Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
P
pdf-miner
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Qin Kaijie
pdf-miner
Commits
20937b09
Unverified
Commit
20937b09
authored
Sep 12, 2024
by
Xiaomeng Zhao
Committed by
GitHub
Sep 12, 2024
Browse files
Options
Browse Files
Download
Plain Diff
Merge pull request #607 from myhloli/dev
fix: solve conflicts
parents
31a1ecdb
a4c72e2e
Changes
18
Show whitespace changes
Inline
Side-by-side
Showing
18 changed files
with
0 additions
and
323 deletions
+0
-323
LICENSE.md
LICENSE.md
+0
-3
README.md
README.md
+0
-5
README_zh-CN.md
README_zh-CN.md
+0
-9
app.py
app.py
+0
-167
version.py
magic_pdf/libs/version.py
+0
-4
doc_analyze_by_custom_model.py
magic_pdf/model/doc_analyze_by_custom_model.py
+0
-4
pdf_extract_kit.py
magic_pdf/model/pdf_extract_kit.py
+0
-13
AbsPipe.py
magic_pdf/pipe/AbsPipe.py
+0
-7
OCRPipe.py
magic_pdf/pipe/OCRPipe.py
+0
-9
TXTPipe.py
magic_pdf/pipe/TXTPipe.py
+0
-9
UNIPipe.py
magic_pdf/pipe/UNIPipe.py
+0
-17
model_configs.yaml
magic_pdf/resources/model_config/model_configs.yaml
+0
-4
cli.py
magic_pdf/tools/cli.py
+0
-10
user_api.py
magic_pdf/user_api.py
+0
-10
mv_pdf.py
mv_pdf.py
+0
-26
README.md
projects/README.md
+0
-3
README_zh-CN.md
projects/README_zh-CN.md
+0
-3
README_zh-CN.md
projects/llama_index_rag/README_zh-CN.md
+0
-20
No files found.
LICENSE.md
View file @
20937b09
...
@@ -660,6 +660,3 @@ if any, to sign a "copyright disclaimer" for the program, if necessary.
...
@@ -660,6 +660,3 @@ if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>
.
<https://www.gnu.org/licenses/>
.
$^1$
\ No newline at end of file
README.md
View file @
20937b09
...
@@ -14,14 +14,9 @@
...
@@ -14,14 +14,9 @@
[
](https://pepy.tech/project/magic-pdf)
[
](https://pepy.tech/project/magic-pdf)
[
](https://pepy.tech/project/magic-pdf)
[
](https://pepy.tech/project/magic-pdf)
<<<<<<< HEAD
[
](https://huggingface.co/spaces/opendatalab/MinerU)
[](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
=======
[
](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[
](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[
](https://huggingface.co/spaces/opendatalab/MinerU)
[
](https://huggingface.co/spaces/opendatalab/MinerU)
[
](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[
](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
[
](https://colab.research.google.com/gist/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
[
](https://colab.research.google.com/gist/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
[
](#)
[
](#)
...
...
README_zh-CN.md
View file @
20937b09
...
@@ -14,14 +14,9 @@
...
@@ -14,14 +14,9 @@
[
](https://pepy.tech/project/magic-pdf)
[
](https://pepy.tech/project/magic-pdf)
[
](https://pepy.tech/project/magic-pdf)
[
](https://pepy.tech/project/magic-pdf)
<<<<<<< HEAD
[
](https://huggingface.co/spaces/opendatalab/MinerU)
[](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
=======
[
](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[
](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[
](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[
](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[
](https://huggingface.co/spaces/opendatalab/MinerU)
[
](https://huggingface.co/spaces/opendatalab/MinerU)
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
[
](https://colab.research.google.com/gist/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
[
](https://colab.research.google.com/gist/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
[
](#)
[
](#)
...
@@ -185,13 +180,9 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
...
@@ -185,13 +180,9 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
### 在线体验
### 在线体验
<<<<<<< HEAD
[在线体验点击这里](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
=======
[
](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[
](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[
](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[
](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[
](https://huggingface.co/spaces/opendatalab/MinerU)
[
](https://huggingface.co/spaces/opendatalab/MinerU)
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
### 使用CPU快速体验
### 使用CPU快速体验
...
