From e08464d1a1bd7315fc366fa7a3c094560fac5b7c Mon Sep 17 00:00:00 2001 From: MAHDTech Date: Thu, 16 Oct 2025 21:16:04 +1100 Subject: [PATCH 1/9] fix: git hooks --- devenv.lock | 38 +++++++++++--------------------------- devenv.nix | 20 ++------------------ devenv.yaml | 5 ++--- 3 files changed, 15 insertions(+), 48 deletions(-) diff --git a/devenv.lock b/devenv.lock index fc0124e..b75cdc5 100644 --- a/devenv.lock +++ b/devenv.lock @@ -3,10 +3,10 @@ "devenv": { "locked": { "dir": "src/modules", - "lastModified": 1755039979, + "lastModified": 1760560333, "owner": "cachix", "repo": "devenv", - "rev": "63db0a32cd767c2a9089fbaf24b0bb91c64c0652", + "rev": "0a4043938f540027e562c5a0feebbe6be872c3ea", "type": "github" }, "original": { @@ -57,10 +57,10 @@ ] }, "locked": { - "lastModified": 1754416808, + "lastModified": 1760392170, "owner": "cachix", "repo": "git-hooks.nix", - "rev": "9c52372878df6911f9afc1e2a1391f55e4dfc864", + "rev": "46d55f0aeb1d567a78223e69729734f3dca25a85", "type": "github" }, "original": { @@ -95,10 +95,10 @@ "nixpkgs": "nixpkgs" }, "locked": { - "lastModified": 1754078208, + "lastModified": 1759991118, "owner": "nix-community", "repo": "gomod2nix", - "rev": "7f963246a71626c7fc70b431a315c4388a0c95cf", + "rev": "7f8d7438f5870eb167abaf2c39eea3d2302019d1", "type": "github" }, "original": { @@ -142,10 +142,10 @@ }, "nixpkgs": { "locked": { - "lastModified": 1755042551, + "lastModified": 1760608560, "owner": "NixOS", "repo": "nixpkgs", - "rev": "e4b54494cba4c82005d5fe3c0329a8f66fbfcff7", + "rev": "9c15c2a846a00eb6a98ac974b335ca7be2404311", "type": "github" }, "original": { @@ -155,32 +155,17 @@ "type": "github" } }, - "nixpkgs-unstable": { - "locked": { - "lastModified": 1754990257, - "owner": "nixos", - "repo": "nixpkgs", - "rev": "372d9eeeafa5b15913201e2b92e8e539ac7c64d1", - "type": "github" - }, - "original": { - "owner": "nixos", - "ref": "nixpkgs-unstable", - "repo": "nixpkgs", - "type": "github" - } - }, "nixpkgs_2": { "locked": { - "lastModified": 1754299112, + "lastModified": 1760346906, "owner": "cachix", "repo": "devenv-nixpkgs", - "rev": "16c21c9f5c6fb978466e91182a248dd8ca1112ac", + "rev": "0b429772c9c9b6f96cca629371a3150eb3cf862d", "type": "github" }, "original": { "owner": "cachix", - "ref": "rolling", + "ref": "bump-rolling", "repo": "devenv-nixpkgs", "type": "github" } @@ -193,7 +178,6 @@ "mk-shell-bin": "mk-shell-bin", "nix2container": "nix2container", "nixpkgs": "nixpkgs_2", - "nixpkgs-unstable": "nixpkgs-unstable", "pre-commit-hooks": [ "git-hooks" ] diff --git a/devenv.nix b/devenv.nix index 3276d1f..0c9ec68 100644 --- a/devenv.nix +++ b/devenv.nix @@ -2,7 +2,6 @@ pkgs, config, lib, - inputs, ... }: let @@ -20,16 +19,6 @@ let inherit pkgs; }; - # All available unstable packages. - pkgsUnstable = import inputs.nixpkgs-unstable { - config.allowUnfree = true; - }; - - # Installed unstable packages. - unstablePackages = with pkgsUnstable; [ - #golangci-lint - ]; - # Common stable packages. commonPackages = with pkgs; [ figlet @@ -74,7 +63,6 @@ in packages = commonPackages - ++ unstablePackages ++ lib.optionals (!config.container.isBuilding || config.name == "devenv") devPackages; enterShell = '' @@ -104,15 +92,11 @@ in }; git-hooks = { - excludes = [ - ".cache" - ".devenv" - ".direnv" - "src/vendor" - ]; + excludes = [ ]; hooks = { beautysh.enable = false; actionlint.enable = true; + action-validator.enable = true; check-merge-conflicts.enable = true; check-shebang-scripts-are-executable.enable = true; check-symlinks.enable = true; diff --git a/devenv.yaml b/devenv.yaml index 35af34d..0bc77b4 100644 --- a/devenv.yaml +++ b/devenv.yaml @@ -2,9 +2,8 @@ # yaml-language-server: $schema=https://devenv.sh/devenv.schema.json inputs: nixpkgs: - url: github:cachix/devenv-nixpkgs/rolling - nixpkgs-unstable: - url: github:nixos/nixpkgs/nixpkgs-unstable + #url: github:cachix/devenv-nixpkgs/rolling + url: github:cachix/devenv-nixpkgs/bump-rolling nix2container: url: github:nlewo/nix2container inputs: From a643400270a7801d2e70866234d90bccf1a3363c Mon Sep 17 00:00:00 2001 From: MAHDTech Date: Fri, 17 Oct 2025 09:15:03 +1100 Subject: [PATCH 2/9] chore: cleanup --- .github/workflows/devenv.yaml | 1 - devenv.nix | 4 +- scripts/yolo.sh | 2 +- src/go.mod | 11 +- src/go.sum | 22 +- src/gomod2nix.toml | 21 +- .../mimetype/CODE_OF_CONDUCT.md | 76 - .../gabriel-vasile/mimetype/CONTRIBUTING.md | 12 - .../gabriel-vasile/mimetype/README.md | 35 +- .../mimetype/internal/charset/charset.go | 230 +- .../mimetype/internal/csv/parser.go | 125 + .../mimetype/internal/json/parser.go | 30 +- .../mimetype/internal/magic/document.go | 47 +- .../mimetype/internal/magic/magic.go | 81 +- .../mimetype/internal/magic/ms_office.go | 31 +- .../mimetype/internal/magic/netpbm.go | 111 + .../mimetype/internal/magic/text.go | 146 +- .../mimetype/internal/magic/text_csv.go | 80 +- .../mimetype/internal/magic/zip.go | 186 +- .../mimetype/internal/markup/markup.go | 103 + .../mimetype/internal/scan/bytes.go | 213 ++ .../gabriel-vasile/mimetype/mime.go | 26 +- .../mimetype/supported_mimes.md | 22 +- .../gabriel-vasile/mimetype/tree.go | 62 +- .../go-playground/validator/v10/README.md | 7 +- .../go-playground/validator/v10/baked_in.go | 39 + .../go-playground/validator/v10/doc.go | 13 + .../go-playground/validator/v10/regexes.go | 2 + .../validator/v10/validator_instance.go | 60 +- src/vendor/golang.org/x/net/LICENSE | 27 - src/vendor/golang.org/x/net/PATENTS | 22 - src/vendor/golang.org/x/net/html/atom/atom.go | 78 - .../golang.org/x/net/html/atom/table.go | 785 ------ src/vendor/golang.org/x/net/html/const.go | 111 - src/vendor/golang.org/x/net/html/doc.go | 122 - src/vendor/golang.org/x/net/html/doctype.go | 156 -- src/vendor/golang.org/x/net/html/entity.go | 2253 --------------- src/vendor/golang.org/x/net/html/escape.go | 339 --- src/vendor/golang.org/x/net/html/foreign.go | 221 -- src/vendor/golang.org/x/net/html/iter.go | 56 - src/vendor/golang.org/x/net/html/node.go | 229 -- src/vendor/golang.org/x/net/html/parse.go | 2464 ----------------- src/vendor/golang.org/x/net/html/render.go | 293 -- src/vendor/golang.org/x/net/html/token.go | 1286 --------- src/vendor/modules.txt | 27 +- 45 files changed, 1276 insertions(+), 8991 deletions(-) delete mode 100644 src/vendor/github.com/gabriel-vasile/mimetype/CODE_OF_CONDUCT.md delete mode 100644 src/vendor/github.com/gabriel-vasile/mimetype/CONTRIBUTING.md create mode 100644 src/vendor/github.com/gabriel-vasile/mimetype/internal/csv/parser.go create mode 100644 src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/netpbm.go create mode 100644 src/vendor/github.com/gabriel-vasile/mimetype/internal/markup/markup.go create mode 100644 src/vendor/github.com/gabriel-vasile/mimetype/internal/scan/bytes.go delete mode 100644 src/vendor/golang.org/x/net/LICENSE delete mode 100644 src/vendor/golang.org/x/net/PATENTS delete mode 100644 src/vendor/golang.org/x/net/html/atom/atom.go delete mode 100644 src/vendor/golang.org/x/net/html/atom/table.go delete mode 100644 src/vendor/golang.org/x/net/html/const.go delete mode 100644 src/vendor/golang.org/x/net/html/doc.go delete mode 100644 src/vendor/golang.org/x/net/html/doctype.go delete mode 100644 src/vendor/golang.org/x/net/html/entity.go delete mode 100644 src/vendor/golang.org/x/net/html/escape.go delete mode 100644 src/vendor/golang.org/x/net/html/foreign.go delete mode 100644 src/vendor/golang.org/x/net/html/iter.go delete mode 100644 src/vendor/golang.org/x/net/html/node.go delete mode 100644 src/vendor/golang.org/x/net/html/parse.go delete mode 100644 src/vendor/golang.org/x/net/html/render.go delete mode 100644 src/vendor/golang.org/x/net/html/token.go diff --git a/.github/workflows/devenv.yaml b/.github/workflows/devenv.yaml index 158ca27..2a7712f 100644 --- a/.github/workflows/devenv.yaml +++ b/.github/workflows/devenv.yaml @@ -18,7 +18,6 @@ on: # yamllint disable-line rule:truthy - devenv.nix - devenv.yaml - devenv.lock - - devenv/** - src/** concurrency: diff --git a/devenv.nix b/devenv.nix index 0c9ec68..5eafc2f 100644 --- a/devenv.nix +++ b/devenv.nix @@ -92,7 +92,9 @@ in }; git-hooks = { - excludes = [ ]; + excludes = [ + "src/vendor/" + ]; hooks = { beautysh.enable = false; actionlint.enable = true; diff --git a/scripts/yolo.sh b/scripts/yolo.sh index 34ff6d3..bacbb11 100755 --- a/scripts/yolo.sh +++ b/scripts/yolo.sh @@ -94,7 +94,7 @@ function detect_os() { return 0 } -# shellcheck disable=SC2317 +# shellcheck disable=SC2317,SC2329 function cleanup() { msg "INFO" "๐Ÿงน Cleaning up temporary directory" rm -rf "${TMP_DIR}" || { diff --git a/src/go.mod b/src/go.mod index ca02d4a..e6ca152 100644 --- a/src/go.mod +++ b/src/go.mod @@ -3,17 +3,16 @@ module github.com/MAHDTech/nixos-installer go 1.24.1 require ( - github.com/go-playground/validator/v10 v10.27.0 + github.com/go-playground/validator/v10 v10.28.0 gopkg.in/yaml.v3 v3.0.1 ) require ( - github.com/gabriel-vasile/mimetype v1.4.9 // indirect + github.com/gabriel-vasile/mimetype v1.4.10 // indirect github.com/go-playground/locales v0.14.1 // indirect github.com/go-playground/universal-translator v0.18.1 // indirect github.com/leodido/go-urn v1.4.0 // indirect - golang.org/x/crypto v0.41.0 // indirect - golang.org/x/net v0.43.0 // indirect - golang.org/x/sys v0.35.0 // indirect - golang.org/x/text v0.28.0 // indirect + golang.org/x/crypto v0.43.0 // indirect + golang.org/x/sys v0.37.0 // indirect + golang.org/x/text v0.30.0 // indirect ) diff --git a/src/go.sum b/src/go.sum index 3a35a9f..b237198 100644 --- a/src/go.sum +++ b/src/go.sum @@ -1,29 +1,27 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= -github.com/gabriel-vasile/mimetype v1.4.9 h1:5k+WDwEsD9eTLL8Tz3L0VnmVh9QxGjRmjBvAG7U/oYY= -github.com/gabriel-vasile/mimetype v1.4.9/go.mod h1:WnSQhFKJuBlRyLiKohA/2DtIlPFAbguNaG7QCHcyGok= +github.com/gabriel-vasile/mimetype v1.4.10 h1:zyueNbySn/z8mJZHLt6IPw0KoZsiQNszIpU+bX4+ZK0= +github.com/gabriel-vasile/mimetype v1.4.10/go.mod h1:d+9Oxyo1wTzWdyVUPMmXFvp4F9tea18J8ufA774AB3s= github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s= github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4= github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA= github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY= github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY= github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY= -github.com/go-playground/validator/v10 v10.27.0 h1:w8+XrWVMhGkxOaaowyKH35gFydVHOvC0/uWoy2Fzwn4= -github.com/go-playground/validator/v10 v10.27.0/go.mod h1:I5QpIEbmr8On7W0TktmJAumgzX4CA1XNl4ZmDuVHKKo= +github.com/go-playground/validator/v10 v10.28.0 h1:Q7ibns33JjyW48gHkuFT91qX48KG0ktULL6FgHdG688= +github.com/go-playground/validator/v10 v10.28.0/go.mod h1:GoI6I1SjPBh9p7ykNE/yj3fFYbyDOpwMn5KXd+m2hUU= github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ= github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk= github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo= -golang.org/x/crypto v0.41.0 h1:WKYxWedPGCTVVl5+WHSSrOBT0O8lx32+zxmHxijgXp4= -golang.org/x/crypto v0.41.0/go.mod h1:pO5AFd7FA68rFak7rOAGVuygIISepHftHnr8dr6+sUc= -golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE= -golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg= -golang.org/x/sys v0.35.0 h1:vz1N37gP5bs89s7He8XuIYXpyY0+QlsKmzipCbUtyxI= -golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k= -golang.org/x/text v0.28.0 h1:rhazDwis8INMIwQ4tpjLDzUhx6RlXqZNPEM0huQojng= -golang.org/x/text v0.28.0/go.mod h1:U8nCwOR8jO/marOQ0QbDiOngZVEBB7MAiitBuMjXiNU= +golang.org/x/crypto v0.43.0 h1:dduJYIi3A3KOfdGOHX8AVZ/jGiyPa3IbBozJ5kNuE04= +golang.org/x/crypto v0.43.0/go.mod h1:BFbav4mRNlXJL4wNeejLpWxB7wMbc79PdRGhWKncxR0= +golang.org/x/sys v0.37.0 h1:fdNQudmxPjkdUTPnLn5mdQv7Zwvbvpaxqs831goi9kQ= +golang.org/x/sys v0.37.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks= +golang.org/x/text v0.30.0 h1:yznKA/E9zq54KzlzBEAWn1NXSQ8DIp/NYMy88xJjl4k= +golang.org/x/text v0.30.0/go.mod h1:yDdHFIX9t+tORqspjENWgzaCVXgk0yYnYuSZ8UzzBVM= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= diff --git a/src/gomod2nix.toml b/src/gomod2nix.toml index 31f73c4..d0de542 100644 --- a/src/gomod2nix.toml +++ b/src/gomod2nix.toml @@ -2,8 +2,8 @@ schema = 3 [mod] [mod."github.com/gabriel-vasile/mimetype"] - version = "v1.4.9" - hash = "sha256-75uELLqb01djHTe7KdXvUidBK7SuejarYouEUuxaj8Q=" + version = "v1.4.10" + hash = "sha256-ha8NJOAWcmEfQaybfNxyUupt0+zlWxoAKLjCacew43s=" [mod."github.com/go-playground/locales"] version = "v0.14.1" hash = "sha256-BMJGAexq96waZn60DJXZfByRHb8zA/JP/i6f/YrW9oQ=" @@ -11,23 +11,20 @@ schema = 3 version = "v0.18.1" hash = "sha256-2/B2qP51zfiY+k8G0w0D03KXUc7XpWj6wKY7NjNP/9E=" [mod."github.com/go-playground/validator/v10"] - version = "v10.27.0" - hash = "sha256-S6RXBwCOaLUumtS1xucTzOPGxA9XuA3R8RNdGE7w2Qc=" + version = "v10.28.0" + hash = "sha256-uKGZF1ChxE2aLeiU2V5YtzMqae+ksNI/UwZedOdpRmo=" [mod."github.com/leodido/go-urn"] version = "v1.4.0" hash = "sha256-Q6kplWkY37Tzy6GOme3Wut40jFK4Izun+ij/BJvcEu0=" [mod."golang.org/x/crypto"] - version = "v0.41.0" - hash = "sha256-o5Di0lsFmYnXl7a5MBTqmN9vXMCRpE9ay71C1Ar8jEY=" - [mod."golang.org/x/net"] version = "v0.43.0" - hash = "sha256-bf3iQFrsC8BoarVaS0uSspEFAcr1zHp1uziTtBpwV34=" + hash = "sha256-Klv4v0G024WY2OWXsOEl4sKKI+SsUyqx++als1B6yn4=" [mod."golang.org/x/sys"] - version = "v0.35.0" - hash = "sha256-ZKM8pesQE6NAFZeKQ84oPn5JMhGr8g4TSwLYAsHMGSI=" + version = "v0.37.0" + hash = "sha256-5aT0xP02sW1o9sfJHtWoGGNVYDdwb9FyiX/n6RAlzPo=" [mod."golang.org/x/text"] - version = "v0.28.0" - hash = "sha256-8UlJniGK+km4Hmrw6XMxELnExgrih7+z8tU26Cntmto=" + version = "v0.30.0" + hash = "sha256-VPT1Y2zzgdk+Q3Gx8hdwKdxbVh0/Zn/HwDpILCW3ZNA=" [mod."gopkg.in/yaml.v3"] version = "v3.0.1" hash = "sha256-FqL9TKYJ0XkNwJFnq9j0VvJ5ZUU1RvH/52h/f5bkYAU=" diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/CODE_OF_CONDUCT.md b/src/vendor/github.com/gabriel-vasile/mimetype/CODE_OF_CONDUCT.md deleted file mode 100644 index 8479cd8..0000000 --- a/src/vendor/github.com/gabriel-vasile/mimetype/CODE_OF_CONDUCT.md +++ /dev/null @@ -1,76 +0,0 @@ -# Contributor Covenant Code of Conduct - -## Our Pledge - -In the interest of fostering an open and welcoming environment, we as -contributors and maintainers pledge to making participation in our project and -our community a harassment-free experience for everyone, regardless of age, body -size, disability, ethnicity, sex characteristics, gender identity and expression, -level of experience, education, socio-economic status, nationality, personal -appearance, race, religion, or sexual identity and orientation. - -## Our Standards - -Examples of behavior that contributes to creating a positive environment -include: - -* Using welcoming and inclusive language -* Being respectful of differing viewpoints and experiences -* Gracefully accepting constructive criticism -* Focusing on what is best for the community -* Showing empathy towards other community members - -Examples of unacceptable behavior by participants include: - -* The use of sexualized language or imagery and unwelcome sexual attention or - advances -* Trolling, insulting/derogatory comments, and personal or political attacks -* Public or private harassment -* Publishing others' private information, such as a physical or electronic - address, without explicit permission -* Other conduct which could reasonably be considered inappropriate in a - professional setting - -## Our Responsibilities - -Project maintainers are responsible for clarifying the standards of acceptable -behavior and are expected to take appropriate and fair corrective action in -response to any instances of unacceptable behavior. - -Project maintainers have the right and responsibility to remove, edit, or -reject comments, commits, code, wiki edits, issues, and other contributions -that are not aligned to this Code of Conduct, or to ban temporarily or -permanently any contributor for other behaviors that they deem inappropriate, -threatening, offensive, or harmful. - -## Scope - -This Code of Conduct applies both within project spaces and in public spaces -when an individual is representing the project or its community. Examples of -representing a project or community include using an official project e-mail -address, posting via an official social media account, or acting as an appointed -representative at an online or offline event. Representation of a project may be -further defined and clarified by project maintainers. - -## Enforcement - -Instances of abusive, harassing, or otherwise unacceptable behavior may be -reported by contacting the project team at vasile.gabriel@email.com. All -complaints will be reviewed and investigated and will result in a response that -is deemed necessary and appropriate to the circumstances. The project team is -obligated to maintain confidentiality with regard to the reporter of an incident. -Further details of specific enforcement policies may be posted separately. - -Project maintainers who do not follow or enforce the Code of Conduct in good -faith may face temporary or permanent repercussions as determined by other -members of the project's leadership. - -## Attribution - -This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4, -available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html - -[homepage]: https://www.contributor-covenant.org - -For answers to common questions about this code of conduct, see -https://www.contributor-covenant.org/faq diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/CONTRIBUTING.md b/src/vendor/github.com/gabriel-vasile/mimetype/CONTRIBUTING.md deleted file mode 100644 index 56ae4e5..0000000 --- a/src/vendor/github.com/gabriel-vasile/mimetype/CONTRIBUTING.md +++ /dev/null @@ -1,12 +0,0 @@ -## Contribute -Contributions to **mimetype** are welcome. If you find an issue and you consider -contributing, you can use the [Github issues tracker](https://github.com/gabriel-vasile/mimetype/issues) -in order to report it, or better yet, open a pull request. - -Code contributions must respect these rules: - - code must be test covered - - code must be formatted using gofmt tool - - exported names must be documented - -**Important**: By submitting a pull request, you agree to allow the project -owner to license your work under the same license as that used by the project. diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/README.md b/src/vendor/github.com/gabriel-vasile/mimetype/README.md index aa88b4b..f28f56c 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/README.md +++ b/src/vendor/github.com/gabriel-vasile/mimetype/README.md @@ -27,6 +27,7 @@ - possibility to [extend](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#example-package-Extend) with other file formats - common file formats are prioritized - [text vs. binary files differentiation](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#example-package-TextVsBinary) +- no external dependencies - safe for concurrent usage ## Install @@ -45,8 +46,7 @@ fmt.Println(mtype.String(), mtype.Extension()) ``` See the [runnable Go Playground examples](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#pkg-overview). -## Usage' -Only use libraries like **mimetype** as a last resort. Content type detection +Caution: only use libraries like **mimetype** as a last resort. Content type detection using magic numbers is slow, inaccurate, and non-standard. Most of the times protocols have methods for specifying such metadata; e.g., `Content-Type` header in HTTP and SMTP. @@ -67,6 +67,18 @@ mimetype.DetectFile("file.doc") If increasing the limit does not help, please [open an issue](https://github.com/gabriel-vasile/mimetype/issues/new?assignees=&labels=&template=mismatched-mime-type-detected.md&title=). +## Tests +In addition to unit tests, +[mimetype_tests](https://github.com/gabriel-vasile/mimetype_tests) compares the +library with the [Unix file utility](https://en.wikipedia.org/wiki/File_(command)) +for around 50 000 sample files. Check the latest comparison results +[here](https://github.com/gabriel-vasile/mimetype_tests/actions). + +## Benchmarks +Benchmarks for each file format are performed when a PR is open. The results can +be seen on the [workflows page](https://github.com/gabriel-vasile/mimetype/actions/workflows/benchmark.yml). +Performance improvements are welcome but correctness is prioritized. + ## Structure **mimetype** uses a hierarchical structure to keep the MIME type detection logic. This reduces the number of calls needed for detecting the file type. The reason @@ -84,19 +96,8 @@ or from a [file](https://pkg.go.dev/github.com/gabriel-vasile/mimetype#DetectFil how project is structured -## Performance -Thanks to the hierarchical structure, searching for common formats first, -and limiting itself to file headers, **mimetype** matches the performance of -stdlib `http.DetectContentType` while outperforming the alternative package. - -```bash - mimetype http.DetectContentType filetype -BenchmarkMatchTar-24 250 ns/op 400 ns/op 3778 ns/op -BenchmarkMatchZip-24 524 ns/op 351 ns/op 4884 ns/op -BenchmarkMatchJpeg-24 103 ns/op 228 ns/op 839 ns/op -BenchmarkMatchGif-24 139 ns/op 202 ns/op 751 ns/op -BenchmarkMatchPng-24 165 ns/op 221 ns/op 1176 ns/op -``` - ## Contributing -See [CONTRIBUTING.md](CONTRIBUTING.md). +Contributions are unexpected but welcome. When submitting a PR for detection of +a new file format, please make sure to add a record to the list of testcases +from [mimetype_test.go](mimetype_test.go). For complex files a record can be added +in the [testdata](testdata) directory. diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/charset/charset.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/charset/charset.go index 0647f73..8c5a05e 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/charset/charset.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/charset/charset.go @@ -2,11 +2,10 @@ package charset import ( "bytes" - "encoding/xml" - "strings" "unicode/utf8" - "golang.org/x/net/html" + "github.com/gabriel-vasile/mimetype/internal/markup" + "github.com/gabriel-vasile/mimetype/internal/scan" ) const ( @@ -141,20 +140,31 @@ func FromXML(content []byte) string { } return FromPlain(content) } -func fromXML(content []byte) string { - content = trimLWS(content) - dec := xml.NewDecoder(bytes.NewReader(content)) - rawT, err := dec.RawToken() - if err != nil { - return "" - } - - t, ok := rawT.(xml.ProcInst) - if !ok { - return "" +func fromXML(s scan.Bytes) string { + xml := []byte(" 0 && line[n-1] == '\r' { + return line[:n-1], false // drop \r at end of line + } + + // This line is problematic. The logic from CountFields comes from + // encoding/csv.Reader which relies on mutating the input bytes. + // https://github.com/golang/go/blob/b3251514531123d7fd007682389bce7428d159a0/src/encoding/csv/reader.go#L275-L279 + // To avoid mutating the input, we return cutShort. #680 + if n >= 2 && line[n-2] == '\r' && line[n-1] == '\n' { + return line[:n-2], true + } + return line, false +} + +// CountFields reads one CSV line and counts how many records that line contained. +// hasMore reports whether there are more lines in the input. +// collectIndexes makes CountFields return a list of indexes where CSV fields +// start in the line. These indexes are used to test the correctness against the +// encoding/csv parser. +func (r *Parser) CountFields(collectIndexes bool) (fields int, fieldPos []int, hasMore bool) { + finished := false + var line scan.Bytes + cutShort := false + for { + line, cutShort = r.readLine() + if finished { + return 0, nil, false + } + finished = len(r.s) == 0 && len(line) == 0 + if len(line) == lengthNL(line) { + line = nil + continue // Skip empty lines. + } + if len(line) > 0 && line[0] == r.comment { + line = nil + continue + } + break + } + + indexes := []int{} + originalLine := line +parseField: + for { + if len(line) == 0 || line[0] != '"' { // non-quoted string field + fields++ + if collectIndexes { + indexes = append(indexes, len(originalLine)-len(line)) + } + i := bytes.IndexByte(line, r.comma) + if i >= 0 { + line.Advance(i + 1) // 1 to get over ending comma + continue parseField + } + break parseField + } else { // Quoted string field. + if collectIndexes { + indexes = append(indexes, len(originalLine)-len(line)) + } + line.Advance(1) // get over starting quote + for { + i := bytes.IndexByte(line, '"') + if i >= 0 { + line.Advance(i + 1) // 1 for ending quote + switch rn := line.Peek(); { + case rn == '"': + line.Advance(1) + case rn == r.comma: + line.Advance(1) + fields++ + continue parseField + case lengthNL(line) == len(line): + fields++ + break parseField + } + } else if len(line) > 0 || cutShort { + line, cutShort = r.readLine() + originalLine = line + } else { + fields++ + break parseField + } + } + } + } + + return fields, indexes, fields != 0 +} + +// lengthNL reports the number of bytes for the trailing \n. +func lengthNL(b []byte) int { + if len(b) > 0 && b[len(b)-1] == '\n' { + return 1 + } + return 0 +} diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/json/parser.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/json/parser.go index fd8dd52..4bc8617 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/json/parser.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/json/parser.go @@ -258,7 +258,7 @@ out: } func (p *parserState) consumeArray(b []byte, qs []query, lvl int) (n int) { - p.currPath = append(p.currPath, []byte{'['}) + p.appendPath([]byte{'['}, qs) if len(b) == 0 { return 0 } @@ -270,7 +270,7 @@ func (p *parserState) consumeArray(b []byte, qs []query, lvl int) (n int) { } if b[n] == ']' { p.ib++ - p.currPath = p.currPath[:len(p.currPath)-1] + p.popLastPath(qs) return n + 1 } innerParsed := p.consumeAny(b[n:], qs, lvl) @@ -305,6 +305,20 @@ func queryPathMatch(qs []query, path [][]byte) int { return -1 } +// appendPath will append a path fragment if queries is not empty. +// If we don't need query functionality (just checking if a JSON is valid), +// then we can skip keeping track of the path we're currently in. +func (p *parserState) appendPath(path []byte, qs []query) { + if len(qs) != 0 { + p.currPath = append(p.currPath, path) + } +} +func (p *parserState) popLastPath(qs []query) { + if len(qs) != 0 { + p.currPath = p.currPath[:len(p.currPath)-1] + } +} + func (p *parserState) consumeObject(b []byte, qs []query, lvl int) (n int) { for n < len(b) { n += p.consumeSpace(b[n:]) @@ -326,7 +340,7 @@ func (p *parserState) consumeObject(b []byte, qs []query, lvl int) (n int) { if keyLen := p.consumeString(b[n:]); keyLen == 0 { return 0 } else { - p.currPath = append(p.currPath, b[n:n+keyLen-1]) + p.appendPath(b[n:n+keyLen-1], qs) if !p.querySatisfied { queryMatched = queryPathMatch(qs, p.currPath) } @@ -368,12 +382,12 @@ func (p *parserState) consumeObject(b []byte, qs []query, lvl int) (n int) { } switch b[n] { case ',': - p.currPath = p.currPath[:len(p.currPath)-1] + p.popLastPath(qs) n++ p.ib++ continue case '}': - p.currPath = p.currPath[:len(p.currPath)-1] + p.popLastPath(qs) p.ib++ return n + 1 default: @@ -388,6 +402,9 @@ func (p *parserState) consumeAny(b []byte, qs []query, lvl int) (n int) { if p.maxRecursion != 0 && lvl > p.maxRecursion { return 0 } + if len(qs) == 0 { + p.querySatisfied = true + } n += p.consumeSpace(b) if len(b[n:]) == 0 { return 0 @@ -426,9 +443,6 @@ func (p *parserState) consumeAny(b []byte, qs []query, lvl int) (n int) { if lvl == 0 { p.firstToken = t } - if len(qs) == 0 { - p.querySatisfied = true - } if rv <= 0 { return n } diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/document.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/document.go index b3b26d5..7f9308d 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/document.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/document.go @@ -1,18 +1,11 @@ package magic -import "bytes" +import ( + "bytes" + "encoding/binary" +) var ( - // Pdf matches a Portable Document Format file. - // https://github.com/file/file/blob/11010cc805546a3e35597e67e1129a481aed40e8/magic/Magdir/pdf - Pdf = prefix( - // usual pdf signature - []byte("%PDF-"), - // new-line prefixed signature - []byte("\012%PDF-"), - // UTF-8 BOM prefixed signature - []byte("\xef\xbb\xbf%PDF-"), - ) // Fdf matches a Forms Data Format file. Fdf = prefix([]byte("%FDF")) // Mobi matches a Mobi file. @@ -21,8 +14,18 @@ var ( Lit = prefix([]byte("ITOLITLS")) ) +// PDF matches a Portable Document Format file. +// The %PDF- header should be the first thing inside the file but many +// implementations don't follow the rule. The PDF spec at Appendix H says the +// signature can be prepended by anything. +// https://bugs.astron.com/view.php?id=446 +func PDF(raw []byte, _ uint32) bool { + raw = raw[:min(len(raw), 1024)] + return bytes.Contains(raw, []byte("%PDF-")) +} + // DjVu matches a DjVu file. -func DjVu(raw []byte, limit uint32) bool { +func DjVu(raw []byte, _ uint32) bool { if len(raw) < 12 { return false } @@ -36,7 +39,7 @@ func DjVu(raw []byte, limit uint32) bool { } // P7s matches an .p7s signature File (PEM, Base64). -func P7s(raw []byte, limit uint32) bool { +func P7s(raw []byte, _ uint32) bool { // Check for PEM Encoding. if bytes.HasPrefix(raw, []byte("-----BEGIN PKCS7")) { return true @@ -60,3 +63,21 @@ func P7s(raw []byte, limit uint32) bool { return false } + +// Lotus123 matches a Lotus 1-2-3 spreadsheet document. +func Lotus123(raw []byte, _ uint32) bool { + if len(raw) <= 20 { + return false + } + version := binary.BigEndian.Uint32(raw) + if version == 0x00000200 { + return raw[6] != 0 && raw[7] == 0 + } + + return version == 0x00001a00 && raw[20] > 0 && raw[20] < 32 +} + +// CHM matches a Microsoft Compiled HTML Help file. +func CHM(raw []byte, _ uint32) bool { + return bytes.HasPrefix(raw, []byte("ITSF\003\000\000\000\x60\000\000\000")) +} diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/magic.