text-rope (empty) → 0.1
raw patch · 18 files changed
+4231/−0 lines, 18 filesdep +basedep +deepseqdep +random
Dependencies added: base, deepseq, random, tasty, tasty-bench, tasty-quickcheck, text, text-rope, vector
Files
- LICENSE +30/−0
- README.md +90/−0
- bench/Main.hs +177/−0
- bench/bench.txt +1844/−0
- cbits/utils.c +116/−0
- changelog.md +3/−0
- src/Data/Text/Lines.hs +25/−0
- src/Data/Text/Lines/Internal.hs +404/−0
- src/Data/Text/Rope.hs +354/−0
- src/Data/Text/Utf16/Lines.hs +275/−0
- src/Data/Text/Utf16/Rope.hs +362/−0
- test/CharLines.hs +98/−0
- test/CharRope.hs +51/−0
- test/Main.hs +26/−0
- test/Utf16Lines.hs +118/−0
- test/Utf16Rope.hs +69/−0
- test/Utils.hs +101/−0
- text-rope.cabal +88/−0
+ LICENSE view
@@ -0,0 +1,30 @@+Copyright Andrew Lelechenko (c) 2021-2022++All rights reserved.++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 Andrew Lelechenko nor the names of other+ 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.
+ README.md view
@@ -0,0 +1,90 @@+# text-rope [](https://hackage.haskell.org/package/text-rope) [](http://stackage.org/lts/package/text-rope) [](http://stackage.org/nightly/package/text-rope)++A wrapper around `Text` for fast line/column navigation and logarithmic concatenation.++Here are benchmarks for 1000 edits over 70K text:++```+Split at position+ Unicode+ text-rope:+ 3.09 ms ± 94 μs+ yi-rope:+ 49.4 ms ± 1.4 ms, 15.98x+ UTF-16+ text-rope:+ 3.09 ms ± 106 μs+ rope-utf16-splay:+ 10.6 ms ± 337 μs, 3.44x+Split at offset+ Unicode+ text-rope:+ 3.04 ms ± 112 μs+ core-text:+ 14.0 ms ± 297 μs, 4.59x+ yi-rope:+ 6.25 ms ± 102 μs, 2.06x+ UTF-16+ text-rope:+ 3.40 ms ± 70 μs+ rope-utf16-splay:+ 8.92 ms ± 169 μs, 2.62x+```++For 10000 edits over 700K text:++```+Split at position+ Unicode+ text-rope:+ 62.9 ms ± 4.2 ms+ yi-rope:+ 568 ms ± 31 ms, 9.04x+ UTF-16+ text-rope:+ 61.0 ms ± 3.9 ms+ rope-utf16-splay:+ 325 ms ± 13 ms, 5.32x+Split at offset+ Unicode+ text-rope:+ 59.6 ms ± 3.8 ms+ core-text:+ 209 ms ± 15 ms, 3.50x+ yi-rope:+ 105 ms ± 7.4 ms, 1.76x+ UTF-16+ text-rope:+ 63.6 ms ± 5.3 ms+ rope-utf16-splay:+ 230 ms ± 9.0 ms, 3.62x+```++For 100000 edits over 7M text:++```+Split at position+ Unicode+ text-rope:+ 963 ms ± 43 ms+ yi-rope:+ 6.379 s ± 138 ms, 6.62x+ UTF-16+ text-rope:+ 988 ms ± 19 ms+ rope-utf16-splay: T+ 57.408 s ± 4.24 s, 58.12x+Split at offset+ Unicode+ text-rope:+ 1.014 s ± 70 ms+ core-text:+ 3.008 s ± 138 ms, 2.97x+ yi-rope:+ 1.716 s ± 76 ms, 1.69x+ UTF-16+ text-rope:+ 1.065 s ± 53 ms+ rope-utf16-splay:+ 38.852 s ± 568 ms, 36.49x+```
+ bench/Main.hs view
@@ -0,0 +1,177 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++{-# LANGUAGE CPP #-}+{-# LANGUAGE ScopedTypeVariables #-}+{-# LANGUAGE TypeApplications #-}++module Main+ ( main+ ) where++import Prelude (fromIntegral, (<$>), (*))+import Paths_text_rope (getDataFileName)+import Data.Function (($), (.))+import Data.Int (Int)+import Data.List (foldl', take, zip, length)+import Data.Maybe (fromJust)+import Data.Monoid (Monoid, mappend)+import Data.Proxy (Proxy(..))+import Data.Semigroup ((<>))+import qualified Data.Text as T+import qualified Data.Text.IO as T+import Data.Word (Word)+import System.IO (IO)+import System.IO.Unsafe (unsafePerformIO)+import System.Random (randomRs, mkStdGen)+import Test.Tasty.Bench (defaultMain, bgroup, bench, nf, bcompare)++import qualified Data.Text.Rope as CharRope+import qualified Data.Text.Utf16.Rope as Utf16Rope+#ifdef MIN_VERSION_core_text+import qualified Core.Text.Rope as CoreText+#endif+#ifdef MIN_VERSION_rope_utf16_splay+import qualified Data.Rope.UTF16 as RopeSplay+#endif+#ifdef MIN_VERSION_yi_rope+import qualified Yi.Rope as YiRope+#endif++main :: IO ()+main = defaultMain+ [ bgroup "Split at position"+ [ bgroup "Unicode"+ [ bench "text-rope" $ nf (editByPosition (Proxy @CharRope.Rope)) txt+#ifdef MIN_VERSION_yi_rope+ , bcompare "$NF == \"text-rope\" && $(NF-1) == \"Unicode\" && $(NF-2) == \"Split at position\""+ $ bench "yi-rope" $ nf (editByPosition (Proxy @YiRope.YiString)) txt+#endif+ ]+ , bgroup "UTF-16"+ [ bench "text-rope" $ nf (editByPosition (Proxy @Utf16Rope.Rope)) txt+#ifdef MIN_VERSION_rope_utf16_splay+ , bcompare "$NF == \"text-rope\" && $(NF-1) == \"UTF-16\" && $(NF-2) == \"Split at position\""+ $ bench "rope-utf16-splay" $ nf (editByPosition (Proxy @RopeSplay.Rope)) txt+#endif+ ]+ ]+ , bgroup "Split at offset"+ [ bgroup "Unicode"+ [ bench "text-rope" $ nf (editByOffset (Proxy @CharRope.Rope)) txt+#ifdef MIN_VERSION_core_text+ , bcompare "$NF == \"text-rope\" && $(NF-1) == \"Unicode\" && $(NF-2) == \"Split at offset\""+ $ bench "core-text" $ nf (editByOffset (Proxy @CoreText.Rope)) txt+#endif+#ifdef MIN_VERSION_yi_rope+ , bcompare "$NF == \"text-rope\" && $(NF-1) == \"Unicode\" && $(NF-2) == \"Split at offset\""+ $ bench "yi-rope" $ nf (editByOffset (Proxy @YiRope.YiString)) txt+#endif+ ]+ , bgroup "UTF-16"+ [ bench "text-rope" $ nf (editByOffset (Proxy @Utf16Rope.Rope)) txt+#ifdef MIN_VERSION_rope_utf16_splay+ , bcompare "$NF == \"text-rope\" && $(NF-1) == \"UTF-16\" && $(NF-2) == \"Split at offset\""+ $ bench "rope-utf16-splay" $ nf (editByOffset (Proxy @RopeSplay.Rope)) txt+#endif+ ]+ ]+ ]++scale :: Int+scale = 1++txt :: T.Text+txt = unsafePerformIO $ do+ fn <- getDataFileName "bench/bench.txt"+ T.replicate scale <$> T.readFile fn+{-# NOINLINE txt #-}++randomOffsets :: [Word]+randomOffsets = take (1000 * scale) $+ randomRs (0, fromIntegral $ T.length txt) (mkStdGen 33)+{-# NOINLINE randomOffsets #-}++randomPositions :: [(Word, Word)]+randomPositions = take (1000 * scale) $ zip ls cs+ where+ ls = randomRs (0, fromIntegral $ length $ T.lines txt) (mkStdGen 42)+ -- assuming reasonable line length is < 80+ cs = randomRs (0, 80) (mkStdGen 24)+{-# NOINLINE randomPositions #-}++class Monoid a => Splittable a where+ fromText :: T.Text -> a+ toText :: a -> T.Text+ splitAt :: Word -> a -> (a, a)++class Splittable a => SplittableAtPosition a where+ splitAtPosition :: Word -> Word -> a -> (a, a)++instance Splittable CharRope.Rope where+ fromText = CharRope.fromText+ toText = CharRope.toText+ splitAt = CharRope.splitAt++instance SplittableAtPosition CharRope.Rope where+ splitAtPosition l c = CharRope.splitAtPosition (CharRope.Position l c)++instance Splittable Utf16Rope.Rope where+ fromText = Utf16Rope.fromText+ toText = Utf16Rope.toText+ splitAt = (fromJust . ) . Utf16Rope.splitAt++instance SplittableAtPosition Utf16Rope.Rope where+ splitAtPosition l c = fromJust . Utf16Rope.splitAtPosition (Utf16Rope.Position l c)++#ifdef MIN_VERSION_core_text+instance Splittable CoreText.Rope where+ fromText = CoreText.intoRope+ toText = CoreText.fromRope+ splitAt = CoreText.splitRope . fromIntegral+#endif++#ifdef MIN_VERSION_yi_rope+instance Splittable YiRope.YiString where+ fromText = YiRope.fromText+ toText = YiRope.toText+ splitAt = YiRope.splitAt . fromIntegral++instance SplittableAtPosition YiRope.YiString where+ splitAtPosition l c orig = (before `mappend` mid, after)+ where+ (before, after') = YiRope.splitAtLine (fromIntegral l) orig+ (mid, after) = YiRope.splitAt (fromIntegral c) after'+#endif++#ifdef MIN_VERSION_rope_utf16_splay+instance Splittable RopeSplay.Rope where+ fromText = RopeSplay.fromText+ toText = RopeSplay.toText+ splitAt = RopeSplay.splitAt . fromIntegral++instance SplittableAtPosition RopeSplay.Rope where+ splitAtPosition l c orig = RopeSplay.splitAt k orig+ where+ k = RopeSplay.rowColumnCodeUnits (RopeSplay.RowColumn (fromIntegral l) (fromIntegral c)) orig+#endif++editByOffset :: forall a. Splittable a => Proxy a -> T.Text -> T.Text+editByOffset _ txt = (toText @a) $ foldl' edit (fromText txt) randomOffsets+ where+ edit orig c = before `mappend` mid `mappend` after+ where+ (before, after') = splitAt c orig+ -- edit 10 characters+ (mid, after) = splitAt 10 after'++editByPosition :: forall a. SplittableAtPosition a => Proxy a -> T.Text -> T.Text+editByPosition _ txt = (toText @a) $ foldl' edit (fromText txt) randomPositions+ where+ edit orig (l, c) = before `mappend` mid `mappend` after+ where+ (before, after') = splitAtPosition l c orig+ -- edit 10 characters+ (mid, after) = splitAt 10 after'
+ bench/bench.txt view
@@ -0,0 +1,1844 @@+{- |+Module: Test.Tasty.Bench+Copyright: (c) 2021 Andrew Lelechenko+Licence: MIT++Featherlight benchmark framework (only one file!) for performance+measurement with API+mimicking [@criterion@](http://hackage.haskell.org/package/criterion)+and [@gauge@](http://hackage.haskell.org/package/gauge).+A prominent feature is built-in comparison against previous runs+and between benchmarks.++=== How lightweight is it?++There is only one source file "Test.Tasty.Bench" and no non-boot+dependencies except [@tasty@](http://hackage.haskell.org/package/tasty). So+if you already depend on @tasty@ for a test suite, there is nothing else+to install.++Compare this to @criterion@ (10+ modules, 50+ dependencies) and @gauge@+(40+ modules, depends on @basement@ and @vector@). A build on a clean machine is up to 16x+faster than @criterion@ and up to 4x faster than @gauge@. A build without dependencies+is up to 6x faster than @criterion@ and up to 8x faster than @gauge@.++@tasty-bench@ is a native Haskell library and works everywhere, where GHC+does. We support a full range of architectures (@i386@, @amd64@, @armhf@,+@arm64@, @ppc64le@, @s390x@) and operating systems (Linux, Windows, MacOS,+FreeBSD), plus any GHC from 7.0 to 9.2.++=== How is it possible?++Our benchmarks are literally regular @tasty@ tests, so we can leverage+all existing machinery for command-line options, resource management,+structuring, listing and filtering benchmarks, running and reporting+results. It also means that @tasty-bench@ can be used in conjunction+with other @tasty@ ingredients.++Unlike @criterion@ and @gauge@ we use a very simple statistical model+described below. This is arguably a questionable choice, but it works+pretty well in practice. A rare developer is sufficiently well-versed in+probability theory to make sense and use of all numbers generated by+@criterion@.++=== How to switch?++<https://cabal.readthedocs.io/en/3.4/cabal-package.html#pkg-field-mixins Cabal mixins>+allow to taste @tasty-bench@ instead of @criterion@ or @gauge@ without+changing a single line of code:++> cabal-version: 2.0+>+> benchmark foo+> ...+> build-depends:+> tasty-bench+> mixins:+> tasty-bench (Test.Tasty.Bench as Criterion, Test.Tasty.Bench as Criterion.Main, Test.Tasty.Bench as Gauge, Test.Tasty.Bench as Gauge.Main)++This works vice versa as well: if you use @tasty-bench@, but at some+point need a more comprehensive statistical analysis, it is easy to+switch temporarily back to @criterion@.++=== How to write a benchmark?++Benchmarks are declared in a separate section of @cabal@ file:++> cabal-version: 2.0+> name: bench-fibo+> version: 0.0+> build-type: Simple+> synopsis: Example of a benchmark+>+> benchmark bench-fibo+> main-is: BenchFibo.hs+> type: exitcode-stdio-1.0+> build-depends: base, tasty-bench+> ghc-options: "-with-rtsopts=-A32m"++And here is @BenchFibo.hs@:++> import Test.Tasty.Bench+>+> fibo :: Int -> Integer+> fibo n = if n < 2 then toInteger n else fibo (n - 1) + fibo (n - 2)+>+> main :: IO ()+> main = defaultMain+> [ bgroup "fibonacci numbers"+> [ bench "fifth" $ nf fibo 5+> , bench "tenth" $ nf fibo 10+> , bench "twentieth" $ nf fibo 20+> ]+> ]++Since @tasty-bench@ provides an API compatible with @criterion@, one can+refer to+<http://www.serpentine.com/criterion/tutorial.html#how-to-write-a-benchmark-suite its documentation>+for more examples.++=== How to read results?++Running the example above (@cabal@ @bench@ or @stack@ @bench@) results in+the following output:++> All+> fibonacci numbers+> fifth: OK (2.13s)+> 63 ns ± 3.4 ns+> tenth: OK (1.71s)+> 809 ns ± 73 ns+> twentieth: OK (3.39s)+> 104 μs ± 4.9 μs+>+> All 3 tests passed (7.25s)++The output says that, for instance, the first benchmark was repeatedly+executed for 2.13 seconds (wall time), its predicted mean CPU time was+63 nanoseconds and means of individual samples do not often diverge from it+further than ±3.4 nanoseconds (double standard deviation). Take standard+deviation numbers with a grain of salt; there are lies, damned lies, and+statistics.++=== Wall-clock time vs. CPU time++What time are we talking about?+Both @criterion@ and @gauge@ by default report wall-clock time, which is+affected by any other application which runs concurrently.+Ideally benchmarks are executed on a dedicated server without any other load,+but — let's face the truth — most of developers run benchmarks+on a laptop with a hundred other services and a window manager, and+watch videos while waiting for benchmarks to finish. That's the cause+of a notorious "variance introduced by outliers: 88% (severely inflated)" warning.++To alleviate this issue @tasty-bench@ measures CPU time by 'getCPUTime'+instead of wall-clock time.+It does not provide a perfect isolation from other processes (e. g.,+if CPU cache is spoiled by others, populating data back from RAM+is your burden), but is a bit more stable.++Caveat: this means that for multithreaded algorithms+@tasty-bench@ reports total elapsed CPU time across all cores, while+@criterion@ and @gauge@ print maximum of core's wall-clock time.+It also means that @tasty-bench@ cannot measure time spent out of process,+e. g., calls to other executables.++=== Statistical model++Here is a procedure used by @tasty-bench@ to measure execution time:++1. Set \( n \leftarrow 1 \).+2. Measure execution time \( t_n \) of \( n \) iterations and execution time+ \( t_{2n} \) of \( 2n \) iterations.+3. Find \( t \) which minimizes deviation of \( (nt, 2nt) \) from+ \( (t_n, t_{2n}) \), namely \( t \leftarrow (t_n + 2t_{2n}) / 5n \).+4. If deviation is small enough (see @--stdev@ below)+ or time is running out soon (see @--timeout@ below),+ return \( t \) as a mean execution time.+5. Otherwise set \( n \leftarrow 2n \) and jump back to Step 2.++This is roughly similar to the linear regression approach which+@criterion@ takes, but we fit only two last points. This allows us to+simplify away all heavy-weight statistical analysis. More importantly,+earlier measurements, which are presumably shorter and noisier, do not+affect overall result. This is in contrast to @criterion@, which fits+all measurements and is biased to use more data points corresponding to+shorter runs (it employs \( n \leftarrow 1.05n \) progression).++Mean time and its deviation does not say much about the+distribution of individual timings. E. g., imagine a computation which+(according to a coarse system timer) takes either 0 ms or 1 ms with equal+probability. While one would be able to establish that its mean time is 0.5 ms+with a very small deviation, this does not imply that individual measurements+are anywhere near 0.5 ms. Even assuming an infinite precision of a system+timer, the distribution of individual times is not known to be+<https://en.wikipedia.org/wiki/Normal_distribution normal>.++Obligatory disclaimer: statistics is a tricky matter, there is no+one-size-fits-all approach. In the absence of a good theory simplistic+approaches are as (un)sound as obscure ones. Those who seek statistical+soundness should rather collect raw data and process it themselves using+a proper statistical toolbox. Data reported by @tasty-bench@ is only of+indicative and comparative significance.++=== Memory usage++Configuring RTS to collect GC statistics+(e. g., via @cabal@ @bench@ @--benchmark-options@ @\'+RTS@ @-T\'@ or+@stack@ @bench@ @--ba@ @\'+RTS@ @-T\'@) enables @tasty-bench@ to estimate and+report memory usage:++> All+> fibonacci numbers+> fifth: OK (2.13s)+> 63 ns ± 3.4 ns, 223 B allocated, 0 B copied, 2.0 MB peak memory+> tenth: OK (1.71s)+> 809 ns ± 73 ns, 2.3 KB allocated, 0 B copied, 4.0 MB peak memory+> twentieth: OK (3.39s)+> 104 μs ± 4.9 μs, 277 KB allocated, 59 B copied, 5.0 MB peak memory+>+> All 3 tests passed (7.25s)++This data is reported as per 'RTSStats' fields: 'allocated_bytes', 'copied_bytes'+and 'max_mem_in_use_bytes'.++=== Combining tests and benchmarks++When optimizing an existing function, it is important to check that its+observable behavior remains unchanged. One can rebuild both tests and+benchmarks after each change, but it would be more convenient to run+sanity checks within benchmark itself. Since our benchmarks are+compatible with @tasty@ tests, we can easily do so.