ci/bin/vendormark

#!/usr/bin/env bash
# vendormark — refuse a repo that carries a site-generator vendor's branding.
# One implementation, every caller.
#
#   vendormark [dir] [git-range]
#
# WHAT THIS CATCHES
#
# Several sites in the estate began life as output from a hosted "prompt to
# React app" generator. The generator does not sign its work in a comment you
# would notice — it signs it in the SHAPE of the repo, in four places at once:
#
#   1. an asset folder named after the vendor, e.g. public/<vendor>-uploads/,
#      so every image the browser requests carries the vendor's name in its URL
#   2. a build plugin dependency in package.json and the lockfiles
#   3. an injected third-party <script> tag in index.html
#   4. commit messages, author identities and Co-authored-by trailers written
#      by the vendor's bot
#
# The fourth is the one nothing else looks at, and the one that survives every
# amount of tidying the working tree: a repo can render a perfect page and
# still say, in `git log`, who really wrote it.
#
# This was not a hypothetical. A sweep of 1,065 repositories across the three
# orgs found the mark in five shipped sites — one of them serving the vendor's
# upload folder as its FAVICON, so the vendor's path was in the <head> of every
# page and in every browser tab. Purging it needed a history rewrite and a
# force-push of every branch. This gate exists so that is never needed twice.
#
# WHY THE CONTENT RULES ARE SO SPECIFIC
#
# The vendor's name is also an ordinary English adjective, and the naive gate —
# case-insensitive substring of that word — is unshippable. Measured across all
# 1,065 repos, the bare word appears legitimately in 20+ of them and NONE of
# them are contaminated:
#
#     tokenizer vocab.json (3 repos)     "lovable</w>": 38565
#     English word lists                 words_alpha.txt, faker adjectives
#     ML training/eval corpora           alpaca, kto, BAGEL eval prompts
#     x/net publicsuffix packed data     a substring of concatenated domains
#     vendored prompt corpora            third-party collections that quote it
#     our own marketing copy             a competitor named in a case study
#
# A gate that reds a fifth of the estate on day one is a gate someone switches
# off, and then we are worse off than before it existed. So the content rules
# are only the strings that CANNOT occur in prose: a path segment, an npm
# package name, an injected script URL, a generator meta tag, a bot's email.
#
# Two candidate rules were DROPPED after measuring them, and it is worth saying
# why: `lovableproject.com` and `lovable.app` red an upstream Clerk SDK bundle,
# which ships a list of dev-preview host suffixes naming several generators. A
# third party's honest list of other people's hosts is not our contamination.
# Those two strings are still refused in commit messages and git identities,
# where no third party can put them.
#
# PATHS AND IDENTITIES ARE ABSOLUTE
#
# Content is judged narrowly; paths and git identities are not. There is no
# legitimate reason for the vendor's name to appear in a filename we track or
# in an author, committer or Co-authored-by line we write. Those are refused on
# the bare word, no exceptions, because that is where the mark is load-bearing
# and where tidying the working tree never reaches.
#
# THE ESCAPE HATCH
#
# `.vendormark-allow` — one path glob per line, `#` comments ignored. It exists
# for exactly one honest case: a repo whose JOB is to name these vendors, such
# as the history-scrubber rule files in hanzoai/.github, which cannot do their
# work without spelling the string they remove. If you are reaching for it for
# any other reason, you are about to ship the mark.
#
# EXIT: 0 clean, 1 mark found.
set -uo pipefail

root=${1:-.}
range=${2:-}
cd "$root" 2>/dev/null || { echo "vendormark: no such directory: $root" >&2; exit 1; }
git rev-parse --git-dir >/dev/null 2>&1 || exit 0   # not a repo: nothing to check

# PATHS: the bare vendor name, no exceptions. Add a vendor here and its
# filenames are refused everywhere.
VENDORS='lovable'

