## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
### Added
- Explicit support for Python 3.11 (PR #164)
### Changed
- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
### Fixed
- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
### Changed
- Skipping the language-detection (CD) on ASCII (PR #155)
## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
### Changed
- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
### Fixed
- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
### Changed
- Improvement over Vietnamese detection (PR #126)
- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
- Code style as refactored by Sourcery-AI (PR #131)
- Minor adjustment on the MD around european words (PR #133)
- Remove and replace SRTs from assets / tests (PR #139)
- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
### Fixed
- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
- Avoid using too insignificant chunk (PR #137)
### Added
- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
### Added
- Add support for Kazakh (Cyrillic) language detection (PR #109)
### Changed
- Further, improve inferring the language from a given single-byte code page (PR #112)
- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
- Various detection improvement (MD+CD) (PR #117)
### Removed
- Remove redundant logging entry about detected language(s) (PR #115)
### Fixed
- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
### Fixed
- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
- Fix CLI crash when using --minimal output in certain cases (PR #103)
### Changed
- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
### Changed
- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
- The Unicode detection is slightly improved (PR #93)
- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
### Removed
- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
### Fixed
- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
- The MANIFEST.in was not exhaustive (PR #78)
## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
### Fixed
- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
- Submatch factoring could be wrong in rare edge cases (PR #72)
- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
- Fix line endings from CRLF to LF for certain project files (PR #67)
### Changed
- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
- Allow fallback on specified encoding if any (PR #71)
## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
### Changed
- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
### Fixed
- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59)
### Changed
- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
### Fixed
- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
### Changed
- Public function normalize default args values were not aligned with from_bytes (PR #53)
### Added
- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
### Changed
- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
- Accent has been made on UTF-8 detection, should perform rather instantaneous.
- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
- utf_7 detection has been reinstated.
### Removed
- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
- The exception hook on UnicodeDecodeError has been removed.
### Deprecated
- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
### Fixed
- The CLI output used the relative path of the file(s). Should be absolute.
## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
### Fixed
- Logger configuration/usage no longer conflict with others (PR #44)
## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
### Removed
- Using standard logging instead of using the package loguru.
- Dropping nose test framework in favor of the maintained pytest.
- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
- Stop support for UTF-7 that does not contain a SIG.
- Dropping PrettyTable, replaced with pure JSON output in CLI.
### Fixed
- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
- Not searching properly for the BOM when trying utf32/16 parent codec.
### Changed
- Improving the package final size by compressing frequencies.json.
- Huge improvement over the larges payload.
### Added
- CLI now produces JSON consumable output.
- Return ASCII if given sequences fit. Given reasonable confidence.
## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
### Fixed
- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
### Fixed
- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
### Fixed
- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
### Changed
- Amend the previous release to allow prettytable 2.0 (PR #35)
## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
### Fixed
- Fix error while using the package with a python pre-release interpreter (PR #33)
### Changed
- Dependencies refactoring, constraints revised.
### Added
- Add python 3.9 and 3.10 to the supported interpreters
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

24
apps/bitwarden_event_logs/lib/charset_normalizer-3.4.4.dist-info/RECORD
Unescape View File

@ -1,24 +0,0 @@
../../bin/normalizer,sha256=9v9CiM1SMj9hAM5YRMeRilB5D2s9HWSQ_qInrU2KpQU,253
charset_normalizer-3.4.4.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-3.4.4.dist-info/METADATA,sha256=jVuUFBti8dav19YLvWissTihVdF2ozUY4KKMw7jdkBQ,37303
charset_normalizer-3.4.4.dist-info/RECORD,,
charset_normalizer-3.4.4.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer-3.4.4.dist-info/WHEEL,sha256=ylJURW79exB2C-59Cgd1o0-VkgYeH2GaNb8U43WRbwg,187
charset_normalizer-3.4.4.dist-info/entry_points.txt,sha256=ADSTKrkXZ3hhdOVFi6DcUEHQRS0xfxDIE_pEz4wLIXA,65
charset_normalizer-3.4.4.dist-info/licenses/LICENSE,sha256=bQ1Bv-FwrGx9wkjJpj4lTQ-0WmDVCoJX0K-SxuJJuIc,1071
charset_normalizer-3.4.4.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
charset_normalizer/__init__.py,sha256=OKRxRv2Zhnqk00tqkN0c1BtJjm165fWXLydE52IKuHc,1590
charset_normalizer/__main__.py,sha256=yzYxMR-IhKRHYwcSlavEv8oGdwxsR89mr2X09qXGdps,109
charset_normalizer/api.py,sha256=V07i8aVeCD8T2fSia3C-fn0i9t8qQguEBhsqszg32Ns,22668
charset_normalizer/cd.py,sha256=WKTo1HDb-H9HfCDc3Bfwq5jzS25Ziy9SE2a74SgTq88,12522
charset_normalizer/cli/__init__.py,sha256=D8I86lFk2-py45JvqxniTirSj_sFyE6sjaY_0-G1shc,136
charset_normalizer/cli/__main__.py,sha256=dMaXG6IJXRvqq8z2tig7Qb83-BpWTln55ooiku5_uvg,12646
charset_normalizer/constant.py,sha256=7UVY4ldYhmQMHUdgQ_sgZmzcQ0xxYxpBunqSZ-XJZ8U,42713
charset_normalizer/legacy.py,sha256=sYBzSpzsRrg_wF4LP536pG64BItw7Tqtc3SMQAHvFLM,2731
charset_normalizer/md.cpython-39-aarch64-linux-gnu.so,sha256=Fl5b5yFpdjEkjaOr3bUxLjAmBYD37YTHfMCVs6SBh6A,201304
charset_normalizer/md.py,sha256=-_oN3h3_X99nkFfqamD3yu45DC_wfk5odH0Tr_CQiXs,20145
charset_normalizer/md__mypyc.cpython-39-aarch64-linux-gnu.so,sha256=nAx9ZddHDN7KxsVUxkP8Qen7djjHdO1_0_bP_aqC34A,324120
charset_normalizer/models.py,sha256=lKXhOnIPtiakbK3i__J9wpOfzx3JDTKj7Dn3Rg0VaRI,12394
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=sTejPgrdlNsKNucZfJCxJ95lMTLA0ShHLLE3n5wpT9Q,12170
charset_normalizer/version.py,sha256=nKE4qBNk5WA4LIJ_yIH_aSDfvtsyizkWMg-PUG-UZVk,115

0
apps/bitwarden_event_logs/lib/charset_normalizer-3.4.4.dist-info/REQUESTED
Unescape View File

7
apps/bitwarden_event_logs/lib/charset_normalizer-3.4.4.dist-info/WHEEL
Unescape View File

@ -1,7 +0,0 @@
Wheel-Version: 1.0
Generator: setuptools (80.9.0)
Root-Is-Purelib: false
Tag: cp39-cp39-manylinux_2_17_aarch64
Tag: cp39-cp39-manylinux2014_aarch64
Tag: cp39-cp39-manylinux_2_28_aarch64

21
apps/bitwarden_event_logs/lib/charset_normalizer-3.4.4.dist-info/licenses/LICENSE
Unescape View File

@ -1,21 +0,0 @@
MIT License
Copyright (c) 2025 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

48
apps/bitwarden_event_logs/lib/charset_normalizer/__init__.py
Unescape View File

@ -1,48 +0,0 @@
"""
Charset-Normalizer
~~~~~~~~~~~~~~
The Real First Universal Charset Detector.
A library that helps you read text from an unknown charset encoding.
Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
All IANA character set names for which the Python core library provides codecs are supported.
Basic usage:
>>> from charset_normalizer import from_bytes
>>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
>>> best_guess = results.best()
>>> str(best_guess)
'Bсеки човек има право на образование. Oбразованието!'
Others methods and usages are available - see the full documentation
at <https://github.com/Ousret/charset_normalizer>.
:copyright: (c) 2021 by Ahmed TAHRI
:license: MIT, see LICENSE for more details.
"""
from __future__ import annotations
import logging
from .api import from_bytes, from_fp, from_path, is_binary
from .legacy import detect
from .models import CharsetMatch, CharsetMatches
from .utils import set_logging_handler
from .version import VERSION, __version__
__all__ = (
"from_fp",
"from_path",
"from_bytes",
"is_binary",
"detect",
"CharsetMatch",
"CharsetMatches",
"__version__",
"VERSION",
"set_logging_handler",
)
# Attach a NullHandler to the top level logger by default
# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())

6
apps/bitwarden_event_logs/lib/charset_normalizer/__main__.py
Unescape View File

@ -1,6 +0,0 @@
from __future__ import annotations
from .cli import cli_detect
if __name__ == "__main__":
cli_detect()

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/__init__.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/api.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/cd.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/constant.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/legacy.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/md.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/models.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/utils.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/__pycache__/version.cpython-39.pyc
View File

Binary file not shown.

669
apps/bitwarden_event_logs/lib/charset_normalizer/api.py
Unescape View File

@ -1,669 +0,0 @@
from __future__ import annotations
import logging
from os import PathLike
from typing import BinaryIO
from .cd import (
coherence_ratio,
encoding_languages,
mb_encoding_languages,
merge_coherence_ratios,
)
from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE
from .md import mess_ratio
from .models import CharsetMatch, CharsetMatches
from .utils import (
any_specified_encoding,
cut_sequence_chunks,
iana_name,
identify_sig_or_bom,
is_cp_similar,
is_multi_byte_encoding,
should_strip_sig_or_bom,
)
logger = logging.getLogger("charset_normalizer")
explain_handler = logging.StreamHandler()
explain_handler.setFormatter(
logging.Formatter("%(asctime)s | %(levelname)s | %(message)s")
)
def from_bytes(
sequences: bytes | bytearray,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.2,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Given a raw bytes sequence, return the best possibles charset usable to render str objects.
If there is no results, it is a strong indicator that the source is binary/not text.
By default, the process will extract 5 blocks of 512o each to assess the mess and coherence of a given sequence.
And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
but never take it for granted. Can improve the performance.
