KaKi87
e2c18960ec
* Bundle on-device ML Kit OCR to fix PDF translation hang Sideloaded builds never receive Play Services install-time OCR modules, so image/PDF translation could sit forever on "Updating the text module". Ship bundled text-recognition models/native code via the build script, and cap DialogOcrLoad retries so the wait dialog cannot loop indefinitely. Bump version to 2.0.0-testing.36. Co-authored-by: KaKi87 <KaKi87@pm.me> * Add GMS dynamic API aliases for bundled OCR Bundled text-recognition-common calls IObjectWrapper.Stub.asInterface and ObjectWrapper.unwrap, but R8 renamed those to I1/f2 in this APK. Add public aliases so OCR init no longer throws NoSuchMethodError. Bump to 2.0.0-testing.37. Co-authored-by: KaKi87 <KaKi87@pm.me> * Restore ImageUtils APIs required by bundled OCR text-recognition-bundled-common calls ImageUtils.getInstance and getUprightRotationMatrix, which R8 had stripped from vision-common. Restore those methods, add ImageConvertUtils buffer helpers and ObjectWrapper.wrap for the same public API surface. Bump to 2.0.0-testing.38. Co-authored-by: KaKi87 <KaKi87@pm.me> * Move restored ImageUtils helpers to smali_classes4 classes3 is at the DEX method-ref ceiling; relocating ImageUtils and ImageConvertUtils keeps apktool builds reliable after restoring the bundled-OCR public APIs. Co-authored-by: KaKi87 <KaKi87@pm.me> * Download ML Kit OCR models at runtime from Maven Stop packaging OCR assets and native libs into the APK. DialogOcrLoad now fetches text-recognition AARs from Google Maven, extracts models + the pipeline .so, and activates them via System.load / AssetManager.addAssetPath. Keep only the small module dex in the APK (JVM jars cannot be loaded on-device). Bump to 2.0.0-testing.39. Co-authored-by: KaKi87 <KaKi87@pm.me> * Move OCR install helpers to smali_classes4 Avoid DEX method-ref overflow in classes3 when assembling DialogOcrLoad install task/progress classes. Co-authored-by: KaKi87 <KaKi87@pm.me> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
100 lines
3.3 KiB
Bash
Executable file
100 lines
3.3 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
# Stage the small OCR module dex (ModuleDescriptors + BundledTextRecognizerCreator)
|
|
# used by the thick ML Kit path. Model assets and native libs are NOT packaged;
|
|
# OcrRuntimeInstaller downloads those from Google Maven at runtime.
|
|
set -euo pipefail
|
|
|
|
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
|
OUT_DIR="${ROOT_DIR}/bundled-ocr"
|
|
CACHE_DIR="${ROOT_DIR}/tools/mlkit-aar-cache"
|
|
ANDROID_HOME="${ANDROID_HOME:-${ANDROID_SDK_ROOT:-${HOME}/android-sdk}}"
|
|
|
|
MAVEN="https://dl.google.com/dl/android/maven2/com/google/mlkit"
|
|
TEXT_RECOGNITION_VERSION="16.0.1"
|
|
BUNDLED_COMMON_VERSION="17.0.0"
|
|
|
|
mkdir -p "${CACHE_DIR}" "${OUT_DIR}"
|
|
|
|
download() {
|
|
local url="$1"
|
|
local dest="$2"
|
|
if [[ -f "${dest}" ]]; then
|
|
return 0
|
|
fi
|
|
echo " downloading $(basename "${dest}")..."
|
|
curl -fsSL -o "${dest}.tmp" "${url}"
|
|
mv "${dest}.tmp" "${dest}"
|
|
}
|
|
|
|
echo "Preparing OCR module dex (runtime downloads models/libs)..."