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/magic.go index a34c609..5fe435b 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/magic.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/magic.go @@ -4,6 +4,8 @@ package magic import ( "bytes" "fmt" + + "github.com/gabriel-vasile/mimetype/internal/scan" ) type ( @@ -74,12 +76,13 @@ func ciCheck(sig, raw []byte) bool { // matches the raw input. func xml(sigs ...xmlSig) Detector { return func(raw []byte, limit uint32) bool { - raw = trimLWS(raw) - if len(raw) == 0 { + b := scan.Bytes(raw) + b.TrimLWS() + if len(b) == 0 { return false } for _, s := range sigs { - if xmlCheck(s, raw) { + if xmlCheck(s, b) { return true } } @@ -104,19 +107,19 @@ func xmlCheck(sig xmlSig, raw []byte) bool { // matches the raw input. func markup(sigs ...[]byte) Detector { return func(raw []byte, limit uint32) bool { - if bytes.HasPrefix(raw, []byte{0xEF, 0xBB, 0xBF}) { + b := scan.Bytes(raw) + if bytes.HasPrefix(b, []byte{0xEF, 0xBB, 0xBF}) { // We skip the UTF-8 BOM if present to ensure we correctly // process any leading whitespace. The presence of the BOM // is taken into account during charset detection in charset.go. - raw = trimLWS(raw[3:]) - } else { - raw = trimLWS(raw) + b.Advance(3) } - if len(raw) == 0 { + b.TrimLWS() + if len(b) == 0 { return false } for _, s := range sigs { - if markupCheck(s, raw) { + if markupCheck(s, b) { return true } } @@ -139,7 +142,7 @@ func markupCheck(sig, raw []byte) bool { } } // Next byte must be space or right angle bracket. - if db := raw[len(sig)]; db != ' ' && db != '>' { + if db := raw[len(sig)]; !scan.ByteIsWS(db) && db != '>' { return false } @@ -183,8 +186,10 @@ func newXMLSig(localName, xmlns string) xmlSig { // /usr/bin/env is the interpreter, php is the first and only argument. func shebang(sigs ...[]byte) Detector { return func(raw []byte, limit uint32) bool { + b := scan.Bytes(raw) + line := b.Line() for _, s := range sigs { - if shebangCheck(s, firstLine(raw)) { + if shebangCheck(s, line) { return true } } @@ -192,7 +197,7 @@ func shebang(sigs ...[]byte) Detector { } } -func shebangCheck(sig, raw []byte) bool { +func shebangCheck(sig []byte, raw scan.Bytes) bool { if len(raw) < len(sig)+2 { return false } @@ -200,52 +205,8 @@ func shebangCheck(sig, raw []byte) bool { return false } - return bytes.Equal(trimLWS(trimRWS(raw[2:])), sig) -} - -// trimLWS trims whitespace from beginning of the input. -func trimLWS(in []byte) []byte { - firstNonWS := 0 - for ; firstNonWS < len(in) && isWS(in[firstNonWS]); firstNonWS++ { - } - - return in[firstNonWS:] -} - -// trimRWS trims whitespace from the end of the input. -func trimRWS(in []byte) []byte { - lastNonWS := len(in) - 1 - for ; lastNonWS > 0 && isWS(in[lastNonWS]); lastNonWS-- { - } - - return in[:lastNonWS+1] -} - -func firstLine(in []byte) []byte { - lineEnd := 0 - for ; lineEnd < len(in) && in[lineEnd] != '\n'; lineEnd++ { - } - - return in[:lineEnd] -} - -func isWS(b byte) bool { - return b == '\t' || b == '\n' || b == '\x0c' || b == '\r' || b == ' ' -} - -func min(a, b int) int { - if a < b { - return a - } - return b -} - -type readBuf []byte - -func (b *readBuf) advance(n int) bool { - if n < 0 || len(*b) < n { - return false - } - *b = (*b)[n:] - return true + raw.Advance(2) // skip #! we checked above + raw.TrimLWS() + raw.TrimRWS() + return bytes.Equal(raw, sig) } diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/ms_office.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/ms_office.go index 7d60e22..c912823 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/ms_office.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/ms_office.go @@ -7,17 +7,34 @@ import ( // Xlsx matches a Microsoft Excel 2007 file. func Xlsx(raw []byte, limit uint32) bool { - return zipContains(raw, []byte("xl/"), true) + return msoxml(raw, zipEntries{{ + name: []byte("xl/"), + dir: true, + }}, 100) } // Docx matches a Microsoft Word 2007 file. func Docx(raw []byte, limit uint32) bool { - return zipContains(raw, []byte("word/"), true) + return msoxml(raw, zipEntries{{ + name: []byte("word/"), + dir: true, + }}, 100) } // Pptx matches a Microsoft PowerPoint 2007 file. func Pptx(raw []byte, limit uint32) bool { - return zipContains(raw, []byte("ppt/"), true) + return msoxml(raw, zipEntries{{ + name: []byte("ppt/"), + dir: true, + }}, 100) +} + +// Visio matches a Microsoft Visio 2013+ file. +func Visio(raw []byte, limit uint32) bool { + return msoxml(raw, zipEntries{{ + name: []byte("visio/"), + dir: true, + }}, 100) } // Ole matches an Open Linking and Embedding file. @@ -157,6 +174,14 @@ func Msi(raw []byte, limit uint32) bool { }) } +// One matches a Microsoft OneNote file. +func One(raw []byte, limit uint32) bool { + return bytes.HasPrefix(raw, []byte{ + 0xe4, 0x52, 0x5c, 0x7b, 0x8c, 0xd8, 0xa7, 0x4d, + 0xae, 0xb1, 0x53, 0x78, 0xd0, 0x29, 0x96, 0xd3, + }) +} + // Helper to match by a specific CLSID of a compound file. // // http://fileformats.archiveteam.org/wiki/Microsoft_Compound_File diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/netpbm.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/netpbm.go new file mode 100644 index 0000000..4baa257 --- /dev/null +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/netpbm.go @@ -0,0 +1,111 @@ +package magic + +import ( + "bytes" + "strconv" + + "github.com/gabriel-vasile/mimetype/internal/scan" +) + +// NetPBM matches a Netpbm Portable BitMap ASCII/Binary file. +// +// See: https://en.wikipedia.org/wiki/Netpbm +func NetPBM(raw []byte, _ uint32) bool { + return netp(raw, "P1\n", "P4\n") +} + +// NetPGM matches a Netpbm Portable GrayMap ASCII/Binary file. +// +// See: https://en.wikipedia.org/wiki/Netpbm +func NetPGM(raw []byte, _ uint32) bool { + return netp(raw, "P2\n", "P5\n") +} + +// NetPPM matches a Netpbm Portable PixMap ASCII/Binary file. +// +// See: https://en.wikipedia.org/wiki/Netpbm +func NetPPM(raw []byte, _ uint32) bool { + return netp(raw, "P3\n", "P6\n") +} + +// NetPAM matches a Netpbm Portable Arbitrary Map file. +// +// See: https://en.wikipedia.org/wiki/Netpbm +func NetPAM(raw []byte, _ uint32) bool { + if !bytes.HasPrefix(raw, []byte("P7\n")) { + return false + } + w, h, d, m, e := false, false, false, false, false + s := scan.Bytes(raw) + var l scan.Bytes + // Read line by line. + for i := 0; i < 128; i++ { + l = s.Line() + // If the line is empty or a comment, skip. + if len(l) == 0 || l.Peek() == '#' { + if len(s) == 0 { + return false + } + continue + } else if bytes.HasPrefix(l, []byte("TUPLTYPE")) { + continue + } else if bytes.HasPrefix(l, []byte("WIDTH ")) { + w = true + } else if bytes.HasPrefix(l, []byte("HEIGHT ")) { + h = true + } else if bytes.HasPrefix(l, []byte("DEPTH ")) { + d = true + } else if bytes.HasPrefix(l, []byte("MAXVAL ")) { + m = true + } else if bytes.HasPrefix(l, []byte("ENDHDR")) { + e = true + } + // When we reached header, return true if we collected all four required headers. + // WIDTH, HEIGHT, DEPTH and MAXVAL. + if e { + return w && h && d && m + } + } + return false +} + +func netp(s scan.Bytes, prefixes ...string) bool { + foundPrefix := "" + for _, p := range prefixes { + if bytes.HasPrefix(s, []byte(p)) { + foundPrefix = p + } + } + if foundPrefix == "" { + return false + } + s.Advance(len(foundPrefix)) // jump over P1, P2, P3, etc. + + var l scan.Bytes + // Read line by line. + for i := 0; i < 128; i++ { + l = s.Line() + // If the line is a comment, skip. + if l.Peek() == '#' { + continue + } + // If line has leading whitespace, then skip over whitespace. + for scan.ByteIsWS(l.Peek()) { + l.Advance(1) + } + if len(s) == 0 || len(l) > 0 { + break + } + } + + // At this point l should be the two integers denoting the size of the matrix. + width := l.PopUntil(scan.ASCIISpaces...) + for scan.ByteIsWS(l.Peek()) { + l.Advance(1) + } + height := l.PopUntil(scan.ASCIISpaces...) + + w, errw := strconv.ParseInt(string(width), 10, 64) + h, errh := strconv.ParseInt(string(height), 10, 64) + return errw == nil && errh == nil && w > 0 && h > 0 +} diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text.go index 8178e47..1841ee8 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text.go @@ -6,6 +6,8 @@ import ( "github.com/gabriel-vasile/mimetype/internal/charset" "github.com/gabriel-vasile/mimetype/internal/json" + mkup "github.com/gabriel-vasile/mimetype/internal/markup" + "github.com/gabriel-vasile/mimetype/internal/scan" ) var ( @@ -27,6 +29,7 @@ var ( []byte(" +// +// +// +func svgWithoutXMLDeclaration(s scan.Bytes) bool { + for scan.ByteIsWS(s.Peek()) { + s.Advance(1) + } + for mkup.SkipAComment(&s) { + } + if !bytes.HasPrefix(s, []byte(" +// +// +// +func svgWithXMLDeclaration(s scan.Bytes) bool { + for scan.ByteIsWS(s.Peek()) { + s.Advance(1) + } + if !bytes.HasPrefix(s, []byte(" 4096 { + s = s[:4096] + } + return hasVersion && bytes.Contains(s, []byte(" 00:02:19,376) limits second line // length to exactly 29 characters. if len(line) != 29 { @@ -266,7 +380,7 @@ func Srt(raw []byte, _ uint32) bool { return false } - line, _ = scanLine(raw) + line = s.Line() // A third line must exist and not be empty. This is the actual subtitle text. return len(line) != 0 } @@ -295,15 +409,3 @@ func Vtt(raw []byte, limit uint32) bool { return bytes.Equal(raw, []byte{0xEF, 0xBB, 0xBF, 0x57, 0x45, 0x42, 0x56, 0x54, 0x54}) || // UTF-8 BOM and "WEBVTT" bytes.Equal(raw, []byte{0x57, 0x45, 0x42, 0x56, 0x54, 0x54}) // "WEBVTT" } - -// dropCR drops a terminal \r from the data. -func dropCR(data []byte) []byte { - if len(data) > 0 && data[len(data)-1] == '\r' { - return data[0 : len(data)-1] - } - return data -} -func scanLine(b []byte) (line, remainder []byte) { - line, remainder, _ = bytes.Cut(b, []byte("\n")) - return dropCR(line), remainder -} diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text_csv.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text_csv.go index 6083ba8..020b5ee 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text_csv.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/text_csv.go @@ -1,77 +1,43 @@ package magic import ( - "bufio" - "bytes" - "encoding/csv" - "errors" - "io" - "sync" + "github.com/gabriel-vasile/mimetype/internal/csv" + "github.com/gabriel-vasile/mimetype/internal/scan" ) -// A bufio.Reader pool to alleviate problems with memory allocations. -var readerPool = sync.Pool{ - New: func() any { - // Initiate with empty source reader. - return bufio.NewReader(nil) - }, -} - -func newReader(r io.Reader) *bufio.Reader { - br := readerPool.Get().(*bufio.Reader) - br.Reset(r) - return br -} - -// Csv matches a comma-separated values file. -func Csv(raw []byte, limit uint32) bool { +// CSV matches a comma-separated values file. +func CSV(raw []byte, limit uint32) bool { return sv(raw, ',', limit) } -// Tsv matches a tab-separated values file. -func Tsv(raw []byte, limit uint32) bool { +// TSV matches a tab-separated values file. +func TSV(raw []byte, limit uint32) bool { return sv(raw, '\t', limit) } -func sv(in []byte, comma rune, limit uint32) bool { - in = dropLastLine(in, limit) - - br := newReader(bytes.NewReader(in)) - defer readerPool.Put(br) - r := csv.NewReader(br) - r.Comma = comma - r.ReuseRecord = true - r.LazyQuotes = true - r.Comment = '#' +func sv(in []byte, comma byte, limit uint32) bool { + s := scan.Bytes(in) + s.DropLastLine(limit) + r := csv.NewParser(comma, '#', s) - lines := 0 + headerFields, _, hasMore := r.CountFields(false) + if headerFields < 2 || !hasMore { + return false + } + csvLines := 1 // 1 for header for { - _, err := r.Read() - if errors.Is(err, io.EOF) { + fields, _, hasMore := r.CountFields(false) + if !hasMore && fields == 0 { break } - if err != nil { + csvLines++ + if fields != headerFields { return false } - lines++ - } - - return r.FieldsPerRecord > 1 && lines > 1 -} - -// dropLastLine drops the last incomplete line from b. -// -// mimetype limits itself to ReadLimit bytes when performing a detection. -// This means, for file formats like CSV for NDJSON, the last line of the input -// can be an incomplete line. -func dropLastLine(b []byte, readLimit uint32) []byte { - if readLimit == 0 || uint32(len(b)) < readLimit { - return b - } - for i := len(b) - 1; i > 0; i-- { - if b[i] == '\n' { - return b[:i] + if csvLines >= 10 { + return true } } - return b + + return csvLines >= 2 } diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/zip.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/zip.go index f6c6482..17750e6 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/zip.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/magic/zip.go @@ -2,7 +2,8 @@ package magic import ( "bytes" - "encoding/binary" + + "github.com/gabriel-vasile/mimetype/internal/scan" ) var ( @@ -40,92 +41,149 @@ func Zip(raw []byte, limit uint32) bool { (raw[3] == 0x4 || raw[3] == 0x6 || raw[3] == 0x8) } -// Jar matches a Java archive file. +// Jar matches a Java archive file. There are two types of Jar files: +// 1. the ones that can be opened with jexec and have 0xCAFE optional flag +// https://stackoverflow.com/tags/executable-jar/info +// 2. regular jars, same as above, just without the executable flag +// https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=262278#c0 +// There is an argument to only check for manifest, since it's the common nominator +// for both executable and non-executable versions. But the traversing zip entries +// is unreliable because it does linear search for signatures +// (instead of relying on offsets told by the file.) func Jar(raw []byte, limit uint32) bool { - return zipContains(raw, []byte("META-INF/MANIFEST.MF"), false) + return executableJar(raw) || + zipHas(raw, zipEntries{{ + name: []byte("META-INF/MANIFEST.MF"), + }, { + name: []byte("META-INF/"), + }}, 1) } -func zipContains(raw, sig []byte, msoCheck bool) bool { - b := readBuf(raw) - pk := []byte("PK\003\004") - if len(b) < 0x1E { - return false - } +// KMZ matches a zipped KML file, which is "doc.kml" by convention. +func KMZ(raw []byte, _ uint32) bool { + return zipHas(raw, zipEntries{{ + name: []byte("doc.kml"), + }}, 100) +} - if !b.advance(0x1E) { +// An executable Jar has a 0xCAFE flag enabled in the first zip entry. +// The rule from file/file is: +// >(26.s+30) leshort 0xcafe Java archive data (JAR) +func executableJar(b scan.Bytes) bool { + b.Advance(0x1A) + offset, ok := b.Uint16() + if !ok { return false } - if bytes.HasPrefix(b, sig) { - return true - } + b.Advance(int(offset) + 2) - if msoCheck { - skipFiles := [][]byte{ - []byte("[Content_Types].xml"), - []byte("_rels/.rels"), - []byte("docProps"), - []byte("customXml"), - []byte("[trash]"), - } + cafe, ok := b.Uint16() + return ok && cafe == 0xCAFE +} - hasSkipFile := false - for _, sf := range skipFiles { - if bytes.HasPrefix(b, sf) { - hasSkipFile = true - break - } +// zipIterator iterates over a zip file returning the name of the zip entries +// in that file. +type zipIterator struct { + b scan.Bytes +} + +type zipEntries []struct { + name []byte + dir bool // dir means checking just the prefix of the entry, not the whole path +} + +func (z zipEntries) match(file []byte) bool { + for i := range z { + if z[i].dir && bytes.HasPrefix(file, z[i].name) { + return true } - if !hasSkipFile { - return false + if bytes.Equal(file, z[i].name) { + return true } } + return false +} - searchOffset := binary.LittleEndian.Uint32(raw[18:]) + 49 - if !b.advance(int(searchOffset)) { - return false +func zipHas(raw scan.Bytes, searchFor zipEntries, stopAfter int) bool { + iter := zipIterator{raw} + for i := 0; i < stopAfter; i++ { + f := iter.next() + if len(f) == 0 { + break + } + if searchFor.match(f) { + return true + } } - nextHeader := bytes.Index(raw[searchOffset:], pk) - if !b.advance(nextHeader) { - return false - } - if bytes.HasPrefix(b, sig) { - return true - } + return false +} - for i := 0; i < 4; i++ { - if !b.advance(0x1A) { - return false +// msoxml behaves like zipHas, but it puts restrictions on what the first zip +// entry can be. +func msoxml(raw scan.Bytes, searchFor zipEntries, stopAfter int) bool { + iter := zipIterator{raw} + for i := 0; i < stopAfter; i++ { + f := iter.next() + if len(f) == 0 { + break } - nextHeader = bytes.Index(b, pk) - if nextHeader == -1 { - return false - } - if !b.advance(nextHeader + 0x1E) { - return false - } - if bytes.HasPrefix(b, sig) { + if searchFor.match(f) { return true } + // If the first is not one of the next usually expected entries, + // then abort this check. + if i == 0 { + if !bytes.Equal(f, []byte("[Content_Types].xml")) && + !bytes.Equal(f, []byte("_rels/.rels")) && + !bytes.Equal(f, []byte("docProps")) && + !bytes.Equal(f, []byte("customXml")) && + !bytes.Equal(f, []byte("[trash]")) { + return false + } + } } + return false } -// APK matches an Android Package Archive. -// The source of signatures is https://github.com/file/file/blob/1778642b8ba3d947a779a36fcd81f8e807220a19/magic/Magdir/archive#L1820-L1887 -func APK(raw []byte, _ uint32) bool { - apkSignatures := [][]byte{ - []byte("AndroidManifest.xml"), - []byte("META-INF/com/android/build/gradle/app-metadata.properties"), - []byte("classes.dex"), - []byte("resources.arsc"), - []byte("res/drawable"), +// next extracts the name of the next zip entry. +func (i *zipIterator) next() []byte { + pk := []byte("PK\003\004") + + n := bytes.Index(i.b, pk) + if n == -1 { + return nil } - for _, sig := range apkSignatures { - if zipContains(raw, sig, false) { - return true - } + i.b.Advance(n) + if !i.b.Advance(0x1A) { + return nil + } + l, ok := i.b.Uint16() + if !ok { + return nil + } + if !i.b.Advance(0x02) { + return nil + } + if len(i.b) < int(l) { + return nil } + return i.b[:l] +} - return false +// APK matches an Android Package Archive. +// The source of signatures is https://github.com/file/file/blob/1778642b8ba3d947a779a36fcd81f8e807220a19/magic/Magdir/archive#L1820-L1887 +func APK(raw []byte, _ uint32) bool { + return zipHas(raw, zipEntries{{ + name: []byte("AndroidManifest.xml"), + }, { + name: []byte("META-INF/com/android/build/gradle/app-metadata.properties"), + }, { + name: []byte("classes.dex"), + }, { + name: []byte("resources.arsc"), + }, { + name: []byte("res/drawable"), + }}, 100) } diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/markup/markup.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/markup/markup.go new file mode 100644 index 0000000..937fa1d --- /dev/null +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/markup/markup.go @@ -0,0 +1,103 @@ +// Package markup implements functions for extracting info from +// HTML and XML documents. +package markup + +import ( + "bytes" + + "github.com/gabriel-vasile/mimetype/internal/scan" +) + +func GetAnAttribute(s *scan.Bytes) (name, val string, hasMore bool) { + for scan.ByteIsWS(s.Peek()) || s.Peek() == '/' { + s.Advance(1) + } + if s.Peek() == '>' { + return "", "", false + } + // Allocate 10 to avoid resizes. + // Attribute names and values are continuous slices of bytes in input, + // so we could do without allocating and returning slices of input. + nameB := make([]byte, 0, 10) + // step 4 and 5 + for { + // bap means byte at position in the specification. + bap := s.Pop() + if bap == 0 { + return "", "", false + } + if bap == '=' && len(nameB) > 0 { + val, hasMore := getAValue(s) + return string(nameB), string(val), hasMore + } else if scan.ByteIsWS(bap) { + for scan.ByteIsWS(s.Peek()) { + s.Advance(1) + } + if s.Peek() != '=' { + return string(nameB), "", true + } + s.Advance(1) + for scan.ByteIsWS(s.Peek()) { + s.Advance(1) + } + val, hasMore := getAValue(s) + return string(nameB), string(val), hasMore + } else if bap == '/' || bap == '>' { + return string(nameB), "", false + } else if bap >= 'A' && bap <= 'Z' { + nameB = append(nameB, bap+0x20) + } else { + nameB = append(nameB, bap) + } + } +} + +func getAValue(s *scan.Bytes) (_ []byte, hasMore bool) { + for scan.ByteIsWS(s.Peek()) { + s.Advance(1) + } + origS, end := *s, 0 + bap := s.Pop() + if bap == 0 { + return nil, false + } + end++ + // Step 10 + switch bap { + case '"', '\'': + val := s.PopUntil(bap) + if s.Pop() != bap { + return nil, false + } + return val, s.Peek() != 0 && s.Peek() != '>' + case '>': + return nil, false + } + + // Step 11 + for { + bap = s.Pop() + if bap == 0 { + return nil, false + } + switch { + case scan.ByteIsWS(bap): + return origS[:end], true + case bap == '>': + return origS[:end], false + default: + end++ + } + } +} + +func SkipAComment(s *scan.Bytes) (skipped bool) { + if bytes.HasPrefix(*s, []byte("")); i != -1 { + s.Advance(i + 2 + 3) // 2 comes from len(). + return true + } + } + return false +} diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/internal/scan/bytes.go b/src/vendor/github.com/gabriel-vasile/mimetype/internal/scan/bytes.go new file mode 100644 index 0000000..9f09f07 --- /dev/null +++ b/src/vendor/github.com/gabriel-vasile/mimetype/internal/scan/bytes.go @@ -0,0 +1,213 @@ +// Package scan has functions for scanning byte slices. +package scan + +import ( + "bytes" + "encoding/binary" +) + +// Bytes is a byte slice with helper methods for easier scanning. +type Bytes []byte + +func (b *Bytes) Advance(n int) bool { + if n < 0 || len(*b) < n { + return false + } + *b = (*b)[n:] + return true +} + +// TrimLWS trims whitespace from beginning of the bytes. +func (b *Bytes) TrimLWS() { + firstNonWS := 0 + for ; firstNonWS < len(*b) && ByteIsWS((*b)[firstNonWS]); firstNonWS++ { + } + + *b = (*b)[firstNonWS:] +} + +// TrimRWS trims whitespace from the end of the bytes. +func (b *Bytes) TrimRWS() { + lb := len(*b) + for lb > 0 && ByteIsWS((*b)[lb-1]) { + *b = (*b)[:lb-1] + lb-- + } +} + +// Peek one byte from b or 0x00 if b is empty. +func (b *Bytes) Peek() byte { + if len(*b) > 0 { + return (*b)[0] + } + return 0 +} + +// Pop one byte from b or 0x00 if b is empty. +func (b *Bytes) Pop() byte { + if len(*b) > 0 { + ret := (*b)[0] + *b = (*b)[1:] + return ret + } + return 0 +} + +// PopN pops n bytes from b or nil if b is empty. +func (b *Bytes) PopN(n int) []byte { + if len(*b) >= n { + ret := (*b)[:n] + *b = (*b)[n:] + return ret + } + return nil +} + +// PopUntil will advance b until, but not including, the first occurence of stopAt +// character. If no occurence is found, then it will advance until the end of b. +// The returned Bytes is a slice of all the bytes that we're advanced over. +func (b *Bytes) PopUntil(stopAt ...byte) Bytes { + if len(*b) == 0 { + return Bytes{} + } + i := bytes.IndexAny(*b, string(stopAt)) + if i == -1 { + i = len(*b) + } + + prefix := (*b)[:i] + *b = (*b)[i:] + return Bytes(prefix) +} + +// ReadSlice is the same as PopUntil, but the returned value includes stopAt as well. +func (b *Bytes) ReadSlice(stopAt byte) Bytes { + if len(*b) == 0 { + return Bytes{} + } + i := bytes.IndexByte(*b, stopAt) + if i == -1 { + i = len(*b) + } else { + i++ + } + + prefix := (*b)[:i] + *b = (*b)[i:] + return Bytes(prefix) +} + +// Line returns the first line from b and advances b with the length of the +// line. One new line character is trimmed after the line if it exists. +func (b *Bytes) Line() Bytes { + line := b.PopUntil('\n') + lline := len(line) + if lline > 0 && line[lline-1] == '\r' { + line = line[:lline-1] + } + b.Advance(1) + return line +} + +// DropLastLine drops the last incomplete line from b. +// +// mimetype limits itself to ReadLimit bytes when performing a detection. +// This means, for file formats like CSV for NDJSON, the last line of the input +// can be an incomplete line. +// If b length is less than readLimit, it means we received an incomplete file +// and proceed with dropping the last line. +func (b *Bytes) DropLastLine(readLimit uint32) { + if readLimit == 0 || uint32(len(*b)) < readLimit { + return + } + + for i := len(*b) - 1; i > 0; i-- { + if (*b)[i] == '\n' { + *b = (*b)[:i] + return + } + } +} + +func (b *Bytes) Uint16() (uint16, bool) { + if len(*b) < 2 { + return 0, false + } + v := binary.LittleEndian.Uint16(*b) + *b = (*b)[2:] + return v, true +} + +const ( + CompactWS = 1 << iota + IgnoreCase +) + +// Search for occurences of pattern p inside b at any index. +func (b Bytes) Search(p []byte, flags int) int { + if flags == 0 { + return bytes.Index(b, p) + } + + lb, lp := len(b), len(p) + for i := range b { + if lb-i < lp { + return -1 + } + if b[i:].Match(p, flags) { + return i + } + } + + return 0 +} + +// Match pattern p at index 0 of b. +func (b Bytes) Match(p []byte, flags int) bool { + for len(b) > 0 { + // If we finished all we we're looking for from p. + if len(p) == 0 { + return true + } + if flags&IgnoreCase > 0 && isUpper(p[0]) { + if upper(b[0]) != p[0] { + return false + } + b, p = b[1:], p[1:] + } else if flags&CompactWS > 0 && ByteIsWS(p[0]) { + p = p[1:] + if !ByteIsWS(b[0]) { + return false + } + b = b[1:] + if !ByteIsWS(p[0]) { + b.TrimLWS() + } + } else { + if b[0] != p[0] { + return false + } + b, p = b[1:], p[1:] + } + } + return true +} + +func isUpper(c byte) bool { + return c >= 'A' && c <= 'Z' +} +func upper(c byte) byte { + if c >= 'a' && c <= 'z' { + return c - ('a' - 'A') + } + return c +} + +func ByteIsWS(b byte) bool { + return b == '\t' || b == '\n' || b == '\x0c' || b == '\r' || b == ' ' +} + +var ( + ASCIISpaces = []byte{' ', '\r', '\n', '\x0c', '\t'} + ASCIIDigits = []byte{'0', '1', '2', '3', '4', '5', '6', '7', '8', '9'} +) diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/mime.go b/src/vendor/github.com/gabriel-vasile/mimetype/mime.go index 62cb15f..b82627a 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/mime.