Trey T
3ee1563cb0
The book reader's word lookup used DictionaryService, a verb-conjugation index plus ~200 hand-typed words: ordinary nouns like "taza" returned nothing, and homographs always lost (tapping "como" in "como siempre" gave the verb "comer" because the verb index is checked first). Add a glossary phase to the books pipeline (build_glossary.py): every distinct Spanish word is translated once, in its sentence context, by the same Claude-Code-subagent LLM step the pipeline already uses for chapter translation. English front matter is excluded by an ES==EN paragraph-ratio heuristic. The glossary is bundled into book_<slug>.json and is now part of the pipeline for every book. In the app, Book carries the decoded glossary and BookReaderView resolves each tap automatically through cache -> glossary -> DictionaryService -> on-device LLM, citing which source answered so a curated glossary hit reads differently from a best-effort AI guess. book_olly-vol2.json regenerated with a 3,658-word glossary. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
78 lines
2.6 KiB
Bash
Executable File
78 lines
2.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Orchestrate the books pipeline: EPUB -> chapters.json -> per-chapter job
|
|
# manifest -> (translation by Claude Code subagents) -> bundled book_<slug>.json.
|
|
#
|
|
# This script DOES NOT run the LLM translation pass. After Phase 2 it stops
|
|
# and prints how many jobs are pending. Use Claude Code subagents (or a fresh
|
|
# session per the README) to fill in build/<slug>/jobs/*.output.json, then
|
|
# re-run this script — it will pick up where it left off via Phase 3.
|
|
#
|
|
# Usage:
|
|
# ./run.sh <epub_path> [--slug SLUG] [--batch-size N]
|
|
|
|
set -euo pipefail
|
|
|
|
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
cd "$HERE"
|
|
|
|
if [[ $# -lt 1 ]]; then
|
|
echo "usage: $0 <epub_path> [--slug SLUG] [--batch-size N]"
|
|
exit 2
|
|
fi
|
|
|
|
EPUB="$1"; shift
|
|
SLUG=""
|
|
BATCH_SIZE="30"
|
|
GLOSSARY_BATCH_SIZE="150"
|
|
|
|
while [[ $# -gt 0 ]]; do
|
|
case "$1" in
|
|
--slug) SLUG="$2"; shift 2 ;;
|
|
--batch-size) BATCH_SIZE="$2"; shift 2 ;;
|
|
--glossary-batch-size) GLOSSARY_BATCH_SIZE="$2"; shift 2 ;;
|
|
*) echo "unknown option: $1" >&2; exit 2 ;;
|
|
esac
|
|
done
|
|
|
|
EPUB_ABS="$(cd "$(dirname "$EPUB")" && pwd)/$(basename "$EPUB")"
|
|
|
|
echo "=== Phase 1: extract_epub.py ==="
|
|
if [[ -n "$SLUG" ]]; then
|
|
python3 extract_epub.py "$EPUB_ABS" --slug "$SLUG"
|
|
else
|
|
python3 extract_epub.py "$EPUB_ABS"
|
|
fi
|
|
|
|
# If --slug wasn't passed, recover the slug from the chapters file just written.
|
|
if [[ -z "$SLUG" ]]; then
|
|
SLUG=$(python3 -c "import json,glob; p=sorted(glob.glob('build/*/chapters.json'), key=lambda x: -__import__('os').path.getmtime(x))[0]; print(json.load(open(p))['slug'])")
|
|
fi
|
|
|
|
echo
|
|
echo "=== Phase 2: translate_chapters.py ==="
|
|
python3 translate_chapters.py "$SLUG" --batch-size "$BATCH_SIZE"
|
|
|
|
PENDING_FILE="build/$SLUG/jobs/_pending.txt"
|
|
PENDING_COUNT=$(wc -l < "$PENDING_FILE" | tr -d ' ')
|
|
|
|
echo
|
|
echo "=== Phase 2b: build_glossary.py ==="
|
|
python3 build_glossary.py "$SLUG" --batch-size "$GLOSSARY_BATCH_SIZE"
|
|
|
|
GLOSS_PENDING_FILE="build/$SLUG/glossary/_pending.txt"
|
|
GLOSS_PENDING_COUNT=$(wc -l < "$GLOSS_PENDING_FILE" | tr -d ' ')
|
|
TOTAL_PENDING=$((PENDING_COUNT + GLOSS_PENDING_COUNT))
|
|
|
|
echo
|
|
echo "=== Phase 3: bundle_book.py ==="
|
|
if [[ "$TOTAL_PENDING" -gt 0 ]]; then
|
|
echo " $PENDING_COUNT translation job(s) and $GLOSS_PENDING_COUNT glossary job(s) still pending."
|
|
echo " Run the Claude Code subagent step (see README.md) for BOTH manifests:"
|
|
echo " build/$SLUG/jobs/_pending.txt (translation)"
|
|
echo " build/$SLUG/glossary/_pending.txt (glossary)"
|
|
echo " then re-run this script. Bundling with placeholders so you can preview now."
|
|
python3 bundle_book.py "$SLUG"
|
|
else
|
|
python3 bundle_book.py "$SLUG" --require-all
|
|
fi
|