++Imagine you come up with a faster function @myFibo@ to generate+Fibonacci numbers:++> import Test.Tasty.Bench+> import Test.Tasty.QuickCheck -- from tasty-quickcheck package+>+> fibo :: Int -> Integer+> fibo n = if n < 2 then toInteger n else fibo (n - 1) + fibo (n - 2)+>+> myFibo :: Int -> Integer+> myFibo n = if n < 3 then toInteger n else myFibo (n - 1) + myFibo (n - 2)+>+> main :: IO ()+> main = Test.Tasty.Bench.defaultMain -- not Test.Tasty.defaultMain+> [ bench "fibo 20" $ nf fibo 20+> , bench "myFibo 20" $ nf myFibo 20+> , testProperty "myFibo = fibo" $ \n -> fibo n === myFibo n+> ]++This outputs:++> All+> fibo 20: OK (3.02s)+> 104 μs ± 4.9 μs+> myFibo 20: OK (1.99s)+> 71 μs ± 5.3 μs+> myFibo = fibo: FAIL+> *** Failed! Falsified (after 5 tests and 1 shrink):+> 2+> 1 /= 2+> Use --quickcheck-replay=927711 to reproduce.+>+> 1 out of 3 tests failed (5.03s)++We see that @myFibo@ is indeed significantly faster than @fibo@, but+unfortunately does not do the same thing. One should probably look for+another way to speed up generation of Fibonacci numbers.++=== Troubleshooting++- If benchmarks take too long, set @--timeout@ to limit execution time+ of individual benchmarks, and @tasty-bench@ will do its best to fit+ into a given time frame. Without @--timeout@ we rerun benchmarks until+ achieving a target precision set by @--stdev@, which in a noisy+ environment of a modern laptop with GUI may take a lot of time.++ While @criterion@ runs each benchmark at least for 5 seconds,+ @tasty-bench@ is happy to conclude earlier, if it does not+ compromise the quality of results. In our experiments @tasty-bench@+ suites tend to finish earlier, even if some individual benchmarks+ take longer than with @criterion@.++ A common source of noisiness is garbage collection. Setting a larger+ allocation area (/nursery/) is often a good idea, either via+ @cabal@ @bench@ @--benchmark-options@ @\'+RTS@ @-A32m\'@ or+ @stack@ @bench@ @--ba@ @\'+RTS@ @-A32m\'@. Alternatively bake it into @cabal@+ file as @ghc-options:@ @\"-with-rtsopts=-A32m\"@.++ For GHC ≥ 8.10 consider switching benchmarks to a non-moving garbage collector,+ because it decreases GC pauses and corresponding noise: @+RTS@ @--nonmoving-gc@.++- If benchmark results look malformed like below, make sure that you+ are invoking 'Test.Tasty.Bench.defaultMain' and not+ 'Test.Tasty.defaultMain' (the difference is 'consoleBenchReporter'+ vs. 'consoleTestReporter'):++ > All+ > fibo 20: OK (1.46s)+ > Response {respEstimate = Estimate {estMean = Measurement {measTime = 87496728, measAllocs = 0, measCopied = 0}, estStdev = 694487}, respIfSlower = FailIfSlower Infinity, respIfFaster = FailIfFaster Infinity}++- If benchmarks fail with an error message++ > Unhandled resource. Probably a bug in the runner you're using.++ or++ > Unexpected state of the resource (NotCreated) in getResource. Report as a tasty bug.++ this is likely caused by 'env' or 'envWithCleanup' affecting+ benchmarks structure. You can use 'env' to read test data from 'IO',+ but not to read benchmark names or affect their hierarchy in other+ way. This is a fundamental restriction of @tasty@ to list and filter+ benchmarks without launching missiles.++- If benchmarks fail with @Test dependencies form a loop@, this is likely+ because of 'bcompare', which compares a benchmark with itself.+ Locating a benchmark in a global environment may be tricky, please refer to+ [@tasty@ documentation](https://github.com/UnkindPartition/tasty#patterns) for details.++=== Isolating interfering benchmarks++One difficulty of benchmarking in Haskell is that it is hard to isolate+benchmarks so that they do not interfere. Changing the order of+benchmarks or skipping some of them has an effect on heap’s layout and+thus affects garbage collection. This issue is well attested in+<https://github.com/haskell/criterion/issues/166 both>+<https://github.com/haskell/criterion/issues/60 criterion> and+<https://github.com/vincenthz/hs-gauge/issues/2 gauge>.++Usually (but not always) skipping some benchmarks speeds up remaining+ones. That’s because once a benchmark allocated heap which for some+reason was not promptly released afterwards (e. g., it forced a+top-level thunk in an underlying library), all further benchmarks are+slowed down by garbage collector processing this additional amount of+live data over and over again.++There are several mitigation strategies. First of all, giving garbage+collector more breathing space by @+RTS@ @-A32m@ (or more) is often good+enough.++Further, avoid using top-level bindings to store large test data. Once+such thunks are forced, they remain allocated forever, which affects+detrimentally subsequent unrelated benchmarks. Treat them as external+data, supplied via 'env': instead of++> largeData :: String+> largeData = replicate 1000000 'a'+>+> main :: IO ()+> main = defaultMain+> [ bench "large" $ nf length largeData, ... ]++use++> import Control.DeepSeq (force)+> import Control.Exception (evaluate)+>+> main :: IO ()+> main = defaultMain+> [ env (evaluate (force (replicate 1000000 'a'))) $ \largeData ->+> bench "large" $ nf length largeData, ... ]++Finally, as an ultimate measure to reduce interference between+benchmarks, one can run each of them in a separate process. We do not+quite recommend this approach, but if you are desperate, here is how.++Assuming that a benchmark is declared in @cabal@ file as+@benchmark@ @my-bench@ component, let’s first find its executable:++> cabal build --enable-benchmarks my-bench+> MYBENCH=$(cabal list-bin my-bench) # available since cabal-3.4++Now list all benchmark names (hopefully, they do not contain newlines),+escape quotes and slashes, and run each of them separately:++> $MYBENCH -l | sed -e 's/[\"]/\\\\\\&/g' | while read -r name; do $MYBENCH -p '$0 == "'"$name"'"'; done++=== Comparison against baseline++One can compare benchmark results against an earlier baseline in an+automatic way. To use this feature, first run @tasty-bench@ with+@--csv@ @FILE@ key to dump results to @FILE@ in CSV format+(it could be a good idea to set smaller @--stdev@, if possible):++> Name,Mean (ps),2*Stdev (ps)+> All.fibonacci numbers.fifth,48453,4060+> All.fibonacci numbers.tenth,637152,46744+> All.fibonacci numbers.twentieth,81369531,3342646++Now modify implementation and rerun benchmarks with @--baseline@ @FILE@+key. This produces a report as follows:++> All+> fibonacci numbers+> fifth: OK (0.44s)+> 53 ns ± 2.7 ns, 8% slower than baseline+> tenth: OK (0.33s)+> 641 ns ± 59 ns+> twentieth: OK (0.36s)+> 77 μs ± 6.4 μs, 5% faster than baseline+>+> All 3 tests passed (1.50s)++You can also fail benchmarks, which deviate too far from baseline, using+@--fail-if-slower@ and @--fail-if-faster@ options. For example, setting+both of them to 6 will fail the first benchmark above (because it is+more than 6% slower), but the last one still succeeds (even while it is+measurably faster than baseline, deviation is less than 6%). Consider+also using @--hide-successes@ to show only problematic benchmarks, or+even [@tasty-rerun@](http://hackage.haskell.org/package/tasty-rerun)+package to focus on rerunning failing items only.++If you wish to compare two CSV reports non-interactively, here is a handy @awk@ incantation:++> awk 'BEGIN{FS=",";OFS=",";print "Name,Old,New,Ratio"}FNR==1{next}FNR==NR{a[$1]=$2;next}{print $1,a[$1],$2,$2/a[$1];gs+=log($2/a[$1]);gc++}END{print "Geometric mean,,",exp(gs/gc)}' old.csv new.csv++Here is a larger snippet to compare two @git@ commits:++> compareBenches () {+> # compareBenches oldCommit newCommit <other arguments are passed to benchmarks directly>+> OLD="$1"+> shift+> NEW="$1"+> shift+> git checkout "$OLD"+> cabal run benchmarks -- --csv "$OLD".csv "$@"+> git checkout "$NEW"+> cabal run benchmarks -- --baseline "$OLD".csv --csv "$NEW".csv "$@"+> git checkout "@{\-2}"+> awk 'BEGIN{FS=",";OFS=",";print "Name,'"$OLD"','"$NEW"',Ratio"}FNR==1{next}FNR==NR{a[$1]=$2;next}{print $1,a[$1],$2,$2/a[$1];gs+=log($2/a[$1]);gc++}END{print "Geometric mean,,",exp(gs/gc)}' "$OLD".csv "$NEW".csv > "$OLD"-vs-"$NEW".csv+> }++Note that columns in CSV report are different from what @criterion@ or @gauge@+would produce. If names do not contain commas, missing columns can be faked this way:++> cat tasty-bench.csv | awk 'BEGIN {FS=",";OFS=","}; {print $1,$2/1e12,$2/1e12,$2/1e12,$3/2e12,$3/2e12,$3/2e12}' | sed '1s/.*/Name,Mean,MeanLB,MeanUB,Stddev,StddevLB,StddevUB/'++To fake @gauge@ in @--csvraw@ mode use++> cat tasty-bench.csv | awk 'BEGIN {FS=",";OFS=","}; {print $1,1,$2/1e12,0,$2/1e12,$2/1e12,0,$6+0,0,0,0,0,$4+0,0,$5+0,0,0,0,0}' | sed '1s/.*/name,iters,time,cycles,cpuTime,utime,stime,maxrss,minflt,majflt,nvcsw,nivcsw,allocated,numGcs,bytesCopied,mutatorWallSeconds,mutatorCpuSeconds,gcWallSeconds,gcCpuSeconds/'++Please refer to @gawk@ manual, if you wish to process names+with [commas](https://www.gnu.org/software/gawk/manual/gawk.html#Splitting-By-Content)+or [quotes](https://www.gnu.org/software/gawk/manual/gawk.html#More-CSV).++=== Comparison between benchmarks++You can also compare benchmarks to each other without reaching to+external tools, all in the comfort of your terminal.++> import Test.Tasty.Bench+>+> fibo :: Int -> Integer+> fibo n = if n < 2 then toInteger n else fibo (n - 1) + fibo (n - 2)+>+> main :: IO ()+> main = defaultMain+> [ bgroup "fibonacci numbers"+> [ bcompare "tenth" $ bench "fifth" $ nf fibo 5+> , bench "tenth" $ nf fibo 10+> , bcompare "tenth" $ bench "twentieth" $ nf fibo 20+> ]+> ]++This produces a report, comparing mean times of @fifth@ and @twentieth@+to @tenth@:++> All+> fibonacci numbers+> fifth: OK (16.56s)+> 121 ns ± 2.6 ns, 0.08x+> tenth: OK (6.84s)+> 1.6 μs ± 31 ns+> twentieth: OK (6.96s)+> 203 μs ± 4.1 μs, 128.36x++Locating a baseline benchmark in larger suites could get tricky;++> bcompare "$NF == \"tenth\" && $(NF-1) == \"fibonacci numbers\""++is a more robust choice of+an <https://github.com/UnkindPartition/tasty#patterns awk pattern> here.++One can leverage comparisons between benchmarks to implement portable performance+tests, expressing properties like "this algorithm must be at least twice faster+than that one" or "this operation should not be more than thrice slower than that".+This can be achieved with 'bcompareWithin', which takes an acceptable interval+of performance as an argument.++=== Plotting results++Users can dump results into CSV with @--csv@ @FILE@ and plot them using+@gnuplot@ or other software. But for convenience there is also a+built-in quick-and-dirty SVG plotting feature, which can be invoked by+passing @--svg@ @FILE@. Here is a sample of its output:++++=== Build flags++Build flags are a brittle subject and users do not normally need to touch them.++* If you find yourself in an environment, where @tasty@ is not available and you+ have access to boot packages only, you can still use @tasty-bench@! Just copy+ @Test\/Tasty\/Bench.hs@ to your project (imagine it like a header-only C library).+ It will provide you with functions to build 'Benchmarkable' and run them manually+ via 'measureCpuTime'. This mode of operation can be also configured+ by disabling Cabal flag @tasty@.++* If results are amiss or oscillate wildly and adjusting @--timeout@ and @--stdev@+ does not help, you may be interested to investigate individual timings of+ successive runs by enabling Cabal flag @debug@. This will pipe raw data into @stderr@.++=== Command-line options++Use @--help@ to list command-line options.++[@-p@, @--pattern@]:++ This is a standard @tasty@ option, which allows filtering benchmarks+ by a pattern or @awk@ expression. Please refer+ to [@tasty@ documentation](https://github.com/UnkindPartition/tasty#patterns)+ for details.++[@-t@, @--timeout@]:++ This is a standard @tasty@ option, setting timeout for individual+ benchmarks in seconds. Use it when benchmarks tend to take too long:+ @tasty-bench@ will make an effort to report results (even if of+ subpar quality) before timeout. Setting timeout too tight+ (insufficient for at least three iterations) will result in a+ benchmark failure. One can adjust it locally for a group+ of benchmarks, e. g., 'localOption' ('mkTimeout' 100000000) for 100 seconds.++[@--stdev@]:++ Target relative standard deviation of measurements in percents (5%+ by default). Large values correspond to fast and loose benchmarks,+ and small ones to long and precise.+ It can also be adjusted locally for a group of benchmarks,+ e. g., 'localOption' ('RelStDev' 0.02).+ If benchmarking takes far too long, consider setting @--timeout@,+ which will interrupt benchmarks,+ potentially before reaching the target deviation.++[@--csv@]:++ File to write results in CSV format.++[@--baseline@]:++ File to read baseline results in CSV format (as produced by+ @--csv@).++[@--fail-if-slower@, @--fail-if-faster@]:++ Upper bounds of acceptable slow down \/ speed up in percents. If a+ benchmark is unacceptably slower \/ faster than baseline (see+ @--baseline@), it will be reported as failed. Can be used in+ conjunction with a standard @tasty@ option @--hide-successes@ to+ show only problematic benchmarks.+ Both options can be adjusted locally for a group of benchmarks,+ e. g., 'localOption' ('FailIfSlower' 0.10).++[@--svg@]:++ File to plot results in SVG format.++[@+RTS@ @-T@]:++ Estimate and report memory usage.++=== Custom command-line options++As usual with @tasty@, it is easy to extend benchmarks with custom command-line options.+Here is an example:++> import Data.Proxy+> import Test.Tasty.Bench+> import Test.Tasty.Ingredients.Basic+> import Test.Tasty.Options+> import Test.Tasty.Runners+>+> newtype RandomSeed = RandomSeed Int+>+> instance IsOption RandomSeed where+> defaultValue = RandomSeed 42+> parseValue = fmap RandomSeed . safeRead+> optionName = pure "seed"+> optionHelp = pure "Random seed used in benchmarks"+>+> main :: IO ()+> main = do+> let customOpts = [Option (Proxy :: Proxy RandomSeed)]+> ingredients = includingOptions customOpts : benchIngredients+> opts <- parseOptions ingredients benchmarks+> let RandomSeed seed = lookupOption opts+> defaultMainWithIngredients ingredients benchmarks+>+> benchmarks :: Benchmark+> benchmarks = bgroup "All" []++-}++{-# LANGUAGE CPP #-}+{-# LANGUAGE DeriveDataTypeable #-}+{-# LANGUAGE DeriveFunctor #-}+{-# LANGUAGE FlexibleContexts #-}+{-# LANGUAGE FlexibleInstances #-}+{-# LANGUAGE ScopedTypeVariables #-}+{-# LANGUAGE TupleSections #-}++module Test.Tasty.Bench+ (+#ifdef MIN_VERSION_tasty+ -- * Running 'Benchmark'+ defaultMain+ , Benchmark+ , bench+ , bgroup+#if MIN_VERSION_tasty(1,2,0)+ , bcompare+ , bcompareWithin+#endif+ , env+ , envWithCleanup+ ,+#endif+ -- * Creating 'Benchmarkable'+ Benchmarkable(..)+ , nf+ , whnf+ , nfIO+ , whnfIO+ , nfAppIO+ , whnfAppIO+ , measureCpuTime+#ifdef MIN_VERSION_tasty+ -- * Ingredients+ , benchIngredients+ , consoleBenchReporter+ , csvReporter+ , svgReporter+ , RelStDev(..)+ , FailIfSlower(..)+ , FailIfFaster(..)+ , CsvPath(..)+ , BaselinePath(..)+ , SvgPath(..)+#else+ , Timeout(..)+ , RelStDev(..)+#endif+ ) where++import Prelude hiding (Int, Integer)+import qualified Prelude+import Control.Applicative+import Control.Arrow (first, second)+import Control.DeepSeq (NFData, force)+import Control.Exception (bracket, evaluate)+import Control.Monad (void, unless, guard, (>=>), when)+import Data.Data (Typeable)+import Data.Foldable (foldMap, traverse_)+import Data.Int (Int64)+import Data.IORef+import Data.List (intercalate, stripPrefix, isPrefixOf, genericLength, genericDrop)+import Data.Monoid (All(..), Any(..))+import Data.Proxy+import Data.Traversable (forM)+import Data.Word (Word64)+import GHC.Conc+#if MIN_VERSION_base(4,5,0)+import GHC.IO.Encoding+#endif+#if MIN_VERSION_base(4,6,0)+import GHC.Stats+#endif+import System.CPUTime+import System.Exit+import System.IO+import System.IO.Unsafe+import System.Mem+import Text.Printf++#ifdef DEBUG+import Debug.Trace+#endif++#ifdef MIN_VERSION_tasty+#if !MIN_VERSION_base(4,8,0)+import Data.Monoid (Monoid(..))+#endif+#if MIN_VERSION_base(4,9,0)+import Data.Semigroup (Semigroup(..))+#endif+#if MIN_VERSION_containers(0,5,0)+import qualified Data.IntMap.Strict as IM+#else+import qualified Data.IntMap as IM+#endif+import Data.IntMap (IntMap)+import Data.Sequence (Seq, (<|))+import qualified Data.Sequence as Seq+import qualified Data.Set as S+import Test.Tasty hiding (defaultMain)+import qualified Test.Tasty+import Test.Tasty.Ingredients+import Test.Tasty.Ingredients.ConsoleReporter+import Test.Tasty.Options+#if MIN_VERSION_tasty(1,2,0)+import Test.Tasty.Patterns.Eval (eval, asB, withFields)+import Test.Tasty.Patterns.Types (Expr (And, StringLit))+#endif+import Test.Tasty.Providers+import Test.Tasty.Runners+#endif++#ifndef MIN_VERSION_tasty+data Timeout+ = Timeout+ Prelude.Integer -- ^ number of microseconds (e. g., 200000)+ String -- ^ textual representation (e. g., @"0.2s"@)+ | NoTimeout+ deriving (Show)+#endif+++-- | In addition to @--stdev@ command-line option,+-- one can adjust target relative standard deviation+-- for individual benchmarks and groups of benchmarks+-- using 'adjustOption' and 'localOption'.