markup5ever_rcdom-0.3.0/Cargo.lock 0000644 00000037161 00000000001 0012451 0 ustar # This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "futf"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
dependencies = [
"mac",
"new_debug_unreachable",
]
[[package]]
name = "getopts"
version = "0.2.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5"
dependencies = [
"unicode-width",
]
[[package]]
name = "getrandom"
version = "0.2.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "190092ea657667030ac6a35e305e62fc4dd69fd98ac98631e5d3a2b1575a12b5"
dependencies = [
"cfg-if",
"libc",
"wasi 0.11.0+wasi-snapshot-preview1",
]
[[package]]
name = "html5ever"
version = "0.27.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c13771afe0e6e846f1e67d038d4cb29998a6779f93c809212e4e9c32efd244d4"
dependencies = [
"log",
"mac",
"markup5ever",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "itoa"
version = "1.0.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b1a46d1a171d865aa5f83f92695765caa047a9b4cbae2cbf37dbd613a793fd4c"
[[package]]
name = "kernel32-sys"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7507624b29483431c0ba2d82aece8ca6cdba9382bff4ddd0f7490560c056098d"
dependencies = [
"winapi 0.2.8",
"winapi-build",
]
[[package]]
name = "libc"
version = "0.2.153"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
[[package]]
name = "lock_api"
version = "0.4.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3c168f8615b12bc01f9c17e2eb0cc07dcae1940121185446edc3744920e8ef45"
dependencies = [
"autocfg",
"scopeguard",
]
[[package]]
name = "log"
version = "0.4.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
[[package]]
name = "mac"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
[[package]]
name = "markup5ever"
version = "0.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c7940b09815a02810a42b9e1bc41c069880a87de68e9b1dcbe754a3ba3b47c20"
dependencies = [
"log",
"phf",
"phf_codegen",
"string_cache",
"string_cache_codegen",
"tendril",
]
[[package]]
name = "markup5ever_rcdom"
version = "0.3.0"
dependencies = [
"html5ever",
"markup5ever",
"rustc-test",
"serde_json",
"tendril",
"xml5ever",
]
[[package]]
name = "new_debug_unreachable"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
[[package]]
name = "once_cell"
version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]]
name = "parking_lot"
version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f"
dependencies = [
"lock_api",
"parking_lot_core",
]
[[package]]
name = "parking_lot_core"
version = "0.9.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4c42a9226546d68acdd9c0a280d17ce19bfe27a46bf68784e4066115788d008e"
dependencies = [
"cfg-if",
"libc",
"redox_syscall",
"smallvec",
"windows-targets",
]
[[package]]
name = "phf"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
dependencies = [
"phf_shared 0.11.2",
]
[[package]]
name = "phf_codegen"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a"
dependencies = [
"phf_generator 0.11.2",
"phf_shared 0.11.2",
]
[[package]]
name = "phf_generator"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d5285893bb5eb82e6aaf5d59ee909a06a16737a8970984dd7746ba9283498d6"
dependencies = [
"phf_shared 0.10.0",
"rand",
]
[[package]]
name = "phf_generator"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0"
dependencies = [
"phf_shared 0.11.2",
"rand",
]
[[package]]
name = "phf_shared"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096"
dependencies = [
"siphasher",
]
[[package]]
name = "phf_shared"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b"
dependencies = [
"siphasher",
]
[[package]]
name = "ppv-lite86"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
[[package]]
name = "precomputed-hash"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
[[package]]
name = "proc-macro2"
version = "1.0.79"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e835ff2298f5721608eb1a980ecaee1aef2c132bf95ecc026a11b7bf3c01c02e"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
dependencies = [
"proc-macro2",
]
[[package]]
name = "rand"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
dependencies = [
"libc",
"rand_chacha",
"rand_core",
]
[[package]]
name = "rand_chacha"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
dependencies = [
"ppv-lite86",
"rand_core",
]
[[package]]
name = "rand_core"
version = "0.6.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
dependencies = [
"getrandom",
]
[[package]]
name = "redox_syscall"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4722d768eff46b75989dd134e5c353f0d6296e5aaa3132e776cbdb56be7731aa"
dependencies = [
"bitflags",
]
[[package]]
name = "rustc-serialize"
version = "0.3.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fe834bc780604f4674073badbad26d7219cadfb4a2275802db12cbae17498401"
[[package]]
name = "rustc-test"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aacc7967b0ae83af208c8caf2781cbf96f01dac0157cd89f7f05324d6d4e59bb"
dependencies = [
"getopts",
"libc",
"rustc-serialize",
"rustc_version",
"term",
"time",
]
[[package]]
name = "rustc_version"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "138e3e0acb6c9fb258b19b67cb8abd63c00679d2851805ea151465464fe9030a"
dependencies = [
"semver",
]
[[package]]
name = "ryu"
version = "1.0.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e86697c916019a8588c99b5fac3cead74ec0b4b819707a682fd4d23fa0ce1ba1"
[[package]]
name = "scopeguard"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
[[package]]
