Page MenuHomePhorge
Files F111962

No OneTemporary
Actions

Size
15 KB
Referenced Files
None
Subscribers
None

View Options

diff --git a/.gitignore b/.gitignore
index 850381f..e490e54 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,27 +1,30 @@
# SPDX-FileCopyrightText: 2017-2019 myhtmlex authors <https://github.com/Overbryd/myhtmlex>
# SPDX-License-Identifier: LGPL-2.1-only
# The directory Mix will write compiled artifacts to.
/_build/
# If you run "mix test --cover", coverage assets end up here.
/cover/
# The directory Mix downloads your dependencies sources to.
/deps/
# Where 3rd-party dependencies like ExDoc output generated docs.
/doc/
# Ignore .fetch files in case you like to edit your project deps locally.
/.fetch
# If the VM crashes, it generates a dump, let's ignore it too.
erl_crash.dump
# Also ignore archive artifacts (built via "mix archive.build").
*.ez
priv/*
!priv/.gitignore
bench/snapshots
package-test
+
+# Library with CI, mix.lock is just a maintenance burden
+/mix.lock
diff --git a/.gitmodules b/.gitmodules
index 0ac1fa7..0568e2d 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,8 +1,8 @@
# SPDX-FileCopyrightText: 2017-2019 myhtmlex authors <https://github.com/Overbryd/myhtmlex>
# SPDX-FileCopyrightText: 2019-2023 Pleroma Authors <https://pleroma.social>
# SPDX-License-Identifier: LGPL-2.1-only
[submodule "c_src/lexbor"]
path = c_src/lexbor
url = https://github.com/lexbor/lexbor.git
- branch = v2.2.0
+ branch = v2.3.0
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 17fade3..92218d2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,67 +1,78 @@
<!--
SPDX-FileCopyrightText: 2019-2022 Pleroma Authors <https://pleroma.social>
SPDX-License-Identifier: LGPL-2.1-only
-->
# Changelog
All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
+## [2.3.0] - 2023-08-18
+## Added
+- Ability to use system lexbor
+
+## Removed
+- Remove compatibility for Erlang <22
+
+## Changed
+- Allow custom CFLAGS
+- Updated vendored lexbor to 2.3.0
+
## [2.2.0] - 2023-04-08
### Changed
- Updated vendored lexbor to 2.2.0
## [2.0.4] - 2020-09-01
#### Fixed
- Regression of the gcc 10 fix in the hex package, due to an outdated submodule on the publishing machine
## [2.0.3] - 2020-08-30
### Changed
- Improved error message on make errors
## [2.0.2] - 2020-08-26
### Fixed
- lexbor compilation errors with gcc 10
- Inability to use the library with distillery releases due to priv dir being in the source code
## [2.0.1] - 2020-08-04
### Fixed
- Build failures using the hex package due to CMake cache files accidentally included there
### Added
- Changelog is now available at hexdocs
## [2.0.0] - 2020-08-01
### Changed
- **Breaking:** CMake is now required at compile-time due to it being lexbor's build system
- **Breaking:** namespaces are no longer automatically appended. i.e `<svg> </svg>` will be `{"svg", [], []}` instead of `{"svg:svg", [], []}`
- **Breaking:** when using `:nil_self_closing` flag, only valid [void elements](https://html.spec.whatwg.org/#void-elements) will have `nil` in children
- Now deprecated myhtml was switched to [lexbor](https://github.com/lexbor/lexbor)
- The worker process now communicates with the node via stdio, instead of TCP, which was known to cause issues
on BSD systems
### Added
- `FastHtml.Pool` for fast_html workers. There is a default pool of `System.schedulers_online/0` workers, but a custom pool can be started if desired, or it can be disabled altogether. See `FastHtml.Pool` module documentation for more info
## [1.0.3] - 2020-02-10
### Fixed
- C-Node not respawning after being killed.
## [1.0.2] - 2020-02-10
### Fixed
- Incorrect behavior when parsing empty attribute values. Instead of an empty string the attribute name was returned.