+--+-- E. g., set target relative standard deviation to 2% as follows:+--+-- > import Test.Tasty (localOption)+-- > localOption (RelStDev 0.02) (bgroup [...])+--+-- If you set 'RelStDev' to infinity,+-- a benchmark will be executed+-- only once and its standard deviation will be recorded as zero.+-- This is rather a blunt approach, but it might be a necessary evil+-- for extremely long benchmarks. If you wish to run all benchmarks+-- only once, use command-line option @--stdev@ @Infinity@.+--+newtype RelStDev = RelStDev Double+ deriving (Show, Read, Typeable)++#ifdef MIN_VERSION_tasty+instance IsOption RelStDev where+ defaultValue = RelStDev 0.05+ parseValue = fmap RelStDev . parsePositivePercents+ optionName = pure "stdev"+ optionHelp = pure "Target relative standard deviation of measurements in percents (5 by default). Large values correspond to fast and loose benchmarks, and small ones to long and precise. If it takes far too long, consider setting --timeout, which will interrupt benchmarks, potentially before reaching the target deviation."++-- | In addition to @--fail-if-slower@ command-line option,+-- one can adjust an upper bound of acceptable slow down+-- in comparison to baseline for+-- individual benchmarks and groups of benchmarks+-- using 'adjustOption' and 'localOption'.+--+-- E. g., set upper bound of acceptable slow down to 10% as follows:+--+-- > import Test.Tasty (localOption)+-- > localOption (FailIfSlower 0.10) (bgroup [...])+--+newtype FailIfSlower = FailIfSlower Double+ deriving (Show, Read, Typeable)++instance IsOption FailIfSlower where+ defaultValue = FailIfSlower (1.0 / 0.0)+ parseValue = fmap FailIfSlower . parsePositivePercents+ optionName = pure "fail-if-slower"+ optionHelp = pure "Upper bound of acceptable slow down in percents. If a benchmark is unacceptably slower than baseline (see --baseline), it will be reported as failed."++-- | In addition to @--fail-if-faster@ command-line option,+-- one can adjust an upper bound of acceptable speed up+-- in comparison to baseline for+-- individual benchmarks and groups of benchmarks+-- using 'adjustOption' and 'localOption'.+--+-- E. g., set upper bound of acceptable speed up to 10% as follows:+--+-- > import Test.Tasty (localOption)+-- > localOption (FailIfFaster 0.10) (bgroup [...])+--+newtype FailIfFaster = FailIfFaster Double+ deriving (Show, Read, Typeable)++instance IsOption FailIfFaster where+ defaultValue = FailIfFaster (1.0 / 0.0)+ parseValue = fmap FailIfFaster . parsePositivePercents+ optionName = pure "fail-if-faster"+ optionHelp = pure "Upper bound of acceptable speed up in percents. If a benchmark is unacceptably faster than baseline (see --baseline), it will be reported as failed."++parsePositivePercents :: String -> Maybe Double+parsePositivePercents xs = do+ x <- safeRead xs+ guard (x > 0)+ pure (x / 100)+#endif++-- | Something that can be benchmarked, produced by 'nf', 'whnf', 'nfIO', 'whnfIO',+-- 'nfAppIO', 'whnfAppIO' below.+--+-- Drop-in replacement for @Criterion.@'Criterion.Benchmarkable' and+-- @Gauge.@'Gauge.Benchmarkable'.+--+newtype Benchmarkable = Benchmarkable+ { unBenchmarkable :: Word64 -> IO () -- ^ Run benchmark given number of times.+ } deriving (Typeable)++#ifdef MIN_VERSION_tasty++-- | 'defaultMain' forces 'setLocaleEncoding' to 'utf8', but users might+-- be running benchmarks outside of it (e. g., via 'defaultMainWithIngredients').+supportsUnicode :: Bool+#if MIN_VERSION_base(4,5,0)+supportsUnicode = take 3 (textEncodingName enc) == "UTF"+ where+ enc = unsafePerformIO getLocaleEncoding+#else+supportsUnicode = False+#endif+{-# NOINLINE supportsUnicode #-}++mu :: Char+mu = if supportsUnicode then 'μ' else 'u'++pm :: String+pm = if supportsUnicode then " ± " else " +-"++-- | Show picoseconds, fitting number in 3 characters.+showPicos3 :: Word64 -> String+showPicos3 i+ | t < 995 = printf "%3.0f ps" t+ | t < 995e1 = printf "%3.1f ns" (t / 1e3)+ | t < 995e3 = printf "%3.0f ns" (t / 1e3)+ | t < 995e4 = printf "%3.1f %cs" (t / 1e6) mu+ | t < 995e6 = printf "%3.0f %cs" (t / 1e6) mu+ | t < 995e7 = printf "%3.1f ms" (t / 1e9)+ | t < 995e9 = printf "%3.0f ms" (t / 1e9)+ | otherwise = printf "%4.2f s" (t / 1e12)+ where+ t = word64ToDouble i++-- | Show picoseconds, fitting number in 4 characters.+showPicos4 :: Word64 -> String+showPicos4 i+ | t < 995 = printf "%3.0f ps" t+ | t < 995e1 = printf "%4.2f ns" (t / 1e3)+ | t < 995e2 = printf "%4.1f ns" (t / 1e3)+ | t < 995e3 = printf "%3.0f ns" (t / 1e3)+ | t < 995e4 = printf "%4.2f %cs" (t / 1e6) mu+ | t < 995e5 = printf "%4.1f %cs" (t / 1e6) mu+ | t < 995e6 = printf "%3.0f %cs" (t / 1e6) mu+ | t < 995e7 = printf "%4.2f ms" (t / 1e9)+ | t < 995e8 = printf "%4.1f ms" (t / 1e9)+ | t < 995e9 = printf "%3.0f ms" (t / 1e9)+ | otherwise = printf "%4.3f s" (t / 1e12)+ where+ t = word64ToDouble i++showBytes :: Word64 -> String+showBytes i+ | t < 1000 = printf "%3.0f B " t+ | t < 10189 = printf "%3.1f KB" (t / 1024)+ | t < 1023488 = printf "%3.0f KB" (t / 1024)+ | t < 10433332 = printf "%3.1f MB" (t / 1048576)+ | t < 1048051712 = printf "%3.0f MB" (t / 1048576)+ | t < 10683731149 = printf "%3.1f GB" (t / 1073741824)+ | t < 1073204953088 = printf "%3.0f GB" (t / 1073741824)+ | t < 10940140696372 = printf "%3.1f TB" (t / 1099511627776)+ | t < 1098961871962112 = printf "%3.0f TB" (t / 1099511627776)+ | t < 11202704073084108 = printf "%3.1f PB" (t / 1125899906842624)+ | t < 1125336956889202624 = printf "%3.0f PB" (t / 1125899906842624)+ | t < 11471568970838126592 = printf "%3.1f EB" (t / 1152921504606846976)+ | otherwise = printf "%3.0f EB" (t / 1152921504606846976)+ where+ t = word64ToDouble i+#endif++data Measurement = Measurement+ { measTime :: !Word64 -- ^ time in picoseconds+ , measAllocs :: !Word64 -- ^ allocations in bytes+ , measCopied :: !Word64 -- ^ copied bytes+ , measMaxMem :: !Word64 -- ^ max memory in use+ } deriving (Show, Read)++data Estimate = Estimate+ { estMean :: !Measurement+ , estStdev :: !Word64 -- ^ stdev in picoseconds+ } deriving (Show, Read)++#ifdef MIN_VERSION_tasty++data WithLoHi a = WithLoHi+ !a -- payload+ !Double -- lower bound (e. g., 0.9 for -10% speedup)+ !Double -- upper bound (e. g., 1.2 for +20% slowdown)+ deriving (Show, Read)++prettyEstimate :: Estimate -> String+prettyEstimate (Estimate m stdev) =+ showPicos4 (measTime m)+ ++ (if stdev == 0 then " " else pm ++ showPicos3 (2 * stdev))++prettyEstimateWithGC :: Estimate -> String+prettyEstimateWithGC (Estimate m stdev) =+ showPicos4 (measTime m)+ ++ (if stdev == 0 then ", " else pm ++ showPicos3 (2 * stdev) ++ ", ")+ ++ showBytes (measAllocs m) ++ " allocated, "+ ++ showBytes (measCopied m) ++ " copied, "+ ++ showBytes (measMaxMem m) ++ " peak memory"++csvEstimate :: Estimate -> String+csvEstimate (Estimate m stdev) = show (measTime m) ++ "," ++ show (2 * stdev)++csvEstimateWithGC :: Estimate -> String+csvEstimateWithGC (Estimate m stdev) = show (measTime m) ++ "," ++ show (2 * stdev)+ ++ "," ++ show (measAllocs m) ++ "," ++ show (measCopied m) ++ "," ++ show (measMaxMem m)+#endif++predict+ :: Measurement -- ^ time for one run+ -> Measurement -- ^ time for two runs+ -> Estimate+predict (Measurement t1 a1 c1 m1) (Measurement t2 a2 c2 m2) = Estimate+ { estMean = Measurement t (fit a1 a2) (fit c1 c2) (max m1 m2)+ , estStdev = truncate (sqrt d :: Double)+ }+ where+ fit x1 x2 = x1 `quot` 5 + 2 * (x2 `quot` 5)+ t = fit t1 t2+ sqr x = x * x+ d = sqr (word64ToDouble t1 - word64ToDouble t)+ + sqr (word64ToDouble t2 - 2 * word64ToDouble t)++predictPerturbed :: Measurement -> Measurement -> Estimate+predictPerturbed t1 t2 = Estimate+ { estMean = estMean (predict t1 t2)+ , estStdev = max+ (estStdev (predict (lo t1) (hi t2)))+ (estStdev (predict (hi t1) (lo t2)))+ }+ where+ prec = max (fromInteger cpuTimePrecision) 1000000000 -- 1 ms+ hi meas = meas { measTime = measTime meas + prec }+ lo meas = meas { measTime = measTime meas - prec }++hasGCStats :: Bool+#if MIN_VERSION_base(4,10,0)+hasGCStats = unsafePerformIO getRTSStatsEnabled+#elif MIN_VERSION_base(4,6,0)+hasGCStats = unsafePerformIO getGCStatsEnabled+#else+hasGCStats = False+#endif++getAllocsAndCopied :: IO (Word64, Word64, Word64)+getAllocsAndCopied = do+ if not hasGCStats then pure (0, 0, 0) else+#if MIN_VERSION_base(4,10,0)+ (\s -> (allocated_bytes s, copied_bytes s, max_mem_in_use_bytes s)) <$> getRTSStats+#elif MIN_VERSION_base(4,6,0)+ (\s -> (int64ToWord64 $ bytesAllocated s, int64ToWord64 $ bytesCopied s, int64ToWord64 $ peakMegabytesAllocated s * 1024 * 1024)) <$> getGCStats+#else+ pure (0, 0, 0)+#endif++measure :: Word64 -> Benchmarkable -> IO Measurement+measure n (Benchmarkable act) = do+ performGC+ startTime <- fromInteger <$> getCPUTime+ (startAllocs, startCopied, startMaxMemInUse) <- getAllocsAndCopied+ act n+ endTime <- fromInteger <$> getCPUTime+ (endAllocs, endCopied, endMaxMemInUse) <- getAllocsAndCopied+ let meas = Measurement+ { measTime = endTime - startTime+ , measAllocs = endAllocs - startAllocs+ , measCopied = endCopied - startCopied+ , measMaxMem = max endMaxMemInUse startMaxMemInUse+ }+#ifdef DEBUG+ pure $ trace (show n ++ (if n == 1 then " iteration gives " else " iterations give ") ++ show meas) meas+#else+ pure meas+#endif++measureUntil :: Bool -> Timeout -> RelStDev -> Benchmarkable -> IO Estimate+measureUntil _ _ (RelStDev targetRelStDev) b+ | isInfinite targetRelStDev, targetRelStDev > 0 = do+ t1 <- measure 1 b+ pure $ Estimate { estMean = t1, estStdev = 0 }+measureUntil warnIfNoTimeout timeout (RelStDev targetRelStDev) b = do+ t1 <- measure 1 b+ go 1 t1 0+ where+ go :: Word64 -> Measurement -> Word64 -> IO Estimate+ go n t1 sumOfTs = do+ t2 <- measure (2 * n) b++ let Estimate (Measurement meanN allocN copiedN maxMemN) stdevN = predictPerturbed t1 t2+ isTimeoutSoon = case timeout of+ NoTimeout -> False+ -- multiplying by 12/10 helps to avoid accidental timeouts+ Timeout micros _ -> (sumOfTs' + 3 * measTime t2) `quot` (1000000 * 10 `quot` 12) >= fromInteger micros+ isStDevInTargetRange = stdevN < truncate (max 0 targetRelStDev * word64ToDouble meanN)+ scale = (`quot` n)+ sumOfTs' = sumOfTs + measTime t1++ case timeout of+ NoTimeout | warnIfNoTimeout, sumOfTs' + measTime t2 > 100 * 1000000000000+ -> hPutStrLn stderr "This benchmark takes more than 100 seconds. Consider setting --timeout, if this is unexpected (or to silence this warning)."+ _ -> pure ()++ if isStDevInTargetRange || isTimeoutSoon+ then pure $ Estimate+ { estMean = Measurement (scale meanN) (scale allocN) (scale copiedN) maxMemN+ , estStdev = scale stdevN }+ else go (2 * n) t2 sumOfTs'++-- | An internal routine to measure execution time in seconds+-- for a given timeout (put 'NoTimeout', or 'mkTimeout' 100000000 for 100 seconds)+-- and a target relative standard deviation+-- (put 'RelStDev' 0.05 for 5% or 'RelStDev' (1/0) to run only one iteration).+--+-- 'Timeout' takes soft priority over 'RelStDev': this function prefers+-- to finish in time even if at cost of precision. However, timeout is guidance+-- not guarantee: 'measureCpuTime' can take longer, if there is not enough time+-- to run at least thrice or an iteration takes unusually long.+measureCpuTime :: Timeout -> RelStDev -> Benchmarkable -> IO Double+measureCpuTime+ = ((fmap ((/ 1e12) . word64ToDouble . measTime . estMean) .) .)+ . measureUntil False++#ifdef MIN_VERSION_tasty++instance IsTest Benchmarkable where+ testOptions = pure+ [ Option (Proxy :: Proxy RelStDev)+ -- FailIfSlower and FailIfFaster must be options of a test provider rather+ -- than options of an ingredient to allow setting them on per-test level.+ , Option (Proxy :: Proxy FailIfSlower)+ , Option (Proxy :: Proxy FailIfFaster)+ ]+ run opts b = const $ case getNumThreads (lookupOption opts) of+ 1 -> do+ est <- measureUntil True (lookupOption opts) (lookupOption opts) b+ let FailIfSlower ifSlower = lookupOption opts+ FailIfFaster ifFaster = lookupOption opts+ pure $ testPassed $ show (WithLoHi est (1 - ifFaster) (1 + ifSlower))+ _ -> pure $ testFailed "Benchmarks must not be run concurrently. Please pass -j1 and/or avoid +RTS -N."++-- | Attach a name to 'Benchmarkable'.+--+-- This is actually a synonym of 'Test.Tasty.Providers.singleTest' to+-- provide an interface compatible with @Criterion.@'Criterion.bench'+-- and @Gauge.@'Gauge.bench'.+--+bench :: String -> Benchmarkable -> Benchmark+bench = singleTest++-- | Attach a name to a group of 'Benchmark'.+--+-- This is actually a synonym of 'Test.Tasty.testGroup' to provide an+-- interface compatible with @Criterion.@'Criterion.bgroup' and+-- @Gauge@.'Gauge.bgroup'.+--+bgroup :: String -> [Benchmark] -> Benchmark+bgroup = testGroup++#if MIN_VERSION_tasty(1,2,0)+-- | Compare benchmarks, reporting relative speed up or slow down.+--+-- This function is a vague reminiscence of @bcompare@, which existed in pre-1.0+-- versions of @criterion@, but their types are incompatible. Under the hood+-- 'bcompare' is a thin wrapper over 'after' and requires @tasty-1.2@.+--+bcompare+ :: String+ -- ^ @tasty@ pattern, which must unambiguously+ -- match a unique baseline benchmark. Locating a benchmark in a global environment+ -- may be tricky, please refer to+ -- [@tasty@ documentation](https://github.com/UnkindPartition/tasty#patterns) for details.+ -> Benchmark+ -- ^ Benchmark (or a group of benchmarks)+ -- to be compared against the baseline benchmark by dividing measured mean times.+ -- The result is reported by 'consoleBenchReporter', e. g., 0.50x or 1.25x.+ -> Benchmark+bcompare = bcompareWithin (-1/0) (1/0)++-- | Same as 'bcompare', but takes expected lower and upper bounds of+-- comparison. If the result is not within provided bounds, benchmark is failed.+-- This allows to create portable performance tests: instead of comparing+-- to an absolute timeout or to previous runs, you can state that one implementation+-- of an algorithm must be faster than another.+--+-- E. g., 'bcompareWithin' 2.0 3.0 passes only if a benchmark is at least 2x+-- and at most 3x slower than a baseline.+--+bcompareWithin+ :: Double -- ^ Lower bound of relative speed up.+ -> Double -- ^ Upper bound of relative spped up.+ -> String -- ^ @tasty@ pattern to locate a baseline benchmark.+ -> Benchmark -- ^ Benchmark to compare against baseline.+ -> Benchmark+bcompareWithin lo hi s = case parseExpr s of+ Nothing -> error $ "Could not parse bcompare pattern " ++ s+ Just e -> after_ AllSucceed (And (StringLit (bcomparePrefix ++ show (lo, hi))) e)++bcomparePrefix :: String+bcomparePrefix = "tasty-bench"+#endif++-- | Benchmarks are actually just a regular 'Test.Tasty.TestTree' in disguise.+--+-- This is a drop-in replacement for @Criterion.@'Criterion.Benchmark'+-- and @Gauge.@'Gauge.Benchmark'.+--+type Benchmark = TestTree++-- | Run benchmarks and report results, providing an interface+-- compatible with @Criterion.@'Criterion.defaultMain' and+-- @Gauge.@'Gauge.defaultMain'.+--+defaultMain :: [Benchmark] -> IO ()+defaultMain bs = do+#if MIN_VERSION_base(4,5,0)+ setLocaleEncoding utf8+#endif+ Test.Tasty.defaultMainWithIngredients benchIngredients $ testGroup "All" bs++-- | List of default benchmark ingredients. This is what 'defaultMain' runs.+--+benchIngredients :: [Ingredient]+benchIngredients = [listingTests, composeReporters consoleBenchReporter (composeReporters csvReporter svgReporter)]++#endif++funcToBench :: (b -> c) -> (a -> b) -> a -> Benchmarkable+funcToBench frc = (Benchmarkable .) . go+ where+ go f x n+ | n == 0 = pure ()+ | otherwise = do+ _ <- evaluate (frc (f x))+ go f x (n - 1)+{-# INLINE funcToBench #-}++-- | 'nf' @f@ @x@ measures time to compute+-- a normal form (by means of 'force') of an application of @f@ to @x@.+-- This does not include time to evaluate @f@ or @x@ themselves.+-- Ideally @x@ should be a primitive data type like 'Data.Int.Int'.+--+-- The same thunk of @x@ is shared by multiple calls of @f@. We cannot evaluate+-- @x@ beforehand: there is no 'NFData' @a@ constraint, and potentially @x@ may+-- be an infinite structure. Thus @x@ will be evaluated in course of the first+-- application of @f@. This noisy measurement is to be discarded soon,+-- but if @x@ is not a primitive data type, consider forcing its evaluation+-- separately, e. g., via 'env' or 'withResource'.+--+-- Here is a textbook anti-pattern: 'nf' 'sum' @[1..1000000]@.