...
app.py
deleted
100644 → 0
View file @
31a1ecdb
# Copyright (c) Opendatalab. All rights reserved.
import
base64
import
os
import
time
import
zipfile
from
pathlib
import
Path
import
re
from
loguru
import
logger
from
magic_pdf.libs.hash_utils
import
compute_sha256
from
magic_pdf.rw.AbsReaderWriter
import
AbsReaderWriter
from
magic_pdf.rw.DiskReaderWriter
import
DiskReaderWriter
from
magic_pdf.tools.common
import
do_parse
,
prepare_env
os
.
system
(
"pip install gradio"
)
os
.
system
(
"pip install gradio-pdf"
)
import
gradio
as
gr
from
gradio_pdf
import
PDF
def
read_fn
(
path
):
disk_rw
=
DiskReaderWriter
(
os
.
path
.
dirname
(
path
))
return
disk_rw
.
read
(
os
.
path
.
basename
(
path
),
AbsReaderWriter
.
MODE_BIN
)
def
parse_pdf
(
doc_path
,
output_dir
,
end_page_id
):
os
.
makedirs
(
output_dir
,
exist_ok
=
True
)
try
:
file_name
=
f
"{str(Path(doc_path).stem)}_{time.time()}"
pdf_data
=
read_fn
(
doc_path
)
parse_method
=
"auto"
local_image_dir
,
local_md_dir
=
prepare_env
(
output_dir
,
file_name
,
parse_method
)
do_parse
(
output_dir
,
file_name
,
pdf_data
,
[],
parse_method
,
False
,
end_page_id
=
end_page_id
,
)
return
local_md_dir
,
file_name
except
Exception
as
e
:
logger
.
exception
(
e
)
def
compress_directory_to_zip
(
directory_path
,
output_zip_path
):
"""
压缩指定目录到一个 ZIP 文件。
:param directory_path: 要压缩的目录路径
:param output_zip_path: 输出的 ZIP 文件路径
"""
try
:
with
zipfile
.
ZipFile
(
output_zip_path
,
'w'
,
zipfile
.
ZIP_DEFLATED
)
as
zipf
:
# 遍历目录中的所有文件和子目录
for
root
,
dirs
,
files
in
os
.
walk
(
directory_path
):
for
file
in
files
:
# 构建完整的文件路径
file_path
=
os
.
path
.
join
(
root
,
file
)
# 计算相对路径
arcname
=
os
.
path
.
relpath
(
file_path
,
directory_path
)
# 添加文件到 ZIP 文件
zipf
.
write
(
file_path
,
arcname
)
return
0
except
Exception
as
e
:
logger
.
exception
(
e
)
return
-
1
def
image_to_base64
(
image_path
):
with
open
(
image_path
,
"rb"
)
as
image_file
:
return
base64
.
b64encode
(
image_file
.
read
())
.
decode
(
'utf-8'
)
def
replace_image_with_base64
(
markdown_text
,
image_dir_path
):
# 匹配Markdown中的图片标签
pattern
=
r'\!\[(?:[^\]]*)\]\(([^)]+)\)'
# 替换图片链接
def
replace
(
match
):
relative_path
=
match
.
group
(
1
)
full_path
=
os
.
path
.
join
(
image_dir_path
,
relative_path
)
base64_image
=
image_to_base64
(
full_path
)
return
f
""
# 应用替换
return
re
.
sub
(
pattern
,
replace
,
markdown_text
)
def
to_markdown
(
file_path
,
end_pages
):
# 获取识别的md文件以及压缩包文件路径
local_md_dir
,
file_name
=
parse_pdf
(
file_path
,
'./output'
,
end_pages
-
1
)
archive_zip_path
=
os
.
path
.
join
(
"./output"
,
compute_sha256
(
local_md_dir
)
+
".zip"
)
zip_archive_success
=
compress_directory_to_zip
(
local_md_dir
,
archive_zip_path
)
if
zip_archive_success
==
0
:
logger
.
info
(
"压缩成功"
)
else
:
logger
.
error
(
"压缩失败"
)
md_path
=
os
.
path
.
join
(
local_md_dir
,
file_name
+
".md"
)
with
open
(
md_path
,
'r'
,
encoding
=
'utf-8'
)
as
f
:
txt_content
=
f
.
read
()
md_content
=
replace_image_with_base64
(
txt_content
,
local_md_dir
)
# 返回转换后的PDF路径
new_pdf_path
=
os
.
path
.
join
(
local_md_dir
,
file_name
+
"_layout.pdf"
)
return
md_content
,
txt_content
,
archive_zip_path
,
new_pdf_path
# def show_pdf(file_path):
# with open(file_path, "rb") as f:
# base64_pdf = base64.b64encode(f.read()).decode('utf-8')
# pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" ' \
# f'width="100%" height="1000" type="application/pdf">'
# return pdf_display
latex_delimiters
=
[{
"left"
:
"$$"
,
"right"
:
"$$"
,
"display"
:
True
},
{
"left"
:
'$'
,
"right"
:
'$'
,
"display"
:
False
}]
def
init_model
():
from
magic_pdf.model.doc_analyze_by_custom_model
import
ModelSingleton
try
:
model_manager
=
ModelSingleton
()
txt_model
=
model_manager
.