## [1.0.1] - 2019-12-11
### Added
- `:fast_html.decode_fragment`
### Fixed
- Errors from C-Node not being reported, timing out instead
## [1.0.0] - 2019-12-02
### Changed
- **BREAKING:** `:fast_html.decode` now returns an array of nodes at the top level, instead of a single node. This was done because it's possible to have more than one root node, for example in (`<!-- a comment --> <html> </html>` both the comment and the `html` tag are root nodes).
### Fixed
- Worker going into infinite loop when decoding a document with more than one root node.
diff --git a/Makefile b/Makefile
index 1977293..7060795 100644
--- a/Makefile
+++ b/Makefile
@@ -1,54 +1,54 @@
# SPDX-FileCopyrightText: 2017-2019 myhtmlex authors <https://github.com/Overbryd/myhtmlex>
# SPDX-FileCopyrightText: 2019-2022 Pleroma Authors <https://pleroma.social>
# SPDX-License-Identifier: LGPL-2.1-only
MIX = mix
CMAKE = cmake
CFLAGS ?= -g -O2 -pedantic -Wcomment -Wextra -Wno-old-style-declaration -Wall
# set erlang include path
ERLANG_PATH = $(shell erl -eval 'io:format("~s", [lists:concat([code:root_dir(), "/erts-", erlang:system_info(version)])])' -s init stop -noshell)
CNODE_CFLAGS += -I$(ERLANG_PATH)/include
# expecting lexbor as a submodule in c_src/
# that way we can pin a version and package the whole thing in hex
LXB_PATH = c_src/lexbor
LXB_AR = $(LXB_PATH)/liblexbor_static.a
ifeq ($(WITH_SYSTEM_LEXBOR),1)
LXB_CFLAGS =
LXB_LDFLAGS = -llexbor
LXB_DEPS =
else
LXB_CFLAGS = -I$(LXB_PATH)/source
LXB_LDFLAGS = $(LXB_AR)
LXB_DEPS = $(LXB_AR)
endif
# C-Node
ERL_INTERFACE = $(wildcard $(ERLANG_PATH)/../lib/erl_interface-*)
CNODE_CFLAGS += -I$(ERL_INTERFACE)/include
CNODE_LDFLAGS += -L$(ERL_INTERFACE)/lib -lei -lpthread
.PHONY: all
all: priv/fasthtml_worker
$(LXB_AR): $(LXB_PATH)
# Sadly, build components separately seems to sporadically fail
cd $(LXB_PATH); \
CFLAGS='$(CFLAGS)' \
cmake -DLEXBOR_BUILD_SEPARATELY=OFF -DLEXBOR_BUILD_SHARED=OFF
$(MAKE) -C $(LXB_PATH)
priv/fasthtml_worker: c_src/fasthtml_worker.c $(LXB_DEPS)
mkdir -p priv
- $(CC) -std=c99 $(CFLAGS) $(CNODE_CFLAGS) $(LXB_CFLAGS) -o $@ $< $(LDFLAGS) $(CNODE_LDFLAGS) $(LXB_LDFLAGS)
+ $(CC) -std=c99 $(CFLAGS) $(CNODE_CFLAGS) $(LXB_CFLAGS) -o $@ $< $(LDFLAGS) -lm $(CNODE_LDFLAGS) $(LXB_LDFLAGS)
clean: clean-myhtml
$(RM) -r priv/myhtmlex*
$(RM) priv/fasthtml_worker
$(RM) myhtmlex-*.tar
$(RM) -r package-test
clean-myhtml:
$(MAKE) -C $(LXB_PATH) clean
diff --git a/c_src/lexbor b/c_src/lexbor
index 74f28d6..26a8819 160000
--- a/c_src/lexbor
+++ b/c_src/lexbor
@@ -1 +1 @@
-Subproject commit 74f28d6df42759dbb708bed1cae8ec59205a473b
+Subproject commit 26a8819b60801301df92d771f12a01dbe8705a7a
diff --git a/mix.exs b/mix.exs
index 4f042a7..aa4c4d8 100644
--- a/mix.exs
+++ b/mix.exs
@@ -1,98 +1,98 @@
# SPDX-FileCopyrightText: 2017-2019 myhtmlex authors <https://github.com/Overbryd/myhtmlex>
# SPDX-FileCopyrightText: 2019-2022 Pleroma Authors <https://pleroma.social>
# SPDX-License-Identifier: LGPL-2.1-only
defmodule FastHtml.Mixfile do
use Mix.Project
def project do
[
app: :fast_html,
- version: "2.2.0",
+ version: "2.3.0",
elixir: "~> 1.11",
deps: deps(),
package: package(),
compilers: [:elixir_make] ++ Mix.compilers(),
make_env: make_env(),
make_error_message: make_error_message(),
build_embedded: Mix.env() == :prod,
start_permanent: Mix.env() == :prod,
name: "FastHtml",
description: """
A module to decode HTML into a tree,
porting all properties of the underlying
library lexbor, being fast and correct
in regards to the html spec.