# CONTENT: only strings that cannot occur in prose — an asset folder, an npm
# package, the injected script, a generator meta tag, the bot's address. Spelled
# out in full rather than composed from $VENDORS, because half of them do not
# contain the vendor's name at all. See the header for the two that were
# measured against the estate and dropped.
CONTENT_SIG='lovable-uploads/|lovable-tagger|@lovable\.dev|cdn\.gpteng\.co|gptengineer\.js|content="[Ll]ovable"'

# IDENTITIES AND MESSAGES: the bare word plus the vendor hosts, because nothing
# outside our own commits can write these.
IDENT_SIG='lovable|gptengineer|gpt-engineer'

fail=0
tmp=$(mktemp -d); trap 'rm -rf "$tmp"' EXIT

# --- allowlist ------------------------------------------------------------
: > "$tmp/allow"
if [ -f .vendormark-allow ]; then
  grep -vE '^\s*(#|$)' .vendormark-allow > "$tmp/allow" || true
fi
allowed() {  # $1 = path
  [ -s "$tmp/allow" ] || return 1
  while IFS= read -r g; do
    # shellcheck disable=SC2254
    case "$1" in $g) return 0;; esac
  done < "$tmp/allow"
  return 1
}

# --- 1. tracked paths -----------------------------------------------------
git ls-files 2>/dev/null | grep -iE "$VENDORS" > "$tmp/paths" || true
if [ -s "$tmp/paths" ]; then
  n=0
  while IFS= read -r p; do allowed "$p" || { echo "  path:    $p"; n=$((n+1)); }; done < "$tmp/paths"
  if [ "$n" -gt 0 ]; then
    echo "::error::${n} tracked path(s) carry a site-generator vendor's name. Every one of them is a URL the browser requests, so the vendor's branding is in the page. Move the assets to a neutral folder (public/img/) and repoint the references in the same change — a favicon or logo that a <link> or <img> depends on must be REPLACED with the real brand mark, not merely deleted."
    fail=1
  fi
fi

# --- 2. tracked content ---------------------------------------------------
git grep -Iin -E "$CONTENT_SIG" HEAD 2>/dev/null | sed 's#^HEAD:##' > "$tmp/content" || true
if [ -s "$tmp/content" ]; then
  n=0
  while IFS= read -r line; do
    p=${line%%:*}
    allowed "$p" || { echo "  content: $(echo "$line" | cut -c1-140)"; n=$((n+1)); }
  done < "$tmp/content"
  if [ "$n" -gt 0 ]; then
    echo "::error::${n} tracked line(s) reference a site-generator vendor's asset folder, build plugin or injected script. Drop the dependency and the script tag; repoint the asset URLs."
    fail=1
  fi
fi

# --- 3. commit messages, identities, trailers -----------------------------
# Default scope is HEAD alone, which is what a fetch-depth:1 CI checkout has and
# is enough to refuse the commit being pushed. Pass a range (or set
# VENDORMARK_RANGE) to judge more, e.g. origin/main..HEAD for a whole PR.
range=${range:-${VENDORMARK_RANGE:-}}
if [ -n "$range" ]; then set -- "$range"; else set -- -1 HEAD; fi
git log "$@" --format='%H%x01%an <%ae>%x01%cn <%ce>%x01%B%x01%(trailers:unfold=true)%x02' 2>/dev/null \
  | tr -d '\n' | tr '\002' '\n' > "$tmp/log" || true
if [ -s "$tmp/log" ]; then
  n=0
  while IFS= read -r c; do
    echo "$c" | grep -qiE "$IDENT_SIG" || continue
    echo "  commit:  $(echo "$c" | tr '\001' ' ' | cut -c1-150)"
    n=$((n+1))
  done < "$tmp/log"
  if [ "$n" -gt 0 ]; then
    echo "::error::${n} commit(s) name a site-generator vendor in the message, the author/committer identity or a Co-authored-by trailer. A working tree can be tidied; \`git log\` cannot be, short of a history rewrite and a force-push of every branch. Reword before pushing. Describe the work — \"generated placeholder assets\" — and never credit the generator."
    fail=1
  fi
fi

if [ "$fail" -eq 0 ]; then
  echo "vendormark: OK — no site-generator branding in paths, tracked content, messages or identities"
fi
exit "$fail"