papyrus-core 0.1.0

PDF-to-Markdown conversion engine with smart heading detection, bold/italic text extraction, and CommonMark output. Pure Rust, best-effort parsing for corrupted PDFs.
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 = "2021"
name = "papyrus-core"
version = "0.1.0"
authors = ["rfxlamia"]
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "PDF-to-Markdown conversion engine with smart heading detection, bold/italic text extraction, and CommonMark output. Pure Rust, best-effort parsing for corrupted PDFs."
readme = false
keywords = [
    "pdf",
    "markdown",
    "extract",
    "convert",
    "text-extraction",
]
categories = [
    "text-processing",
    "parser-implementations",
    "encoding",
]
license = "MIT OR Apache-2.0"
repository = "https://github.com/rfxlamia/papyrus"

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

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

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

[[test]]
name = "integration_phase3_pipeline"
path = "tests/integration_phase3_pipeline.rs"

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

[dependencies.lopdf]
version = "0.35"

[dev-dependencies.pulldown-cmark]
version = "0.10"

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

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