You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
purpose.
This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
Custom logging format and handler can be set manually.
"""
if not isinstance(sequences, (bytearray, bytes)):
raise TypeError(
"Expected object of type bytes or bytearray, got: {}".format(
type(sequences)
)
)
if explain:
previous_logger_level: int = logger.level
logger.addHandler(explain_handler)
logger.setLevel(TRACE)
length: int = len(sequences)
if length == 0:
logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.")
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level or logging.WARNING)
return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
if cp_isolation is not None:
logger.log(
TRACE,
"cp_isolation is set. use this flag for debugging purpose. "
"limited list of encoding allowed : %s.",
", ".join(cp_isolation),
)
cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
else:
cp_isolation = []
if cp_exclusion is not None:
logger.log(
TRACE,
"cp_exclusion is set. use this flag for debugging purpose. "
"limited list of encoding excluded : %s.",
", ".join(cp_exclusion),
)
cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
else:
cp_exclusion = []
if length <= (chunk_size * steps):
logger.log(
TRACE,
"override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
steps,
chunk_size,
length,
)
steps = 1
chunk_size = length
if steps > 1 and length / steps < chunk_size:
chunk_size = int(length / steps)
is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE
is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE
if is_too_small_sequence:
logger.log(
TRACE,
"Trying to detect encoding from a tiny portion of ({}) byte(s).".format(
length
),
)
elif is_too_large_sequence:
logger.log(
TRACE,
"Using lazy str decoding because the payload is quite large, ({}) byte(s).".format(
length
),
)
prioritized_encodings: list[str] = []
specified_encoding: str | None = (
any_specified_encoding(sequences) if preemptive_behaviour else None
)
if specified_encoding is not None:
prioritized_encodings.append(specified_encoding)
logger.log(
TRACE,
"Detected declarative mark in sequence. Priority +1 given for %s.",
specified_encoding,
)
tested: set[str] = set()
tested_but_hard_failure: list[str] = []
tested_but_soft_failure: list[str] = []
fallback_ascii: CharsetMatch | None = None
fallback_u8: CharsetMatch | None = None
fallback_specified: CharsetMatch | None = None
results: CharsetMatches = CharsetMatches()
early_stop_results: CharsetMatches = CharsetMatches()
sig_encoding, sig_payload = identify_sig_or_bom(sequences)
if sig_encoding is not None:
prioritized_encodings.append(sig_encoding)
logger.log(
TRACE,
"Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.",
len(sig_payload),
sig_encoding,
)
prioritized_encodings.append("ascii")
if "utf_8" not in prioritized_encodings:
prioritized_encodings.append("utf_8")
for encoding_iana in prioritized_encodings + IANA_SUPPORTED:
if cp_isolation and encoding_iana not in cp_isolation:
continue
if cp_exclusion and encoding_iana in cp_exclusion:
continue
if encoding_iana in tested:
continue
tested.add(encoding_iana)
decoded_payload: str | None = None
bom_or_sig_available: bool = sig_encoding == encoding_iana
strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom(
encoding_iana
)
if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
encoding_iana,
)
continue
if encoding_iana in {"utf_7"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.",
encoding_iana,
)
continue
try:
is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana)
except (ModuleNotFoundError, ImportError):
logger.log(
TRACE,
"Encoding %s does not provide an IncrementalDecoder",
encoding_iana,
)
continue
try:
if is_too_large_sequence and is_multi_byte_decoder is False:
str(
(
sequences[: int(50e4)]
if strip_sig_or_bom is False
else sequences[len(sig_payload) : int(50e4)]
),
encoding=encoding_iana,
)
else:
decoded_payload = str(
(
sequences
if strip_sig_or_bom is False
else sequences[len(sig_payload) :]
),
encoding=encoding_iana,
)
except (UnicodeDecodeError, LookupError) as e:
if not isinstance(e, LookupError):
logger.log(
TRACE,
"Code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
similar_soft_failure_test: bool = False
for encoding_soft_failed in tested_but_soft_failure:
if is_cp_similar(encoding_iana, encoding_soft_failed):
similar_soft_failure_test = True
break
if similar_soft_failure_test:
logger.log(
TRACE,
"%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
encoding_iana,
encoding_soft_failed,
)
continue
r_ = range(
0 if not bom_or_sig_available else len(sig_payload),
length,
int(length / steps),
)
multi_byte_bonus: bool = (
is_multi_byte_decoder
and decoded_payload is not None
and len(decoded_payload) < length
)
if multi_byte_bonus:
logger.log(
TRACE,
"Code page %s is a multi byte encoding table and it appear that at least one character "
"was encoded using n-bytes.",
encoding_iana,
)
max_chunk_gave_up: int = int(len(r_) / 4)
max_chunk_gave_up = max(max_chunk_gave_up, 2)
early_stop_count: int = 0
lazy_str_hard_failure = False
md_chunks: list[str] = []
md_ratios = []
try:
for chunk in cut_sequence_chunks(
sequences,
encoding_iana,
r_,
chunk_size,
bom_or_sig_available,
strip_sig_or_bom,
sig_payload,
is_multi_byte_decoder,
decoded_payload,
):
md_chunks.append(chunk)
md_ratios.append(
mess_ratio(
chunk,
threshold,
explain is True and 1 <= len(cp_isolation) <= 2,
)
)
if md_ratios[-1] >= threshold:
early_stop_count += 1
if (early_stop_count >= max_chunk_gave_up) or (
bom_or_sig_available and strip_sig_or_bom is False
):
break
except (
UnicodeDecodeError
) as e: # Lazy str loading may have missed something there
logger.log(
TRACE,
"LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
early_stop_count = max_chunk_gave_up
lazy_str_hard_failure = True
# We might want to check the sequence again with the whole content
# Only if initial MD tests passes
if (
not lazy_str_hard_failure
and is_too_large_sequence
and not is_multi_byte_decoder
):
try:
sequences[int(50e3) :].decode(encoding_iana, errors="strict")
except UnicodeDecodeError as e:
logger.log(
TRACE,
"LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
tested_but_soft_failure.append(encoding_iana)
logger.log(
TRACE,
"%s was excluded because of initial chaos probing. Gave up %i time(s). "
"Computed mean chaos is %f %%.",
encoding_iana,
early_stop_count,
round(mean_mess_ratio * 100, ndigits=3),
)
# Preparing those fallbacks in case we got nothing.
if (
enable_fallback
and encoding_iana
in ["ascii", "utf_8", specified_encoding, "utf_16", "utf_32"]
and not lazy_str_hard_failure
):
fallback_entry = CharsetMatch(
sequences,
encoding_iana,
threshold,
bom_or_sig_available,
[],
decoded_payload,
preemptive_declaration=specified_encoding,
)
if encoding_iana == specified_encoding:
fallback_specified = fallback_entry
elif encoding_iana == "ascii":
fallback_ascii = fallback_entry
else:
fallback_u8 = fallback_entry
continue
logger.log(
TRACE,
"%s passed initial chaos probing. Mean measured chaos is %f %%",
encoding_iana,
round(mean_mess_ratio * 100, ndigits=3),
)
if not is_multi_byte_decoder:
target_languages: list[str] = encoding_languages(encoding_iana)
else:
target_languages = mb_encoding_languages(encoding_iana)
if target_languages:
logger.log(
TRACE,
"{} should target any language(s) of {}".format(
encoding_iana, str(target_languages)
),
)
cd_ratios = []
# We shall skip the CD when its about ASCII
# Most of the time its not relevant to run "language-detection" on it.
if encoding_iana != "ascii":
for chunk in md_chunks:
chunk_languages = coherence_ratio(
chunk,
language_threshold,
",".join(target_languages) if target_languages else None,
)
cd_ratios.append(chunk_languages)
cd_ratios_merged = merge_coherence_ratios(cd_ratios)
if cd_ratios_merged:
logger.log(
TRACE,
"We detected language {} using {}".format(
cd_ratios_merged, encoding_iana
),
)
current_match = CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
(
decoded_payload
if (
is_too_large_sequence is False
or encoding_iana in [specified_encoding, "ascii", "utf_8"]
)
else None
),
preemptive_declaration=specified_encoding,
)
results.append(current_match)
if (
encoding_iana in [specified_encoding, "ascii", "utf_8"]
and mean_mess_ratio < 0.1
):
# If md says nothing to worry about, then... stop immediately!
if mean_mess_ratio == 0.0:
logger.debug(
"Encoding detection: %s is most likely the one.",
current_match.encoding,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([current_match])
early_stop_results.append(current_match)
if (
len(early_stop_results)
and (specified_encoding is None or specified_encoding in tested)
and "ascii" in tested
and "utf_8" in tested
):
probable_result: CharsetMatch = early_stop_results.best() # type: ignore[assignment]
logger.debug(
"Encoding detection: %s is most likely the one.",
probable_result.encoding,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([probable_result])
if encoding_iana == sig_encoding:
logger.debug(
"Encoding detection: %s is most likely the one as we detected a BOM or SIG within "
"the beginning of the sequence.",
encoding_iana,
)
if explain: # Defensive: ensure exit path clean handler
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
if len(results) == 0:
if fallback_u8 or fallback_ascii or fallback_specified:
logger.log(
TRACE,
"Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.",
)
if fallback_specified:
logger.debug(
"Encoding detection: %s will be used as a fallback match",
fallback_specified.encoding,
)
results.append(fallback_specified)
elif (
(fallback_u8 and fallback_ascii is None)
or (
fallback_u8
and fallback_ascii
and fallback_u8.fingerprint != fallback_ascii.fingerprint
)
or (fallback_u8 is not None)
):
logger.debug("Encoding detection: utf_8 will be used as a fallback match")
results.append(fallback_u8)
elif fallback_ascii:
logger.debug("Encoding detection: ascii will be used as a fallback match")
results.append(fallback_ascii)
if results:
logger.debug(
"Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.",
results.best().encoding, # type: ignore
len(results) - 1,
)
else:
logger.debug("Encoding detection: Unable to determine any suitable charset.")
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return results
def from_fp(
fp: BinaryIO,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but using a file pointer that is already ready.
