name:                html-parse
version:             0.2.1.1
synopsis:            A high-performance HTML tokenizer
description:
    This package provides a fast and reasonably robust HTML5 tokenizer built
    upon the @attoparsec@ library. The parsing strategy is based upon the HTML5
    parsing specification with few deviations.
    .
    For instance,
    .
    >>> parseTokens "<div><h1 class=widget>Hello World</h1><br/>"
    [TagOpen "div" [],
     TagOpen "h1" [Attr "class" "widget"],
     ContentText "Hello World",
     TagClose "h1",
     TagSelfClose "br" []]
    .
    The package targets similar use-cases to the venerable @tagsoup@ library,
    but is significantly more efficient, achieving parsing speeds of over 80
    megabytes per second on modern hardware and typical web documents.
    Here are some typical performance numbers taken from parsing a Wikipedia
    article of moderate length:
    .
    @
    benchmarking Forced/tagsoup fast Text
    time                 186.1 ms   (175.3 ms .. 194.6 ms)
                         0.999 R²   (0.995 R² .. 1.000 R²)
    mean                 191.7 ms   (188.9 ms .. 198.3 ms)
    std dev              5.053 ms   (1.092 ms .. 6.809 ms)
    variance introduced by outliers: 14% (moderately inflated)
    .
    benchmarking Forced/tagsoup normal Text
    time                 189.7 ms   (182.8 ms .. 197.7 ms)
                         0.999 R²   (0.998 R² .. 1.000 R²)
    mean                 196.5 ms   (193.1 ms .. 202.1 ms)
    std dev              5.481 ms   (2.141 ms .. 7.383 ms)
    variance introduced by outliers: 14% (moderately inflated)
    .
    benchmarking Forced/html-parser
    time                 15.81 ms   (15.75 ms .. 15.89 ms)
                         1.000 R²   (1.000 R² .. 1.000 R²)
    mean                 15.72 ms   (15.66 ms .. 15.77 ms)
    std dev              140.9 μs   (113.6 μs .. 174.5 μs)
    @

homepage:            http://github.com/bgamari/html-parse
license:             BSD3
license-file:        LICENSE
author:              Ben Gamari
maintainer:          ben@smart-cactus.org
copyright:           (c) 2016 Ben Gamari
category:            Text
build-type:          Simple
cabal-version:       >=1.10
tested-with:         GHC==8.10.7,
                     GHC==9.0.2,
                     GHC==9.2.5,
                     GHC==9.4.5,
                     GHC==9.6.7,
                     GHC==9.8.4,
                     GHC==9.10.1,
                     GHC==9.12.1
extra-source-files:  changelog.md


source-repository head
  type:                git
  location:            git://github.com/bgamari/html-parse

library
  exposed-modules:     Text.HTML.Parser, Text.HTML.Tree
  other-modules:       Text.HTML.Parser.Entities, Data.Trie
  ghc-options:         -Wall
  hs-source-dirs:      src
  other-extensions:    OverloadedStrings, DeriveGeneric
  build-depends:       base >=4.7 && <4.20,
                       deepseq >=1.3 && <1.6,
                       attoparsec >=0.13 && <0.15,
                       text >=1.2 && <2.2,
                       containers >=0.5 && <0.8
  default-language:    Haskell2010

benchmark bench
  type:                exitcode-stdio-1.0
  main-is:             Benchmark.hs
  other-extensions:    OverloadedStrings, DeriveGeneric
  build-depends:       base,
                       deepseq,
                       attoparsec,
                       text,
                       tagsoup >= 0.13,
                       criterion >= 1.1,
                       html-parse
  default-language:    Haskell2010

test-suite spec
  type:                exitcode-stdio-1.0
  hs-source-dirs:      tests
  main-is:             Spec.hs
  other-modules:       Text.HTML.ParserSpec, Text.HTML.TreeSpec
  ghc-options:         -Wall -with-rtsopts=-T
  build-tool-depends:  hspec-discover:hspec-discover
  build-depends:       base,
                       containers,
                       hspec,
                       hspec-discover,
                       html-parse,
                       QuickCheck,
                       quickcheck-instances,
                       string-conversions,
                       text
  default-language:    Haskell2010

-- For performance characterisation during optimisation
executable html-parse-length
  main-is:             app/Main.hs
  buildable:           False
  build-depends:       base,
                       html-parse,
                       text
  default-language:    Haskell2010