get_model
(
False
,
False
)
logger
.
info
(
f
"txt_model init final"
)
ocr_model
=
model_manager
.
get_model
(
True
,
False
)
logger
.
info
(
f
"ocr_model init final"
)
return
0
except
Exception
as
e
:
logger
.
exception
(
e
)
return
-
1
model_init
=
init_model
()
logger
.
info
(
f
"model_init: {model_init}"
)
if
__name__
==
"__main__"
:
with
gr
.
Blocks
()
as
demo
:
with
gr
.
Row
():
with
gr
.
Column
(
variant
=
'panel'
,
scale
=
5
):
pdf_show
=
gr
.
Markdown
()
max_pages
=
gr
.
Slider
(
1
,
10
,
5
,
step
=
1
,
label
=
"Max convert pages"
)
with
gr
.
Row
()
as
bu_flow
:
change_bu
=
gr
.
Button
(
"Convert"
)
clear_bu
=
gr
.
ClearButton
([
pdf_show
],
value
=
"Clear"
)
pdf_show
=
PDF
(
label
=
"Please upload pdf"
,
interactive
=
True
,
height
=
800
)
with
gr
.
Column
(
variant
=
'panel'
,
scale
=
5
):
output_file
=
gr
.
File
(
label
=
"convert result"
,
interactive
=
False
)
with
gr
.
Tabs
():
with
gr
.
Tab
(
"Markdown rendering"
):
md
=
gr
.
Markdown
(
label
=
"Markdown rendering"
,
height
=
900
,
show_copy_button
=
True
,
latex_delimiters
=
latex_delimiters
,
line_breaks
=
True
)
with
gr
.
Tab
(
"Markdown text"
):
md_text
=
gr
.
TextArea
(
lines
=
45
,
show_copy_button
=
True
)
change_bu
.
click
(
fn
=
to_markdown
,
inputs
=
[
pdf_show
,
max_pages
],
outputs
=
[
md
,
md_text
,
output_file
,
pdf_show
])
clear_bu
.
add
([
md
,
pdf_show
,
md_text
,
output_file
])
demo
.
launch
()
magic_pdf/libs/version.py
View file @
20937b09
<<<<<<<
HEAD
__version__
=
"0.7.1"
=======
__version__
=
"0.8.0"
__version__
=
"0.8.0"
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
magic_pdf/model/doc_analyze_by_custom_model.py
View file @
20937b09
...
@@ -106,11 +106,7 @@ def custom_model_init(ocr: bool = False, show_log: bool = False, lang=None):
...
@@ -106,11 +106,7 @@ def custom_model_init(ocr: bool = False, show_log: bool = False, lang=None):
def
doc_analyze
(
pdf_bytes
:
bytes
,
ocr
:
bool
=
False
,
show_log
:
bool
=
False
,
def
doc_analyze
(
pdf_bytes
:
bytes
,
ocr
:
bool
=
False
,
show_log
:
bool
=
False
,
<<<<<<<
HEAD
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
=======
start_page_id
=
0
,
end_page_id
=
None
):
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
model_manager
=
ModelSingleton
()
model_manager
=
ModelSingleton
()
custom_model
=
model_manager
.
get_model
(
ocr
,
show_log
,
lang
)
custom_model
=
model_manager
.
get_model
(
ocr
,
show_log
,
lang
)
...
...
magic_pdf/model/pdf_extract_kit.py
View file @
20937b09
...
@@ -74,16 +74,11 @@ def layout_model_init(weight, config_file, device):
...
@@ -74,16 +74,11 @@ def layout_model_init(weight, config_file, device):
return
model
return
model
<<<<<<<
HEAD
def
ocr_model_init
(
show_log
:
bool
=
False
,
det_db_box_thresh
=
0.3
,
lang
=
None
):
def
ocr_model_init
(
show_log
:
bool
=
False
,
det_db_box_thresh
=
0.3
,
lang
=
None
):
if
lang
is
not
None
:
if
lang
is
not
None
:
model
=
ModifiedPaddleOCR
(
show_log
=
show_log
,
det_db_box_thresh
=
det_db_box_thresh
,
lang
=
lang
)
model
=
ModifiedPaddleOCR
(
show_log
=
show_log
,
det_db_box_thresh
=
det_db_box_thresh
,
lang
=
lang
)
else
:
else
:
model
=
ModifiedPaddleOCR
(
show_log
=
show_log
,
det_db_box_thresh
=
det_db_box_thresh
)
model
=
ModifiedPaddleOCR
(
show_log
=
show_log
,
det_db_box_thresh
=
det_db_box_thresh
)
=======
def
ocr_model_init
(
show_log
:
bool
=
False
,
det_db_box_thresh
=
0.3
):
model
=
ModifiedPaddleOCR
(
show_log
=
show_log
,
det_db_box_thresh
=
det_db_box_thresh
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
return
model
return
model
...