+-- Since an input list is shared by multiple invocations of 'sum',+-- it will be allocated in memory in full, putting immense pressure+-- on garbage collector. Also no list fusion will happen.+-- A better approach is 'nf' (@\\n@ @->@ 'sum' @[1..n]@) @1000000@.+--+-- If you are measuring an inlinable function,+-- it is prudent to ensure that its invocation is fully saturated,+-- otherwise inlining will not happen. That's why one can often+-- see 'nf' (@\\n@ @->@ @f@ @n@) @x@ instead of 'nf' @f@ @x@.+-- Same applies to rewrite rules.+--+-- While @tasty-bench@ is capable to perform micro- and even nanobenchmarks,+-- such measurements are noisy and involve an overhead. Results are more reliable+-- when @f@ @x@ takes at least several milliseconds.+--+-- Note that forcing a normal form requires an additional+-- traverse of the structure. In certain scenarios (imagine benchmarking 'tail'),+-- especially when 'NFData' instance is badly written,+-- this traversal may take non-negligible time and affect results.+--+-- Drop-in replacement for @Criterion.@'Criterion.nf' and+-- @Gauge.@'Gauge.nf'.+--+nf :: NFData b => (a -> b) -> a -> Benchmarkable+nf = funcToBench force+{-# INLINE nf #-}++-- | 'whnf' @f@ @x@ measures time to compute+-- a weak head normal form of an application of @f@ to @x@.+-- This does not include time to evaluate @f@ or @x@ themselves.+-- Ideally @x@ should be a primitive data type like 'Data.Int.Int'.+--+-- The same thunk of @x@ is shared by multiple calls of @f@. We cannot evaluate+-- @x@ beforehand: there is no 'NFData' @a@ constraint, and potentially @x@ may+-- be an infinite structure. Thus @x@ will be evaluated in course of the first+-- application of @f@. This noisy measurement is to be discarded soon,+-- but if @x@ is not a primitive data type, consider forcing its evaluation+-- separately, e. g., via 'env' or 'withResource'.+--+-- Computing only a weak head normal form is+-- rarely what intuitively is meant by "evaluation".+-- Beware that many educational materials contain examples with 'whnf':+-- this is a wrong default.+-- Unless you understand precisely, what is measured,+-- it is recommended to use 'nf' instead.+--+-- Here is a textbook anti-pattern: 'whnf' ('Data.List.replicate' @1000000@) @1@.+-- This will succeed in a matter of nanoseconds, because weak head+-- normal form forces only the first element of the list.+--+-- Drop-in replacement for @Criterion.@'Criterion.whnf' and @Gauge.@'Gauge.whnf'.+--+whnf :: (a -> b) -> a -> Benchmarkable+whnf = funcToBench id+{-# INLINE whnf #-}++ioToBench :: (b -> c) -> IO b -> Benchmarkable+ioToBench frc act = Benchmarkable go+ where+ go n+ | n == 0 = pure ()+ | otherwise = do+ val <- act+ _ <- evaluate (frc val)+ go (n - 1)+{-# INLINE ioToBench #-}++-- | 'nfIO' @x@ measures time to evaluate side-effects of @x@+-- and compute its normal form (by means of 'force').+--+-- Pure subexpression of an effectful computation @x@+-- may be evaluated only once and get cached.+-- To avoid surprising results it is usually preferable+-- to use 'nfAppIO' instead.+--+-- Note that forcing a normal form requires an additional+-- traverse of the structure. In certain scenarios,+-- especially when 'NFData' instance is badly written,+-- this traversal may take non-negligible time and affect results.+--+-- A typical use case is 'nfIO' ('readFile' @"foo.txt"@).+-- However, if your goal is not to benchmark I\/O per se,+-- but just read input data from a file, it is cleaner to+-- use 'env' or 'withResource'.+--+-- Drop-in replacement for @Criterion.@'Criterion.nfIO' and @Gauge.@'Gauge.nfIO'.+--+nfIO :: NFData a => IO a -> Benchmarkable+nfIO = ioToBench force+{-# INLINE nfIO #-}++-- | 'whnfIO' @x@ measures time to evaluate side-effects of @x@+-- and compute its weak head normal form.+--+-- Pure subexpression of an effectful computation @x@+-- may be evaluated only once and get cached.+-- To avoid surprising results it is usually preferable+-- to use 'whnfAppIO' instead.+--+-- Computing only a weak head normal form is+-- rarely what intuitively is meant by "evaluation".+-- Unless you understand precisely, what is measured,+-- it is recommended to use 'nfIO' instead.+--+-- Lazy I\/O is treacherous.+-- If your goal is not to benchmark I\/O per se,+-- but just read input data from a file, it is cleaner to+-- use 'env' or 'withResource'.+--+-- Drop-in replacement for @Criterion.@'Criterion.whnfIO' and @Gauge.@'Gauge.whnfIO'.+--+whnfIO :: IO a -> Benchmarkable+whnfIO = ioToBench id+{-# INLINE whnfIO #-}++ioFuncToBench :: (b -> c) -> (a -> IO b) -> a -> Benchmarkable+ioFuncToBench frc = (Benchmarkable .) . go+ where+ go f x n+ | n == 0 = pure ()+ | otherwise = do+ val <- f x+ _ <- evaluate (frc val)+ go f x (n - 1)+{-# INLINE ioFuncToBench #-}++-- | 'nfAppIO' @f@ @x@ measures time to evaluate side-effects of+-- an application of @f@ to @x@.+-- and compute its normal form (by means of 'force').+-- This does not include time to evaluate @f@ or @x@ themselves.+-- Ideally @x@ should be a primitive data type like 'Data.Int.Int'.+--+-- The same thunk of @x@ is shared by multiple calls of @f@. We cannot evaluate+-- @x@ beforehand: there is no 'NFData' @a@ constraint, and potentially @x@ may+-- be an infinite structure. Thus @x@ will be evaluated in course of the first+-- application of @f@. This noisy measurement is to be discarded soon,+-- but if @x@ is not a primitive data type, consider forcing its evaluation+-- separately, e. g., via 'env' or 'withResource'.+--+-- Note that forcing a normal form requires an additional+-- traverse of the structure. In certain scenarios,+-- especially when 'NFData' instance is badly written,+-- this traversal may take non-negligible time and affect results.+--+-- A typical use case is 'nfAppIO' 'readFile' @"foo.txt"@.+-- However, if your goal is not to benchmark I\/O per se,+-- but just read input data from a file, it is cleaner to+-- use 'env' or 'withResource'.+--+-- Drop-in replacement for @Criterion.@'Criterion.nfAppIO' and @Gauge.@'Gauge.nfAppIO'.+--+nfAppIO :: NFData b => (a -> IO b) -> a -> Benchmarkable+nfAppIO = ioFuncToBench force+{-# INLINE nfAppIO #-}++-- | 'whnfAppIO' @f@ @x@ measures time to evaluate side-effects of+-- an application of @f@ to @x@.+-- and compute its weak head normal form.+-- This does not include time to evaluate @f@ or @x@ themselves.+-- Ideally @x@ should be a primitive data type like 'Data.Int.Int'.+--+-- The same thunk of @x@ is shared by multiple calls of @f@. We cannot evaluate+-- @x@ beforehand: there is no 'NFData' @a@ constraint, and potentially @x@ may+-- be an infinite structure. Thus @x@ will be evaluated in course of the first+-- application of @f@. This noisy measurement is to be discarded soon,+-- but if @x@ is not a primitive data type, consider forcing its evaluation+-- separately, e. g., via 'env' or 'withResource'.+--+-- Computing only a weak head normal form is+-- rarely what intuitively is meant by "evaluation".+-- Unless you understand precisely, what is measured,+-- it is recommended to use 'nfAppIO' instead.+--+-- Lazy I\/O is treacherous.+-- If your goal is not to benchmark I\/O per se,+-- but just read input data from a file, it is cleaner to+-- use 'env' or 'withResource'.+--+-- Drop-in replacement for @Criterion.@'Criterion.whnfAppIO' and @Gauge.@'Gauge.whnfAppIO'.+--+whnfAppIO :: (a -> IO b) -> a -> Benchmarkable+whnfAppIO = ioFuncToBench id+{-# INLINE whnfAppIO #-}++#ifdef MIN_VERSION_tasty++-- | Run benchmarks in the given environment, usually reading large input data from file.+--+-- One might wonder why 'env' is needed,+-- when we can simply read all input data+-- before calling 'defaultMain'. The reason is that large data+-- dangling in the heap causes longer garbage collection+-- and slows down all benchmarks, even those which do not use it at all.+--+-- It is instrumental not only for proper 'IO' actions,+-- but also for a large statically-known data as well. Instead of a top-level+-- definition, which once evaluated will slow down garbage collection+-- during all subsequent benchmarks,+--+-- > largeData :: String+-- > largeData = replicate 1000000 'a'+-- >+-- > main :: IO ()+-- > main = defaultMain+-- > [ bench "large" $ nf length largeData, ... ]+--+-- use+--+-- > import Control.DeepSeq (force)+-- > import Control.Exception (evaluate)+-- >+-- > main :: IO ()+-- > main = defaultMain+-- > [ env (evaluate (force (replicate 1000000 'a'))) $ \largeData ->+-- > bench "large" $ nf length largeData, ... ]+--+-- @Test.Tasty.Bench.@'env' is provided only for the sake of+-- compatibility with @Criterion.@'Criterion.env' and+-- @Gauge.@'Gauge.env', and involves 'unsafePerformIO'. Consider using+-- 'withResource' instead.+--+-- 'defaultMain' requires that the hierarchy of benchmarks and their names is+-- independent of underlying 'IO' actions. While executing 'IO' inside 'bench'+-- via 'nfIO' is fine, and reading test data from files via 'env' is also fine,+-- using 'env' to choose benchmarks or their names depending on 'IO' side effects+-- will throw a rather cryptic error message:+--+-- > Unhandled resource. Probably a bug in the runner you're using.+--+env :: NFData env => IO env -> (env -> Benchmark) -> Benchmark+env res = envWithCleanup res (const $ pure ())++-- | Similar to 'env', but includes an additional argument+-- to clean up created environment.+--+-- Provided only for the sake of compatibility with+-- @Criterion.@'Criterion.envWithCleanup' and+-- @Gauge.@'Gauge.envWithCleanup', and involves+-- 'unsafePerformIO'. Consider using 'withResource' instead.+--+envWithCleanup :: NFData env => IO env -> (env -> IO a) -> (env -> Benchmark) -> Benchmark+envWithCleanup res fin f = withResource+ (res >>= evaluate . force)+ (void . fin)+ (f . unsafePerformIO)++-- | A path to write results in CSV format, populated by @--csv@.+--+-- This is an option of 'csvReporter' and can be set only globally.+-- Modifying it via 'adjustOption' or 'localOption' does not have any effect.+-- One can however pass it to 'tryIngredients' 'benchIngredients'. For example,+-- here is how to set a default CSV location:+--+-- @+-- import Data.Maybe+-- import System.Exit+-- import Test.Tasty.Bench+-- import Test.Tasty.Ingredients+-- import Test.Tasty.Options+-- import Test.Tasty.Runners+--+-- main :: IO ()+-- main = do+-- let benchmarks = bgroup \"All\" ...+-- opts <- parseOptions benchIngredients benchmarks+-- let opts' = changeOption (Just . fromMaybe (CsvPath "foo.csv")) opts+-- case tryIngredients benchIngredients opts' benchmarks of+-- Nothing -> exitFailure+-- Just mb -> mb >>= \\b -> if b then exitSuccess else exitFailure+-- @+--+newtype CsvPath = CsvPath FilePath+ deriving (Typeable)++instance IsOption (Maybe CsvPath) where+ defaultValue = Nothing+ parseValue = Just . Just . CsvPath+ optionName = pure "csv"+ optionHelp = pure "File to write results in CSV format"++-- | Run benchmarks and save results in CSV format.+-- It activates when @--csv@ @FILE@ command line option is specified.+--+csvReporter :: Ingredient+csvReporter = TestReporter [Option (Proxy :: Proxy (Maybe CsvPath))] $+ \opts tree -> do+ CsvPath path <- lookupOption opts+ let names = testsNames opts tree+ namesMap = IM.fromDistinctAscList $ zip [0..] names+ pure $ \smap -> do+ case findNonUniqueElement names of+ Nothing -> pure ()+ Just name -> do -- 'die' is not available before base-4.8+ hPutStrLn stderr $ "CSV report cannot proceed, because name '" ++ name ++ "' corresponds to two or more benchmarks. Please disambiguate them."+ exitFailure+ let augmented = IM.intersectionWith (,) namesMap smap+ bracket+ (do+ h <- openFile path WriteMode+ hSetBuffering h LineBuffering+ hPutStrLn h $ "Name,Mean (ps),2*Stdev (ps)" +++ (if hasGCStats then ",Allocated,Copied,Peak Memory" else "")+ pure h+ )+ hClose+ (`csvOutput` augmented)+ pure $ const $ isSuccessful smap++findNonUniqueElement :: Ord a => [a] -> Maybe a+findNonUniqueElement = go S.empty+ where+ go _ [] = Nothing+ go acc (x : xs)+ | x `S.member` acc = Just x+ | otherwise = go (S.insert x acc) xs++csvOutput :: Handle -> IntMap (TestName, TVar Status) -> IO ()+csvOutput h = traverse_ $ \(name, tv) -> do+ let csv = if hasGCStats then csvEstimateWithGC else csvEstimate+ r <- atomically $ readTVar tv >>= \s -> case s of Done r -> pure r; _ -> retry+ case safeRead (resultDescription r) of+ Nothing -> pure ()+ Just (WithLoHi est _ _) -> do+ msg <- formatMessage $ csv est+ hPutStrLn h (encodeCsv name ++ ',' : msg)++encodeCsv :: String -> String+encodeCsv xs+ | any (`elem` xs) ",\"\n\r"+ = '"' : go xs -- opening quote+ | otherwise = xs+ where+ go [] = '"' : [] -- closing quote+ go ('"' : ys) = '"' : '"' : go ys+ go (y : ys) = y : go ys++-- | A path to plot results in SVG format, populated by @--svg@.+--+-- This is an option of 'svgReporter' and can be set only globally.+-- Modifying it via 'adjustOption' or 'localOption' does not have any effect.+-- One can however pass it to 'tryIngredients' 'benchIngredients'.+--+newtype SvgPath = SvgPath FilePath+ deriving (Typeable)++instance IsOption (Maybe SvgPath) where+ defaultValue = Nothing+ parseValue = Just . Just . SvgPath+ optionName = pure "svg"+ optionHelp = pure "File to plot results in SVG format"++-- | Run benchmarks and plot results in SVG format.+-- It activates when @--svg@ @FILE@ command line option is specified.+--+svgReporter :: Ingredient+svgReporter = TestReporter [Option (Proxy :: Proxy (Maybe SvgPath))] $+ \opts tree -> do+ SvgPath path <- lookupOption opts+ let names = testsNames opts tree+ namesMap = IM.fromDistinctAscList $ zip [0..] names+ pure $ \smap -> do+ ref <- newIORef []+ svgCollect ref (IM.intersectionWith (,) namesMap smap)+ res <- readIORef ref+ writeFile path (svgRender (reverse res))+ pure $ const $ isSuccessful smap++isSuccessful :: StatusMap -> IO Bool+isSuccessful = go . IM.elems+ where+ go [] = pure True+ go (tv : tvs) = do+ b <- atomically $ readTVar tv >>= \s -> case s of Done r -> pure (resultSuccessful r); _ -> retry+ if b then go tvs else pure False++svgCollect :: IORef [(TestName, Estimate)] -> IntMap (TestName, TVar Status) -> IO ()+svgCollect ref = traverse_ $ \(name, tv) -> do+ r <- atomically $ readTVar tv >>= \s -> case s of Done r -> pure r; _ -> retry+ case safeRead (resultDescription r) of+ Nothing -> pure ()+ Just (WithLoHi est _ _) -> modifyIORef ref ((name, est) :)++svgRender :: [(TestName, Estimate)] -> String+svgRender [] = ""+svgRender pairs = header ++ concat (zipWith+ (\i (name, est) -> svgRenderItem i l xMax (dropAllPrefix name) est)+ [0..]+ pairs) ++ footer+ where+ dropAllPrefix+ | all (("All." `isPrefixOf`) . fst) pairs = drop 4+ | otherwise = id++ l = genericLength pairs+ findMaxX (Estimate m stdev) = measTime m + 2 * stdev+ xMax = word64ToDouble $ maximum $ minBound : map (findMaxX . snd) pairs+ header = printf "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"%i\" width=\"%f\" font-size=\"%i\" font-family=\"sans-serif\" stroke-width=\"2\">\n<g transform=\"translate(%f 0)\">\n" (svgItemOffset l - 15) svgCanvasWidth svgFontSize svgCanvasMargin+ footer = "</g>\n</svg>\n"++svgCanvasWidth :: Double+svgCanvasWidth = 960++svgCanvasMargin :: Double+svgCanvasMargin = 10++svgItemOffset :: Word64 -> Word64+svgItemOffset i = 22 + 55 * i++svgFontSize :: Word64+svgFontSize = 16++svgRenderItem :: Word64 -> Word64 -> Double -> TestName -> Estimate -> String+svgRenderItem i iMax xMax name est@(Estimate m stdev) =+ (if genericLength shortTextContent * glyphWidth < boxWidth then longText else shortText) ++ box+ where+ y = svgItemOffset i+ y' = y + (svgFontSize * 3) `quot` 8+ y1 = y' + whiskerMargin+ y2 = y' + boxHeight `quot` 2+ y3 = y' + boxHeight - whiskerMargin+ x1 = boxWidth - whiskerWidth+ x2 = boxWidth + whiskerWidth+ deg = (i * 360) `quot` iMax+ glyphWidth = word64ToDouble svgFontSize / 2++ scale w = word64ToDouble w * (svgCanvasWidth - 2 * svgCanvasMargin) / xMax+ boxWidth = scale (measTime m)+ whiskerWidth = scale (2 * stdev)+ boxHeight = 22+ whiskerMargin = 5++ box = printf boxTemplate+ (prettyEstimate est)+ y' boxHeight boxWidth deg deg+ deg+ x1 x2 y2 y2+ x1 x1 y1 y3+ x2 x2 y1 y3+ boxTemplate+ = "<g>\n<title>%s</title>\n"+ ++ "<rect y=\"%i\" rx=\"5\" height=\"%i\" width=\"%f\" fill=\"hsl(%i, 100%%, 80%%)\" stroke=\"hsl(%i, 100%%, 55%%)\" />\n"+ ++ "<g stroke=\"hsl(%i, 100%%, 40%%)\">"+ ++ "<line x1=\"%f\" x2=\"%f\" y1=\"%i\" y2=\"%i\" />\n"+ ++ "<line x1=\"%f\" x2=\"%f\" y1=\"%i\" y2=\"%i\" />\n"+ ++ "<line x1=\"%f\" x2=\"%f\" y1=\"%i\" y2=\"%i\" />\n"+ ++ "</g>\n</g>\n"++ longText = printf longTextTemplate+ deg+ y (encodeSvg name)+ y boxWidth (showPicos4 (measTime m))+ longTextTemplate+ = "<g fill=\"hsl(%i, 100%%, 40%%)\">\n"+ ++ "<text y=\"%i\">%s</text>\n"+ ++ "<text y=\"%i\" x=\"%f\" text-anchor=\"end\">%s</text>\n"+ ++ "</g>\n"++ shortTextContent = encodeSvg name ++ " " ++ showPicos4 (measTime m)+ shortText = printf shortTextTemplate deg y shortTextContent+ shortTextTemplate = "<text fill=\"hsl(%i, 100%%, 40%%)\" y=\"%i\">%s</text>\n"++encodeSvg :: String -> String+encodeSvg [] = []+encodeSvg ('<' : xs) = '&' : 'l' : 't' : ';' : encodeSvg xs+encodeSvg ('&' : xs) = '&' : 'a' : 'm' : 'p' : ';' : encodeSvg xs+encodeSvg (x : xs) = x : encodeSvg xs++-- | A path to read baseline results in CSV format, populated by @--baseline@.