markkit 0.1.0

Extract clean markdown from any format – HTML, PDF, DOCX, and more
Documentation
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.

[package]
edition = "2024"
name = "markkit"
version = "0.1.0"
authors = ["Everruns <oss@everruns.com>"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Extract clean markdown from any format – HTML, PDF, DOCX, and more"
readme = "README.md"
keywords = [
    "markdown",
    "extraction",
    "conversion",
    "html",
    "pdf",
]
categories = [
    "text-processing",
    "command-line-utilities",
    "parser-implementations",
]
license = "MIT"
repository = "https://github.com/everruns/markkit"
resolver = "2"

[features]
all_formats = [
    "html",
    "pdf",
    "docx",
    "spreadsheet",
]
default = [
    "html",
    "http_client",
]
docx = [
    "dep:zip",
    "dep:quick-xml",
]
html = [
    "dep:scraper",
    "dep:html5ever",
    "dep:lol_html",
]
http_client = ["dep:reqwest"]
logging = [
    "dep:tracing",
    "dep:tracing-subscriber",
]
pdf = []
spreadsheet = [
    "dep:calamine",
    "dep:zip",
    "dep:quick-xml",
    "dep:cfb",
]

[lib]
name = "markkit"
path = "src/lib.rs"

[[test]]
name = "document_detection"
path = "tests/document_detection.rs"

[[test]]
name = "document_security"
path = "tests/document_security.rs"

[[test]]
name = "docx_integration"
path = "tests/docx_integration.rs"

[[test]]
name = "html_fixtures"
path = "tests/html_fixtures.rs"

[[test]]
name = "html_integration"
path = "tests/html_integration.rs"

[[test]]
name = "html_proptest"
path = "tests/html_proptest.rs"

[[test]]
name = "html_security"
path = "tests/html_security.rs"

[[test]]
name = "spreadsheet_integration"
path = "tests/spreadsheet_integration.rs"

[[bench]]
name = "extraction"
path = "benches/extraction.rs"
harness = false

[dependencies.anyhow]
version = "1"

[dependencies.async-trait]
version = "0.1"

[dependencies.base64]
version = "0.22"

[dependencies.calamine]
version = "0.36"
optional = true

[dependencies.cfb]
version = "0.15"
optional = true

[dependencies.encoding_rs]
version = "0.8"

[dependencies.futures]
version = "0.3"

[dependencies.html5ever]
version = "0.39"
optional = true

[dependencies.lol_html]
version = "2"
optional = true

[dependencies.mime]
version = "0.3"

[dependencies.quick-xml]
version = "0.41"
optional = true

[dependencies.regex]
version = "1"

[dependencies.reqwest]
version = "0.12"
features = [
    "rustls-tls",
    "json",
]
optional = true
default-features = false

[dependencies.scraper]
version = "0.26"
optional = true

[dependencies.serde]
version = "1"
features = ["derive"]

[dependencies.serde_json]
version = "1"

[dependencies.thiserror]
version = "2"

[dependencies.tokio]
version = "1"
features = [
    "sync",
    "io-util",
]
default-features = false

[dependencies.tracing]
version = "0.1"
optional = true

[dependencies.tracing-subscriber]
version = "0.3"
features = ["env-filter"]
optional = true

[dependencies.unicode-segmentation]
version = "1"

[dependencies.zip]
version = "8"
features = ["deflate"]
optional = true
default-features = false

[dev-dependencies.cfb]
version = "0.15"

[dev-dependencies.criterion]
version = "0.5"
features = ["html_reports"]

[dev-dependencies.proptest]
version = "1"

[dev-dependencies.tempfile]
version = "3"

[dev-dependencies.tokio]
version = "1"
features = [
    "macros",
    "rt-multi-thread",
]
default-features = false

[dev-dependencies.zip]
version = "8"
features = ["deflate"]
default-features = false