def copy_to(self, database_book: DatabaseBook) -> 'DatabasePage':
if not database_book.exists():
raise FileNotFoundError("Database {} not existing".format(database_book.local_path()))
copy_page = DatabasePage(database_book, self.page)
if copy_page.exists():
shutil.rmtree(copy_page.local_path())
shutil.copytree(self.local_path(), copy_page.local_path())
return copy_page
def load(book: DatabaseBook):
path = book.local_path('book_documents.json')
try:
with open(path) as f:
d = DatabaseBookDocuments.from_book_json(book, json.load(f))
except FileNotFoundError:
d = DatabaseBookDocuments(b_id=book.book)
return d
def load(book: DatabaseBook):
path = book.local_path('book_meta.json')
try:
with open(path) as f:
d = DatabaseBookMeta.from_book_json(book, f.read())
except FileNotFoundError:
d = DatabaseBookMeta(id=book.book, name=book.book)
return d
from database.database_book import DatabaseBook
if __name__ == "__main__":
book = DatabaseBook('Graduel_Fully_Annotated')
page = book.page('Graduel_de_leglise_de_Nevers_035')
pcgts = page.pcgts()
pcgts.page.rotate(-0.125)
pcgts.to_file(page.file('pcgts').local_path())
def update_book_documents(book: DatabaseBook):
d: DatabaseBookDocuments = DatabaseBookDocuments.load(book)
db_pages: List[DatabasePage] = book.pages()
document_page_ids = []
document_page_names = []
textinitium = ''
documents: List[Document] = []
start = None
for page_ind, db_page in enumerate(db_pages):
page = db_page.pcgts().page
if start is not None:
document_page_ids.append(page.p_id)
document_page_names.append(page.location.page)
for ind, t_line in enumerate(page.all_text_lines(), start=1):
if t_line.sentence.document_start:
if start is None:
start = DocumentConnection(
line_id=t_line.id,
page_id=page.p_id,
row=ind,
page_name=page.location.page)
textinitium = t_line.sentence.text(True)
document_page_ids.append(page.p_id)
document_page_names.append(page.location.page)
else:
end_row = ind - 1 if ind - 1 != 0 else len(
db_pages[page_ind -
1].pcgts().page.all_text_lines())
end_page = page.location.page if ind - 1 != 0 else db_pages[
page_ind - 1].pcgts().page.location.page
documents.append(
Document(document_page_ids,
document_page_names,
start=start,
end=DocumentConnection(
line_id=t_line.id,
page_id=page.p_id,
row=end_row,
page_name=end_page),
textinitium=textinitium))
document_page_ids = [page.p_id]
document_page_names = [page.location.page]
start = DocumentConnection(
line_id=t_line.id,
page_id=page.p_id,
row=ind,
page_name=page.location.page)
textinitium = t_line.sentence.text(True)
if start is not None:
db_page = db_pages[-1]
page = db_page.pcgts().page
lines = page.all_text_lines()
documents.append(
Document(document_page_ids,
document_page_names,
start=start,
end=DocumentConnection(
line_id=lines[-1].id if len(lines) > 0 else None,
page_id=page.p_id,
row=len(lines),
page_name=page.location.page),
textinitium=textinitium))
updated_documents: List[Document] = []
for doc in documents:
for orig_doc in d.database_documents.documents:
if doc.start == orig_doc.start:
updated_doc = orig_doc
updated_doc.pages_names = doc.pages_names
updated_doc.pages_ids = doc.pages_ids
updated_doc.end = doc.end
updated_doc.textinitium = doc.textinitium
updated_documents.append(updated_doc)
break
else:
updated_documents.append(doc)
d.database_documents = Documents(documents=updated_documents)
return d
def to_file(self, book: DatabaseBook):
self.b_id = book.book
s = self.to_json()
with open(book.local_path('book_documents.json'), 'w') as f:
js = json.dumps(s, indent=2)
f.write(js)
end=DocumentConnection(
line_id=lines[-1].id if len(lines) > 0 else None,
page_id=page.p_id,
row=len(lines),
page_name=page.location.page),
textinitium=textinitium))
updated_documents: List[Document] = []
for doc in documents:
for orig_doc in d.database_documents.documents:
if doc.start == orig_doc.start:
updated_doc = orig_doc
updated_doc.pages_names = doc.pages_names
updated_doc.pages_ids = doc.pages_ids
updated_doc.end = doc.end
updated_doc.textinitium = doc.textinitium
updated_documents.append(updated_doc)
break
else:
updated_documents.append(doc)
d.database_documents = Documents(documents=updated_documents)
return d
if __name__ == '__main__':
b = DatabaseBookDocuments.update_book_documents(DatabaseBook('demo2'))
b.to_file(DatabaseBook("demo2"))
print(b.to_json())
def to_file(self, book: DatabaseBook):
self.id = book.book
s = self.to_json(indent=2)
with open(book.local_path('book_meta.json'), 'w') as f:
f.write(s)
except FileNotFoundError:
d = DatabaseBookMeta(id=book.book, name=book.book)
return d
@staticmethod
def from_book_json(book: DatabaseBook, json: str):
from database.models.bookstyles import BookStyle, DEFAULT_BOOK_STYLE
meta = DatabaseBookMeta.from_json(json)
meta.id = book.book
if len(meta.name) == 0:
meta.name = book.book
try:
BookStyle.objects.get(id=meta.notationStyle)
except BookStyle.DoesNotExist:
meta.notationStyle = DEFAULT_BOOK_STYLE
return meta
def to_file(self, book: DatabaseBook):
self.id = book.book
s = self.to_json(indent=2)
with open(book.local_path('book_meta.json'), 'w') as f:
f.write(s)
if __name__ == '__main__':
b = DatabaseBookMeta.load(DatabaseBook('Graduel'))
print(b.to_json())
return ImageOperationList(operations)
def __init__(self, pcgts: List[PcGts], params: DatasetParams):
params.pad = (0, 10, 0, 20)
params.dewarp = False
params.staff_lines_only = True
params.cut_region = True
super().__init__(pcgts, params)
if __name__ == '__main__':
import matplotlib.pyplot as plt
from database.database_book import DatabaseBook
from omr.dataset.dataset import LyricsNormalizationParams
pages = [p for p in DatabaseBook('Gothic_Test').pages()]
params = DatasetParams(
height=60,
gt_required=True,
cut_region=True,
pad=[0, 10, 0, 20],
page_scale_reference=PageScaleReference.HIGHRES,
lyrics_normalization=LyricsNormalizationParams(
LyricsNormalization.ONE_STRING),
)
if True:
page = pages[0]
pcgts = PcGts.from_file(page.file('pcgts'))
dataset = TextDataset([pcgts], params)
calamari_dataset = dataset.to_text_line_calamari_dataset()