#!/usr/bin/env sh
# epubcheck over the sample set, as a regression guard.
#
# Every epub spine writes is checked with epubcheck. A *fatal* is never
# acceptable: it means a reader cannot parse the file at all. Errors are
# compared against a recorded allowance, so that the ones known to be
# outstanding do not fail the run while any new one does.
#
# The allowance is deliberately a single number rather than a list of
# messages: a list invites adding to it. When the number goes down, lower it
# here in the same commit that lowers it in the output.
#
# Usage:
#   SpinePOD=../../markup/sisudoc-spine-samples/markup/pod-samples/pod \
#     ./test/test-epub-validity.sh ./bin/spine-ldc
#
# Exit codes:
#   0  no fatals, and errors within the allowance
#   1  a fatal, or more errors than allowed
#   2  set-up problem (no $SpinePOD, no binary, no epubcheck, no samples)

set -e

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
SPINE_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"

# What is known to be outstanding over the whole sample set. Both numbers are
# a ceiling, so a regression fails and an improvement does not; lower them in
# the commit that lowers the output, and say in that commit what went.
#
# There is no allowance for a fatal, and there must never be one. The last
# one - the_public_domain, chapter_2: a bare url ending a footnote body
# swallowed the "}~" close delimiter, so the note closed inside the link
# markup and left an unbalanced </a> behind - was a url boundary defect in
# the abstraction, and is fixed.
#
# No error is allowed either, and none is outstanding. Both numbers being
# zero is the point: anything at all that epubcheck calls an error is a
# regression, and there is no list to add to.
#
# Two warnings remain and are not counted here. Both are NAV-011 in the
# same shape, in two documents: the navigation document lists one file
# twice, and the repeat is behind the previous entry in spine order. It
# comes from how the endnotes part and section headings are ordered, not
# from the navigation writer.
FATALS_ALLOWED=${SpineEpubFatalsAllowed:-0}
ERRORS_ALLOWED=${SpineEpubErrorsAllowed:-0}

if [ -z "$SpinePOD" ]; then
  echo "ERROR: \$SpinePOD is not set." >&2
  echo "  e.g. SpinePOD=../../markup/sisudoc-spine-samples/markup/pod-samples/pod" >&2
  exit 2
fi
SAMPLES_RAW="$SPINE_DIR/$SpinePOD"
if [ -d "$SAMPLES_RAW" ]; then
  SAMPLES_DIR="$(cd "$SAMPLES_RAW" && pwd)"
else
  SAMPLES_DIR="$SAMPLES_RAW"
fi
# SPINE_BIN="${1:-}"
# if [ -z "$SPINE_BIN" ] || [ ! -x "$SPINE_BIN" ]; then
#   echo "ERROR: give the spine binary, e.g. ./bin/spine-ldc" >&2
#   exit 2
# fi
SPINE_BIN="${1:-}"
# find spine binary
if [ -z "$SPINE_BIN" ]; then
  if [ -x "$SPINE_DIR/result/bin/spine" ]; then SPINE_BIN="$SPINE_DIR/result/bin/spine"
  elif [ -x "$SPINE_DIR/bin/spine-ldc" ]; then SPINE_BIN="$SPINE_DIR/bin/spine-ldc"
  elif [ -x "$SPINE_DIR/bin/spine" ]; then SPINE_BIN="$SPINE_DIR/bin/spine"
  else
    echo "ERROR: spine binary not found. Specify path as argument." >&2
    exit 2
  fi
fi
if [ ! -d "$SAMPLES_DIR" ]; then
  echo "ERROR: samples not found: $SAMPLES_DIR" >&2
  exit 2
fi
if ! command -v epubcheck >/dev/null 2>&1; then
  echo "ERROR: epubcheck not on PATH." >&2
  echo "  e.g. nix shell \"nixpkgs#epubcheck\" -c $0 $SPINE_BIN" >&2
  exit 2
fi

echo "spine binary: $SPINE_BIN"
echo "samples: $SAMPLES_DIR"

OUT_DIR="$(mktemp -d)"
trap 'rm -rf "$OUT_DIR"' EXIT

echo "Generating epubs ..."
"$SPINE_BIN" --epub --output="$OUT_DIR" "$SAMPLES_DIR"/* 2>&1 | tail -1

FATALS=0
ERRORS=0
DOCS=0
for f in $(find "$OUT_DIR" -name '*.epub' | sort); do
  DOCS=$((DOCS + 1))
  msg=$(epubcheck "$f" 2>&1 | grep -E '^Messages:' || true)
  ff=$(echo "$msg" | sed -n 's/.*: \([0-9]*\) fatal.*/\1/p')
  ee=$(echo "$msg" | sed -n 's/.*\/ \([0-9]*\) error.*/\1/p')
  ff=${ff:-0}; ee=${ee:-0}
  FATALS=$((FATALS + ff))
  ERRORS=$((ERRORS + ee))
  if [ "$ff" -gt 0 ]; then
    echo "  FATAL in $(basename "$f"): $ff"
    epubcheck "$f" 2>&1 | grep -i 'FATAL' | head -3 | sed 's/^/    /'
  fi
done

echo "checked $DOCS epubs: $FATALS fatal (allowed $FATALS_ALLOWED), $ERRORS errors (allowed $ERRORS_ALLOWED)"

if [ "$FATALS" -gt "$FATALS_ALLOWED" ]; then
  echo "FAIL: $FATALS fatal(s), more than the $FATALS_ALLOWED allowed;"
  echo "  a fatal means a reader cannot parse that file at all"
  exit 1
fi
if [ "$ERRORS" -gt "$ERRORS_ALLOWED" ]; then
  echo "FAIL: $ERRORS errors, more than the $ERRORS_ALLOWED allowed"
  echo "  if this is a deliberate change, say why and adjust ERRORS_ALLOWED"
  exit 1
fi
echo "PASS: $FATALS fatal and $ERRORS errors, both within what is recorded"
exit 0