Will not close the file pointer.
"""
return from_bytes(
fp.read(),
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
language_threshold,
enable_fallback,
)
def from_path(
path: str | bytes | PathLike, # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
Can raise IOError.
"""
with open(path, "rb") as fp:
return from_fp(
fp,
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
language_threshold,
enable_fallback,
)
def is_binary(
fp_or_path_or_payload: PathLike | str | BinaryIO | bytes, # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: list[str] | None = None,
cp_exclusion: list[str] | None = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = False,
) -> bool:
"""
Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string.
Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match
are disabled to be stricter around ASCII-compatible but unlikely to be a string.
"""
if isinstance(fp_or_path_or_payload, (str, PathLike)):
guesses = from_path(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
elif isinstance(
fp_or_path_or_payload,
(
bytes,
bytearray,
),
):
guesses = from_bytes(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
else:
guesses = from_fp(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
return not guesses

395
apps/bitwarden_event_logs/lib/charset_normalizer/cd.py
Unescape View File

@ -1,395 +0,0 @@
from __future__ import annotations
import importlib
from codecs import IncrementalDecoder
from collections import Counter
from functools import lru_cache
from typing import Counter as TypeCounter
from .constant import (
FREQUENCIES,
KO_NAMES,
LANGUAGE_SUPPORTED_COUNT,
TOO_SMALL_SEQUENCE,
ZH_NAMES,
)
from .md import is_suspiciously_successive_range
from .models import CoherenceMatches
from .utils import (
is_accentuated,
is_latin,
is_multi_byte_encoding,
is_unicode_range_secondary,
unicode_range,
)
def encoding_unicode_range(iana_name: str) -> list[str]:
"""
Return associated unicode ranges in a single byte code page.
"""
if is_multi_byte_encoding(iana_name):
raise OSError("Function not supported on multi-byte code page")
decoder = importlib.import_module(f"encodings.{iana_name}").IncrementalDecoder
p: IncrementalDecoder = decoder(errors="ignore")
seen_ranges: dict[str, int] = {}
character_count: int = 0
for i in range(0x40, 0xFF):
chunk: str = p.decode(bytes([i]))
if chunk:
character_range: str | None = unicode_range(chunk)
if character_range is None:
continue
if is_unicode_range_secondary(character_range) is False:
if character_range not in seen_ranges:
seen_ranges[character_range] = 0
seen_ranges[character_range] += 1
character_count += 1
return sorted(
[
character_range
for character_range in seen_ranges
if seen_ranges[character_range] / character_count >= 0.15
]
)
def unicode_range_languages(primary_range: str) -> list[str]:
"""
Return inferred languages used with a unicode range.
"""
languages: list[str] = []
for language, characters in FREQUENCIES.items():
for character in characters:
if unicode_range(character) == primary_range:
languages.append(language)
break
return languages
@lru_cache()
def encoding_languages(iana_name: str) -> list[str]:
"""
Single-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
unicode_ranges: list[str] = encoding_unicode_range(iana_name)
primary_range: str | None = None
for specified_range in unicode_ranges:
if "Latin" not in specified_range:
primary_range = specified_range
break
if primary_range is None:
return ["Latin Based"]
return unicode_range_languages(primary_range)
@lru_cache()
def mb_encoding_languages(iana_name: str) -> list[str]:
"""
Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
"""
if (
iana_name.startswith("shift_")
or iana_name.startswith("iso2022_jp")
or iana_name.startswith("euc_j")
or iana_name == "cp932"
):
return ["Japanese"]
if iana_name.startswith("gb") or iana_name in ZH_NAMES:
return ["Chinese"]
if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES:
return ["Korean"]
return []
@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT)
def get_target_features(language: str) -> tuple[bool, bool]:
"""
Determine main aspects from a supported language if it contains accents and if is pure Latin.
"""
target_have_accents: bool = False
target_pure_latin: bool = True
for character in FREQUENCIES[language]:
if not target_have_accents and is_accentuated(character):
target_have_accents = True
if target_pure_latin and is_latin(character) is False:
target_pure_latin = False
return target_have_accents, target_pure_latin
def alphabet_languages(
characters: list[str], ignore_non_latin: bool = False
) -> list[str]:
"""
Return associated languages associated to given characters.
"""
languages: list[tuple[str, float]] = []
source_have_accents = any(is_accentuated(character) for character in characters)
for language, language_characters in FREQUENCIES.items():
target_have_accents, target_pure_latin = get_target_features(language)
if ignore_non_latin and target_pure_latin is False:
continue
if target_have_accents is False and source_have_accents:
continue
character_count: int = len(language_characters)
character_match_count: int = len(
[c for c in language_characters if c in characters]
)
ratio: float = character_match_count / character_count
if ratio >= 0.2:
languages.append((language, ratio))
languages = sorted(languages, key=lambda x: x[1], reverse=True)
return [compatible_language[0] for compatible_language in languages]
def characters_popularity_compare(
language: str, ordered_characters: list[str]
) -> float:
"""
Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
"""
if language not in FREQUENCIES:
raise ValueError(f"{language} not available")
character_approved_count: int = 0
FREQUENCIES_language_set = set(FREQUENCIES[language])
ordered_characters_count: int = len(ordered_characters)
target_language_characters_count: int = len(FREQUENCIES[language])
large_alphabet: bool = target_language_characters_count > 26
for character, character_rank in zip(
ordered_characters, range(0, ordered_characters_count)
):
if character not in FREQUENCIES_language_set:
continue
character_rank_in_language: int = FREQUENCIES[language].index(character)
expected_projection_ratio: float = (
target_language_characters_count / ordered_characters_count
)
character_rank_projection: int = int(character_rank * expected_projection_ratio)
if (
large_alphabet is False
and abs(character_rank_projection - character_rank_in_language) > 4
):
continue
if (
large_alphabet is True
and abs(character_rank_projection - character_rank_in_language)
< target_language_characters_count / 3
):
character_approved_count += 1
continue
characters_before_source: list[str] = FREQUENCIES[language][
0:character_rank_in_language
]
characters_after_source: list[str] = FREQUENCIES[language][
character_rank_in_language:
]
characters_before: list[str] = ordered_characters[0:character_rank]
characters_after: list[str] = ordered_characters[character_rank:]
before_match_count: int = len(
set(characters_before) & set(characters_before_source)
)
after_match_count: int = len(
set(characters_after) & set(characters_after_source)
)
if len(characters_before_source) == 0 and before_match_count <= 4:
character_approved_count += 1
continue
if len(characters_after_source) == 0 and after_match_count <= 4:
character_approved_count += 1
continue
if (
before_match_count / len(characters_before_source) >= 0.4
or after_match_count / len(characters_after_source) >= 0.4
):
character_approved_count += 1
continue
return character_approved_count / len(ordered_characters)
def alpha_unicode_split(decoded_sequence: str) -> list[str]:
"""
Given a decoded text sequence, return a list of str. Unicode range / alphabet separation.
Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list;
One containing the latin letters and the other hebrew.
"""
layers: dict[str, str] = {}
for character in decoded_sequence:
if character.isalpha() is False:
continue
character_range: str | None = unicode_range(character)
if character_range is None:
continue
layer_target_range: str | None = None
for discovered_range in layers:
if (
is_suspiciously_successive_range(discovered_range, character_range)
is False
):
layer_target_range = discovered_range
break
if layer_target_range is None:
layer_target_range = character_range
if layer_target_range not in layers:
layers[layer_target_range] = character.lower()
continue
layers[layer_target_range] += character.lower()
return list(layers.values())
def merge_coherence_ratios(results: list[CoherenceMatches]) -> CoherenceMatches:
"""
This function merge results previously given by the function coherence_ratio.
The return type is the same as coherence_ratio.
"""
per_language_ratios: dict[str, list[float]] = {}
for result in results:
for sub_result in result:
language, ratio = sub_result
if language not in per_language_ratios:
per_language_ratios[language] = [ratio]
continue
per_language_ratios[language].append(ratio)
merge = [
(
language,
round(
sum(per_language_ratios[language]) / len(per_language_ratios[language]),
4,
),
)
for language in per_language_ratios
]
return sorted(merge, key=lambda x: x[1], reverse=True)
def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches:
"""
We shall NOT return "English—" in CoherenceMatches because it is an alternative
of "English". This function only keeps the best match and remove the em-dash in it.
"""
index_results: dict[str, list[float]] = dict()
for result in results:
language, ratio = result
no_em_name: str = language.replace("—", "")
if no_em_name not in index_results:
index_results[no_em_name] = []
index_results[no_em_name].append(ratio)
if any(len(index_results[e]) > 1 for e in index_results):
filtered_results: CoherenceMatches = []
for language in index_results:
filtered_results.append((language, max(index_results[language])))
return filtered_results
return results
@lru_cache(maxsize=2048)
def coherence_ratio(
decoded_sequence: str, threshold: float = 0.1, lg_inclusion: str | None = None
) -> CoherenceMatches:
"""
Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
A layer = Character extraction by alphabets/ranges.
"""
results: list[tuple[str, float]] = []
ignore_non_latin: bool = False
sufficient_match_count: int = 0
lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else []
if "Latin Based" in lg_inclusion_list:
ignore_non_latin = True
lg_inclusion_list.remove("Latin Based")
for layer in alpha_unicode_split(decoded_sequence):
sequence_frequencies: TypeCounter[str] = Counter(layer)
most_common = sequence_frequencies.most_common()
character_count: int = sum(o for c, o in most_common)
if character_count <= TOO_SMALL_SEQUENCE:
continue
popular_character_ordered: list[str] = [c for c, o in most_common]
for language in lg_inclusion_list or alphabet_languages(
popular_character_ordered, ignore_non_latin
):
ratio: float = characters_popularity_compare(
language, popular_character_ordered
)
if ratio < threshold:
continue
elif ratio >= 0.8:
sufficient_match_count += 1
results.append((language, round(ratio, 4)))
if sufficient_match_count >= 3:
break
return sorted(
filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True
)

8
apps/bitwarden_event_logs/lib/charset_normalizer/cli/__init__.py
Unescape View File

@ -1,8 +0,0 @@
from __future__ import annotations
from .__main__ import cli_detect, query_yes_no
__all__ = (
"cli_detect",
"query_yes_no",
)

381
apps/bitwarden_event_logs/lib/charset_normalizer/cli/__main__.py
Unescape View File

@ -1,381 +0,0 @@
from __future__ import annotations
import argparse
import sys
import typing
from json import dumps
from os.path import abspath, basename, dirname, join, realpath
from platform import python_version
from unicodedata import unidata_version
import charset_normalizer.md as md_module
from charset_normalizer import from_fp
from charset_normalizer.models import CliDetectionResult
from charset_normalizer.version import __version__
def query_yes_no(question: str, default: str = "yes") -> bool:
"""Ask a yes/no question via input() and return their answer.