name = "semver"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1d7eb9ef2c18661902cc47e535f9bc51b78acd254da71d375c2f6720d9a40403"
dependencies = [
"semver-parser",
]
[[package]]
name = "semver-parser"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
[[package]]
name = "serde"
version = "1.0.197"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fb1c873e1b9b056a4dc4c0c198b24c3ffa059243875552b2bd0933b1aee4ce2"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.197"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7eb0b34b42edc17f6b7cac84a52a1c5f0e1bb2227e997ca9011ea3dd34e8610b"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.114"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c5f09b1bd632ef549eaa9f60a1f8de742bdbc698e6cee2095fc84dde5f549ae0"
dependencies = [
"itoa",
"ryu",
"serde",
]
[[package]]
name = "siphasher"
version = "0.3.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d"
[[package]]
name = "smallvec"
version = "1.13.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
[[package]]
name = "string_cache"
version = "0.8.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f91138e76242f575eb1d3b38b4f1362f10d3a43f47d182a5b359af488a02293b"
dependencies = [
"new_debug_unreachable",
"once_cell",
"parking_lot",
"phf_shared 0.10.0",
"precomputed-hash",
"serde",
]
[[package]]
name = "string_cache_codegen"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6bb30289b722be4ff74a408c3cc27edeaad656e06cb1fe8fa9231fa59c728988"
dependencies = [
"phf_generator 0.10.0",
"phf_shared 0.10.0",
"proc-macro2",
"quote",
]
[[package]]
name = "syn"
version = "2.0.53"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7383cd0e49fff4b6b90ca5670bfd3e9d6a733b3f90c686605aa7eec8c4996032"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "tendril"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
dependencies = [
"futf",
"mac",
"utf-8",
]
[[package]]
name = "term"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa63644f74ce96fbeb9b794f66aff2a52d601cbd5e80f4b97123e3899f4570f1"
dependencies = [
"kernel32-sys",
"winapi 0.2.8",
]
[[package]]
name = "time"
version = "0.1.45"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1b797afad3f312d1c66a56d11d0316f916356d11bd158fbc6ca6389ff6bf805a"
dependencies = [
"libc",
"wasi 0.10.0+wasi-snapshot-preview1",
"winapi 0.3.9",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
[[package]]
name = "unicode-width"
version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e51733f11c9c4f72aa0c160008246859e340b00807569a0da0e7a1079b27ba85"
[[package]]
name = "utf-8"
version = "0.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
[[package]]
name = "wasi"
version = "0.10.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1a143597ca7c7793eff794def352d41792a93c481eb1042423ff7ff72ba2c31f"
[[package]]
name = "wasi"
version = "0.11.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
[[package]]
name = "winapi"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "167dc9d6949a9b857f3451275e911c3f44255842c1f7a76f33c55103a909087a"
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-build"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2d315eee3b34aca4797b2da6b13ed88266e6d612562a0c46390af8299fc699bc"
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]]
name = "windows-targets"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
[[package]]
name = "windows_aarch64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
[[package]]
name = "windows_i686_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
[[package]]
name = "windows_i686_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
[[package]]
name = "windows_x86_64_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
[[package]]
name = "windows_x86_64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
[[package]]
name = "xml5ever"
version = "0.18.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7c376f76ed09df711203e20c3ef5ce556f0166fa03d39590016c0fd625437fad"
dependencies = [
"log",
"mac",
"markup5ever",
]
markup5ever_rcdom-0.3.0/Cargo.toml 0000644 00000002426 00000000001 0012470 0 ustar # 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 = "markup5ever_rcdom"
version = "0.3.0"
authors = ["The html5ever Project Developers"]
include = [
"lib.rs",
"Cargo.toml",
"README.md",
"LICENSE*",
]
description = "Basic, unsupported DOM structure for use by tests in html5ever/xml5ever"
documentation = "https://docs.rs/markup5ever_rcdom"
readme = "README.md"
categories = [
"parser-implementations",
"web-programming",
]
license = "MIT OR Apache-2.0"
repository = "https://github.com/servo/html5ever"
[lib]
path = "lib.rs"
[dependencies.html5ever]
version = "0.27"
[dependencies.markup5ever]
version = "0.12"
[dependencies.tendril]
version = "0.4"
[dependencies.xml5ever]
version = "0.18"
[dev-dependencies.rustc-test]
version = "0.3"
[dev-dependencies.serde_json]
version = "1.0"
[badges.maintenance]
status = "as-is"
markup5ever_rcdom-0.3.0/Cargo.toml.orig 0000644 0000000 0000000 00000001445 10461020230 0016151 0 ustar 0000000 0000000 [package]
name = "markup5ever_rcdom"
version = "0.3.0"
authors = [ "The html5ever Project Developers" ]
license = "MIT OR Apache-2.0"
repository = "https://github.com/servo/html5ever"
description = "Basic, unsupported DOM structure for use by tests in html5ever/xml5ever"
readme = "README.md"
documentation = "https://docs.rs/markup5ever_rcdom"
categories = [ "parser-implementations", "web-programming" ]
edition = "2021"