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/mime.go @@ -103,15 +103,17 @@ func (m *MIME) match(in []byte, readLimit uint32) *MIME { "text/html": charset.FromHTML, "text/xml": charset.FromXML, } - // ps holds optional MIME parameters. - ps := map[string]string{} + charset := "" if f, ok := needsCharset[m.mime]; ok { - if cset := f(in); cset != "" { - ps["charset"] = cset - } + // The charset comes from BOM, from HTML headers, from XML headers. + // Limit the number of bytes searched for to 1024. + charset = f(in[:min(len(in), 1024)]) + } + if m == root { + return m } - return m.cloneHierarchy(ps) + return m.cloneHierarchy(charset) } // flatten transforms an hierarchy of MIMEs into a slice of MIMEs. @@ -125,10 +127,10 @@ func (m *MIME) flatten() []*MIME { } // clone creates a new MIME with the provided optional MIME parameters. -func (m *MIME) clone(ps map[string]string) *MIME { +func (m *MIME) clone(charset string) *MIME { clonedMIME := m.mime - if len(ps) > 0 { - clonedMIME = mime.FormatMediaType(m.mime, ps) + if charset != "" { + clonedMIME = m.mime + "; charset=" + charset } return &MIME{ @@ -140,11 +142,11 @@ func (m *MIME) clone(ps map[string]string) *MIME { // cloneHierarchy creates a clone of m and all its ancestors. The optional MIME // parameters are set on the last child of the hierarchy. -func (m *MIME) cloneHierarchy(ps map[string]string) *MIME { - ret := m.clone(ps) +func (m *MIME) cloneHierarchy(charset string) *MIME { + ret := m.clone(charset) lastChild := ret for p := m.Parent(); p != nil; p = p.Parent() { - pClone := p.clone(nil) + pClone := p.clone("") lastChild.parent = pClone lastChild = pClone } diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/supported_mimes.md b/src/vendor/github.com/gabriel-vasile/mimetype/supported_mimes.md index 6f45bfb..3186a8b 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/supported_mimes.md +++ b/src/vendor/github.com/gabriel-vasile/mimetype/supported_mimes.md @@ -1,4 +1,4 @@ -## 179 Supported MIME types +## 191 Supported MIME types This file is automatically generated when running tests. Do not edit manually. Extension | MIME type | Aliases @@ -7,12 +7,12 @@ Extension | MIME type | Aliases **.xpm** | image/x-xpixmap | - **.7z** | application/x-7z-compressed | - **.zip** | application/zip | application/x-zip, application/x-zip-compressed -**.xlsx** | application/vnd.openxmlformats-officedocument.spreadsheetml.sheet | - **.docx** | application/vnd.openxmlformats-officedocument.wordprocessingml.document | - **.pptx** | application/vnd.openxmlformats-officedocument.presentationml.presentation | - +**.xlsx** | application/vnd.openxmlformats-officedocument.spreadsheetml.sheet | - **.epub** | application/epub+zip | - **.apk** | application/vnd.android.package-archive | - -**.jar** | application/jar | - +**.jar** | application/java-archive | application/jar, application/jar-archive, application/x-java-archive **.odt** | application/vnd.oasis.opendocument.text | application/x-vnd.oasis.opendocument.text **.ott** | application/vnd.oasis.opendocument.text-template | application/x-vnd.oasis.opendocument.text-template **.ods** | application/vnd.oasis.opendocument.spreadsheet | application/x-vnd.oasis.opendocument.spreadsheet @@ -24,6 +24,8 @@ Extension | MIME type | Aliases **.odf** | application/vnd.oasis.opendocument.formula | application/x-vnd.oasis.opendocument.formula **.odc** | application/vnd.oasis.opendocument.chart | application/x-vnd.oasis.opendocument.chart **.sxc** | application/vnd.sun.xml.calc | - +**.kmz** | application/vnd.google-earth.kmz | - +**.vsdx** | application/vnd.ms-visio.drawing.main+xml | - **.pdf** | application/pdf | application/x-pdf **.fdf** | application/vnd.fdf | - **n/a** | application/x-ole-storage | - @@ -61,9 +63,10 @@ Extension | MIME type | Aliases **.tar** | application/x-tar | - **.xar** | application/x-xar | - **.bz2** | application/x-bzip2 | - -**.fits** | application/fits | - +**.fits** | application/fits | image/fits **.tiff** | image/tiff | - **.bmp** | image/bmp | image/x-bmp, image/x-ms-bmp +**.123** | application/vnd.lotus-1-2-3 | - **.ico** | image/x-icon | - **.mp3** | audio/mpeg | audio/x-mpeg, audio/mp3 **.flac** | audio/flac | - @@ -146,9 +149,11 @@ Extension | MIME type | Aliases **.cab** | application/x-installshield | - **.jxr** | image/jxr | image/vnd.ms-photo **.parquet** | application/vnd.apache.parquet | application/x-parquet +**.one** | application/onenote | - +**.chm** | application/vnd.ms-htmlhelp | - **.txt** | text/plain | - -**.html** | text/html | - **.svg** | image/svg+xml | - +**.html** | text/html | - **.xml** | text/xml | application/xml **.rss** | application/rss+xml | text/rss **.atom** | application/atom+xml | - @@ -163,11 +168,13 @@ Extension | MIME type | Aliases **.3mf** | application/vnd.ms-package.3dmanufacturing-3dmodel+xml | - **.xfdf** | application/vnd.adobe.xfdf | - **.owl** | application/owl+xml | - +**.html** | application/xhtml+xml | - **.php** | text/x-php | - **.js** | text/javascript | application/x-javascript, application/javascript **.lua** | text/x-lua | - **.pl** | text/x-perl | - **.py** | text/x-python | text/x-script.python, application/x-python +**.rb** | text/x-ruby | application/x-ruby **.json** | application/json | - **.geojson** | application/geo+json | - **.har** | application/json | - @@ -182,3 +189,8 @@ Extension | MIME type | Aliases **.ics** | text/calendar | - **.warc** | application/warc | - **.vtt** | text/vtt | - +**.sh** | text/x-shellscript | text/x-sh, application/x-shellscript, application/x-sh +**.pbm** | image/x-portable-bitmap | - +**.pgm** | image/x-portable-graymap | - +**.ppm** | image/x-portable-pixmap | - +**.pam** | image/x-portable-arbitrarymap | - diff --git a/src/vendor/github.com/gabriel-vasile/mimetype/tree.go b/src/vendor/github.com/gabriel-vasile/mimetype/tree.go index 63a2093..edbde89 100644 --- a/src/vendor/github.com/gabriel-vasile/mimetype/tree.go +++ b/src/vendor/github.com/gabriel-vasile/mimetype/tree.go @@ -18,12 +18,13 @@ import ( var root = newMIME("application/octet-stream", "", func([]byte, uint32) bool { return true }, xpm, sevenZ, zip, pdf, fdf, ole, ps, psd, p7s, ogg, png, jpg, jxl, jp2, jpx, - jpm, jxs, gif, webp, exe, elf, ar, tar, xar, bz2, fits, tiff, bmp, ico, mp3, - flac, midi, ape, musePack, amr, wav, aiff, au, mpeg, quickTime, mp4, webM, + jpm, jxs, gif, webp, exe, elf, ar, tar, xar, bz2, fits, tiff, bmp, lotus, ico, + mp3, flac, midi, ape, musePack, amr, wav, aiff, au, mpeg, quickTime, mp4, webM, avi, flv, mkv, asf, aac, voc, m3u, rmvb, gzip, class, swf, crx, ttf, woff, woff2, otf, ttc, eot, wasm, shx, dbf, dcm, rar, djvu, mobi, lit, bpg, cbor, sqlite3, dwg, nes, lnk, macho, qcp, icns, hdr, mrc, mdb, accdb, zstd, cab, rpm, xz, lzip, torrent, cpio, tzif, xcf, pat, gbr, glb, cabIS, jxr, parquet, + oneNote, chm, // Keep text last because it is the slowest check. text, ) @@ -48,22 +49,24 @@ var ( // This means APK should be a child of JAR detector, but in practice, // the decisive signature for JAR might be located at the end of the file // and not reachable because of library readLimit. - zip = newMIME("application/zip", ".zip", magic.Zip, xlsx, docx, pptx, epub, apk, jar, odt, ods, odp, odg, odf, odc, sxc). + zip = newMIME("application/zip", ".zip", magic.Zip, docx, pptx, xlsx, epub, apk, jar, odt, ods, odp, odg, odf, odc, sxc, kmz, visio). alias("application/x-zip", "application/x-zip-compressed") tar = newMIME("application/x-tar", ".tar", magic.Tar) xar = newMIME("application/x-xar", ".xar", magic.Xar) bz2 = newMIME("application/x-bzip2", ".bz2", magic.Bz2) - pdf = newMIME("application/pdf", ".pdf", magic.Pdf). + pdf = newMIME("application/pdf", ".pdf", magic.PDF). alias("application/x-pdf") - fdf = newMIME("application/vnd.fdf", ".fdf", magic.Fdf) - xlsx = newMIME("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", ".xlsx", magic.Xlsx) - docx = newMIME("application/vnd.openxmlformats-officedocument.wordprocessingml.document", ".docx", magic.Docx) - pptx = newMIME("application/vnd.openxmlformats-officedocument.presentationml.presentation", ".pptx", magic.Pptx) - epub = newMIME("application/epub+zip", ".epub", magic.Epub) - jar = newMIME("application/jar", ".jar", magic.Jar) - apk = newMIME("application/vnd.android.package-archive", ".apk", magic.APK) - ole = newMIME("application/x-ole-storage", "", magic.Ole, msi, aaf, msg, xls, pub, ppt, doc) - msi = newMIME("application/x-ms-installer", ".msi", magic.Msi). + fdf = newMIME("application/vnd.fdf", ".fdf", magic.Fdf) + xlsx = newMIME("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", ".xlsx", magic.Xlsx) + docx = newMIME("application/vnd.openxmlformats-officedocument.wordprocessingml.document", ".docx", magic.Docx) + pptx = newMIME("application/vnd.openxmlformats-officedocument.presentationml.presentation", ".pptx", magic.Pptx) + visio = newMIME("application/vnd.ms-visio.drawing.main+xml", ".vsdx", magic.Visio) + epub = newMIME("application/epub+zip", ".epub", magic.Epub) + jar = newMIME("application/java-archive", ".jar", magic.Jar). + alias("application/jar", "application/jar-archive", "application/x-java-archive") + apk = newMIME("application/vnd.android.package-archive", ".apk", magic.APK) + ole = newMIME("application/x-ole-storage", "", magic.Ole, msi, aaf, msg, xls, pub, ppt, doc) + msi = newMIME("application/x-ms-installer", ".msi", magic.Msi). alias("application/x-windows-installer", "application/x-msi") aaf = newMIME("application/octet-stream", ".aaf", magic.Aaf) doc = newMIME("application/msword", ".doc", magic.Doc). @@ -75,18 +78,19 @@ var ( alias("application/msexcel") msg = newMIME("application/vnd.ms-outlook", ".msg", magic.Msg) ps = newMIME("application/postscript", ".ps", magic.Ps) - fits = newMIME("application/fits", ".fits", magic.Fits) + fits = newMIME("application/fits", ".fits", magic.Fits).alias("image/fits") ogg = newMIME("application/ogg", ".ogg", magic.Ogg, oggAudio, oggVideo). alias("application/x-ogg") oggAudio = newMIME("audio/ogg", ".oga", magic.OggAudio) oggVideo = newMIME("video/ogg", ".ogv", magic.OggVideo) - text = newMIME("text/plain", ".txt", magic.Text, html, svg, xml, php, js, lua, perl, python, json, ndJSON, rtf, srt, tcl, csv, tsv, vCard, iCalendar, warc, vtt) - xml = newMIME("text/xml", ".xml", magic.XML, rss, atom, x3d, kml, xliff, collada, gml, gpx, tcx, amf, threemf, xfdf, owl2). + text = newMIME("text/plain", ".txt", magic.Text, svg, html, xml, php, js, lua, perl, python, ruby, json, ndJSON, rtf, srt, tcl, csv, tsv, vCard, iCalendar, warc, vtt, shell, netpbm, netpgm, netppm, netpam) + xml = newMIME("text/xml", ".xml", magic.XML, rss, atom, x3d, kml, xliff, collada, gml, gpx, tcx, amf, threemf, xfdf, owl2, xhtml). alias("application/xml") + xhtml = newMIME("application/xhtml+xml", ".html", magic.XHTML) json = newMIME("application/json", ".json", magic.JSON, geoJSON, har, gltf) har = newMIME("application/json", ".har", magic.HAR) - csv = newMIME("text/csv", ".csv", magic.Csv) - tsv = newMIME("text/tab-separated-values", ".tsv", magic.Tsv) + csv = newMIME("text/csv", ".csv", magic.CSV) + tsv = newMIME("text/tab-separated-values", ".tsv", magic.TSV) geoJSON = newMIME("application/geo+json", ".geojson", magic.GeoJSON) ndJSON = newMIME("application/x-ndjson", ".ndjson", magic.NdJSON) html = newMIME("text/html", ".html", magic.HTML) @@ -101,6 +105,10 @@ var ( perl = newMIME("text/x-perl", ".pl", magic.Perl) python = newMIME("text/x-python", ".py", magic.Python). alias("text/x-script.python", "application/x-python") + ruby = newMIME("text/x-ruby", ".rb", magic.Ruby). + alias("application/x-ruby") + shell = newMIME("text/x-shellscript", ".sh", magic.Shell). + alias("text/x-sh", "application/x-shellscript", "application/x-sh") tcl = newMIME("text/x-tcl", ".tcl", magic.Tcl). alias("application/x-tcl") vCard = newMIME("text/vcard", ".vcf", magic.VCard) @@ -112,6 +120,7 @@ var ( atom = newMIME("application/atom+xml", ".atom", magic.Atom) x3d = newMIME("model/x3d+xml", ".x3d", magic.X3d) kml = newMIME("application/vnd.google-earth.kml+xml", ".kml", magic.Kml) + kmz = newMIME("application/vnd.google-earth.kmz", ".kmz", magic.KMZ) xliff = newMIME("application/x-xliff+xml", ".xlf", magic.Xliff) collada = newMIME("model/vnd.collada+xml", ".dae", magic.Collada) gml = newMIME("application/gml+xml", ".gml", magic.Gml) @@ -135,9 +144,12 @@ var ( tiff = newMIME("image/tiff", ".tiff", magic.Tiff) bmp = newMIME("image/bmp", ".bmp", magic.Bmp). alias("image/x-bmp", "image/x-ms-bmp") - ico = newMIME("image/x-icon", ".ico", magic.Ico) - icns = newMIME("image/x-icns", ".icns", magic.Icns) - psd = newMIME("image/vnd.adobe.photoshop", ".psd", magic.Psd). + // lotus check must be done before ico because some ico detection is a bit + // relaxed and some lotus files are wrongfully identified as ico otherwise. + lotus = newMIME("application/vnd.lotus-1-2-3", ".123", magic.Lotus123) + ico = newMIME("image/x-icon", ".ico", magic.Ico) + icns = newMIME("image/x-icns", ".icns", magic.Icns) + psd = newMIME("image/vnd.adobe.photoshop", ".psd", magic.Psd). alias("image/x-psd", "application/photoshop") heic = newMIME("image/heic", ".heic", magic.Heic) heicSeq = newMIME("image/heic-sequence", ".heic", magic.HeicSequence) @@ -267,5 +279,11 @@ var ( jxr = newMIME("image/jxr", ".jxr", magic.Jxr).alias("image/vnd.ms-photo") parquet = newMIME("application/vnd.apache.parquet", ".parquet", magic.Par1). alias("application/x-parquet") - cbor = newMIME("application/cbor", ".cbor", magic.CBOR) + netpbm = newMIME("image/x-portable-bitmap", ".pbm", magic.NetPBM) + netpgm = newMIME("image/x-portable-graymap", ".pgm", magic.NetPGM) + netppm = newMIME("image/x-portable-pixmap", ".ppm", magic.NetPPM) + netpam = newMIME("image/x-portable-arbitrarymap", ".pam", magic.NetPAM) + cbor = newMIME("application/cbor", ".cbor", magic.CBOR) + oneNote = newMIME("application/onenote", ".one", magic.One) + chm = newMIME("application/vnd.ms-htmlhelp", ".chm", magic.CHM) ) diff --git a/src/vendor/github.com/go-playground/validator/v10/README.md b/src/vendor/github.com/go-playground/validator/v10/README.md index 28f7e15..cb5d419 100644 --- a/src/vendor/github.com/go-playground/validator/v10/README.md +++ b/src/vendor/github.com/go-playground/validator/v10/README.md @@ -106,8 +106,9 @@ validate := validator.New(validator.WithRequiredStructEnabled()) | datauri | Data URL | | fqdn | Full Qualified Domain Name (FQDN) | | hostname | Hostname RFC 952 | -| hostname_port | HostPort | | hostname_rfc1123 | Hostname RFC 1123 | +| hostname_port | HostPort | +| port | Port number | | ip | Internet Protocol Address IP | | ip4_addr | Internet Protocol Address IPv4 | | ip6_addr | Internet Protocol Address IPv6 | @@ -124,7 +125,8 @@ validate := validator.New(validator.WithRequiredStructEnabled()) | unix_addr | Unix domain socket end point Address | | uri | URI String | | url | URL String | -| http_url | HTTP URL String | +| http_url | HTTP(s) URL String | +| https_url | HTTPS-only URL String | | url_encoded | URL Encoded | | urn_rfc2141 | Urn RFC 2141 String | @@ -133,6 +135,7 @@ validate := validator.New(validator.WithRequiredStructEnabled()) | Tag | Description | | - | - | | alpha | Alpha Only | +| alphaspace | Alpha Space | | alphanum | Alphanumeric | | alphanumunicode | Alphanumeric Unicode | | alphaunicode | Alpha Unicode | diff --git a/src/vendor/github.com/go-playground/validator/v10/baked_in.go b/src/vendor/github.com/go-playground/validator/v10/baked_in.go index c968ad4..8fd55e7 100644 --- a/src/vendor/github.com/go-playground/validator/v10/baked_in.go +++ b/src/vendor/github.com/go-playground/validator/v10/baked_in.go @@ -118,6 +118,7 @@ var ( "fieldcontains": fieldContains, "fieldexcludes": fieldExcludes, "alpha": isAlpha, + "alphaspace": isAlphaSpace, "alphanum": isAlphanum, "alphaunicode": isAlphaUnicode, "alphanumunicode": isAlphanumUnicode, @@ -134,6 +135,7 @@ var ( "email": isEmail, "url": isURL, "http_url": isHttpURL, + "https_url": isHttpsURL, "uri": isURI, "urn_rfc2141": isUrnRFC2141, // RFC 2141 "file": isFile, @@ -1513,6 +1515,29 @@ func isHttpURL(fl FieldLevel) bool { panic(fmt.Sprintf("Bad field type %s", field.Type())) } +// isHttpsURL is the validation function for validating if the current field's value is a valid HTTPS-only URL. +func isHttpsURL(fl FieldLevel) bool { + if !isURL(fl) { + return false + } + + field := fl.Field() + switch field.Kind() { + case reflect.String: + + s := strings.ToLower(field.String()) + + url, err := url.Parse(s) + if err != nil || url.Host == "" { + return false + } + + return url.Scheme == "https" + } + + panic(fmt.Sprintf("Bad field type %s", field.Type())) +} + // isUrnRFC2141 is the validation function for validating if the current field's value is a valid URN as per RFC 2141. func isUrnRFC2141(fl FieldLevel) bool { field := fl.Field() @@ -1743,6 +1768,11 @@ func isAlphanumUnicode(fl FieldLevel) bool { return alphaUnicodeNumericRegex().MatchString(fl.Field().String()) } +// isAlphaSpace is the validation function for validating if the current field's value is a valid alpha value with spaces. +func isAlphaSpace(fl FieldLevel) bool { + return alphaSpaceRegex().MatchString(fl.Field().String()) +} + // isAlphaUnicode is the validation function for validating if the current field's value is a valid alpha unicode value. func isAlphaUnicode(fl FieldLevel) bool { return alphaUnicodeRegex().MatchString(fl.Field().String()) @@ -1872,6 +1902,15 @@ func requiredIf(fl FieldLevel) bool { if len(params)%2 != 0 { panic(fmt.Sprintf("Bad param number for required_if %s", fl.FieldName())) } + + seen := make(map[string]struct{}) + for i := 0; i < len(params); i += 2 { + if _, ok := seen[params[i]]; ok { + panic(fmt.Sprintf("Duplicate param %s for required_if %s", params[i], fl.FieldName())) + } + seen[params[i]] = struct{}{} + } + for i := 0; i < len(params); i += 2 { if !requireCheckFieldValue(fl, params[i], params[i+1], false) { return true diff --git a/src/vendor/github.com/go-playground/validator/v10/doc.go b/src/vendor/github.com/go-playground/validator/v10/doc.go index 23cce99..52918e4 100644 --- a/src/vendor/github.com/go-playground/validator/v10/doc.go +++ b/src/vendor/github.com/go-playground/validator/v10/doc.go @@ -264,6 +264,7 @@ The field under validation must be present and not empty only if all the other specified fields are equal to the value following the specified field. For strings ensures value is not "". For slices, maps, pointers, interfaces, channels and functions ensures the value is not nil. For structs ensures value is not the zero value. +Using the same field name multiple times in the parameters will result in a panic at runtime. Usage: required_if @@ -776,6 +777,12 @@ This validates that a string value contains ASCII alpha characters only Usage: alpha +# Alpha Space + +This validates that a string value contains ASCII alpha characters and spaces only + + Usage: alphaspace + # Alphanumeric This validates that a string value contains ASCII alphanumeric characters only @@ -1330,6 +1337,12 @@ can be used to validate fields typically passed to sockets and connections. Usage: hostname_port +# Port + +This validates that the value falls within the valid port number range of 1 to 65,535. + + Usage: port + # Datetime This validates that a string value is a valid datetime based on the supplied datetime format. diff --git a/src/vendor/github.com/go-playground/validator/v10/regexes.go b/src/vendor/github.com/go-playground/validator/v10/regexes.go index 93909b2..0b3615f 100644 --- a/src/vendor/github.com/go-playground/validator/v10/regexes.go +++ b/src/vendor/github.com/go-playground/validator/v10/regexes.go @@ -7,6 +7,7 @@ import ( const ( alphaRegexString = "^[a-zA-Z]+$" + alphaSpaceRegexString = "^[a-zA-Z ]+$" alphaNumericRegexString = "^[a-zA-Z0-9]+$" alphaUnicodeRegexString = "^[\\p{L}]+$" alphaUnicodeNumericRegexString = "^[\\p{L}\\p{N}]+$" @@ -93,6 +94,7 @@ func lazyRegexCompile(str string) func() *regexp.Regexp { var ( alphaRegex = lazyRegexCompile(alphaRegexString) + alphaSpaceRegex = lazyRegexCompile(alphaSpaceRegexString) alphaNumericRegex = lazyRegexCompile(alphaNumericRegexString) alphaUnicodeRegex = lazyRegexCompile(alphaUnicodeRegexString) alphaUnicodeNumericRegex = lazyRegexCompile(alphaUnicodeNumericRegexString) diff --git a/src/vendor/github.com/go-playground/validator/v10/validator_instance.go b/src/vendor/github.com/go-playground/validator/v10/validator_instance.go index 9362cd7..5ba64e5 100644 --- a/src/vendor/github.com/go-playground/validator/v10/validator_instance.go +++ b/src/vendor/github.com/go-playground/validator/v10/validator_instance.go @@ -181,7 +181,7 @@ func (v Validate) ValidateMapCtx(ctx context.Context, data map[string]interface{ errs[field] = errors.New("The field: '" + field + "' is not a map to dive") } } else if ruleStr, ok := rule.(string); ok { - err := v.VarCtx(ctx, data[field], ruleStr) + err := v.VarWithKeyCtx(ctx, field, data[field], ruleStr) if err != nil { errs[field] = err } @@ -681,6 +681,64 @@ func (v *Validate) VarWithValueCtx(ctx context.Context, field interface{}, other return } +// VarWithKey validates a single variable with a key to be included in the returned error using tag style validation +// eg. +// var s string +// validate.VarWithKey("email_address", s, "required,email") +// +// WARNING: a struct can be passed for validation eg. time.Time is a struct or +// if you have a custom type and have registered a custom type handler, so must +// allow it; however unforeseen validations will occur if trying to validate a +// struct that is meant to be passed to 'validate.Struct' +// +// It returns InvalidValidationError for bad values passed in and nil or ValidationErrors as error otherwise. +// You will need to assert the error if it's not nil eg. err.(validator.ValidationErrors) to access the array of errors. +// validate Array, Slice and maps fields which may contain more than one error +func (v *Validate) VarWithKey(key string, field interface{}, tag string) error { + return v.VarWithKeyCtx(context.Background(), key, field, tag) +} + +// VarWithKeyCtx validates a single variable with a key to be included in the returned error using tag style validation +// and allows passing of contextual validation information via context.Context. +// eg. +// var s string +// validate.VarWithKeyCtx("email_address", s, "required,email") +// +// WARNING: a struct can be passed for validation eg. time.Time is a struct or +// if you have a custom type and have registered a custom type handler, so must +// allow it; however unforeseen validations will occur if trying to validate a +// struct that is meant to be passed to 'validate.Struct' +// +// It returns InvalidValidationError for bad values passed in and nil or ValidationErrors as error otherwise. +// You will need to assert the error if it's not nil eg. err.(validator.ValidationErrors) to access the array of errors. +// validate Array, Slice and maps fields which may contain more than one error +func (v *Validate) VarWithKeyCtx(ctx context.Context, key string, field interface{}, tag string) (err error) { + if len(tag) == 0 || tag == skipValidationTag { + return nil + } + + ctag := v.fetchCacheTag(tag) + + cField := &cField{ + name: key, + altName: key, + namesEqual: true, + } + + val := reflect.ValueOf(field) + vd := v.pool.Get().(*validate) + vd.top = val + vd.isPartial = false + vd.traverseField(ctx, val, val, vd.ns[0:0], vd.actualNs[0:0], cField, ctag) + + if len(vd.errs) > 0 { + err = vd.errs + vd.errs = nil + } + v.pool.Put(vd) + return +} + func (v *Validate) registerValidation(tag string, fn FuncCtx, bakedIn bool, nilCheckable bool) error { if len(tag) == 0 { return errors.New("function Key cannot be empty") diff --git a/src/vendor/golang.org/x/net/LICENSE b/src/vendor/golang.org/x/net/LICENSE deleted file mode 100644 index 2a7cf70..0000000 --- a/src/vendor/golang.org/x/net/LICENSE +++ /dev/null @@ -1,27 +0,0 @@ -Copyright 2009 The Go Authors. - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are -met: - - * Redistributions of source code must retain the above copyright -notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above -copyright notice, this list of conditions and the following disclaimer -in the documentation and/or other materials provided with the -distribution. - * Neither the name of Google LLC nor the names of its -contributors may be used to endorse or promote products derived from -this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/src/vendor/golang.org/x/net/PATENTS b/src/vendor/golang.org/x/net/PATENTS deleted file mode 100644 index 7330990..0000000 --- a/src/vendor/golang.org/x/net/PATENTS +++ /dev/null @@ -1,22 +0,0 @@ -Additional IP Rights Grant (Patents) - -"This implementation" means the copyrightable works distributed by -Google as part of the Go project. - -Google 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, -transfer and otherwise run, modify and propagate the contents of this -implementation of Go, where such license applies only to those patent -claims, both currently owned or controlled by Google and acquired in -the future, licensable by Google that are necessarily infringed by this -implementation of Go. This grant does not include claims that would be -infringed only as a consequence of further modification of this -implementation. If you or your agent or exclusive licensee institute or -order or agree to the institution of patent litigation against any -entity (including a cross-claim or counterclaim in a lawsuit) alleging -that this implementation of Go or any code incorporated within this -implementation of Go constitutes direct or contributory patent -infringement, or inducement of patent infringement, then any patent -rights granted to you under this License for this implementation of Go -shall terminate as of the date such litigation is filed. diff --git a/src/vendor/golang.org/x/net/html/atom/atom.go b/src/vendor/golang.org/x/net/html/atom/atom.go deleted file mode 100644 index cd0a8ac..0000000 --- a/src/vendor/golang.org/x/net/html/atom/atom.go +++ /dev/null @@ -1,78 +0,0 @@ -// Copyright 2012 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -// Package atom provides integer codes (also known as atoms) for a fixed set of -// frequently occurring HTML strings: tag names and attribute keys such as "p" -// and "id". -// -// Sharing an atom's name between all elements with the same tag can result in -// fewer string allocations when tokenizing and parsing HTML. Integer -// comparisons are also generally faster than string comparisons. -// -// The value of an atom's particular code is not guaranteed to stay the same -// between versions of this package. Neither is any ordering guaranteed: -// whether atom.H1 < atom.H2 may also change. The codes are not guaranteed to -// be dense. The only guarantees are that e.g. looking up "div" will yield -// atom.Div, calling atom.Div.String will return "div", and atom.Div != 0. -package atom // import "golang.org/x/net/html/atom" - -// Atom is an integer code for a string. The zero value maps to "". -type Atom uint32 - -// String returns the atom's name. -func (a Atom) String() string { - start := uint32(a >> 8) - n := uint32(a & 0xff) - if start+n > uint32(len(atomText)) { - return "" - } - return atomText[start : start+n] -} - -func (a Atom) string() string { - return atomText[a>>8 : a>>8+a&0xff] -} - -// fnv computes the FNV hash with an arbitrary starting value h. -func fnv(h uint32, s []byte) uint32 { - for i := range s { - h ^= uint32(s[i]) - h *= 16777619 - } - return h -} - -func match(s string, t []byte) bool { - for i, c := range t { - if s[i] != c { - return false - } - } - return true -} - -// Lookup returns the atom whose name is s. It returns zero if there is no -// such atom. The lookup is case sensitive. -func Lookup(s []byte) Atom { - if len(s) == 0 || len(s) > maxAtomLen { - return 0 - } - h := fnv(hash0, s) - if a := table[h&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) { - return a - } - if a := table[(h>>16)&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) { - return a - } - return 0 -} - -// String returns a string whose contents are equal to s. In that sense, it is -// equivalent to string(s) but may be more efficient. -func String(s []byte) string { - if a := Lookup(s); a != 0 { - return a.String() - } - return string(s) -} diff --git a/src/vendor/golang.org/x/net/html/atom/table.go b/src/vendor/golang.org/x/net/html/atom/table.go deleted file mode 100644 index b460e6f..0000000 --- a/src/vendor/golang.org/x/net/html/atom/table.go +++ /dev/null @@ -1,785 +0,0 @@ -// Code generated by go generate gen.go; DO NOT EDIT. - -//go:generate go run gen.go - -package atom - -const ( - A Atom = 0x1 - Abbr Atom = 0x4 - Accept Atom = 0x1a06 - AcceptCharset Atom = 0x1a0e - Accesskey Atom = 0x2c09 - Acronym Atom = 0xaa07 - Action Atom = 0x26506 - Address Atom = 0x6f107 - Align Atom = 0xb105 - Allowfullscreen Atom = 0x3280f - Allowpaymentrequest Atom = 0xc113 - Allowusermedia Atom = 0xdd0e - Alt Atom = 0xf303 - Annotation Atom = 0x1c90a - AnnotationXml Atom = 0x1c90e - Applet Atom = 0x30806 - Area Atom = 0x35004 - Article Atom = 0x3f607 - As Atom = 0x3c02 - Aside Atom = 0x10705 - Async Atom = 0xff05 - Audio Atom = 0x11505 - Autocomplete Atom = 0x26b0c - Autofocus Atom = 0x12109 - Autoplay Atom = 0x13c08 - B Atom = 0x101 - Base Atom = 0x3b04 - Basefont Atom = 0x3b08 - Bdi Atom = 0xba03 - Bdo Atom = 0x14b03 - Bgsound Atom = 0x15e07 - Big Atom = 0x17003 - Blink Atom = 0x17305 - Blockquote Atom = 0x1870a - Body Atom = 0x2804 - Br Atom = 0x202 - Button Atom = 0x19106 - Canvas Atom = 0x10306 - Caption Atom = 0x22407 - Center Atom = 0x21306 - Challenge Atom = 0x28e09 - Charset Atom = 0x2107 - Checked Atom = 0x5b507 - Cite Atom = 0x19c04 - Class Atom = 0x55805 - Code Atom = 0x5ee04 - Col Atom = 0x1ab03 - Colgroup Atom = 0x1ab08 - Color Atom = 0x1bf05 - Cols Atom = 0x1c404 - Colspan Atom = 0x1c407 - Command Atom = 0x1d707 - Content Atom = 0x57b07 - Contenteditable Atom = 0x57b0f - Contextmenu Atom = 0x37a0b - Controls Atom = 0x1de08 - Coords Atom = 0x1f006 - Crossorigin Atom = 0x1fa0b - Data Atom = 0x49904 - Datalist Atom = 0x49908 - Datetime Atom = 0x2ab08 - Dd Atom = 0x2bf02 - Default Atom = 0x10a07 - Defer Atom = 0x5f005 - Del Atom = 0x44c03 - Desc Atom = 0x55504 - Details Atom = 0x7207 - Dfn Atom = 0x8703 - Dialog Atom = 0xbb06 - Dir Atom = 0x9303 - Dirname Atom = 0x9307 - Disabled Atom = 0x16408 - Div Atom = 0x16b03 - Dl Atom = 0x5d602 - Download Atom = 0x45d08 - Draggable Atom = 0x17a09 - Dropzone Atom = 0x3ff08 - Dt Atom = 0x64002 - Em Atom = 0x6e02 - Embed Atom = 0x6e05 - Enctype Atom = 0x28007 - Face Atom = 0x21104 - Fieldset Atom = 0x21908 - Figcaption Atom = 0x2210a - Figure Atom = 0x23b06 - Font Atom = 0x3f04 - Footer Atom = 0xf606 - For Atom = 0x24703 - ForeignObject Atom = 0x2470d - Foreignobject Atom = 0x2540d - Form Atom = 0x26104 - Formaction Atom = 0x2610a - Formenctype Atom = 0x27c0b - Formmethod Atom = 0x2970a - Formnovalidate Atom = 0x2a10e - Formtarget Atom = 0x2b30a - Frame Atom = 0x8b05 - Frameset Atom = 0x8b08 - H1 Atom = 0x15c02 - H2 Atom = 0x56102 - H3 Atom = 0x2cd02 - H4 Atom = 0x2fc02 - H5 Atom = 0x33f02 - H6 Atom = 0x34902 - Head Atom = 0x32004 - Header Atom = 0x32006 - Headers Atom = 0x32007 - Height Atom = 0x5206 - Hgroup Atom = 0x64206 - Hidden Atom = 0x2bd06 - High Atom = 0x2ca04 - Hr Atom = 0x15702 - Href Atom = 0x2cf04 - Hreflang Atom = 0x2cf08 - Html Atom = 0x5604 - HttpEquiv Atom = 0x2d70a - I Atom = 0x601 - Icon Atom = 0x57a04 - Id Atom = 0x10902 - Iframe Atom = 0x2eb06 - Image Atom = 0x2f105 - Img Atom = 0x2f603 - Input Atom = 0x44505 - Inputmode Atom = 0x44509 - Ins Atom = 0x20303 - Integrity Atom = 0x23209 - Is Atom = 0x16502 - Isindex Atom = 0x2fe07 - Ismap Atom = 0x30505 - Itemid Atom = 0x38506 - Itemprop Atom = 0x19d08 - Itemref Atom = 0x3c707 - Itemscope Atom = 0x66f09 - Itemtype Atom = 0x30e08 - Kbd Atom = 0xb903 - Keygen Atom = 0x3206 - Keytype Atom = 0xd607 - Kind Atom = 0x17704 - Label Atom = 0x5905 - Lang Atom = 0x2d304 - Legend Atom = 0x18106 - Li Atom = 0xb202 - Link Atom = 0x17404 - List Atom = 0x49d04 - Listing Atom = 0x49d07 - Loop Atom = 0x5d04 - Low Atom = 0xc303 - Main Atom = 0x1004 - Malignmark Atom = 0xb00a - Manifest Atom = 0x6d508 - Map Atom = 0x30703 - Mark Atom = 0xb604 - Marquee Atom = 0x31607 - Math Atom = 0x31d04 - Max Atom = 0x33703 - Maxlength Atom = 0x33709 - Media Atom = 0xe605 - Mediagroup Atom = 0xe60a - Menu Atom = 0x38104 - Menuitem Atom = 0x38108 - Meta Atom = 0x4ac04 - Meter Atom = 0x9805 - Method Atom = 0x29b06 - Mglyph Atom = 0x2f706 - Mi Atom = 0x34102 - Min Atom = 0x34103 - Minlength Atom = 0x34109 - Mn Atom = 0x2a402 - Mo Atom = 0xa402 - Ms Atom = 0x67202 - Mtext Atom = 0x34b05 - Multiple Atom = 0x35908 - Muted Atom = 0x36105 - Name Atom = 0x9604 - Nav Atom = 0x1303 - Nobr Atom = 0x3704 - Noembed Atom = 0x6c07 - Noframes Atom = 0x8908 - Nomodule Atom = 0xa208 - Nonce Atom = 0x1a605 - Noscript Atom = 0x2c208 - Novalidate Atom = 0x2a50a - Object Atom = 0x25b06 - Ol Atom = 0x13702 - Onabort Atom = 0x19507 - Onafterprint Atom = 0x2290c - Onautocomplete Atom = 0x2690e - Onautocompleteerror Atom = 0x26913 - Onauxclick Atom = 0x6140a - Onbeforeprint Atom = 0x69c0d - Onbeforeunload Atom = 0x6e50e - Onblur Atom = 0x1ea06 - Oncancel Atom = 0x11908 - Oncanplay Atom = 0x14d09 - Oncanplaythrough Atom = 0x14d10 - Onchange Atom = 0x41508 - Onclick Atom = 0x2e407 - Onclose Atom = 0x36607 - Oncontextmenu Atom = 0x3780d - Oncopy Atom = 0x38b06 - Oncuechange Atom = 0x3910b - Oncut Atom = 0x39c05 - Ondblclick Atom = 0x3a10a - Ondrag Atom = 0x3ab06 - Ondragend Atom = 0x3ab09 - Ondragenter Atom = 0x3b40b - Ondragexit Atom = 0x3bf0a - Ondragleave Atom = 0x3d90b - Ondragover Atom = 0x3e40a - Ondragstart Atom = 0x3ee0b - Ondrop Atom = 0x3fd06 - Ondurationchange Atom = 0x40d10 - Onemptied Atom = 0x40409 - Onended Atom = 0x41d07 - Onerror Atom = 0x42407 - Onfocus Atom = 0x42b07 - Onhashchange Atom = 0x4370c - Oninput Atom = 0x44307 - Oninvalid Atom = 0x44f09 - Onkeydown Atom = 0x45809 - Onkeypress Atom = 0x4650a - Onkeyup Atom = 0x47407 - Onlanguagechange Atom = 0x48110 - Onload Atom = 0x49106 - Onloadeddata Atom = 0x4910c - Onloadedmetadata Atom = 0x4a410 - Onloadend Atom = 0x4ba09 - Onloadstart Atom = 0x4c30b - Onmessage Atom = 0x4ce09 - Onmessageerror Atom = 0x4ce0e - Onmousedown Atom = 0x4dc0b - Onmouseenter Atom = 0x4e70c - Onmouseleave Atom = 0x4f30c - Onmousemove Atom = 0x4ff0b - Onmouseout Atom = 0x50a0a - Onmouseover Atom = 0x5170b - Onmouseup Atom = 0x52209 - Onmousewheel Atom = 0x5300c - Onoffline Atom = 0x53c09 - Ononline Atom = 0x54508 - Onpagehide Atom = 0x54d0a - Onpageshow Atom = 0x5630a - Onpaste Atom = 0x56f07 - Onpause Atom = 0x58a07 - Onplay Atom = 0x59406 - Onplaying Atom = 0x59409 - Onpopstate Atom = 0x59d0a - Onprogress Atom = 0x5a70a - Onratechange Atom = 0x5bc0c - Onrejectionhandled Atom = 0x5c812 - Onreset Atom = 0x5da07 - Onresize Atom = 0x5e108 - Onscroll Atom = 0x5f508 - Onsecuritypolicyviolation Atom = 0x5fd19 - Onseeked Atom = 0x61e08 - Onseeking Atom = 0x62609 - Onselect Atom = 0x62f08 - Onshow Atom = 0x63906 - Onsort Atom = 0x64d06 - Onstalled Atom = 0x65709 - Onstorage Atom = 0x66009 - Onsubmit Atom = 0x66908 - Onsuspend Atom = 0x67909 - Ontimeupdate Atom = 0x400c - Ontoggle Atom = 0x68208 - Onunhandledrejection Atom = 0x68a14 - Onunload Atom = 0x6a908 - Onvolumechange Atom = 0x6b10e - Onwaiting Atom = 0x6bf09 - Onwheel Atom = 0x6c807 - Open Atom = 0x1a304 - Optgroup Atom = 0x5f08 - Optimum Atom = 0x6cf07 - Option Atom = 0x6e106 - Output Atom = 0x51106 - P Atom = 0xc01 - Param Atom = 0xc05 - Pattern Atom = 0x6607 - Picture Atom = 0x7b07 - Ping Atom = 0xef04 - Placeholder Atom = 0x1310b - Plaintext Atom = 0x1b209 - Playsinline Atom = 0x1400b - Poster Atom = 0x64706 - Pre Atom = 0x46a03 - Preload Atom = 0x47a07 - Progress Atom = 0x5a908 - Prompt Atom = 0x52a06 - Public Atom = 0x57606 - Q Atom = 0xcf01 - Radiogroup Atom = 0x30a - Rb Atom = 0x3a02 - Readonly Atom = 0x35108 - Referrerpolicy Atom = 0x3cb0e - Rel Atom = 0x47b03 - Required Atom = 0x23f08 - Reversed Atom = 0x8008 - Rows Atom = 0x9c04 - Rowspan Atom = 0x9c07 - Rp Atom = 0x22f02 - Rt Atom = 0x19a02 - Rtc Atom = 0x19a03 - Ruby Atom = 0xfb04 - S Atom = 0x2501 - Samp Atom = 0x7804 - Sandbox Atom = 0x12907 - Scope Atom = 0x67305 - Scoped Atom = 0x67306 - Script Atom = 0x2c406 - Seamless Atom = 0x36b08 - Search Atom = 0x55c06 - Section Atom = 0x1e507 - Select Atom = 0x63106 - Selected Atom = 0x63108 - Shape Atom = 0x1f505 - Size Atom = 0x5e504 - Sizes Atom = 0x5e505 - Slot Atom = 0x20504 - Small Atom = 0x32605 - Sortable Atom = 0x64f08 - Sorted Atom = 0x37206 - Source Atom = 0x43106 - Spacer Atom = 0x46e06 - Span Atom = 0x9f04 - Spellcheck Atom = 0x5b00a - Src Atom = 0x5e903 - Srcdoc Atom = 0x5e906 - Srclang Atom = 0x6f707 - Srcset Atom = 0x6fe06 - Start Atom = 0x3f405 - Step Atom = 0x57304 - Strike Atom = 0xd206 - Strong Atom = 0x6db06 - Style Atom = 0x70405 - Sub Atom = 0x66b03 - Summary Atom = 0x70907 - Sup Atom = 0x71003 - Svg Atom = 0x71303 - System Atom = 0x71606 - Tabindex Atom = 0x4b208 - Table Atom = 0x58505 - Target Atom = 0x2b706 - Tbody Atom = 0x2705 - Td Atom = 0x9202 - Template Atom = 0x71908 - Textarea Atom = 0x34c08 - Tfoot Atom = 0xf505 - Th Atom = 0x15602 - Thead Atom = 0x31f05 - Time Atom = 0x4204 - Title Atom = 0x11005 - Tr Atom = 0xcc02 - Track Atom = 0x1ba05 - Translate Atom = 0x20809 - Tt Atom = 0x6802 - Type Atom = 0xd904 - Typemustmatch Atom = 0x2830d - U Atom = 0xb01 - Ul Atom = 0xa702 - Updateviacache Atom = 0x460e - Usemap Atom = 0x58e06 - Value Atom = 0x1505 - Var Atom = 0x16d03 - Video Atom = 0x2e005 - Wbr Atom = 0x56c03 - Width Atom = 0x63e05 - Workertype Atom = 0x7210a - Wrap Atom = 0x72b04 - Xmp Atom = 0x12f03 -) - -const hash0 = 0x84f70e16 - -const maxAtomLen = 25 - -var table = [1 << 9]Atom{ - 0x1: 0x3ff08, // dropzone - 0x2: 0x3b08, // basefont - 0x3: 0x23209, // integrity - 0x4: 0x43106, // source - 0x5: 0x2c09, // accesskey - 0x6: 0x1a06, // accept - 0x7: 0x6c807, // onwheel - 0xb: 0x47407, // onkeyup - 0xc: 0x32007, // headers - 0xd: 0x67306, // scoped - 0xe: 0x67909, // onsuspend - 0xf: 0x8908, // noframes - 0x10: 0x1fa0b, // crossorigin - 0x11: 0x2e407, // onclick - 0x12: 0x3f405, // start - 0x13: 0x37a0b, // contextmenu - 0x14: 0x5e903, // src - 0x15: 0x1c404, // cols - 0x16: 0xbb06, // dialog - 0x17: 0x47a07, // preload - 0x18: 0x3c707, // itemref - 0x1b: 0x2f105, // image - 0x1d: 0x4ba09, // onloadend - 0x1e: 0x45d08, // download - 0x1f: 0x46a03, // pre - 0x23: 0x2970a, // formmethod - 0x24: 0x71303, // svg - 0x25: 0xcf01, // q - 0x26: 0x64002, // dt - 0x27: 0x1de08, // controls - 0x2a: 0x2804, // body - 0x2b: 0xd206, // strike - 0x2c: 0x3910b, // oncuechange - 0x2d: 0x4c30b, // onloadstart - 0x2e: 0x2fe07, // isindex - 0x2f: 0xb202, // li - 0x30: 0x1400b, // playsinline - 0x31: 0x34102, // mi - 0x32: 0x30806, // applet - 0x33: 0x4ce09, // onmessage - 0x35: 0x13702, // ol - 0x36: 0x1a304, // open - 0x39: 0x14d09, // oncanplay - 0x3a: 0x6bf09, // onwaiting - 0x3b: 0x11908, // oncancel - 0x3c: 0x6a908, // onunload - 0x3e: 0x53c09, // onoffline - 0x3f: 0x1a0e, // accept-charset - 0x40: 0x32004, // head - 0x42: 0x3ab09, // ondragend - 0x43: 0x1310b, // placeholder - 0x44: 0x2b30a, // formtarget - 0x45: 0x2540d, // foreignobject - 0x47: 0x400c, // ontimeupdate - 0x48: 0xdd0e, // allowusermedia - 0x4a: 0x69c0d, // onbeforeprint - 0x4b: 0x5604, // html - 0x4c: 0x9f04, // span - 0x4d: 0x64206, // hgroup - 0x4e: 0x16408, // disabled - 0x4f: 0x4204, // time - 0x51: 0x42b07, // onfocus - 0x53: 0xb00a, // malignmark - 0x55: 0x4650a, // onkeypress - 0x56: 0x55805, // class - 0x57: 0x1ab08, // colgroup - 0x58: 0x33709, // maxlength - 0x59: 0x5a908, // progress - 0x5b: 0x70405, // style - 0x5c: 0x2a10e, // formnovalidate - 0x5e: 0x38b06, // oncopy - 0x60: 0x26104, // form - 0x61: 0xf606, // footer - 0x64: 0x30a, // radiogroup - 0x66: 0xfb04, // ruby - 0x67: 0x4ff0b, // onmousemove - 0x68: 0x19d08, // itemprop - 0x69: 0x2d70a, // http-equiv - 0x6a: 0x15602, // th - 0x6c: 0x6e02, // em - 0x6d: 0x38108, // menuitem - 0x6e: 0x63106, // select - 0x6f: 0x48110, // onlanguagechange - 0x70: 0x31f05, // thead - 0x71: 0x15c02, // h1 - 0x72: 0x5e906, // srcdoc - 0x75: 0x9604, // name - 0x76: 0x19106, // button - 0x77: 0x55504, // desc - 0x78: 0x17704, // kind - 0x79: 0x1bf05, // color - 0x7c: 0x58e06, // usemap - 0x7d: 0x30e08, // itemtype - 0x7f: 0x6d508, // manifest - 0x81: 0x5300c, // onmousewheel - 0x82: 0x4dc0b, // onmousedown - 0x84: 0xc05, // param - 0x85: 0x2e005, // video - 0x86: 0x4910c, // onloadeddata - 0x87: 0x6f107, // address - 0x8c: 0xef04, // ping - 0x8d: 0x24703, // for - 0x8f: 0x62f08, // onselect - 0x90: 0x30703, // map - 0x92: 0xc01, // p - 0x93: 0x8008, // reversed - 0x94: 0x54d0a, // onpagehide - 0x95: 0x3206, // keygen - 0x96: 0x34109, // minlength - 0x97: 0x3e40a, // ondragover - 0x98: 0x42407, // onerror - 0x9a: 0x2107, // charset - 0x9b: 0x29b06, // method - 0x9c: 0x101, // b - 0x9d: 0x68208, // ontoggle - 0x9e: 0x2bd06, // hidden - 0xa0: 0x3f607, // article - 0xa2: 0x63906, // onshow - 0xa3: 0x64d06, // onsort - 0xa5: 0x57b0f, // contenteditable - 0xa6: 0x66908, // onsubmit - 0xa8: 0x44f09, // oninvalid - 0xaa: 0x202, // br - 0xab: 0x10902, // id - 0xac: 0x5d04, // loop - 0xad: 0x5630a, // onpageshow - 0xb0: 0x2cf04, // href - 0xb2: 0x2210a, // figcaption - 0xb3: 0x2690e, // onautocomplete - 0xb4: 0x49106, // onload - 0xb6: 0x9c04, // rows - 0xb7: 0x1a605, // nonce - 0xb8: 0x68a14, // onunhandledrejection - 0xbb: 0x21306, // center - 0xbc: 0x59406, // onplay - 0xbd: 0x33f02, // h5 - 0xbe: 0x49d07, // listing - 0xbf: 0x57606, // public - 0xc2: 0x23b06, // figure - 0xc3: 0x57a04, // icon - 0xc4: 0x1ab03, // col - 0xc5: 0x47b03, // rel - 0xc6: 0xe605, // media - 0xc7: 0x12109, // autofocus - 0xc8: 0x19a02, // rt - 0xca: 0x2d304, // lang - 0xcc: 0x49908, // datalist - 0xce: 0x2eb06, // iframe - 0xcf: 0x36105, // muted - 0xd0: 0x6140a, // onauxclick - 0xd2: 0x3c02, // as - 0xd6: 0x3fd06, // ondrop - 0xd7: 0x1c90a, // annotation - 0xd8: 0x21908, // fieldset - 0xdb: 0x2cf08, // hreflang - 0xdc: 0x4e70c, // onmouseenter - 0xdd: 0x2a402, // mn - 0xde: 0xe60a, // mediagroup - 0xdf: 0x9805, // meter - 0xe0: 0x56c03, // wbr - 0xe2: 0x63e05, // width - 0xe3: 0x2290c, // onafterprint - 0xe4: 0x30505, // ismap - 0xe5: 0x1505, // value - 0xe7: 0x1303, // nav - 0xe8: 0x54508, // ononline - 0xe9: 0xb604, // mark - 0xea: 0xc303, // low - 0xeb: 0x3ee0b, // ondragstart - 0xef: 0x12f03, // xmp - 0xf0: 0x22407, // caption - 0xf1: 0xd904, // type - 0xf2: 0x70907, // summary - 0xf3: 0x6802, // tt - 0xf4: 0x20809, // translate - 0xf5: 0x1870a, // blockquote - 0xf8: 0x15702, // hr - 0xfa: 0x2705, // tbody - 0xfc: 0x7b07, // picture - 0xfd: 0x5206, // height - 0xfe: 0x19c04, // cite - 0xff: 0x2501, // s - 0x101: 0xff05, // async - 0x102: 0x56f07, // onpaste - 0x103: 0x19507, // onabort - 0x104: 0x2b706, // target - 0x105: 0x14b03, // bdo - 0x106: 0x1f006, // coords - 0x107: 0x5e108, // onresize - 0x108: 0x71908, // template - 0x10a: 0x3a02, // rb - 0x10b: 0x2a50a, // novalidate - 0x10c: 0x460e, // updateviacache - 0x10d: 0x71003, // sup - 0x10e: 0x6c07, // noembed - 0x10f: 0x16b03, // div - 0x110: 0x6f707, // srclang - 0x111: 0x17a09, // draggable - 0x112: 0x67305, // scope - 0x113: 0x5905, // label - 0x114: 0x22f02, // rp - 0x115: 0x23f08, // required - 0x116: 0x3780d, // oncontextmenu - 0x117: 0x5e504, // size - 0x118: 0x5b00a, // spellcheck - 0x119: 0x3f04, // font - 0x11a: 0x9c07, // rowspan - 0x11b: 0x10a07, // default - 0x11d: 0x44307, // oninput - 0x11e: 0x38506, // itemid - 0x11f: 0x5ee04, // code - 0x120: 0xaa07, // acronym - 0x121: 0x3b04, // base - 0x125: 0x2470d, // foreignObject - 0x126: 0x2ca04, // high - 0x127: 0x3cb0e, // referrerpolicy - 0x128: 0x33703, // max - 0x129: 0x59d0a, // onpopstate - 0x12a: 0x2fc02, // h4 - 0x12b: 0x4ac04, // meta - 0x12c: 0x17305, // blink - 0x12e: 0x5f508, // onscroll - 0x12f: 0x59409, // onplaying - 0x130: 0xc113, // allowpaymentrequest - 0x131: 0x19a03, // rtc - 0x132: 0x72b04, // wrap - 0x134: 0x8b08, // frameset - 0x135: 0x32605, // small - 0x137: 0x32006, // header - 0x138: 0x40409, // onemptied - 0x139: 0x34902, // h6 - 0x13a: 0x35908, // multiple - 0x13c: 0x52a06, // prompt - 0x13f: 0x28e09, // challenge - 0x141: 0x4370c, // onhashchange - 0x142: 0x57b07, // content - 0x143: 0x1c90e, // annotation-xml - 0x144: 0x36607, // onclose - 0x145: 0x14d10, // oncanplaythrough - 0x148: 0x5170b, // onmouseover - 0x149: 0x64f08, // sortable - 0x14a: 0xa402, // mo - 0x14b: 0x2cd02, // h3 - 0x14c: 0x2c406, // script - 0x14d: 0x41d07, // onended - 0x14f: 0x64706, // poster - 0x150: 0x7210a, // workertype - 0x153: 0x1f505, // shape - 0x154: 0x4, // abbr - 0x155: 0x1, // a - 0x156: 0x2bf02, // dd - 0x157: 0x71606, // system - 0x158: 0x4ce0e, // onmessageerror - 0x159: 0x36b08, // seamless - 0x15a: 0x2610a, // formaction - 0x15b: 0x6e106, // option - 0x15c: 0x31d04, // math - 0x15d: 0x62609, // onseeking - 0x15e: 0x39c05, // oncut - 0x15f: 0x44c03, // del - 0x160: 0x11005, // title - 0x161: 0x11505, // audio - 0x162: 0x63108, // selected - 0x165: 0x3b40b, // ondragenter - 0x166: 0x46e06, // spacer - 0x167: 0x4a410, // onloadedmetadata - 0x168: 0x44505, // input - 0x16a: 0x58505, // table - 0x16b: 0x41508, // onchange - 0x16e: 0x5f005, // defer - 0x171: 0x50a0a, // onmouseout - 0x172: 0x20504, // slot - 0x175: 0x3704, // nobr - 0x177: 0x1d707, // command - 0x17a: 0x7207, // details - 0x17b: 0x38104, // menu - 0x17c: 0xb903, // kbd - 0x17d: 0x57304, // step - 0x17e: 0x20303, // ins - 0x17f: 0x13c08, // autoplay - 0x182: 0x34103, // min - 0x183: 0x17404, // link - 0x185: 0x40d10, // ondurationchange - 0x186: 0x9202, // td - 0x187: 0x8b05, // frame - 0x18a: 0x2ab08, // datetime - 0x18b: 0x44509, // inputmode - 0x18c: 0x35108, // readonly - 0x18d: 0x21104, // face - 0x18f: 0x5e505, // sizes - 0x191: 0x4b208, // tabindex - 0x192: 0x6db06, // strong - 0x193: 0xba03, // bdi - 0x194: 0x6fe06, // srcset - 0x196: 0x67202, // ms - 0x197: 0x5b507, // checked - 0x198: 0xb105, // align - 0x199: 0x1e507, // section - 0x19b: 0x6e05, // embed - 0x19d: 0x15e07, // bgsound - 0x1a2: 0x49d04, // list - 0x1a3: 0x61e08, // onseeked - 0x1a4: 0x66009, // onstorage - 0x1a5: 0x2f603, // img - 0x1a6: 0xf505, // tfoot - 0x1a9: 0x26913, // onautocompleteerror - 0x1aa: 0x5fd19, // onsecuritypolicyviolation - 0x1ad: 0x9303, // dir - 0x1ae: 0x9307, // dirname - 0x1b0: 0x5a70a, // onprogress - 0x1b2: 0x65709, // onstalled - 0x1b5: 0x66f09, // itemscope - 0x1b6: 0x49904, // data - 0x1b7: 0x3d90b, // ondragleave - 0x1b8: 0x56102, // h2 - 0x1b9: 0x2f706, // mglyph - 0x1ba: 0x16502, // is - 0x1bb: 0x6e50e, // onbeforeunload - 0x1bc: 0x2830d, // typemustmatch - 0x1bd: 0x3ab06, // ondrag - 0x1be: 0x5da07, // onreset - 0x1c0: 0x51106, // output - 0x1c1: 0x12907, // sandbox - 0x1c2: 0x1b209, // plaintext - 0x1c4: 0x34c08, // textarea - 0x1c7: 0xd607, // keytype - 0x1c8: 0x34b05, // mtext - 0x1c9: 0x6b10e, // onvolumechange - 0x1ca: 0x1ea06, // onblur - 0x1cb: 0x58a07, // onpause - 0x1cd: 0x5bc0c, // onratechange - 0x1ce: 0x10705, // aside - 0x1cf: 0x6cf07, // optimum - 0x1d1: 0x45809, // onkeydown - 0x1d2: 0x1c407, // colspan - 0x1d3: 0x1004, // main - 0x1d4: 0x66b03, // sub - 0x1d5: 0x25b06, // object - 0x1d6: 0x55c06, // search - 0x1d7: 0x37206, // sorted - 0x1d8: 0x17003, // big - 0x1d9: 0xb01, // u - 0x1db: 0x26b0c, // autocomplete - 0x1dc: 0xcc02, // tr - 0x1dd: 0xf303, // alt - 0x1df: 0x7804, // samp - 0x1e0: 0x5c812, // onrejectionhandled - 0x1e1: 0x4f30c, // onmouseleave - 0x1e2: 0x28007, // enctype - 0x1e3: 0xa208, // nomodule - 0x1e5: 0x3280f, // allowfullscreen - 0x1e6: 0x5f08, // optgroup - 0x1e8: 0x27c0b, // formenctype - 0x1e9: 0x18106, // legend - 0x1ea: 0x10306, // canvas - 0x1eb: 0x6607, // pattern - 0x1ec: 0x2c208, // noscript - 0x1ed: 0x601, // i - 0x1ee: 0x5d602, // dl - 0x1ef: 0xa702, // ul - 0x1f2: 0x52209, // onmouseup - 0x1f4: 0x1ba05, // track - 0x1f7: 0x3a10a, // ondblclick - 0x1f8: 0x3bf0a, // ondragexit - 0x1fa: 0x8703, // dfn - 0x1fc: 0x26506, // action - 0x1fd: 0x35004, // area - 0x1fe: 0x31607, // marquee - 0x1ff: 0x16d03, // var -} - -const atomText = "abbradiogrouparamainavalueaccept-charsetbodyaccesskeygenobrb" + - "asefontimeupdateviacacheightmlabelooptgroupatternoembedetail" + - "sampictureversedfnoframesetdirnameterowspanomoduleacronymali" + - "gnmarkbdialogallowpaymentrequestrikeytypeallowusermediagroup" + - "ingaltfooterubyasyncanvasidefaultitleaudioncancelautofocusan" + - "dboxmplaceholderautoplaysinlinebdoncanplaythrough1bgsoundisa" + - "bledivarbigblinkindraggablegendblockquotebuttonabortcitempro" + - "penoncecolgrouplaintextrackcolorcolspannotation-xmlcommandco" + - "ntrolsectionblurcoordshapecrossoriginslotranslatefacenterfie" + - "ldsetfigcaptionafterprintegrityfigurequiredforeignObjectfore" + - "ignobjectformactionautocompleteerrorformenctypemustmatchalle" + - "ngeformmethodformnovalidatetimeformtargethiddenoscripthigh3h" + - "reflanghttp-equivideonclickiframeimageimglyph4isindexismappl" + - "etitemtypemarqueematheadersmallowfullscreenmaxlength5minleng" + - "th6mtextareadonlymultiplemutedoncloseamlessortedoncontextmen" + - "uitemidoncopyoncuechangeoncutondblclickondragendondragentero" + - "ndragexitemreferrerpolicyondragleaveondragoverondragstarticl" + - "eondropzonemptiedondurationchangeonendedonerroronfocusourceo" + - "nhashchangeoninputmodeloninvalidonkeydownloadonkeypresspacer" + - "onkeyupreloadonlanguagechangeonloadeddatalistingonloadedmeta" + - "databindexonloadendonloadstartonmessageerroronmousedownonmou" + - "seenteronmouseleaveonmousemoveonmouseoutputonmouseoveronmous" + - "eupromptonmousewheelonofflineononlineonpagehidesclassearch2o" + - "npageshowbronpastepublicontenteditableonpausemaponplayingonp" + - "opstateonprogresspellcheckedonratechangeonrejectionhandledon" + - "resetonresizesrcdocodeferonscrollonsecuritypolicyviolationau" + - "xclickonseekedonseekingonselectedonshowidthgrouposteronsorta" + - "bleonstalledonstorageonsubmitemscopedonsuspendontoggleonunha" + - "ndledrejectionbeforeprintonunloadonvolumechangeonwaitingonwh" + - "eeloptimumanifestrongoptionbeforeunloaddressrclangsrcsetstyl" + - "esummarysupsvgsystemplateworkertypewrap" diff --git a/src/vendor/golang.org/x/net/html/const.go b/src/vendor/golang.org/x/net/html/const.go deleted file mode 100644 index ff7acf2..0000000 --- a/src/vendor/golang.org/x/net/html/const.go +++ /dev/null @@ -1,111 +0,0 @@ -// Copyright 2011 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -package html - -// Section 12.2.4.2 of the HTML5 specification says "The following elements -// have varying levels of special parsing rules". -// https://html.spec.whatwg.org/multipage/syntax.html#the-stack-of-open-elements -var isSpecialElementMap = map[string]bool{ - "address": true, - "applet": true, - "area": true, - "article": true, - "aside": true, - "base": true, - "basefont": true, - "bgsound": true, - "blockquote": true, - "body": true, - "br": true, - "button": true, - "caption": true, - "center": true, - "col": true, - "colgroup": true, - "dd": true, - "details": true, - "dir": true, - "div": true, - "dl": true, - "dt": true, - "embed": true, - "fieldset": true, - "figcaption": true, - "figure": true, - "footer": true, - "form": true, - "frame": true, - "frameset": true, - "h1": true, - "h2": true, - "h3": true, - "h4": true, - "h5": true, - "h6": true, - "head": true, - "header": true, - "hgroup": true, - "hr": true, - "html": true, - "iframe": true, - "img": true, - "input": true, - "keygen": true, // "keygen" has been removed from the spec, but are kept here for backwards compatibility. - "li": true, - "link": true, - "listing": true, - "main": true, - "marquee": true, - "menu": true, - "meta": true, - "nav": true, - "noembed": true, - "noframes": true, - "noscript": true, - "object": true, - "ol": true, - "p": true, - "param": true, - "plaintext": true, - "pre": true, - "script": true, - "section": true, - "select": true, - "source": true, - "style": true, - "summary": true, - "table": true, - "tbody": true, - "td": true, - "template": true, - "textarea": true, - "tfoot": true, - "th": true, - "thead": true, - "title": true, - "tr": true, - "track": true, - "ul": true, - "wbr": true, - "xmp": true, -} - -func isSpecialElement(element *Node) bool { - switch element.Namespace { - case "", "html": - return isSpecialElementMap[element.Data] - case "math": - switch element.Data { - case "mi", "mo", "mn", "ms", "mtext", "annotation-xml": - return true - } - case "svg": - switch element.Data { - case "foreignObject", "desc", "title": - return true - } - } - return false -} diff --git a/src/vendor/golang.org/x/net/html/doc.go b/src/vendor/golang.org/x/net/html/doc.go deleted file mode 100644 index 885c4c5..0000000 --- a/src/vendor/golang.org/x/net/html/doc.go +++ /dev/null @@ -1,122 +0,0 @@ -// Copyright 2010 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -/* -Package html implements an HTML5-compliant tokenizer and parser. - -Tokenization is done by creating a Tokenizer for an io.Reader r. It is the -caller's responsibility to ensure that r provides UTF-8 encoded HTML. - - z := html.NewTokenizer(r) - -Given a Tokenizer z, the HTML is tokenized by repeatedly calling z.Next(), -which parses the next token and returns its type, or an error: - - for { - tt := z.Next() - if tt == html.ErrorToken { - // ... - return ... - } - // Process the current token. - } - -There are two APIs for retrieving the current token. The high-level API is to -call Token; the low-level API is to call Text or TagName / TagAttr. Both APIs -allow optionally calling Raw after Next but before Token, Text, TagName, or -TagAttr. In EBNF notation, the valid call sequence per token is: - - Next {Raw} [ Token | Text | TagName {TagAttr} ] - -Token returns an independent data structure that completely describes a token. -Entities (such as "<") are unescaped, tag names and attribute keys are -lower-cased, and attributes are collected into a []Attribute. For example: - - for { - if z.Next() == html.ErrorToken { - // Returning io.EOF indicates success. - return z.Err() - } - emitToken(z.Token()) - } - -The low-level API performs fewer allocations and copies, but the contents of -the []byte values returned by Text, TagName and TagAttr may change on the next -call to Next. For example, to extract an HTML page's anchor text: - - depth := 0 - for { - tt := z.Next() - switch tt { - case html.ErrorToken: - return z.Err() - case html.TextToken: - if depth > 0 { - // emitBytes should copy the []byte it receives, - // if it doesn't process it immediately. - emitBytes(z.Text()) - } - case html.StartTagToken, html.EndTagToken: - tn, _ := z.TagName() - if len(tn) == 1 && tn[0] == 'a' { - if tt == html.StartTagToken { - depth++ - } else { - depth-- - } - } - } - } - -Parsing is done by calling Parse with an io.Reader, which returns the root of -the parse tree (the document element) as a *Node. It is the caller's -responsibility to ensure that the Reader provides UTF-8 encoded HTML. For -example, to process each anchor node in depth-first order: - - doc, err := html.Parse(r) - if err != nil { - // ... - } - for n := range doc.Descendants() { - if n.Type == html.ElementNode && n.Data == "a" { - // Do something with n... - } - } - -The relevant specifications include: -https://html.spec.whatwg.org/multipage/syntax.html and -https://html.spec.whatwg.org/multipage/syntax.html#tokenization - -# Security Considerations - -Care should be taken when parsing and interpreting HTML, whether full documents -or fragments, within the framework of the HTML specification, especially with -regard to untrusted inputs. - -This package provides both a tokenizer and a parser, which implement the -tokenization, and tokenization and tree construction stages of the WHATWG HTML -parsing specification respectively. While the tokenizer parses and normalizes -individual HTML tokens, only the parser constructs the DOM tree from the -tokenized HTML, as described in the tree construction stage of the -specification, dynamically modifying or extending the document's DOM tree. - -If your use case requires semantically well-formed HTML documents, as defined by -the WHATWG specification, the parser should be used rather than the tokenizer. - -In security contexts, if trust decisions are being made using the tokenized or -parsed content, the input must be re-serialized (for instance by using Render or -Token.String) in order for those trust decisions to hold, as the process of -tokenization or parsing may alter the content. -*/ -package html // import "golang.org/x/net/html" - -// The tokenization algorithm implemented by this package is not a line-by-line -// transliteration of the relatively verbose state-machine in the WHATWG -// specification. A more direct approach is used instead, where the program -// counter implies the state, such as whether it is tokenizing a tag or a text -// node. Specification compliance is verified by checking expected and actual -// outputs over a test suite rather than aiming for algorithmic fidelity. - -// TODO(nigeltao): Does a DOM API belong in this package or a separate one? -// TODO(nigeltao): How does parsing interact with a JavaScript engine? diff --git a/src/vendor/golang.org/x/net/html/doctype.go b/src/vendor/golang.org/x/net/html/doctype.go deleted file mode 100644 index bca3ae9..0000000 --- a/src/vendor/golang.org/x/net/html/doctype.go +++ /dev/null @@ -1,156 +0,0 @@ -// Copyright 2011 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -package html - -import ( - "strings" -) - -// parseDoctype parses the data from a DoctypeToken into a name, -// public identifier, and system identifier. It returns a Node whose Type -// is DoctypeNode, whose Data is the name, and which has attributes -// named "system" and "public" for the two identifiers if they were present. -// quirks is whether the document should be parsed in "quirks mode". -func parseDoctype(s string) (n *Node, quirks bool) { - n = &Node{Type: DoctypeNode} - - // Find the name. - space := strings.IndexAny(s, whitespace) - if space == -1 { - space = len(s) - } - n.Data = s[:space] - // The comparison to "html" is case-sensitive. - if n.Data != "html" { - quirks = true - } - n.Data = strings.ToLower(n.Data) - s = strings.TrimLeft(s[space:], whitespace) - - if len(s) < 6 { - // It can't start with "PUBLIC" or "SYSTEM". - // Ignore the rest of the string. - return n, quirks || s != "" - } - - key := strings.ToLower(s[:6]) - s = s[6:] - for key == "public" || key == "system" { - s = strings.TrimLeft(s, whitespace) - if s == "" { - break - } - quote := s[0] - if quote != '"' && quote != '\'' { - break - } - s = s[1:] - q := strings.IndexRune(s, rune(quote)) - var id string - if q == -1 { - id = s - s = "" - } else { - id = s[:q] - s = s[q+1:] - } - n.Attr = append(n.Attr, Attribute{Key: key, Val: id}) - if key == "public" { - key = "system" - } else { - key = "" - } - } - - if key != "" || s != "" { - quirks = true - } else if len(n.Attr) > 0 { - if n.Attr[0].Key == "public" { - public := strings.ToLower(n.Attr[0].Val) - switch public { - case "-//w3o//dtd w3 html strict 3.0//en//", "-/w3d/dtd html 4.0 transitional/en", "html": - quirks = true - default: - for _, q := range quirkyIDs { - if strings.HasPrefix(public, q) { - quirks = true - break - } - } - } - // The following two public IDs only cause quirks mode if there is no system ID. - if len(n.Attr) == 1 && (strings.HasPrefix(public, "-//w3c//dtd html 4.01 frameset//") || - strings.HasPrefix(public, "-//w3c//dtd html 4.01 transitional//")) { - quirks = true - } - } - if lastAttr := n.Attr[len(n.Attr)-1]; lastAttr.Key == "system" && - strings.EqualFold(lastAttr.Val, "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { - quirks = true - } - } - - return n, quirks -} - -// quirkyIDs is a list of public doctype identifiers that cause a document -// to be interpreted in quirks mode. The identifiers should be in lower case. -var quirkyIDs = []string{ - "+//silmaril//dtd html pro v0r11 19970101//", - "-//advasoft ltd//dtd html 3.0 aswedit + extensions//", - "-//as//dtd html 3.0 aswedit + extensions//", - "-//ietf//dtd html 2.0 level 1//", - "-//ietf//dtd html 2.0 level 2//", - "-//ietf//dtd html 2.0 strict level 1//", - "-//ietf//dtd html 2.0 strict level 2//", - "-//ietf//dtd html 2.0 strict//", - "-//ietf//dtd html 2.0//", - "-//ietf//dtd html 2.1e//", - "-//ietf//dtd html 3.0//", - "-//ietf//dtd html 3.2 final//", - "-//ietf//dtd html 3.2//", - "-//ietf//dtd html 3//", - "-//ietf//dtd html level 0//", - "-//ietf//dtd html level 1//", - "-//ietf//dtd html level 2//", - "-//ietf//dtd html level 3//", - "-//ietf//dtd html strict level 0//", - "-//ietf//dtd html strict level 1//", - "-//ietf//dtd html strict level 2//", - "-//ietf//dtd html strict level 3//", - "-//ietf//dtd html strict//", - "-//ietf//dtd html//", - "-//metrius//dtd metrius presentational//", - "-//microsoft//dtd internet explorer 2.0 html strict//", - "-//microsoft//dtd internet explorer 2.0 html//", - "-//microsoft//dtd internet explorer 2.0 tables//", - "-//microsoft//dtd internet explorer 3.0 html strict//", - "-//microsoft//dtd internet explorer 3.0 html//", - "-//microsoft//dtd internet explorer 3.0 tables//", - "-//netscape comm. corp.//dtd html//", - "-//netscape comm. corp.//dtd strict html//", - "-//o'reilly and associates//dtd html 2.0//", - "-//o'reilly and associates//dtd html extended 1.0//", - "-//o'reilly and associates//dtd html extended relaxed 1.0//", - "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//", - "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//", - "-//spyglass//dtd html 2.0 extended//", - "-//sq//dtd html 2.0 hotmetal + extensions//", - "-//sun microsystems corp.