@@ -142,12 +137,8 @@ def atom_model_init(model_name: str, **kwargs):
...
@@ -142,12 +137,8 @@ def atom_model_init(model_name: str, **kwargs):
elif
model_name
==
AtomicModel
.
OCR
:
elif
model_name
==
AtomicModel
.
OCR
:
atom_model
=
ocr_model_init
(
atom_model
=
ocr_model_init
(
kwargs
.
get
(
"ocr_show_log"
),
kwargs
.
get
(
"ocr_show_log"
),
<<<<<<<
HEAD
kwargs
.
get
(
"det_db_box_thresh"
),
kwargs
.
get
(
"det_db_box_thresh"
),
kwargs
.
get
(
"lang"
)
kwargs
.
get
(
"lang"
)
=======
kwargs
.
get
(
"det_db_box_thresh"
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
)
)
elif
model_name
==
AtomicModel
.
Table
:
elif
model_name
==
AtomicModel
.
Table
:
atom_model
=
table_model_init
(
atom_model
=
table_model_init
(
...
@@ -244,12 +235,8 @@ class CustomPEKModel:
...
@@ -244,12 +235,8 @@ class CustomPEKModel:
self
.
ocr_model
=
atom_model_manager
.
get_atom_model
(
self
.
ocr_model
=
atom_model_manager
.
get_atom_model
(
atom_model_name
=
AtomicModel
.
OCR
,
atom_model_name
=
AtomicModel
.
OCR
,
ocr_show_log
=
show_log
,
ocr_show_log
=
show_log
,
<<<<<<<
HEAD
det_db_box_thresh
=
0.3
,
det_db_box_thresh
=
0.3
,
lang
=
self
.
lang
lang
=
self
.
lang
=======
det_db_box_thresh
=
0.3
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
)
)
# init table model
# init table model
if
self
.
apply_table
:
if
self
.
apply_table
:
...
...
magic_pdf/pipe/AbsPipe.py
View file @
20937b09
...
@@ -17,11 +17,7 @@ class AbsPipe(ABC):
...
@@ -17,11 +17,7 @@ class AbsPipe(ABC):
PIP_TXT
=
"txt"
PIP_TXT
=
"txt"
def
__init__
(
self
,
pdf_bytes
:
bytes
,
model_list
:
list
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
def
__init__
(
self
,
pdf_bytes
:
bytes
,
model_list
:
list
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
<<<<<<<
HEAD
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
=======
start_page_id
=
0
,
end_page_id
=
None
):
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
self
.
pdf_bytes
=
pdf_bytes
self
.
pdf_bytes
=
pdf_bytes
self
.
model_list
=
model_list
self
.
model_list
=
model_list
self
.
image_writer
=
image_writer
self
.
image_writer
=
image_writer
...
@@ -29,10 +25,7 @@ class AbsPipe(ABC):
...
@@ -29,10 +25,7 @@ class AbsPipe(ABC):
self
.
is_debug
=
is_debug
self
.
is_debug
=
is_debug
self
.
start_page_id
=
start_page_id
self
.
start_page_id
=
start_page_id
self
.
end_page_id
=
end_page_id
self
.
end_page_id
=
end_page_id
<<<<<<<
HEAD
self
.
lang
=
lang
self
.
lang
=
lang
=======
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
def
get_compress_pdf_mid_data
(
self
):
def
get_compress_pdf_mid_data
(
self
):
return
JsonCompressor
.
compress_json
(
self
.
pdf_mid_data
)
return
JsonCompressor
.
compress_json
(
self
.
pdf_mid_data
)
...
...
magic_pdf/pipe/OCRPipe.py
View file @
20937b09
...
@@ -10,25 +10,16 @@ from magic_pdf.user_api import parse_ocr_pdf
...
@@ -10,25 +10,16 @@ from magic_pdf.user_api import parse_ocr_pdf
class
OCRPipe
(
AbsPipe
):
class
OCRPipe
(
AbsPipe
):
def
__init__
(
self
,
pdf_bytes
:
bytes
,
model_list
:
list
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
def
__init__
(
self
,
pdf_bytes
:
bytes
,
model_list
:
list
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
<<<<<<<
HEAD
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
super
()
.
