Merge remote-tracking branch 'origin/topic/awelzel/license-header-cleanup'

* origin/topic/awelzel/license-header-cleanup:
  Add missing copyright line to headers and cc files
  pre-commit: Add license-header check inspired by Spicy
  Add missing "COPYING" in file comments

.pre-commit-config.yaml

@@ -2,6 +2,17 @@
 # See https://pre-commit.com/hooks.html for more hooks
 #
 repos:
+- repo: local
+  hooks:
+  - id: license
+    name: Check for license headers
+    entry: ./ci/license-header.py
+    language: python
+    types_or:
+      - "c"
+      - "c++"
+    exclude: '^(testing/btest/plugins/.*|testing/builtin-plugins/.*)$'
+
 - repo: https://github.com/pre-commit/mirrors-clang-format
   rev: 'v19.1.4'
   hooks:

CHANGES

@@ -1,3 +1,14 @@
+7.1.0-dev.720 | 2024-12-09 12:22:44 -0700
+
+  * Add missing copyright line to headers and cc files (Arne Welzel, Corelight)
+
+  * pre-commit: Add license-header check inspired by Spicy (Arne Welzel, Corelight)
+
+  * Add missing "COPYING" in file comments (Arne Welzel, Corelight)
+
+    This was just done via sed. There's a number of files that don't
+    have a license entry at all.
+
 7.1.0-dev.716 | 2024-12-09 12:15:46 -0700
 
   * BTest baseline updates for compile-to-C++ (Vern Paxson, Corelight)

VERSION

@@ -1 +1 @@
-7.1.0-dev.716
+7.1.0-dev.720

ci/license-header.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+
+import sys
+import re
+
+exit_code = 0
+
+pat1 = re.compile(r"See the file \"COPYING\" in the main distribution directory for copyright.")
+
+# This is the copyright line used within Spicy plugin and popular in
+# Spicy analyzers.
+pat2 = re.compile(r"Copyright \(c\) 2... by the Zeek Project. See COPYING for details.")
+
+
+def match_line(line):
+    for pat in [pat1, pat2]:
+        m = pat.search(line)
+        if m is not None:
+            return True
+
+    return False
+
+
+for f in sys.argv[1:]:
+    has_license_header = False
+    with open(f) as fp:
+        for line in fp:
+            line = line.strip()
+            if has_license_header := match_line(line):
+                break
+
+    if not has_license_header:
+        print(f"{f}:does not seem to contain a license header", file=sys.stderr)
+        exit_code = 1
+
+sys.exit(exit_code)

src/Anon.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/Anon.h"
 
 #include <sys/time.h>

src/Anon.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // The prefix-preserving IP address anonymization code is largely
 // based on (and sometimes directly copied from) Eddie Kohler's
 // ipsumdump-1.20 code, per:

src/Base64.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/Base64.h"
 
 #include "zeek/zeek-config.h"

src/Base64.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include "zeek/zeek-config.h"

src/DNS_Mapping.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/DNS_Mapping.h"
 
 #include <ares_nameser.h>

src/DNS_Mapping.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <netdb.h>

src/DbgBreakpoint.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Implementation of breakpoints.
 
 #include "zeek/DbgBreakpoint.h"

src/DbgBreakpoint.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Structures and methods for implementing breakpoints in the Zeek debugger.
 
 #pragma once

src/DbgDisplay.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Structures and methods for implementing watches in the Zeek debugger.
 
 #pragma once

src/DbgHelp.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Zeek Debugger Help
 
 #include "zeek/zeek-config.h"

src/DbgWatch.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Implementation of watches
 
 #include "zeek/DbgWatch.h"

src/DbgWatch.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Structures and methods for implementing watches in the Zeek debugger.
 
 #pragma once

src/Debug.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Debugging support for Zeek policy files.
 
 #include "zeek/Debug.h"

src/Debug.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Debugging support for Zeek policy files.
 
 #pragma once

src/DebugCmds.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Support routines to help deal with Zeek debugging commands and
 // implementation of most commands.
 

src/DebugCmds.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Support routines to help deal with Zeek debugging commands and
 // implementation of most commands.
 

src/DebugLogger.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #ifdef DEBUG
 
 #include "zeek/DebugLogger.h"

src/DebugLogger.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // A logger for (selective) debugging output. Only compiled in if DEBUG is
 // defined.
 

src/EventHandler.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/EventHandler.h"
 
 #include "zeek/Desc.h"

src/EventHandler.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Capsulates local and remote event handlers.
 
 #pragma once

src/EventLauncher.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/EventLauncher.h"
 
 #include "event.bif.func_def"

src/EventLauncher.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include "zeek/Conn.h"

src/EventRegistry.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/EventRegistry.h"
 
 #include <algorithm>

src/EventRegistry.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Each event raised/handled by Zeek is registered in the EventRegistry.
 
 #pragma once

src/EventTrace.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Classes for tracing/dumping Zeek events.
 