include = ["lib.rs", "Cargo.toml", "README.md", "LICENSE*"]
[lib]
path = "lib.rs"
[dependencies]
tendril = "0.4"
html5ever = { version = "0.27", path = "../html5ever" }
markup5ever = { version = "0.12", path = "../markup5ever" }
xml5ever = { version = "0.18", path = "../xml5ever" }
[dev-dependencies]
serde_json = "1.0"
rustc-test = "0.3"
[badges]
maintenance.status = "as-is"
markup5ever_rcdom-0.3.0/LICENSE-APACHE 0000644 0000000 0000000 00000025137 10461020230 0015212 0 ustar 0000000 0000000 Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
markup5ever_rcdom-0.3.0/LICENSE-MIT 0000644 0000000 0000000 00000002064 10461020230 0014714 0 ustar 0000000 0000000 Copyright (c) 2014 The html5ever Project Developers
Permission is hereby granted, free of charge, to any
person obtaining a copy of this software and associated
documentation files (the "Software"), to deal in the
Software without restriction, including without
limitation the rights to use, copy, modify, merge,
publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software
is furnished to do so, subject to the following
conditions:
The above copyright notice and this permission notice
shall be included in all copies or substantial portions
of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF
ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR
IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
markup5ever_rcdom-0.3.0/README.md 0000644 0000000 0000000 00000000703 10461020230 0014535 0 ustar 0000000 0000000 # markup5ever_rcdom
This crate is built for the express purpose of writing automated tests for the `html5ever`
and `xml5ever` crates. It is not intended to be a production-quality DOM implementation,
and has not been fuzzed or tested against arbitrary, malicious, or nontrivial inputs. No maintenance
or support for any such issues will be provided. If you use this DOM implementation in a production,
user-facing system, you do so at your own risk.
markup5ever_rcdom-0.3.0/html5lib-tests/LICENSE 0000644 0000000 0000000 00000002117 10461020230 0017144 0 ustar 0000000 0000000 Copyright (c) 2006-2013 James Graham, Geoffrey Sneddon, and
other contributors
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
markup5ever_rcdom-0.3.0/html5lib-tests/lint_lib/_vendor/funcparserlib/LICENSE 0000644 0000000 0000000 00000002054 10461020230 0025233 0 ustar 0000000 0000000 Copyright © 2009/2021 Andrey Vlasovskikh
Permission is hereby granted, free of charge, to any person obtaining a copy of this
software and associated documentation files (the "Software"), to deal in the Software
without restriction, including without limitation the rights to use, copy, modify,
merge, publish, distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to the following
conditions:
The above copyright notice and this permission notice shall be included in all copies or
substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT
OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
markup5ever_rcdom-0.3.0/html5lib-tests/tokenizer/README.md 0000644 0000000 0000000 00000007524 10461020230 0021437 0 ustar 0000000 0000000 Tokenizer tests
===============
The test format is [JSON](http://www.json.org/). This has the advantage
that the syntax allows backward-compatible extensions to the tests and
the disadvantage that it is relatively verbose.
Basic Structure
---------------
{"tests": [
{"description": "Test description",
"input": "input_string",
"output": [expected_output_tokens],
"initialStates": [initial_states],
"lastStartTag": last_start_tag,
"errors": [parse_errors]
}
]}
Multiple tests per file are allowed simply by adding more objects to the
"tests" list.
Each parse error is an object that contains error `code` and one-based
error location indices: `line` and `col`.
`description`, `input` and `output` are always present. The other values
are optional.
### Test set-up
`test.input` is a string containing the characters to pass to the
tokenizer. Specifically, it represents the characters of the **input
stream**, and so implementations are expected to perform the processing
described in the spec's **Preprocessing the input stream** section
before feeding the result to the tokenizer.
If `test.doubleEscaped` is present and `true`, then `test.input` is not
quite as described above. Instead, it must first be subjected to another
round of unescaping (i.e., in addition to any unescaping involved in the
JSON import), and the result of *that* represents the characters of the
input stream. Currently, the only unescaping required by this option is
to convert each sequence of the form \\uHHHH (where H is a hex digit)
into the corresponding Unicode code point. (Note that this option also
affects the interpretation of `test.output`.)
`test.initialStates` is a list of strings, each being the name of a
tokenizer state which can be one of the following:
- `Data state`
- `PLAINTEXT state`
- `RCDATA state`
- `RAWTEXT state`
- `Script data state`
- `CDATA section state`
The test should be run once for each string, using it
to set the tokenizer's initial state for that run. If
`test.initialStates` is omitted, it defaults to `["Data state"]`.
`test.lastStartTag` is a lowercase string that should be used as "the
tag name of the last start tag to have been emitted from this
tokenizer", referenced in the spec's definition of **appropriate end tag
token**. If it is omitted, it is treated as if "no start tag has been
emitted from this tokenizer".
