From 0e7696c64db78f698c40686d4869e2a8d0ab2696 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Thu, 4 Nov 2021 13:13:29 +0000 Subject: ci: disallow directional formatting As described in https://trojansource.codes/trojan-source.pdf, it is possible to abuse directional formatting (a feature of Unicode) to deceive human readers into interpreting code differently from compilers. For example, an "if ()" expression could be enclosed in a comment, but rendered as if it was outside of that comment. In effect, this could fool a reviewer into misinterpreting the code flow as benign when it is not. It is highly unlikely that Git's source code wants to contain such directional formatting in the first place, so let's just disallow it. Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- .github/workflows/main.yml | 1 + ci/check-directional-formatting.bash | 27 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) create mode 100755 ci/check-directional-formatting.bash diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index b053b01c66..6b35909e6c 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -287,6 +287,7 @@ jobs: - uses: actions/checkout@v2 - run: ci/install-dependencies.sh - run: ci/run-static-analysis.sh + - run: ci/check-directional-formatting.bash sparse: needs: ci-config if: needs.ci-config.outputs.enabled == 'yes' diff --git a/ci/check-directional-formatting.bash b/ci/check-directional-formatting.bash new file mode 100755 index 0000000000..e6211b141a --- /dev/null +++ b/ci/check-directional-formatting.bash @@ -0,0 +1,27 @@ +#!/bin/bash + +# This script verifies that the non-binary files tracked in the Git index do +# not contain any Unicode directional formatting: such formatting could be used +# to deceive reviewers into interpreting code differently from the compiler. +# This is intended to run on an Ubuntu agent in a GitHub workflow. +# +# To allow translated messages to introduce such directional formatting in the +# future, we exclude the `.po` files from this validation. +# +# Neither GNU grep nor `git grep` (not even with `-P`) handle `\u` as a way to +# specify UTF-8. +# +# To work around that, we use `printf` to produce the pattern as a byte +# sequence, and then feed that to `git grep` as a byte sequence (setting +# `LC_CTYPE` to make sure that the arguments are interpreted as intended). +# +# Note: we need to use Bash here because its `printf` interprets `\uNNNN` as +# UTF-8 code points, as desired. Running this script through Ubuntu's `dash`, +# for example, would use a `printf` that does not understand that syntax. + +# U+202a..U+2a2e: LRE, RLE, PDF, LRO and RLO +# U+2066..U+2069: LRI, RLI, FSI and PDI +regex='(\u202a|\u202b|\u202c|\u202d|\u202e|\u2066|\u2067|\u2068|\u2069)' + +! LC_CTYPE=C git grep -El "$(LC_CTYPE=C.UTF-8 printf "$regex")" \ + -- ':(exclude,attr:binary)' ':(exclude)*.po' -- cgit v1.2.3