+--+-- This is an option of 'csvReporter' and can be set only globally.+-- Modifying it via 'adjustOption' or 'localOption' does not have any effect.+-- One can however pass it to 'tryIngredients' 'benchIngredients'.+--+newtype BaselinePath = BaselinePath FilePath+ deriving (Typeable)++instance IsOption (Maybe BaselinePath) where+ defaultValue = Nothing+ parseValue = Just . Just . BaselinePath+ optionName = pure "baseline"+ optionHelp = pure "File with baseline results in CSV format to compare against"++-- | Run benchmarks and report results+-- in a manner similar to 'consoleTestReporter'.+--+-- If @--baseline@ @FILE@ command line option is specified,+-- compare results against an earlier run and mark+-- too slow / too fast benchmarks as failed in accordance to+-- bounds specified by @--fail-if-slower@ @PERCENT@ and @--fail-if-faster@ @PERCENT@.+--+consoleBenchReporter :: Ingredient+consoleBenchReporter = modifyConsoleReporter [Option (Proxy :: Proxy (Maybe BaselinePath))] $ \opts -> do+ baseline <- case lookupOption opts of+ Nothing -> pure S.empty+ Just (BaselinePath path) -> S.fromList . joinQuotedFields . lines <$> (readFile path >>= evaluate . force)+ let pretty = if hasGCStats then prettyEstimateWithGC else prettyEstimate+ pure $ \name mDepR r -> case safeRead (resultDescription r) of+ Nothing -> r+ Just (WithLoHi est lowerBound upperBound) ->+ (if isAcceptable then id else forceFail)+ r { resultDescription = pretty est ++ bcompareMsg ++ formatSlowDown slowDown }+ where+ isAcceptable = isAcceptableVsBaseline && isAcceptableVsBcompare+ slowDown = compareVsBaseline baseline name est+ isAcceptableVsBaseline = slowDown >= lowerBound && slowDown <= upperBound+ (isAcceptableVsBcompare, bcompareMsg) = case mDepR of+ Nothing -> (True, "")+ Just (WithLoHi depR depLowerBound depUpperBound) -> case safeRead (resultDescription depR) of+ Nothing -> (True, "")+ Just (WithLoHi depEst _ _) -> let ratio = estTime est / estTime depEst in+ ( ratio >= depLowerBound && ratio <= depUpperBound+ , printf ", %.2fx" ratio+ )++-- | A well-formed CSV entry contains an even number of quotes: 0, 2 or more.+joinQuotedFields :: [String] -> [String]+joinQuotedFields [] = []+joinQuotedFields (x : xs)+ | areQuotesBalanced x = x : joinQuotedFields xs+ | otherwise = case span areQuotesBalanced xs of+ (_, []) -> [] -- malformed CSV+ (ys, z : zs) -> unlines (x : ys ++ [z]) : joinQuotedFields zs+ where+ areQuotesBalanced = even . length . filter (== '"')++estTime :: Estimate -> Double+estTime = word64ToDouble . measTime . estMean++compareVsBaseline :: S.Set String -> TestName -> Estimate -> Double+compareVsBaseline baseline name (Estimate m stdev) = case mOld of+ Nothing -> 1+ Just (oldTime, oldDoubleSigma)+ -- time and oldTime must be signed integers to use 'abs'+ | abs (time - oldTime) < max (2 * word64ToInt64 stdev) oldDoubleSigma -> 1+ | otherwise -> int64ToDouble time / int64ToDouble oldTime+ where+ time = word64ToInt64 $ measTime m++ mOld :: Maybe (Int64, Int64)+ mOld = do+ let prefix = encodeCsv name ++ ","+ (line, furtherLines) <- S.minView $ snd $ S.split prefix baseline++ case S.minView furtherLines of+ Nothing -> pure ()+ Just (nextLine, _) -> case stripPrefix prefix nextLine of+ Nothing -> pure ()+ -- If there are several lines matching prefix, skip them all.+ -- Should not normally happen, 'csvReporter' prohibits repeating test names.+ Just{} -> Nothing++ (timeCell, ',' : rest) <- span (/= ',') <$> stripPrefix prefix line+ let doubleSigmaCell = takeWhile (/= ',') rest+ (,) <$> safeRead timeCell <*> safeRead doubleSigmaCell++formatSlowDown :: Double -> String+formatSlowDown n = case m `compare` 0 of+ LT -> printf ", %2i%% faster than baseline" (-m)+ EQ -> ""+ GT -> printf ", %2i%% slower than baseline" m+ where+ m :: Int64+ m = truncate ((n - 1) * 100)++forceFail :: Result -> Result+forceFail r = r { resultOutcome = Failure TestFailed, resultShortDescription = "FAIL" }++data Unique a = None | Unique !a | NotUnique+ deriving (Functor)++appendUnique :: Unique a -> Unique a -> Unique a+appendUnique None a = a+appendUnique a None = a+appendUnique _ _ = NotUnique++#if MIN_VERSION_base(4,9,0)+instance Semigroup (Unique a) where+ (<>) = appendUnique+#endif++instance Monoid (Unique a) where+ mempty = None+#if MIN_VERSION_base(4,9,0)+ mappend = (<>)+#else+ mappend = appendUnique+#endif++modifyConsoleReporter+ :: [OptionDescription]+ -> (OptionSet -> IO (TestName -> Maybe (WithLoHi Result) -> Result -> Result))+ -> Ingredient+modifyConsoleReporter desc' iof = TestReporter (desc ++ desc') $ \opts tree ->+ let nameSeqs = IM.fromDistinctAscList $ zip [0..] $ testNameSeqs opts tree+ namesAndDeps = IM.fromDistinctAscList $ zip [0..] $ map (second isSingle)+ $ testNamesAndDeps nameSeqs opts tree+ modifySMap = (iof opts >>=) . flip postprocessResult+ . IM.intersectionWith (\(a, b) c -> (a, b, c)) namesAndDeps+ in (modifySMap >=>) <$> cb opts tree+ where+ (desc, cb) = case consoleTestReporter of+ TestReporter d c -> (d, c)+ _ -> error "modifyConsoleReporter: consoleTestReporter must be TestReporter"++ isSingle (Unique a) = Just a+ isSingle _ = Nothing++testNameSeqs :: OptionSet -> TestTree -> [Seq TestName]+testNameSeqs = foldTestTree trivialFold+ { foldSingle = const $ const . (:[]) . Seq.singleton+#if MIN_VERSION_tasty(1,4,0)+ , foldGroup = const $ map . (<|)+#else+ , foldGroup = map . (<|)+#endif+ }++testNamesAndDeps :: IntMap (Seq TestName) -> OptionSet -> TestTree -> [(TestName, Unique (WithLoHi IM.Key))]+testNamesAndDeps im = foldTestTree trivialFold+ { foldSingle = const $ const . (: []) . (, mempty)+#if MIN_VERSION_tasty(1,4,0)+ , foldGroup = const $ map . first . (++) . (++ ".")+ , foldAfter = const foldDeps+#else+ , foldGroup = map . first . (++) . (++ ".")+#if MIN_VERSION_tasty(1,2,0)+ , foldAfter = foldDeps+#endif+#endif+ }+#if MIN_VERSION_tasty(1,2,0)+ where+ foldDeps :: DependencyType -> Expr -> [(a, Unique (WithLoHi IM.Key))] -> [(a, Unique (WithLoHi IM.Key))]+ foldDeps AllSucceed (And (StringLit xs) p)+ | bcomparePrefix `isPrefixOf` xs+ , Just (lo :: Double, hi :: Double) <- safeRead $ drop (length bcomparePrefix) xs+ = map $ second $ mappend $ (\x -> WithLoHi x lo hi) <$> findMatchingKeys im p+ foldDeps _ _ = id++findMatchingKeys :: IntMap (Seq TestName) -> Expr -> Unique IM.Key+findMatchingKeys im pattern =+ foldMap (\(k, v) -> if withFields v pat == Right True then Unique k else mempty) $ IM.assocs im+ where+ pat = eval pattern >>= asB+#endif++postprocessResult+ :: (TestName -> Maybe (WithLoHi Result) -> Result -> Result)+ -> IntMap (TestName, Maybe (WithLoHi IM.Key), TVar Status)+ -> IO StatusMap+postprocessResult f src = do+ paired <- forM src $ \(name, mDepId, tv) -> (name, mDepId, tv,) <$> newTVarIO NotStarted+ let doUpdate = atomically $ do+ (Any anyUpdated, All allDone) <-+ getApp $ flip foldMap paired $ \(name, mDepId, newTV, oldTV) -> Ap $ do+ old <- readTVar oldTV+ case old of+ Done{} -> pure (Any False, All True)+ _ -> do+ new <- readTVar newTV+ case new of+ Done res -> do++ depRes <- case mDepId of+ Nothing -> pure Nothing+ Just (WithLoHi depId lo hi) -> case IM.lookup depId src of+ Nothing -> pure Nothing+ Just (_, _, depTV) -> do+ depStatus <- readTVar depTV+ case depStatus of+ Done dep -> pure $ Just (WithLoHi dep lo hi)+ _ -> pure Nothing++ writeTVar oldTV (Done (f name depRes res))+ pure (Any True, All True)+ -- ignoring Progress nodes, we do not report any+ -- it would be helpful to have instance Eq Progress+ _ -> pure (Any False, All False)+ if anyUpdated || allDone then pure allDone else retry+ adNauseam = doUpdate >>= (`unless` adNauseam)+ _ <- forkIO adNauseam+ pure $ fmap (\(_, _, _, a) -> a) paired++int64ToDouble :: Int64 -> Double+int64ToDouble = fromIntegral++word64ToInt64 :: Word64 -> Int64+word64ToInt64 = fromIntegral++#endif++word64ToDouble :: Word64 -> Double+word64ToDouble = fromIntegral++#if !MIN_VERSION_base(4,10,0) && MIN_VERSION_base(4,6,0)+int64ToWord64 :: Int64 -> Word64+int64ToWord64 = fromIntegral+#endif
+ cbits/utils.c view
@@ -0,0 +1,116 @@+/*+ * Copyright (c) 2021 Andrew Lelechenko <andrew.lelechenko@gmail.com>+ */++#include <stdint.h>+#include <stdio.h>+#include <string.h>+#include <sys/types.h>+#ifdef __x86_64__+#include <emmintrin.h>+#include <xmmintrin.h>+#endif++ssize_t _hs_text_lines_memchr0A(const void *arr, size_t off, size_t len)+{+ const void *ptr = memchr(arr + off, 0x0A, len);+ return ptr == NULL ? -1 : ptr - (arr + off);+}++ssize_t _hs_text_lines_length_utf8_as_utf16(const uint8_t *arr, size_t off, size_t len)+{+ const uint8_t *src = arr + off;+ const uint8_t *srcend = src + len;+ ssize_t ret = 0;++ while (src < srcend){++#ifdef __x86_64__+ if (src < srcend - 15){+ __m128i w128 = _mm_loadu_si128((__m128i *)src);+ // Which bytes are < 128?+ uint16_t mask = _mm_movemask_epi8(w128);+ if (!mask){+ src+=16;+ ret+=16;+ continue;+ }+ }+#endif++ if(src < srcend - 7){+ uint64_t w64;+ memcpy(&w64, src, sizeof(uint64_t));+ if (!(w64 & 0x8080808080808080ULL)){+ src+=8;+ ret+=8;+ continue;+ }+ }++ uint8_t leadByte = *src++;+ if (leadByte < 0x80){+ ret++;+ } else if (leadByte < 0xe0){+ ret++;+ src++;+ } else if (leadByte < 0xf0){+ ret++;+ src+=2;+ } else {+ ret+=2;+ src+=3;+ }+ }++ return ret;+}++ssize_t _hs_text_lines_take_utf8_as_utf16(const uint8_t *arr, size_t off, size_t len, size_t cnt)+{+ const uint8_t *src = arr + off;+ const uint8_t *srcend = src + len;++ while (src < srcend && cnt > 0){++#ifdef __x86_64__+ if (src < srcend - 15 && cnt >= 16){+ __m128i w128 = _mm_loadu_si128((__m128i *)src);+ // Which bytes are < 128?+ uint16_t mask = _mm_movemask_epi8(w128);+ if (!mask){+ src+=16;+ cnt-=16;+ continue;+ }+ }+#endif++ if(src < srcend - 7 && cnt >= 8){+ uint64_t w64;+ memcpy(&w64, src, sizeof(uint64_t));+ if (!(w64 & 0x8080808080808080ULL)){+ src+=8;+ cnt-=8;+ continue;+ }+ }++ uint8_t leadByte = *src++;+ if (leadByte < 0x80){+ cnt--;+ } else if (leadByte < 0xe0){+ cnt--;+ src++;+ } else if (leadByte < 0xf0){+ cnt--;+ src+=2;+ } else {+ if(cnt < 2) return -1;+ cnt-=2;+ src+=3;+ }+ }++ return src - arr - off;+}
+ changelog.md view
@@ -0,0 +1,3 @@+# 0.1++* Initial release.
+ src/Data/Text/Lines.hs view
@@ -0,0 +1,25 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++module Data.Text.Lines+ ( TextLines+ , fromText+ , toText+ , null+ -- * Lines+ , lines+ , lengthInLines+ , splitAtLine+ -- * Code points+ , length+ , span+ , splitAt+ , Position(..)+ , lengthAsPosition+ , splitAtPosition+ ) where++import Prelude ()+import Data.Text.Lines.Internal
+ src/Data/Text/Lines/Internal.hs view
@@ -0,0 +1,404 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++{-# LANGUAGE BangPatterns #-}+{-# LANGUAGE CPP #-}+{-# LANGUAGE MagicHash #-}+{-# LANGUAGE UnliftedFFITypes #-}++module Data.Text.Lines.Internal+ ( TextLines(..)+ , fromText+ , null+ -- * Lines+ , lines+ , lengthInLines+ , splitAtLine+ -- * Code points+ , length+ , span+ , splitAt+ , Position(..)+ , lengthAsPosition+ , splitAtPosition+ -- * Utils+ , textLines+ , binarySearch+ , wordToInt+ , intToWord+ ) where++import Prelude ((+), (-), subtract, quot, fromIntegral, seq)+import Control.DeepSeq (NFData, rnf)+import Data.Bits (toIntegralSized)+import Data.Bool (Bool, otherwise)+import Data.Char (Char)+import Data.Eq (Eq, (==))+import Data.Function (on, (.), ($))+import Data.Int (Int)+import Data.Maybe (Maybe(..))+import Data.Monoid (Monoid(..))+import Data.Ord (Ord, compare, (<=), (<), (>))+import Data.Semigroup (Semigroup(..))+import Data.String (IsString(..))+import qualified Data.Text.Array as TA+import Data.Text.Internal (Text(..))+import qualified Data.Text as T+import qualified Data.Vector.Unboxed as U+import Data.Word (Word)+import Foreign.C.Types (CSize(..))+import GHC.Exts (ByteArray#)+import System.IO (IO)+import System.IO.Unsafe (unsafeDupablePerformIO)+import System.Posix.Types (CSsize(..))+import Text.Show (Show, show)++#if MIN_VERSION_text(2,0,0)+#else+import Prelude ((*))+import Data.Bits (shiftR)+#endif++#ifdef DEBUG+import Prelude (error)+import Data.Bool ((&&), not)+import Data.Char (generalCategory, GeneralCategory(..))+import Data.Eq ((/=))+import Data.List ((++))+import Data.Ord ((>=))+import Data.Text.Internal (showText)+import GHC.Stack (HasCallStack)+#else+#define HasCallStack ()+#endif++-- | A wrapper around 'Text' for fast line/column navigation.+-- Concatenation takes linear time.+--+-- This is a building block for 'Data.Text.Rope.Rope',+-- which provides logarithmic concatenation.+data TextLines = TextLines+ { toText :: !Text+ -- ^ Extract 'Text', O(1).+ , _nlIndices :: !(U.Vector Int)+ }++instance NFData TextLines where+ rnf (TextLines a b) = rnf a `seq` rnf b++instance Eq TextLines where+ (==) = (==) `on` toText+ {-# INLINE (==) #-}++instance Ord TextLines where+ compare = compare `on` toText+ {-# INLINE compare #-}++instance Show TextLines where+#ifdef DEBUG+ show (TextLines x y) = "TextLines { " ++ showText x ++ ", " ++ show y ++ " }"+#else+ show = show . toText+ {-# INLINE show #-}+#endif++instance IsString TextLines where+ fromString = fromText . fromString+ {-# INLINE fromString #-}++-- | Create from 'Text', linear time.+fromText :: HasCallStack => Text -> TextLines+fromText t = textLines t (U.fromList $ nlIndices t)+{-# INLINABLE fromText #-}++nlIndices :: Text -> [Int]+#if MIN_VERSION_text(2,0,0)+nlIndices (Text (TA.ByteArray arr#) off len) = go off+ where+ go !n+ | delta < 0 = []+ | otherwise = (n + delta) : go (n + delta + 1)+ where+ delta = fromIntegral $ unsafeDupablePerformIO $+ memchr arr# (fromIntegral n) (fromIntegral (len + off - n))+#else+nlIndices (Text arr off len) = go off+ where+ go !n+ | delta < 0 = []+ | TA.unsafeIndex arr (n + delta) == 0x0A = (n + delta) : go (n + delta + 1)+ | otherwise = go (n + delta + 1)+ where+ delta = fromIntegral (unsafeDupablePerformIO $+ memchr (TA.aBA arr) (2 * fromIntegral n) (2 * fromIntegral (len + off - n))) `shiftR` 1+#endif+{-# INLINABLE nlIndices #-}++foreign import ccall unsafe "_hs_text_lines_memchr0A" memchr+ :: ByteArray# -> CSize -> CSize -> IO CSsize++-- | Check whether a text is empty, O(1).+null :: TextLines -> Bool+null = T.null . toText+{-# INLINE null #-}++instance Semigroup TextLines where+ TextLines t1@(Text _ off1 len1) s1 <> TextLines t2@(Text _ off2 _) s2+ | T.null t1 = textLines t2 s2+ | T.null t2 = textLines t1 s1+ | otherwise = textLines+ (t1 <> t2)+ (U.map (subtract off1) s1 <> U.map (+ (len1 - off2)) s2)+ -- This relies on specific implementation of instance Semigroup Text!+ {-# INLINABLE (<>) #-}+ -- TODO implement sconcat via Builder++instance Monoid TextLines where+ mempty = textLines mempty mempty+ {-# INLINE mempty #-}+ mappend = (<>)+ {-# INLINE mappend #-}+ -- TODO implement mconcat via Builder++-- | Equivalent to 'Data.List.length' . 'lines', but in O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lengthInLines ""+-- 0+-- >>> lengthInLines "foo"+-- 1+-- >>> lengthInLines "foo\n"+-- 1+-- >>> lengthInLines "foo\n\n"+-- 2+-- >>> lengthInLines "foo\nbar"+-- 2+--+lengthInLines :: TextLines -> Word+lengthInLines (TextLines t nls) = case T.unsnoc t of+ Nothing -> 0+ Just (_, ch) -> intToWord $ U.length nls + (if ch == '\n' then 0 else 1)++-- | Split into lines by @\\n@, similar to @Data.Text.@'Data.Text.lines'.+-- Each line is produced in O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lines ""+-- []+-- >>> lines "foo"+-- ["foo"]+-- >>> lines "foo\n"+-- ["foo"]+-- >>> lines "foo\n\n"+-- ["foo",""]+-- >>> lines "foo\nbar"+-- ["foo","bar"]+--+lines :: TextLines -> [Text]+lines (TextLines (Text arr off len) nls) = go off (U.toList nls)+ where+ arrLen = off + len+ go i [] = [Text arr i (arrLen - i) | i < arrLen]+ go i (x : xs) = Text arr i (x - i) : go (x + 1) xs+{-# INLINABLE lines #-}++-- | Split at given line, O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> map (\l -> splitAtLine l "foo\nbar") [0..3]+-- [("","foo\nbar"),("foo\n","bar"),("foo\nbar",""),("foo\nbar","")]+--+splitAtLine :: HasCallStack => Word -> TextLines -> (TextLines, TextLines)+splitAtLine k = splitAtPosition (Position k 0)+{-# INLINE splitAtLine #-}++-------------------------------------------------------------------------------+-- Unicode code points++-- | Length in code points, similar to @Data.Text.