### Test results
`test.output` is a list of tokens, ordered with the first produced by
the tokenizer the first (leftmost) in the list. The list must mach the
**complete** list of tokens that the tokenizer should produce. Valid
tokens are:
["DOCTYPE", name, public_id, system_id, correctness]
["StartTag", name, {attributes}*, true*]
["StartTag", name, {attributes}]
["EndTag", name]
["Comment", data]
["Character", data]
`public_id` and `system_id` are either strings or `null`. `correctness`
is either `true` or `false`; `true` corresponds to the force-quirks flag
being false, and vice-versa.
When the self-closing flag is set, the `StartTag` array has `true` as
its fourth entry. When the flag is not set, the array has only three
entries for backwards compatibility.
All adjacent character tokens are coalesced into a single
`["Character", data]` token.
If `test.doubleEscaped` is present and `true`, then every string within
`test.output` must be further unescaped (as described above) before
comparing with the tokenizer's output.
xmlViolation tests
------------------
`tokenizer/xmlViolation.test` differs from the above in a couple of
ways:
- The name of the single member of the top-level JSON object is
"xmlViolationTests" instead of "tests".
- Each test's expected output assumes that implementation is applying
the tweaks given in the spec's "Coercing an HTML DOM into an
infoset" section.
markup5ever_rcdom-0.3.0/html5lib-tests/tree-construction/README.md 0000644 0000000 0000000 00000011252 10461020230 0023105 0 ustar 0000000 0000000 Tree Construction Tests
=======================
Each file containing tree construction tests consists of any number of
tests separated by two newlines (LF) and a single newline before the end
of the file. For instance:
[TEST]LF
LF
[TEST]LF
LF
[TEST]LF
Where [TEST] is the following format:
Each test must begin with a string "\#data" followed by a newline (LF).
All subsequent lines until a line that says "\#errors" are the test data
and must be passed to the system being tested unchanged, except with the
final newline (on the last line) removed.
Then there must be a line that says "\#errors". It must be followed by
one line per parse error that a conformant checker would return. It
doesn't matter what those lines are, although they can't be
"\#new-errors", "\#document-fragment", "\#document", "\#script-off",
"\#script-on", or empty, the only thing that matters is that there be
the right number of parse errors.
Then there \*may\* be a line that says "\#new-errors", which works like
the "\#errors" section adding more errors to the expected number of
errors.
Then there \*may\* be a line that says "\#document-fragment", which must
be followed by a newline (LF), followed by a string of characters that
indicates the context element, followed by a newline (LF). If the string
of characters starts with "svg ", the context element is in the SVG
namespace and the substring after "svg " is the local name. If the
string of characters starts with "math ", the context element is in the
MathML namespace and the substring after "math " is the local name.
Otherwise, the context element is in the HTML namespace and the string
is the local name. If this line is present the "\#data" must be parsed
using the HTML fragment parsing algorithm with the context element as
context.
Then there \*may\* be a line that says "\#script-off" or
"\#script-on". If a line that says "\#script-off" is present, the
parser must set the scripting flag to disabled. If a line that says
"\#script-on" is present, it must set it to enabled. Otherwise, the
test should be run in both modes.
Then there must be a line that says "\#document", which must be followed
by a dump of the tree of the parsed DOM. Each node must be represented
by a single line. Each line must start with "| ", followed by two spaces
per parent node that the node has before the root document node.
- Element nodes must be represented by a "`<`" then the *tag name
string* "`>`", and all the attributes must be given, sorted
lexicographically by UTF-16 code unit according to their *attribute
name string*, on subsequent lines, as if they were children of the
element node.
- Attribute nodes must have the *attribute name string*, then an "="
sign, then the attribute value in double quotes (").
- Text nodes must be the string, in double quotes. Newlines aren't
escaped.
- Comments must be "`<`" then "`!-- `" then the data then "` -->`".
- DOCTYPEs must be "``".
- Processing instructions must be "``". (The HTML parser cannot emit
processing instructions, but scripts can, and the WebVTT to DOM
rules can emit them.)
- Template contents are represented by the string "content" with the
children below it.
The *tag name string* is the local name prefixed by a namespace
designator. For the HTML namespace, the namespace designator is the
empty string, i.e. there's no prefix. For the SVG namespace, the
namespace designator is "svg ". For the MathML namespace, the namespace
designator is "math ".
The *attribute name string* is the local name prefixed by a namespace
designator. For no namespace, the namespace designator is the empty
string, i.e. there's no prefix. For the XLink namespace, the namespace
designator is "xlink ". For the XML namespace, the namespace designator
is "xml ". For the XMLNS namespace, the namespace designator is "xmlns
". Note the difference between "xlink:href" which is an attribute in no
namespace with the local name "xlink:href" and "xlink href" which is an
attribute in the xlink namespace with the local name "href".
If there is also a "\#document-fragment" the bit following "\#document"
must be a representation of the HTML fragment serialization for the
context element given by "\#document-fragment".
For example:
#data
One
Two
#errors
3: Missing document type declaration
#document
|
|
|
|
| "One"
|
| "Two"
markup5ever_rcdom-0.3.0/lib.rs 0000644 0000000 0000000 00000036203 10461020230 0014376 0 ustar 0000000 0000000 // Copyright 2014-2017 The html5ever Project Developers. See the
// COPYRIGHT file at the top-level directory of this distribution.
