navexOCR 1.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (14) hide show
  1. navexocr-1.0.0/MANIFEST.in +0 -0
  2. navexocr-1.0.0/PKG-INFO +18 -0
  3. navexocr-1.0.0/README.md +0 -0
  4. navexocr-1.0.0/navexOCR/__init__.py +1 -0
  5. navexocr-1.0.0/navexOCR/api.py +47 -0
  6. navexocr-1.0.0/navexOCR/config.py +38 -0
  7. navexocr-1.0.0/navexOCR/main.py +32 -0
  8. navexocr-1.0.0/navexOCR.egg-info/PKG-INFO +18 -0
  9. navexocr-1.0.0/navexOCR.egg-info/SOURCES.txt +12 -0
  10. navexocr-1.0.0/navexOCR.egg-info/dependency_links.txt +1 -0
  11. navexocr-1.0.0/navexOCR.egg-info/requires.txt +10 -0
  12. navexocr-1.0.0/navexOCR.egg-info/top_level.txt +1 -0
  13. navexocr-1.0.0/setup.cfg +4 -0
  14. navexocr-1.0.0/setup.py +30 -0
navexocr-1.0.0/MANIFEST.in ADDED
File without changes
navexocr-1.0.0/PKG-INFO ADDED
@@ -0,0 +1,18 @@
1
+ Metadata-Version: 2.4
2
+ Name: navexOCR
3
+ Version: 1.0.0
4
+ Summary: AI OCR PDF to Word Conversion Engine
5
+ Author: Naveen S
6
+ Requires-Dist: fastapi
7
+ Requires-Dist: uvicorn
8
+ Requires-Dist: python-multipart
9
+ Requires-Dist: pymupdf
10
+ Requires-Dist: pillow
11
+ Requires-Dist: paddleocr==2.7.0.3
12
+ Requires-Dist: paddlepaddle==2.6.2
13
+ Requires-Dist: pywin32
14
+ Requires-Dist: numpy==1.26.4
15
+ Requires-Dist: pyfiglet
16
+ Dynamic: author
17
+ Dynamic: requires-dist
18
+ Dynamic: summary
navexocr-1.0.0/README.md ADDED
File without changes
navexocr-1.0.0/navexOCR/__init__.py ADDED
@@ -0,0 +1 @@
1
+ from navexOCR.api import convert_pdf_file
navexocr-1.0.0/navexOCR/api.py ADDED
@@ -0,0 +1,47 @@
1
+ import os
2
+ import uuid
3
+
4
+ from navexOCR.services.ocr_service import (
5
+ create_searchable_pdf
6
+ )
7
+
8
+ from navexOCR.services.word_service import (
9
+ pdf_to_word
10
+ )
11
+
12
+ from navexOCR.config import TEMP_DIR
13
+
14
+
15
+ def convert_pdf_file(input_pdf):
16
+
17
+ job_id = str(uuid.uuid4())
18
+
19
+ work_dir = os.path.join(
20
+ TEMP_DIR,
21
+ job_id
22
+ )
23
+
24
+ os.makedirs(work_dir, exist_ok=True)
25
+
26
+ searchable_pdf = os.path.join(
27
+ work_dir,
28
+ "searchable.pdf"
29
+ )
30
+
31
+ output_docx = os.path.join(
32
+ work_dir,
33
+ "output.docx"
34
+ )
35
+
36
+ create_searchable_pdf(
37
+ input_pdf,
38
+ searchable_pdf
39
+ )
40
+
41
+ pdf_to_word(
42
+ searchable_pdf,
43
+ output_docx,
44
+ work_dir
45
+ )
46
+
47
+ return output_docx
navexocr-1.0.0/navexOCR/config.py ADDED
@@ -0,0 +1,38 @@
1
+ import os
2
+
3
+ BASE_DIR = os.path.dirname(
4
+ os.path.dirname(os.path.abspath(__file__))
5
+ )
6
+
7
+ TEMP_DIR = os.path.join(
8
+ BASE_DIR,
9
+ "navexOCR",
10
+ "temp"
11
+ )
12
+
13
+ OUTPUT_DIR = os.path.join(
14
+ BASE_DIR,
15
+ "outputs"
16
+ )
17
+
18
+ os.makedirs(TEMP_DIR, exist_ok=True)
19
+
20
+ os.makedirs(OUTPUT_DIR, exist_ok=True)
21
+
22
+ DET_MODEL_DIR = os.path.join(
23
+ BASE_DIR,
24
+ "models",
25
+ "det"
26
+ )
27
+
28
+ REC_MODEL_DIR = os.path.join(
29
+ BASE_DIR,
30
+ "models",
31
+ "rec"
32
+ )
33
+
34
+ CLS_MODEL_DIR = os.path.join(
35
+ BASE_DIR,
36
+ "models",
37
+ "cls"
38
+ )
navexocr-1.0.0/navexOCR/main.py ADDED
@@ -0,0 +1,32 @@
1
+ from fastapi import FastAPI
2
+
3
+ from navexOCR.routes.convert import router
4
+
5
+ import pyfiglet
6
+
7
+
8
+ banner = pyfiglet.figlet_format(
9
+ "navexOCR",
10
+ font="slant"
11
+ )
12
+
13
+ print(banner)
14
+
15
+
16
+ app = FastAPI(
17
+
18
+ title="navexOCR API",
19
+
20
+ version="1.0.0"
21
+ )
22
+
23
+ app.include_router(router)
24
+
25
+
26
+ @app.get("/")
27
+ def home():
28
+
29
+ return {
30
+
31
+ "message": "navexOCR API Running"
32
+ }
navexocr-1.0.0/navexOCR.egg-info/PKG-INFO ADDED
@@ -0,0 +1,18 @@
1
+ Metadata-Version: 2.4
2
+ Name: navexOCR
3
+ Version: 1.0.0
4
+ Summary: AI OCR PDF to Word Conversion Engine
5
+ Author: Naveen S
6
+ Requires-Dist: fastapi
7
+ Requires-Dist: uvicorn
8
+ Requires-Dist: python-multipart
9
+ Requires-Dist: pymupdf
10
+ Requires-Dist: pillow
11
+ Requires-Dist: paddleocr==2.7.0.3
12
+ Requires-Dist: paddlepaddle==2.6.2
13
+ Requires-Dist: pywin32
14
+ Requires-Dist: numpy==1.26.4
15
+ Requires-Dist: pyfiglet
16
+ Dynamic: author
17
+ Dynamic: requires-dist
18
+ Dynamic: summary
navexocr-1.0.0/navexOCR.egg-info/SOURCES.txt ADDED
@@ -0,0 +1,12 @@
1
+ MANIFEST.in
2
+ README.md
3
+ setup.py
4
+ navexOCR/__init__.py
5
+ navexOCR/api.py
6
+ navexOCR/config.py
7
+ navexOCR/main.py
8
+ navexOCR.egg-info/PKG-INFO
9
+ navexOCR.egg-info/SOURCES.txt
10
+ navexOCR.egg-info/dependency_links.txt
11
+ navexOCR.egg-info/requires.txt
12
+ navexOCR.egg-info/top_level.txt
navexocr-1.0.0/navexOCR.egg-info/requires.txt ADDED
@@ -0,0 +1,10 @@
1
+ fastapi
2
+ uvicorn
3
+ python-multipart
4
+ pymupdf
5
+ pillow
6
+ paddleocr==2.7.0.3
7
+ paddlepaddle==2.6.2
8
+ pywin32
9
+ numpy==1.26.4
10
+ pyfiglet
navexocr-1.0.0/navexOCR.egg-info/top_level.txt ADDED
@@ -0,0 +1 @@
1
+ navexOCR
navexocr-1.0.0/setup.cfg ADDED
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
navexocr-1.0.0/setup.py ADDED
@@ -0,0 +1,30 @@
1
+ from setuptools import setup, find_packages
2
+
3
+ setup(
4
+
5
+ name="navexOCR",
6
+
7
+ version="1.0.0",
8
+
9
+ author="Naveen S",
10
+
11
+ description="AI OCR PDF to Word Conversion Engine",
12
+
13
+ packages=find_packages(),
14
+
15
+ include_package_data=True,
16
+
17
+ install_requires=[
18
+
19
+ "fastapi",
20
+ "uvicorn",
21
+ "python-multipart",
22
+ "pymupdf",
23
+ "pillow",
24
+ "paddleocr==2.7.0.3",
25
+ "paddlepaddle==2.6.2",
26
+ "pywin32",
27
+ "numpy==1.26.4",
28
+ "pyfiglet"
29
+ ]
30
+ )