tagsoup 0.14.7 → 0.14.8

raw patch · 6 files changed

+17/−36 lines, 6 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

+ Text.StringLike: strMap :: StringLike a => (Char -> Char) -> a -> a

- Text.HTML.TagSoup: ParseOptions :: Bool -> Bool -> (str, Bool) -> [Tag str] -> (str, Bool) -> (str, [Tag str]) -> Bool -> ParseOptions str

+ Text.HTML.TagSoup: ParseOptions :: Bool -> Bool -> ((str, Bool) -> [Tag str]) -> ((str, Bool) -> (str, [Tag str])) -> Bool -> ParseOptions str

- Text.HTML.TagSoup: RenderOptions :: str -> str -> str -> Bool -> str -> Bool -> RenderOptions str

+ Text.HTML.TagSoup: RenderOptions :: (str -> str) -> (str -> Bool) -> (str -> Bool) -> RenderOptions str

- Text.HTML.TagSoup.Tree: ParseOptions :: Bool -> Bool -> (str, Bool) -> [Tag str] -> (str, Bool) -> (str, [Tag str]) -> Bool -> ParseOptions str

+ Text.HTML.TagSoup.Tree: ParseOptions :: Bool -> Bool -> ((str, Bool) -> [Tag str]) -> ((str, Bool) -> (str, [Tag str])) -> Bool -> ParseOptions str

- Text.HTML.TagSoup.Tree: RenderOptions :: str -> str -> str -> Bool -> str -> Bool -> RenderOptions str

+ Text.HTML.TagSoup.Tree: RenderOptions :: (str -> str) -> (str -> Bool) -> (str -> Bool) -> RenderOptions str

- Text.HTML.TagSoup.Tree: TagLeaf :: (Tag str) -> TagTree str

+ Text.HTML.TagSoup.Tree: TagLeaf :: Tag str -> TagTree str

Files

CHANGES.txt +2/−0
LICENSE +1/−1
README.md +3/−13
src/Text/StringLike.hs +7/−0
tagsoup.cabal +3/−3
test/TagSoup/Benchmark.hs +1/−19

CHANGES.txt view

@@ -1,5 +1,7 @@ Changelog for TagSoup +0.14.8, released 2019-05-01+    #78, add strMap 0.14.7, released 2018-09-18     #75, escape single quote (') characters as &#39;     #72, update some dead URLs

LICENSE view

@@ -1,4 +1,4 @@-Copyright Neil Mitchell 2006-2018.+Copyright Neil Mitchell 2006-2019. All rights reserved.  Redistribution and use in source and binary forms, with or without

README.md view

@@ -1,4 +1,4 @@-# TagSoup [![Hackage version](https://img.shields.io/hackage/v/tagsoup.svg?label=Hackage)](https://hackage.haskell.org/package/tagsoup) [![Stackage version](https://www.stackage.org/package/tagsoup/badge/nightly?label=Stackage)](https://www.stackage.org/package/tagsoup) [![Linux Build Status](https://img.shields.io/travis/ndmitchell/tagsoup/master.svg?label=Linux%20build)](https://travis-ci.org/ndmitchell/tagsoup) [![Windows Build Status](https://img.shields.io/appveyor/ci/ndmitchell/tagsoup/master.svg?label=Windows%20build)](https://ci.appveyor.com/project/ndmitchell/tagsoup)+# TagSoup [![Hackage version](https://img.shields.io/hackage/v/tagsoup.svg?label=Hackage)](https://hackage.haskell.org/package/tagsoup) [![Stackage version](https://www.stackage.org/package/tagsoup/badge/nightly?label=Stackage)](https://www.stackage.org/package/tagsoup) [![Linux build status](https://img.shields.io/travis/ndmitchell/tagsoup/master.svg?label=Linux%20build)](https://travis-ci.org/ndmitchell/tagsoup) [![Windows build status](https://img.shields.io/appveyor/ci/ndmitchell/tagsoup/master.svg?label=Windows%20build)](https://ci.appveyor.com/project/ndmitchell/tagsoup)  TagSoup is a library for parsing HTML/XML. It supports the HTML 5 specification, and can be used to parse either well-formed XML, or unstructured and malformed HTML from the web. The library also provides useful functions to extract information from an HTML document, making it ideal for screen-scraping. @@ -74,16 +74,6 @@  Now open `temp.htm`, find the fragment of HTML containing the hit count, and examine it. -#### Using the `tagsoup` Program--TagSoup installs both as a library and a program. The program contains all the-examples mentioned on this page, along with a few other useful functions. In-order to download a URL to a file:--```bash-$ tagsoup grab http://wiki.haskell.org/Haskell > temp.htm-```- ### Finding the Information  Now we examine both the fragment that contains our snippet of information, and@@ -204,7 +194,7 @@  ## Other Examples -Several more examples are given in the Example file, including obtaining the (short) list of papers from my site, getting the current time and a basic XML validator. All can be invoked using the `tagsoup` executable program. All use very much the same style as presented here - writing screen scrapers follow a standard pattern. We present the code from two for enjoyment only.+Several more examples are given in the [Sample.hs](https://github.com/ndmitchell/tagsoup/blob/master/test/TagSoup/Sample.hs) file, including obtaining the (short) list of papers from my site, getting the current time and a basic XML validator. All use very much the same style as presented here - writing screen scrapers follow a standard pattern. We present the code from two for enjoyment only.  ### My Papers @@ -252,6 +242,7 @@ ```  ## Other Examples+ In [Sample.hs](https://github.com/ndmitchell/tagsoup/blob/master/test/TagSoup/Sample.hs) the following additional examples are listed: @@ -259,7 +250,6 @@ - Package list form Hackage - Print names of story contributors on sequence.complete.org - Parse rows of a table-  ## Related Projects