//
// Licensed under the Apache License, Version 2.0 or the MIT license
// , at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! A simple reference-counted DOM.
//!
//! This is sufficient as a static parse tree, but don't build a
//! web browser using it. :)
//!
//! A DOM is a [tree structure] with ordered children that can be represented in an XML-like
//! format. For example, the following graph
//!
//! ```text
//! div
//! +- "text node"
//! +- span
//! ```
//! in HTML would be serialized as
//!
//! ```html
//! text node
//! ```
//!
//! See the [document object model article on wikipedia][dom wiki] for more information.
//!
//! This implementation stores the information associated with each node once, and then hands out
//! refs to children. The nodes themselves are reference-counted to avoid copying - you can create
//! a new ref and then a node will outlive the document. Nodes own their children, but only have
//! weak references to their parents.
//!
//! [tree structure]: https://en.wikipedia.org/wiki/Tree_(data_structure)
//! [dom wiki]: https://en.wikipedia.org/wiki/Document_Object_Model
extern crate markup5ever;
extern crate tendril;
use std::borrow::Cow;
use std::cell::{Cell, RefCell};
use std::collections::{HashSet, VecDeque};
use std::fmt;
use std::io;
use std::mem;
use std::rc::{Rc, Weak};
use tendril::StrTendril;
use markup5ever::interface::tree_builder;
use markup5ever::interface::tree_builder::{ElementFlags, NodeOrText, QuirksMode, TreeSink};
use markup5ever::serialize::TraversalScope;
use markup5ever::serialize::TraversalScope::{ChildrenOnly, IncludeNode};
use markup5ever::serialize::{Serialize, Serializer};
use markup5ever::Attribute;
use markup5ever::ExpandedName;
use markup5ever::QualName;
/// The different kinds of nodes in the DOM.
#[derive(Debug)]
pub enum NodeData {
/// The `Document` itself - the root node of a HTML document.
Document,
/// A `DOCTYPE` with name, public id, and system id. See
/// [document type declaration on wikipedia][dtd wiki].
///
/// [dtd wiki]: https://en.wikipedia.org/wiki/Document_type_declaration
Doctype {
name: StrTendril,
public_id: StrTendril,
system_id: StrTendril,
},
/// A text node.
Text { contents: RefCell },
/// A comment.
Comment { contents: StrTendril },
/// An element with attributes.
Element {
name: QualName,
attrs: RefCell>,
/// For HTML \ elements, the [template contents].
///
/// [template contents]: https://html.spec.whatwg.org/multipage/#template-contents
template_contents: RefCell>,
/// Whether the node is a [HTML integration point].
///
/// [HTML integration point]: https://html.spec.whatwg.org/multipage/#html-integration-point
mathml_annotation_xml_integration_point: bool,
},
/// A Processing instruction.
ProcessingInstruction {
target: StrTendril,
contents: StrTendril,
},
}
/// A DOM node.
pub struct Node {
/// Parent node.
pub parent: Cell>,
/// Child nodes of this node.
pub children: RefCell>,
/// Represents this node's data.
pub data: NodeData,
}
impl Node {
/// Create a new node from its contents
pub fn new(data: NodeData) -> Rc {
Rc::new(Node {
data,
parent: Cell::new(None),
children: RefCell::new(Vec::new()),
})
}
}
impl Drop for Node {
fn drop(&mut self) {
let mut nodes = mem::take(&mut *self.children.borrow_mut());
while let Some(node) = nodes.pop() {
let children = mem::take(&mut *node.children.borrow_mut());
nodes.extend(children.into_iter());
if let NodeData::Element {
ref template_contents,
..
} = node.data
{
if let Some(template_contents) = template_contents.borrow_mut().take() {
nodes.push(template_contents);
}
}
}
}
}
impl fmt::Debug for Node {
fn fmt(&self, fmt: &mut fmt::Formatter) -> fmt::Result {
fmt.debug_struct("Node")
.field("data", &self.data)
.field("children", &self.children)
.finish()
}
}
/// Reference to a DOM node.
pub type Handle = Rc;
/// Weak reference to a DOM node, used for parent pointers.
pub type WeakHandle = Weak;
/// Append a parentless node to another nodes' children
fn append(new_parent: &Handle, child: Handle) {
let previous_parent = child.parent.replace(Some(Rc::downgrade(new_parent)));
// Invariant: child cannot have existing parent
assert!(previous_parent.is_none());
new_parent.children.borrow_mut().push(child);
}
/// If the node has a parent, get it and this node's position in its children
fn get_parent_and_index(target: &Handle) -> Option<(Handle, usize)> {
if let Some(weak) = target.parent.take() {
let parent = weak.upgrade().expect("dangling weak pointer");
target.parent.set(Some(weak));
let i = match parent
.children
.borrow()
.iter()
.enumerate()
.find(|&(_, child)| Rc::ptr_eq(child, target))
{
Some((i, _)) => i,
None => panic!("have parent but couldn't find in parent's children!"),
};
Some((parent, i))
} else {
None
}
}
fn append_to_existing_text(prev: &Handle, text: &str) -> bool {
match prev.data {
NodeData::Text { ref contents } => {
contents.borrow_mut().push_slice(text);
true
},
_ => false,
}
}
fn remove_from_parent(target: &Handle) {
if let Some((parent, i)) = get_parent_and_index(target) {
parent.children.borrow_mut().remove(i);
target.parent.set(None);
}
}
/// The DOM itself; the result of parsing.
