diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -1,3 +1,9 @@ +0.2.1 +=== + +- added Data instances + + 0.2.0 === diff --git a/markup-parse.cabal b/markup-parse.cabal --- a/markup-parse.cabal +++ b/markup-parse.cabal @@ -1,6 +1,6 @@ cabal-version: 3.0 name: markup-parse -version: 0.2.0.0 +version: 0.2.1.0 license: BSD-3-Clause license-file: LICENSE copyright: Copyright, Tony Day, 2023- @@ -11,78 +11,100 @@ bug-reports: https://github.com/tonyday567/markup-parse/issues synopsis: A markup parser. description: - A markup parser and printer, from and to strict bytestrings, optimised for speed. + A markup parser and printer, from and to strict bytestrings, optimised for speed. + build-type: Simple tested-with: - , GHC == 9.6.7 - , GHC == 9.8.4 - , GHC == 9.10.2 - , GHC == 9.12.2 + ghc ==9.6.7 + ghc ==9.8.4 + ghc ==9.10.2 + ghc ==9.12.2 + extra-doc-files: - ChangeLog.md - other/*.html - other/*.svg - readme.md + ChangeLog.md + other/*.html + other/*.svg + readme.md source-repository head - type: git - location: https://github.com/tonyday567/markup-parse + type: git + location: https://github.com/tonyday567/markup-parse common ghc-options-exe-stanza - ghc-options: - -fforce-recomp - -funbox-strict-fields - -rtsopts - -threaded + ghc-options: + -fforce-recomp + -funbox-strict-fields + -rtsopts + -threaded common ghc-options-stanza - ghc-options: - -Wall - -Wcompat - -Wincomplete-record-updates - -Wincomplete-uni-patterns - -Wredundant-constraints + ghc-options: + -Wall + -Wcompat + -Wincomplete-record-updates + -Wincomplete-uni-patterns + -Wredundant-constraints -common ghc2021-stanza - default-language: GHC2021 +common ghc2024-additions + default-extensions: + DataKinds + DerivingStrategies + DisambiguateRecordFields + ExplicitNamespaces + GADTs + LambdaCase + MonoLocalBinds + RoleAnnotations +common ghc2024-stanza + if impl(ghc >=9.10) + default-language: + GHC2024 + else + import: ghc2024-additions + default-language: + GHC2021 + library - import: ghc-options-stanza - import: ghc2021-stanza - hs-source-dirs: src - build-depends: - , base >=4.14 && <5 - , bytestring >=0.11.3 && <0.13 - , containers >=0.6 && <0.9 - , deepseq >=1.4 && <1.6 - , flatparse >=0.3.5 && <0.6 - , string-interpolate >=0.3 && <0.4 - , these >=1.1 && <1.3 - exposed-modules: - MarkupParse - MarkupParse.Internal.FlatParse + import: ghc-options-stanza + import: ghc2024-stanza + hs-source-dirs: src + build-depends: + base >=4.14 && <5, + bytestring >=0.11.3 && <0.13, + containers >=0.6 && <0.9, + deepseq >=1.4 && <1.6, + flatparse >=0.3.5 && <0.6, + string-interpolate >=0.3 && <0.4, + these >=1.1 && <1.3, + exposed-modules: + MarkupParse + MarkupParse.Internal.FlatParse + test-suite doctests - import: ghc2021-stanza - main-is: doctests.hs - hs-source-dirs: test - build-depends: - , base >=4.14 && <5 - , doctest-parallel >=0.3 && <0.5 - ghc-options: -threaded - type: exitcode-stdio-1.0 + import: ghc2024-stanza + main-is: doctests.hs + hs-source-dirs: test + build-depends: + base >=4.14 && <5, + doctest-parallel >=0.3 && <0.5, + ghc-options: -threaded + type: exitcode-stdio-1.0 + test-suite markup-parse-diff - import: ghc-options-exe-stanza - import: ghc-options-stanza - import: ghc2021-stanza - main-is: markup-parse-diff.hs - hs-source-dirs: app - build-depends: - , base >=4.14 && <5 - , bytestring >=0.11.3 && <0.13 - , markup-parse - , tasty >=1.2 && <1.6 - , tasty-golden >=2.3.1.1 && <2.4 - , Diff >=1.0 && <1.1 - type: exitcode-stdio-1.0 + import: ghc-options-exe-stanza + import: ghc-options-stanza + import: ghc2024-stanza + main-is: markup-parse-diff.hs + hs-source-dirs: app + build-depends: + Diff >=1.0 && <1.1, + base >=4.14 && <5, + bytestring >=0.11.3 && <0.13, + markup-parse, + tasty >=1.2 && <1.6, + tasty-golden >=2.3.1.1 && <2.4, + + type: exitcode-stdio-1.0 diff --git a/readme.md b/readme.md --- a/readme.md +++ b/readme.md @@ -1,33 +1,14 @@ - -# Table of Contents - -1. [markup-parse](#org813b686) -2. [Development](#org3d7b96c) -3. [Main Pipeline