@'Data.Text.length'.+-- Takes linear time.+--+-- >>> :set -XOverloadedStrings+-- >>> length "fя𐀀"+-- 3+-- >>> Data.Text.Utf16.Lines.length "fя𐀀"+-- 4+--+length :: TextLines -> Word+length = intToWord . T.length . toText+{-# INLINE length #-}++-- | Represent a position in a text.+data Position = Position+ { posLine :: !Word -- ^ Line.+ , posColumn :: !Word -- ^ Column in code points.+ } deriving (Eq, Ord, Show)++instance NFData Position where+ rnf (Position a b) = rnf a `seq` rnf b++-- | Associativity does not hold when 'posLine' overflows.+instance Semigroup Position where+ Position l1 c1 <> Position l2 c2 =+ Position (l1 + l2) (if l2 == 0 then c1 + c2 else c2)++instance Monoid Position where+ mempty = Position 0 0+ mappend = (<>)++-- | Measure text length as an amount of lines and columns.+-- Time is proportional to the length of the last line.+--+-- >>> :set -XOverloadedStrings+-- >>> lengthAsPosition "f𐀀"+-- Position {posLine = 0, posColumn = 2}+-- >>> lengthAsPosition "f\n𐀀"+-- Position {posLine = 1, posColumn = 1}+-- >>> lengthAsPosition "f\n𐀀\n"+-- Position {posLine = 2, posColumn = 0}+--+lengthAsPosition+ :: TextLines+ -> Position+lengthAsPosition (TextLines (Text arr off len) nls) = Position+ { posLine = intToWord $ U.length nls+ , posColumn = intToWord $ T.length $ Text arr nl (off + len - nl)+ }+ where+ nl = if U.null nls then off else U.last nls + 1+{-# INLINABLE lengthAsPosition #-}++-- | Span by a predicate, similar to @Data.Text.@'Data.Text.span'.+-- Takes linear (by length of the prefix satisfying the predicate) time.+span+ :: HasCallStack+ => (Char -> Bool)+ -> TextLines+ -> (TextLines, TextLines)+span f tl@(TextLines tx@(Text arr off _) nls)+ | len' == 0 = (mempty, tl)+ | otherwise = (y, z)+ where+ (Text _ off' len', tz) = T.span f tx+ -- This assumes that offset is the same as in tx+ n = binarySearch nls (off' + len')+ y = textLines (Text arr off (off' + len' - off)) (U.take n nls)+ z = textLines tz (U.drop n nls)+{-# INLINABLE span #-}++-- | Combination of 'splitAtLine' and subsequent 'splitAt'.+-- Time is linear in 'posColumn', but does not depend on 'posLine'.+--+-- >>> :set -XOverloadedStrings+-- >>> splitAtPosition (Position 1 0) "f\n𐀀я"+-- ("f\n","𐀀я")+-- >>> splitAtPosition (Position 1 1) "f\n𐀀я"+-- ("f\n𐀀","я")+-- >>> splitAtPosition (Position 1 2) "f\n𐀀я"+-- ("f\n𐀀я","")+-- >>> splitAtPosition (Position 0 2) "f\n𐀀я"+-- ("f\n","𐀀я")+-- >>> splitAtPosition (Position 0 3) "f\n𐀀я"+-- ("f\n𐀀","я")+-- >>> splitAtPosition (Position 0 4) "f\n𐀀я"+-- ("f\n𐀀я","")+--+splitAtPosition+ :: HasCallStack+ => Position+ -> TextLines+ -> (TextLines, TextLines)+splitAtPosition (Position line column) (TextLines (Text arr off len) nls) = (y, z)+ where+ arrLen = off + len+ nl+ | line <= 0 = off+ | line > intToWord (U.length nls) = arrLen+ | otherwise = nls U.! (wordToInt line - 1) + 1+ tx = Text arr nl (arrLen - nl)+ (Text _ off' len', tz)+ | column <= 0 = (Text arr nl 0, tx)+ | otherwise = case toIntegralSized column of+ Nothing -> (tx, mempty)+ Just column' -> T.splitAt column' tx+ -- This assumes that offset is the same as in tx+ n = binarySearch nls (off' + len')+ y = textLines (Text arr off (off' + len' - off)) (U.take n nls)+ z = textLines tz (U.drop n nls)+{-# INLINABLE splitAtPosition #-}++-- | Split at given code point, similar to @Data.Text.@'Data.Text.splitAt'.+-- Takes linear time.+--+-- >>> :set -XOverloadedStrings+-- >>> map (\c -> splitAt c "fя𐀀") [0..4]+-- [("","fя𐀀"),("f","я𐀀"),("fя","𐀀"),("fя𐀀",""),("fя𐀀","")]+--+splitAt :: HasCallStack => Word -> TextLines -> (TextLines, TextLines)+splitAt = splitAtPosition . Position 0+{-# INLINE splitAt #-}++-------------------------------------------------------------------------------+-- Utils++binarySearch+ :: (Ord a, U.Unbox a)+ => U.Vector a+ -> a+ -> Int+binarySearch vec el+ | U.null vec = 0+ | el <= U.head vec = 0+ | U.last vec < el = U.length vec+ | otherwise = go 0 (U.length vec - 1)+ where+ go i j+ | i + 1 == j = j+ | vec U.! k < el = go k j+ | otherwise = go i k+ where+ k = (i + j) `quot` 2+{-# SPECIALIZE binarySearch :: U.Vector Int -> Int -> Int #-}+{-# INLINABLE binarySearch #-}++intToWord :: Int -> Word+intToWord = fromIntegral+{-# INLINE intToWord #-}++wordToInt :: Word -> Int+wordToInt = fromIntegral+{-# INLINE wordToInt #-}++-------------------------------------------------------------------------------+-- Debug++#ifdef DEBUG++isValid :: TextLines -> Bool+isValid (TextLines t@(Text arr off len) stops) =+ not containsSurrogates && len >= 0 && go off (U.toList stops)+ where+ arrLen = off + len+ go i [] = T.all (/= '\n') (Text arr i (arrLen - i))+ go i (x : xs) = i <= x+ && T.all (/= '\n') (Text arr i (x - i))+ && T.head (Text arr x (arrLen - x)) == '\n'+ && go (x + 1) xs+ containsSurrogates = T.any ((== Surrogate) . generalCategory) t++textLines :: HasCallStack => Text -> U.Vector Int -> TextLines+textLines x y+ | isValid t = t+ | otherwise = error $ "Data.Text.Lines: violated internal invariant in " ++ show t+ where+ t = TextLines x y++#else++textLines :: HasCallStack => Text -> U.Vector Int -> TextLines+textLines = TextLines+{-# INLINE textLines #-}++#endif
+ src/Data/Text/Rope.hs view
@@ -0,0 +1,354 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++{-# LANGUAGE BangPatterns #-}+{-# LANGUAGE CPP #-}+{-# LANGUAGE GeneralizedNewtypeDeriving #-}+{-# LANGUAGE LambdaCase #-}+{-# LANGUAGE MultiParamTypeClasses #-}+{-# LANGUAGE StandaloneDeriving #-}+{-# LANGUAGE TupleSections #-}++#ifdef DEBUG+#define DEFRAGMENTATION_THRESHOLD 4+#else+#define DEFRAGMENTATION_THRESHOLD 4096+#endif++module Data.Text.Rope+ ( Rope+ , fromText+ , fromTextLines+ , toText+ , toTextLines+ , null+ -- * Lines+ , lines+ , lengthInLines+ , splitAtLine+ -- * Code points+ , length+ , splitAt+ , Position(..)+ , lengthAsPosition+ , splitAtPosition+ ) where++import Prelude ((-), (+), seq)+import Control.DeepSeq (NFData, rnf)+import Data.Bool (Bool(..), otherwise)+import Data.Char (Char)+import Data.Eq (Eq, (==))+import Data.Function ((.), ($), on, id)+import Data.Maybe (Maybe(..))+import Data.Monoid (Monoid(..))+import Data.Ord (Ord, compare, (<), (<=), Ordering(..))+import Data.Semigroup (Semigroup(..))+import Data.String (IsString(..))+import Data.Text (Text)+import qualified Data.Text as T+import qualified Data.Text.Lazy as TextLazy+import qualified Data.Text.Lazy.Builder as Builder+import Data.Text.Lines (Position(..))+import qualified Data.Text.Lines as TL+import Data.Word (Word)+import Text.Show (Show)++#ifdef DEBUG+import Prelude (error)+import GHC.Stack (HasCallStack)+#else+#define HasCallStack ()+import Text.Show (show)+#endif++-- | Rope of 'Text' chunks with logarithmic concatenation.+data Rope+ = Empty+ | Node !Rope !TL.TextLines !Rope !Word !Position++instance NFData Rope where+ rnf Empty = ()+ rnf (Node a b c d e) = rnf a `seq` rnf b `seq` rnf c `seq` rnf d `seq` rnf e++instance Eq Rope where+ (==) = (==) `on` toLazyText++instance Ord Rope where+ compare = compare `on` toLazyText++#ifdef DEBUG+deriving instance Show Rope+#else+instance Show Rope where+ show = show . toLazyText+#endif++instance IsString Rope where+ fromString = fromTextLines . fromString++-- | Check whether a rope is empty, O(1).+null :: Rope -> Bool+null = \case+ Empty -> True+ Node{} -> False++-- | Length in code points, similar to @Data.Text.@'Data.Text.length', O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> length "fя𐀀"+-- 3+-- >>> Data.Text.Utf16.Rope.length "fя𐀀"+-- 4+--+length :: Rope -> Word+length = \case+ Empty -> 0+ Node _ _ _ w _ -> w++-- | Measure text length as an amount of lines and columns, O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lengthAsPosition "f𐀀"+-- Position {posLine = 0, posColumn = 2}+-- >>> lengthAsPosition "f\n𐀀"+-- Position {posLine = 1, posColumn = 1}+-- >>> lengthAsPosition "f\n𐀀\n"+-- Position {posLine = 2, posColumn = 0}+--+lengthAsPosition :: Rope -> Position+lengthAsPosition = \case+ Empty -> mempty+ Node _ _ _ _ p -> p++instance Semigroup Rope where+ Empty <> t = t+ t <> Empty = t+ Node l1 c1 r1 u1 p1 <> Node l2 c2 r2 u2 p2 = defragment+ l1+ c1+ (Node (r1 <> l2) c2 r2 (length r1 + u2) (lengthAsPosition r1 <> p2))+ (u1 + u2)+ (p1 <> p2)++instance Monoid Rope where+ mempty = Empty+ mappend = (<>)++defragment :: HasCallStack => Rope -> TL.TextLines -> Rope -> Word -> Position -> Rope+defragment !l !c !r !u !p+#ifdef DEBUG+ | TL.null c = error "Data.Text.Lines: violated internal invariant"+#endif+ | u < DEFRAGMENTATION_THRESHOLD+ = Node Empty (toTextLines rp) Empty u p+ | otherwise+ = rp+ where+ rp = Node l c r u p++-- | Create from 'TL.TextLines', linear time.+fromTextLines :: TL.TextLines -> Rope+fromTextLines tl+ | TL.null tl = Empty+ | otherwise = Node Empty tl Empty (TL.length tl) (TL.lengthAsPosition tl)++node :: HasCallStack => Rope -> TL.TextLines -> Rope -> Rope+node l c r = defragment l c r totalLength totalLengthAsPosition+ where+ totalLength = length l + TL.length c + length r+ totalLengthAsPosition = lengthAsPosition l <> TL.lengthAsPosition c <> lengthAsPosition r++(|>) :: Rope -> TL.TextLines -> Rope+tr |> tl+ | TL.null tl = tr+ | otherwise = node tr tl Empty++(<|) :: TL.TextLines -> Rope -> Rope+tl <| tr+ | TL.null tl = tr+ | otherwise = node Empty tl tr++-- | Create from 'Text', linear time.+fromText :: Text -> Rope+fromText = fromTextLines . TL.fromText++foldMapRope :: Monoid a => (TL.TextLines -> a) -> Rope -> a+foldMapRope f = go+ where+ go = \case+ Empty -> mempty+ Node l c r _ _ -> go l `mappend` f c `mappend` go r++data Lines = Lines ![Text] !Bool++instance Semigroup Lines where+ Lines [] _ <> ls = ls+ ls <> Lines [] _ = ls+ Lines xs x <> Lines ys y = Lines (if x then xs <> ys else go xs ys) y+ where+ go [] vs = vs+ go [u] (v : vs) = (u <> v) : vs+ go (u : us) vs = u : go us vs++instance Monoid Lines where+ mempty = Lines [] False+ mappend = (<>)++-- | Split into lines by @\\n@, similar to @Data.Text.@'Data.Text.lines'.+-- Each line is produced in O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lines ""+-- []+-- >>> lines "foo"+-- ["foo"]+-- >>> lines "foo\n"+-- ["foo"]+-- >>> lines "foo\n\n"+-- ["foo",""]+-- >>> lines "foo\nbar"+-- ["foo","bar"]+--+lines :: Rope -> [Text]+lines = (\(Lines ls _) -> ls) . foldMapRope+ -- This assumes that there are no empty chunks:+ (\tl -> Lines (TL.lines tl) (T.last (TL.toText tl) == '\n'))++lastChar :: Rope -> Maybe Char+lastChar = \case+ Empty -> Nothing+ -- This assumes that there are no empty chunks:+ Node _ c Empty _ _ -> Just $ T.last $ TL.toText c+ Node _ _ r _ _ -> lastChar r++-- | Equivalent to 'Data.List.length' . 'lines', but in logarithmic time.+--+-- >>> :set -XOverloadedStrings+-- >>> lengthInLines ""+-- 0+-- >>> lengthInLines "foo"+-- 1+-- >>> lengthInLines "foo\n"+-- 1+-- >>> lengthInLines "foo\n\n"+-- 2+-- >>> lengthInLines "foo\nbar"+-- 2+--+lengthInLines :: Rope -> Word+lengthInLines rp = case lastChar rp of+ Nothing -> 0+ Just ch -> TL.posLine (lengthAsPosition rp) + (if ch == '\n' then 0 else 1)++-- | Glue chunks into 'TL.TextLines', linear time.+toTextLines :: Rope -> TL.TextLines+toTextLines = foldMapRope id+-- TODO make it fast! implement via mconcat for TextLines++toLazyText :: Rope -> TextLazy.Text+toLazyText = foldMapRope (TextLazy.fromStrict . TL.toText)++-- | Glue chunks into 'Text', linear time.+toText :: Rope -> Text+toText = TextLazy.toStrict . Builder.toLazyText . foldMapRope (Builder.fromText . TL.toText)++-- | Split at given code point, similar to @Data.Text.@'Data.Text.splitAt'.+-- Takes linear time.+--+-- >>> :set -XOverloadedStrings+-- >>> map (\c -> splitAt c "fя𐀀") [0..4]+-- [("","fя𐀀"),("f","я𐀀"),("fя","𐀀"),("fя𐀀",""),("fя𐀀","")]+--+splitAt :: HasCallStack => Word -> Rope -> (Rope, Rope)+splitAt !len = \case+ Empty -> (Empty, Empty)+ Node l c r _ _+ | len <= ll -> case splitAt len l of+ (before, after) -> (before, node after c r)+ | len <= llc -> case TL.splitAt (len - ll) c of+ (before, after) -> (l |> before, after <| r)+ | otherwise -> case splitAt (len - llc) r of+ (before, after) -> (node l c before, after)+ where+ ll = length l+ llc = ll + TL.length c++-- | Split at given line, logarithmic time.+--+-- >>> :set -XOverloadedStrings+-- >>> map (\l -> splitAtLine l "foo\nbar") [0..3]+-- [("","foo\nbar"),("foo\n","bar"),("foo\nbar",""),("foo\nbar","")]+--+splitAtLine :: HasCallStack => Word -> Rope -> (Rope, Rope)+splitAtLine !len = \case+ Empty -> (Empty, Empty)+ Node l c r _ _+ | len <= ll -> case splitAtLine len l of+ (before, after) -> (before, node after c r)+ | len <= llc -> case TL.splitAtLine (len - ll) c of+ (before, after) -> (l |> before, after <| r)+ | otherwise -> case splitAtLine (len - llc) r of+ (before, after) -> (node l c before, after)+ where+ ll = TL.posLine (lengthAsPosition l)+ llc = ll + TL.posLine (TL.lengthAsPosition c)++subOnRope :: Rope -> Position -> Position -> Position+subOnRope rp (Position xl xc) (Position yl yc) = case xl `compare` yl of+ GT -> Position (xl - yl) xc+ EQ -> Position 0 (xc - yc)+ LT -> Position 0 (xc - length rp')+ where+ (_, rp') = splitAtLine xl rp++subOnLines :: TL.TextLines -> Position -> Position -> Position+subOnLines tl (Position xl xc) (Position yl yc) = case xl `compare` yl of+ GT -> Position (xl - yl) xc+ EQ -> Position 0 (xc - yc)+ LT -> Position 0 (xc - TL.length tl')+ where+ (_, tl') = TL.splitAtLine xl tl++-- | Combination of 'splitAtLine' and subsequent 'splitAt'.+-- Time is linear in 'posColumn' and logarithmic in 'posLine'.+--+-- >>> :set -XOverloadedStrings+-- >>> splitAtPosition (Position 1 0) "f\n𐀀я"+-- ("f\n","𐀀я")+-- >>> splitAtPosition (Position 1 1) "f\n𐀀я"+-- ("f\n𐀀","я")+-- >>> splitAtPosition (Position 1 2) "f\n𐀀я"+-- ("f\n𐀀я","")+-- >>> splitAtPosition (Position 0 2) "f\n𐀀я"+-- ("f\n","𐀀я")+-- >>> splitAtPosition (Position 0 3) "f\n𐀀я"+-- ("f\n𐀀","я")+-- >>> splitAtPosition (Position 0 4) "f\n𐀀я"+-- ("f\n𐀀я","")+--+splitAtPosition :: HasCallStack => Position -> Rope -> (Rope, Rope)+splitAtPosition (Position 0 0) = (mempty,)+splitAtPosition !len = \case+ Empty -> (Empty, Empty)+ Node l c r _ _+ | len <= ll -> case splitAtPosition len l of+ (before, after)+ | null after -> case splitAtPosition len' (c <| r) of+ (r', r'') -> (l <> r', r'')+ | otherwise -> (before, node after c r)+ | len <= llc -> case TL.splitAtPosition len' c of+ (before, after)+ | TL.null after -> case splitAtPosition len'' r of+ (r', r'') -> ((l |> c) <> r', r'')+ | otherwise -> (l |> before, after <| r)+ | otherwise -> case splitAtPosition len'' r of+ (before, after) -> (node l c before, after)+ where+ ll = lengthAsPosition l+ lc = TL.lengthAsPosition c+ llc = ll <> lc+ len' = subOnRope l len ll+ len'' = subOnLines c len' lc
+ src/Data/Text/Utf16/Lines.hs view