pub struct RcDom {
/// The `Document` itself.
pub document: Handle,
/// Errors that occurred during parsing.
pub errors: Vec>,
/// The document's quirks mode.
pub quirks_mode: QuirksMode,
}
impl TreeSink for RcDom {
type Output = Self;
fn finish(self) -> Self {
self
}
type Handle = Handle;
fn parse_error(&mut self, msg: Cow<'static, str>) {
self.errors.push(msg);
}
fn get_document(&mut self) -> Handle {
self.document.clone()
}
fn get_template_contents(&mut self, target: &Handle) -> Handle {
if let NodeData::Element {
ref template_contents,
..
} = target.data
{
template_contents
.borrow()
.as_ref()
.expect("not a template element!")
.clone()
} else {
panic!("not a template element!")
}
}
fn set_quirks_mode(&mut self, mode: QuirksMode) {
self.quirks_mode = mode;
}
fn same_node(&self, x: &Handle, y: &Handle) -> bool {
Rc::ptr_eq(x, y)
}
fn elem_name<'a>(&self, target: &'a Handle) -> ExpandedName<'a> {
return match target.data {
NodeData::Element { ref name, .. } => name.expanded(),
_ => panic!("not an element!"),
};
}
fn create_element(
&mut self,
name: QualName,
attrs: Vec,
flags: ElementFlags,
) -> Handle {
Node::new(NodeData::Element {
name,
attrs: RefCell::new(attrs),
template_contents: RefCell::new(if flags.template {
Some(Node::new(NodeData::Document))
} else {
None
}),
mathml_annotation_xml_integration_point: flags.mathml_annotation_xml_integration_point,
})
}
fn create_comment(&mut self, text: StrTendril) -> Handle {
Node::new(NodeData::Comment { contents: text })
}
fn create_pi(&mut self, target: StrTendril, data: StrTendril) -> Handle {
Node::new(NodeData::ProcessingInstruction {
target,
contents: data,
})
}
fn append(&mut self, parent: &Handle, child: NodeOrText) {
// Append to an existing Text node if we have one.
if let NodeOrText::AppendText(text) = &child {
if let Some(h) = parent.children.borrow().last() {
if append_to_existing_text(h, text) {
return;
}
}
}
append(
parent,
match child {
NodeOrText::AppendText(text) => Node::new(NodeData::Text {
contents: RefCell::new(text),
}),
NodeOrText::AppendNode(node) => node,
},
);
}
fn append_before_sibling(&mut self, sibling: &Handle, child: NodeOrText) {
let (parent, i) = get_parent_and_index(sibling)
.expect("append_before_sibling called on node without parent");
let child = match (child, i) {
// No previous node.
(NodeOrText::AppendText(text), 0) => Node::new(NodeData::Text {
contents: RefCell::new(text),
}),
// Look for a text node before the insertion point.
(NodeOrText::AppendText(text), i) => {
let children = parent.children.borrow();
let prev = &children[i - 1];
if append_to_existing_text(prev, &text) {
return;
}
Node::new(NodeData::Text {
contents: RefCell::new(text),
})
},
// The tree builder promises we won't have a text node after
// the insertion point.
// Any other kind of node.
(NodeOrText::AppendNode(node), _) => node,
};
remove_from_parent(&child);
child.parent.set(Some(Rc::downgrade(&parent)));
parent.children.borrow_mut().insert(i, child);
}
fn append_based_on_parent_node(
&mut self,
element: &Self::Handle,
prev_element: &Self::Handle,
child: NodeOrText,
) {
let parent = element.parent.take();
let has_parent = parent.is_some();
element.parent.set(parent);
if has_parent {
self.append_before_sibling(element, child);
} else {
self.append(prev_element, child);
}
}
fn append_doctype_to_document(
&mut self,
name: StrTendril,
public_id: StrTendril,
system_id: StrTendril,
) {
append(
&self.document,
Node::new(NodeData::Doctype {
name,
public_id,
system_id,
}),
);
}
fn add_attrs_if_missing(&mut self, target: &Handle, attrs: Vec) {
let mut existing = if let NodeData::Element { ref attrs, .. } = target.data {
attrs.borrow_mut()
} else {
panic!("not an element")
};
let existing_names = existing
.iter()
.map(|e| e.name.clone())
.collect::>();
existing.extend(
attrs
.into_iter()
.filter(|attr| !existing_names.contains(&attr.name)),
);
}
fn remove_from_parent(&mut self, target: &Handle) {
remove_from_parent(target);
}
fn reparent_children(&mut self, node: &Handle, new_parent: &Handle) {
let mut children = node.children.borrow_mut();
let mut new_children = new_parent.children.borrow_mut();
for child in children.iter() {
let previous_parent = child.parent.replace(Some(Rc::downgrade(new_parent)));
assert!(Rc::ptr_eq(
node,
&previous_parent.unwrap().upgrade().expect("dangling weak")
))
}
new_children.extend(mem::take(&mut *children));
}
fn is_mathml_annotation_xml_integration_point(&self, target: &Handle) -> bool {
if let NodeData::Element {
mathml_annotation_xml_integration_point,
..