 #pragma once

src/IntSet.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/IntSet.h"
 
 #include "zeek/zeek-config.h"

src/IntSet.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // A simple but fast data structure for sets of integers.
 // Only supported operations are insert, remove and membership test.
 //

src/List.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/List.h"
 
 #include "zeek/3rdparty/doctest.h"

src/List.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 // BaseList.h --

src/PacketFilter.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/PacketFilter.h"
 
 #include "zeek/IP.h"

src/PacketFilter.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Provides some very limited but fast packet filter mechanisms
 
 #pragma once

src/PolicyFile.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/PolicyFile.h"
 
 #include "zeek/zeek-config.h"

src/PolicyFile.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 // Functions for displaying the contents of policy files.

src/PrefixTable.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/PrefixTable.h"
 
 #include "zeek/Reporter.h"

src/PrefixTable.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 extern "C" {

src/RandTest.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 /*
     Apply various randomness tests to a stream of bytes
 

src/RandTest.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include "zeek/zeek-config.h"

src/Rule.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/Rule.h"
 
 #include "zeek/zeek-config.h"

src/Rule.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <climits>

src/RuleAction.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/RuleAction.h"
 
 #include "zeek/zeek-config.h"

src/RuleAction.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <sys/types.h> // for u_char

src/RuleCondition.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/RuleCondition.h"
 
 #include "zeek/zeek-config.h"

src/RuleCondition.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <sys/types.h> // for u_char

src/RuleMatcher.cc

@@ -1,3 +1,4 @@
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/RuleMatcher.h"
 

src/RuleMatcher.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <sys/types.h> // for u_char

src/ScannedFile.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/ScannedFile.h"
 
 #include <cerrno>

src/ScriptCoverageManager.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/ScriptCoverageManager.h"
 
 #include <sys/stat.h>

src/ScriptCoverageManager.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <list>

src/ScriptValidation.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/ScriptValidation.h"
 
 #include "zeek/Func.h"

src/SerializationFormat.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/SerializationFormat.h"
 
 #include <cctype>

src/SerializationFormat.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Implements different data formats for serialization.
 
 #pragma once

src/Stats.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/Stats.h"
 
 #include <sys/resource.h>

src/Stats.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Classes that collect and report statistics.
 
 #pragma once

src/Trigger.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/Trigger.h"
 
 #include <algorithm>

src/Trigger.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <list>

src/WeirdState.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/WeirdState.h"
 
 #include "zeek/RunState.h"

src/ZeekArgs.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/ZeekArgs.h"
 
 #include "zeek/Desc.h"

src/analyzer/protocol/bittorrent/BitTorrent.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // This code contributed by Nadi Sarrar.
 
 #include "zeek/analyzer/protocol/bittorrent/BitTorrent.h"

src/analyzer/protocol/bittorrent/BitTorrent.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // This code contributed by Nadi Sarrar.
 
 #pragma once

src/analyzer/protocol/bittorrent/BitTorrentTracker.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // This code contributed by Nadi Sarrar.
 
 #include "zeek/analyzer/protocol/bittorrent/BitTorrentTracker.h"

src/analyzer/protocol/bittorrent/BitTorrentTracker.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // This code contributed by Nadi Sarrar.
 
 #pragma once

src/analyzer/protocol/bittorrent/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/conn-size/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/dce-rpc/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/dhcp/DHCP.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/analyzer/protocol/dhcp/DHCP.h"
 
 #include "zeek/analyzer/protocol/dhcp/events.bif.h"

src/analyzer/protocol/dhcp/DHCP.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include "analyzer/protocol/dhcp/dhcp_pac.h"

src/analyzer/protocol/dhcp/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/dnp3/DNP3.cc

@@ -1,4 +1,5 @@
-//
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // DNP3 was initially used over serial links; it defined its own application
 // layer, transport layer, and data link layer. This hierarchy cannot be
 // mapped to the TCP/IP stack directly. As a result, all three DNP3 layers

src/analyzer/protocol/dnp3/DNP3.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include "zeek/analyzer/protocol/tcp/TCP.h"

src/analyzer/protocol/dnp3/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/dns/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/file/File.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/analyzer/protocol/file/File.h"
 
 #include <algorithm>

src/analyzer/protocol/file/File.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Analyzer for connections that transfer binary data.
 
 #pragma once

src/analyzer/protocol/file/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/finger/legacy/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/ftp/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/gnutella/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/gssapi/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/http/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/ident/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/imap/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/irc/IRC.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // An IRC analyzer contributed by Roland Gruber.
 
 #include "zeek/analyzer/protocol/irc/IRC.h"

src/analyzer/protocol/irc/IRC.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // An IRC analyzer contributed by Roland Gruber.
 
 #pragma once

src/analyzer/protocol/irc/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/krb/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/login/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/mime/MIME.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/analyzer/protocol/mime/MIME.h"
 
 #include "zeek/zeek-config.h"

src/analyzer/protocol/mime/MIME.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include <cassert>

src/analyzer/protocol/mime/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/modbus/Modbus.cc

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #include "zeek/analyzer/protocol/modbus/Modbus.h"
 
 #include "zeek/analyzer/protocol/modbus/events.bif.h"

src/analyzer/protocol/modbus/Modbus.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 #pragma once
 
 #include "zeek/analyzer/protocol/tcp/TCP.h"

src/analyzer/protocol/modbus/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/mqtt/MQTT.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/analyzer/protocol/mqtt/MQTT.h"
 

src/analyzer/protocol/mqtt/MQTT.h

@@ -1,3 +1,5 @@
+// See the file "COPYING" in the main distribution directory for copyright.
+
 // Generated by binpac_quickstart
 
 #pragma once

src/analyzer/protocol/mqtt/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"
 

src/analyzer/protocol/ncp/Plugin.cc

@@ -1,4 +1,4 @@
-// See the file  in the main distribution directory for copyright.
+// See the file "COPYING" in the main distribution directory for copyright.
 
 #include "zeek/plugin/Plugin.h"