@@ -0,0 +1,275 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++{-# LANGUAGE BangPatterns #-}+{-# LANGUAGE CPP #-}+{-# LANGUAGE MagicHash #-}+{-# LANGUAGE GeneralizedNewtypeDeriving #-}+{-# LANGUAGE UnliftedFFITypes #-}++module Data.Text.Utf16.Lines+ ( TextLines+ , fromText+ , toText+ , null+ -- * Lines+ , lines+ , lengthInLines+ , splitAtLine+ -- * UTF-16 code units+ , length+ , splitAt+ , Position(..)+ , lengthAsPosition+ , splitAtPosition+ ) where++import Prelude ((+), (-), seq)+import Control.DeepSeq (NFData, rnf)+import Data.Bool (Bool, otherwise)+import Data.Coerce (coerce)+import Data.Eq (Eq, (==))+import Data.Function ((.), ($))+import Data.Maybe (Maybe(..))+import Data.Monoid (Monoid(..))+import Data.Ord (Ord, (<=), (>), (>=))+import Data.Semigroup (Semigroup(..))+import Data.String (IsString)+import qualified Data.Text.Array as TA+import Data.Text.Internal (Text(..))+import qualified Data.Text.Lines.Internal as I+import qualified Data.Vector.Unboxed as U+import Data.Word (Word)+import Text.Show (Show, show)++#if MIN_VERSION_text(2,0,0)+import Prelude (fromIntegral)+import Foreign.C.Types (CSize(..))+import GHC.Exts (ByteArray#)+import System.IO (IO)+import System.IO.Unsafe (unsafeDupablePerformIO)+import System.Posix.Types (CSsize(..))+#else+import Data.Bool ((&&))+import Data.Ord ((<))+#endif++#ifdef DEBUG+import GHC.Stack (HasCallStack)+#else+#define HasCallStack ()+#endif++-- | A wrapper around 'Text' for fast line/column navigation.+-- Concatenation takes linear time.+--+-- This is a building block for 'Data.Text.Utf16.Rope.Rope',+-- which provides logarithmic concatenation.+newtype TextLines = TextLines I.TextLines+ deriving (Eq, Ord, IsString, Semigroup, Monoid, NFData)++instance Show TextLines where+ show (TextLines t) = show t++-- | Create from 'Text', linear time.+fromText :: HasCallStack => Text -> TextLines+fromText = coerce I.fromText+{-# INLINE fromText #-}++-- | Extract 'Text', O(1).+toText :: TextLines -> Text+toText = coerce I.toText+{-# INLINE toText #-}++-- | Check whether a text is empty, O(1).+null :: TextLines -> Bool+null = coerce I.null+{-# INLINE null #-}++-- | Split into lines by @\\n@, similar to @Data.Text.@'Data.Text.lines'.+-- Each line is produced in O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lines ""+-- []+-- >>> lines "foo"+-- ["foo"]+-- >>> lines "foo\n"+-- ["foo"]+-- >>> lines "foo\n\n"+-- ["foo",""]+-- >>> lines "foo\nbar"+-- ["foo","bar"]+--+lines :: TextLines -> [Text]+lines = coerce I.lines+{-# INLINE lines #-}++-- | Equivalent to 'Data.List.length' . 'lines', but in O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lengthInLines ""+-- 0+-- >>> lengthInLines "foo"+-- 1+-- >>> lengthInLines "foo\n"+-- 1+-- >>> lengthInLines "foo\n\n"+-- 2+-- >>> lengthInLines "foo\nbar"+-- 2+--+lengthInLines :: TextLines -> Word+lengthInLines = coerce I.lengthInLines+{-# INLINE lengthInLines #-}++-- | Split at given line, O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> map (\l -> splitAtLine l "foo\nbar") [0..3]+-- [("","foo\nbar"),("foo\n","bar"),("foo\nbar",""),("foo\nbar","")]+--+splitAtLine :: HasCallStack => Word -> TextLines -> (TextLines, TextLines)+splitAtLine = coerce I.splitAtLine+{-# INLINE splitAtLine #-}++lengthTextUtf16 :: Text -> Word+#if MIN_VERSION_text(2,0,0)+lengthTextUtf16 (Text (TA.ByteArray arr) off len) = fromIntegral $ unsafeDupablePerformIO $+ lengthUtf8AsUtf16 arr (fromIntegral off) (fromIntegral len)++foreign import ccall unsafe "_hs_text_lines_length_utf8_as_utf16" lengthUtf8AsUtf16+ :: ByteArray# -> CSize -> CSize -> IO CSsize+#else+lengthTextUtf16 (Text _ _ len) = I.intToWord len+#endif+{-# INLINABLE lengthTextUtf16 #-}++-- | Length in UTF-16 code units.+-- Takes linear time.+--+-- >>> :set -XOverloadedStrings+-- >>> length "fя𐀀"+-- 4+-- >>> Data.Text.Lines.length "fя𐀀"+-- 3+--+length :: TextLines -> Word+length = lengthTextUtf16 . toText+{-# INLINE length #-}++-- | Represent a position in a text.+data Position = Position+ { posLine :: !Word -- ^ Line.+ , posColumn :: !Word -- ^ Column in UTF-16 code units.+ } deriving (Eq, Ord, Show)++instance NFData Position where+ rnf (Position a b) = rnf a `seq` rnf b++-- | Associativity does not hold when 'posLine' overflows.+instance Semigroup Position where+ Position l1 c1 <> Position l2 c2 =+ Position (l1 + l2) (if l2 == 0 then c1 + c2 else c2)++instance Monoid Position where+ mempty = Position 0 0+ mappend = (<>)++-- | Measure text length as an amount of lines and columns.+-- Time is proportional to the length of the last line.+--+-- >>> :set -XOverloadedStrings+-- >>> lengthAsPosition "f𐀀"+-- Position {posLine = 0, posColumn = 3}+-- >>> lengthAsPosition "f\n𐀀"+-- Position {posLine = 1, posColumn = 2}+-- >>> lengthAsPosition "f\n𐀀\n"+-- Position {posLine = 2, posColumn = 0}+--+lengthAsPosition+ :: TextLines+ -> Position+lengthAsPosition (TextLines (I.TextLines (Text arr off len) nls)) = Position+ { posLine = I.intToWord $ U.length nls+ , posColumn = lengthTextUtf16 $ Text arr nl (off + len - nl)+ }+ where+ nl = if U.null nls then off else U.last nls + 1+{-# INLINABLE lengthAsPosition #-}++splitTextAtUtf16Index :: Word -> Text -> Maybe (Text, Text)+splitTextAtUtf16Index k t@(Text arr off len)+ | k <= 0 = Just (Text arr off 0, t)+ | k >= I.intToWord len = Just (t, mempty)+#if MIN_VERSION_text(2,0,0)+ | o >= 0 = Just (Text arr off o, Text arr (off + o) (len - o))+ | otherwise = Nothing+ where+ !(TA.ByteArray arr#) = arr+ o = fromIntegral $ unsafeDupablePerformIO $+ takeUtf8AsUtf16 arr# (fromIntegral off) (fromIntegral len) (fromIntegral k)++foreign import ccall unsafe "_hs_text_lines_take_utf8_as_utf16" takeUtf8AsUtf16+ :: ByteArray# -> CSize -> CSize -> CSize -> IO CSsize+#else+ -- Something wrong is going here:+ | otherwise = if c >= 0xdc00 && c < 0xe000 then Nothing else Just+ (Text arr off k', Text arr (off + k') (len - k'))+ where+ k' = I.wordToInt k+ c = TA.unsafeIndex arr (off + k')+#endif+{-# INLINABLE splitTextAtUtf16Index #-}++-- | Combination of 'splitAtLine' and subsequent 'splitAt'.+-- If requested number of code units splits a code point in half, return 'Nothing'.+-- Time is linear in 'posColumn', but does not depend on 'posLine'.+--+-- >>> :set -XOverloadedStrings+-- >>> splitAtPosition (Position 1 0) "f\n𐀀я"+-- Just ("f\n","𐀀я")+-- >>> splitAtPosition (Position 1 1) "f\n𐀀я"+-- Nothing+-- >>> splitAtPosition (Position 1 2) "f\n𐀀я"+-- Just ("f\n𐀀","я")+-- >>> splitAtPosition (Position 0 2) "f\n𐀀я"+-- Just ("f\n","𐀀я")+-- >>> splitAtPosition (Position 0 3) "f\n𐀀я"+-- Nothing+-- >>> splitAtPosition (Position 0 4) "f\n𐀀я"+-- Just ("f\n𐀀","я")+--+splitAtPosition+ :: HasCallStack+ => Position+ -> TextLines+ -> Maybe (TextLines, TextLines)+splitAtPosition (Position line column) (TextLines (I.TextLines (Text arr off len) nls)) =+ case splitTextAtUtf16Index column tx of+ Nothing -> Nothing+ Just (Text _ off' len', tz) -> let n = I.binarySearch nls (off' + len') in Just+ ( TextLines $ I.textLines (Text arr off (off' + len' - off)) (U.take n nls)+ , TextLines $ I.textLines tz (U.drop n nls))+ where+ arrLen = off + len+ nl+ | line <= 0 = off+ | line > I.intToWord (U.length nls) = arrLen+ | otherwise = nls U.! (I.wordToInt line - 1) + 1+ tx = Text arr nl (arrLen - nl)+{-# INLINABLE splitAtPosition #-}++-- | Split at given UTF-16 code unit.+-- If requested number of code units splits a code point in half, return 'Nothing'.+-- Takes linear time.+--+-- >>> :set -XOverloadedStrings+-- >>> map (\c -> splitAt c "fя𐀀") [0..4]+-- [Just ("","fя𐀀"),Just ("f","я𐀀"),Just ("fя","𐀀"),Nothing,Just ("fя𐀀","")]+--+splitAt :: HasCallStack => Word -> TextLines -> Maybe (TextLines, TextLines)+splitAt = splitAtPosition . Position 0+{-# INLINE splitAt #-}
+ src/Data/Text/Utf16/Rope.hs view
@@ -0,0 +1,362 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++{-# LANGUAGE BangPatterns #-}+{-# LANGUAGE CPP #-}+{-# LANGUAGE GeneralizedNewtypeDeriving #-}+{-# LANGUAGE LambdaCase #-}+{-# LANGUAGE MultiParamTypeClasses #-}+{-# LANGUAGE StandaloneDeriving #-}+{-# LANGUAGE TupleSections #-}++#ifdef DEBUG+#define DEFRAGMENTATION_THRESHOLD 4+#else+#define DEFRAGMENTATION_THRESHOLD 4096+#endif++module Data.Text.Utf16.Rope+ ( Rope+ , fromText+ , fromTextLines+ , toText+ , toTextLines+ , null+ -- * Lines+ , lines+ , lengthInLines+ , splitAtLine+ -- * UTF-16 code units+ , length+ , splitAt+ , Position(..)+ , lengthAsPosition+ , splitAtPosition+ ) where++import Prelude ((-), (+), seq)+import Control.DeepSeq (NFData, rnf)+import Data.Bool (Bool(..), otherwise)+import Data.Char (Char)+import Data.Eq (Eq, (==))+import Data.Function ((.), ($), on, id)+import Data.Maybe (Maybe(..))+import Data.Monoid (Monoid(..))+import Data.Ord (Ord, compare, (<), (<=), Ordering(..))+import Data.Semigroup (Semigroup(..))+import Data.String (IsString(..))+import Data.Text (Text)+import qualified Data.Text as T+import qualified Data.Text.Lazy as TextLazy+import qualified Data.Text.Lazy.Builder as Builder+import Data.Text.Utf16.Lines (Position(..))+import qualified Data.Text.Utf16.Lines as TL+import Data.Word (Word)+import Text.Show (Show)++#ifdef DEBUG+import Prelude (error)+import GHC.Stack (HasCallStack)+#else+#define HasCallStack ()+import Text.Show (show)+#endif++-- | Rope of 'Text' chunks with logarithmic concatenation.+data Rope+ = Empty+ | Node !Rope !TL.TextLines !Rope !Word !Position++instance NFData Rope where+ rnf Empty = ()+ rnf (Node a b c d e) = rnf a `seq` rnf b `seq` rnf c `seq` rnf d `seq` rnf e++instance Eq Rope where+ (==) = (==) `on` toLazyText++instance Ord Rope where+ compare = compare `on` toLazyText++#ifdef DEBUG+deriving instance Show Rope+#else+instance Show Rope where+ show = show . toLazyText+#endif++instance IsString Rope where+ fromString = fromTextLines . fromString++-- | Check whether a rope is empty, O(1).+null :: Rope -> Bool+null = \case+ Empty -> True+ Node{} -> False++-- | Length in UTF-16 code units, O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> length "fя𐀀"+-- 4+-- >>> Data.Text.Rope.length "fя𐀀"+-- 3+length :: Rope -> Word+length = \case+ Empty -> 0+ Node _ _ _ w _ -> w++-- | Measure text length as an amount of lines and columns, O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lengthAsPosition "f𐀀"+-- Position {posLine = 0, posColumn = 3}+-- >>> lengthAsPosition "f\n𐀀"+-- Position {posLine = 1, posColumn = 2}+-- >>> lengthAsPosition "f\n𐀀\n"+-- Position {posLine = 2, posColumn = 0}+--+lengthAsPosition :: Rope -> Position+lengthAsPosition = \case+ Empty -> mempty+ Node _ _ _ _ p -> p++instance Semigroup Rope where+ Empty <> t = t+ t <> Empty = t+ Node l1 c1 r1 u1 p1 <> Node l2 c2 r2 u2 p2 = defragment+ l1+ c1+ (Node (r1 <> l2) c2 r2 (length r1 + u2) (lengthAsPosition r1 <> p2))+ (u1 + u2)+ (p1 <> p2)++instance Monoid Rope where+ mempty = Empty+ mappend = (<>)++defragment :: HasCallStack => Rope -> TL.TextLines -> Rope -> Word -> Position -> Rope+defragment !l !c !r !u !p+#ifdef DEBUG+ | TL.null c = error "Data.Text.Lines: violated internal invariant"+#endif+ | u < DEFRAGMENTATION_THRESHOLD+ = Node Empty (toTextLines rp) Empty u p+ | otherwise+ = rp+ where+ rp = Node l c r u p++-- | Create from 'TL.TextLines', linear time.+fromTextLines :: TL.TextLines -> Rope+fromTextLines tl+ | TL.null tl = Empty+ | otherwise = Node Empty tl Empty (TL.length tl) (TL.lengthAsPosition tl)++node :: HasCallStack => Rope -> TL.TextLines -> Rope -> Rope+node l c r = defragment l c r totalLength totalLengthAsPosition+ where+ totalLength = length l + TL.length c + length r+ totalLengthAsPosition = lengthAsPosition l <> TL.lengthAsPosition c <> lengthAsPosition r++(|>) :: Rope -> TL.TextLines -> Rope+tr |> tl+ | TL.null tl = tr+ | otherwise = node tr tl Empty++(<|) :: TL.TextLines -> Rope -> Rope+tl <| tr+ | TL.null tl = tr+ | otherwise = node Empty tl tr++-- | Create from 'Text', linear time.+fromText :: Text -> Rope+fromText = fromTextLines . TL.fromText++foldMapRope :: Monoid a => (TL.TextLines -> a) -> Rope -> a+foldMapRope f = go+ where+ go = \case+ Empty -> mempty+ Node l c r _ _ -> go l `mappend` f c `mappend` go r++data Lines = Lines ![Text] !Bool++instance Semigroup Lines where+ Lines [] _ <> ls = ls+ ls <> Lines [] _ = ls+ Lines xs x <> Lines ys y = Lines (if x then xs <> ys else go xs ys) y+ where+ go [] vs = vs+ go [u] (v : vs) = (u <> v) : vs+ go (u : us) vs = u : go us vs++instance Monoid Lines where+ mempty = Lines [] False+ mappend = (<>)++-- | Split into lines by @\\n@, similar to @Data.Text.@'Data.Text.lines'.+-- Each line is produced in O(1).+--+-- >>> :set -XOverloadedStrings+-- >>> lines ""+-- []+-- >>> lines "foo"+-- ["foo"]+-- >>> lines "foo\n"+-- ["foo"]+-- >>> lines "foo\n\n"+-- ["foo",""]+-- >>> lines "foo\nbar"+-- ["foo","bar"]+--+lines :: Rope -> [Text]+lines = (\(Lines ls _) -> ls) . foldMapRope+ -- This assumes that there are no empty chunks:+ (\tl -> Lines (TL.lines tl) (T.last (TL.toText tl) == '\n'))++lastChar :: Rope -> Maybe Char+lastChar = \case+ Empty -> Nothing+ -- This assumes that there are no empty chunks:+ Node _ c Empty _ _ -> Just $ T.last $ TL.toText c+ Node _ _ r _ _ -> lastChar r++-- | Equivalent to 'Data.List.length' . 'lines', but in logarithmic time.+--+-- >>> :set -XOverloadedStrings+-- >>> lengthInLines ""+-- 0+-- >>> lengthInLines "foo"+-- 1+-- >>> lengthInLines "foo\n"+-- 1+-- >>> lengthInLines "foo\n\n"+-- 2+-- >>> lengthInLines "foo\nbar"+-- 2+--+lengthInLines :: Rope -> Word+lengthInLines rp = case lastChar rp of+ Nothing -> 0+ Just ch -> TL.posLine (lengthAsPosition rp) + (if ch == '\n' then 0 else 1)++-- | Glue chunks into 'TL.TextLines', linear time.+toTextLines :: Rope -> TL.TextLines+toTextLines = foldMapRope id+-- TODO make it fast! implement via mconcat for TextLines++toLazyText :: Rope -> TextLazy.Text+toLazyText = foldMapRope (TextLazy.fromStrict . TL.toText)++-- | Glue chunks into 'Text', linear time.+toText :: Rope -> Text+toText = TextLazy.toStrict . Builder.toLazyText . foldMapRope (Builder.fromText . TL.toText)++-- | Split at given UTF-16 code unit.+-- If requested number of code units splits a code point in half, return 'Nothing'.+-- Takes linear time.+--+-- >>> :set -XOverloadedStrings+-- >>> map (\c -> splitAt c "fя𐀀") [0..4]+-- [Just ("","fя𐀀"),Just ("f","я𐀀"),Just ("fя","𐀀"),Nothing,Just ("fя𐀀","")]+--+splitAt :: HasCallStack => Word -> Rope -> Maybe (Rope, Rope)+splitAt !len = \case+ Empty -> Just (Empty, Empty)+ Node l c r _ _+ | len <= ll -> case splitAt len l of+ Nothing -> Nothing+ Just (before, after) -> Just (before, node after c r)+ | len <= llc -> case TL.splitAt (len - ll) c of+ Nothing -> Nothing+ Just (before, after) -> Just (l |> before, after <| r)+ | otherwise -> case splitAt (len - llc) r of+ Nothing -> Nothing+ Just (before, after) -> Just (node l c before, after)+ where+ ll = length l+ llc = ll + TL.length c++-- | Split at given line, logarithmic time.+--+-- >>> :set -XOverloadedStrings+-- >>> map (\l -> splitAtLine l "foo\nbar") [0..3]+-- [("","foo\nbar"),("foo\n","bar"),("foo\nbar",""),("foo\nbar","")]+--+splitAtLine :: HasCallStack => Word -> Rope -> (Rope, Rope)+splitAtLine !len = \case+ Empty -> (Empty, Empty)+ Node l c r _ _+ | len <= ll -> case splitAtLine len l of+ (before, after) -> (before, node after c r)+ | len <= llc -> case TL.splitAtLine (len - ll) c of+ (before, after) -> (l |> before, after <| r)+ | otherwise -> case splitAtLine (len - llc) r of+ (before, after) -> (node l c before, after)+ where+ ll = TL.posLine (lengthAsPosition l)+ llc = ll + TL.posLine (TL.lengthAsPosition c)++subOnRope :: Rope -> Position -> Position -> Position+subOnRope rp (Position xl xc) (Position yl yc) = case xl `compare` yl of+ GT -> Position (xl - yl) xc+ EQ -> Position 0 (xc - yc)+ LT -> Position 0 (xc - length rp')+ where+ (_, rp') = splitAtLine xl rp++subOnLines :: TL.TextLines -> Position -> Position -> Position+subOnLines tl (Position xl xc) (Position yl yc) = case xl `compare` yl of+ GT -> Position (xl - yl) xc+ EQ -> Position 0 (xc - yc)+ LT -> Position 0 (xc - TL.length tl')+ where+ (_, tl') = TL.splitAtLine xl tl++-- | Combination of 'splitAtLine' and subsequent 'splitAt'.+-- Time is linear in 'posColumn' and logarithmic in 'posLine'.+--+-- >>> :set -XOverloadedStrings+-- >>> splitAtPosition (Position 1 0) "f\n𐀀я"+-- Just ("f\n","𐀀я")+-- >>> splitAtPosition (Position 1 1) "f\n𐀀я"+-- Nothing+-- >>> splitAtPosition (Position 1 2) "f\n𐀀я"+-- Just ("f\n𐀀","я")+-- >>> splitAtPosition (Position 0 2) "f\n𐀀я"+-- Just ("f\n","𐀀я")+-- >>> splitAtPosition (Position 0 3) "f\n𐀀я"+-- Nothing+-- >>> splitAtPosition (Position 0 4) "f\n𐀀я"+-- Just ("f\n𐀀","я")+--+splitAtPosition :: HasCallStack => Position -> Rope -> Maybe (Rope, Rope)+splitAtPosition (Position 0 0) = Just . (mempty,)+splitAtPosition !len = \case+ Empty -> Just (Empty, Empty)+ Node l c r _ _+ | len <= ll -> case splitAtPosition len l of+ Nothing -> Nothing+ Just (before, after)+ | null after -> case splitAtPosition len' (c <| r) of+ Nothing -> Nothing+ Just (r', r'') -> Just (l <> r', r'')+ | otherwise -> Just (before, node after c r)+ | len <= llc -> case TL.splitAtPosition len' c of+ Nothing -> Nothing+ Just (before, after)+ | TL.null after -> case splitAtPosition len'' r of+ Nothing -> Nothing+ Just (r', r'') -> Just ((l |> c) <> r', r'')+ | otherwise -> Just (l |> before, after <| r)+ | otherwise -> case splitAtPosition len'' r of+ Nothing -> Nothing+ Just (before, after) -> Just (node l c before, after)+ where+ ll = lengthAsPosition l+ lc = TL.lengthAsPosition c+ llc = ll <> lc+ len' = subOnRope l len ll+ len'' = subOnLines c len' lc
+ test/CharLines.hs view