} = target.data
{
mathml_annotation_xml_integration_point
} else {
panic!("not an element!")
}
}
}
impl Default for RcDom {
fn default() -> RcDom {
RcDom {
document: Node::new(NodeData::Document),
errors: vec![],
quirks_mode: tree_builder::NoQuirks,
}
}
}
enum SerializeOp {
Open(Handle),
Close(QualName),
}
pub struct SerializableHandle(Handle);
impl From for SerializableHandle {
fn from(h: Handle) -> SerializableHandle {
SerializableHandle(h)
}
}
impl Serialize for SerializableHandle {
fn serialize(&self, serializer: &mut S, traversal_scope: TraversalScope) -> io::Result<()>
where
S: Serializer,
{
let mut ops = VecDeque::new();
match traversal_scope {
IncludeNode => ops.push_back(SerializeOp::Open(self.0.clone())),
ChildrenOnly(_) => ops.extend(
self.0
.children
.borrow()
.iter()
.map(|h| SerializeOp::Open(h.clone())),
),
}
while let Some(op) = ops.pop_front() {
match op {
SerializeOp::Open(handle) => match handle.data {
NodeData::Element {
ref name,
ref attrs,
..
} => {
serializer.start_elem(
name.clone(),
attrs.borrow().iter().map(|at| (&at.name, &at.value[..])),
)?;
ops.reserve(1 + handle.children.borrow().len());
ops.push_front(SerializeOp::Close(name.clone()));
for child in handle.children.borrow().iter().rev() {
ops.push_front(SerializeOp::Open(child.clone()));
}
},
NodeData::Doctype { ref name, .. } => serializer.write_doctype(name)?,
NodeData::Text { ref contents } => serializer.write_text(&contents.borrow())?,
NodeData::Comment { ref contents } => serializer.write_comment(contents)?,
NodeData::ProcessingInstruction {
ref target,
ref contents,
} => serializer.write_processing_instruction(target, contents)?,
NodeData::Document => panic!("Can't serialize Document node itself"),
},
SerializeOp::Close(name) => {
serializer.end_elem(name)?;
},
}
}
Ok(())
}
}
markup5ever_rcdom-0.3.0/xml5lib-tests/LICENSE 0000644 0000000 0000000 00000002116 10461020230 0016777 0 ustar 0000000 0000000 Copyright (c) 2006-2013 James Graham, Geoffrey Sneddon and
other contributors
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
markup5ever_rcdom-0.3.0/xml5lib-tests/tokenizer/README.md 0000644 0000000 0000000 00000007246 10461020230 0021274 0 ustar 0000000 0000000 Tokenizer tests
===============
The test format is [JSON](http://www.json.org/). This has the advantage
that the syntax allows backward-compatible extensions to the tests and
the disadvantage that it is relatively verbose.
Basic Structure
---------------
{"tests": [
{"description": "Test description",
"input": "input_string",
"output": [expected_output_tokens],
"initialStates": [initial_states],
"lastStartTag": last_start_tag,
"ignoreErrorOrder": ignore_error_order
}
]}
Multiple tests per file are allowed simply by adding more objects to the
"tests" list.
`description`, `input` and `output` are always present. The other values
are optional.
### Test set-up
`test.input` is a string containing the characters to pass to the
tokenizer. Specifically, it represents the characters of the **input
stream**, and so implementations are expected to perform the processing
described in the spec's **Preprocessing the input stream** section
before feeding the result to the tokenizer.
If `test.doubleEscaped` is present and `true`, then `test.input` is not
quite as described above. Instead, it must first be subjected to another
round of unescaping (i.e., in addition to any unescaping involved in the
JSON import), and the result of *that* represents the characters of the
input stream. Currently, the only unescaping required by this option is
to convert each sequence of the form \\uHHHH (where H is a hex digit)
into the corresponding Unicode code point. (Note that this option also
affects the interpretation of `test.output`.)
`test.initialStates` is a list of strings, each being the name of a
tokenizer state. The test should be run once for each string, using it
to set the tokenizer's initial state for that run. If
`test.initialStates` is omitted, it defaults to `["data state"]`.
`test.lastStartTag` is a lowercase string that should be used as "the
tag name of the last start tag to have been emitted from this
tokenizer", referenced in the spec's definition of **appropriate end tag
token**. If it is omitted, it is treated as if "no start tag has been
emitted from this tokenizer".
