pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine manual parser (#140)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-21 18:17:32 +08:00
committed by GitHub
parent f4ec7cfa76
commit 6c6b144de2
11 changed files with 77 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/app/one.py
View File

@ -10,12 +10,10 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
import copy
import re
from rag.app import laws
from rag.nlp import huqie, is_english, tokenize, naive_merge, tokenize_table, add_positions
from rag.nlp import huqie, tokenize
from deepdoc.parser import PdfParser, ExcelParser
from rag.settings import cron_logger
class Pdf(PdfParser):
@ -33,7 +31,7 @@ class Pdf(PdfParser):
from timeit import default_timer as timer
start = timer()
self._layouts_rec(zoomin)
self._layouts_rec(zoomin, drop=False)
callback(0.63, "Layout analysis finished.")
print("paddle layouts:", timer() - start)
self._table_transformer_job(zoomin)