#!/usr/bin/env bash
# Phase 4 exit criterion: generated PDFs open cleanly in external viewers.
#
# No test inside this repository can assert that. Every reader here is an
# implementation nigig-pdf shares no code with — qpdf for structure, poppler
# for semantics — so a file that satisfies both is not merely self-consistent
# with our own parser, which is the failure this exists to rule out.
#
# The distinction matters. `pdf-document`'s round-trip tests prove we can
# read what we wrote; they cannot prove anyone *else* can. A writer and a
# reader that share a bug agree perfectly.
#
# Usage:
#   ./tools/check-pdf-external-readers.sh
#   KEEP_PDF=1 ./tools/check-pdf-external-readers.sh   # keep the artefacts
#
# Requires qpdf and poppler-utils. Skips with a clear message when absent,
# rather than passing vacuously:
#
#   sudo apt-get install -y qpdf poppler-utils

set -Eeuo pipefail
IFS=$'\n\t'

ROOT="$(CDPATH= cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd)"
KEEP_PDF="${KEEP_PDF:-0}"

missing=0
for tool in qpdf pdfinfo pdftotext pdffonts; do
    command -v "$tool" >/dev/null 2>&1 || { echo "missing: $tool" >&2; missing=1; }
done
if [ "$missing" = 1 ]; then
    echo "install qpdf and poppler-utils to run this check" >&2
    exit 2
fi

WORK="$(mktemp -d "${TMPDIR:-/tmp}/pdf-external.XXXXXXXX")"
cleanup() {
    local status=$?
    if [ "$KEEP_PDF" = "1" ]; then
        printf 'kept artefacts in %s\n' "$WORK" >&2
    else
        rm -rf -- "$WORK"
    fi
    exit "$status"
}
trap cleanup EXIT HUP INT TERM

PDF="$WORK/sample.pdf"
echo "generating the Phase 4 sample"
ENCRYPTED="$WORK/encrypted.pdf"
cargo run --quiet --manifest-path "$ROOT/crates/apps/pdf/pdf-graphics/Cargo.toml" \
    --example generate_sample -- "$PDF" "$ENCRYPTED"

fail=0
note() { printf '  %s\n' "$1"; }
check() {
    local label="$1" haystack="$2" needle="$3"
    if printf '%s' "$haystack" | grep -qF -- "$needle"; then
        note "ok    $label"
    else
        note "FAIL  $label (expected to find: $needle)"
        fail=1
    fi
}

echo
echo "== qpdf: structural validity =="
# `--check` reports syntax and stream-encoding errors. A warning is not a
# pass: qpdf warns where it had to recover, and recovering is exactly what a
# stricter viewer will refuse to do.
if qpdf_out="$(qpdf --check "$PDF" 2>&1)"; then
    if printf '%s' "$qpdf_out" | grep -q 'WARNING'; then
        note "FAIL  qpdf reported warnings:"
        printf '%s\n' "$qpdf_out" | sed 's/^/        /'
        fail=1
    else
        note "ok    no syntax or stream encoding errors"
    fi
else
    note "FAIL  qpdf --check rejected the file:"
    printf '%s\n' "$qpdf_out" | sed 's/^/        /'
    fail=1
fi

echo
echo "== poppler: document semantics =="
info="$(pdfinfo "$PDF" 2>&1)"
check "title survives"              "$info" "Nigig PDF Phase 4 sample"
check "author survives"             "$info" "nigig"
check "keywords survive"            "$info" "phase4"
# Three pages: text, the form, and the CFF sample. The count is asserted
# exactly rather than as "more than one" — a page silently dropped by a
# writer bug is precisely the kind of thing this catches, and it caught the
# CFF page being added.
check "all three pages are present"  "$info" "Pages:           3"
check "the AcroForm is recognised"  "$info" "AcroForm"