src/Text/StringLike.hs view

@@ -37,6 +37,8 @@     strNull :: a -> Bool     -- | > append = (++)     append :: a -> a -> a+    -- | > strMap = map+    strMap :: (Char -> Char) -> a -> a   -- | Convert a String from one type to another.@@ -54,6 +56,7 @@     strNull = null     cons c = (c:)     append = (++)+    strMap = fmap  instance StringLike BS.ByteString where     uncons = BS.uncons@@ -64,6 +67,7 @@     strNull = BS.null     cons = BS.cons     append = BS.append+    strMap = BS.map  instance StringLike LBS.ByteString where     uncons = LBS.uncons@@ -74,6 +78,7 @@     strNull = LBS.null     cons = LBS.cons     append = LBS.append+    strMap = LBS.map  instance StringLike T.Text where     uncons = T.uncons@@ -84,6 +89,7 @@     strNull = T.null     cons = T.cons     append = T.append+    strMap = T.map  instance StringLike LT.Text where     uncons = LT.uncons@@ -94,3 +100,4 @@     strNull = LT.null     cons = LT.cons     append = LT.append+    strMap = LT.map

tagsoup.cabal view

@@ -1,7 +1,7 @@ cabal-version:  >= 1.18 name:           tagsoup-version:        0.14.7-copyright:      Neil Mitchell 2006-2018+version:        0.14.8+copyright:      Neil Mitchell 2006-2019 author:         Neil Mitchell <ndmitchell@gmail.com> maintainer:     Neil Mitchell <ndmitchell@gmail.com> homepage:       https://github.com/ndmitchell/tagsoup#readme@@ -11,7 +11,7 @@ license-file:   LICENSE build-type:     Simple synopsis:       Parsing and extracting information from (possibly malformed) HTML/XML documents-tested-with:    GHC==8.4.3, GHC==8.2.2, GHC==8.0.2, GHC==7.10.3, GHC==7.8.4, GHC==7.6.3, GHC==7.4.2+tested-with:    GHC==8.6.5, GHC==8.4.4, GHC==8.2.2, GHC==8.0.2, GHC==7.10.3 description:     TagSoup is a library for parsing HTML/XML. It supports the HTML 5 specification,     and can be used to parse either well-formed XML, or unstructured and malformed HTML

test/TagSoup/Benchmark.hs view

@@ -1,4 +1,3 @@-{-# LANGUAGE CPP #-} {-# OPTIONS_GHC -fno-warn-orphans #-} -- test file, so OK  module TagSoup.Benchmark where@@ -67,7 +66,7 @@  disp xs = showUnit (floor xbar) ++ " (~" ++ rng ++ "%)"     where xbar = mean xs-          rng = if length xs <= 1 then "?" else show (ceiling $ (range conf xs) * 100 / xbar) +          rng = if length xs <= 1 then "?" else show (ceiling $ (range conf xs) * 100 / xbar)  cons x = fmap (x:) @@ -157,23 +156,6 @@     rnf (TagComment x) = rnf x     rnf (TagWarning x) = rnf x     rnf (TagPosition x y) = () -- both are already ! bound---#ifndef BYTESTRING_HAS_NFDATA-# ifdef MIN_VERSION_bytestring-#  define BYTESTRING_HAS_NFDATA (MIN_VERSION_bytestring(0,10,0))-# else-#  define BYTESTRING_HAS_NFDATA (__GLASGOW_HASKELL__ >= 706)-# endif-#endif--#if !BYTESTRING_HAS_NFDATA-instance NFData LBS.ByteString where-    rnf x = LBS.length x `seq` ()--instance NFData BS.ByteString where-    rnf x = BS.length x `seq` ()-#endif   ---------------------------------------------------------------------