__init__
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
,
start_page_id
,
end_page_id
,
lang
)
super
()
.
__init__
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
,
start_page_id
,
end_page_id
,
lang
)
=======
start_page_id
=
0
,
end_page_id
=
None
):
super
()
.
__init__
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
,
start_page_id
,
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
def
pipe_classify
(
self
):
def
pipe_classify
(
self
):
pass
pass
def
pipe_analyze
(
self
):
def
pipe_analyze
(
self
):
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
True
,
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
True
,
<<<<<<<
HEAD
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
lang
=
self
.
lang
)
lang
=
self
.
lang
)
=======
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
def
pipe_parse
(
self
):
def
pipe_parse
(
self
):
self
.
pdf_mid_data
=
parse_ocr_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
is_debug
=
self
.
is_debug
,
self
.
pdf_mid_data
=
parse_ocr_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
is_debug
=
self
.
is_debug
,
...
...
magic_pdf/pipe/TXTPipe.py
View file @
20937b09
...
@@ -11,25 +11,16 @@ from magic_pdf.user_api import parse_txt_pdf
...
@@ -11,25 +11,16 @@ from magic_pdf.user_api import parse_txt_pdf
class
TXTPipe
(
AbsPipe
):
class
TXTPipe
(
AbsPipe
):
def
__init__
(
self
,
pdf_bytes
:
bytes
,
model_list
:
list
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
def
__init__
(
self
,
pdf_bytes
:
bytes
,
model_list
:
list
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
<<<<<<<
HEAD
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
super
()
.
__init__
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
,
start_page_id
,
end_page_id
,
lang
)
super
()
.
__init__
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
,
start_page_id
,
end_page_id
,
lang
)
=======
start_page_id
=
0
,
end_page_id
=
None
):
super
()
.
__init__
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
,
start_page_id
,
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
def
pipe_classify
(
self
):
def
pipe_classify
(
self
):
pass
pass
def
pipe_analyze
(
self
):
def
pipe_analyze
(
self
):
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
False
,
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
False
,
<<<<<<<
HEAD
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
lang
=
self
.
lang
)
lang
=
self
.
lang
)
=======
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
def
pipe_parse
(
self
):
def
pipe_parse
(
self
):
self
.
pdf_mid_data
=
parse_txt_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
is_debug
=
self
.
is_debug
,
self
.
pdf_mid_data
=
parse_txt_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
is_debug
=
self
.
is_debug
,
...
...
magic_pdf/pipe/UNIPipe.py
View file @
20937b09
...
@@ -14,15 +14,9 @@ from magic_pdf.user_api import parse_union_pdf, parse_ocr_pdf
...
@@ -14,15 +14,9 @@ from magic_pdf.user_api import parse_union_pdf, parse_ocr_pdf
class
UNIPipe
(
AbsPipe
):
class
UNIPipe
(
AbsPipe
):
def
__init__
(
self
,
pdf_bytes
:
bytes
,
jso_useful_key
:
dict
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
def
__init__
(
self
,
pdf_bytes
:
bytes
,
jso_useful_key
:
dict
,
image_writer
:
AbsReaderWriter
,
is_debug
:
bool
=
False
,
<<<<<<<
HEAD
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
):
self
.
pdf_type
=
jso_useful_key
[
"_pdf_type"
]
self
.
pdf_type
=
jso_useful_key
[
"_pdf_type"
]
super
()
.
__init__
(
pdf_bytes
,
jso_useful_key
[
"model_list"
],
image_writer
,
is_debug
,
start_page_id
,
end_page_id
,
lang
)
super
()
.
__init__
(
pdf_bytes
,
jso_useful_key
[
"model_list"
],
image_writer
,
is_debug
,
start_page_id
,
end_page_id
,
lang
)
=======
start_page_id
=
0
,
end_page_id
=
None
):
self
.
pdf_type
=
jso_useful_key
[
"_pdf_type"
]
super
()
.
__init__
(
pdf_bytes
,
jso_useful_key
[
"model_list"
],
image_writer
,
is_debug
,
start_page_id
,
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
if
len
(
self
.
model_list
)
==
0
:
if
len
(
self
.
model_list
)
==
0
:
self
.
input_model_is_empty
=
True
self
.
input_model_is_empty
=
True
else
:
else
:
...
@@ -34,30 +28,19 @@ class UNIPipe(AbsPipe):
...
@@ -34,30 +28,19 @@ class UNIPipe(AbsPipe):
def
pipe_analyze
(
self
):
def
pipe_analyze
(
self
):
if
self
.
pdf_type
==
self
.