"question" is a string that is presented to the user.
"default" is the presumed answer if the user just hits <Enter>.
It must be "yes" (the default), "no" or None (meaning
an answer is required of the user).
The "answer" return value is True for "yes" or False for "no".
Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input
"""
valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False}
if default is None:
prompt = " [y/n] "
elif default == "yes":
prompt = " [Y/n] "
elif default == "no":
prompt = " [y/N] "
else:
raise ValueError("invalid default answer: '%s'" % default)
while True:
sys.stdout.write(question + prompt)
choice = input().lower()
if default is not None and choice == "":
return valid[default]
elif choice in valid:
return valid[choice]
else:
sys.stdout.write("Please respond with 'yes' or 'no' (or 'y' or 'n').\n")
class FileType:
"""Factory for creating file object types
Instances of FileType are typically passed as type= arguments to the
ArgumentParser add_argument() method.
Keyword Arguments:
- mode -- A string indicating how the file is to be opened. Accepts the
same values as the builtin open() function.
- bufsize -- The file's desired buffer size. Accepts the same values as
the builtin open() function.
- encoding -- The file's encoding. Accepts the same values as the
builtin open() function.
- errors -- A string indicating how encoding and decoding errors are to
be handled. Accepts the same value as the builtin open() function.
Backported from CPython 3.12
"""
def __init__(
self,
mode: str = "r",
bufsize: int = -1,
encoding: str | None = None,
errors: str | None = None,
):
self._mode = mode
self._bufsize = bufsize
self._encoding = encoding
self._errors = errors
def __call__(self, string: str) -> typing.IO: # type: ignore[type-arg]
# the special argument "-" means sys.std{in,out}
if string == "-":
if "r" in self._mode:
return sys.stdin.buffer if "b" in self._mode else sys.stdin
elif any(c in self._mode for c in "wax"):
return sys.stdout.buffer if "b" in self._mode else sys.stdout
else:
msg = f'argument "-" with mode {self._mode}'
raise ValueError(msg)
# all other arguments are used as file names
try:
return open(string, self._mode, self._bufsize, self._encoding, self._errors)
except OSError as e:
message = f"can't open '{string}': {e}"
raise argparse.ArgumentTypeError(message)
def __repr__(self) -> str:
args = self._mode, self._bufsize
kwargs = [("encoding", self._encoding), ("errors", self._errors)]
args_str = ", ".join(
[repr(arg) for arg in args if arg != -1]
+ [f"{kw}={arg!r}" for kw, arg in kwargs if arg is not None]
)
return f"{type(self).__name__}({args_str})"
def cli_detect(argv: list[str] | None = None) -> int:
"""
CLI assistant using ARGV and ArgumentParser
:param argv:
:return: 0 if everything is fine, anything else equal trouble
"""
parser = argparse.ArgumentParser(
description="The Real First Universal Charset Detector. "
"Discover originating encoding used on text file. "
"Normalize text to unicode."
)
parser.add_argument(
"files", type=FileType("rb"), nargs="+", help="File(s) to be analysed"
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
default=False,
dest="verbose",
help="Display complementary information about file if any. "
"Stdout will contain logs about the detection process.",
)
parser.add_argument(
"-a",
"--with-alternative",
action="store_true",
default=False,
dest="alternatives",
help="Output complementary possibilities if any. Top-level JSON WILL be a list.",
)
parser.add_argument(
"-n",
"--normalize",
action="store_true",
default=False,
dest="normalize",
help="Permit to normalize input file. If not set, program does not write anything.",
)
parser.add_argument(
"-m",
"--minimal",
action="store_true",
default=False,
dest="minimal",
help="Only output the charset detected to STDOUT. Disabling JSON output.",
)
parser.add_argument(
"-r",
"--replace",
action="store_true",
default=False,
dest="replace",
help="Replace file when trying to normalize it instead of creating a new one.",
)
parser.add_argument(
"-f",
"--force",
action="store_true",
default=False,
dest="force",
help="Replace file without asking if you are sure, use this flag with caution.",
)
parser.add_argument(
"-i",
"--no-preemptive",
action="store_true",
default=False,
dest="no_preemptive",
help="Disable looking at a charset declaration to hint the detector.",
)
parser.add_argument(
"-t",
"--threshold",
action="store",
default=0.2,
type=float,
dest="threshold",
help="Define a custom maximum amount of noise allowed in decoded content. 0. <= noise <= 1.",
)
parser.add_argument(
"--version",
action="version",
version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format(
__version__,
python_version(),
unidata_version,
"OFF" if md_module.__file__.lower().endswith(".py") else "ON",
),
help="Show version information and exit.",
)
args = parser.parse_args(argv)
if args.replace is True and args.normalize is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --replace in addition of --normalize only.", file=sys.stderr)
return 1
if args.force is True and args.replace is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --force in addition of --replace only.", file=sys.stderr)
return 1
if args.threshold < 0.0 or args.threshold > 1.0:
if args.files:
for my_file in args.files:
my_file.close()
print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
return 1
x_ = []
for my_file in args.files:
matches = from_fp(
my_file,
threshold=args.threshold,
explain=args.verbose,
preemptive_behaviour=args.no_preemptive is False,
)
best_guess = matches.best()
if best_guess is None:
print(
'Unable to identify originating encoding for "{}". {}'.format(
my_file.name,
(
"Maybe try increasing maximum amount of chaos."
if args.threshold < 1.0
else ""
),
),
file=sys.stderr,
)
x_.append(
CliDetectionResult(
abspath(my_file.name),
None,
[],
[],
"Unknown",
[],
False,
1.0,
0.0,
None,
True,
)
)
else:
x_.append(
CliDetectionResult(
abspath(my_file.name),
best_guess.encoding,
best_guess.encoding_aliases,
[
cp
for cp in best_guess.could_be_from_charset
if cp != best_guess.encoding
],
best_guess.language,
best_guess.alphabets,
best_guess.bom,
best_guess.percent_chaos,
best_guess.percent_coherence,
None,
True,
)
)
if len(matches) > 1 and args.alternatives:
for el in matches:
if el != best_guess:
x_.append(
CliDetectionResult(
abspath(my_file.name),
el.encoding,
el.encoding_aliases,
[
cp
for cp in el.could_be_from_charset
if cp != el.encoding
],
el.language,
el.alphabets,
el.bom,
el.percent_chaos,
el.percent_coherence,
None,
False,
)
)
if args.normalize is True:
if best_guess.encoding.startswith("utf") is True:
print(
'"{}" file does not need to be normalized, as it already came from unicode.'.format(
my_file.name
),
file=sys.stderr,
)
if my_file.closed is False:
my_file.close()
continue
dir_path = dirname(realpath(my_file.name))
file_name = basename(realpath(my_file.name))
o_: list[str] = file_name.split(".")
if args.replace is False:
o_.insert(-1, best_guess.encoding)
if my_file.closed is False:
my_file.close()
elif (
args.force is False
and query_yes_no(
'Are you sure to normalize "{}" by replacing it ?'.format(
my_file.name
),
"no",
)
is False
):
if my_file.closed is False:
my_file.close()
continue
try:
x_[0].unicode_path = join(dir_path, ".".join(o_))
with open(x_[0].unicode_path, "wb") as fp:
fp.write(best_guess.output())
except OSError as e:
print(str(e), file=sys.stderr)
if my_file.closed is False:
my_file.close()
return 2
if my_file.closed is False:
my_file.close()
if args.minimal is False:
print(
dumps(
[el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__,
ensure_ascii=True,
indent=4,
)
)
else:
for my_file in args.files:
print(
", ".join(
[
el.encoding or "undefined"
for el in x_
if el.path == abspath(my_file.name)
]
)
)
return 0
if __name__ == "__main__":
cli_detect()

2015
apps/bitwarden_event_logs/lib/charset_normalizer/constant.py
View File

File diff suppressed because it is too large Load Diff

80
apps/bitwarden_event_logs/lib/charset_normalizer/legacy.py
Unescape View File

@ -1,80 +0,0 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from warnings import warn
from .api import from_bytes
from .constant import CHARDET_CORRESPONDENCE, TOO_SMALL_SEQUENCE
# TODO: remove this check when dropping Python 3.7 support
if TYPE_CHECKING:
from typing_extensions import TypedDict
class ResultDict(TypedDict):
encoding: str | None
language: str
confidence: float | None
def detect(
byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
) -> ResultDict:
"""
chardet legacy method
Detect the encoding of the given byte string. It should be mostly backward-compatible.
Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
This function is deprecated and should be used to migrate your project easily, consult the documentation for
further information. Not planned for removal.
:param byte_str: The byte sequence to examine.
:param should_rename_legacy: Should we rename legacy encodings
to their more modern equivalents?
