From 957314143faec08b4687822557dac6ac32216cb9 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 20 Mar 2019 12:22:17 -0700
Subject: [PATCH] Improve pdfSize in ImageSize.
Improves fix to #4322.
---
pandoc.cabal | 3 ++-
src/Text/Pandoc/ImageSize.hs | 45 ++++++++++++++++++++----------------
2 files changed, 27 insertions(+), 21 deletions(-)
diff --git a/pandoc.cabal b/pandoc.cabal
index 8adcf8d47..e3b890f64 100644
--- a/pandoc.cabal
+++ b/pandoc.cabal
@@ -404,7 +404,8 @@ library
case-insensitive >= 1.2 && < 1.3,
unicode-transforms >= 0.3 && < 0.4,
HsYAML >= 0.1.1.1 && < 0.2,
- ipynb >= 0.1 && < 0.2
+ ipynb >= 0.1 && < 0.2,
+ attoparsec >= 0.12 && < 0.14
if impl(ghc < 8.0)
build-depends: semigroups == 0.18.*,
-- basement 0.0.8 and foundation 0.0.21, transitive
diff --git a/src/Text/Pandoc/ImageSize.hs b/src/Text/Pandoc/ImageSize.hs
index 802959484..c5289bbc2 100644
--- a/src/Text/Pandoc/ImageSize.hs
+++ b/src/Text/Pandoc/ImageSize.hs
@@ -50,7 +50,9 @@ import qualified Text.Pandoc.UTF8 as UTF8
import qualified Text.XML.Light as Xml
import qualified Data.Map as M
import Control.Monad.Except
+import Control.Applicative
import Data.Maybe (fromMaybe)
+import qualified Data.Attoparsec.ByteString.Char8 as A
-- quick and dirty functions to get image sizes
-- algorithms borrowed from wwwis.pl
@@ -267,26 +269,29 @@ epsSize img = do
pdfSize :: ByteString -> Maybe ImageSize
pdfSize img =
- case dropWhile (\l -> not (l == "stream" ||
- "/MediaBox" `B.isPrefixOf` l)) (B.lines img) of
- (x:_)
- | "/MediaBox" `B.isPrefixOf` x
- -> case B.words . B.takeWhile (/=']')
- . B.drop 1
- . B.dropWhile (/='[')
- $ x of
- [x1, y1, x2, y2] -> do
- x1' <- safeRead $ B.unpack x1
- x2' <- safeRead $ B.unpack x2
- y1' <- safeRead $ B.unpack y1
- y2' <- safeRead $ B.unpack y2
- return ImageSize{
- pxX = x2' - x1'
- , pxY = y2' - y1'
- , dpiX = 72
- , dpiY = 72 }
- _ -> mzero
- _ -> mzero
+ case A.parseOnly pPdfSize img of
+ Left _ -> Nothing
+ Right sz -> Just sz
+
+pPdfSize :: A.Parser ImageSize
+pPdfSize = do
+ A.skipWhile (/='/')
+ A.char8 '/'
+ (do A.string "MediaBox"
+ A.char8 '['
+ [x1,y1,x2,y2] <- A.count 4 $ do
+ A.skipWhile (==' ')
+ raw <- A.many1 $ A.satisfy (\c -> isDigit c || c == '.')
+ case safeRead raw of
+ Just (r :: Double) -> return $ floor r
+ Nothing -> mzero
+ A.char8 ']'
+ return $ ImageSize{
+ pxX = x2 - x1
+ , pxY = y2 - y1
+ , dpiX = 72
+ , dpiY = 72 }
+ ) <|> pPdfSize
pngSize :: ByteString -> Maybe ImageSize
pngSize img = do