|
|
|
|
download \
|
|
"${MAVEN}/text-recognition/${TEXT_RECOGNITION_VERSION}/text-recognition-${TEXT_RECOGNITION_VERSION}.aar" \
|
|
"${CACHE_DIR}/text-recognition.aar"
|
|
download \
|
|
"${MAVEN}/text-recognition-bundled-common/${BUNDLED_COMMON_VERSION}/text-recognition-bundled-common-${BUNDLED_COMMON_VERSION}.aar" \
|
|
"${CACHE_DIR}/text-recognition-bundled-common.aar"
|
|
|
|
for lang in chinese japanese korean devanagari; do
|
|
download \
|
|
"${MAVEN}/text-recognition-${lang}/${TEXT_RECOGNITION_VERSION}/text-recognition-${lang}-${TEXT_RECOGNITION_VERSION}.aar" \
|
|
"${CACHE_DIR}/text-recognition-${lang}.aar"
|
|
done
|
|
|
|
STAGE="$(mktemp -d)"
|
|
cleanup() { rm -rf "${STAGE}"; }
|
|
trap cleanup EXIT
|
|
|
|
extract_aar() {
|
|
local aar="$1"
|
|
local dest="$2"
|
|
mkdir -p "${dest}"
|
|
unzip -qo "${aar}" -d "${dest}"
|
|
find "${dest}" -type f -exec chmod u+w {} \;
|
|
}
|
|
|
|
extract_aar "${CACHE_DIR}/text-recognition.aar" "${STAGE}/latin"
|
|
extract_aar "${CACHE_DIR}/text-recognition-bundled-common.aar" "${STAGE}/common"
|
|
for lang in chinese japanese korean devanagari; do
|
|
extract_aar "${CACHE_DIR}/text-recognition-${lang}.aar" "${STAGE}/${lang}"
|
|
done
|
|
|
|
# Do not stage assets/ or lib/ — those are downloaded on-device by OcrRuntimeInstaller.
|
|
rm -rf "${OUT_DIR}/assets" "${OUT_DIR}/lib"
|
|
|
|
# Merge Java classes: bundled pipeline + ModuleDescriptors for each script.
|
|
JAR_MERGE="${STAGE}/jar-merge"
|
|
mkdir -p "${JAR_MERGE}"
|
|
(
|
|
cd "${JAR_MERGE}"
|
|
jar xf "${STAGE}/common/classes.jar"
|
|
jar xf "${STAGE}/latin/classes.jar"
|
|
for lang in chinese japanese korean devanagari; do
|
|
jar xf "${STAGE}/${lang}/classes.jar"
|
|
done
|
|
jar cf "${STAGE}/ocr-bundled.jar" .
|
|
)
|
|
|
|
D8="$(find "${ANDROID_HOME}/build-tools" -name d8 -type f 2>/dev/null | sort -V | tail -1 || true)"
|
|
if [[ -z "${D8}" ]]; then
|
|
echo "error: d8 not found under ${ANDROID_HOME}/build-tools" >&2
|
|
exit 1
|
|
fi
|
|
|
|
DEX_OUT="${STAGE}/dex-out"
|
|
mkdir -p "${DEX_OUT}"
|
|
"${D8}" --release --output "${DEX_OUT}" "${STAGE}/ocr-bundled.jar"
|
|
cp "${DEX_OUT}/classes.dex" "${OUT_DIR}/classes_ocr.dex"
|
|
|
|
cat > "${OUT_DIR}/README.md" << 'EOF'
|
|
# OCR module dex (not full models)
|
|
|
|
`classes_ocr.dex` contains ModuleDescriptors + BundledTextRecognizerCreator so the
|
|
thick ML Kit path works without Play Services. Model assets and
|
|
`libmlkit_google_ocr_pipeline.so` are downloaded at runtime from Google Maven by
|
|
`OcrRuntimeInstaller` (see DialogOcrLoad).
|
|
|
|
Regenerate with: `./scripts/prepare-bundled-ocr.sh`
|
|
EOF
|
|
|
|
echo "OCR module dex ready at ${OUT_DIR} ($(du -sh "${OUT_DIR}" | awk '{print $1}'))"
|