//dtd hotjava html//", - "-//sun microsystems corp.//dtd hotjava strict html//", - "-//w3c//dtd html 3 1995-03-24//", - "-//w3c//dtd html 3.2 draft//", - "-//w3c//dtd html 3.2 final//", - "-//w3c//dtd html 3.2//", - "-//w3c//dtd html 3.2s draft//", - "-//w3c//dtd html 4.0 frameset//", - "-//w3c//dtd html 4.0 transitional//", - "-//w3c//dtd html experimental 19960712//", - "-//w3c//dtd html experimental 970421//", - "-//w3c//dtd w3 html//", - "-//w3o//dtd w3 html 3.0//", - "-//webtechs//dtd mozilla html 2.0//", - "-//webtechs//dtd mozilla html//", -} diff --git a/src/vendor/golang.org/x/net/html/entity.go b/src/vendor/golang.org/x/net/html/entity.go deleted file mode 100644 index b628880..0000000 --- a/src/vendor/golang.org/x/net/html/entity.go +++ /dev/null @@ -1,2253 +0,0 @@ -// Copyright 2010 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -package html - -// All entities that do not end with ';' are 6 or fewer bytes long. -const longestEntityWithoutSemicolon = 6 - -// entity is a map from HTML entity names to their values. The semicolon matters: -// https://html.spec.whatwg.org/multipage/syntax.html#named-character-references -// lists both "amp" and "amp;" as two separate entries. -// -// Note that the HTML5 list is larger than the HTML4 list at -// http://www.w3.org/TR/html4/sgml/entities.html -var entity = map[string]rune{ - "AElig;": '\U000000C6', - "AMP;": '\U00000026', - "Aacute;": '\U000000C1', - "Abreve;": '\U00000102', - "Acirc;": '\U000000C2', - "Acy;": '\U00000410', - "Afr;": '\U0001D504', - "Agrave;": '\U000000C0', - "Alpha;": '\U00000391', - "Amacr;": '\U00000100', - "And;": '\U00002A53', - "Aogon;": '\U00000104', - "Aopf;": '\U0001D538', - "ApplyFunction;": '\U00002061', - "Aring;": '\U000000C5', - "Ascr;": '\U0001D49C', - "Assign;": '\U00002254', - "Atilde;": '\U000000C3', - "Auml;": '\U000000C4', - "Backslash;": '\U00002216', - "Barv;": '\U00002AE7', - "Barwed;": '\U00002306', - "Bcy;": '\U00000411', - "Because;": '\U00002235', - "Bernoullis;": '\U0000212C', - "Beta;": '\U00000392', - "Bfr;": '\U0001D505', - "Bopf;": '\U0001D539', - "Breve;": '\U000002D8', - "Bscr;": '\U0000212C', - "Bumpeq;": '\U0000224E', - "CHcy;": '\U00000427', - "COPY;": '\U000000A9', - "Cacute;": '\U00000106', - "Cap;": '\U000022D2', - "CapitalDifferentialD;": '\U00002145', - "Cayleys;": '\U0000212D', - "Ccaron;": '\U0000010C', - "Ccedil;": '\U000000C7', - "Ccirc;": '\U00000108', - "Cconint;": '\U00002230', - "Cdot;": '\U0000010A', - "Cedilla;": '\U000000B8', - "CenterDot;": '\U000000B7', - "Cfr;": '\U0000212D', - "Chi;": '\U000003A7', - "CircleDot;": '\U00002299', - "CircleMinus;": '\U00002296', - "CirclePlus;": '\U00002295', - "CircleTimes;": '\U00002297', - "ClockwiseContourIntegral;": '\U00002232', - "CloseCurlyDoubleQuote;": '\U0000201D', - "CloseCurlyQuote;": '\U00002019', - "Colon;": '\U00002237', - "Colone;": '\U00002A74', - "Congruent;": '\U00002261', - "Conint;": '\U0000222F', - "ContourIntegral;": '\U0000222E', - "Copf;": '\U00002102', - "Coproduct;": '\U00002210', - "CounterClockwiseContourIntegral;": '\U00002233', - "Cross;": '\U00002A2F', - "Cscr;": '\U0001D49E', - "Cup;": '\U000022D3', - "CupCap;": '\U0000224D', - "DD;": '\U00002145', - "DDotrahd;": '\U00002911', - "DJcy;": '\U00000402', - "DScy;": '\U00000405', - "DZcy;": '\U0000040F', - "Dagger;": '\U00002021', - "Darr;": '\U000021A1', - "Dashv;": '\U00002AE4', - "Dcaron;": '\U0000010E', - "Dcy;": '\U00000414', - "Del;": '\U00002207', - "Delta;": '\U00000394', - "Dfr;": '\U0001D507', - "DiacriticalAcute;": '\U000000B4', - "DiacriticalDot;": '\U000002D9', - "DiacriticalDoubleAcute;": '\U000002DD', - "DiacriticalGrave;": '\U00000060', - "DiacriticalTilde;": '\U000002DC', - "Diamond;": '\U000022C4', - "DifferentialD;": '\U00002146', - "Dopf;": '\U0001D53B', - "Dot;": '\U000000A8', - "DotDot;": '\U000020DC', - "DotEqual;": '\U00002250', - "DoubleContourIntegral;": '\U0000222F', - "DoubleDot;": '\U000000A8', - "DoubleDownArrow;": '\U000021D3', - "DoubleLeftArrow;": '\U000021D0', - "DoubleLeftRightArrow;": '\U000021D4', - "DoubleLeftTee;": '\U00002AE4', - "DoubleLongLeftArrow;": '\U000027F8', - "DoubleLongLeftRightArrow;": '\U000027FA', - "DoubleLongRightArrow;": '\U000027F9', - "DoubleRightArrow;": '\U000021D2', - "DoubleRightTee;": '\U000022A8', - "DoubleUpArrow;": '\U000021D1', - "DoubleUpDownArrow;": '\U000021D5', - "DoubleVerticalBar;": '\U00002225', - "DownArrow;": '\U00002193', - "DownArrowBar;": '\U00002913', - "DownArrowUpArrow;": '\U000021F5', - "DownBreve;": '\U00000311', - "DownLeftRightVector;": '\U00002950', - "DownLeftTeeVector;": '\U0000295E', - "DownLeftVector;": '\U000021BD', - "DownLeftVectorBar;": '\U00002956', - "DownRightTeeVector;": '\U0000295F', - "DownRightVector;": '\U000021C1', - "DownRightVectorBar;": '\U00002957', - "DownTee;": '\U000022A4', - "DownTeeArrow;": '\U000021A7', - "Downarrow;": '\U000021D3', - "Dscr;": '\U0001D49F', - "Dstrok;": '\U00000110', - "ENG;": '\U0000014A', - "ETH;": '\U000000D0', - "Eacute;": '\U000000C9', - "Ecaron;": '\U0000011A', - "Ecirc;": '\U000000CA', - "Ecy;": '\U0000042D', - "Edot;": '\U00000116', - "Efr;": '\U0001D508', - "Egrave;": '\U000000C8', - "Element;": '\U00002208', - "Emacr;": '\U00000112', - "EmptySmallSquare;": '\U000025FB', - "EmptyVerySmallSquare;": '\U000025AB', - "Eogon;": '\U00000118', - "Eopf;": '\U0001D53C', - "Epsilon;": '\U00000395', - "Equal;": '\U00002A75', - "EqualTilde;": '\U00002242', - "Equilibrium;": '\U000021CC', - "Escr;": '\U00002130', - "Esim;": '\U00002A73', - "Eta;": '\U00000397', - "Euml;": '\U000000CB', - "Exists;": '\U00002203', - "ExponentialE;": '\U00002147', - "Fcy;": '\U00000424', - "Ffr;": '\U0001D509', - "FilledSmallSquare;": '\U000025FC', - "FilledVerySmallSquare;": '\U000025AA', - "Fopf;": '\U0001D53D', - "ForAll;": '\U00002200', - "Fouriertrf;": '\U00002131', - "Fscr;": '\U00002131', - "GJcy;": '\U00000403', - "GT;": '\U0000003E', - "Gamma;": '\U00000393', - "Gammad;": '\U000003DC', - "Gbreve;": '\U0000011E', - "Gcedil;": '\U00000122', - "Gcirc;": '\U0000011C', - "Gcy;": '\U00000413', - "Gdot;": '\U00000120', - "Gfr;": '\U0001D50A', - "Gg;": '\U000022D9', - "Gopf;": '\U0001D53E', - "GreaterEqual;": '\U00002265', - "GreaterEqualLess;": '\U000022DB', - "GreaterFullEqual;": '\U00002267', - "GreaterGreater;": '\U00002AA2', - "GreaterLess;": '\U00002277', - "GreaterSlantEqual;": '\U00002A7E', - "GreaterTilde;": '\U00002273', - "Gscr;": '\U0001D4A2', - "Gt;": '\U0000226B', - "HARDcy;": '\U0000042A', - "Hacek;": '\U000002C7', - "Hat;": '\U0000005E', - "Hcirc;": '\U00000124', - "Hfr;": '\U0000210C', - "HilbertSpace;": '\U0000210B', - "Hopf;": '\U0000210D', - "HorizontalLine;": '\U00002500', - "Hscr;": '\U0000210B', - "Hstrok;": '\U00000126', - "HumpDownHump;": '\U0000224E', - "HumpEqual;": '\U0000224F', - "IEcy;": '\U00000415', - "IJlig;": '\U00000132', - "IOcy;": '\U00000401', - "Iacute;": '\U000000CD', - "Icirc;": '\U000000CE', - "Icy;": '\U00000418', - "Idot;": '\U00000130', - "Ifr;": '\U00002111', - "Igrave;": '\U000000CC', - "Im;": '\U00002111', - "Imacr;": '\U0000012A', - "ImaginaryI;": '\U00002148', - "Implies;": '\U000021D2', - "Int;": '\U0000222C', - "Integral;": '\U0000222B', - "Intersection;": '\U000022C2', - "InvisibleComma;": '\U00002063', - "InvisibleTimes;": '\U00002062', - "Iogon;": '\U0000012E', - "Iopf;": '\U0001D540', - "Iota;": '\U00000399', - "Iscr;": '\U00002110', - "Itilde;": '\U00000128', - "Iukcy;": '\U00000406', - "Iuml;": '\U000000CF', - "Jcirc;": '\U00000134', - "Jcy;": '\U00000419', - "Jfr;": '\U0001D50D', - "Jopf;": '\U0001D541', - "Jscr;": '\U0001D4A5', - "Jsercy;": '\U00000408', - "Jukcy;": '\U00000404', - "KHcy;": '\U00000425', - "KJcy;": '\U0000040C', - "Kappa;": '\U0000039A', - "Kcedil;": '\U00000136', - "Kcy;": '\U0000041A', - "Kfr;": '\U0001D50E', - "Kopf;": '\U0001D542', - "Kscr;": '\U0001D4A6', - "LJcy;": '\U00000409', - "LT;": '\U0000003C', - "Lacute;": '\U00000139', - "Lambda;": '\U0000039B', - "Lang;": '\U000027EA', - "Laplacetrf;": '\U00002112', - "Larr;": '\U0000219E', - "Lcaron;": '\U0000013D', - "Lcedil;": '\U0000013B', - "Lcy;": '\U0000041B', - "LeftAngleBracket;": '\U000027E8', - "LeftArrow;": '\U00002190', - "LeftArrowBar;": '\U000021E4', - "LeftArrowRightArrow;": '\U000021C6', - "LeftCeiling;": '\U00002308', - "LeftDoubleBracket;": '\U000027E6', - "LeftDownTeeVector;": '\U00002961', - "LeftDownVector;": '\U000021C3', - "LeftDownVectorBar;": '\U00002959', - "LeftFloor;": '\U0000230A', - "LeftRightArrow;": '\U00002194', - "LeftRightVector;": '\U0000294E', - "LeftTee;": '\U000022A3', - "LeftTeeArrow;": '\U000021A4', - "LeftTeeVector;": '\U0000295A', - "LeftTriangle;": '\U000022B2', - "LeftTriangleBar;": '\U000029CF', - "LeftTriangleEqual;": '\U000022B4', - "LeftUpDownVector;": '\U00002951', - "LeftUpTeeVector;": '\U00002960', - "LeftUpVector;": '\U000021BF', - "LeftUpVectorBar;": '\U00002958', - "LeftVector;": '\U000021BC', - "LeftVectorBar;": '\U00002952', - "Leftarrow;": '\U000021D0', - "Leftrightarrow;": '\U000021D4', - "LessEqualGreater;": '\U000022DA', - "LessFullEqual;": '\U00002266', - "LessGreater;": '\U00002276', - "LessLess;": '\U00002AA1', - "LessSlantEqual;": '\U00002A7D', - "LessTilde;": '\U00002272', - "Lfr;": '\U0001D50F', - "Ll;": '\U000022D8', - "Lleftarrow;": '\U000021DA', - "Lmidot;": '\U0000013F', - "LongLeftArrow;": '\U000027F5', - "LongLeftRightArrow;": '\U000027F7', - "LongRightArrow;": '\U000027F6', - "Longleftarrow;": '\U000027F8', - "Longleftrightarrow;": '\U000027FA', - "Longrightarrow;": '\U000027F9', - "Lopf;": '\U0001D543', - "LowerLeftArrow;": '\U00002199', - "LowerRightArrow;": '\U00002198', - "Lscr;": '\U00002112', - "Lsh;": '\U000021B0', - "Lstrok;": '\U00000141', - "Lt;": '\U0000226A', - "Map;": '\U00002905', - "Mcy;": '\U0000041C', - "MediumSpace;": '\U0000205F', - "Mellintrf;": '\U00002133', - "Mfr;": '\U0001D510', - "MinusPlus;": '\U00002213', - "Mopf;": '\U0001D544', - "Mscr;": '\U00002133', - "Mu;": '\U0000039C', - "NJcy;": '\U0000040A', - "Nacute;": '\U00000143', - "Ncaron;": '\U00000147', - "Ncedil;": '\U00000145', - "Ncy;": '\U0000041D', - "NegativeMediumSpace;": '\U0000200B', - "NegativeThickSpace;": '\U0000200B', - "NegativeThinSpace;": '\U0000200B', - "NegativeVeryThinSpace;": '\U0000200B', - "NestedGreaterGreater;": '\U0000226B', - "NestedLessLess;": '\U0000226A', - "NewLine;": '\U0000000A', - "Nfr;": '\U0001D511', - "NoBreak;": '\U00002060', - "NonBreakingSpace;": '\U000000A0', - "Nopf;": '\U00002115', - "Not;": '\U00002AEC', - "NotCongruent;": '\U00002262', - "NotCupCap;": '\U0000226D', - "NotDoubleVerticalBar;": '\U00002226', - "NotElement;": '\U00002209', - "NotEqual;": '\U00002260', - "NotExists;": '\U00002204', - "NotGreater;": '\U0000226F', - "NotGreaterEqual;": '\U00002271', - "NotGreaterLess;": '\U00002279', - "NotGreaterTilde;": '\U00002275', - "NotLeftTriangle;": '\U000022EA', - "NotLeftTriangleEqual;": '\U000022EC', - "NotLess;": '\U0000226E', - "NotLessEqual;": '\U00002270', - "NotLessGreater;": '\U00002278', - "NotLessTilde;": '\U00002274', - "NotPrecedes;": '\U00002280', - "NotPrecedesSlantEqual;": '\U000022E0', - "NotReverseElement;": '\U0000220C', - "NotRightTriangle;": '\U000022EB', - "NotRightTriangleEqual;": '\U000022ED', - "NotSquareSubsetEqual;": '\U000022E2', - "NotSquareSupersetEqual;": '\U000022E3', - "NotSubsetEqual;": '\U00002288', - "NotSucceeds;": '\U00002281', - "NotSucceedsSlantEqual;": '\U000022E1', - "NotSupersetEqual;": '\U00002289', - "NotTilde;": '\U00002241', - "NotTildeEqual;": '\U00002244', - "NotTildeFullEqual;": '\U00002247', - "NotTildeTilde;": '\U00002249', - "NotVerticalBar;": '\U00002224', - "Nscr;": '\U0001D4A9', - "Ntilde;": '\U000000D1', - "Nu;": '\U0000039D', - "OElig;": '\U00000152', - "Oacute;": '\U000000D3', - "Ocirc;": '\U000000D4', - "Ocy;": '\U0000041E', - "Odblac;": '\U00000150', - "Ofr;": '\U0001D512', - "Ograve;": '\U000000D2', - "Omacr;": '\U0000014C', - "Omega;": '\U000003A9', - "Omicron;": '\U0000039F', - "Oopf;": '\U0001D546', - "OpenCurlyDoubleQuote;": '\U0000201C', - "OpenCurlyQuote;": '\U00002018', - "Or;": '\U00002A54', - "Oscr;": '\U0001D4AA', - "Oslash;": '\U000000D8', - "Otilde;": '\U000000D5', - "Otimes;": '\U00002A37', - "Ouml;": '\U000000D6', - "OverBar;": '\U0000203E', - "OverBrace;": '\U000023DE', - "OverBracket;": '\U000023B4', - "OverParenthesis;": '\U000023DC', - "PartialD;": '\U00002202', - "Pcy;": '\U0000041F', - "Pfr;": '\U0001D513', - "Phi;": '\U000003A6', - "Pi;": '\U000003A0', - "PlusMinus;": '\U000000B1', - "Poincareplane;": '\U0000210C', - "Popf;": '\U00002119', - "Pr;": '\U00002ABB', - "Precedes;": '\U0000227A', - "PrecedesEqual;": '\U00002AAF', - "PrecedesSlantEqual;": '\U0000227C', - "PrecedesTilde;": '\U0000227E', - "Prime;": '\U00002033', - "Product;": '\U0000220F', - "Proportion;": '\U00002237', - "Proportional;": '\U0000221D', - "Pscr;": '\U0001D4AB', - "Psi;": '\U000003A8', - "QUOT;": '\U00000022', - "Qfr;": '\U0001D514', - "Qopf;": '\U0000211A', - "Qscr;": '\U0001D4AC', - "RBarr;": '\U00002910', - "REG;": '\U000000AE', - "Racute;": '\U00000154', - "Rang;": '\U000027EB', - "Rarr;": '\U000021A0', - "Rarrtl;": '\U00002916', - "Rcaron;": '\U00000158', - "Rcedil;": '\U00000156', - "Rcy;": '\U00000420', - "Re;": '\U0000211C', - "ReverseElement;": '\U0000220B', - "ReverseEquilibrium;": '\U000021CB', - "ReverseUpEquilibrium;": '\U0000296F', - "Rfr;": '\U0000211C', - "Rho;": '\U000003A1', - "RightAngleBracket;": '\U000027E9', - "RightArrow;": '\U00002192', - "RightArrowBar;": '\U000021E5', - "RightArrowLeftArrow;": '\U000021C4', - "RightCeiling;": '\U00002309', - "RightDoubleBracket;": '\U000027E7', - "RightDownTeeVector;": '\U0000295D', - "RightDownVector;": '\U000021C2', - "RightDownVectorBar;": '\U00002955', - "RightFloor;": '\U0000230B', - "RightTee;": '\U000022A2', - "RightTeeArrow;": '\U000021A6', - "RightTeeVector;": '\U0000295B', - "RightTriangle;": '\U000022B3', - "RightTriangleBar;": '\U000029D0', - "RightTriangleEqual;": '\U000022B5', - "RightUpDownVector;": '\U0000294F', - "RightUpTeeVector;": '\U0000295C', - "RightUpVector;": '\U000021BE', - "RightUpVectorBar;": '\U00002954', - "RightVector;": '\U000021C0', - "RightVectorBar;": '\U00002953', - "Rightarrow;": '\U000021D2', - "Ropf;": '\U0000211D', - "RoundImplies;": '\U00002970', - "Rrightarrow;": '\U000021DB', - "Rscr;": '\U0000211B', - "Rsh;": '\U000021B1', - "RuleDelayed;": '\U000029F4', - "SHCHcy;": '\U00000429', - "SHcy;": '\U00000428', - "SOFTcy;": '\U0000042C', - "Sacute;": '\U0000015A', - "Sc;": '\U00002ABC', - "Scaron;": '\U00000160', - "Scedil;": '\U0000015E', - "Scirc;": '\U0000015C', - "Scy;": '\U00000421', - "Sfr;": '\U0001D516', - "ShortDownArrow;": '\U00002193', - "ShortLeftArrow;": '\U00002190', - "ShortRightArrow;": '\U00002192', - "ShortUpArrow;": '\U00002191', - "Sigma;": '\U000003A3', - "SmallCircle;": '\U00002218', - "Sopf;": '\U0001D54A', - "Sqrt;": '\U0000221A', - "Square;": '\U000025A1', - "SquareIntersection;": '\U00002293', - "SquareSubset;": '\U0000228F', - "SquareSubsetEqual;": '\U00002291', - "SquareSuperset;": '\U00002290', - "SquareSupersetEqual;": '\U00002292', - "SquareUnion;": '\U00002294', - "Sscr;": '\U0001D4AE', - "Star;": '\U000022C6', - "Sub;": '\U000022D0', - "Subset;": '\U000022D0', - "SubsetEqual;": '\U00002286', - "Succeeds;": '\U0000227B', - "SucceedsEqual;": '\U00002AB0', - "SucceedsSlantEqual;": '\U0000227D', - "SucceedsTilde;": '\U0000227F', - "SuchThat;": '\U0000220B', - "Sum;": '\U00002211', - "Sup;": '\U000022D1', - "Superset;": '\U00002283', - "SupersetEqual;": '\U00002287', - "Supset;": '\U000022D1', - "THORN;": '\U000000DE', - "TRADE;": '\U00002122', - "TSHcy;": '\U0000040B', - "TScy;": '\U00000426', - "Tab;": '\U00000009', - "Tau;": '\U000003A4', - "Tcaron;": '\U00000164', - "Tcedil;": '\U00000162', - "Tcy;": '\U00000422', - "Tfr;": '\U0001D517', - "Therefore;": '\U00002234', - "Theta;": '\U00000398', - "ThinSpace;": '\U00002009', - "Tilde;": '\U0000223C', - "TildeEqual;": '\U00002243', - "TildeFullEqual;": '\U00002245', - "TildeTilde;": '\U00002248', - "Topf;": '\U0001D54B', - "TripleDot;": '\U000020DB', - "Tscr;": '\U0001D4AF', - "Tstrok;": '\U00000166', - "Uacute;": '\U000000DA', - "Uarr;": '\U0000219F', - "Uarrocir;": '\U00002949', - "Ubrcy;": '\U0000040E', - "Ubreve;": '\U0000016C', - "Ucirc;": '\U000000DB', - "Ucy;": '\U00000423', - "Udblac;": '\U00000170', - "Ufr;": '\U0001D518', - "Ugrave;": '\U000000D9', - "Umacr;": '\U0000016A', - "UnderBar;": '\U0000005F', - "UnderBrace;": '\U000023DF', - "UnderBracket;": '\U000023B5', - "UnderParenthesis;": '\U000023DD', - "Union;": '\U000022C3', - "UnionPlus;": '\U0000228E', - "Uogon;": '\U00000172', - "Uopf;": '\U0001D54C', - "UpArrow;": '\U00002191', - "UpArrowBar;": '\U00002912', - "UpArrowDownArrow;": '\U000021C5', - "UpDownArrow;": '\U00002195', - "UpEquilibrium;": '\U0000296E', - "UpTee;": '\U000022A5', - "UpTeeArrow;": '\U000021A5', - "Uparrow;": '\U000021D1', - "Updownarrow;": '\U000021D5', - "UpperLeftArrow;": '\U00002196', - "UpperRightArrow;": '\U00002197', - "Upsi;": '\U000003D2', - "Upsilon;": '\U000003A5', - "Uring;": '\U0000016E', - "Uscr;": '\U0001D4B0', - "Utilde;": '\U00000168', - "Uuml;": '\U000000DC', - "VDash;": '\U000022AB', - "Vbar;": '\U00002AEB', - "Vcy;": '\U00000412', - "Vdash;": '\U000022A9', - "Vdashl;": '\U00002AE6', - "Vee;": '\U000022C1', - "Verbar;": '\U00002016', - "Vert;": '\U00002016', - "VerticalBar;": '\U00002223', - "VerticalLine;": '\U0000007C', - "VerticalSeparator;": '\U00002758', - "VerticalTilde;": '\U00002240', - "VeryThinSpace;": '\U0000200A', - "Vfr;": '\U0001D519', - "Vopf;": '\U0001D54D', - "Vscr;": '\U0001D4B1', - "Vvdash;": '\U000022AA', - "Wcirc;": '\U00000174', - "Wedge;": '\U000022C0', - "Wfr;": '\U0001D51A', - "Wopf;": '\U0001D54E', - "Wscr;": '\U0001D4B2', - "Xfr;": '\U0001D51B', - "Xi;": '\U0000039E', - "Xopf;": '\U0001D54F', - "Xscr;": '\U0001D4B3', - "YAcy;": '\U0000042F', - "YIcy;": '\U00000407', - "YUcy;": '\U0000042E', - "Yacute;": '\U000000DD', - "Ycirc;": '\U00000176', - "Ycy;": '\U0000042B', - "Yfr;": '\U0001D51C', - "Yopf;": '\U0001D550', - "Yscr;": '\U0001D4B4', - "Yuml;": '\U00000178', - "ZHcy;": '\U00000416', - "Zacute;": '\U00000179', - "Zcaron;": '\U0000017D', - "Zcy;": '\U00000417', - "Zdot;": '\U0000017B', - "ZeroWidthSpace;": '\U0000200B', - "Zeta;": '\U00000396', - "Zfr;": '\U00002128', - "Zopf;": '\U00002124', - "Zscr;": '\U0001D4B5', - "aacute;": '\U000000E1', - "abreve;": '\U00000103', - "ac;": '\U0000223E', - "acd;": '\U0000223F', - "acirc;": '\U000000E2', - "acute;": '\U000000B4', - "acy;": '\U00000430', - "aelig;": '\U000000E6', - "af;": '\U00002061', - "afr;": '\U0001D51E', - "agrave;": '\U000000E0', - "alefsym;": '\U00002135', - "aleph;": '\U00002135', - "alpha;": '\U000003B1', - "amacr;": '\U00000101', - "amalg;": '\U00002A3F', - "amp;": '\U00000026', - "and;": '\U00002227', - "andand;": '\U00002A55', - "andd;": '\U00002A5C', - "andslope;": '\U00002A58', - "andv;": '\U00002A5A', - "ang;": '\U00002220', - "ange;": '\U000029A4', - "angle;": '\U00002220', - "angmsd;": '\U00002221', - "angmsdaa;": '\U000029A8', - "angmsdab;": '\U000029A9', - "angmsdac;": '\U000029AA', - "angmsdad;": '\U000029AB', - "angmsdae;": '\U000029AC', - "angmsdaf;": '\U000029AD', - "angmsdag;": '\U000029AE', - "angmsdah;": '\U000029AF', - "angrt;": '\U0000221F', - "angrtvb;": '\U000022BE', - "angrtvbd;": '\U0000299D', - "angsph;": '\U00002222', - "angst;": '\U000000C5', - "angzarr;": '\U0000237C', - "aogon;": '\U00000105', - "aopf;": '\U0001D552', - "ap;": '\U00002248', - "apE;": '\U00002A70', - "apacir;": '\U00002A6F', - "ape;": '\U0000224A', - "apid;": '\U0000224B', - "apos;": '\U00000027', - "approx;": '\U00002248', - "approxeq;": '\U0000224A', - "aring;": '\U000000E5', - "ascr;": '\U0001D4B6', - "ast;": '\U0000002A', - "asymp;": '\U00002248', - "asympeq;": '\U0000224D', - "atilde;": '\U000000E3', - "auml;": '\U000000E4', - "awconint;": '\U00002233', - "awint;": '\U00002A11', - "bNot;": '\U00002AED', - "backcong;": '\U0000224C', - "backepsilon;": '\U000003F6', - "backprime;": '\U00002035', - "backsim;": '\U0000223D', - "backsimeq;": '\U000022CD', - "barvee;": '\U000022BD', - "barwed;": '\U00002305', - "barwedge;": '\U00002305', - "bbrk;": '\U000023B5', - "bbrktbrk;": '\U000023B6', - "bcong;": '\U0000224C', - "bcy;": '\U00000431', - "bdquo;": '\U0000201E', - "becaus;": '\U00002235', - "because;": '\U00002235', - "bemptyv;": '\U000029B0', - "bepsi;": '\U000003F6', - "bernou;": '\U0000212C', - "beta;": '\U000003B2', - "beth;": '\U00002136', - "between;": '\U0000226C', - "bfr;": '\U0001D51F', - "bigcap;": '\U000022C2', - "bigcirc;": '\U000025EF', - "bigcup;": '\U000022C3', - "bigodot;": '\U00002A00', - "bigoplus;": '\U00002A01', - "bigotimes;": '\U00002A02', - "bigsqcup;": '\U00002A06', - "bigstar;": '\U00002605', - "bigtriangledown;": '\U000025BD', - "bigtriangleup;": '\U000025B3', - "biguplus;": '\U00002A04', - "bigvee;": '\U000022C1', - "bigwedge;": '\U000022C0', - "bkarow;": '\U0000290D', - "blacklozenge;": '\U000029EB', - "blacksquare;": '\U000025AA', - "blacktriangle;": '\U000025B4', - "blacktriangledown;": '\U000025BE', - "blacktriangleleft;": '\U000025C2', - "blacktriangleright;": '\U000025B8', - "blank;": '\U00002423', - "blk12;": '\U00002592', - "blk14;": '\U00002591', - "blk34;": '\U00002593', - "block;": '\U00002588', - "bnot;": '\U00002310', - "bopf;": '\U0001D553', - "bot;": '\U000022A5', - "bottom;": '\U000022A5', - "bowtie;": '\U000022C8', - "boxDL;": '\U00002557', - "boxDR;": '\U00002554', - "boxDl;": '\U00002556', - "boxDr;": '\U00002553', - "boxH;": '\U00002550', - "boxHD;": '\U00002566', - "boxHU;": '\U00002569', - "boxHd;": '\U00002564', - "boxHu;": '\U00002567', - "boxUL;": '\U0000255D', - "boxUR;": '\U0000255A', - "boxUl;": '\U0000255C', - "boxUr;": '\U00002559', - "boxV;": '\U00002551', - "boxVH;": '\U0000256C', - "boxVL;": '\U00002563', - "boxVR;": '\U00002560', - "boxVh;": '\U0000256B', - "boxVl;": '\U00002562', - "boxVr;": '\U0000255F', - "boxbox;": '\U000029C9', - "boxdL;": '\U00002555', - "boxdR;": '\U00002552', - "boxdl;": '\U00002510', - "boxdr;": '\U0000250C', - "boxh;": '\U00002500', - "boxhD;": '\U00002565', - "boxhU;": '\U00002568', - "boxhd;": '\U0000252C', - "boxhu;": '\U00002534', - "boxminus;": '\U0000229F', - "boxplus;": '\U0000229E', - "boxtimes;": '\U000022A0', - "boxuL;": '\U0000255B', - "boxuR;": '\U00002558', - "boxul;": '\U00002518', - "boxur;": '\U00002514', - "boxv;": '\U00002502', - "boxvH;": '\U0000256A', - "boxvL;": '\U00002561', - "boxvR;": '\U0000255E', - "boxvh;": '\U0000253C', - "boxvl;": '\U00002524', - "boxvr;": '\U0000251C', - "bprime;": '\U00002035', - "breve;": '\U000002D8', - "brvbar;": '\U000000A6', - "bscr;": '\U0001D4B7', - "bsemi;": '\U0000204F', - "bsim;": '\U0000223D', - "bsime;": '\U000022CD', - "bsol;": '\U0000005C', - "bsolb;": '\U000029C5', - "bsolhsub;": '\U000027C8', - "bull;": '\U00002022', - "bullet;": '\U00002022', - "bump;": '\U0000224E', - "bumpE;": '\U00002AAE', - "bumpe;": '\U0000224F', - "bumpeq;": '\U0000224F', - "cacute;": '\U00000107', - "cap;": '\U00002229', - "capand;": '\U00002A44', - "capbrcup;": '\U00002A49', - "capcap;": '\U00002A4B', - "capcup;": '\U00002A47', - "capdot;": '\U00002A40', - "caret;": '\U00002041', - "caron;": '\U000002C7', - "ccaps;": '\U00002A4D', - "ccaron;": '\U0000010D', - "ccedil;": '\U000000E7', - "ccirc;": '\U00000109', - "ccups;": '\U00002A4C', - "ccupssm;": '\U00002A50', - "cdot;": '\U0000010B', - "cedil;": '\U000000B8', - "cemptyv;": '\U000029B2', - "cent;": '\U000000A2', - "centerdot;": '\U000000B7', - "cfr;": '\U0001D520', - "chcy;": '\U00000447', - "check;": '\U00002713', - "checkmark;": '\U00002713', - "chi;": '\U000003C7', - "cir;": '\U000025CB', - "cirE;": '\U000029C3', - "circ;": '\U000002C6', - "circeq;": '\U00002257', - "circlearrowleft;": '\U000021BA', - "circlearrowright;": '\U000021BB', - "circledR;": '\U000000AE', - "circledS;": '\U000024C8', - "circledast;": '\U0000229B', - "circledcirc;": '\U0000229A', - "circleddash;": '\U0000229D', - "cire;": '\U00002257', - "cirfnint;": '\U00002A10', - "cirmid;": '\U00002AEF', - "cirscir;": '\U000029C2', - "clubs;": '\U00002663', - "clubsuit;": '\U00002663', - "colon;": '\U0000003A', - "colone;": '\U00002254', - "coloneq;": '\U00002254', - "comma;": '\U0000002C', - "commat;": '\U00000040', - "comp;": '\U00002201', - "compfn;": '\U00002218', - "complement;": '\U00002201', - "complexes;": '\U00002102', - "cong;": '\U00002245', - "congdot;": '\U00002A6D', - "conint;": '\U0000222E', - "copf;": '\U0001D554', - "coprod;": '\U00002210', - "copy;": '\U000000A9', - "copysr;": '\U00002117', - "crarr;": '\U000021B5', - "cross;": '\U00002717', - "cscr;": '\U0001D4B8', - "csub;": '\U00002ACF', - "csube;": '\U00002AD1', - "csup;": '\U00002AD0', - "csupe;": '\U00002AD2', - "ctdot;": '\U000022EF', - "cudarrl;": '\U00002938', - "cudarrr;": '\U00002935', - "cuepr;": '\U000022DE', - "cuesc;": '\U000022DF', - "cularr;": '\U000021B6', - "cularrp;": '\U0000293D', - "cup;": '\U0000222A', - "cupbrcap;": '\U00002A48', - "cupcap;": '\U00002A46', - "cupcup;": '\U00002A4A', - "cupdot;": '\U0000228D', - "cupor;": '\U00002A45', - "curarr;": '\U000021B7', - "curarrm;": '\U0000293C', - "curlyeqprec;": '\U000022DE', - "curlyeqsucc;": '\U000022DF', - "curlyvee;": '\U000022CE', - "curlywedge;": '\U000022CF', - "curren;": '\U000000A4', - "curvearrowleft;": '\U000021B6', - "curvearrowright;": '\U000021B7', - "cuvee;": '\U000022CE', - "cuwed;": '\U000022CF', - "cwconint;": '\U00002232', - "cwint;": '\U00002231', - "cylcty;": '\U0000232D', - "dArr;": '\U000021D3', - "dHar;": '\U00002965', - "dagger;": '\U00002020', - "daleth;": '\U00002138', - "darr;": '\U00002193', - "dash;": '\U00002010', - "dashv;": '\U000022A3', - "dbkarow;": '\U0000290F', - "dblac;": '\U000002DD', - "dcaron;": '\U0000010F', - "dcy;": '\U00000434', - "dd;": '\U00002146', - "ddagger;": '\U00002021', - "ddarr;": '\U000021CA', - "ddotseq;": '\U00002A77', - "deg;": '\U000000B0', - "delta;": '\U000003B4', - "demptyv;": '\U000029B1', - "dfisht;": '\U0000297F', - "dfr;": '\U0001D521', - "dharl;": '\U000021C3', - "dharr;": '\U000021C2', - "diam;": '\U000022C4', - "diamond;": '\U000022C4', - "diamondsuit;": '\U00002666', - "diams;": '\U00002666', - "die;": '\U000000A8', - "digamma;": '\U000003DD', - "disin;": '\U000022F2', - "div;": '\U000000F7', - "divide;": '\U000000F7', - "divideontimes;": '\U000022C7', - "divonx;": '\U000022C7', - "djcy;": '\U00000452', - "dlcorn;": '\U0000231E', - "dlcrop;": '\U0000230D', - "dollar;": '\U00000024', - "dopf;": '\U0001D555', - "dot;": '\U000002D9', - "doteq;": '\U00002250', - "doteqdot;": '\U00002251', - "dotminus;": '\U00002238', - "dotplus;": '\U00002214', - "dotsquare;": '\U000022A1', - "doublebarwedge;": '\U00002306', - "downarrow;": '\U00002193', - "downdownarrows;": '\U000021CA', - "downharpoonleft;": '\U000021C3', - "downharpoonright;": '\U000021C2', - "drbkarow;": '\U00002910', - "drcorn;": '\U0000231F', - "drcrop;": '\U0000230C', - "dscr;": '\U0001D4B9', - "dscy;": '\U00000455', - "dsol;": '\U000029F6', - "dstrok;": '\U00000111', - "dtdot;": '\U000022F1', - "dtri;": '\U000025BF', - "dtrif;": '\U000025BE', - "duarr;": '\U000021F5', - "duhar;": '\U0000296F', - "dwangle;": '\U000029A6', - "dzcy;": '\U0000045F', - "dzigrarr;": '\U000027FF', - "eDDot;": '\U00002A77', - "eDot;": '\U00002251', - "eacute;": '\U000000E9', - "easter;": '\U00002A6E', - "ecaron;": '\U0000011B', - "ecir;": '\U00002256', - "ecirc;": '\U000000EA', - "ecolon;": '\U00002255', - "ecy;": '\U0000044D', - "edot;": '\U00000117', - "ee;": '\U00002147', - "efDot;": '\U00002252', - "efr;": '\U0001D522', - "eg;": '\U00002A9A', - "egrave;": '\U000000E8', - "egs;": '\U00002A96', - "egsdot;": '\U00002A98', - "el;": '\U00002A99', - "elinters;": '\U000023E7', - "ell;": '\U00002113', - "els;": '\U00002A95', - "elsdot;": '\U00002A97', - "emacr;": '\U00000113', - "empty;": '\U00002205', - "emptyset;": '\U00002205', - "emptyv;": '\U00002205', - "emsp;": '\U00002003', - "emsp13;": '\U00002004', - "emsp14;": '\U00002005', - "eng;": '\U0000014B', - "ensp;": '\U00002002', - "eogon;": '\U00000119', - "eopf;": '\U0001D556', - "epar;": '\U000022D5', - "eparsl;": '\U000029E3', - "eplus;": '\U00002A71', - "epsi;": '\U000003B5', - "epsilon;": '\U000003B5', - "epsiv;": '\U000003F5', - "eqcirc;": '\U00002256', - "eqcolon;": '\U00002255', - "eqsim;": '\U00002242', - "eqslantgtr;": '\U00002A96', - "eqslantless;": '\U00002A95', - "equals;": '\U0000003D', - "equest;": '\U0000225F', - "equiv;": '\U00002261', - "equivDD;": '\U00002A78', - "eqvparsl;": '\U000029E5', - "erDot;": '\U00002253', - "erarr;": '\U00002971', - "escr;": '\U0000212F', - "esdot;": '\U00002250', - "esim;": '\U00002242', - "eta;": '\U000003B7', - "eth;": '\U000000F0', - "euml;": '\U000000EB', - "euro;": '\U000020AC', - "excl;": '\U00000021', - "exist;": '\U00002203', - "expectation;": '\U00002130', - "exponentiale;": '\U00002147', - "fallingdotseq;": '\U00002252', - "fcy;": '\U00000444', - "female;": '\U00002640', - "ffilig;": '\U0000FB03', - "fflig;": '\U0000FB00', - "ffllig;": '\U0000FB04', - "ffr;": '\U0001D523', - "filig;": '\U0000FB01', - "flat;": '\U0000266D', - "fllig;": '\U0000FB02', - "fltns;": '\U000025B1', - "fnof;": '\U00000192', - "fopf;": '\U0001D557', - "forall;": '\U00002200', - "fork;": '\U000022D4', - "forkv;": '\U00002AD9', - "fpartint;": '\U00002A0D', - "frac12;": '\U000