""",
docs: docs()
]
end
def package do
[
maintainers: ["Ariadne Conill", "rinpatch"],
licenses: ["LGPL-2.1-only"],
links: %{
"GitLab" => "https://git.pleroma.social/pleroma/elixir-libraries/fast_html/",
"Issues" => "https://git.pleroma.social/pleroma/elixir-libraries/fast_html/issues",
"lexbor" => "https://github.com/lexbor/lexbor"
},
files: hex_files()
]
end
def application do
[
extra_applications: [:logger],
mod: {FastHtml.Application, []}
]
end
defp deps do
[
# documentation helpers
{:ex_doc, "~> 0.19", only: :dev},
# benchmarking helpers
{:benchee, "~> 1.0", only: :bench, optional: true},
{:dialyxir, "~> 1.0", only: [:dev, :test], runtime: false},
{:myhtmlex, "~> 0.2.0", only: :bench, runtime: false, optional: true},
{:mochiweb, "~> 2.18", only: :bench, optional: true},
{:html5ever,
git: "https://github.com/rusterlium/html5ever_elixir.git", only: :bench, optional: true},
{:nimble_pool, "~> 0.2.0"},
{:elixir_make, "~> 0.4", runtime: false}
]
end
defp docs do
[
main: "readme",
extras: ["README.md", "CHANGELOG.md"]
]
end
defp hex_files do
# This is run every time mix is executed, so it will fail in the hex package,
# therefore check if git is even available
if File.exists?(".git") and System.find_executable("git") do
{files, 0} = System.cmd("git", ["ls-files", "--recurse-submodules"])
files
|> String.split("\n")
# Last element is "", which makes hex include all files in the folder to the project
|> List.delete_at(-1)
|> Enum.reject(fn path ->
Path.dirname(path) == "bench_fixtures" or
(Path.dirname(path) != "priv" and String.starts_with?(Path.basename(path), "."))
end)
else
[]
end
end
defp make_env, do: %{}
defp make_error_message,
do:
"Please check you have: a C compiler, GNU Make, CMake and Erlang development headers installed before reporting an issue."
end
diff --git a/mix.lock b/mix.lock
deleted file mode 100644
index 99bee42..0000000
--- a/mix.lock
+++ /dev/null
@@ -1,26 +0,0 @@
-%{
- "benchee": {:hex, :benchee, "1.1.0", "f3a43817209a92a1fade36ef36b86e1052627fd8934a8b937ac9ab3a76c43062", [:mix], [{:deep_merge, "~> 1.0", [hex: :deep_merge, repo: "hexpm", optional: false]}, {:statistex, "~> 1.0", [hex: :statistex, repo: "hexpm", optional: false]}], "hexpm", "7da57d545003165a012b587077f6ba90b89210fd88074ce3c60ce239eb5e6d93"},
- "castore": {:hex, :castore, "0.1.18", "deb5b9ab02400561b6f5708f3e7660fc35ca2d51bfc6a940d2f513f89c2975fc", [:mix], [], "hexpm", "61bbaf6452b782ef80b33cdb45701afbcf0a918a45ebe7e73f1130d661e66a06"},
- "deep_merge": {:hex, :deep_merge, "1.0.0", "b4aa1a0d1acac393bdf38b2291af38cb1d4a52806cf7a4906f718e1feb5ee961", [:mix], [], "hexpm", "ce708e5f094b9cd4e8f2be4f00d2f4250c4095be93f8cd6d018c753894885430"},
