import os
block_cipher = None
app_dir = 'C:\\Users\\dom\\ai\\anonymisation'

datas = [
    (os.path.join(app_dir, 'config'), 'config'),
    (os.path.join(app_dir, 'data', 'bdpm'), os.path.join('data', 'bdpm')),
    (os.path.join(app_dir, 'data', 'finess'), os.path.join('data', 'finess')),
    (os.path.join(app_dir, 'data', 'insee'), os.path.join('data', 'insee')),
    (os.path.join(app_dir, 'models', 'camembert-bio-deid', 'onnx'), os.path.join('models', 'camembert-bio-deid', 'onnx')),
    (os.path.join(app_dir, 'detectors'), 'detectors'),
    (os.path.join(app_dir, 'scripts'), 'scripts'),
]
# Fichiers directs dans data/ — IMPÉRATIF pour fonctionnement correct du core.
# Sans eux : stop-words/villes/DPI labels/companion blacklist sont des sets vides,
# ce qui dégrade la qualité d'anonymisation et peut masquer/laisser passer des faux-positifs.
for data_file in [
    'stopwords_manuels.txt',
    'villes_blacklist.txt',
    'dpi_labels_blacklist.txt',
    'companion_blacklist.txt',
]:
    src = os.path.join(app_dir, 'data', data_file)
    if os.path.exists(src):
        datas.append((src, 'data'))
for pyfile in ['anonymizer_core_refactored_onnx.py', 'eds_pseudo_manager.py',
               'gliner_manager.py', 'camembert_ner_manager.py',
               'Pseudonymisation_Gui_V5.py']:
    datas.append((os.path.join(app_dir, pyfile), '.'))

a = Analysis(
    [os.path.join(app_dir, 'launcher.py')],
    pathex=[app_dir],
    datas=datas,
    hiddenimports=[
        'anonymizer_core_refactored_onnx', 'eds_pseudo_manager',
        'gliner_manager', 'camembert_ner_manager', 'Pseudonymisation_Gui_V5',
        'edsnlp', 'edsnlp.pipes', 'edsnlp.pipes.ner', 'edsnlp.pipes.ner.pseudo',
        'spacy', 'spacy.lang.fr', 'gliner', 'onnxruntime',
        'transformers', 'tokenizers', 'torch', 'pdfplumber',
        'ahocorasick', 'sklearn', 'scipy', 'pydantic', 'yaml', 'PIL',
        'loguru', 'regex',
    ],
    cipher=block_cipher,
    noarchive=False,
)
pyz = PYZ(a.pure, a.zipped_data, cipher=block_cipher)
exe = EXE(
    pyz, a.scripts, a.binaries, a.zipfiles, a.datas, [],
    name='Anonymisation',
    debug=False,
    strip=False,
    upx=False,
    console=False,
    icon=None,
)