"""
if len(kwargs):
warn(
f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
)
if not isinstance(byte_str, (bytearray, bytes)):
raise TypeError( # pragma: nocover
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
if isinstance(byte_str, bytearray):
byte_str = bytes(byte_str)
r = from_bytes(byte_str).best()
encoding = r.encoding if r is not None else None
language = r.language if r is not None and r.language != "Unknown" else ""
confidence = 1.0 - r.chaos if r is not None else None
# automatically lower confidence
# on small bytes samples.
# https://github.com/jawah/charset_normalizer/issues/391
if (
confidence is not None
and confidence >= 0.9
and encoding
not in {
"utf_8",
"ascii",
}
and r.bom is False # type: ignore[union-attr]
and len(byte_str) < TOO_SMALL_SEQUENCE
):
confidence -= 0.2
# Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
# but chardet does return 'utf-8-sig' and it is a valid codec name.
if r is not None and encoding == "utf_8" and r.bom:
encoding += "_sig"
if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE:
encoding = CHARDET_CORRESPONDENCE[encoding]
return {
"encoding": encoding,
"language": language,
"confidence": confidence,
}

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/md.cpython-39-aarch64-linux-gnu.so
View File

Binary file not shown.

635
apps/bitwarden_event_logs/lib/charset_normalizer/md.py
Unescape View File

@ -1,635 +0,0 @@
from __future__ import annotations
from functools import lru_cache
from logging import getLogger
from .constant import (
COMMON_SAFE_ASCII_CHARACTERS,
TRACE,
UNICODE_SECONDARY_RANGE_KEYWORD,
)
from .utils import (
is_accentuated,
is_arabic,
is_arabic_isolated_form,
is_case_variable,
is_cjk,
is_emoticon,
is_hangul,
is_hiragana,
is_katakana,
is_latin,
is_punctuation,
is_separator,
is_symbol,
is_thai,
is_unprintable,
remove_accent,
unicode_range,
is_cjk_uncommon,
)
class MessDetectorPlugin:
"""
Base abstract class used for mess detection plugins.
All detectors MUST extend and implement given methods.
"""
def eligible(self, character: str) -> bool:
"""
Determine if given character should be fed in.
"""
raise NotImplementedError # pragma: nocover
def feed(self, character: str) -> None:
"""
The main routine to be executed upon character.
Insert the logic in witch the text would be considered chaotic.
"""
raise NotImplementedError # pragma: nocover
def reset(self) -> None: # pragma: no cover
"""
Permit to reset the plugin to the initial state.
"""
raise NotImplementedError
@property
def ratio(self) -> float:
"""
Compute the chaos ratio based on what your feed() has seen.
Must NOT be lower than 0.; No restriction gt 0.
"""
raise NotImplementedError # pragma: nocover
class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._punctuation_count: int = 0
self._symbol_count: int = 0
self._character_count: int = 0
self._last_printable_char: str | None = None
self._frenzy_symbol_in_word: bool = False
def eligible(self, character: str) -> bool:
return character.isprintable()
def feed(self, character: str) -> None:
self._character_count += 1
if (
character != self._last_printable_char
and character not in COMMON_SAFE_ASCII_CHARACTERS
):
if is_punctuation(character):
self._punctuation_count += 1
elif (
character.isdigit() is False
and is_symbol(character)
and is_emoticon(character) is False
):
self._symbol_count += 2
self._last_printable_char = character
def reset(self) -> None: # Abstract
self._punctuation_count = 0
self._character_count = 0
self._symbol_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
ratio_of_punctuation: float = (
self._punctuation_count + self._symbol_count
) / self._character_count
return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0
class TooManyAccentuatedPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._character_count: int = 0
self._accentuated_count: int = 0
def eligible(self, character: str) -> bool:
return character.isalpha()
def feed(self, character: str) -> None:
self._character_count += 1
if is_accentuated(character):
self._accentuated_count += 1
def reset(self) -> None: # Abstract
self._character_count = 0
self._accentuated_count = 0
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
ratio_of_accentuation: float = self._accentuated_count / self._character_count
return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0
class UnprintablePlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._unprintable_count: int = 0
self._character_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if is_unprintable(character):
self._unprintable_count += 1
self._character_count += 1
def reset(self) -> None: # Abstract
self._unprintable_count = 0
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._unprintable_count * 8) / self._character_count
class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._successive_count: int = 0
self._character_count: int = 0
self._last_latin_character: str | None = None
def eligible(self, character: str) -> bool:
return character.isalpha() and is_latin(character)
def feed(self, character: str) -> None:
self._character_count += 1
if (
self._last_latin_character is not None
and is_accentuated(character)
and is_accentuated(self._last_latin_character)
):
if character.isupper() and self._last_latin_character.isupper():
self._successive_count += 1
# Worse if its the same char duplicated with different accent.
if remove_accent(character) == remove_accent(self._last_latin_character):
self._successive_count += 1
self._last_latin_character = character
def reset(self) -> None: # Abstract
self._successive_count = 0
self._character_count = 0
self._last_latin_character = None
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return (self._successive_count * 2) / self._character_count
class SuspiciousRange(MessDetectorPlugin):
def __init__(self) -> None:
self._suspicious_successive_range_count: int = 0
self._character_count: int = 0
self._last_printable_seen: str | None = None
def eligible(self, character: str) -> bool:
return character.isprintable()
def feed(self, character: str) -> None:
self._character_count += 1
if (
character.isspace()
or is_punctuation(character)
or character in COMMON_SAFE_ASCII_CHARACTERS
):
self._last_printable_seen = None
return
if self._last_printable_seen is None:
self._last_printable_seen = character
return
unicode_range_a: str | None = unicode_range(self._last_printable_seen)
unicode_range_b: str | None = unicode_range(character)
if is_suspiciously_successive_range(unicode_range_a, unicode_range_b):
self._suspicious_successive_range_count += 1
self._last_printable_seen = character
def reset(self) -> None: # Abstract
self._character_count = 0
self._suspicious_successive_range_count = 0
self._last_printable_seen = None
@property
def ratio(self) -> float:
if self._character_count <= 13:
return 0.0
ratio_of_suspicious_range_usage: float = (
self._suspicious_successive_range_count * 2
) / self._character_count
return ratio_of_suspicious_range_usage
class SuperWeirdWordPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._word_count: int = 0
self._bad_word_count: int = 0
self._foreign_long_count: int = 0
self._is_current_word_bad: bool = False
self._foreign_long_watch: bool = False
self._character_count: int = 0
self._bad_character_count: int = 0
self._buffer: str = ""
self._buffer_accent_count: int = 0
self._buffer_glyph_count: int = 0
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
if character.isalpha():
self._buffer += character
if is_accentuated(character):
self._buffer_accent_count += 1
if (
self._foreign_long_watch is False
and (is_latin(character) is False or is_accentuated(character))
and is_cjk(character) is False
and is_hangul(character) is False
and is_katakana(character) is False
and is_hiragana(character) is False
and is_thai(character) is False
):
self._foreign_long_watch = True
if (
is_cjk(character)
or is_hangul(character)
or is_katakana(character)
or is_hiragana(character)
or is_thai(character)
):
self._buffer_glyph_count += 1
return
if not self._buffer:
return
if (
character.isspace() or is_punctuation(character) or is_separator(character)
) and self._buffer:
self._word_count += 1
buffer_length: int = len(self._buffer)
self._character_count += buffer_length
if buffer_length >= 4:
if self._buffer_accent_count / buffer_length >= 0.5:
self._is_current_word_bad = True
# Word/Buffer ending with an upper case accentuated letter are so rare,
# that we will consider them all as suspicious. Same weight as foreign_long suspicious.
elif (
is_accentuated(self._buffer[-1])
and self._buffer[-1].isupper()
and all(_.isupper() for _ in self._buffer) is False
):
self._foreign_long_count += 1
self._is_current_word_bad = True
elif self._buffer_glyph_count == 1:
self._is_current_word_bad = True
self._foreign_long_count += 1
if buffer_length >= 24 and self._foreign_long_watch:
camel_case_dst = [
i
for c, i in zip(self._buffer, range(0, buffer_length))
if c.isupper()
]
probable_camel_cased: bool = False
if camel_case_dst and (len(camel_case_dst) / buffer_length <= 0.3):
probable_camel_cased = True
if not probable_camel_cased:
self._foreign_long_count += 1
self._is_current_word_bad = True
if self._is_current_word_bad:
self._bad_word_count += 1
self._bad_character_count += len(self._buffer)
self._is_current_word_bad = False
self._foreign_long_watch = False
self._buffer = ""
self._buffer_accent_count = 0
self._buffer_glyph_count = 0
elif (
character not in {"<", ">", "-", "=", "~", "|", "_"}
and character.isdigit() is False
and is_symbol(character)
):
self._is_current_word_bad = True
self._buffer += character
def reset(self) -> None: # Abstract
self._buffer = ""
self._is_current_word_bad = False
self._foreign_long_watch = False
self._bad_word_count = 0
self._word_count = 0
self._character_count = 0
self._bad_character_count = 0
self._foreign_long_count = 0
@property
def ratio(self) -> float:
if self._word_count <= 10 and self._foreign_long_count == 0:
return 0.0
return self._bad_character_count / self._character_count
class CjkUncommonPlugin(MessDetectorPlugin):
"""
Detect messy CJK text that probably means nothing.