PIP_TXT
:
if
self
.
pdf_type
==
self
.
PIP_TXT
:
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
False
,
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
False
,
<<<<<<<
HEAD
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
lang
=
self
.
lang
)
lang
=
self
.
lang
)
elif
self
.
pdf_type
==
self
.
PIP_OCR
:
elif
self
.
pdf_type
==
self
.
PIP_OCR
:
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
True
,
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
True
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
lang
=
self
.
lang
)
lang
=
self
.
lang
)
=======
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
)
elif
self
.
pdf_type
==
self
.
PIP_OCR
:
self
.
model_list
=
doc_analyze
(
self
.
pdf_bytes
,
ocr
=
True
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
def
pipe_parse
(
self
):
def
pipe_parse
(
self
):
if
self
.
pdf_type
==
self
.
PIP_TXT
:
if
self
.
pdf_type
==
self
.
PIP_TXT
:
self
.
pdf_mid_data
=
parse_union_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
self
.
pdf_mid_data
=
parse_union_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
is_debug
=
self
.
is_debug
,
input_model_is_empty
=
self
.
input_model_is_empty
,
is_debug
=
self
.
is_debug
,
input_model_is_empty
=
self
.
input_model_is_empty
,
<<<<<<<
HEAD
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
,
lang
=
self
.
lang
)
lang
=
self
.
lang
)
=======
start_page_id
=
self
.
start_page_id
,
end_page_id
=
self
.
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
elif
self
.
pdf_type
==
self
.
PIP_OCR
:
elif
self
.
pdf_type
==
self
.
PIP_OCR
:
self
.
pdf_mid_data
=
parse_ocr_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
self
.
pdf_mid_data
=
parse_ocr_pdf
(
self
.
pdf_bytes
,
self
.
model_list
,
self
.
image_writer
,
is_debug
=
self
.
is_debug
,
is_debug
=
self
.
is_debug
,
...
...
magic_pdf/resources/model_config/model_configs.yaml
View file @
20937b09
...
@@ -10,10 +10,6 @@ config:
...
@@ -10,10 +10,6 @@ config:
weights
:
weights
:
layout
:
Layout/model_final.pth
layout
:
Layout/model_final.pth
mfd
:
MFD/weights.pt
mfd
:
MFD/weights.pt
<<<<<<< HEAD
mfr
:
MFR/unimernet_base
mfr
:
MFR/unimernet_base
=======
mfr
:
MFR/UniMERNet
>
>>>>>>
0140d7d271ac3b1561ca2272030e9e038b469999
struct_eqtable
:
TabRec/StructEqTable
struct_eqtable
:
TabRec/StructEqTable
TableMaster
:
TabRec/TableMaster
TableMaster
:
TabRec/TableMaster
\ No newline at end of file
magic_pdf/tools/cli.py
View file @
20937b09
...
@@ -45,7 +45,6 @@ without method specified, auto will be used by default.""",
...
@@ -45,7 +45,6 @@ without method specified, auto will be used by default.""",
default
=
'auto'
,
default
=
'auto'
,
)
)
@
click
.
option
(
@
click
.
option
(
<<<<<<<
HEAD
'-l'
,
'-l'
,
'--lang'
,
'--lang'
,
'lang'
,
'lang'
,
...
@@ -58,8 +57,6 @@ without method specified, auto will be used by default.""",
...
@@ -58,8 +57,6 @@ without method specified, auto will be used by default.""",
default
=
None
,
default
=
None
,
)
)
@
click
.
option
(
@
click
.
option
(
=======
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
'-d'
,
'-d'
,
'--debug'
,
'--debug'
,
'debug_able'
,
'debug_able'
,
...
@@ -83,11 +80,7 @@ without method specified, auto will be used by default.""",
...
@@ -83,11 +80,7 @@ without method specified, auto will be used by default.""",
help
=
'The ending page for PDF parsing, beginning from 0.'
,
help
=
'The ending page for PDF parsing, beginning from 0.'
,
default
=
None
,
default
=
None
,
)
)
<<<<<<<
HEAD
def
cli
(
path
,
output_dir
,
method
,
lang
,
debug_able
,
start_page_id
,
end_page_id
):
def
cli
(
path
,
output_dir
,
method
,
lang
,
debug_able
,
start_page_id
,
end_page_id
):
=======
def
cli
(
path
,
output_dir
,
method
,
debug_able
,
start_page_id
,
end_page_id
):
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
model_config
.
__use_inside_model__
=
True
model_config
.