000BD', - "frac13;": '\U00002153', - "frac14;": '\U000000BC', - "frac15;": '\U00002155', - "frac16;": '\U00002159', - "frac18;": '\U0000215B', - "frac23;": '\U00002154', - "frac25;": '\U00002156', - "frac34;": '\U000000BE', - "frac35;": '\U00002157', - "frac38;": '\U0000215C', - "frac45;": '\U00002158', - "frac56;": '\U0000215A', - "frac58;": '\U0000215D', - "frac78;": '\U0000215E', - "frasl;": '\U00002044', - "frown;": '\U00002322', - "fscr;": '\U0001D4BB', - "gE;": '\U00002267', - "gEl;": '\U00002A8C', - "gacute;": '\U000001F5', - "gamma;": '\U000003B3', - "gammad;": '\U000003DD', - "gap;": '\U00002A86', - "gbreve;": '\U0000011F', - "gcirc;": '\U0000011D', - "gcy;": '\U00000433', - "gdot;": '\U00000121', - "ge;": '\U00002265', - "gel;": '\U000022DB', - "geq;": '\U00002265', - "geqq;": '\U00002267', - "geqslant;": '\U00002A7E', - "ges;": '\U00002A7E', - "gescc;": '\U00002AA9', - "gesdot;": '\U00002A80', - "gesdoto;": '\U00002A82', - "gesdotol;": '\U00002A84', - "gesles;": '\U00002A94', - "gfr;": '\U0001D524', - "gg;": '\U0000226B', - "ggg;": '\U000022D9', - "gimel;": '\U00002137', - "gjcy;": '\U00000453', - "gl;": '\U00002277', - "glE;": '\U00002A92', - "gla;": '\U00002AA5', - "glj;": '\U00002AA4', - "gnE;": '\U00002269', - "gnap;": '\U00002A8A', - "gnapprox;": '\U00002A8A', - "gne;": '\U00002A88', - "gneq;": '\U00002A88', - "gneqq;": '\U00002269', - "gnsim;": '\U000022E7', - "gopf;": '\U0001D558', - "grave;": '\U00000060', - "gscr;": '\U0000210A', - "gsim;": '\U00002273', - "gsime;": '\U00002A8E', - "gsiml;": '\U00002A90', - "gt;": '\U0000003E', - "gtcc;": '\U00002AA7', - "gtcir;": '\U00002A7A', - "gtdot;": '\U000022D7', - "gtlPar;": '\U00002995', - "gtquest;": '\U00002A7C', - "gtrapprox;": '\U00002A86', - "gtrarr;": '\U00002978', - "gtrdot;": '\U000022D7', - "gtreqless;": '\U000022DB', - "gtreqqless;": '\U00002A8C', - "gtrless;": '\U00002277', - "gtrsim;": '\U00002273', - "hArr;": '\U000021D4', - "hairsp;": '\U0000200A', - "half;": '\U000000BD', - "hamilt;": '\U0000210B', - "hardcy;": '\U0000044A', - "harr;": '\U00002194', - "harrcir;": '\U00002948', - "harrw;": '\U000021AD', - "hbar;": '\U0000210F', - "hcirc;": '\U00000125', - "hearts;": '\U00002665', - "heartsuit;": '\U00002665', - "hellip;": '\U00002026', - "hercon;": '\U000022B9', - "hfr;": '\U0001D525', - "hksearow;": '\U00002925', - "hkswarow;": '\U00002926', - "hoarr;": '\U000021FF', - "homtht;": '\U0000223B', - "hookleftarrow;": '\U000021A9', - "hookrightarrow;": '\U000021AA', - "hopf;": '\U0001D559', - "horbar;": '\U00002015', - "hscr;": '\U0001D4BD', - "hslash;": '\U0000210F', - "hstrok;": '\U00000127', - "hybull;": '\U00002043', - "hyphen;": '\U00002010', - "iacute;": '\U000000ED', - "ic;": '\U00002063', - "icirc;": '\U000000EE', - "icy;": '\U00000438', - "iecy;": '\U00000435', - "iexcl;": '\U000000A1', - "iff;": '\U000021D4', - "ifr;": '\U0001D526', - "igrave;": '\U000000EC', - "ii;": '\U00002148', - "iiiint;": '\U00002A0C', - "iiint;": '\U0000222D', - "iinfin;": '\U000029DC', - "iiota;": '\U00002129', - "ijlig;": '\U00000133', - "imacr;": '\U0000012B', - "image;": '\U00002111', - "imagline;": '\U00002110', - "imagpart;": '\U00002111', - "imath;": '\U00000131', - "imof;": '\U000022B7', - "imped;": '\U000001B5', - "in;": '\U00002208', - "incare;": '\U00002105', - "infin;": '\U0000221E', - "infintie;": '\U000029DD', - "inodot;": '\U00000131', - "int;": '\U0000222B', - "intcal;": '\U000022BA', - "integers;": '\U00002124', - "intercal;": '\U000022BA', - "intlarhk;": '\U00002A17', - "intprod;": '\U00002A3C', - "iocy;": '\U00000451', - "iogon;": '\U0000012F', - "iopf;": '\U0001D55A', - "iota;": '\U000003B9', - "iprod;": '\U00002A3C', - "iquest;": '\U000000BF', - "iscr;": '\U0001D4BE', - "isin;": '\U00002208', - "isinE;": '\U000022F9', - "isindot;": '\U000022F5', - "isins;": '\U000022F4', - "isinsv;": '\U000022F3', - "isinv;": '\U00002208', - "it;": '\U00002062', - "itilde;": '\U00000129', - "iukcy;": '\U00000456', - "iuml;": '\U000000EF', - "jcirc;": '\U00000135', - "jcy;": '\U00000439', - "jfr;": '\U0001D527', - "jmath;": '\U00000237', - "jopf;": '\U0001D55B', - "jscr;": '\U0001D4BF', - "jsercy;": '\U00000458', - "jukcy;": '\U00000454', - "kappa;": '\U000003BA', - "kappav;": '\U000003F0', - "kcedil;": '\U00000137', - "kcy;": '\U0000043A', - "kfr;": '\U0001D528', - "kgreen;": '\U00000138', - "khcy;": '\U00000445', - "kjcy;": '\U0000045C', - "kopf;": '\U0001D55C', - "kscr;": '\U0001D4C0', - "lAarr;": '\U000021DA', - "lArr;": '\U000021D0', - "lAtail;": '\U0000291B', - "lBarr;": '\U0000290E', - "lE;": '\U00002266', - "lEg;": '\U00002A8B', - "lHar;": '\U00002962', - "lacute;": '\U0000013A', - "laemptyv;": '\U000029B4', - "lagran;": '\U00002112', - "lambda;": '\U000003BB', - "lang;": '\U000027E8', - "langd;": '\U00002991', - "langle;": '\U000027E8', - "lap;": '\U00002A85', - "laquo;": '\U000000AB', - "larr;": '\U00002190', - "larrb;": '\U000021E4', - "larrbfs;": '\U0000291F', - "larrfs;": '\U0000291D', - "larrhk;": '\U000021A9', - "larrlp;": '\U000021AB', - "larrpl;": '\U00002939', - "larrsim;": '\U00002973', - "larrtl;": '\U000021A2', - "lat;": '\U00002AAB', - "latail;": '\U00002919', - "late;": '\U00002AAD', - "lbarr;": '\U0000290C', - "lbbrk;": '\U00002772', - "lbrace;": '\U0000007B', - "lbrack;": '\U0000005B', - "lbrke;": '\U0000298B', - "lbrksld;": '\U0000298F', - "lbrkslu;": '\U0000298D', - "lcaron;": '\U0000013E', - "lcedil;": '\U0000013C', - "lceil;": '\U00002308', - "lcub;": '\U0000007B', - "lcy;": '\U0000043B', - "ldca;": '\U00002936', - "ldquo;": '\U0000201C', - "ldquor;": '\U0000201E', - "ldrdhar;": '\U00002967', - "ldrushar;": '\U0000294B', - "ldsh;": '\U000021B2', - "le;": '\U00002264', - "leftarrow;": '\U00002190', - "leftarrowtail;": '\U000021A2', - "leftharpoondown;": '\U000021BD', - "leftharpoonup;": '\U000021BC', - "leftleftarrows;": '\U000021C7', - "leftrightarrow;": '\U00002194', - "leftrightarrows;": '\U000021C6', - "leftrightharpoons;": '\U000021CB', - "leftrightsquigarrow;": '\U000021AD', - "leftthreetimes;": '\U000022CB', - "leg;": '\U000022DA', - "leq;": '\U00002264', - "leqq;": '\U00002266', - "leqslant;": '\U00002A7D', - "les;": '\U00002A7D', - "lescc;": '\U00002AA8', - "lesdot;": '\U00002A7F', - "lesdoto;": '\U00002A81', - "lesdotor;": '\U00002A83', - "lesges;": '\U00002A93', - "lessapprox;": '\U00002A85', - "lessdot;": '\U000022D6', - "lesseqgtr;": '\U000022DA', - "lesseqqgtr;": '\U00002A8B', - "lessgtr;": '\U00002276', - "lesssim;": '\U00002272', - "lfisht;": '\U0000297C', - "lfloor;": '\U0000230A', - "lfr;": '\U0001D529', - "lg;": '\U00002276', - "lgE;": '\U00002A91', - "lhard;": '\U000021BD', - "lharu;": '\U000021BC', - "lharul;": '\U0000296A', - "lhblk;": '\U00002584', - "ljcy;": '\U00000459', - "ll;": '\U0000226A', - "llarr;": '\U000021C7', - "llcorner;": '\U0000231E', - "llhard;": '\U0000296B', - "lltri;": '\U000025FA', - "lmidot;": '\U00000140', - "lmoust;": '\U000023B0', - "lmoustache;": '\U000023B0', - "lnE;": '\U00002268', - "lnap;": '\U00002A89', - "lnapprox;": '\U00002A89', - "lne;": '\U00002A87', - "lneq;": '\U00002A87', - "lneqq;": '\U00002268', - "lnsim;": '\U000022E6', - "loang;": '\U000027EC', - "loarr;": '\U000021FD', - "lobrk;": '\U000027E6', - "longleftarrow;": '\U000027F5', - "longleftrightarrow;": '\U000027F7', - "longmapsto;": '\U000027FC', - "longrightarrow;": '\U000027F6', - "looparrowleft;": '\U000021AB', - "looparrowright;": '\U000021AC', - "lopar;": '\U00002985', - "lopf;": '\U0001D55D', - "loplus;": '\U00002A2D', - "lotimes;": '\U00002A34', - "lowast;": '\U00002217', - "lowbar;": '\U0000005F', - "loz;": '\U000025CA', - "lozenge;": '\U000025CA', - "lozf;": '\U000029EB', - "lpar;": '\U00000028', - "lparlt;": '\U00002993', - "lrarr;": '\U000021C6', - "lrcorner;": '\U0000231F', - "lrhar;": '\U000021CB', - "lrhard;": '\U0000296D', - "lrm;": '\U0000200E', - "lrtri;": '\U000022BF', - "lsaquo;": '\U00002039', - "lscr;": '\U0001D4C1', - "lsh;": '\U000021B0', - "lsim;": '\U00002272', - "lsime;": '\U00002A8D', - "lsimg;": '\U00002A8F', - "lsqb;": '\U0000005B', - "lsquo;": '\U00002018', - "lsquor;": '\U0000201A', - "lstrok;": '\U00000142', - "lt;": '\U0000003C', - "ltcc;": '\U00002AA6', - "ltcir;": '\U00002A79', - "ltdot;": '\U000022D6', - "lthree;": '\U000022CB', - "ltimes;": '\U000022C9', - "ltlarr;": '\U00002976', - "ltquest;": '\U00002A7B', - "ltrPar;": '\U00002996', - "ltri;": '\U000025C3', - "ltrie;": '\U000022B4', - "ltrif;": '\U000025C2', - "lurdshar;": '\U0000294A', - "luruhar;": '\U00002966', - "mDDot;": '\U0000223A', - "macr;": '\U000000AF', - "male;": '\U00002642', - "malt;": '\U00002720', - "maltese;": '\U00002720', - "map;": '\U000021A6', - "mapsto;": '\U000021A6', - "mapstodown;": '\U000021A7', - "mapstoleft;": '\U000021A4', - "mapstoup;": '\U000021A5', - "marker;": '\U000025AE', - "mcomma;": '\U00002A29', - "mcy;": '\U0000043C', - "mdash;": '\U00002014', - "measuredangle;": '\U00002221', - "mfr;": '\U0001D52A', - "mho;": '\U00002127', - "micro;": '\U000000B5', - "mid;": '\U00002223', - "midast;": '\U0000002A', - "midcir;": '\U00002AF0', - "middot;": '\U000000B7', - "minus;": '\U00002212', - "minusb;": '\U0000229F', - "minusd;": '\U00002238', - "minusdu;": '\U00002A2A', - "mlcp;": '\U00002ADB', - "mldr;": '\U00002026', - "mnplus;": '\U00002213', - "models;": '\U000022A7', - "mopf;": '\U0001D55E', - "mp;": '\U00002213', - "mscr;": '\U0001D4C2', - "mstpos;": '\U0000223E', - "mu;": '\U000003BC', - "multimap;": '\U000022B8', - "mumap;": '\U000022B8', - "nLeftarrow;": '\U000021CD', - "nLeftrightarrow;": '\U000021CE', - "nRightarrow;": '\U000021CF', - "nVDash;": '\U000022AF', - "nVdash;": '\U000022AE', - "nabla;": '\U00002207', - "nacute;": '\U00000144', - "nap;": '\U00002249', - "napos;": '\U00000149', - "napprox;": '\U00002249', - "natur;": '\U0000266E', - "natural;": '\U0000266E', - "naturals;": '\U00002115', - "nbsp;": '\U000000A0', - "ncap;": '\U00002A43', - "ncaron;": '\U00000148', - "ncedil;": '\U00000146', - "ncong;": '\U00002247', - "ncup;": '\U00002A42', - "ncy;": '\U0000043D', - "ndash;": '\U00002013', - "ne;": '\U00002260', - "neArr;": '\U000021D7', - "nearhk;": '\U00002924', - "nearr;": '\U00002197', - "nearrow;": '\U00002197', - "nequiv;": '\U00002262', - "nesear;": '\U00002928', - "nexist;": '\U00002204', - "nexists;": '\U00002204', - "nfr;": '\U0001D52B', - "nge;": '\U00002271', - "ngeq;": '\U00002271', - "ngsim;": '\U00002275', - "ngt;": '\U0000226F', - "ngtr;": '\U0000226F', - "nhArr;": '\U000021CE', - "nharr;": '\U000021AE', - "nhpar;": '\U00002AF2', - "ni;": '\U0000220B', - "nis;": '\U000022FC', - "nisd;": '\U000022FA', - "niv;": '\U0000220B', - "njcy;": '\U0000045A', - "nlArr;": '\U000021CD', - "nlarr;": '\U0000219A', - "nldr;": '\U00002025', - "nle;": '\U00002270', - "nleftarrow;": '\U0000219A', - "nleftrightarrow;": '\U000021AE', - "nleq;": '\U00002270', - "nless;": '\U0000226E', - "nlsim;": '\U00002274', - "nlt;": '\U0000226E', - "nltri;": '\U000022EA', - "nltrie;": '\U000022EC', - "nmid;": '\U00002224', - "nopf;": '\U0001D55F', - "not;": '\U000000AC', - "notin;": '\U00002209', - "notinva;": '\U00002209', - "notinvb;": '\U000022F7', - "notinvc;": '\U000022F6', - "notni;": '\U0000220C', - "notniva;": '\U0000220C', - "notnivb;": '\U000022FE', - "notnivc;": '\U000022FD', - "npar;": '\U00002226', - "nparallel;": '\U00002226', - "npolint;": '\U00002A14', - "npr;": '\U00002280', - "nprcue;": '\U000022E0', - "nprec;": '\U00002280', - "nrArr;": '\U000021CF', - "nrarr;": '\U0000219B', - "nrightarrow;": '\U0000219B', - "nrtri;": '\U000022EB', - "nrtrie;": '\U000022ED', - "nsc;": '\U00002281', - "nsccue;": '\U000022E1', - "nscr;": '\U0001D4C3', - "nshortmid;": '\U00002224', - "nshortparallel;": '\U00002226', - "nsim;": '\U00002241', - "nsime;": '\U00002244', - "nsimeq;": '\U00002244', - "nsmid;": '\U00002224', - "nspar;": '\U00002226', - "nsqsube;": '\U000022E2', - "nsqsupe;": '\U000022E3', - "nsub;": '\U00002284', - "nsube;": '\U00002288', - "nsubseteq;": '\U00002288', - "nsucc;": '\U00002281', - "nsup;": '\U00002285', - "nsupe;": '\U00002289', - "nsupseteq;": '\U00002289', - "ntgl;": '\U00002279', - "ntilde;": '\U000000F1', - "ntlg;": '\U00002278', - "ntriangleleft;": '\U000022EA', - "ntrianglelefteq;": '\U000022EC', - "ntriangleright;": '\U000022EB', - "ntrianglerighteq;": '\U000022ED', - "nu;": '\U000003BD', - "num;": '\U00000023', - "numero;": '\U00002116', - "numsp;": '\U00002007', - "nvDash;": '\U000022AD', - "nvHarr;": '\U00002904', - "nvdash;": '\U000022AC', - "nvinfin;": '\U000029DE', - "nvlArr;": '\U00002902', - "nvrArr;": '\U00002903', - "nwArr;": '\U000021D6', - "nwarhk;": '\U00002923', - "nwarr;": '\U00002196', - "nwarrow;": '\U00002196', - "nwnear;": '\U00002927', - "oS;": '\U000024C8', - "oacute;": '\U000000F3', - "oast;": '\U0000229B', - "ocir;": '\U0000229A', - "ocirc;": '\U000000F4', - "ocy;": '\U0000043E', - "odash;": '\U0000229D', - "odblac;": '\U00000151', - "odiv;": '\U00002A38', - "odot;": '\U00002299', - "odsold;": '\U000029BC', - "oelig;": '\U00000153', - "ofcir;": '\U000029BF', - "ofr;": '\U0001D52C', - "ogon;": '\U000002DB', - "ograve;": '\U000000F2', - "ogt;": '\U000029C1', - "ohbar;": '\U000029B5', - "ohm;": '\U000003A9', - "oint;": '\U0000222E', - "olarr;": '\U000021BA', - "olcir;": '\U000029BE', - "olcross;": '\U000029BB', - "oline;": '\U0000203E', - "olt;": '\U000029C0', - "omacr;": '\U0000014D', - "omega;": '\U000003C9', - "omicron;": '\U000003BF', - "omid;": '\U000029B6', - "ominus;": '\U00002296', - "oopf;": '\U0001D560', - "opar;": '\U000029B7', - "operp;": '\U000029B9', - "oplus;": '\U00002295', - "or;": '\U00002228', - "orarr;": '\U000021BB', - "ord;": '\U00002A5D', - "order;": '\U00002134', - "orderof;": '\U00002134', - "ordf;": '\U000000AA', - "ordm;": '\U000000BA', - "origof;": '\U000022B6', - "oror;": '\U00002A56', - "orslope;": '\U00002A57', - "orv;": '\U00002A5B', - "oscr;": '\U00002134', - "oslash;": '\U000000F8', - "osol;": '\U00002298', - "otilde;": '\U000000F5', - "otimes;": '\U00002297', - "otimesas;": '\U00002A36', - "ouml;": '\U000000F6', - "ovbar;": '\U0000233D', - "par;": '\U00002225', - "para;": '\U000000B6', - "parallel;": '\U00002225', - "parsim;": '\U00002AF3', - "parsl;": '\U00002AFD', - "part;": '\U00002202', - "pcy;": '\U0000043F', - "percnt;": '\U00000025', - "period;": '\U0000002E', - "permil;": '\U00002030', - "perp;": '\U000022A5', - "pertenk;": '\U00002031', - "pfr;": '\U0001D52D', - "phi;": '\U000003C6', - "phiv;": '\U000003D5', - "phmmat;": '\U00002133', - "phone;": '\U0000260E', - "pi;": '\U000003C0', - "pitchfork;": '\U000022D4', - "piv;": '\U000003D6', - "planck;": '\U0000210F', - "planckh;": '\U0000210E', - "plankv;": '\U0000210F', - "plus;": '\U0000002B', - "plusacir;": '\U00002A23', - "plusb;": '\U0000229E', - "pluscir;": '\U00002A22', - "plusdo;": '\U00002214', - "plusdu;": '\U00002A25', - "pluse;": '\U00002A72', - "plusmn;": '\U000000B1', - "plussim;": '\U00002A26', - "plustwo;": '\U00002A27', - "pm;": '\U000000B1', - "pointint;": '\U00002A15', - "popf;": '\U0001D561', - "pound;": '\U000000A3', - "pr;": '\U0000227A', - "prE;": '\U00002AB3', - "prap;": '\U00002AB7', - "prcue;": '\U0000227C', - "pre;": '\U00002AAF', - "prec;": '\U0000227A', - "precapprox;": '\U00002AB7', - "preccurlyeq;": '\U0000227C', - "preceq;": '\U00002AAF', - "precnapprox;": '\U00002AB9', - "precneqq;": '\U00002AB5', - "precnsim;": '\U000022E8', - "precsim;": '\U0000227E', - "prime;": '\U00002032', - "primes;": '\U00002119', - "prnE;": '\U00002AB5', - "prnap;": '\U00002AB9', - "prnsim;": '\U000022E8', - "prod;": '\U0000220F', - "profalar;": '\U0000232E', - "profline;": '\U00002312', - "profsurf;": '\U00002313', - "prop;": '\U0000221D', - "propto;": '\U0000221D', - "prsim;": '\U0000227E', - "prurel;": '\U000022B0', - "pscr;": '\U0001D4C5', - "psi;": '\U000003C8', - "puncsp;": '\U00002008', - "qfr;": '\U0001D52E', - "qint;": '\U00002A0C', - "qopf;": '\U0001D562', - "qprime;": '\U00002057', - "qscr;": '\U0001D4C6', - "quaternions;": '\U0000210D', - "quatint;": '\U00002A16', - "quest;": '\U0000003F', - "questeq;": '\U0000225F', - "quot;": '\U00000022', - "rAarr;": '\U000021DB', - "rArr;": '\U000021D2', - "rAtail;": '\U0000291C', - "rBarr;": '\U0000290F', - "rHar;": '\U00002964', - "racute;": '\U00000155', - "radic;": '\U0000221A', - "raemptyv;": '\U000029B3', - "rang;": '\U000027E9', - "rangd;": '\U00002992', - "range;": '\U000029A5', - "rangle;": '\U000027E9', - "raquo;": '\U000000BB', - "rarr;": '\U00002192', - "rarrap;": '\U00002975', - "rarrb;": '\U000021E5', - "rarrbfs;": '\U00002920', - "rarrc;": '\U00002933', - "rarrfs;": '\U0000291E', - "rarrhk;": '\U000021AA', - "rarrlp;": '\U000021AC', - "rarrpl;": '\U00002945', - "rarrsim;": '\U00002974', - "rarrtl;": '\U000021A3', - "rarrw;": '\U0000219D', - "ratail;": '\U0000291A', - "ratio;": '\U00002236', - "rationals;": '\U0000211A', - "rbarr;": '\U0000290D', - "rbbrk;": '\U00002773', - "rbrace;": '\U0000007D', - "rbrack;": '\U0000005D', - "rbrke;": '\U0000298C', - "rbrksld;": '\U0000298E', - "rbrkslu;": '\U00002990', - "rcaron;": '\U00000159', - "rcedil;": '\U00000157', - "rceil;": '\U00002309', - "rcub;": '\U0000007D', - "rcy;": '\U00000440', - "rdca;": '\U00002937', - "rdldhar;": '\U00002969', - "rdquo;": '\U0000201D', - "rdquor;": '\U0000201D', - "rdsh;": '\U000021B3', - "real;": '\U0000211C', - "realine;": '\U0000211B', - "realpart;": '\U0000211C', - "reals;": '\U0000211D', - "rect;": '\U000025AD', - "reg;": '\U000000AE', - "rfisht;": '\U0000297D', - "rfloor;": '\U0000230B', - "rfr;": '\U0001D52F', - "rhard;": '\U000021C1', - "rharu;": '\U000021C0', - "rharul;": '\U0000296C', - "rho;": '\U000003C1', - "rhov;": '\U000003F1', - "rightarrow;": '\U00002192', - "rightarrowtail;": '\U000021A3', - "rightharpoondown;": '\U000021C1', - "rightharpoonup;": '\U000021C0', - "rightleftarrows;": '\U000021C4', - "rightleftharpoons;": '\U000021CC', - "rightrightarrows;": '\U000021C9', - "rightsquigarrow;": '\U0000219D', - "rightthreetimes;": '\U000022CC', - "ring;": '\U000002DA', - "risingdotseq;": '\U00002253', - "rlarr;": '\U000021C4', - "rlhar;": '\U000021CC', - "rlm;": '\U0000200F', - "rmoust;": '\U000023B1', - "rmoustache;": '\U000023B1', - "rnmid;": '\U00002AEE', - "roang;": '\U000027ED', - "roarr;": '\U000021FE', - "robrk;": '\U000027E7', - "ropar;": '\U00002986', - "ropf;": '\U0001D563', - "roplus;": '\U00002A2E', - "rotimes;": '\U00002A35', - "rpar;": '\U00000029', - "rpargt;": '\U00002994', - "rppolint;": '\U00002A12', - "rrarr;": '\U000021C9', - "rsaquo;": '\U0000203A', - "rscr;": '\U0001D4C7', - "rsh;": '\U000021B1', - "rsqb;": '\U0000005D', - "rsquo;": '\U00002019', - "rsquor;": '\U00002019', - "rthree;": '\U000022CC', - "rtimes;": '\U000022CA', - "rtri;": '\U000025B9', - "rtrie;": '\U000022B5', - "rtrif;": '\U000025B8', - "rtriltri;": '\U000029CE', - "ruluhar;": '\U00002968', - "rx;": '\U0000211E', - "sacute;": '\U0000015B', - "sbquo;": '\U0000201A', - "sc;": '\U0000227B', - "scE;": '\U00002AB4', - "scap;": '\U00002AB8', - "scaron;": '\U00000161', - "sccue;": '\U0000227D', - "sce;": '\U00002AB0', - "scedil;": '\U0000015F', - "scirc;": '\U0000015D', - "scnE;": '\U00002AB6', - "scnap;": '\U00002ABA', - "scnsim;": '\U000022E9', - "scpolint;": '\U00002A13', - "scsim;": '\U0000227F', - "scy;": '\U00000441', - "sdot;": '\U000022C5', - "sdotb;": '\U000022A1', - "sdote;": '\U00002A66', - "seArr;": '\U000021D8', - "searhk;": '\U00002925', - "searr;": '\U00002198', - "searrow;": '\U00002198', - "sect;": '\U000000A7', - "semi;": '\U0000003B', - "seswar;": '\U00002929', - "setminus;": '\U00002216', - "setmn;": '\U00002216', - "sext;": '\U00002736', - "sfr;": '\U0001D530', - "sfrown;": '\U00002322', - "sharp;": '\U0000266F', - "shchcy;": '\U00000449', - "shcy;": '\U00000448', - "shortmid;": '\U00002223', - "shortparallel;": '\U00002225', - "shy;": '\U000000AD', - "sigma;": '\U000003C3', - "sigmaf;": '\U000003C2', - "sigmav;": '\U000003C2', - "sim;": '\U0000223C', - "simdot;": '\U00002A6A', - "sime;": '\U00002243', - "simeq;": '\U00002243', - "simg;": '\U00002A9E', - "simgE;": '\U00002AA0', - "siml;": '\U00002A9D', - "simlE;": '\U00002A9F', - "simne;": '\U00002246', - "simplus;": '\U00002A24', - "simrarr;": '\U00002972', - "slarr;": '\U00002190', - "smallsetminus;": '\U00002216', - "smashp;": '\U00002A33', - "smeparsl;": '\U000029E4', - "smid;": '\U00002223', - "smile;": '\U00002323', - "smt;": '\U00002AAA', - "smte;": '\U00002AAC', - "softcy;": '\U0000044C', - "sol;": '\U0000002F', - "solb;": '\U000029C4', - "solbar;": '\U0000233F', - "sopf;": '\U0001D564', - "spades;": '\U00002660', - "spadesuit;": '\U00002660', - "spar;": '\U00002225', - "sqcap;": '\U00002293', - "sqcup;": '\U00002294', - "sqsub;": '\U0000228F', - "sqsube;": '\U00002291', - "sqsubset;": '\U0000228F', - "sqsubseteq;": '\U00002291', - "sqsup;": '\U00002290', - "sqsupe;": '\U00002292', - "sqsupset;": '\U00002290', - "sqsupseteq;": '\U00002292', - "squ;": '\U000025A1', - "square;": '\U000025A1', - "squarf;": '\U000025AA', - "squf;": '\U000025AA', - "srarr;": '\U00002192', - "sscr;": '\U0001D4C8', - "ssetmn;": '\U00002216', - "ssmile;": '\U00002323', - "sstarf;": '\U000022C6', - "star;": '\U00002606', - "starf;": '\U00002605', - "straightepsilon;": '\U000003F5', - "straightphi;": '\U000003D5', - "strns;": '\U000000AF', - "sub;": '\U00002282', - "subE;": '\U00002AC5', - "subdot;": '\U00002ABD', - "sube;": '\U00002286', - "subedot;": '\U00002AC3', - "submult;": '\U00002AC1', - "subnE;": '\U00002ACB', - "subne;": '\U0000228A', - "subplus;": '\U00002ABF', - "subrarr;": '\U00002979', - "subset;": '\U00002282', - "subseteq;": '\U00002286', - "subseteqq;": '\U00002AC5', - "subsetneq;": '\U0000228A', - "subsetneqq;": '\U00002ACB', - "subsim;": '\U00002AC7', - "subsub;": '\U00002AD5', - "subsup;": '\U00002AD3', - "succ;": '\U0000227B', - "succapprox;": '\U00002AB8', - "succcurlyeq;": '\U0000227D', - "succeq;": '\U00002AB0', - "succnapprox;": '\U00002ABA', - "succneqq;": '\U00002AB6', - "succnsim;": '\U000022E9', - "succsim;": '\U0000227F', - "sum;": '\U00002211', - "sung;": '\U0000266A', - "sup;": '\U00002283', - "sup1;": '\U000000B9', - "sup2;": '\U000000B2', - "sup3;": '\U000000B3', - "supE;": '\U00002AC6', - "supdot;": '\U00002ABE', - "supdsub;": '\U00002AD8', - "supe;": '\U00002287', - "supedot;": '\U00002AC4', - "suphsol;": '\U000027C9', - "suphsub;": '\U00002AD7', - "suplarr;": '\U0000297B', - "supmult;": '\U00002AC2', - "supnE;": '\U00002ACC', - "supne;": '\U0000228B', - "supplus;": '\U00002AC0', - "supset;": '\U00002283', - "supseteq;": '\U00002287', - "supseteqq;": '\U00002AC6', - "supsetneq;": '\U0000228B', - "supsetneqq;": '\U00002ACC', - "supsim;": '\U00002AC8', - "supsub;": '\U00002AD4', - "supsup;": '\U00002AD6', - "swArr;": '\U000021D9', - "swarhk;": '\U00002926', - "swarr;": '\U00002199', - "swarrow;": '\U00002199', - "swnwar;": '\U0000292A', - "szlig;": '\U000000DF', - "target;": '\U00002316', - "tau;": '\U000003C4', - "tbrk;": '\U000023B4', - "tcaron;": '\U00000165', - "tcedil;": '\U00000163', - "tcy;": '\U00000442', - "tdot;": '\U000020DB', - "telrec;": '\U00002315', - "tfr;": '\U0001D531', - "there4;": '\U00002234', - "therefore;": '\U00002234', - "theta;": '\U000003B8', - "thetasym;": '\U000003D1', - "thetav;": '\U000003D1', - "thickapprox;": '\U00002248', - "thicksim;": '\U0000223C', - "thinsp;": '\U00002009', - "thkap;": '\U00002248', - "thksim;": '\U0000223C', - "thorn;": '\U000000FE', - "tilde;": '\U000002DC', - "times;": '\U000000D7', - "timesb;": '\U000022A0', - "timesbar;": '\U00002A31', - "timesd;": '\U00002A30', - "tint;": '\U0000222D', - "toea;": '\U00002928', - "top;": '\U000022A4', - "topbot;": '\U00002336', - "topcir;": '\U00002AF1', - "topf;": '\U0001D565', - "topfork;": '\U00002ADA', - "tosa;": '\U00002929', - "tprime;": '\U00002034', - "trade;": '\U00002122', - "triangle;": '\U000025B5', - "triangledown;": '\U000025BF', - "triangleleft;": '\U000025C3', - "trianglelefteq;": '\U000022B4', - "triangleq;": '\U0000225C', - "triangleright;": '\U000025B9', - "trianglerighteq;": '\U000022B5', - "tridot;": '\U000025EC', - "trie;": '\U0000225C', - "triminus;": '\U00002A3A', - "triplus;": '\U00002A39', - "trisb;": '\U000029CD', - "tritime;": '\U00002A3B', - "trpezium;": '\U000023E2', - "tscr;": '\U0001D4C9', - "tscy;": '\U00000446', - "tshcy;": '\U0000045B', - "tstrok;": '\U00000167', - "twixt;": '\U0000226C', - "twoheadleftarrow;": '\U0000219E', - "twoheadrightarrow;": '\U000021A0', - "uArr;": '\U000021D1', - "uHar;": '\U00002963', - "uacute;": '\U000000FA', - "uarr;": '\U00002191', - "ubrcy;": '\U0000045E', - "ubreve;": '\U0000016D', - "ucirc;": '\U000000FB', - "ucy;": '\U00000443', - "udarr;": '\U000021C5', - "udblac;": '\U00000171', - "udhar;": '\U0000296E', - "ufisht;": '\U0000297E', - "ufr;": '\U0001D532', - "ugrave;": '\U000000F9', - "uharl;": '\U000021BF', - "uharr;": '\U000021BE', - "uhblk;": '\U00002580', - "ulcorn;": '\U0000231C', - "ulcorner;": '\U0000231C', - "ulcrop;": '\U0000230F', - "ultri;": '\U000025F8', - "umacr;": '\U0000016B', - "uml;": '\U000000A8', - "uogon;": '\U00000173', - "uopf;": '\U0001D566', - "uparrow;": '\U00002191', - "updownarrow;": '\U00002195', - "upharpoonleft;": '\U000021BF', - "upharpoonright;": '\U000021BE', - "uplus;": '\U0000228E', - "upsi;": '\U000003C5', - "upsih;": '\U000003D2', - "upsilon;": '\U000003C5', - "upuparrows;": '\U000021C8', - "urcorn;": '\U0000231D', - "urcorner;": '\U0000231D', - "urcrop;": '\U0000230E', - "uring;": '\U0000016F', - "urtri;": '\U000025F9', - "uscr;": '\U0001D4CA', - "utdot;": '\U000022F0', - "utilde;": '\U00000169', - "utri;": '\U000025B5', - "utrif;": '\U000025B4', - "uuarr;": '\U000021C8', - "uuml;": '\U000000FC', - "uwangle;": '\U000029A7', - "vArr;": '\U000021D5', - "vBar;": '\U00002AE8', - "vBarv;": '\U00002AE9', - "vDash;": '\U000022A8', - "vangrt;": '\U0000299C', - "varepsilon;": '\U000003F5', - "varkappa;": '\U000003F0', - "varnothing;": '\U00002205', - "varphi;": '\U000003D5', - "varpi;": '\U000003D6', - "varpropto;": '\U0000221D', - "varr;": '\U00002195', - "varrho;": '\U000003F1', - "varsigma;": '\U000003C2', - "vartheta;": '\U000003D1', - "vartriangleleft;": '\U000022B2', - "vartriangleright;": '\U000022B3', - "vcy;": '\U00000432', - "vdash;": '\U000022A2', - "vee;": '\U00002228', - "veebar;": '\U000022BB', - "veeeq;": '\U0000225A', - "vellip;": '\U000022EE', - "verbar;": '\U0000007C', - "vert;": '\U0000007C', - "vfr;": '\U0001D533', - "vltri;": '\U000022B2', - "vopf;": '\U0001D567', - "vprop;": '\U0000221D', - "vrtri;": '\U000022B3', - "vscr;": '\U0001D4CB', - "vzigzag;": '\U0000299A', - "wcirc;": '\U00000175', - "wedbar;": '\U00002A5F', - "wedge;": '\U00002227', - "wedgeq;": '\U00002259', - "weierp;": '\U00002118', - "wfr;": '\U0001D534', - "wopf;": '\U0001D568', - "wp;": '\U00002118', - "wr;": '\U00002240', - "wreath;": '\U00002240', - "wscr;": '\U0001D4CC', - "xcap;": '\U000022C2', - "xcirc;": '\U000025EF', - "xcup;": '\U000022C3', - "xdtri;": '\U000025BD', - "xfr;": '\U0001D535', - "xhArr;": '\U000027FA', - "xharr;": '\U000027F7', - "xi;": '\U000003BE', - "xlArr;": '\U000027F8', - "xlarr;": '\U000027F5', - "xmap;": '\U000027FC', - "xnis;": '\U000022FB', - "xodot;": '\U00002A00', - "xopf;": '\U0001D569', - "xoplus;": '\U00002A01', - "xotime;": '\U00002A02', - "xrArr;": '\U000027F9', - "xrarr;": '\U000027F6', - "xscr;": '\U0001D4CD', - "xsqcup;": '\U00002A06', - "xuplus;": '\U00002A04', - "xutri;": '\U000025B3', - "xvee;": '\U000022C1', - "xwedge;": '\U000022C0', - "yacute;": '\U000000FD', - "yacy;": '\U0000044F', - "ycirc;": '\U00000177', - "ycy;": '\U0000044B', - "yen;": '\U000000A5', - "yfr;": '\U0001D536', - "yicy;": '\U00000457', - "yopf;": '\U0001D56A', - "yscr;": '\U0001D4CE', - "yucy;": '\U0000044E', - "yuml;": '\U000000FF', - "zacute;": '\U0000017A', - "zcaron;": '\U0000017E', - "zcy;": '\U00000437', - "zdot;": '\U0000017C', - "zeetrf;": '\U00002128', - "zeta;": '\U000003B6', - "zfr;": '\U0001D537', - "zhcy;": '\U00000436', - "zigrarr;": '\U000021DD', - "zopf;": '\U0001D56B', - "zscr;": '\U0001D4CF', - "zwj;": '\U0000200D', - "zwnj;": '\U0000200C', - "AElig": '\U000000C6', - "AMP": '\U00000026', - "Aacute": '\U000000C1', - "Acirc": '\U000000C2', - "Agrave": '\U000000C0', - "Aring": '\U000000C5', - "Atilde": '\U000000C3', - "Auml": '\U000000C4', - "COPY": '\U000000A9', - "Ccedil": '\U000000C7', - "ETH": '\U000000D0', - "Eacute": '\U000000C9', - "Ecirc": '\U000000CA', - "Egrave": '\U000000C8', - "Euml": '\U000000CB', - "GT": '\U0000003E', - "Iacute": '\U000000CD', - "Icirc": '\U000000CE', - "Igrave": '\U000000CC', - "Iuml": '\U000000CF', - "LT": '\U0000003C', - "Ntilde": '\U000000D1', - "Oacute": '\U000000D3', - "Ocirc": '\U000000D4', - "Ograve": '\U000000D2', - "Oslash": '\U000000D8', - "Otilde": '\U000000D5', - "Ouml": '\U000000D6', - "QUOT": '\U00000022', - "REG": '\U000000AE', - "THORN": '\U000000DE', - "Uacute": '\U000000DA', - "Ucirc": '\U000000DB', - "Ugrave": '\U000000D9', - "Uuml": '\U000000DC', - "Yacute": '\U000000DD', - "aacute": '\U000000E1', - "acirc": '\U000000E2', - "acute": '\U000000B4', - "aelig": '\U000000E6', - "agrave": '\U000000E0', - "amp": '\U00000026', - "aring": '\U000000E5', - "atilde": '\U000000E3', - "auml": '\U000000E4', - "brvbar": '\U000000A6', - "ccedil": '\U000000E7', - "cedil": '\U000000B8', - "cent": '\U000000A2', - "copy": '\U000000A9', - "curren": '\U000000A4', - "deg": '\U000000B0', - "divide": '\U000000F7', - "eacute": '\U000000E9', - "ecirc": '\U000000EA', - "egrave": '\U000000E8', - "eth": '\U000000F0', - "euml": '\U000000EB', - "frac12": '\U000000BD', - "frac14": '\U000000BC', - "frac34": '\U000000BE', - "gt": '\U0000003E', - "iacute": '\U000000ED', - "icirc": '\U000000EE', - "iexcl": '\U000000A1', - "igrave": '\U000000EC', - "iquest": '\U000000BF', - "iuml": '\U000000EF', - "laquo": '\U000000AB', - "lt": '\U0000003C', - "macr": '\U000000AF', - "micro": '\U000000B5', - "middot": '\U000000B7', - "nbsp": '\U000000A0', - "not": '\U000000AC', - "ntilde": '\U000000F1', - "oacute": '\U000000F3', - "ocirc": '\U000000F4', - "ograve": '\U000000F2', - "ordf": '\U000000AA', - "ordm": '\U000000BA', - "oslash": '\U000000F8', - "otilde": '\U000000F5', - "ouml": '\U000000F6', - "para": '\U000000B6', - "plusmn": '\U000000B1', - "pound": '\U000000A3', - "quot": '\U00000022', - "raquo": '\U000000BB', - "reg": '\U000000AE', - "sect": '\U000000A7', - "shy": '\U000000AD', - "sup1": '\U000000B9', - "sup2": '\U000000B2', - "sup3": '\U000000B3', - "szlig": '\U000000DF', - "thorn": '\U000000FE', - "times": '\U000000D7', - "uacute": '\U000000FA', - "ucirc": '\U000000FB', - "ugrave": '\U000000F9', - "uml": '\U000000A8', - "uuml": '\U000000FC', - "yacute": '\U000000FD', - "yen": '\U000000A5', - "yuml": '\U000000FF', -} - -// HTML