[package]
edition = "2021"
name = "undoc"
version = "0.1.13"
authors = ["iyulab"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "High-performance Microsoft Office document extraction to Markdown"
readme = "README.md"
keywords = [
"docx",
"xlsx",
"pptx",
"markdown",
"office",
]
categories = [
"parsing",
"text-processing",
]
license = "MIT"
repository = "https://github.com/iyulab/undoc"
[features]
async = ["tokio"]
default = [
"docx",
"xlsx",
"pptx",
]
docx = []
ffi = []
pptx = []
xlsx = []
[lib]
name = "undoc"
crate-type = [
"lib",
"cdylib",
]
path = "src/lib.rs"
[[bin]]
name = "explore"
path = "src/bin/explore.rs"
[[bin]]
name = "explore_pptx"
path = "src/bin/explore_pptx.rs"
[[bin]]
name = "explore_xlsx"
path = "src/bin/explore_xlsx.rs"
[[test]]
name = "officedissector_corpus"
path = "tests/officedissector_corpus.rs"
[[test]]
name = "quality_report"
path = "tests/quality_report.rs"
[dependencies.quick-xml]
version = "0.37"
features = ["serialize"]
[dependencies.rayon]
version = "1.10"
[dependencies.regex]
version = "1.11"
[dependencies.serde]
version = "1.0"
features = ["derive"]
[dependencies.serde_json]
version = "1.0"
[dependencies.thiserror]
version = "2.0"
[dependencies.tokio]
version = "1.42"
features = [
"rt",
"fs",
]
optional = true
[dependencies.unicode-normalization]
version = "0.1"
[dependencies.unicode-width]
version = "0.2"
[dependencies.zip]
version = "2.2"
[dev-dependencies.tempfile]
version = "3.14"