__use_inside_model__
=
True
model_config
.
__model_mode__
=
'full'
model_config
.
__model_mode__
=
'full'
os
.
makedirs
(
output_dir
,
exist_ok
=
True
)
os
.
makedirs
(
output_dir
,
exist_ok
=
True
)
...
@@ -109,10 +102,7 @@ def cli(path, output_dir, method, debug_able, start_page_id, end_page_id):
...
@@ -109,10 +102,7 @@ def cli(path, output_dir, method, debug_able, start_page_id, end_page_id):
debug_able
,
debug_able
,
start_page_id
=
start_page_id
,
start_page_id
=
start_page_id
,
end_page_id
=
end_page_id
,
end_page_id
=
end_page_id
,
<<<<<<<
HEAD
lang
=
lang
lang
=
lang
=======
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
)
)
except
Exception
as
e
:
except
Exception
as
e
:
...
...
magic_pdf/user_api.py
View file @
20937b09
...
@@ -71,11 +71,7 @@ def parse_ocr_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWrit
...
@@ -71,11 +71,7 @@ def parse_ocr_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWrit
def
parse_union_pdf
(
pdf_bytes
:
bytes
,
pdf_models
:
list
,
imageWriter
:
AbsReaderWriter
,
is_debug
=
False
,
def
parse_union_pdf
(
pdf_bytes
:
bytes
,
pdf_models
:
list
,
imageWriter
:
AbsReaderWriter
,
is_debug
=
False
,
input_model_is_empty
:
bool
=
False
,
input_model_is_empty
:
bool
=
False
,
<<<<<<<
HEAD
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
,
start_page_id
=
0
,
end_page_id
=
None
,
lang
=
None
,
=======
start_page_id
=
0
,
end_page_id
=
None
,
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
*
args
,
**
kwargs
):
*
args
,
**
kwargs
):
"""
"""
ocr和文本混合的pdf，全部解析出来
ocr和文本混合的pdf，全部解析出来
...
@@ -99,17 +95,11 @@ def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWr
...
@@ -99,17 +95,11 @@ def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWr
if
pdf_info_dict
is
None
or
pdf_info_dict
.
get
(
"_need_drop"
,
False
):
if
pdf_info_dict
is
None
or
pdf_info_dict
.
get
(
"_need_drop"
,
False
):
logger
.
warning
(
f
"parse_pdf_by_txt drop or error, switch to parse_pdf_by_ocr"
)
logger
.
warning
(
f
"parse_pdf_by_txt drop or error, switch to parse_pdf_by_ocr"
)
if
input_model_is_empty
:
if
input_model_is_empty
:
<<<<<<<
HEAD
pdf_models
=
doc_analyze
(
pdf_bytes
,
pdf_models
=
doc_analyze
(
pdf_bytes
,
ocr
=
True
,
ocr
=
True
,
start_page_id
=
start_page_id
,
start_page_id
=
start_page_id
,
end_page_id
=
end_page_id
,
end_page_id
=
end_page_id
,
lang
=
lang
)
lang
=
lang
)
=======
pdf_models
=
doc_analyze
(
pdf_bytes
,
ocr
=
True
,
start_page_id
=
start_page_id
,
end_page_id
=
end_page_id
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
pdf_info_dict
=
parse_pdf
(
parse_pdf_by_ocr
)
pdf_info_dict
=
parse_pdf
(
parse_pdf_by_ocr
)
if
pdf_info_dict
is
None
:
if
pdf_info_dict
is
None
:
raise
Exception
(
"Both parse_pdf_by_txt and parse_pdf_by_ocr failed."
)
raise
Exception
(
"Both parse_pdf_by_txt and parse_pdf_by_ocr failed."
)
...
...
mv_pdf.py
deleted
100644 → 0
View file @
31a1ecdb
import
os
import
shutil
def
move_pdfs
(
root_folder
,
destination_folder
):
# 遍历根目录及其子目录中的所有文件
for
root
,
dirs
,
files
in
os
.
walk
(
root_folder
):
for
file
in
files
:
if
file
.
endswith
(
'.pdf'
):
# 构建完整的文件路径
src_path
=
os
.
path
.
join
(
root
,
file
)
# 构建目标路径
dst_path
=
os
.
path
.
join
(
destination_folder
,
file
)
# 移动文件
shutil
.
move
(
src_path
,
dst_path
)
print
(
f
'Moved {file} to {destination_folder}'
)
# 使用方法
root_folder
=
r'D:\mineru\datasets\datasets'
# 源文件夹路径
destination_folder
=
r'D:\mineru\datasets\pdf'
# 目标文件夹路径
# 创建目标文件夹如果不存在
if
not
os
.
path
.
exists
(
destination_folder
):
os
.
makedirs
(
destination_folder
)
move_pdfs
(
root_folder
,
destination_folder
)
\ No newline at end of file
projects/README.md
View file @
20937b09
...
