From b4384b848bec9d241bd0cdc97071fecd3b2ddb85 Mon Sep 17 00:00:00 2001
From: Vladislav Zavialov <vlad.z.4096@gmail.com>
Date: Wed, 1 Jan 2025 15:21:06 +0300
Subject: [PATCH] [#311] Fix a "resource exhausted" crash

Problem: xrefcheck was crashing on repositories containing a large
number of Markdown files, reporting the following internal error:
  openBinaryFile: resource exhausted (Too many open files)

Solution: use strict file IO (BS.readFile instead of BS.L.readFile) to
ensure that file handles are released in a timely fashion.
---
 CHANGES.md                         |  4 ++++
 src/Xrefcheck/Scanners/Markdown.hs | 10 ++++------
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/CHANGES.md b/CHANGES.md
index ce10154e..3c6fd7ee 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -7,6 +7,10 @@
 Unreleased
 ==========
 
+* [#311](https://github.com/serokell/xrefcheck/issues/311)
+  + Fix a "resource exhausted" crash on repositories containing a large number
+    of Markdown files.
+
 0.3.0
 ==========
 
diff --git a/src/Xrefcheck/Scanners/Markdown.hs b/src/Xrefcheck/Scanners/Markdown.hs
index a6872315..6264e42c 100644
--- a/src/Xrefcheck/Scanners/Markdown.hs
+++ b/src/Xrefcheck/Scanners/Markdown.hs
@@ -23,11 +23,10 @@ import CMarkGFM
 import Control.Lens (_Just, makeLenses, makeLensesFor, use, (.=))
 import Control.Monad.Trans.Writer.CPS (Writer, runWriter, tell)
 import Data.Aeson (FromJSON (..), genericParseJSON)
-import Data.ByteString.Lazy qualified as BSL
+import Data.ByteString qualified as BS
 import Data.DList qualified as DList
 import Data.Reflection (Given)
 import Data.Text qualified as T
-import Data.Text.Lazy qualified as LT
 import Fmt (Buildable (..), nameF)
 import Text.HTML.TagSoup
 import Text.Interpolation.Nyan
@@ -409,18 +408,17 @@ textToMode ("ignore" : [x])
   | otherwise        = InvalidMode x
 textToMode _         = NotAnAnnotation
 
-parseFileInfo :: MarkdownConfig -> String -> LT.Text -> (FileInfo, [ScanError 'Parse])
+parseFileInfo :: MarkdownConfig -> String -> T.Text -> (FileInfo, [ScanError 'Parse])
 parseFileInfo config pathForPrinting input
   = runWriter
   $ flip runReaderT (ExtractorCtx config pathForPrinting)
   $ nodeExtractInfo
-  $ commonmarkToNode [optFootnotes] [extAutolink]
-  $ toStrict input
+  $ commonmarkToNode [optFootnotes] [extAutolink] input
 
 markdownScanner :: Given PrintUnixPaths => MarkdownConfig -> ScanAction
 markdownScanner config root relativePath =
   parseFileInfo config pathForPrinting . decodeUtf8
-    <$> BSL.readFile rootedPath
+    <$> BS.readFile rootedPath
   where
     rootedPath = filePathFromRoot root relativePath
     pathForPrinting = mkPathForPrinting rootedPath