Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
MinerU
Commits
34cd1350
"vscode:/vscode.git/clone" did not exist on "0f3656b9653c0f208f278c87c69486a41865ec8d"
Unverified
Commit
34cd1350
authored
Dec 18, 2024
by
Xiaomeng Zhao
Committed by
GitHub
Dec 18, 2024
Browse files
Merge pull request #1321 from icecraft/docs/fix_docs
Docs/fix docs
parents
d94ddcf8
c968ce86
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
101 additions
and
4 deletions
+101
-4
magic_pdf/data/dataset.py
magic_pdf/data/dataset.py
+1
-1
magic_pdf/operators/__init__.py
magic_pdf/operators/__init__.py
+97
-0
magic_pdf/operators/models.py
magic_pdf/operators/models.py
+2
-2
next_docs/en/api/model_operators.rst
next_docs/en/api/model_operators.rst
+1
-1
No files found.
magic_pdf/data/dataset.py
View file @
34cd1350
...
@@ -9,7 +9,6 @@ from magic_pdf.config.enums import SupportedPdfParseMethod
...
@@ -9,7 +9,6 @@ from magic_pdf.config.enums import SupportedPdfParseMethod
from
magic_pdf.data.schemas
import
PageInfo
from
magic_pdf.data.schemas
import
PageInfo
from
magic_pdf.data.utils
import
fitz_doc_to_image
from
magic_pdf.data.utils
import
fitz_doc_to_image
from
magic_pdf.filter
import
classify
from
magic_pdf.filter
import
classify
from
magic_pdf.model.sub_modules.language_detection.utils
import
auto_detect_lang
class
PageableData
(
ABC
):
class
PageableData
(
ABC
):
...
@@ -149,6 +148,7 @@ class PymuDocDataset(Dataset):
...
@@ -149,6 +148,7 @@ class PymuDocDataset(Dataset):
if
lang
==
''
:
if
lang
==
''
:
self
.
_lang
=
None
self
.
_lang
=
None
elif
lang
==
'auto'
:
elif
lang
==
'auto'
:
from
magic_pdf.model.sub_modules.language_detection.utils
import
auto_detect_lang
self
.
_lang
=
auto_detect_lang
(
bits
)
self
.
_lang
=
auto_detect_lang
(
bits
)
logger
.
info
(
f
"lang:
{
lang
}
, detect_lang:
{
self
.
_lang
}
"
)
logger
.
info
(
f
"lang:
{
lang
}
, detect_lang:
{
self
.
_lang
}
"
)
else
:
else
:
...
...
magic_pdf/operators/__init__.py
View file @
34cd1350
from
abc
import
ABC
,
abstractmethod
from
typing
import
Callable
from
magic_pdf.data.data_reader_writer
import
DataWriter
from
magic_pdf.data.dataset
import
Dataset
from
magic_pdf.operators.pipes
import
PipeResult
__use_inside_model__
=
True
__model_mode__
=
'full'
class
InferenceResultBase
(
ABC
):
@
abstractmethod
def
__init__
(
self
,
inference_results
:
list
,
dataset
:
Dataset
):
"""Initialized method.
Args:
inference_results (list): the inference result generated by model
dataset (Dataset): the dataset related with model inference result
"""
pass
@
abstractmethod
def
draw_model
(
self
,
file_path
:
str
)
->
None
:
"""Draw model inference result.
Args:
file_path (str): the output file path
"""
pass
@
abstractmethod
def
dump_model
(
self
,
writer
:
DataWriter
,
file_path
:
str
):
"""Dump model inference result to file.
Args:
writer (DataWriter): writer handle
file_path (str): the location of target file
"""
pass
@
abstractmethod
def
get_infer_res
(
self
):
"""Get the inference result.
Returns:
list: the inference result generated by model
"""
pass
@
abstractmethod
def
apply
(
self
,
proc
:
Callable
,
*
args
,
**
kwargs
):
"""Apply callable method which.
Args:
proc (Callable): invoke proc as follows:
proc(inference_result, *args, **kwargs)
Returns:
Any: return the result generated by proc
"""
pass
def
pipe_txt_mode
(
self
,
imageWriter
:
DataWriter
,
start_page_id
=
0
,
end_page_id
=
None
,
debug_mode
=
False
,
lang
=
None
,
)
->
PipeResult
:
"""Post-proc the model inference result, Extract the text using the
third library, such as `pymupdf`
Args:
imageWriter (DataWriter): the image writer handle
start_page_id (int, optional): Defaults to 0. Let user select some pages He/She want to process
end_page_id (int, optional): Defaults to the last page index of dataset. Let user select some pages He/She want to process
debug_mode (bool, optional): Defaults to False. will dump more log if enabled
lang (str, optional): Defaults to None.
Returns:
PipeResult: the result
"""
pass
@
abstractmethod
def
pipe_ocr_mode
(
self
,
imageWriter
:
DataWriter
,
start_page_id
=
0
,
end_page_id
=
None
,
debug_mode
=
False
,
lang
=
None
,
)
->
PipeResult
:
pass
magic_pdf/operators/models.py
View file @
34cd1350
...
@@ -11,9 +11,9 @@ from magic_pdf.libs.draw_bbox import draw_model_bbox
...
@@ -11,9 +11,9 @@ from magic_pdf.libs.draw_bbox import draw_model_bbox
from
magic_pdf.libs.version
import
__version__
from
magic_pdf.libs.version
import
__version__
from
magic_pdf.operators.pipes
import
PipeResult
from
magic_pdf.operators.pipes
import
PipeResult
from
magic_pdf.pdf_parse_union_core_v2
import
pdf_parse_union
from
magic_pdf.pdf_parse_union_core_v2
import
pdf_parse_union
from
magic_pdf.operators
import
InferenceResultBase
class
InferenceResult
(
InferenceResultBase
):
class
InferenceResult
:
def
__init__
(
self
,
inference_results
:
list
,
dataset
:
Dataset
):
def
__init__
(
self
,
inference_results
:
list
,
dataset
:
Dataset
):
"""Initialized method.
"""Initialized method.
...
...
next_docs/en/api/model_operators.rst
View file @
34cd1350
...
@@ -2,7 +2,7 @@
...
@@ -2,7 +2,7 @@
Model Api
Model Api
==========
==========
.. autoclass:: magic_pdf.operators.
models.
InferenceResult
.. autoclass:: magic_pdf.operators.InferenceResult
Base
:members:
:members:
:inherited-members:
:inherited-members:
:show-inheritance:
:show-inheritance:
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment