doc_extractor 0.1.1

Extract text chunks from common document formats.
Documentation 
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

[package]
authors.workspace      = true
categories             = ["text-processing"]
description            = "Extract text chunks from common document formats."
edition.workspace      = true
homepage.workspace     = true
keywords               = ["document", "extract", "markdown"]
license.workspace      = true
name                   = "doc_extractor"
repository.workspace   = true
rust-version.workspace = true
version                = "0.1.1"

[dependencies]
infer                  = { workspace = true }
office_oxide           = { workspace = true }
path-ext               = { workspace = true }
pdf_oxide              = { workspace = true }
readability            = { workspace = true }
serde                  = { workspace = true, features = ["derive"] }
serde_json             = { workspace = true }
strum_macros           = { workspace = true }
text-splitter          = { workspace = true }
thiserror              = { workspace = true }
tiktoken-rs            = { workspace = true }
tree-sitter            = { workspace = true }
tree-sitter-c          = { workspace = true }
tree-sitter-cpp        = { workspace = true }
tree-sitter-go         = { workspace = true }
tree-sitter-javascript = { workspace = true }
tree-sitter-python     = { workspace = true }
tree-sitter-rust       = { workspace = true }
tree-sitter-typescript = { workspace = true }
url                    = { workspace = true }