- "dialyxir": {:hex, :dialyxir, "1.2.0", "58344b3e87c2e7095304c81a9ae65cb68b613e28340690dfe1a5597fd08dec37", [:mix], [{:erlex, ">= 0.2.6", [hex: :erlex, repo: "hexpm", optional: false]}], "hexpm", "61072136427a851674cab81762be4dbeae7679f85b1272b6d25c3a839aff8463"},
- "earmark": {:hex, :earmark, "1.4.2", "3aa0bd23bc4c61cf2f1e5d752d1bb470560a6f8539974f767a38923bb20e1d7f", [:mix], [], "hexpm", "5e8806285d8a3a8999bd38e4a73c58d28534c856bc38c44818e5ba85bbda16fb"},
- "earmark_parser": {:hex, :earmark_parser, "1.4.26", "f4291134583f373c7d8755566122908eb9662df4c4b63caa66a0eabe06569b0a", [:mix], [], "hexpm", "48d460899f8a0c52c5470676611c01f64f3337bad0b26ddab43648428d94aabc"},
- "elixir_make": {:hex, :elixir_make, "0.6.3", "bc07d53221216838d79e03a8019d0839786703129599e9619f4ab74c8c096eac", [:mix], [], "hexpm", "f5cbd651c5678bcaabdbb7857658ee106b12509cd976c2c2fca99688e1daf716"},
- "erlex": {:hex, :erlex, "0.2.6", "c7987d15e899c7a2f34f5420d2a2ea0d659682c06ac607572df55a43753aa12e", [:mix], [], "hexpm", "2ed2e25711feb44d52b17d2780eabf998452f6efda104877a3881c2f8c0c0c75"},
- "ex_doc": {:hex, :ex_doc, "0.28.4", "001a0ea6beac2f810f1abc3dbf4b123e9593eaa5f00dd13ded024eae7c523298", [:mix], [{:earmark_parser, "~> 1.4.19", [hex: :earmark_parser, repo: "hexpm", optional: false]}, {:makeup_elixir, "~> 0.14", [hex: :makeup_elixir, repo: "hexpm", optional: false]}, {:makeup_erlang, "~> 0.1", [hex: :makeup_erlang, repo: "hexpm", optional: false]}], "hexpm", "bf85d003dd34911d89c8ddb8bda1a958af3471a274a4c2150a9c01c78ac3f8ed"},
- "html5ever": {:git, "https://github.com/rusterlium/html5ever_elixir.git", "6bc235cbfc284e5d9c7d4f680e9eba6f75e2f0bf", []},
- "jason": {:hex, :jason, "1.3.0", "fa6b82a934feb176263ad2df0dbd91bf633d4a46ebfdffea0c8ae82953714946", [:mix], [{:decimal, "~> 1.0 or ~> 2.0", [hex: :decimal, repo: "hexpm", optional: true]}], "hexpm", "53fc1f51255390e0ec7e50f9cb41e751c260d065dcba2bf0d08dc51a4002c2ac"},
- "makeup": {:hex, :makeup, "1.1.0", "6b67c8bc2882a6b6a445859952a602afc1a41c2e08379ca057c0f525366fc3ca", [:mix], [{:nimble_parsec, "~> 1.2.2 or ~> 1.3", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm", "0a45ed501f4a8897f580eabf99a2e5234ea3e75a4373c8a52824f6e873be57a6"},
- "makeup_elixir": {:hex, :makeup_elixir, "0.16.0", "f8c570a0d33f8039513fbccaf7108c5d750f47d8defd44088371191b76492b0b", [:mix], [{:makeup, "~> 1.0", [hex: :makeup, repo: "hexpm", optional: false]}, {:nimble_parsec, "~> 1.2.3", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm", "28b2cbdc13960a46ae9a8858c4bebdec3c9a6d7b4b9e7f4ed1502f8159f338e7"},
- "makeup_erlang": {:hex, :makeup_erlang, "0.1.1", "3fcb7f09eb9d98dc4d208f49cc955a34218fc41ff6b84df7c75b3e6e533cc65f", [:mix], [{:makeup, "~> 1.0", [hex: :makeup, repo: "hexpm", optional: false]}], "hexpm", "174d0809e98a4ef0b3309256cbf97101c6ec01c4ab0b23e926a9e17df2077cbb"},