"""
def __init__(self) -> None:
self._character_count: int = 0
self._uncommon_count: int = 0
def eligible(self, character: str) -> bool:
return is_cjk(character)
def feed(self, character: str) -> None:
self._character_count += 1
if is_cjk_uncommon(character):
self._uncommon_count += 1
return
def reset(self) -> None: # Abstract
self._character_count = 0
self._uncommon_count = 0
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
uncommon_form_usage: float = self._uncommon_count / self._character_count
# we can be pretty sure it's garbage when uncommon characters are widely
# used. otherwise it could just be traditional chinese for example.
return uncommon_form_usage / 10 if uncommon_form_usage > 0.5 else 0.0
class ArchaicUpperLowerPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._buf: bool = False
self._character_count_since_last_sep: int = 0
self._successive_upper_lower_count: int = 0
self._successive_upper_lower_count_final: int = 0
self._character_count: int = 0
self._last_alpha_seen: str | None = None
self._current_ascii_only: bool = True
def eligible(self, character: str) -> bool:
return True
def feed(self, character: str) -> None:
is_concerned = character.isalpha() and is_case_variable(character)
chunk_sep = is_concerned is False
if chunk_sep and self._character_count_since_last_sep > 0:
if (
self._character_count_since_last_sep <= 64
and character.isdigit() is False
and self._current_ascii_only is False
):
self._successive_upper_lower_count_final += (
self._successive_upper_lower_count
)
self._successive_upper_lower_count = 0
self._character_count_since_last_sep = 0
self._last_alpha_seen = None
self._buf = False
self._character_count += 1
self._current_ascii_only = True
return
if self._current_ascii_only is True and character.isascii() is False:
self._current_ascii_only = False
if self._last_alpha_seen is not None:
if (character.isupper() and self._last_alpha_seen.islower()) or (
character.islower() and self._last_alpha_seen.isupper()
):
if self._buf is True:
self._successive_upper_lower_count += 2
self._buf = False
else:
self._buf = True
else:
self._buf = False
self._character_count += 1
self._character_count_since_last_sep += 1
self._last_alpha_seen = character
def reset(self) -> None: # Abstract
self._character_count = 0
self._character_count_since_last_sep = 0
self._successive_upper_lower_count = 0
self._successive_upper_lower_count_final = 0
self._last_alpha_seen = None
self._buf = False
self._current_ascii_only = True
@property
def ratio(self) -> float:
if self._character_count == 0:
return 0.0
return self._successive_upper_lower_count_final / self._character_count
class ArabicIsolatedFormPlugin(MessDetectorPlugin):
def __init__(self) -> None:
self._character_count: int = 0
self._isolated_form_count: int = 0
def reset(self) -> None: # Abstract
self._character_count = 0
self._isolated_form_count = 0
def eligible(self, character: str) -> bool:
return is_arabic(character)
def feed(self, character: str) -> None:
self._character_count += 1
if is_arabic_isolated_form(character):
self._isolated_form_count += 1
@property
def ratio(self) -> float:
if self._character_count < 8:
return 0.0
isolated_form_usage: float = self._isolated_form_count / self._character_count
return isolated_form_usage
@lru_cache(maxsize=1024)
def is_suspiciously_successive_range(
unicode_range_a: str | None, unicode_range_b: str | None
) -> bool:
"""
Determine if two Unicode range seen next to each other can be considered as suspicious.
"""
if unicode_range_a is None or unicode_range_b is None:
return True
if unicode_range_a == unicode_range_b:
return False
if "Latin" in unicode_range_a and "Latin" in unicode_range_b:
return False
if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b:
return False
# Latin characters can be accompanied with a combining diacritical mark
# eg. Vietnamese.
if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and (
"Combining" in unicode_range_a or "Combining" in unicode_range_b
):
return False
keywords_range_a, keywords_range_b = (
unicode_range_a.split(" "),
unicode_range_b.split(" "),
)
for el in keywords_range_a:
if el in UNICODE_SECONDARY_RANGE_KEYWORD:
continue
if el in keywords_range_b:
return False
# Japanese Exception
range_a_jp_chars, range_b_jp_chars = (
unicode_range_a
in (
"Hiragana",
"Katakana",
),
unicode_range_b in ("Hiragana", "Katakana"),
)
if (range_a_jp_chars or range_b_jp_chars) and (
"CJK" in unicode_range_a or "CJK" in unicode_range_b
):
return False
if range_a_jp_chars and range_b_jp_chars:
return False
if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b:
if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
return False
if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
return False
# Chinese/Japanese use dedicated range for punctuation and/or separators.
if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or (
unicode_range_a in ["Katakana", "Hiragana"]
and unicode_range_b in ["Katakana", "Hiragana"]
):
if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b:
return False
if "Forms" in unicode_range_a or "Forms" in unicode_range_b:
return False
if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
return False
return True
@lru_cache(maxsize=2048)
def mess_ratio(
decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False
) -> float:
"""
Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier.
"""
detectors: list[MessDetectorPlugin] = [
md_class() for md_class in MessDetectorPlugin.__subclasses__()
]
length: int = len(decoded_sequence) + 1
mean_mess_ratio: float = 0.0
if length < 512:
intermediary_mean_mess_ratio_calc: int = 32
elif length <= 1024:
intermediary_mean_mess_ratio_calc = 64
else:
intermediary_mean_mess_ratio_calc = 128
for character, index in zip(decoded_sequence + "\n", range(length)):
for detector in detectors:
if detector.eligible(character):
detector.feed(character)
if (
index > 0 and index % intermediary_mean_mess_ratio_calc == 0
) or index == length - 1:
mean_mess_ratio = sum(dt.ratio for dt in detectors)
if mean_mess_ratio >= maximum_threshold:
break
if debug:
logger = getLogger("charset_normalizer")
logger.log(
TRACE,
"Mess-detector extended-analysis start. "
f"intermediary_mean_mess_ratio_calc={intermediary_mean_mess_ratio_calc} mean_mess_ratio={mean_mess_ratio} "
f"maximum_threshold={maximum_threshold}",
)
if len(decoded_sequence) > 16:
logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}")
logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}")
for dt in detectors:
logger.log(TRACE, f"{dt.__class__}: {dt.ratio}")
return round(mean_mess_ratio, 3)

BIN
apps/bitwarden_event_logs/lib/charset_normalizer/md__mypyc.cpython-39-aarch64-linux-gnu.so
View File

Binary file not shown.

360
apps/bitwarden_event_logs/lib/charset_normalizer/models.py
Unescape View File

@ -1,360 +0,0 @@
from __future__ import annotations
from encodings.aliases import aliases
from hashlib import sha256
from json import dumps
from re import sub
from typing import Any, Iterator, List, Tuple
from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE
from .utils import iana_name, is_multi_byte_encoding, unicode_range
class CharsetMatch:
def __init__(
self,
payload: bytes,
guessed_encoding: str,
mean_mess_ratio: float,
has_sig_or_bom: bool,
languages: CoherenceMatches,
decoded_payload: str | None = None,
preemptive_declaration: str | None = None,
):
self._payload: bytes = payload
self._encoding: str = guessed_encoding
self._mean_mess_ratio: float = mean_mess_ratio
self._languages: CoherenceMatches = languages
self._has_sig_or_bom: bool = has_sig_or_bom
self._unicode_ranges: list[str] | None = None
self._leaves: list[CharsetMatch] = []
self._mean_coherence_ratio: float = 0.0
self._output_payload: bytes | None = None
self._output_encoding: str | None = None
self._string: str | None = decoded_payload
self._preemptive_declaration: str | None = preemptive_declaration
def __eq__(self, other: object) -> bool:
if not isinstance(other, CharsetMatch):
if isinstance(other, str):
return iana_name(other) == self.encoding
return False
return self.encoding == other.encoding and self.fingerprint == other.fingerprint
def __lt__(self, other: object) -> bool:
"""
Implemented to make sorted available upon CharsetMatches items.
"""
if not isinstance(other, CharsetMatch):
raise ValueError
chaos_difference: float = abs(self.chaos - other.chaos)
coherence_difference: float = abs(self.coherence - other.coherence)
# Below 1% difference --> Use Coherence
if chaos_difference < 0.01 and coherence_difference > 0.02:
return self.coherence > other.coherence
elif chaos_difference < 0.01 and coherence_difference <= 0.02:
# When having a difficult decision, use the result that decoded as many multi-byte as possible.
# preserve RAM usage!
if len(self._payload) >= TOO_BIG_SEQUENCE:
return self.chaos < other.chaos
return self.multi_byte_usage > other.multi_byte_usage
return self.chaos < other.chaos
@property
def multi_byte_usage(self) -> float:
return 1.0 - (len(str(self)) / len(self.raw))
def __str__(self) -> str:
# Lazy Str Loading
if self._string is None:
self._string = str(self._payload, self._encoding, "strict")
return self._string
def __repr__(self) -> str:
return f"<CharsetMatch '{self.encoding}' bytes({self.fingerprint})>"
def add_submatch(self, other: CharsetMatch) -> None:
if not isinstance(other, CharsetMatch) or other == self:
raise ValueError(
"Unable to add instance <{}> as a submatch of a CharsetMatch".format(
other.__class__
)
)
other._string = None # Unload RAM usage; dirty trick.
self._leaves.append(other)
@property
def encoding(self) -> str:
return self._encoding
@property
def encoding_aliases(self) -> list[str]:
"""
Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
"""
also_known_as: list[str] = []
for u, p in aliases.items():
if self.encoding == u:
also_known_as.append(p)
elif self.encoding == p:
also_known_as.append(u)
return also_known_as
@property
def bom(self) -> bool:
return self._has_sig_or_bom
@property
def byte_order_mark(self) -> bool:
return self._has_sig_or_bom
@property
def languages(self) -> list[str]:
"""
Return the complete list of possible languages found in decoded sequence.
Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
"""
return [e[0] for e in self._languages]
@property
def language(self) -> str:
"""
Most probable language found in decoded sequence. If none were detected or inferred, the property will return
"Unknown".
"""
if not self._languages:
# Trying to infer the language based on the given encoding
# Its either English or we should not pronounce ourselves in certain cases.
if "ascii" in self.could_be_from_charset:
return "English"
# doing it there to avoid circular import
from charset_normalizer.cd import encoding_languages, mb_encoding_languages
languages = (
mb_encoding_languages(self.encoding)
if is_multi_byte_encoding(self.encoding)
else encoding_languages(self.encoding)
)
if len(languages) == 0 or "Latin Based" in languages:
return "Unknown"
return languages[0]
return self._languages[0][0]
@property
def chaos(self) -> float:
return self._mean_mess_ratio
@property
def coherence(self) -> float:
if not self._languages:
return 0.0
return self._languages[0][1]
@property
def percent_chaos(self) -> float:
return round(self.chaos * 100, ndigits=3)
@property
def percent_coherence(self) -> float:
return round(self.coherence * 100, ndigits=3)
@property
def raw(self) -> bytes:
"""
Original untouched bytes.