@@ -3,9 +3,6 @@
...
@@ -3,9 +3,6 @@
## Project List
## Project List
-
[
llama_index_rag
](
./llama_index_rag/README.md
)
: Build a lightweight RAG system based on llama_index
-
[
llama_index_rag
](
./llama_index_rag/README.md
)
: Build a lightweight RAG system based on llama_index
<<<<<<< HEAD
-
[
gradio_app
](
./gradio_app/README.md
)
: Build a web app based on gradio
-
[
gradio_app
](
./gradio_app/README.md
)
: Build a web app based on gradio
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
projects/README_zh-CN.md
View file @
20937b09
...
@@ -3,8 +3,5 @@
...
@@ -3,8 +3,5 @@
## 项目列表
## 项目列表
-
[
llama_index_rag
](
./llama_index_rag/README_zh-CN.md
)
: 基于 llama_index 构建轻量级 RAG 系统
-
[
llama_index_rag
](
./llama_index_rag/README_zh-CN.md
)
: 基于 llama_index 构建轻量级 RAG 系统
<<<<<<< HEAD
-
[
gradio_app
](
./gradio_app/README_zh-CN.md
)
: 基于 Gradio 的 Web 应用
-
[
gradio_app
](
./gradio_app/README_zh-CN.md
)
: 基于 Gradio 的 Web 应用
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
projects/llama_index_rag/README_zh-CN.md
View file @
20937b09
...
@@ -59,10 +59,6 @@ Server: Docker Engine - Community
...
@@ -59,10 +59,6 @@ Server: Docker Engine - Community
```
bash
```
bash
# install
# install
pip
install
modelscope
==
1.14.0
pip
install
modelscope
==
1.14.0
<<<<<<
< HEAD
=======
>>>>>>>
0140d7d271ac3b1561ca2272030e9e038b469999
pip
install
llama-index-vector-stores-elasticsearch
==
0.2.0
pip
install
llama-index-vector-stores-elasticsearch
==
0.2.0
pip
install
llama-index-embeddings-dashscope
==
0.2.0
pip
install
llama-index-embeddings-dashscope
==
0.2.0
pip
install
llama-index-core
==
0.10.68
pip
install
llama-index-core
==
0.10.68
...
@@ -74,19 +70,12 @@ pip install accelerate==0.33.0
...
@@ -74,19 +70,12 @@ pip install accelerate==0.33.0
pip uninstall transformer-engine
pip uninstall transformer-engine
```
```
<<<<<<< HEAD
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
## 示例
## 示例
```
`bash
```
`bash
cd projects/llama_index_rag
cd projects/llama_index_rag
<<<<<<< HEAD
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
docker compose up -d
docker compose up -d
or
or
...
@@ -94,20 +83,14 @@ or
...
@@ -94,20 +83,14 @@ or
docker-compose up -d
docker-compose up -d
<<<<<<< HEAD
# 配置环境变量
# 配置环境变量
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
export ES_USER=elastic
export ES_USER=elastic
export ES_PASSWORD=llama_index
export ES_PASSWORD=llama_index
export ES_URL=http://127.0.0.1:9200
export ES_URL=http://127.0.0.1:9200
export DASHSCOPE_API_KEY={some_key}
export DASHSCOPE_API_KEY={some_key}
<<<<<<< HEAD
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
DASHSCOPE_API_KEY 开通参考[文档](https://help.aliyun.com/zh/dashscope/opening-service)
DASHSCOPE_API_KEY 开通参考[文档](https://help.aliyun.com/zh/dashscope/opening-service)
# 未导入数据，查询问题。返回通义千问默认答案
# 未导入数据，查询问题。返回通义千问默认答案
...
@@ -135,10 +118,7 @@ python data_ingestion.py -p example/data/declaration_of_the_rights_of_man_1789.p
...
@@ -135,10 +118,7 @@ python data_ingestion.py -p example/data/declaration_of_the_rights_of_man_1789.p
# 导入数据后，查询问题。通义千问模型会根据 RAG 系统的检索结果，结合上下文，给出答案。
# 导入数据后，查询问题。通义千问模型会根据 RAG 系统的检索结果，结合上下文，给出答案。
<<<<<<< HEAD
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
python query.py -q 'how about the rights of men'
python query.py -q 'how about the rights of men'
## outputs
## outputs
...
...
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