- "mochiweb": {:hex, :mochiweb, "2.22.0", "f104d6747c01a330c38613561977e565b788b9170055c5241ac9dd6e4617cba5", [:rebar3], [], "hexpm", "cbbd1fd315d283c576d1c8a13e0738f6dafb63dc840611249608697502a07655"},
- "myhtml": {:git, "https://github.com/lexborisov/myhtml.git", "fe2cf577570666d058a2b7167c26d3384a758e19", [branch: "master"]},
- "myhtmlex": {:hex, :myhtmlex, "0.2.1", "d6f3eb1826f7cdaa0225a996569da0930d1a334405510845c905ae59295ab226", [:make, :mix], [{:nodex, "~> 0.1.1", [hex: :nodex, repo: "hexpm", optional: false]}], "hexpm", "1c22e79731cc492365279d111fcaf7f4f17ca845d2b9660d2285b91c56cbd1c2"},
- "nimble_parsec": {:hex, :nimble_parsec, "1.2.3", "244836e6e3f1200c7f30cb56733fd808744eca61fd182f731eac4af635cc6d0b", [:mix], [], "hexpm", "c8d789e39b9131acf7b99291e93dae60ab48ef14a7ee9d58c6964f59efb570b0"},
- "nimble_pool": {:hex, :nimble_pool, "0.2.6", "91f2f4c357da4c4a0a548286c84a3a28004f68f05609b4534526871a22053cde", [:mix], [], "hexpm", "1c715055095d3f2705c4e236c18b618420a35490da94149ff8b580a2144f653f"},
- "nodex": {:hex, :nodex, "0.1.2", "7e9c81dd9a0ad7d8cdef7fa1512a9009ecca22cbc82827f99978432a3bf07a61", [:mix], [], "hexpm", "ceac2d37f2463f60bd1f0beeeebb621178cae12d6e626b587057ec7b14e6f236"},
- "rustler": {:hex, :rustler, "0.24.0", "b8362a2fee1c9d2c7373b0bfdc98f75bbc02864efcec50df173fe6c4f72d4cc4", [:mix], [{:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}, {:toml, "~> 0.6", [hex: :toml, repo: "hexpm", optional: false]}], "hexpm", "2773167fca68a6525822ad977b41368ea3c2af876c42ebaa7c9d6bb69b67f1ce"},
- "rustler_precompiled": {:hex, :rustler_precompiled, "0.5.1", "93df423bd7b14b67dcacf994443d132d300623f80756974cac4febeab40af74a", [:mix], [{:castore, "~> 0.1", [hex: :castore, repo: "hexpm", optional: false]}, {:rustler, "~> 0.23", [hex: :rustler, repo: "hexpm", optional: true]}], "hexpm", "3f8cbc8e92eef4e1a71bf441b568b868b16a3730f63f5b803c68073017e30b13"},
- "statistex": {:hex, :statistex, "1.0.0", "f3dc93f3c0c6c92e5f291704cf62b99b553253d7969e9a5fa713e5481cd858a5", [:mix], [], "hexpm", "ff9d8bee7035028ab4742ff52fc80a2aa35cece833cf5319009b52f1b5a86c27"},
- "toml": {:hex, :toml, "0.6.2", "38f445df384a17e5d382befe30e3489112a48d3ba4c459e543f748c2f25dd4d1", [:mix], [], "hexpm", "d013e45126d74c0c26a38d31f5e8e9b83ea19fc752470feb9a86071ca5a672fa"},
-}
diff --git a/mix.lock.license b/mix.lock.license
deleted file mode 100644
index e7038e9..0000000
--- a/mix.lock.license
+++ /dev/null
@@ -1,4 +0,0 @@
-SPDX-FileCopyrightText: 2017-2019 myhtmlex authors <https://github.com/Overbryd/myhtmlex>
-SPDX-FileCopyrightText: 2019-2022 Pleroma Authors <https://pleroma.social>
-
-SPDX-License-Identifier: LGPL-2.1-only

File Metadata

Mime Type
text/x-diff
Expires
Fri, Nov 22, 1:12 PM (10 h, 9 s)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
38686
Default Alt Text
(15 KB)

Event Timeline