"""
return self._payload
@property
def submatch(self) -> list[CharsetMatch]:
return self._leaves
@property
def has_submatch(self) -> bool:
return len(self._leaves) > 0
@property
def alphabets(self) -> list[str]:
if self._unicode_ranges is not None:
return self._unicode_ranges
# list detected ranges
detected_ranges: list[str | None] = [unicode_range(char) for char in str(self)]
# filter and sort
self._unicode_ranges = sorted(list({r for r in detected_ranges if r}))
return self._unicode_ranges
@property
def could_be_from_charset(self) -> list[str]:
"""
The complete list of encoding that output the exact SAME str result and therefore could be the originating
encoding.
This list does include the encoding available in property 'encoding'.
"""
return [self._encoding] + [m.encoding for m in self._leaves]
def output(self, encoding: str = "utf_8") -> bytes:
"""
Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
Any errors will be simply ignored by the encoder NOT replaced.
"""
if self._output_encoding is None or self._output_encoding != encoding:
self._output_encoding = encoding
decoded_string = str(self)
if (
self._preemptive_declaration is not None
and self._preemptive_declaration.lower()
not in ["utf-8", "utf8", "utf_8"]
):
patched_header = sub(
RE_POSSIBLE_ENCODING_INDICATION,
lambda m: m.string[m.span()[0] : m.span()[1]].replace(
m.groups()[0],
iana_name(self._output_encoding).replace("_", "-"), # type: ignore[arg-type]
),
decoded_string[:8192],
count=1,
)
decoded_string = patched_header + decoded_string[8192:]
self._output_payload = decoded_string.encode(encoding, "replace")
return self._output_payload # type: ignore
@property
def fingerprint(self) -> str:
"""
Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
"""
return sha256(self.output()).hexdigest()
class CharsetMatches:
"""
Container with every CharsetMatch items ordered by default from most probable to the less one.
Act like a list(iterable) but does not implements all related methods.
"""
def __init__(self, results: list[CharsetMatch] | None = None):
self._results: list[CharsetMatch] = sorted(results) if results else []
def __iter__(self) -> Iterator[CharsetMatch]:
yield from self._results
def __getitem__(self, item: int | str) -> CharsetMatch:
"""
Retrieve a single item either by its position or encoding name (alias may be used here).
Raise KeyError upon invalid index or encoding not present in results.
"""
if isinstance(item, int):
return self._results[item]
if isinstance(item, str):
item = iana_name(item, False)
for result in self._results:
if item in result.could_be_from_charset:
return result
raise KeyError
def __len__(self) -> int:
return len(self._results)
def __bool__(self) -> bool:
return len(self._results) > 0
def append(self, item: CharsetMatch) -> None:
"""
Insert a single match. Will be inserted accordingly to preserve sort.
Can be inserted as a submatch.
"""
if not isinstance(item, CharsetMatch):
raise ValueError(
"Cannot append instance '{}' to CharsetMatches".format(
str(item.__class__)
)
)
# We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
if len(item.raw) < TOO_BIG_SEQUENCE:
for match in self._results:
if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
match.add_submatch(item)
return
self._results.append(item)
self._results = sorted(self._results)
def best(self) -> CharsetMatch | None:
"""
Simply return the first match. Strict equivalent to matches[0].
"""
if not self._results:
return None
return self._results[0]
def first(self) -> CharsetMatch | None:
"""
Redundant method, call the method best(). Kept for BC reasons.
"""
return self.best()
CoherenceMatch = Tuple[str, float]
CoherenceMatches = List[CoherenceMatch]
class CliDetectionResult:
def __init__(
self,
path: str,
encoding: str | None,
encoding_aliases: list[str],
alternative_encodings: list[str],
language: str,
alphabets: list[str],
has_sig_or_bom: bool,
chaos: float,
coherence: float,
unicode_path: str | None,
is_preferred: bool,
):
self.path: str = path
self.unicode_path: str | None = unicode_path
self.encoding: str | None = encoding
self.encoding_aliases: list[str] = encoding_aliases
self.alternative_encodings: list[str] = alternative_encodings
self.language: str = language
self.alphabets: list[str] = alphabets
self.has_sig_or_bom: bool = has_sig_or_bom
self.chaos: float = chaos
self.coherence: float = coherence
self.is_preferred: bool = is_preferred
@property
def __dict__(self) -> dict[str, Any]: # type: ignore
return {
"path": self.path,
"encoding": self.encoding,
"encoding_aliases": self.encoding_aliases,
"alternative_encodings": self.alternative_encodings,
"language": self.language,
"alphabets": self.alphabets,
"has_sig_or_bom": self.has_sig_or_bom,
"chaos": self.chaos,
"coherence": self.coherence,
"unicode_path": self.unicode_path,
"is_preferred": self.is_preferred,
}
def to_json(self) -> str:
return dumps(self.__dict__, ensure_ascii=True, indent=4)

0
apps/bitwarden_event_logs/lib/charset_normalizer/py.typed
Unescape View File

414
apps/bitwarden_event_logs/lib/charset_normalizer/utils.py
Unescape View File

@ -1,414 +0,0 @@
from __future__ import annotations
import importlib
import logging
import unicodedata
from codecs import IncrementalDecoder
from encodings.aliases import aliases
from functools import lru_cache
from re import findall
from typing import Generator
from _multibytecodec import ( # type: ignore[import-not-found,import]
MultibyteIncrementalDecoder,
)
from .constant import (
ENCODING_MARKS,
IANA_SUPPORTED_SIMILAR,
RE_POSSIBLE_ENCODING_INDICATION,
UNICODE_RANGES_COMBINED,
UNICODE_SECONDARY_RANGE_KEYWORD,
UTF8_MAXIMAL_ALLOCATION,
COMMON_CJK_CHARACTERS,
)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_accentuated(character: str) -> bool:
try:
description: str = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return (
"WITH GRAVE" in description
or "WITH ACUTE" in description
or "WITH CEDILLA" in description
or "WITH DIAERESIS" in description
or "WITH CIRCUMFLEX" in description
or "WITH TILDE" in description
or "WITH MACRON" in description
or "WITH RING ABOVE" in description
)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def remove_accent(character: str) -> str:
decomposed: str = unicodedata.decomposition(character)
if not decomposed:
return character
codes: list[str] = decomposed.split(" ")
return chr(int(codes[0], 16))
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def unicode_range(character: str) -> str | None:
"""
Retrieve the Unicode range official name from a single character.
"""
character_ord: int = ord(character)
for range_name, ord_range in UNICODE_RANGES_COMBINED.items():
if character_ord in ord_range:
return range_name
return None
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_latin(character: str) -> bool:
try:
description: str = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "LATIN" in description
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_punctuation(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "P" in character_category:
return True
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Punctuation" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_symbol(character: str) -> bool:
character_category: str = unicodedata.category(character)
if "S" in character_category or "N" in character_category:
return True
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Forms" in character_range and character_category != "Lo"
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_emoticon(character: str) -> bool:
character_range: str | None = unicode_range(character)
if character_range is None:
return False
return "Emoticons" in character_range or "Pictographs" in character_range
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_separator(character: str) -> bool:
if character.isspace() or character in {"｜", "+", "<", ">"}:
return True
character_category: str = unicodedata.category(character)
return "Z" in character_category or character_category in {"Po", "Pd", "Pc"}
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_case_variable(character: str) -> bool:
return character.islower() != character.isupper()
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "CJK" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hiragana(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "HIRAGANA" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_katakana(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "KATAKANA" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_hangul(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "HANGUL" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_thai(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "THAI" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "ARABIC" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_arabic_isolated_form(character: str) -> bool:
try:
character_name = unicodedata.name(character)
except ValueError: # Defensive: unicode database outdated?
return False
return "ARABIC" in character_name and "ISOLATED FORM" in character_name
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_cjk_uncommon(character: str) -> bool:
return character not in COMMON_CJK_CHARACTERS
@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
def is_unicode_range_secondary(range_name: str) -> bool:
return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)
@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
def is_unprintable(character: str) -> bool:
return (
character.isspace() is False # includes \n \t \r \v
and character.isprintable() is False
and character != "\x1a" # Why? Its the ASCII substitute character.
and character != "\ufeff" # bug discovered in Python,
# Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space.
)
def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> str | None:
"""
Extract using ASCII-only decoder any specified encoding in the first n-bytes.
"""
if not isinstance(sequence, bytes):
raise TypeError
seq_len: int = len(sequence)
results: list[str] = findall(
RE_POSSIBLE_ENCODING_INDICATION,
sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"),
)
if len(results) == 0:
return None
for specified_encoding in results:
specified_encoding = specified_encoding.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if encoding_alias == specified_encoding:
return encoding_iana
if encoding_iana == specified_encoding:
return encoding_iana
return None
@lru_cache(maxsize=128)
def is_multi_byte_encoding(name: str) -> bool:
"""
Verify is a specific encoding is a multi byte one based on it IANA name
"""
return name in {
"utf_8",
"utf_8_sig",
"utf_16",
"utf_16_be",
"utf_16_le",
"utf_32",
"utf_32_le",
"utf_32_be",
"utf_7",
} or issubclass(
importlib.import_module(f"encodings.{name}").IncrementalDecoder,
MultibyteIncrementalDecoder,
)
def identify_sig_or_bom(sequence: bytes) -> tuple[str | None, bytes]:
"""
Identify and extract SIG/BOM in given sequence.
"""
for iana_encoding in ENCODING_MARKS:
marks: bytes | list[bytes] = ENCODING_MARKS[iana_encoding]
if isinstance(marks, bytes):
marks = [marks]
for mark in marks:
if sequence.startswith(mark):
return iana_encoding, mark
return None, b""
def should_strip_sig_or_bom(iana_encoding: str) -> bool:
return iana_encoding not in {"utf_16", "utf_32"}
def iana_name(cp_name: str, strict: bool = True) -> str:
"""Returns the Python normalized encoding name (Not the IANA official name)."""
cp_name = cp_name.lower().replace("-", "_")
encoding_alias: str
encoding_iana: str
for encoding_alias, encoding_iana in aliases.items():
if cp_name in [encoding_alias, encoding_iana]:
return encoding_iana
if strict:
raise ValueError(f"Unable to retrieve IANA for '{cp_name}'")
return cp_name
def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
return 0.0
decoder_a = importlib.import_module(f"encodings.{iana_name_a}").IncrementalDecoder
decoder_b = importlib.import_module(f"encodings.{iana_name_b}").IncrementalDecoder
id_a: IncrementalDecoder = decoder_a(errors="ignore")
id_b: IncrementalDecoder = decoder_b(errors="ignore")
character_match_count: int = 0
for i in range(255):
to_be_decoded: bytes = bytes([i])
if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
character_match_count += 1
return character_match_count / 254
def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
"""
Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
the function cp_similarity.
