pdftext/pyproject.toml at master · datalab-to/pdftext · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
[tool.poetry]
name = "pdftext"
version = "0.6.3"
description = "Extract structured text from pdfs quickly"
authors = ["Vik Paruchuri <vik.paruchuri@gmail.com>"]
license = "Apache-2.0"
readme = "README.md"
repository = "https://github.com/VikParuchuri/pdftext"
keywords = ["pdf", "text", "extraction"]
packages = [
    {include = "pdftext"}
]

[tool.poetry.dependencies]
python = "^3.10"
pypdfium2 = "=4.30.0"
pydantic = "^2.7.1"
pydantic-settings = "^2.2.1"

click = "^8.1.8"
[tool.poetry.group.dev.dependencies]
pymupdf = "^1.24.2"
datasets = "^2.19.0"
pdfplumber = "^0.11.0"
pillow = "^10.3.0"
rapidfuzz = "^3.8.1"
tabulate = "^0.9.0"

pytest = "^8.3.4"
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

[tool.poetry.scripts]
pdftext = "pdftext.scripts.extract_text:extract_text_cli"