### Test results
`test.output` is a list of tokens, ordered with the first produced by
the tokenizer the first (leftmost) in the list. The list must mach the
**complete** list of tokens that the tokenizer should produce. Valid
tokens are:
["DOCTYPE", name, public_id, system_id, correctness]
["StartTag", name, {attributes}*, true*]
["StartTag", name, {attributes}]
["EndTag", name]
["Comment", data]
["Character", data]
"ParseError"
`public_id` and `system_id` are either strings or `null`. `correctness`
is either `true` or `false`; `true` corresponds to the force-quirks flag
being false, and vice-versa.
When the self-closing flag is set, the `StartTag` array has `true` as
its fourth entry. When the flag is not set, the array has only three
entries for backwards compatibility.
All adjacent character tokens are coalesced into a single
`["Character", data]` token.
If `test.doubleEscaped` is present and `true`, then every string within
`test.output` must be further unescaped (as described above) before
comparing with the tokenizer's output.
`test.ignoreErrorOrder` is a boolean value indicating that the order of
`ParseError` tokens relative to other tokens in the output stream is
unimportant, and implementations should ignore such differences between
their output and `expected_output_tokens`. (This is used for errors
emitted by the input stream preprocessing stage, since it is useful to
test that code but it is undefined when the errors occur). If it is
omitted, it defaults to `false`.
markup5ever_rcdom-0.3.0/xml5lib-tests/tree-construction/README.md 0000644 0000000 0000000 00000011005 10461020230 0022735 0 ustar 0000000 0000000 Tree Construction Tests
=======================
Each file containing tree construction tests consists of any number of
tests separated by two newlines (LF) and a single newline before the end
of the file. For instance:
[TEST]LF
LF
[TEST]LF
LF
[TEST]LF
Where [TEST] is the following format:
Each test must begin with a string "\#data" followed by a newline (LF).
All subsequent lines until a line that says "\#errors" are the test data
and must be passed to the system being tested unchanged, except with the
final newline (on the last line) removed.
Then there must be a line that says "\#errors". It must be followed by
one line per parse error that a conformant checker would return. It
doesn't matter what those lines are, although they can't be
"\#document-fragment", "\#document", "\#script-off", "\#script-on", or
empty, the only thing that matters is that there be the right number
of parse errors.
Then there \*may\* be a line that says "\#document-fragment", which must
be followed by a newline (LF), followed by a string of characters that
indicates the context element, followed by a newline (LF). If the string
of characters starts with "svg ", the context element is in the SVG
namespace and the substring after "svg " is the local name. If the
string of characters starts with "math ", the context element is in the
MathML namespace and the substring after "math " is the local name.
Otherwise, the context element is in the HTML namespace and the string
is the local name. If this line is present the "\#data" must be parsed
using the HTML fragment parsing algorithm with the context element as
context.
Then there \*may\* be a line that says "\#script-off" or
"\#script-in". If a line that says "\#script-off" is present, the
parser must set the scripting flag to disabled. If a line that says
"\#script-on" is present, it must set it to enabled. Otherwise, the
test should be run in both modes.
Then there must be a line that says "\#document", which must be followed
by a dump of the tree of the parsed DOM. Each node must be represented
by a single line. Each line must start with "| ", followed by two spaces
per parent node that the node has before the root document node.
- Element nodes must be represented by a "`<`" then the *tag name
string* "`>`", and all the attributes must be given, sorted
lexicographically by UTF-16 code unit according to their *attribute
name string*, on subsequent lines, as if they were children of the
element node.
- Attribute nodes must have the *attribute name string*, then an "="
sign, then the attribute value in double quotes (").
- Text nodes must be the string, in double quotes. Newlines aren't
escaped.
- Comments must be "`<`" then "`!-- `" then the data then "` -->`".
- DOCTYPEs must be "``".
- Processing instructions must be "``". (The HTML parser cannot emit
processing instructions, but scripts can, and the WebVTT to DOM
rules can emit them.)
- Template contents are represented by the string "content" with the
children below it.
The *tag name string* is the local name prefixed by a namespace
designator. For the HTML namespace, the namespace designator is the
empty string, i.e. there's no prefix. For the SVG namespace, the
namespace designator is "svg ". For the MathML namespace, the namespace
designator is "math ".
The *attribute name string* is the local name prefixed by a namespace
designator. For no namespace, the namespace designator is the empty
string, i.e. there's no prefix. For the XLink namespace, the namespace
designator is "xlink ". For the XML namespace, the namespace designator
is "xml ". For the XMLNS namespace, the namespace designator is "xmlns
". Note the difference between "xlink:href" which is an attribute in no
namespace with the local name "xlink:href" and "xlink href" which is an
attribute in the xlink namespace with the local name "href".
If there is also a "\#document-fragment" the bit following "\#document"
must be a representation of the HTML fragment serialization for the
context element given by "\#document-fragment".
For example:
#data
One
Two
#errors
3: Missing document type declaration
#document
|
|
|
|
| "One"
|
| "Two"