"""
return (
iana_name_a in IANA_SUPPORTED_SIMILAR
and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]
)
def set_logging_handler(
name: str = "charset_normalizer",
level: int = logging.INFO,
format_string: str = "%(asctime)s | %(levelname)s | %(message)s",
) -> None:
logger = logging.getLogger(name)
logger.setLevel(level)
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter(format_string))
logger.addHandler(handler)
def cut_sequence_chunks(
sequences: bytes,
encoding_iana: str,
offsets: range,
chunk_size: int,
bom_or_sig_available: bool,
strip_sig_or_bom: bool,
sig_payload: bytes,
is_multi_byte_decoder: bool,
decoded_payload: str | None = None,
) -> Generator[str, None, None]:
if decoded_payload and is_multi_byte_decoder is False:
for i in offsets:
chunk = decoded_payload[i : i + chunk_size]
if not chunk:
break
yield chunk
else:
for i in offsets:
chunk_end = i + chunk_size
if chunk_end > len(sequences) + 8:
continue
cut_sequence = sequences[i : i + chunk_size]
if bom_or_sig_available and strip_sig_or_bom is False:
cut_sequence = sig_payload + cut_sequence
chunk = cut_sequence.decode(
encoding_iana,
errors="ignore" if is_multi_byte_decoder else "strict",
)
# multi-byte bad cutting detector and adjustment
# not the cleanest way to perform that fix but clever enough for now.
if is_multi_byte_decoder and i > 0:
chunk_partial_size_chk: int = min(chunk_size, 16)
if (
decoded_payload
and chunk[:chunk_partial_size_chk] not in decoded_payload
):
for j in range(i, i - 4, -1):
cut_sequence = sequences[j:chunk_end]
if bom_or_sig_available and strip_sig_or_bom is False:
cut_sequence = sig_payload + cut_sequence
chunk = cut_sequence.decode(encoding_iana, errors="ignore")
if chunk[:chunk_partial_size_chk] in decoded_payload:
break
yield chunk

8
apps/bitwarden_event_logs/lib/charset_normalizer/version.py
Unescape View File

@ -1,8 +0,0 @@
"""
Expose version
"""
from __future__ import annotations
__version__ = "3.4.4"
VERSION = __version__.split(".")

24
apps/bitwarden_event_logs/lib/dateutil/__init__.py
Unescape View File

@ -1,24 +0,0 @@
# -*- coding: utf-8 -*-
import sys
try:
from ._version import version as __version__
except ImportError:
__version__ = 'unknown'
__all__ = ['easter', 'parser', 'relativedelta', 'rrule', 'tz',
'utils', 'zoneinfo']
def __getattr__(name):
import importlib
if name in __all__:
return importlib.import_module("." + name, __name__)
raise AttributeError(
"module {!r} has not attribute {!r}".format(__name__, name)
)
def __dir__():
# __dir__ should include all the lazy-importable modules as well.
return [x for x in globals() if x not in sys.modules] + __all__

BIN
apps/bitwarden_event_logs/lib/dateutil/__pycache__/__init__.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/dateutil/__pycache__/_common.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/dateutil/__pycache__/_version.cpython-39.pyc
View File

Binary file not shown.

BIN
apps/bitwarden_event_logs/lib/dateutil/__pycache__/relativedelta.cpython-39.pyc
View File

Binary file not shown.

43
apps/bitwarden_event_logs/lib/dateutil/_common.py
Unescape View File

@ -1,43 +0,0 @@
"""
Common code used in multiple modules.
"""
class weekday(object):
__slots__ = ["weekday", "n"]
def __init__(self, weekday, n=None):
self.weekday = weekday
self.n = n
def __call__(self, n):
if n == self.n:
return self
else:
return self.__class__(self.weekday, n)
def __eq__(self, other):
try:
if self.weekday != other.weekday or self.n != other.n:
return False
except AttributeError:
return False
return True
def __hash__(self):
return hash((
self.weekday,
self.n,
))
def __ne__(self, other):
return not (self == other)
def __repr__(self):
s = ("MO", "TU", "WE", "TH", "FR", "SA", "SU")[self.weekday]
if not self.n:
return s
else:
return "%s(%+d)" % (s, self.n)
# vim:ts=4:sw=4:et

4
apps/bitwarden_event_logs/lib/dateutil/_version.py
Unescape View File

@ -1,4 +0,0 @@
# file generated by setuptools_scm
# don't change, don't track in version control
__version__ = version = '2.9.0.post0'
__version_tuple__ = version_tuple = (2, 9, 0)

89
apps/bitwarden_event_logs/lib/dateutil/easter.py
Unescape View File

@ -1,89 +0,0 @@
# -*- coding: utf-8 -*-
"""
This module offers a generic Easter computing method for any given year, using
Western, Orthodox or Julian algorithms.
"""
import datetime
__all__ = ["easter", "EASTER_JULIAN", "EASTER_ORTHODOX", "EASTER_WESTERN"]
EASTER_JULIAN = 1
EASTER_ORTHODOX = 2
EASTER_WESTERN = 3
def easter(year, method=EASTER_WESTERN):
"""
This method was ported from the work done by GM Arts,
on top of the algorithm by Claus Tondering, which was
based in part on the algorithm of Ouding (1940), as
quoted in "Explanatory Supplement to the Astronomical
Almanac", P. Kenneth Seidelmann, editor.
This algorithm implements three different Easter
calculation methods:
1. Original calculation in Julian calendar, valid in
dates after 326 AD
2. Original method, with date converted to Gregorian
calendar, valid in years 1583 to 4099
3. Revised method, in Gregorian calendar, valid in
years 1583 to 4099 as well
These methods are represented by the constants:
* ``EASTER_JULIAN = 1``
* ``EASTER_ORTHODOX = 2``
* ``EASTER_WESTERN = 3``
The default method is method 3.
More about the algorithm may be found at:
`GM Arts: Easter Algorithms <http://www.gmarts.org/index.php?go=415>`_
and
`The Calendar FAQ: Easter <https://www.tondering.dk/claus/cal/easter.php>`_
"""
if not (1 <= method <= 3):
raise ValueError("invalid method")
# g - Golden year - 1
# c - Century
# h - (23 - Epact) mod 30
# i - Number of days from March 21 to Paschal Full Moon
# j - Weekday for PFM (0=Sunday, etc)
# p - Number of days from March 21 to Sunday on or before PFM
# (-6 to 28 methods 1 & 3, to 56 for method 2)
# e - Extra days to add for method 2 (converting Julian
# date to Gregorian date)
y = year
g = y % 19
e = 0
if method < 3:
# Old method
i = (19*g + 15) % 30
j = (y + y//4 + i) % 7
if method == 2:
# Extra dates to convert Julian to Gregorian date
e = 10
if y > 1600:
e = e + y//100 - 16 - (y//100 - 16)//4
else:
# New method
c = y//100
h = (c - c//4 - (8*c + 13)//25 + 19*g + 15) % 30
i = h - (h//28)*(1 - (h//28)*(29//(h + 1))*((21 - g)//11))
j = (y + y//4 + i + 2 - c + c//4) % 7
# p can be from -6 to 56 corresponding to dates 22 March to 23 May
# (later dates apply to method 2, although 23 May never actually occurs)
p = i - j + e
d = 1 + (p + 27 + (p + 6)//40) % 31
m = 3 + (p + 26)//30
return datetime.date(int(y), int(m), int(d))

61
apps/bitwarden_event_logs/lib/dateutil/parser/__init__.py
Unescape View File

@ -1,61 +0,0 @@
# -*- coding: utf-8 -*-
from ._parser import parse, parser, parserinfo, ParserError
from ._parser import DEFAULTPARSER, DEFAULTTZPARSER
from ._parser import UnknownTimezoneWarning
from ._parser import __doc__
from .isoparser import isoparser, isoparse
__all__ = ['parse', 'parser', 'parserinfo',
'isoparse', 'isoparser',
'ParserError',
'UnknownTimezoneWarning']
###
# Deprecate portions of the private interface so that downstream code that
# is improperly relying on it is given *some* notice.
def __deprecated_private_func(f):
from functools import wraps
import warnings
msg = ('{name} is a private function and may break without warning, '
'it will be moved and or renamed in future versions.')
msg = msg.format(name=f.__name__)
@wraps(f)
def deprecated_func(*args, **kwargs):
warnings.warn(msg, DeprecationWarning)
return f(*args, **kwargs)
return deprecated_func
def __deprecate_private_class(c):
import warnings
msg = ('{name} is a private class and may break without warning, '
'it will be moved and or renamed in future versions.')
msg = msg.format(name=c.__name__)
class private_class(c):
__doc__ = c.__doc__
def __init__(self, *args, **kwargs):
warnings.warn(msg, DeprecationWarning)
super(private_class, self).__init__(*args, **kwargs)
private_class.__name__ = c.__name__
return private_class
from ._parser import _timelex, _resultbase
from ._parser import _tzparser, _parsetz
_timelex = __deprecate_private_class(_timelex)
_tzparser = __deprecate_private_class(_tzparser)
_resultbase = __deprecate_private_class(_resultbase)
_parsetz = __deprecated_private_func(_parsetz)

BIN
apps/bitwarden_event_logs/lib/dateutil/parser/__pycache__/__init__.cpython-39.pyc
View File

Binary file not shown.

Some files were not shown because too many files have changed in this diff Show More

Write Preview
Loading…
Cancel
Save