echo
echo "== poppler: text extraction =="
# Text extraction is the strongest single signal available here: it only
# works if the font, its encoding and the content stream all agree. The
# em-dash is deliberate — it is outside ASCII, so it exercises the embedded
# subset's cmap rather than a lucky byte-for-byte match.
text="$(pdftotext "$PDF" - 2>&1)"
check "embedded-subset heading extracts" "$text" "Nigig PDF — Phase 4"
check "base-14 text extracts"            "$text" "base-14 Helvetica"
check "form field values extract"        "$text" "Ada Lovelace"
# Text set in the whole-embedded CFF font. This only extracts if the CFF
# program loaded, /Identity-H addressed its glyphs, and /ToUnicode mapped
# them back — the whole embedding path in one assertion.
check "CFF-set text extracts"            "$text" "Hello CFF 123"

echo
echo "== poppler: embedded fonts =="
# `pdffonts` is the only check here that inspects a font *program* rather
# than the file structure. It is what proves a CFF font was written with
# the right /FontFile key and descendant subtype: get either wrong and the
# font either fails to load or loads as the wrong type, both of which show
# up in this table rather than in qpdf --check.
fonts="$(pdffonts "$PDF" 2>&1)"
check "the subset TrueType font is embedded" "$fonts" "CID TrueType"
check "the whole CFF font is embedded"       "$fonts" "CID Type 0C"
# `emb yes` for both, and `sub` distinguishing them: the TrueType one is a
# real subset, the CFF one is the whole program. That column is the visible
# consequence of `SubsetFont::subsetted`.
if printf '%s' "$fonts" | grep -qE 'CID Type 0C.*[[:space:]]yes[[:space:]]+no[[:space:]]'; then
    note "ok    the CFF font is embedded whole, not claiming to be subset"
else
    note "FAIL  the CFF font's embedded/subset columns are wrong"
    printf '%s\n' "$fonts" | sed 's/^/        /'
    fail=1
fi

echo
echo "== qpdf: attachments =="
attach="$(qpdf --list-attachments --verbose "$PDF" 2>&1)"
check "the attachment is listed"     "$attach" "readme.txt"
check "its description survives"     "$attach" "About this file"

echo
echo "== catalogue features =="
# Read as bytes: these are structural keys, and their presence is what a
# viewer keys off. `/Metadata` is checked by pdfinfo above where set.
for key in /Outlines /Names /EmbeddedFiles /PageLabels /Dests /PageMode \
           /ViewerPreferences /AcroForm; do
    if grep -qa -- "$key" "$PDF"; then
        note "ok    $key present"
    else
        note "FAIL  $key missing"
        fail=1
    fi
done

echo
echo "== encrypted document (ADR 0024) =="
# The point of these three: a file we encrypt must be openable by an
# implementation sharing no code with ours, must refuse the wrong
# password, and must not carry its plaintext on disk.
enc_check="$(qpdf --password=hunter2 --check "$ENCRYPTED" 2>&1 || true)"
check "qpdf opens it with the password" "$enc_check" "No syntax or stream encoding errors"
check "it really is AES-256"            "$enc_check" "AESv3"

if qpdf --password=WRONGPASSWORD --check "$ENCRYPTED" >/dev/null 2>&1; then
    note "FAIL  the wrong password opened the document"
    fail=1
else
    note "ok    the wrong password is refused"
fi

enc_text="$(pdftotext -upw hunter2 "$ENCRYPTED" - 2>/dev/null || true)"
check "poppler decrypts the content" "$enc_text" "ENCRYPTEDSAMPLE"

# The plaintext must not be in the bytes. grep -a because the file is
# binary; a match here is a leak, so the sense of the test is inverted.
if grep -qa "ENCRYPTEDSAMPLE" "$ENCRYPTED"; then
    note "FAIL  plaintext found in the encrypted file"
    fail=1
else
    note "ok    no plaintext in the encrypted file"
fi

echo
if [ "$fail" = 0 ]; then
    echo "all external-reader checks passed"
else
    echo "external-reader checks FAILED" >&2
    echo "The file may still be structurally valid: a PDF that qpdf accepts" >&2
    echo "and poppler renders incorrectly is the interesting case, and it is" >&2
    echo "what these semantic checks are for." >&2
    exit 1
fi