@@ -0,0 +1,98 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++module CharLines+ ( testSuite+ ) where++import Prelude (fromIntegral, maxBound, (-))+import Data.Bool ((||), not, (&&))+import Data.Function (($))+import qualified Data.List as L+import Data.Monoid (mempty)+import Data.Ord (min, (>=), (<))+import Data.Semigroup ((<>))+import qualified Data.Text as T+import Data.Text.Lines+import Data.Tuple (snd)+import Test.Tasty (testGroup, TestTree)+import Test.Tasty.QuickCheck (testProperty, (===), applyFun, (.||.), (.&&.), (==>))++import Utils ()++testSuite :: TestTree+testSuite = testGroup "Char Lines"+ [ testProperty "toText . fromText" $+ \x -> toText (fromText x) === x++ , testProperty "null" $+ \x -> null x === T.null (toText x)++ , testProperty "TextLines associativity" $+ \x y z -> (x <> y) <> z === x <> (y <> z :: TextLines)+ , testProperty "TextLines mempty <>" $+ \x -> mempty <> x === (x :: TextLines)+ , testProperty "TextLines <> mempty" $+ \x -> x <> mempty === (x :: TextLines)++ , testProperty "Position associativity" $+ \x y z -> posLine x < maxBound - posLine y && posLine y < maxBound - posLine z ==>+ (x <> y) <> z === x <> (y <> z :: Position)+ , testProperty "Position mempty <>" $+ \x -> mempty <> x === (x :: Position)+ , testProperty "Position <> mempty" $+ \x -> x <> mempty === (x :: Position)++ , testProperty "lines" $+ \x -> T.lines x === lines (fromText x)+ , testProperty "lengthInLines" $+ \x -> L.genericLength (T.lines x) === lengthInLines (fromText x)++ , testProperty "span 1" $+ \f x -> let (y, z) = span (applyFun f) x in x === y <> z+ , testProperty "span 2" $+ \f x -> let (y, _) = span (applyFun f) x in+ T.all (applyFun f) (toText y)+ , testProperty "span 3" $+ \f x -> let (_, z) = span (applyFun f) x in+ null z || not (applyFun f (T.head (toText z)))++ , testProperty "splitAtLine 1" $+ \i x -> let (y, z) = splitAtLine i x in x === y <> z+ , testProperty "splitAtLine 2" $+ \i x -> let (y, z) = splitAtLine i x in lines x === lines y <> lines z+ , testProperty "splitAtLine 3" $+ \i x -> let (y, _) = splitAtLine i x in+ L.genericLength (lines y) === min i (L.genericLength (lines x))++ , testProperty "length" $+ \x -> length x === fromIntegral (T.length (toText x))+ , testProperty "splitAt 1" $+ \i x -> let (y, z) = splitAt i x in x === y <> z+ , testProperty "splitAt 2" $+ \i x -> let (y, _) = splitAt i x in+ length y === min i (length x)++ , testProperty "lengthAsPosition 1" $+ \x -> splitAtPosition (lengthAsPosition x) x === (x, mempty)+ , testProperty "lengthAsPosition 2" $+ \x -> let Position l c = lengthAsPosition x in+ length (snd (splitAtLine l x)) === c++ , testProperty "splitAtPosition 1" $+ \i x -> let (y, z) = splitAtPosition i x in x === y <> z+ , testProperty "splitAtPosition 2" $+ \i x -> let (y, z) = splitAtPosition i x in+ lengthAsPosition x === lengthAsPosition y <> lengthAsPosition z+ , testProperty "splitAtPosition 3" $+ \i@(Position l _) x -> let (y, _) = splitAtPosition i x in+ let l' = min l (posLine (lengthAsPosition x)) in+ posLine (lengthAsPosition y) >= l'+ , testProperty "splitAtPosition 4" $+ \i@(Position l c) x -> let (y, z) = splitAtPosition i x in+ null z .||. length (snd (splitAtLine l y)) === c+ , testProperty "splitAtPosition 5" $+ \i -> let (y, z) = splitAtPosition i mempty in y === mempty .&&. z === mempty+ ]
+ test/CharRope.hs view
@@ -0,0 +1,51 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++module CharRope+ ( testSuite+ ) where++import Prelude ()+import Data.Function (($))+import Data.Semigroup ((<>))+import qualified Data.Text.Lines as Lines+import qualified Data.Text.Rope as Rope+import Test.Tasty (testGroup, TestTree)+import Test.Tasty.QuickCheck (testProperty, (===), (.&&.))++import Utils ()++testSuite :: TestTree+testSuite = testGroup "Char Rope"+ [ testProperty "null" $+ \x -> Rope.null x === Lines.null (Rope.toTextLines x)++ , testProperty "length" $+ \x -> Rope.length x === Lines.length (Rope.toTextLines x)++ , testProperty "lengthInLines" $+ \x -> Rope.lengthInLines x === Lines.lengthInLines (Rope.toTextLines x)++ , testProperty "lines" $+ \x -> Rope.lines x === Lines.lines (Rope.toTextLines x)++ , testProperty "splitAtLine" $+ \i x -> let (y, z) = Rope.splitAtLine i x in+ (Rope.toTextLines y, Rope.toTextLines z) === Lines.splitAtLine i (Rope.toTextLines x)++ , testProperty "splitAt 1" $+ \i x -> case Rope.splitAt i x of+ (y, z) -> x === y <> z+ , testProperty "splitAt 2" $+ \i x -> case (Rope.splitAt i x, Lines.splitAt i (Lines.fromText $ Rope.toText x)) of+ ((y, z), (y', z')) -> Lines.fromText (Rope.toText y) === y' .&&. Lines.fromText (Rope.toText z) === z'++ , testProperty "splitAtPosition 1" $+ \i x -> case Rope.splitAtPosition i x of+ (y, z) -> x === y <> z+ , testProperty "splitAtPosition 2" $+ \i x -> case (Rope.splitAtPosition i x, Lines.splitAtPosition i (Lines.fromText $ Rope.toText x)) of+ ((y, z), (y', z')) -> Lines.fromText (Rope.toText y) === y' .&&. Lines.fromText (Rope.toText z) === z'+ ]
+ test/Main.hs view
@@ -0,0 +1,26 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++module Main+ ( main+ ) where++import qualified CharLines+import qualified CharRope+import qualified Utf16Lines+import qualified Utf16Rope++import Prelude ()+import Data.Function (($))+import System.IO (IO)+import Test.Tasty (defaultMain, testGroup)++main :: IO ()+main = defaultMain $ testGroup "All"+ [ CharLines.testSuite+ , CharRope.testSuite+ , Utf16Lines.testSuite+ , Utf16Rope.testSuite+ ]
+ test/Utf16Lines.hs view
@@ -0,0 +1,118 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++module Utf16Lines+ ( testSuite+ ) where++import Prelude ((+), (-), maxBound)+import Data.Bool (Bool(..), (&&))+import Data.Function (($))+import qualified Data.List as L+import Data.Maybe (Maybe(..), isJust)+import Data.Monoid (mempty)+import Data.Ord (min, (>=), (<))+import Data.Semigroup ((<>))+import qualified Data.Text as T+import Data.Text.Utf16.Lines+import Data.Tuple (snd)+import Test.Tasty (testGroup, TestTree)+import Test.Tasty.QuickCheck (testProperty, (===), property, (.||.), (.&&.), (==>))++import Utils++testSuite :: TestTree+testSuite = testGroup "Utf16 Lines"+ [ testProperty "toText . fromText" $+ \x -> toText (fromText x) === x++ , testProperty "null" $+ \x -> null x === T.null (toText x)++ , testProperty "TextLines associativity" $+ \x y z -> (x <> y) <> z === x <> (y <> z :: TextLines)+ , testProperty "TextLines mempty <>" $+ \x -> mempty <> x === (x :: TextLines)+ , testProperty "TextLines <> mempty" $+ \x -> x <> mempty === (x :: TextLines)++ , testProperty "Position associativity" $+ \x y z -> posLine x < maxBound - posLine y && posLine y < maxBound - posLine z ==>+ (x <> y) <> z === x <> (y <> z :: Position)+ , testProperty "Position mempty <>" $+ \x -> mempty <> x === (x :: Position)+ , testProperty "Position <> mempty" $+ \x -> x <> mempty === (x :: Position)++ , testProperty "lines" $+ \x -> T.lines x === lines (fromText x)+ , testProperty "lengthInLines" $+ \x -> L.genericLength (T.lines x) === lengthInLines (fromText x)++ , testProperty "splitAtLine 1" $+ \i x -> let (y, z) = splitAtLine i x in x === y <> z+ , testProperty "splitAtLine 2" $+ \i x -> let (y, z) = splitAtLine i x in lines x === lines y <> lines z+ , testProperty "splitAtLine 3" $+ \i x -> let (y, _) = splitAtLine i x in+ L.genericLength (lines y) === min i (L.genericLength (lines x))++ , testProperty "length 1" $+ \x -> length x === utf16Length (toText x)+ , testProperty "length 2" $+ length (fromText (T.singleton '\xffff')) === 1+ , testProperty "length 3" $+ length (fromText (T.singleton '\x10000')) === 2++ , testProperty "splitAt 1" $+ \i x -> case splitAt i x of+ Nothing -> property True+ Just (y, z) -> x === y <> z+ , testProperty "splitAt 2" $+ \i x -> case splitAt i x of+ Nothing -> property True+ Just (y, _) -> utf16Length (toText y) === min i (utf16Length (toText x))+ , testProperty "splitAt 3" $+ \i x -> case splitAt i x of+ Just{} -> True+ Nothing -> isJust (splitAt (i - 1) x) && isJust (splitAt (i + 1) x)+ , testProperty "splitAt 4" $ let t = fromText (T.singleton '\xffff') in+ splitAt 1 t === Just (t, mempty)+ , testProperty "splitAt 5" $ let t = fromText (T.singleton '\x10000') in+ splitAt 1 t === Nothing++ , testProperty "lengthAsPosition 1" $+ \x -> splitAtPosition (lengthAsPosition x) x === Just (x, mempty)+ , testProperty "lengthAsPosition 2" $+ \x -> let Position l c = lengthAsPosition x in+ length (snd (splitAtLine l x)) === c++ , testProperty "splitAtPosition 1" $+ \i x -> case splitAtPosition i x of+ Nothing -> property True+ Just (y, z) -> x === y <> z+ , testProperty "splitAtPosition 2" $+ \i x -> case splitAtPosition i x of+ Nothing -> property True+ Just (y, z) -> lengthAsPosition x === lengthAsPosition y <> lengthAsPosition z+ , testProperty "splitAtPosition 3" $+ \i@(Position l _) x -> case splitAtPosition i x of+ Nothing -> True+ Just (y, _) ->+ let l' = min l (posLine (lengthAsPosition x)) in+ posLine (lengthAsPosition y) >= l'+ , testProperty "splitAtPosition 4" $+ \i@(Position l c) x -> case splitAtPosition i x of+ Nothing -> property True+ Just (y, z) -> null z .||. length (snd (splitAtLine l y)) === c+ , testProperty "splitAtPosition 5" $+ \i -> case splitAtPosition i mempty of+ Nothing -> property False+ Just (y, z) -> y === mempty .&&. z === mempty+ , testProperty "splitAtPosition 6" $+ \i x -> case splitAtPosition i x of+ Just{} -> True+ Nothing -> isJust (splitAtPosition (i <> Position 0 1) x)+ ]
+ test/Utf16Rope.hs view
@@ -0,0 +1,69 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++module Utf16Rope+ ( testSuite+ ) where++import Prelude ((+), (-))+import Data.Bool (Bool(..), (&&))+import Data.Function (($))+import Data.Maybe (Maybe(..), isJust)+import Data.Semigroup ((<>))+import qualified Data.Text.Utf16.Lines as Lines +import qualified Data.Text.Utf16.Rope as Rope+import Test.Tasty (testGroup, TestTree)+import Test.Tasty.QuickCheck (testProperty, (===), property, (.&&.), counterexample)++import Utils ()++testSuite :: TestTree+testSuite = testGroup "Utf16 Rope"+ [ testProperty "null" $+ \x -> Rope.null x === Lines.null (Rope.toTextLines x)++ , testProperty "length" $+ \x -> Rope.length x === Lines.length (Rope.toTextLines x)++ , testProperty "lengthInLines" $+ \x -> Rope.lengthInLines x === Lines.lengthInLines (Rope.toTextLines x)++ , testProperty "lines" $+ \x -> Rope.lines x === Lines.lines (Rope.toTextLines x)++ , testProperty "splitAtLine" $+ \i x -> let (y, z) = Rope.splitAtLine i x in+ (Rope.toTextLines y, Rope.toTextLines z) === Lines.splitAtLine i (Rope.toTextLines x)++ , testProperty "splitAt 1" $+ \i x -> case Rope.splitAt i x of+ Nothing -> property True+ Just (y, z) -> x === y <> z+ , testProperty "splitAt 2" $+ \i x -> case (Rope.splitAt i x, Lines.splitAt i (Lines.fromText $ Rope.toText x)) of+ (Nothing, Nothing) -> property True+ (Nothing, Just{}) -> counterexample "can split TextLines, but not Rope" False+ (Just{}, Nothing) -> counterexample "can split Rope, but not TextLines" False+ (Just (y, z), Just (y', z')) -> Lines.fromText (Rope.toText y) === y' .&&. Lines.fromText (Rope.toText z) === z'+ , testProperty "splitAt 3" $+ \i x -> case Rope.splitAt i x of+ Just{} -> True+ Nothing -> isJust (Rope.splitAt (i - 1) x) && isJust (Rope.splitAt (i + 1) x)++ , testProperty "splitAtPosition 1" $+ \i x -> case Rope.splitAtPosition i x of+ Nothing -> property True+ Just (y, z) -> x === y <> z+ , testProperty "splitAtPosition 2" $+ \i x -> case (Rope.splitAtPosition i x, Lines.splitAtPosition i (Lines.fromText $ Rope.toText x)) of+ (Nothing, Nothing) -> property True+ (Nothing, Just{}) -> counterexample "can split TextLines, but not Rope" False+ (Just{}, Nothing) -> counterexample "can split Rope, but not TextLines" False+ (Just (y, z), Just (y', z')) -> Lines.fromText (Rope.toText y) === y' .&&. Lines.fromText (Rope.toText z) === z'+ , testProperty "splitAtPosition 3" $+ \i x -> case Rope.splitAtPosition i x of+ Just{} -> True+ Nothing -> isJust (Rope.splitAtPosition (i <> Lines.Position 0 1) x)+ ]
+ test/Utils.hs view
@@ -0,0 +1,101 @@+-- |+-- Copyright: (c) 2021-2022 Andrew Lelechenko+-- Licence: BSD3+-- Maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>++{-# OPTIONS_GHC -fno-warn-orphans #-}++module Utils+ ( utf16Length+ ) where++import Prelude (mod, (+), (-), maxBound)+import Control.Applicative (pure, (<$>), (<*>))+import Data.Char (Char)+import Data.Function (($), (.))+import qualified Data.List as L+import Data.Ord ((>))+import qualified Data.Text as T+import Data.Text.Internal (Text(..))+import qualified Data.Text.Lines as Char+import qualified Data.Text.Rope as CharRope+import qualified Data.Text.Utf16.Lines as Utf16+import qualified Data.Text.Utf16.Rope as Utf16Rope+import Data.Word (Word)+import Test.Tasty.QuickCheck (Gen, Arbitrary (arbitrary), arbitrary, shrink, frequency, arbitraryASCIIChar, arbitraryUnicodeChar, listOf, oneof)+import Data.Monoid (mconcat, mappend)+import Data.Bool (otherwise)+import Data.Maybe (maybe)++utf16Length :: Text -> Word+utf16Length t = L.genericLength xs + L.genericLength (L.filter (> '\xFFFF') xs)+ where+ xs = T.unpack t++charGen :: Gen Char+charGen = frequency+ [ (1, pure '\n')+ , (1, arbitraryASCIIChar)+ , (1, arbitraryUnicodeChar)+ ]++instance Arbitrary Text where+ arbitrary = do+ xs <- T.pack <$> listOf charGen+ d <- (`mod` (T.length xs + 1)) <$> arbitrary+ pure $ T.drop d xs+ shrink t@(Text arr off len)+ = L.map (T.drop d . T.pack) (shrink ys)+ L.++ L.map (\d' -> T.drop d' $ T.pack $ L.drop (d - d') ys) (shrink d)+ where+ xs = T.unpack t+ ys = T.unpack (Text arr 0 (off + len))+ d = L.length ys - L.length xs++instance Arbitrary Char.TextLines where+ arbitrary = Char.fromText <$> arbitrary+ shrink = L.map Char.fromText . shrink . Char.toText++instance Arbitrary Utf16.TextLines where+ arbitrary = Utf16.fromText <$> arbitrary+ shrink = L.map Utf16.fromText . shrink . Utf16.toText++instance Arbitrary Char.Position where+ arbitrary = oneof+ [ Char.Position <$> arbitrary <*> arbitrary+ , (\l -> Char.Position (maxBound - l)) <$> arbitrary <*> arbitrary+ , (\l c -> Char.Position l (maxBound - c)) <$> arbitrary <*> arbitrary+ , (\l c -> Char.Position (maxBound - l) (maxBound - c)) <$> arbitrary <*> arbitrary+ ]+ shrink (Char.Position x y) =+ [Char.Position x' y | x' <- shrink x] L.++ [Char.Position x y' | y' <- shrink y]++instance Arbitrary Utf16.Position where+ arbitrary = oneof+ [ Utf16.Position <$> arbitrary <*> arbitrary+ , (\l -> Utf16.Position (maxBound - l)) <$> arbitrary <*> arbitrary+ , (\l c -> Utf16.Position l (maxBound - c)) <$> arbitrary <*> arbitrary+ , (\l c -> Utf16.Position (maxBound - l) (maxBound - c)) <$> arbitrary <*> arbitrary+ ]+ shrink (Utf16.Position x y) =+ [Utf16.Position x' y | x' <- shrink x] L.++ [Utf16.Position x y' | y' <- shrink y]++instance Arbitrary CharRope.Rope where+ arbitrary = frequency+ [ (9, mconcat . L.map CharRope.fromText <$> arbitrary)+ , (1, mappend <$> arbitrary <*> arbitrary)+ ]+ shrink rp+ | CharRope.null rp = []+ | otherwise = L.concatMap (\i -> (\(x, y) -> [x, y]) (CharRope.splitAt i rp))+ [1..CharRope.length rp - 1]++instance Arbitrary Utf16Rope.Rope where+ arbitrary = frequency+ [ (9, mconcat . L.map Utf16Rope.fromText <$> arbitrary)+ , (1, mappend <$> arbitrary <*> arbitrary)+ ]+ shrink rp+ | Utf16Rope.null rp = []+ | otherwise = L.concatMap (\i -> maybe [] (\(x, y) -> [x, y]) (Utf16Rope.splitAt i rp))+ [1..Utf16Rope.length rp - 1]
+ text-rope.cabal view
@@ -0,0 +1,88 @@+name: text-rope+version: 0.1+cabal-version: >=1.10+build-type: Simple+license: BSD3+license-file: LICENSE+copyright: 2021-2022 Andrew Lelechenko+maintainer: Andrew Lelechenko <andrew.lelechenko@gmail.com>+homepage: https://github.com/Bodigrim/text-rope+category: Text+synopsis: Text lines and ropes+description:+ A wrapper around `Text` for fast line/column navigation and logarithmic concatenation.+author: Andrew Lelechenko <andrew.lelechenko@gmail.com>+extra-source-files:+ changelog.md+ README.md+data-files:+ bench/bench.txt++tested-with: GHC == 9.2.1, GHC==9.0.2, GHC==8.10.7, GHC==8.8.4, GHC==8.6.5, GHC==8.4.4, GHC==8.2.2, GHC==8.0.2++source-repository head+ type: git+ location: git://github.com/Bodigrim/text-rope.git++flag debug+ default: False+ manual: True+ description: Build library with sanity checks enabled.++library+ exposed-modules:+ Data.Text.Lines+ Data.Text.Rope+ Data.Text.Utf16.Lines+ Data.Text.Utf16.Rope+ other-modules:+ Data.Text.Lines.Internal+ build-depends:+ base >=4.9 && <5,+ deepseq,+ text >= 1.2.3,+ vector >=0.11+ default-language: Haskell2010+ hs-source-dirs: src+ ghc-options: -O2 -Wall -Wcompat+ if flag(debug)+ cpp-options: -DDEBUG+ c-sources:+ cbits/utils.c++test-suite text-rope-tests+ type: exitcode-stdio-1.0+ main-is: Main.hs+ other-modules:+ CharLines+ CharRope+ Utf16Lines+ Utf16Rope+ Utils+ build-depends:+ base,+ text-rope,+ tasty,+ tasty-quickcheck,+ text+ default-language: Haskell2010+ hs-source-dirs: test+ ghc-options: -Wall -threaded -rtsopts -Wcompat "-with-rtsopts -N"++benchmark text-rope-bench+ type: exitcode-stdio-1.0+ main-is: Main.hs+ other-modules:+ Paths_text_rope+ hs-source-dirs: bench+ ghc-options: -O2 -rtsopts+ build-depends:+ base,+ -- core-text,+ text-rope,+ random,+ -- yi-rope,+ -- rope-utf16-splay,+ tasty-bench >= 0.3,+ text+ default-language: Haskell2010