entities that are two unicode codepoints. -var entity2 = map[string][2]rune{ - // TODO(nigeltao): Handle replacements that are wider than their names. - // "nLt;": {'\u226A', '\u20D2'}, - // "nGt;": {'\u226B', '\u20D2'}, - "NotEqualTilde;": {'\u2242', '\u0338'}, - "NotGreaterFullEqual;": {'\u2267', '\u0338'}, - "NotGreaterGreater;": {'\u226B', '\u0338'}, - "NotGreaterSlantEqual;": {'\u2A7E', '\u0338'}, - "NotHumpDownHump;": {'\u224E', '\u0338'}, - "NotHumpEqual;": {'\u224F', '\u0338'}, - "NotLeftTriangleBar;": {'\u29CF', '\u0338'}, - "NotLessLess;": {'\u226A', '\u0338'}, - "NotLessSlantEqual;": {'\u2A7D', '\u0338'}, - "NotNestedGreaterGreater;": {'\u2AA2', '\u0338'}, - "NotNestedLessLess;": {'\u2AA1', '\u0338'}, - "NotPrecedesEqual;": {'\u2AAF', '\u0338'}, - "NotRightTriangleBar;": {'\u29D0', '\u0338'}, - "NotSquareSubset;": {'\u228F', '\u0338'}, - "NotSquareSuperset;": {'\u2290', '\u0338'}, - "NotSubset;": {'\u2282', '\u20D2'}, - "NotSucceedsEqual;": {'\u2AB0', '\u0338'}, - "NotSucceedsTilde;": {'\u227F', '\u0338'}, - "NotSuperset;": {'\u2283', '\u20D2'}, - "ThickSpace;": {'\u205F', '\u200A'}, - "acE;": {'\u223E', '\u0333'}, - "bne;": {'\u003D', '\u20E5'}, - "bnequiv;": {'\u2261', '\u20E5'}, - "caps;": {'\u2229', '\uFE00'}, - "cups;": {'\u222A', '\uFE00'}, - "fjlig;": {'\u0066', '\u006A'}, - "gesl;": {'\u22DB', '\uFE00'}, - "gvertneqq;": {'\u2269', '\uFE00'}, - "gvnE;": {'\u2269', '\uFE00'}, - "lates;": {'\u2AAD', '\uFE00'}, - "lesg;": {'\u22DA', '\uFE00'}, - "lvertneqq;": {'\u2268', '\uFE00'}, - "lvnE;": {'\u2268', '\uFE00'}, - "nGg;": {'\u22D9', '\u0338'}, - "nGtv;": {'\u226B', '\u0338'}, - "nLl;": {'\u22D8', '\u0338'}, - "nLtv;": {'\u226A', '\u0338'}, - "nang;": {'\u2220', '\u20D2'}, - "napE;": {'\u2A70', '\u0338'}, - "napid;": {'\u224B', '\u0338'}, - "nbump;": {'\u224E', '\u0338'}, - "nbumpe;": {'\u224F', '\u0338'}, - "ncongdot;": {'\u2A6D', '\u0338'}, - "nedot;": {'\u2250', '\u0338'}, - "nesim;": {'\u2242', '\u0338'}, - "ngE;": {'\u2267', '\u0338'}, - "ngeqq;": {'\u2267', '\u0338'}, - "ngeqslant;": {'\u2A7E', '\u0338'}, - "nges;": {'\u2A7E', '\u0338'}, - "nlE;": {'\u2266', '\u0338'}, - "nleqq;": {'\u2266', '\u0338'}, - "nleqslant;": {'\u2A7D', '\u0338'}, - "nles;": {'\u2A7D', '\u0338'}, - "notinE;": {'\u22F9', '\u0338'}, - "notindot;": {'\u22F5', '\u0338'}, - "nparsl;": {'\u2AFD', '\u20E5'}, - "npart;": {'\u2202', '\u0338'}, - "npre;": {'\u2AAF', '\u0338'}, - "npreceq;": {'\u2AAF', '\u0338'}, - "nrarrc;": {'\u2933', '\u0338'}, - "nrarrw;": {'\u219D', '\u0338'}, - "nsce;": {'\u2AB0', '\u0338'}, - "nsubE;": {'\u2AC5', '\u0338'}, - "nsubset;": {'\u2282', '\u20D2'}, - "nsubseteqq;": {'\u2AC5', '\u0338'}, - "nsucceq;": {'\u2AB0', '\u0338'}, - "nsupE;": {'\u2AC6', '\u0338'}, - "nsupset;": {'\u2283', '\u20D2'}, - "nsupseteqq;": {'\u2AC6', '\u0338'}, - "nvap;": {'\u224D', '\u20D2'}, - "nvge;": {'\u2265', '\u20D2'}, - "nvgt;": {'\u003E', '\u20D2'}, - "nvle;": {'\u2264', '\u20D2'}, - "nvlt;": {'\u003C', '\u20D2'}, - "nvltrie;": {'\u22B4', '\u20D2'}, - "nvrtrie;": {'\u22B5', '\u20D2'}, - "nvsim;": {'\u223C', '\u20D2'}, - "race;": {'\u223D', '\u0331'}, - "smtes;": {'\u2AAC', '\uFE00'}, - "sqcaps;": {'\u2293', '\uFE00'}, - "sqcups;": {'\u2294', '\uFE00'}, - "varsubsetneq;": {'\u228A', '\uFE00'}, - "varsubsetneqq;": {'\u2ACB', '\uFE00'}, - "varsupsetneq;": {'\u228B', '\uFE00'}, - "varsupsetneqq;": {'\u2ACC', '\uFE00'}, - "vnsub;": {'\u2282', '\u20D2'}, - "vnsup;": {'\u2283', '\u20D2'}, - "vsubnE;": {'\u2ACB', '\uFE00'}, - "vsubne;": {'\u228A', '\uFE00'}, - "vsupnE;": {'\u2ACC', '\uFE00'}, - "vsupne;": {'\u228B', '\uFE00'}, -} diff --git a/src/vendor/golang.org/x/net/html/escape.go b/src/vendor/golang.org/x/net/html/escape.go deleted file mode 100644 index 04c6bec..0000000 --- a/src/vendor/golang.org/x/net/html/escape.go +++ /dev/null @@ -1,339 +0,0 @@ -// Copyright 2010 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -package html - -import ( - "bytes" - "strings" - "unicode/utf8" -) - -// These replacements permit compatibility with old numeric entities that -// assumed Windows-1252 encoding. -// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference -var replacementTable = [...]rune{ - '\u20AC', // First entry is what 0x80 should be replaced with. - '\u0081', - '\u201A', - '\u0192', - '\u201E', - '\u2026', - '\u2020', - '\u2021', - '\u02C6', - '\u2030', - '\u0160', - '\u2039', - '\u0152', - '\u008D', - '\u017D', - '\u008F', - '\u0090', - '\u2018', - '\u2019', - '\u201C', - '\u201D', - '\u2022', - '\u2013', - '\u2014', - '\u02DC', - '\u2122', - '\u0161', - '\u203A', - '\u0153', - '\u009D', - '\u017E', - '\u0178', // Last entry is 0x9F. - // 0x00->'\uFFFD' is handled programmatically. - // 0x0D->'\u000D' is a no-op. -} - -// unescapeEntity reads an entity like "<" from b[src:] and writes the -// corresponding "<" to b[dst:], returning the incremented dst and src cursors. -// Precondition: b[src] == '&' && dst <= src. -// attribute should be true if parsing an attribute value. -func unescapeEntity(b []byte, dst, src int, attribute bool) (dst1, src1 int) { - // https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference - - // i starts at 1 because we already know that s[0] == '&'. - i, s := 1, b[src:] - - if len(s) <= 1 { - b[dst] = b[src] - return dst + 1, src + 1 - } - - if s[i] == '#' { - if len(s) <= 3 { // We need to have at least "&#.". - b[dst] = b[src] - return dst + 1, src + 1 - } - i++ - c := s[i] - hex := false - if c == 'x' || c == 'X' { - hex = true - i++ - } - - x := '\x00' - for i < len(s) { - c = s[i] - i++ - if hex { - if '0' <= c && c <= '9' { - x = 16*x + rune(c) - '0' - continue - } else if 'a' <= c && c <= 'f' { - x = 16*x + rune(c) - 'a' + 10 - continue - } else if 'A' <= c && c <= 'F' { - x = 16*x + rune(c) - 'A' + 10 - continue - } - } else if '0' <= c && c <= '9' { - x = 10*x + rune(c) - '0' - continue - } - if c != ';' { - i-- - } - break - } - - if i <= 3 { // No characters matched. - b[dst] = b[src] - return dst + 1, src + 1 - } - - if 0x80 <= x && x <= 0x9F { - // Replace characters from Windows-1252 with UTF-8 equivalents. - x = replacementTable[x-0x80] - } else if x == 0 || (0xD800 <= x && x <= 0xDFFF) || x > 0x10FFFF { - // Replace invalid characters with the replacement character. - x = '\uFFFD' - } - - return dst + utf8.EncodeRune(b[dst:], x), src + i - } - - // Consume the maximum number of characters possible, with the - // consumed characters matching one of the named references. - - for i < len(s) { - c := s[i] - i++ - // Lower-cased characters are more common in entities, so we check for them first. - if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' { - continue - } - if c != ';' { - i-- - } - break - } - - entityName := string(s[1:i]) - if entityName == "" { - // No-op. - } else if attribute && entityName[len(entityName)-1] != ';' && len(s) > i && s[i] == '=' { - // No-op. - } else if x := entity[entityName]; x != 0 { - return dst + utf8.EncodeRune(b[dst:], x), src + i - } else if x := entity2[entityName]; x[0] != 0 { - dst1 := dst + utf8.EncodeRune(b[dst:], x[0]) - return dst1 + utf8.EncodeRune(b[dst1:], x[1]), src + i - } else if !attribute { - maxLen := len(entityName) - 1 - if maxLen > longestEntityWithoutSemicolon { - maxLen = longestEntityWithoutSemicolon - } - for j := maxLen; j > 1; j-- { - if x := entity[entityName[:j]]; x != 0 { - return dst + utf8.EncodeRune(b[dst:], x), src + j + 1 - } - } - } - - dst1, src1 = dst+i, src+i - copy(b[dst:dst1], b[src:src1]) - return dst1, src1 -} - -// unescape unescapes b's entities in-place, so that "a<b" becomes "a' byte that, per above, we'd like to avoid escaping unless we have to. -// -// Studying the summary table (and T actions in its '>' column) closely, we -// only need to escape in states 43, 44, 49, 51 and 52. State 43 is at the -// start of the comment data. State 52 is after a '!'. The other three states -// are after a '-'. -// -// Our algorithm is thus to escape every '&' and to escape '>' if and only if: -// - The '>' is after a '!' or '-' (in the unescaped data) or -// - The '>' is at the start of the comment data (after the opening ""); err != nil { - return err - } - return nil - case DoctypeNode: - if _, err := w.WriteString("') - case RawNode: - _, err := w.WriteString(n.Data) - return err - default: - return errors.New("html: unknown node type") - } - - // Render the opening tag. - if err := w.WriteByte('<'); err != nil { - return err - } - if _, err := w.WriteString(n.Data); err != nil { - return err - } - for _, a := range n.Attr { - if err := w.WriteByte(' '); err != nil { - return err - } - if a.Namespace != "" { - if _, err := w.WriteString(a.Namespace); err != nil { - return err - } - if err := w.WriteByte(':'); err != nil { - return err - } - } - if _, err := w.WriteString(a.Key); err != nil { - return err - } - if _, err := w.WriteString(`="`); err != nil { - return err - } - if err := escape(w, a.Val); err != nil { - return err - } - if err := w.WriteByte('"'); err != nil { - return err - } - } - if voidElements[n.Data] { - if n.FirstChild != nil { - return fmt.Errorf("html: void element <%s> has child nodes", n.Data) - } - _, err := w.WriteString("/>") - return err - } - if err := w.WriteByte('>'); err != nil { - return err - } - - // Add initial newline where there is danger of a newline beging ignored. - if c := n.FirstChild; c != nil && c.Type == TextNode && strings.HasPrefix(c.Data, "\n") { - switch n.Data { - case "pre", "listing", "textarea": - if err := w.WriteByte('\n'); err != nil { - return err - } - } - } - - // Render any child nodes - if childTextNodesAreLiteral(n) { - for c := n.FirstChild; c != nil; c = c.NextSibling { - if c.Type == TextNode { - if _, err := w.WriteString(c.Data); err != nil { - return err - } - } else { - if err := render1(w, c); err != nil { - return err - } - } - } - if n.Data == "plaintext" { - // Don't render anything else. must be the - // last element in the file, with no closing tag. - return plaintextAbort - } - } else { - for c := n.FirstChild; c != nil; c = c.NextSibling { - if err := render1(w, c); err != nil { - return err - } - } - } - - // Render the </xxx> closing tag. - if _, err := w.WriteString("</"); err != nil { - return err - } - if _, err := w.WriteString(n.Data); err != nil { - return err - } - return w.WriteByte('>') -} - -func childTextNodesAreLiteral(n *Node) bool { - // Per WHATWG HTML 13.3, if the parent of the current node is a style, - // script, xmp, iframe, noembed, noframes, or plaintext element, and the - // current node is a text node, append the value of the node's data - // literally. The specification is not explicit about it, but we only - // enforce this if we are in the HTML namespace (i.e. when the namespace is - // ""). - // NOTE: we also always include noscript elements, although the - // specification states that they should only be rendered as such if - // scripting is enabled for the node (which is not something we track). - if n.Namespace != "" { - return false - } - switch n.Data { - case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "xmp": - return true - default: - return false - } -} - -// writeQuoted writes s to w surrounded by quotes. Normally it will use double -// quotes, but if s contains a double quote, it will use single quotes. -// It is used for writing the identifiers in a doctype declaration. -// In valid HTML, they can't contain both types of quotes. -func writeQuoted(w writer, s string) error { - var q byte = '"' - if strings.Contains(s, `"`) { - q = '\'' - } - if err := w.WriteByte(q); err != nil { - return err - } - if _, err := w.WriteString(s); err != nil { - return err - } - if err := w.WriteByte(q); err != nil { - return err - } - return nil -} - -// Section 12.1.2, "Elements", gives this list of void elements. Void elements -// are those that can't have any contents. -var voidElements = map[string]bool{ - "area": true, - "base": true, - "br": true, - "col": true, - "embed": true, - "hr": true, - "img": true, - "input": true, - "keygen": true, // "keygen" has been removed from the spec, but are kept here for backwards compatibility. - "link": true, - "meta": true, - "param": true, - "source": true, - "track": true, - "wbr": true, -} diff --git a/src/vendor/golang.org/x/net/html/token.go b/src/vendor/golang.org/x/net/html/token.go deleted file mode 100644 index 6598c1f..0000000 --- a/src/vendor/golang.org/x/net/html/token.go +++ /dev/null @@ -1,1286 +0,0 @@ -// Copyright 2010 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -package html - -import ( - "bytes" - "errors" - "io" - "strconv" - "strings" - - "golang.org/x/net/html/atom" -) - -// A TokenType is the type of a Token. -type TokenType uint32 - -const ( - // ErrorToken means that an error occurred during tokenization. - ErrorToken TokenType = iota - // TextToken means a text node. - TextToken - // A StartTagToken looks like <a>. - StartTagToken - // An EndTagToken looks like </a>. - EndTagToken - // A SelfClosingTagToken tag looks like <br/>. - SelfClosingTagToken - // A CommentToken looks like <!--x-->. - CommentToken - // A DoctypeToken looks like <!DOCTYPE x> - DoctypeToken -) - -// ErrBufferExceeded means that the buffering limit was exceeded. -var ErrBufferExceeded = errors.New("max buffer exceeded") - -// String returns a string representation of the TokenType. -func (t TokenType) String() string { - switch t { - case ErrorToken: - return "Error" - case TextToken: - return "Text" - case StartTagToken: - return "StartTag" - case EndTagToken: - return "EndTag" - case SelfClosingTagToken: - return "SelfClosingTag" - case CommentToken: - return "Comment" - case DoctypeToken: - return "Doctype" - } - return "Invalid(" + strconv.Itoa(int(t)) + ")" -} - -// An Attribute is an attribute namespace-key-value triple. Namespace is -// non-empty for foreign attributes like xlink, Key is alphabetic (and hence -// does not contain escapable characters like '&', '<' or '>'), and Val is -// unescaped (it looks like "a<b" rather than "a&lt;b"). -// -// Namespace is only used by the parser, not the tokenizer. -type Attribute struct { - Namespace, Key, Val string -} - -// A Token consists of a TokenType and some Data (tag name for start and end -// tags, content for text, comments and doctypes). A tag Token may also contain -// a slice of Attributes. Data is unescaped for all Tokens (it looks like "a<b" -// rather than "a&lt;b"). For tag Tokens, DataAtom is the atom for Data, or -// zero if Data is not a known tag name. -type Token struct { - Type TokenType - DataAtom atom.Atom - Data string - Attr []Attribute -} - -// tagString returns a string representation of a tag Token's Data and Attr. -func (t Token) tagString() string { - if len(t.Attr) == 0 { - return t.Data - } - buf := bytes.NewBufferString(t.Data) - for _, a := range t.Attr { - buf.WriteByte(' ') - buf.WriteString(a.Key) - buf.WriteString(`="`) - escape(buf, a.Val) - buf.WriteByte('"') - } - return buf.String() -} - -// String returns a string representation of the Token. -func (t Token) String() string { - switch t.Type { - case ErrorToken: - return "" - case TextToken: - return EscapeString(t.Data) - case StartTagToken: - return "<" + t.tagString() + ">" - case EndTagToken: - return "</" + t.tagString() + ">" - case SelfClosingTagToken: - return "<" + t.tagString() + "/>" - case CommentToken: - return "<!--" + escapeCommentString(t.Data) + "-->" - case DoctypeToken: - return "<!DOCTYPE " + EscapeString(t.Data) + ">" - } - return "Invalid(" + strconv.Itoa(int(t.Type)) + ")" -} - -// span is a range of bytes in a Tokenizer's buffer. The start is inclusive, -// the end is exclusive. -type span struct { - start, end int -} - -// A Tokenizer returns a stream of HTML Tokens. -type Tokenizer struct { - // r is the source of the HTML text. - r io.Reader - // tt is the TokenType of the current token. - tt TokenType - // err is the first error encountered during tokenization. It is possible - // for tt != Error && err != nil to hold: this means that Next returned a - // valid token but the subsequent Next call will return an error token. - // For example, if the HTML text input was just "plain", then the first - // Next call would set z.err to io.EOF but return a TextToken, and all - // subsequent Next calls would return an ErrorToken. - // err is never reset. Once it becomes non-nil, it stays non-nil. - err error - // readErr is the error returned by the io.Reader r. It is separate from - // err because it is valid for an io.Reader to return (n int, err1 error) - // such that n > 0 && err1 != nil, and callers should always process the - // n > 0 bytes before considering the error err1. - readErr error - // buf[raw.start:raw.end] holds the raw bytes of the current token. - // buf[raw.end:] is buffered input that will yield future tokens. - raw span - buf []byte - // maxBuf limits the data buffered in buf. A value of 0 means unlimited. - maxBuf int - // buf[data.start:data.end] holds the raw bytes of the current token's data: - // a text token's text, a tag token's tag name, etc. - data span - // pendingAttr is the attribute key and value currently being tokenized. - // When complete, pendingAttr is pushed onto attr. nAttrReturned is - // incremented on each call to TagAttr. - pendingAttr [2]span - attr [][2]span - nAttrReturned int - // rawTag is the "script" in "</script>" that closes the next token. If - // non-empty, the subsequent call to Next will return a raw or RCDATA text - // token: one that treats "<p>" as text instead of an element. - // rawTag's contents are lower-cased. - rawTag string - // textIsRaw is whether the current text token's data is not escaped. - textIsRaw bool - // convertNUL is whether NUL bytes in the current token's data should - // be converted into \ufffd replacement characters. - convertNUL bool - // allowCDATA is whether CDATA sections are allowed in the current context. - allowCDATA bool -} - -// AllowCDATA sets whether or not the tokenizer recognizes <![CDATA[foo]]> as -// the text "foo". The default value is false, which means to recognize it as -// a bogus comment "<!-- [CDATA[foo]] -->" instead. -// -// Strictly speaking, an HTML5 compliant tokenizer should allow CDATA if and -// only if tokenizing foreign content, such as MathML and SVG. However, -// tracking foreign-contentness is difficult to do purely in the tokenizer, -// as opposed to the parser, due to HTML integration points: an <svg> element -// can contain a <foreignObject> that is foreign-to-SVG but not foreign-to- -// HTML. For strict compliance with the HTML5 tokenization algorithm, it is the -// responsibility of the user of a tokenizer to call AllowCDATA as appropriate. -// In practice, if using the tokenizer without caring whether MathML or SVG -// CDATA is text or comments, such as tokenizing HTML to find all the anchor -// text, it is acceptable to ignore this responsibility. -func (z *Tokenizer) AllowCDATA(allowCDATA bool) { - z.allowCDATA = allowCDATA -} - -// NextIsNotRawText instructs the tokenizer that the next token should not be -// considered as 'raw text'. Some elements, such as script and title elements, -// normally require the next token after the opening tag to be 'raw text' that -// has no child elements. For example, tokenizing "<title>a<b>c</b>d</title>" -// yields a start tag token for "<title>", a text token for "a<b>c</b>d", and -// an end tag token for "</title>". There are no distinct start tag or end tag -// tokens for the "<b>" and "</b>". -// -// This tokenizer implementation will generally look for raw text at the right -// times. Strictly speaking, an HTML5 compliant tokenizer should not look for -// raw text if in foreign content: <title> generally needs raw text, but a -// <title> inside an <svg> does not. Another example is that a <textarea> -// generally needs raw text, but a <textarea> is not allowed as an immediate -// child of a <select>; in normal parsing, a <textarea> implies </select>, but -// one cannot close the implicit element when parsing a <select>'s InnerHTML. -// Similarly to AllowCDATA, tracking the correct moment to override raw-text- -// ness is difficult to do purely in the tokenizer, as opposed to the parser. -// For strict compliance with the HTML5 tokenization algorithm, it is the -// responsibility of the user of a tokenizer to call NextIsNotRawText as -// appropriate. In practice, like AllowCDATA, it is acceptable to ignore this -// responsibility for basic usage. -// -// Note that this 'raw text' concept is different from the one offered by the -// Tokenizer.Raw method. -func (z *Tokenizer) NextIsNotRawText() { - z.rawTag = "" -} - -// Err returns the error associated with the most recent ErrorToken token. -// This is typically io.EOF, meaning the end of tokenization. -func (z *Tokenizer) Err() error { - if z.tt != ErrorToken { - return nil - } - return z.err -} - -// readByte returns the next byte from the input stream, doing a buffered read -// from z.r into z.buf if necessary. z.buf[z.raw.start:z.raw.end] remains a contiguous byte -// slice that holds all the bytes read so far for the current token. -// It sets z.err if the underlying reader returns an error. -// Pre-condition: z.err == nil. -func (z *Tokenizer) readByte() byte { - if z.raw.end >= len(z.buf) { - // Our buffer is exhausted and we have to read from z.r. Check if the - // previous read resulted in an error. - if z.readErr != nil { - z.err = z.readErr - return 0 - } - // We copy z.buf[z.raw.start:z.raw.end] to the beginning of z.buf. If the length - // z.raw.end - z.raw.start is more than half the capacity of z.buf, then we - // allocate a new buffer before the copy. - c := cap(z.buf) - d := z.raw.end - z.raw.start - var buf1 []byte - if 2*d > c { - buf1 = make([]byte, d, 2*c) - } else { - buf1 = z.buf[:d] - } - copy(buf1, z.buf[z.raw.start:z.raw.end]) - if x := z.raw.start; x != 0 { - // Adjust the data/attr spans to refer to the same contents after the copy. - z.data.start -= x - z.data.end -= x - z.pendingAttr[0].start -= x - z.pendingAttr[0].end -= x - z.pendingAttr[1].start -= x - z.pendingAttr[1].end -= x - for i := range z.attr { - z.attr[i][0].start -= x - z.attr[i][0].end -= x - z.attr[i][1].start -= x - z.attr[i][1].end -= x - } - } - z.raw.start, z.raw.end, z.buf = 0, d, buf1[:d] - // Now that we have copied the live bytes to the start of the buffer, - // we read from z.r into the remainder. - var n int - n, z.readErr = readAtLeastOneByte(z.r, buf1[d:cap(buf1)]) - if n == 0 { - z.err = z.readErr - return 0 - } - z.buf = buf1[:d+n] - } - x := z.buf[z.raw.end] - z.raw.end++ - if z.maxBuf > 0 && z.raw.end-z.raw.start >= z.maxBuf { - z.err = ErrBufferExceeded - return 0 - } - return x -} - -// Buffered returns a slice containing data buffered but not yet tokenized. -func (z *Tokenizer) Buffered() []byte { - return z.buf[z.raw.end:] -} - -// readAtLeastOneByte wraps an io.Reader so that reading cannot return (0, nil). -// It returns io.ErrNoProgress if the underlying r.Read method returns (0, nil) -// too many times in succession. -func readAtLeastOneByte(r io.Reader, b []byte) (int, error) { - for i := 0; i < 100; i++ { - if n, err := r.Read(b); n != 0 || err != nil { - return n, err - } - } - return 0, io.ErrNoProgress -} - -// skipWhiteSpace skips past any white space. -func (z *Tokenizer) skipWhiteSpace() { - if z.err != nil { - return - } - for { - c := z.readByte() - if z.err != nil { - return - } - switch c { - case ' ', '\n', '\r', '\t', '\f': - // No-op. - default: - z.raw.end-- - return - } - } -} - -// readRawOrRCDATA reads until the next "</foo>", where "foo" is z.rawTag and -// is typically something like "script" or "textarea". -func (z *Tokenizer) readRawOrRCDATA() { - if z.rawTag == "script" { - z.readScript() - z.textIsRaw = true - z.rawTag = "" - return - } -loop: - for { - c := z.readByte() - if z.err != nil { - break loop - } - if c != '<' { - continue loop - } - c = z.readByte() - if z.err != nil { - break loop - } - if c != '/' { - z.raw.end-- - continue loop - } - if z.readRawEndTag() || z.err != nil { - break loop - } - } - z.data.end = z.raw.end - // A textarea's or title's RCDATA can contain escaped entities. - z.textIsRaw = z.rawTag != "textarea" && z.rawTag != "title" - z.rawTag = "" -} - -// readRawEndTag attempts to read a tag like "</foo>", where "foo" is z.rawTag. -// If it succeeds, it backs up the input position to reconsume the tag and -// returns true. Otherwise it returns false. The opening "</" has already been -// consumed. -func (z *Tokenizer) readRawEndTag() bool { - for i := 0; i < len(z.rawTag); i++ { - c := z.readByte() - if z.err != nil { - return false - } - if c != z.rawTag[i] && c != z.rawTag[i]-('a'-'A') { - z.raw.end-- - return false - } - } - c := z.readByte() - if z.err != nil { - return false - } - switch c { - case ' ', '\n', '\r', '\t', '\f', '/', '>': - // The 3 is 2 for the leading "</" plus 1 for the trailing character c. - z.raw.end -= 3 + len(z.rawTag) - return true - } - z.raw.end-- - return false -} - -// readScript reads until the next </script> tag, following the byzantine -// rules for escaping/hiding the closing tag. -func (z *Tokenizer) readScript() { - defer func() { - z.data.end = z.raw.end - }() - var c byte - -scriptData: - c = z.readByte() - if z.err != nil { - return - } - if c == '<' { - goto scriptDataLessThanSign - } - goto scriptData - -scriptDataLessThanSign: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '/': - goto scriptDataEndTagOpen - case '!': - goto scriptDataEscapeStart - } - z.raw.end-- - goto scriptData - -scriptDataEndTagOpen: - if z.readRawEndTag() || z.err != nil { - return - } - goto scriptData - -scriptDataEscapeStart: - c = z.readByte() - if z.err != nil { - return - } - if c == '-' { - goto scriptDataEscapeStartDash - } - z.raw.end-- - goto scriptData - -scriptDataEscapeStartDash: - c = z.readByte() - if z.err != nil { - return - } - if c == '-' { - goto scriptDataEscapedDashDash - } - z.raw.end-- - goto scriptData - -scriptDataEscaped: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '-': - goto scriptDataEscapedDash - case '<': - goto scriptDataEscapedLessThanSign - } - goto scriptDataEscaped - -scriptDataEscapedDash: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '-': - goto scriptDataEscapedDashDash - case '<': - goto scriptDataEscapedLessThanSign - } - goto scriptDataEscaped - -scriptDataEscapedDashDash: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '-': - goto scriptDataEscapedDashDash - case '<': - goto scriptDataEscapedLessThanSign - case '>': - goto scriptData - } - goto scriptDataEscaped - -scriptDataEscapedLessThanSign: - c = z.readByte() - if z.err != nil { - return - } - if c == '/' { - goto scriptDataEscapedEndTagOpen - } - if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' { - goto scriptDataDoubleEscapeStart - } - z.raw.end-- - goto scriptData - -scriptDataEscapedEndTagOpen: - if z.readRawEndTag() || z.err != nil { - return - } - goto scriptDataEscaped - -scriptDataDoubleEscapeStart: - z.raw.end-- - for i := 0; i < len("script"); i++ { - c = z.readByte() - if z.err != nil { - return - } - if c != "script"[i] && c != "SCRIPT"[i] { - z.raw.end-- - goto scriptDataEscaped - } - } - c = z.readByte() - if z.err != nil { - return - } - switch c { - case ' ', '\n', '\r', '\t', '\f', '/', '>': - goto scriptDataDoubleEscaped - } - z.raw.end-- - goto scriptDataEscaped - -scriptDataDoubleEscaped: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '-': - goto scriptDataDoubleEscapedDash - case '<': - goto scriptDataDoubleEscapedLessThanSign - } - goto scriptDataDoubleEscaped - -scriptDataDoubleEscapedDash: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '-': - goto scriptDataDoubleEscapedDashDash - case '<': - goto scriptDataDoubleEscapedLessThanSign - } - goto scriptDataDoubleEscaped - -scriptDataDoubleEscapedDashDash: - c = z.readByte() - if z.err != nil { - return - } - switch c { - case '-': - goto scriptDataDoubleEscapedDashDash - case '<': - goto scriptDataDoubleEscapedLessThanSign - case '>': - goto scriptData - } - goto scriptDataDoubleEscaped - -scriptDataDoubleEscapedLessThanSign: - c = z.readByte() - if z.err != nil { - return - } - if c == '/' { - goto scriptDataDoubleEscapeEnd - } - z.raw.end-- - goto scriptDataDoubleEscaped - -scriptDataDoubleEscapeEnd: - if z.readRawEndTag() { - z.raw.end += len("</script>") - goto scriptDataEscaped - } - if z.err != nil { - return - } - goto scriptDataDoubleEscaped -} - -// readComment reads the next comment token starting with "<!