types](#orgb8f20ca) -4. [MarkupParse.Patch](#org3c16287) -5. [wiki diff test debug](#org25edc96) -6. [Reference](#org4a018da) - 1. [Prior Art](#org1ed6bdf) -7. [Performance](#org9b10723) - 1. [Profiling](#orgf660933) - - - - # markup-parse [![img](https://img.shields.io/hackage/v/markup-parse.svg)](https://hackage.haskell.org/package/markup-parse) -[![img](https://github.com/tonyday567/markup-parse/workflows/haskell-ci/badge.svg)](https://github.com/tonyday567/markup-parse/actions?query=workflow%3Ahaskell-ci) +[![img](https://github.com/tonyday567/markup-parse/actions/workflows/haskell-ci.yml/badge.svg)](https://github.com/tonyday567/markup-parse/actions/workflows/haskell-ci.yml) `markup-parse` parses and prints a subset of common XML & HTML structured data, from and to strict bytestrings - - # Development :r - :set prompt "> " :set -Wno-type-defaults :set -Wno-name-shadowing :set -XOverloadedStrings @@ -35,32 +16,22 @@ :set -XQuasiQuotes import Control.Monad import MarkupParse - import MarkupParse.FlatParse - import MarkupParse.Patch + import MarkupParse.Internal.FlatParse import Data.ByteString qualified as B import Data.ByteString.Char8 qualified as C import Data.Map.Strict qualified as Map import Data.Function import FlatParse.Basic hiding (take) import Data.String.Interpolate - import Data.TreeDiff import Control.Monad bs <- B.readFile "other/line.svg" C.length bs - Preprocessing library for markup-parse-0.1.1.. - GHCi, version 9.6.2: https://www.haskell.org/ghc/ :? for help - [1 of 3] Compiling MarkupParse.FlatParse ( src/MarkupParse/FlatParse.hs, interpreted ) - [2 of 3] Compiling MarkupParse ( src/MarkupParse.hs, interpreted ) - [3 of 3] Compiling MarkupParse.Patch ( src/MarkupParse/Patch.hs, interpreted ) - Ok, three modules loaded. - g - Ok, three modules loaded. + [1 of 2] Compiling MarkupParse.Internal.FlatParse ( src/MarkupParse/Internal/FlatParse.hs, interpreted ) [Flags changed] + Ok, two modules reloaded. 7554 - - # Main Pipeline types :t tokenize Html @@ -78,28 +49,19 @@ tokenize Html >=> gather Html >=> (normalize >>> pure) >=> degather Html >=> (fmap (detokenize Html) >>> pure) :: ByteString -> These [MarkupWarning] [ByteString] -Round trip equality - m = markup_ Xml bs - m == (markup_ Xml $ markdown_ Compact Xml m) - - True +## tests - - -# MarkupParse.Patch - -Obviously, patch doesn’t belong here long-term but has been very useful in testing and development. +### Round trip equality - showPatch $ patch [1, 2, 3, 5] [0, 1, 2, 4, 6] + m = markup_ Xml bs + m == (markup_ Xml $ markdown_ Compact Xml m) - [+0, -3, +4, -5, +6] + True - - -# wiki diff test debug +### wiki diff test debug bs <- B.readFile "other/Parsing - Wikipedia.html" m = markup_ Html bs @@ -108,8 +70,6 @@ True - - # Reference [HTML Standard](https://html.spec.whatwg.org/#toc-syntax) @@ -119,8 +79,6 @@ [Extensible Markup Language (XML) 1.0 (Fifth Edition)](https://www.w3.org/TR/xml/) - - ## Prior Art [html-parse](https://hackage.haskell.org/package/html-parse) is an attoparsec-based parser for HTML. The HTML parsing here has referenced this parsing logic for HTML elements. @@ -132,15 +90,12 @@ [XMLParser](https://hackage.haskell.org/package/XMLParser) & [hexml](https://hackage.haskell.org/package/hexml) are parsec-based parsers. - - # Performance -The [perf](https://hackage.haskell.org/package/perf) library has been used to measure performance of the library. -\`cabal bench\` runs the default benchmarking: +## perf - cabal bench +The [perf](https://hackage.haskell.org/package/perf) library has been used to measure performance of the library. Running 1 benchmarks... Benchmark markup-parse-speed: RUNNING... @@ -155,8 +110,6 @@ tokenize time 8.59e5 8.67e5 Benchmark markup-parse-speed: FINISH - - ## Profiling diff --git a/src/MarkupParse.hs b/src/MarkupParse.hs --- a/src/MarkupParse.hs +++ b/src/MarkupParse.hs @@ -1,6 +1,3 @@ -{-# LANGUAGE DeriveAnyClass #-} -{-# LANGUAGE DerivingStrategies #-} -{-# LANGUAGE LambdaCase #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE QuasiQuotes #-} {-# LANGUAGE TemplateHaskell #-} @@ -103,6 +100,7 @@ import Data.ByteString (ByteString) import Data.ByteString.Char8 qualified as B import Data.Char hiding (isDigit) +import Data.Data import Data.Foldable import Data.Function import Data.List qualified as List @@ -172,17 +170,21 @@ -- The xml parsing logic is based on the XML productions found in https://www.w3.org/TR/xml/ -- -- The html parsing was based on a reading of , but ignores the various '\x00' to '\xfffd' & eof directives that form part of the html standards. -data Standard = Html | Xml deriving (Eq, Show, Ord, Generic, NFData) +data Standard = Html | Xml + deriving stock (Eq, Ord, Show, Generic, Data) +instance NFData Standard + -- | A list of 'Element's or 'Tree' 'Token's -- -- >>> markup Html "baz" -- That (Markup {elements = [Node {rootLabel = OpenTag StartTag "foo" [Attr {attrName = "class", attrValue = "bar"}], subForest = [Node {rootLabel = Content "baz", subForest = []}]}]}) newtype Markup = Markup {elements :: [Element]} - deriving stock (Show, Eq, Ord, Generic) - deriving anyclass (NFData) + deriving stock (Eq, Ord, Show, Generic, Data) deriving newtype (Semigroup, Monoid) +instance NFData Markup + -- | markup-parse generally tries to continue on parse errors, and return what has/can still be parsed, together with any warnings. data MarkupWarning = -- | A tag ending with "/>" that is not an element of 'selfClosers' (Html only). @@ -204,8 +206,10 @@ | -- | Badly formed declaration BadDecl | MarkupParser ParserWarning - deriving (Eq, Show, Ord, Generic, NFData) + deriving (Eq, Ord, Show, Generic, Data) +instance NFData MarkupWarning + showWarnings :: [MarkupWarning] -> String showWarnings = List.nub >>> fmap show >>> unlines @@ -284,8 +288,11 @@ type NameTag = ByteString -- | Whether an opening tag is a start tag or an empty element tag. -data OpenTagType = StartTag | EmptyElemTag deriving (Show, Ord, Eq, Generic, NFData) +data OpenTagType = StartTag | EmptyElemTag + deriving (Eq, Ord, Show, Generic, Data) +instance NFData OpenTagType + -- | A Markup token. The term is borrowed from standards but is used across 'Html' and 'Xml' in this library. -- -- Note that the 'Token' type is used in two slightly different contexts: @@ -332,8 +339,10 @@ Decl !ByteString ![Attr] | -- | Contents of a doctype declaration. Doctype !ByteString - deriving (Show, Ord, Eq, Generic, NFData) + deriving (Eq, Ord, Show, Generic, Data) +instance NFData Token + -- | Escape a single character. escapeChar :: Char -> ByteString escapeChar '<' = "<" @@ -484,7 +493,7 @@ -- >>> detokenize Html <$> tokenize_ Html [i||] -- [""] data Attr = Attr {attrName :: !AttrName, attrValue :: !AttrValue} - deriving (Generic, Show, Eq, Ord) + deriving (Eq, Ord, Show, Generic, Data) instance NFData Attr @@ -544,7 +553,7 @@ (Decl t as) -> bool [i||] [i||] (s == Html) -- | @Indented 0@ puts newlines in between the tags. -data RenderStyle = Compact | Indented Int deriving (Eq, Show, Generic) +data RenderStyle = Compact | Indented Int deriving (Eq, Ord, Show, Generic, Data) indentChildren :: RenderStyle -> [ByteString] -> [ByteString] indentChildren Compact = id @@ -960,7 +969,13 @@ -- -- >>> runParserWarn (ws `cut` "no whitespace") "x" -- This (ParserError "no whitespace") -data ParserWarning = ParserLeftover ByteString | ParserError ByteString | ParserUncaught deriving (Eq, Show, Ord, Generic, NFData) +data ParserWarning + = ParserLeftover ByteString + | ParserError ByteString + | ParserUncaught + deriving (Eq, Ord, Show, Generic, Data) + +instance NFData ParserWarning -- | Run parser, returning leftovers and errors as 'ParserWarning's. -- diff --git a/src/MarkupParse/Internal/FlatParse.hs b/src/MarkupParse/Internal/FlatParse.hs --- a/src/MarkupParse/Internal/FlatParse.hs +++ b/src/MarkupParse/Internal/FlatParse.hs @@ -1,5 +1,3 @@ -{-# LANGUAGE DeriveAnyClass #-} -{-# LANGUAGE LambdaCase #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE TemplateHaskell #-}