diff --git a/.serena/.gitignore b/.serena/.gitignore new file mode 100644 index 00000000000..2e510aff585 --- /dev/null +++ b/.serena/.gitignore @@ -0,0 +1,2 @@ +/cache +/project.local.yml diff --git a/.serena/project.yml b/.serena/project.yml new file mode 100644 index 00000000000..3afa517402d --- /dev/null +++ b/.serena/project.yml @@ -0,0 +1,169 @@ +# the name by which the project can be referenced within Serena/when chatting with the LLM. +project_name: "filing-scapy" + +# list of language servers to start when using the LSP backend; choose from: +# ada al angular ansible bash +# bsl clojure cpp cpp_ccls crystal +# csharp csharp_omnisharp cue dart deno +# elixir elm erlang fortran fsharp +# gdscript gleam go groovy haskell +# haxe hlsl html java json +# julia julia_fatou kotlin latex lean4 +# lua luau markdown matlab msl +# nextflow nix ocaml pascal perl +# php php_phpactor php_phpantom powershell python +# python_basedpyright python_jedi python_pyrefly python_ty qml +# r rego ruby ruby_solargraph rust +# scala scss solidity svelte swift +# systemverilog terraform toml typescript typescript_vts +# vue wolfram yaml zig +# (This list may be outdated; generated with scripts/print_language_list.py; +# For the current list, see values of the LanguageServerId enum here: +# https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py) +# For some languages, there are several alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.) +# Note: +# - For C, use cpp +# - For JavaScript, use typescript +# - For Angular projects, use angular (subsumes typescript+html; requires `npm install` in the project root) +# - For Svelte projects, use svelte (subsumes typescript/javascript for .svelte projects; requires npm) +# - For Deno projects, use deno (serves the same .ts/.js files as typescript; requires the deno CLI on PATH) +# - For SCSS / Sass / plain CSS, use scss (some-sass-language-server handles all three) +# - For Free Pascal/Lazarus, use pascal +# Special requirements: +# Some language servers require additional setup/installations. +# See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers +# When using multiple language servers, the first language server that supports a given file will be used for that file. +# The first language server is the default language and the respective language server will be used as a fallback. +# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored. +language_servers: +- python + +# the encoding used by text files in the project +# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings +encoding: "utf-8" + +# optional shell command to run before the language backend (LSP or JetBrains) is initialised. +# the command runs in the project root directory and is only executed if the project is trusted +# (see trusted_project_path_patterns in the global configuration). +# serena waits for the command to exit: a non-zero exit code is logged as an error but does not +# abort activation. a per-project timeout (activation_command_timeout, default 180s) is the safety +# backstop for non-terminating commands; on expiry the process is killed and activation continues. +# example: activation_command: "npx nx run-many -t build" +activation_command: + +# maximum time in seconds to wait for activation_command to complete before killing it (default 180s). +# must be a positive number. +activation_command_timeout: 180.0 + +# line ending convention to use when writing source files. +# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default) +# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings. +line_ending: + +# The language backend to use for this project. +# If not set, the global setting from serena_config.yml is used. +# Valid values: LSP, JetBrains +# Note: the backend is fixed at startup. If a project with a different backend +# is activated post-init, an error will be returned. +language_backend: + +# whether to use project's .gitignore files to ignore files +ignore_all_files_in_gitignore: true + +# advanced configuration option allowing to configure language server-specific options. +# Maps the language key to the options. +# The settings are considered only if the project is trusted (see global configuration to define trusted projects). +# See https://oraios.github.io/serena/02-usage/050_configuration.html#language-server-specific-settings +ls_specific_settings: {} + +# list of workspace folder paths (LSP backend only). +# These folders will be used to build up Serena's symbol index. +# Paths must be within the project root and should thus be relative to the project root. +# Furthermore, the paths should not be filtered by ignore settings. +# Default setting: The entire project root folder (".") is considered. +# In (large) monorepos, this can be used to index only subfolders of the project root, e.g. +# ls_workspace_folders: +# - "./subproject1" +# - "./subproject2" +ls_workspace_folders: +- "." + +# list of additional workspace folder paths for cross-package reference support. +# Paths can be absolute or relative to the project root. +# Each folder is registered as an LSP workspace folder, enabling language servers to discover +# symbols and references across package boundaries, but these folders are not indexed by Serena, +# i.e. the respective symbols will not be found using Serena's symbol search tools. +# Example: +# additional_workspace_folders: +# - ../sibling-package +# - ../shared-lib +ls_additional_workspace_folders: [] + +# list of additional paths to ignore in this project. +# Same syntax as gitignore, so you can use * and **. +# Important: quote patterns that start with `*`, otherwise YAML treats them as aliases. +# Example: +# ignored_paths: +# - "examples/**" +# - ".worktrees/**" +# - "**/bin/**" +# - "**/obj/**" +# Note: global ignored_paths from serena_config.yml are also applied additively. +ignored_paths: [] + +# whether the project is in read-only mode +# If set to true, all editing tools will be disabled and attempts to use them will result in an error +# Added on 2025-04-18 +read_only: false + +# list of tool names to exclude. +# This extends the existing exclusions (e.g. from the global configuration) +# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html +excluded_tools: [] + +# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default). +# This extends the existing inclusions (e.g. from the global configuration). +# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html +included_optional_tools: [] + +# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools. +# This cannot be combined with non-empty excluded_tools or included_optional_tools. +# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html +fixed_tools: [] + +# list of mode names that are to be activated by default, overriding the setting in the global configuration. +# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes. +# If the setting is undefined/empty, the default_modes from the global configuration (serena_config.yml) apply. +# Otherwise, this overrides the setting from the global configuration (serena_config.yml). +# Therefore, you can set this to [] if you do not want the default modes defined in the global config to apply +# for this project. +# This setting can, in turn, be overridden by CLI parameters (--mode). +# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes +default_modes: + +# list of mode names to be activated additionally for this project, e.g. ["query-projects"] +# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes. +# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes +added_modes: + +# initial prompt for the project. It will always be given to the LLM upon activating the project +# (contrary to the memories, which are loaded on demand). +initial_prompt: "" + +# time budget (seconds) per tool call for the retrieval of additional symbol information +# such as docstrings or parameter information. +# This overrides the corresponding setting in the global configuration; see the documentation there. +# If null or missing, use the setting from the global configuration. +symbol_info_budget: + +# list of regex patterns which, when matched, mark a memory entry as read‑only. +# Extends the list from the global configuration, merging the two lists. +read_only_memory_patterns: [] + +# list of regex patterns for memories to completely ignore. +# Matching memories will not appear in list_memories or activate_project output +# and cannot be accessed via read_memory or write_memory. +# To access ignored memory files, use the read_file tool on the raw file path. +# Extends the list from the global configuration, merging the two lists. +# Example: ["_archive/.*", "_episodes/.*"] +ignored_memory_patterns: [] diff --git a/scapy/layers/inet.py b/scapy/layers/inet.py index 006875bd53e..443e2cd2f85 100644 --- a/scapy/layers/inet.py +++ b/scapy/layers/inet.py @@ -1493,13 +1493,21 @@ def _defrag_ip_pkt(pkt, frags): raise BadFragments(frags=badfrags) # re-build initial packet without fragmentation p = curfrags[0][0].copy() - pay_class = p[IP].payload.__class__ + pay_class = p[IP].guess_payload_class(data) p[IP].flags.MF = False p[IP].remove_payload() p[IP].len = None p[IP].chksum = None - # append defragmented payload - p /= pay_class(data) + # append defragmented payload. The reassembled bytes may still fail + # to dissect, and that has to fall back the way dissection itself + # does rather than escape into the caller's sniff loop. + try: + payload = pay_class(data) + except Exception: + if conf.debug_dissector: + raise + payload = conf.raw_layer(load=data) + p[IP].add_payload(payload) # cleanup del frags[uid] return True, p diff --git a/test/scapy/layers/inet.uts b/test/scapy/layers/inet.uts index 7803eb734f0..238608e90ea 100644 --- a/test/scapy/layers/inet.uts +++ b/test/scapy/layers/inet.uts @@ -604,6 +604,46 @@ with no_debug_dissector(reverse=True): split_layers(TCP, CustomPacket, sport=12345) += TCPSession parses application data after IPv4 defragmentation +~ http + +load_layer("http") + +def fragmented_http_response(fragsize): + payload = b"HTTP/1.1 200 OK\r\nContent-Length: 4\r\n\r\nBODY" + packet = ( + IP(src="192.0.2.1", dst="192.0.2.2", id=1234) / + TCP(sport=80, dport=2345, seq=1, flags="PA") / + Raw(payload) + ) + fragments = [IP(raw(pkt)) for pkt in fragment(packet, fragsize)] + return sniff(offline=fragments, session=TCPSession) + +with no_debug_dissector(): + for fragsize in (8, 24): + packets = fragmented_http_response(fragsize) + assert len(packets) == 1 + assert HTTPResponse in packets[0] + assert packets[0][Raw].load == b"BODY" + += Fragments reassembling to less than their protocol's header keep sniffing + +# The reassembled payload is shorter than a TCP header, so dissecting it fails. +# That must not escape: IPSession would close the socket and end the capture. +# no_debug_dissector() is required rather than incidental -- the campaign runs +# with conf.debug_dissector on, where dissection failures raise either way. + +with no_debug_dissector(): + short = [ + Ether() / IP(src="192.0.2.1", dst="192.0.2.2", id=99, proto=6, + flags="MF", frag=0) / Raw(b"A" * 8), + Ether() / IP(src="192.0.2.1", dst="192.0.2.2", id=99, proto=6, + frag=1) / Raw(b"B" * 4), + ] + short = [Ether(raw(pkt)) for pkt in short] + assert defragment([pkt[IP] for pkt in short])[0][Raw].load == b"A" * 8 + b"B" * 4 + assert len(sniff(offline=short, session=IPSession)) == 1 + = Layer binding