--". The opening -// "<!--" has already been consumed. -func (z *Tokenizer) readComment() { - // When modifying this function, consider manually increasing the - // maxSuffixLen constant in func TestComments, from 6 to e.g. 9 or more. - // That increase should only be temporary, not committed, as it - // exponentially affects the test running time. - - z.data.start = z.raw.end - defer func() { - if z.data.end < z.data.start { - // It's a comment with no data, like <!-->. - z.data.end = z.data.start - } - }() - - var dashCount int - beginning := true - for { - c := z.readByte() - if z.err != nil { - z.data.end = z.calculateAbruptCommentDataEnd() - return - } - switch c { - case '-': - dashCount++ - continue - case '>': - if dashCount >= 2 || beginning { - z.data.end = z.raw.end - len("-->") - return - } - case '!': - if dashCount >= 2 { - c = z.readByte() - if z.err != nil { - z.data.end = z.calculateAbruptCommentDataEnd() - return - } else if c == '>' { - z.data.end = z.raw.end - len("--!>") - return - } else if c == '-' { - dashCount = 1 - beginning = false - continue - } - } - } - dashCount = 0 - beginning = false - } -} - -func (z *Tokenizer) calculateAbruptCommentDataEnd() int { - raw := z.Raw() - const prefixLen = len("<!--") - if len(raw) >= prefixLen { - raw = raw[prefixLen:] - if hasSuffix(raw, "--!") { - return z.raw.end - 3 - } else if hasSuffix(raw, "--") { - return z.raw.end - 2 - } else if hasSuffix(raw, "-") { - return z.raw.end - 1 - } - } - return z.raw.end -} - -func hasSuffix(b []byte, suffix string) bool { - if len(b) < len(suffix) { - return false - } - b = b[len(b)-len(suffix):] - for i := range b { - if b[i] != suffix[i] { - return false - } - } - return true -} - -// readUntilCloseAngle reads until the next ">". -func (z *Tokenizer) readUntilCloseAngle() { - z.data.start = z.raw.end - for { - c := z.readByte() - if z.err != nil { - z.data.end = z.raw.end - return - } - if c == '>' { - z.data.end = z.raw.end - len(">") - return - } - } -} - -// readMarkupDeclaration reads the next token starting with "<!". It might be -// a "<!--comment-->", a "<!DOCTYPE foo>", a "<![CDATA[section]]>" or -// "<!a bogus comment". The opening "<!" has already been consumed. -func (z *Tokenizer) readMarkupDeclaration() TokenType { - z.data.start = z.raw.end - var c [2]byte - for i := 0; i < 2; i++ { - c[i] = z.readByte() - if z.err != nil { - z.data.end = z.raw.end - return CommentToken - } - } - if c[0] == '-' && c[1] == '-' { - z.readComment() - return CommentToken - } - z.raw.end -= 2 - if z.readDoctype() { - return DoctypeToken - } - if z.allowCDATA && z.readCDATA() { - z.convertNUL = true - return TextToken - } - // It's a bogus comment. - z.readUntilCloseAngle() - return CommentToken -} - -// readDoctype attempts to read a doctype declaration and returns true if -// successful. The opening "<!" has already been consumed. -func (z *Tokenizer) readDoctype() bool { - const s = "DOCTYPE" - for i := 0; i < len(s); i++ { - c := z.readByte() - if z.err != nil { - z.data.end = z.raw.end - return false - } - if c != s[i] && c != s[i]+('a'-'A') { - // Back up to read the fragment of "DOCTYPE" again. - z.raw.end = z.data.start - return false - } - } - if z.skipWhiteSpace(); z.err != nil { - z.data.start = z.raw.end - z.data.end = z.raw.end - return true - } - z.readUntilCloseAngle() - return true -} - -// readCDATA attempts to read a CDATA section and returns true if -// successful. The opening "<!" has already been consumed. -func (z *Tokenizer) readCDATA() bool { - const s = "[CDATA[" - for i := 0; i < len(s); i++ { - c := z.readByte() - if z.err != nil { - z.data.end = z.raw.end - return false - } - if c != s[i] { - // Back up to read the fragment of "[CDATA[" again. - z.raw.end = z.data.start - return false - } - } - z.data.start = z.raw.end - brackets := 0 - for { - c := z.readByte() - if z.err != nil { - z.data.end = z.raw.end - return true - } - switch c { - case ']': - brackets++ - case '>': - if brackets >= 2 { - z.data.end = z.raw.end - len("]]>") - return true - } - brackets = 0 - default: - brackets = 0 - } - } -} - -// startTagIn returns whether the start tag in z.buf[z.data.start:z.data.end] -// case-insensitively matches any element of ss. -func (z *Tokenizer) startTagIn(ss ...string) bool { -loop: - for _, s := range ss { - if z.data.end-z.data.start != len(s) { - continue loop - } - for i := 0; i < len(s); i++ { - c := z.buf[z.data.start+i] - if 'A' <= c && c <= 'Z' { - c += 'a' - 'A' - } - if c != s[i] { - continue loop - } - } - return true - } - return false -} - -// readStartTag reads the next start tag token. The opening "<a" has already -// been consumed, where 'a' means anything in [A-Za-z]. -func (z *Tokenizer) readStartTag() TokenType { - z.readTag(true) - if z.err != nil { - return ErrorToken - } - // Several tags flag the tokenizer's next token as raw. - c, raw := z.buf[z.data.start], false - if 'A' <= c && c <= 'Z' { - c += 'a' - 'A' - } - switch c { - case 'i': - raw = z.startTagIn("iframe") - case 'n': - raw = z.startTagIn("noembed", "noframes", "noscript") - case 'p': - raw = z.startTagIn("plaintext") - case 's': - raw = z.startTagIn("script", "style") - case 't': - raw = z.startTagIn("textarea", "title") - case 'x': - raw = z.startTagIn("xmp") - } - if raw { - z.rawTag = strings.ToLower(string(z.buf[z.data.start:z.data.end])) - } - // Look for a self-closing token (e.g. <br/>). - // - // Originally, we did this by just checking that the last character of the - // tag (ignoring the closing bracket) was a solidus (/) character, but this - // is not always accurate. - // - // We need to be careful that we don't misinterpret a non-self-closing tag - // as self-closing, as can happen if the tag contains unquoted attribute - // values (i.e. <p a=/>). - // - // To avoid this, we check that the last non-bracket character of the tag - // (z.raw.end-2) isn't the same character as the last non-quote character of - // the last attribute of the tag (z.pendingAttr[1].end-1), if the tag has - // attributes. - nAttrs := len(z.attr) - if z.err == nil && z.buf[z.raw.end-2] == '/' && (nAttrs == 0 || z.raw.end-2 != z.attr[nAttrs-1][1].end-1) { - return SelfClosingTagToken - } - return StartTagToken -} - -// readTag reads the next tag token and its attributes. If saveAttr, those -// attributes are saved in z.attr, otherwise z.attr is set to an empty slice. -// The opening "<a" or "</a" has already been consumed, where 'a' means anything -// in [A-Za-z]. -func (z *Tokenizer) readTag(saveAttr bool) { - z.attr = z.attr[:0] - z.nAttrReturned = 0 - // Read the tag name and attribute key/value pairs. - z.readTagName() - if z.skipWhiteSpace(); z.err != nil { - return - } - for { - c := z.readByte() - if z.err != nil || c == '>' { - break - } - z.raw.end-- - z.readTagAttrKey() - z.readTagAttrVal() - // Save pendingAttr if saveAttr and that attribute has a non-empty key. - if saveAttr && z.pendingAttr[0].start != z.pendingAttr[0].end { - z.attr = append(z.attr, z.pendingAttr) - } - if z.skipWhiteSpace(); z.err != nil { - break - } - } -} - -// readTagName sets z.data to the "div" in "<div k=v>". The reader (z.raw.end) -// is positioned such that the first byte of the tag name (the "d" in "<div") -// has already been consumed. -func (z *Tokenizer) readTagName() { - z.data.start = z.raw.end - 1 - for { - c := z.readByte() - if z.err != nil { - z.data.end = z.raw.end - return - } - switch c { - case ' ', '\n', '\r', '\t', '\f': - z.data.end = z.raw.end - 1 - return - case '/', '>': - z.raw.end-- - z.data.end = z.raw.end - return - } - } -} - -// readTagAttrKey sets z.pendingAttr[0] to the "k" in "<div k=v>". -// Precondition: z.err == nil. -func (z *Tokenizer) readTagAttrKey() { - z.pendingAttr[0].start = z.raw.end - for { - c := z.readByte() - if z.err != nil { - z.pendingAttr[0].end = z.raw.end - return - } - switch c { - case '=': - if z.pendingAttr[0].start+1 == z.raw.end { - // WHATWG 13.2.5.32, if we see an equals sign before the attribute name - // begins, we treat it as a character in the attribute name and continue. - continue - } - fallthrough - case ' ', '\n', '\r', '\t', '\f', '/', '>': - // WHATWG 13.2.5.33 Attribute name state - // We need to reconsume the char in the after attribute name state to support the / character - z.raw.end-- - z.pendingAttr[0].end = z.raw.end - return - } - } -} - -// readTagAttrVal sets z.pendingAttr[1] to the "v" in "<div k=v>". -func (z *Tokenizer) readTagAttrVal() { - z.pendingAttr[1].start = z.raw.end - z.pendingAttr[1].end = z.raw.end - if z.skipWhiteSpace(); z.err != nil { - return - } - c := z.readByte() - if z.err != nil { - return - } - if c == '/' { - // WHATWG 13.2.5.34 After attribute name state - // U+002F SOLIDUS (/) - Switch to the self-closing start tag state. - return - } - if c != '=' { - z.raw.end-- - return - } - if z.skipWhiteSpace(); z.err != nil { - return - } - quote := z.readByte() - if z.err != nil { - return - } - switch quote { - case '>': - z.raw.end-- - return - - case '\'', '"': - z.pendingAttr[1].start = z.raw.end - for { - c := z.readByte() - if z.err != nil { - z.pendingAttr[1].end = z.raw.end - return - } - if c == quote { - z.pendingAttr[1].end = z.raw.end - 1 - return - } - } - - default: - z.pendingAttr[1].start = z.raw.end - 1 - for { - c := z.readByte() - if z.err != nil { - z.pendingAttr[1].end = z.raw.end - return - } - switch c { - case ' ', '\n', '\r', '\t', '\f': - z.pendingAttr[1].end = z.raw.end - 1 - return - case '>': - z.raw.end-- - z.pendingAttr[1].end = z.raw.end - return - } - } - } -} - -// Next scans the next token and returns its type. -func (z *Tokenizer) Next() TokenType { - z.raw.start = z.raw.end - z.data.start = z.raw.end - z.data.end = z.raw.end - if z.err != nil { - z.tt = ErrorToken - return z.tt - } - if z.rawTag != "" { - if z.rawTag == "plaintext" { - // Read everything up to EOF. - for z.err == nil { - z.readByte() - } - z.data.end = z.raw.end - z.textIsRaw = true - } else { - z.readRawOrRCDATA() - } - if z.data.end > z.data.start { - z.tt = TextToken - z.convertNUL = true - return z.tt - } - } - z.textIsRaw = false - z.convertNUL = false - -loop: - for { - c := z.readByte() - if z.err != nil { - break loop - } - if c != '<' { - continue loop - } - - // Check if the '<' we have just read is part of a tag, comment - // or doctype. If not, it's part of the accumulated text token. - c = z.readByte() - if z.err != nil { - break loop - } - var tokenType TokenType - switch { - case 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z': - tokenType = StartTagToken - case c == '/': - tokenType = EndTagToken - case c == '!' || c == '?': - // We use CommentToken to mean any of "<!--actual comments-->", - // "<!DOCTYPE declarations>" and "<?xml processing instructions?>". - tokenType = CommentToken - default: - // Reconsume the current character. - z.raw.end-- - continue - } - - // We have a non-text token, but we might have accumulated some text - // before that. If so, we return the text first, and return the non- - // text token on the subsequent call to Next. - if x := z.raw.end - len("<a"); z.raw.start < x { - z.raw.end = x - z.data.end = x - z.tt = TextToken - return z.tt - } - switch tokenType { - case StartTagToken: - z.tt = z.readStartTag() - return z.tt - case EndTagToken: - c = z.readByte() - if z.err != nil { - break loop - } - if c == '>' { - // "</>" does not generate a token at all. Generate an empty comment - // to allow passthrough clients to pick up the data using Raw. - // Reset the tokenizer state and start again. - z.tt = CommentToken - return z.tt - } - if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' { - z.readTag(false) - if z.err != nil { - z.tt = ErrorToken - } else { - z.tt = EndTagToken - } - return z.tt - } - z.raw.end-- - z.readUntilCloseAngle() - z.tt = CommentToken - return z.tt - case CommentToken: - if c == '!' { - z.tt = z.readMarkupDeclaration() - return z.tt - } - z.raw.end-- - z.readUntilCloseAngle() - z.tt = CommentToken - return z.tt - } - } - if z.raw.start < z.raw.end { - z.data.end = z.raw.end - z.tt = TextToken - return z.tt - } - z.tt = ErrorToken - return z.tt -} - -// Raw returns the unmodified text of the current token. Calling Next, Token, -// Text, TagName or TagAttr may change the contents of the returned slice. -// -// The token stream's raw bytes partition the byte stream (up until an -// ErrorToken). There are no overlaps or gaps between two consecutive token's -// raw bytes. One implication is that the byte offset of the current token is -// the sum of the lengths of all previous tokens' raw bytes. -func (z *Tokenizer) Raw() []byte { - return z.buf[z.raw.start:z.raw.end] -} - -// convertNewlines converts "\r" and "\r\n" in s to "\n". -// The conversion happens in place, but the resulting slice may be shorter. -func convertNewlines(s []byte) []byte { - for i, c := range s { - if c != '\r' { - continue - } - - src := i + 1 - if src >= len(s) || s[src] != '\n' { - s[i] = '\n' - continue - } - - dst := i - for src < len(s) { - if s[src] == '\r' { - if src+1 < len(s) && s[src+1] == '\n' { - src++ - } - s[dst] = '\n' - } else { - s[dst] = s[src] - } - src++ - dst++ - } - return s[:dst] - } - return s -} - -var ( - nul = []byte("\x00") - replacement = []byte("\ufffd") -) - -// Text returns the unescaped text of a text, comment or doctype token. The -// contents of the returned slice may change on the next call to Next. -func (z *Tokenizer) Text() []byte { - switch z.tt { - case TextToken, CommentToken, DoctypeToken: - s := z.buf[z.data.start:z.data.end] - z.data.start = z.raw.end - z.data.end = z.raw.end - s = convertNewlines(s) - if (z.convertNUL || z.tt == CommentToken) && bytes.Contains(s, nul) { - s = bytes.Replace(s, nul, replacement, -1) - } - if !z.textIsRaw { - s = unescape(s, false) - } - return s - } - return nil -} - -// TagName returns the lower-cased name of a tag token (the `img` out of -// `<IMG SRC="foo">`) and whether the tag has attributes. -// The contents of the returned slice may change on the next call to Next. -func (z *Tokenizer) TagName() (name []byte, hasAttr bool) { - if z.data.start < z.data.end { - switch z.tt { - case StartTagToken, EndTagToken, SelfClosingTagToken: - s := z.buf[z.data.start:z.data.end] - z.data.start = z.raw.end - z.data.end = z.raw.end - return lower(s), z.nAttrReturned < len(z.attr) - } - } - return nil, false -} - -// TagAttr returns the lower-cased key and unescaped value of the next unparsed -// attribute for the current tag token and whether there are more attributes. -// The contents of the returned slices may change on the next call to Next. -func (z *Tokenizer) TagAttr() (key, val []byte, moreAttr bool) { - if z.nAttrReturned < len(z.attr) { - switch z.tt { - case StartTagToken, SelfClosingTagToken: - x := z.attr[z.nAttrReturned] - z.nAttrReturned++ - key = z.buf[x[0].start:x[0].end] - val = z.buf[x[1].start:x[1].end] - return lower(key), unescape(convertNewlines(val), true), z.nAttrReturned < len(z.attr) - } - } - return nil, nil, false -} - -// Token returns the current Token. The result's Data and Attr values remain -// valid after subsequent Next calls. -func (z *Tokenizer) Token() Token { - t := Token{Type: z.tt} - switch z.tt { - case TextToken, CommentToken, DoctypeToken: - t.Data = string(z.Text()) - case StartTagToken, SelfClosingTagToken, EndTagToken: - name, moreAttr := z.TagName() - for moreAttr { - var key, val []byte - key, val, moreAttr = z.TagAttr() - t.Attr = append(t.Attr, Attribute{"", atom.String(key), string(val)}) - } - if a := atom.Lookup(name); a != 0 { - t.DataAtom, t.Data = a, a.String() - } else { - t.DataAtom, t.Data = 0, string(name) - } - } - return t -} - -// SetMaxBuf sets a limit on the amount of data buffered during tokenization. -// A value of 0 means unlimited. -func (z *Tokenizer) SetMaxBuf(n int) { - z.maxBuf = n -} - -// NewTokenizer returns a new HTML Tokenizer for the given Reader. -// The input is assumed to be UTF-8 encoded. -func NewTokenizer(r io.Reader) *Tokenizer { - return NewTokenizerFragment(r, "") -} - -// NewTokenizerFragment returns a new HTML Tokenizer for the given Reader, for -// tokenizing an existing element's InnerHTML fragment. contextTag is that -// element's tag, such as "div" or "iframe". -// -// For example, how the InnerHTML "a<b" is tokenized depends on whether it is -// for a <p> tag or a <script> tag. -// -// The input is assumed to be UTF-8 encoded. -func NewTokenizerFragment(r io.Reader, contextTag string) *Tokenizer { - z := &Tokenizer{ - r: r, - buf: make([]byte, 0, 4096), - } - if contextTag != "" { - switch s := strings.ToLower(contextTag); s { - case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "title", "textarea", "xmp": - z.rawTag = s - } - } - return z -} diff --git a/src/vendor/modules.txt b/src/vendor/modules.txt index c4fe2be..1ca1734 100644 --- a/src/vendor/modules.txt +++ b/src/vendor/modules.txt @@ -1,9 +1,12 @@ -# github.com/gabriel-vasile/mimetype v1.4.9 -## explicit; go 1.23.0 +# github.com/gabriel-vasile/mimetype v1.4.10 +## explicit; go 1.21 github.com/gabriel-vasile/mimetype github.com/gabriel-vasile/mimetype/internal/charset +github.com/gabriel-vasile/mimetype/internal/csv github.com/gabriel-vasile/mimetype/internal/json github.com/gabriel-vasile/mimetype/internal/magic +github.com/gabriel-vasile/mimetype/internal/markup +github.com/gabriel-vasile/mimetype/internal/scan # github.com/go-playground/locales v0.14.1 ## explicit; go 1.17 github.com/go-playground/locales @@ -11,25 +14,21 @@ github.com/go-playground/locales/currency # github.com/go-playground/universal-translator v0.18.1 ## explicit; go 1.18 github.com/go-playground/universal-translator -# github.com/go-playground/validator/v10 v10.27.0 -## explicit; go 1.20 +# github.com/go-playground/validator/v10 v10.28.0 +## explicit; go 1.24.0 github.com/go-playground/validator/v10 # github.com/leodido/go-urn v1.4.0 ## explicit; go 1.18 github.com/leodido/go-urn github.com/leodido/go-urn/scim/schema -# golang.org/x/crypto v0.41.0 -## explicit; go 1.23.0 +# golang.org/x/crypto v0.43.0 +## explicit; go 1.24.0 golang.org/x/crypto/sha3 -# golang.org/x/net v0.43.0 -## explicit; go 1.23.0 -golang.org/x/net/html -golang.org/x/net/html/atom -# golang.org/x/sys v0.35.0 -## explicit; go 1.23.0 +# golang.org/x/sys v0.37.0 +## explicit; go 1.24.0 golang.org/x/sys/cpu -# golang.org/x/text v0.28.0 -## explicit; go 1.23.0 +# golang.org/x/text v0.30.0 +## explicit; go 1.24.0 golang.org/x/text/internal/language golang.org/x/text/internal/language/compact golang.org/x/text/internal/tag From 9b7c5ab1e55d5bb29f8e47491e625243a05fee6e Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 09:21:15 +1100 Subject: [PATCH 3/9] fix: devenv tests --- devenv.nix | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/devenv.nix b/devenv.nix index 5eafc2f..6bd9e98 100644 --- a/devenv.nix +++ b/devenv.nix @@ -152,8 +152,15 @@ in starship.enable = true; enterTest = '' - echo "Running tests" + echo -e "\nSTART: Running tests" + + echo -e "\nTEST: Show git version" git --version | grep --color=auto "${pkgs.git.version}" + + echo -e "\nTEST: Show nix-installer version" + nixos-installer --version + + echo -e "\nEND: Running tests" ''; scripts = { From 3a849b47361f23eb4d2da4b84b5ac113772a9e99 Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 09:43:41 +1100 Subject: [PATCH 4/9] fix: Nancy needs auth now --- .github/workflows/nancy.yaml | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/.github/workflows/nancy.yaml b/.github/workflows/nancy.yaml index a024b3e..7cd9f95 100644 --- a/.github/workflows/nancy.yaml +++ b/.github/workflows/nancy.yaml @@ -68,11 +68,12 @@ jobs: lfs: false submodules: recursive - - id: test_go_sum - name: Test for go.sum + - id: check_nancy + name: Check for Nancy run conditions shell: bash run: | - cd ${{ env.GOHOME }} + # Condition 1. We need a go.sum file. + pushd ${{ env.GOHOME }} if [ -f "go.sum" ]; then echo "๐Ÿ” go.sum file present, running Nancy." @@ -82,12 +83,26 @@ jobs: echo "๐Ÿ” No go.sum file present, skipping Nancy." echo "run_nancy=false" >> "$GITHUB_OUTPUT" fi + popd + # Condition 2. We need OSS Index username and password. + if [ "${{ secrets.OSS_INDEX_USERNAME }}" != '' ] && [ "${{ secrets.OSS_INDEX_TOKEN }}" != '' ]; + then + echo "๐Ÿ” OSS Index username and token present, running Nancy." + echo "run_nancy=true" >> "$GITHUB_OUTPUT" + else + echo "๐Ÿ” OSS Index username or token missing, skipping Nancy." + echo "run_nancy=false" >> "$GITHUB_OUTPUT" + fi - id: run_nancy name: Run Nancy - if: ${{ steps.test_go_sum.outputs.run_nancy == 'true' }} + if: steps.check_nancy.outputs.run_nancy == 'true' uses: sonatype-nexus-community/nancy-github-action@main with: githubToken: ${{ secrets.GITHUB_TOKEN }} nancyVersion: latest - nancyCommand: sleuth --loud + nancyCommand: -> + sleuth + --username ${{ vars.OSS_INDEX_USERNAME }} + --token ${{ secrets.OSS_INDEX_TOKEN }} + --loud From 7ac14f9f0760522f5f3084aed13404efd033edcb Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 09:59:11 +1100 Subject: [PATCH 5/9] fix: Nancy needs auth now --- .github/workflows/nancy.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/nancy.yaml b/.github/workflows/nancy.yaml index 7cd9f95..3c5b2dd 100644 --- a/.github/workflows/nancy.yaml +++ b/.github/workflows/nancy.yaml @@ -85,7 +85,7 @@ jobs: fi popd # Condition 2. We need OSS Index username and password. - if [ "${{ secrets.OSS_INDEX_USERNAME }}" != '' ] && [ "${{ secrets.OSS_INDEX_TOKEN }}" != '' ]; + if [ "${{ vars.OSS_INDEX_USERNAME }}" != '' ] && [ "${{ secrets.OSS_INDEX_TOKEN }}" != '' ]; then echo "๐Ÿ” OSS Index username and token present, running Nancy." echo "run_nancy=true" >> "$GITHUB_OUTPUT" From 6d41bd4807e00fd09a0cf260329861fe19c69d34 Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 10:03:15 +1100 Subject: [PATCH 6/9] fix: Nancy needs auth now --- .github/workflows/nancy.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/nancy.yaml b/.github/workflows/nancy.yaml index 3c5b2dd..f991a7f 100644 --- a/.github/workflows/nancy.yaml +++ b/.github/workflows/nancy.yaml @@ -84,7 +84,7 @@ jobs: echo "run_nancy=false" >> "$GITHUB_OUTPUT" fi popd - # Condition 2. We need OSS Index username and password. + # Condition 2. We need OSS Index username and token. if [ "${{ vars.OSS_INDEX_USERNAME }}" != '' ] && [ "${{ secrets.OSS_INDEX_TOKEN }}" != '' ]; then echo "๐Ÿ” OSS Index username and token present, running Nancy." @@ -101,7 +101,7 @@ jobs: with: githubToken: ${{ secrets.GITHUB_TOKEN }} nancyVersion: latest - nancyCommand: -> + nancyCommand: <- sleuth --username ${{ vars.OSS_INDEX_USERNAME }} --token ${{ secrets.OSS_INDEX_TOKEN }} From 803606ad85230f3e9a00a8d1d875f0019dfe787b Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 11:53:30 +1100 Subject: [PATCH 7/9] fix: Nancy needs auth now --- .github/workflows/nancy.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/nancy.yaml b/.github/workflows/nancy.yaml index f991a7f..4ebb5d3 100644 --- a/.github/workflows/nancy.yaml +++ b/.github/workflows/nancy.yaml @@ -101,7 +101,7 @@ jobs: with: githubToken: ${{ secrets.GITHUB_TOKEN }} nancyVersion: latest - nancyCommand: <- + nancyCommand: >- sleuth --username ${{ vars.OSS_INDEX_USERNAME }} --token ${{ secrets.OSS_INDEX_TOKEN }} From 443fae43e228bde3a42599e97ff6fcdfd865380d Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 12:01:11 +1100 Subject: [PATCH 8/9] chore: bump actions --- .github/workflows/codeql.yaml | 6 +++--- .github/workflows/devenv-update.yaml | 2 +- .github/workflows/devenv.yaml | 2 +- .github/workflows/go.yaml | 4 ++-- .github/workflows/linter.yaml | 2 +- .github/workflows/nancy.yaml | 2 +- .github/workflows/release.yaml | 10 +++++----- .github/workflows/trivy.yaml | 4 ++-- devenv.nix | 2 +- 9 files changed, 17 insertions(+), 17 deletions(-) diff --git a/.github/workflows/codeql.yaml b/.github/workflows/codeql.yaml index aba3ff1..2ffe0b3 100644 --- a/.github/workflows/codeql.yaml +++ b/.github/workflows/codeql.yaml @@ -66,14 +66,14 @@ jobs: steps: - id: checkout_repository name: Checkout repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: recursive - id: codeql_init name: Initialize CodeQL - uses: github/codeql-action/init@v3 + uses: github/codeql-action/init@v4 with: source-root: ${{ env.GOHOME }} languages: ${{ matrix.language }} @@ -81,6 +81,6 @@ jobs: - id: codeql_analyze name: Perform CodeQL Analysis - uses: github/codeql-action/analyze@v3 + uses: github/codeql-action/analyze@v4 with: category: "/language:${{matrix.language}}" diff --git a/.github/workflows/devenv-update.yaml b/.github/workflows/devenv-update.yaml index ea18fe7..8df7a4c 100644 --- a/.github/workflows/devenv-update.yaml +++ b/.github/workflows/devenv-update.yaml @@ -61,7 +61,7 @@ jobs: steps: - id: checkout_repository name: Checkout repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: recursive diff --git a/.github/workflows/devenv.yaml b/.github/workflows/devenv.yaml index 2a7712f..a97a6ee 100644 --- a/.github/workflows/devenv.yaml +++ b/.github/workflows/devenv.yaml @@ -65,7 +65,7 @@ jobs: steps: - id: checkout_repository name: Checkout repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: recursive diff --git a/.github/workflows/go.yaml b/.github/workflows/go.yaml index 24b31e0..6967f85 100644 --- a/.github/workflows/go.yaml +++ b/.github/workflows/go.yaml @@ -69,14 +69,14 @@ jobs: steps: - id: checkout_repository name: Checkout repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: recursive - id: go_setup name: Set up Go (${{ matrix.go-version }}) - uses: actions/setup-go@v5 + uses: actions/setup-go@v6 with: check-latest: true go-version: ${{ matrix.go-version }} diff --git a/.github/workflows/linter.yaml b/.github/workflows/linter.yaml index 3ddf87d..5532462 100644 --- a/.github/workflows/linter.yaml +++ b/.github/workflows/linter.yaml @@ -43,7 +43,7 @@ jobs: steps: - id: checkout_repository name: Checkout repository with all history and tags - uses: actions/checkout@v4 + uses: actions/checkout@v5 env: GITHUB_TOKEN: ${{ secrets.SUPER_LINTER_TOKEN }} with: diff --git a/.github/workflows/nancy.yaml b/.github/workflows/nancy.yaml index 4ebb5d3..2d18f4e 100644 --- a/.github/workflows/nancy.yaml +++ b/.github/workflows/nancy.yaml @@ -63,7 +63,7 @@ jobs: steps: - id: checkout_repository name: Checkout repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: recursive diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml index b555832..4c3090b 100644 --- a/.github/workflows/release.yaml +++ b/.github/workflows/release.yaml @@ -71,7 +71,7 @@ jobs: - id: checkout_repository name: Checkout Repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: none @@ -119,7 +119,7 @@ jobs: ARTIFACT_FILE_1="${{ env.ARTIFACT_PATH }}/bin/${{ env.REPO_NAME }}" ARTIFACT_FILE_2="${{ env.ARTIFACT_PATH }}/bin/${{ matrix.goos }}_${{ matrix.goarch }}/${{ env.REPO_NAME }}" - mkdir -p artifacts + mkdir -p artifacts if [[ -f "${ARTIFACT_FILE_1}" ]]; then @@ -185,7 +185,7 @@ jobs: - id: checkout_repository name: Checkout Repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: none @@ -303,7 +303,7 @@ jobs: - id: create_release name: Create GitHub release - uses: actions/github-script@v7 + uses: actions/github-script@v8 if: steps.check_version_bump.outputs.CREATE_RELEASE == 'true' with: github-token: ${{ secrets.GITHUB_TOKEN }} @@ -426,7 +426,7 @@ jobs: steps: - id: checkout_repository name: Checkout Repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: none diff --git a/.github/workflows/trivy.yaml b/.github/workflows/trivy.yaml index e1eba16..3eaa8bb 100644 --- a/.github/workflows/trivy.yaml +++ b/.github/workflows/trivy.yaml @@ -74,7 +74,7 @@ jobs: steps: - id: checkout_repository name: Checkout repository - uses: actions/checkout@v4 + uses: actions/checkout@v5 with: lfs: false submodules: recursive @@ -115,7 +115,7 @@ jobs: - id: trivy_upload name: Trivy (upload) - uses: github/codeql-action/upload-sarif@v3 + uses: github/codeql-action/upload-sarif@v4 with: sarif_file: "trivy-results.sarif" diff --git a/devenv.nix b/devenv.nix index 6bd9e98..2852747 100644 --- a/devenv.nix +++ b/devenv.nix @@ -8,7 +8,7 @@ let # Variables name = "nixos-installer"; - version = "0.1.5"; + version = "0.1.6"; # Custom packages. nixos-installer = import ./devenv/nixos-installer.nix { From 155c9bbd18362b56b0898a3537f4ceb3eb40f5d5 Mon Sep 17 00:00:00 2001 From: MAHDTech <MAHDTech@saltlabs.tech> Date: Fri, 17 Oct 2025 12:13:09 +1100 Subject: [PATCH 9/9] chore: bump go --- .github/workflows/go.yaml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/.github/workflows/go.yaml b/.github/workflows/go.yaml index 6967f85..f6513d7 100644 --- a/.github/workflows/go.yaml +++ b/.github/workflows/go.yaml @@ -54,9 +54,8 @@ jobs: fail-fast: false matrix: go-version: - - "1.22" - - "1.23" - "1.24" + - "1.25" go-os: - "linux" - "darwin"