diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,12 @@ # Changelog +## 0.4.6.1 (2026-07-06) + +### Fixed + +- Object streams whose entries mix dictionaries and arrays (e.g. page-tree nodes stored in a single ObjStm) no longer leave intermediate `/Pages` nodes unresolved; page 1 and document order match the PDF catalog again. +- `hpdft.cabal`: `cabal-version` lowered to 3.8 and dependency bounds widened for GHC 9.8 (Hackage docbuilder compatibility). + ## 0.4.6.0 (2026-07-05) ### Changed diff --git a/hpdft.cabal b/hpdft.cabal --- a/hpdft.cabal +++ b/hpdft.cabal @@ -1,6 +1,6 @@ -cabal-version: 3.12 +cabal-version: 3.8 name: hpdft -version: 0.4.6.0 +version: 0.4.6.1 synopsis: PDF parsing library and CLI for text, layout, diff, images, and forms description: hpdft is a Haskell library and command-line tool for parsing PDF files. @@ -67,22 +67,22 @@ other-modules: Paths_hpdft other-extensions: OverloadedStrings build-depends: attoparsec >= 0.14.4 && < 0.15 - , base >= 4.20.0 && < 4.23 + , base >= 4.18.0 && < 4.23 , binary >= 0.8.9 && < 0.9 - , bytestring >= 0.11.5 && < 0.13 - , containers >= 0.7 && < 0.9 + , bytestring >= 0.11.4 && < 0.13 + , containers >= 0.6.7 && < 0.9 , crypton >= 0.34 && < 0.36 - , directory >= 1.3.9 && < 1.4 + , directory >= 1.3.8 && < 1.4 , dlist >= 1.0 && < 1.1 , file-embed >= 0.0.16 && < 0.1 - , filepath >= 1.5.2 && < 1.6 + , filepath >= 1.4.2 && < 1.6 , memory >= 0.18.0 && < 0.19 , optparse-applicative >= 0.18.1 && < 0.19 , parallel >= 3.2.2 && < 3.4 , deepseq >= 1.4.8 && < 1.6 , parsec >= 3.1.18 && < 3.2 , semigroups >= 0.20 && < 0.21 - , text >= 2.1.2 && < 2.2.2 + , text >= 2.0.2 && < 2.2.2 , utf8-string >= 1.0.2 && < 1.1 , zlib >= 0.7.1 && < 0.8 autogen-modules: Paths_hpdft @@ -98,8 +98,8 @@ , TuiScroll other-extensions: OverloadedStrings build-depends: array >= 0.5 && < 0.6 - , base >= 4.20.0 && < 4.23 - , bytestring >= 0.11.5 && < 0.13 + , base >= 4.18.0 && < 4.23 + , bytestring >= 0.11.4 && < 0.13 , hpdft , memory >= 0.18.0 && < 0.19 , optparse-applicative >= 0.18.1 && < 0.19 @@ -107,7 +107,7 @@ , regex-tdfa >= 1.3.2 && < 1.4 , semigroups >= 0.20 && < 0.21 , terminal-size >= 0.3 && < 0.4 - , text >= 2.1.2 && < 2.2.2 + , text >= 2.0.2 && < 2.2.2 , utf8-string >= 1.0.2 && < 1.1 autogen-modules: Paths_hpdft default-language: Haskell2010 @@ -118,10 +118,10 @@ main-is: Golden.hs hs-source-dirs: test ghc-options: -threaded -rtsopts "-with-rtsopts=-N -A64m" - build-depends: base >= 4.20.0 && < 4.23 - , bytestring >= 0.11.5 && < 0.13 - , directory >= 1.3.9 && < 1.4 - , filepath >= 1.5.2 && < 1.6 + build-depends: base >= 4.18.0 && < 4.23 + , bytestring >= 0.11.4 && < 0.13 + , directory >= 1.3.8 && < 1.4 + , filepath >= 1.4.2 && < 1.6 , hpdft default-language: Haskell2010 @@ -131,32 +131,32 @@ hs-source-dirs: test , . ghc-options: -threaded -rtsopts "-with-rtsopts=-N -A64m" - build-depends: base >= 4.20.0 && < 4.23 - , bytestring >= 0.11.5 && < 0.13 - , containers >= 0.7 && < 0.9 - , directory >= 1.3.9 && < 1.4 - , filepath >= 1.5.2 && < 1.6 + build-depends: base >= 4.18.0 && < 4.23 + , bytestring >= 0.11.4 && < 0.13 + , containers >= 0.6.7 && < 0.9 + , directory >= 1.3.8 && < 1.4 + , filepath >= 1.4.2 && < 1.6 , hpdft - , text >= 2.1.2 && < 2.2.2 + , text >= 2.0.2 && < 2.2.2 other-modules: TuiScroll default-language: Haskell2010 executable interpret-page main-is: scripts/interpret_page.hs hs-source-dirs: . - build-depends: base >= 4.20.0 && < 4.23 + build-depends: base >= 4.18.0 && < 4.23 , hpdft - , text >= 2.1.2 && < 2.2.2 + , text >= 2.0.2 && < 2.2.2 default-language: Haskell2010 buildable: True executable extract-text main-is: Main.hs hs-source-dirs: examples/extract-text - build-depends: base >= 4.20.0 && < 4.23 - , bytestring >= 0.11.5 && < 0.13 - , directory >= 1.3.9 && < 1.4 - , filepath >= 1.5.2 && < 1.6 + build-depends: base >= 4.18.0 && < 4.23 + , bytestring >= 0.11.4 && < 0.13 + , directory >= 1.3.8 && < 1.4 + , filepath >= 1.4.2 && < 1.6 , hpdft default-language: Haskell2010 buildable: True @@ -164,10 +164,10 @@ executable page-api main-is: Main.hs hs-source-dirs: examples/page-api - build-depends: base >= 4.20.0 && < 4.23 - , directory >= 1.3.9 && < 1.4 - , filepath >= 1.5.2 && < 1.6 + build-depends: base >= 4.18.0 && < 4.23 + , directory >= 1.3.8 && < 1.4 + , filepath >= 1.4.2 && < 1.6 , hpdft - , text >= 2.1.2 && < 2.2.2 + , text >= 2.0.2 && < 2.2.2 default-language: Haskell2010 buildable: True diff --git a/src/PDF/ContentStream.hs b/src/PDF/ContentStream.hs --- a/src/PDF/ContentStream.hs +++ b/src/PDF/ContentStream.hs @@ -336,11 +336,44 @@ hexletters :: PSParser T.Text hexletters = do + st <- getState char '<' - lets <- manyTill hexletter (try $ char '>') + hexChars <- many (oneOf "0123456789ABCDEFabcdef") + char '>' spaces - return $ T.concat lets + let cmap = Map.findWithDefault Map.empty (curfont st) (cmaps st) + codes = hexStringToCodes (fontBytesPerCode st) hexChars + parts <- mapM (lookupUcs cmap) codes + return $ T.concat parts +-- | Split a hex string into character codes (matches 'PDF.Interpret.hexPairs' +-- and 'bytesToCodes' for 1- vs 2-byte fonts). +fontBytesPerCode :: PSR -> Int +fontBytesPerCode st = + case Map.lookup (curfont st) (fontmaps st) of + Just (CIDmap _) -> 2 + _ -> 1 + +hexStringToCodes :: Int -> String -> [Int] +hexStringToCodes bpc hex = + let bytes = hexPairs hex + in if bpc == 2 then pairBytes bytes else bytes + where + pairBytes [] = [] + pairBytes [_] = [] + pairBytes (a:b:rest) = (a * 256 + b) : pairBytes rest + +hexPairs :: String -> [Int] +hexPairs [] = [] +hexPairs [x] = + case readHex [x, '0'] of + [(n, "")] -> [n] + _ -> [] +hexPairs (a:b:rest) = + case readHex [a, b] of + [(n, "")] -> n : hexPairs rest + _ -> hexPairs rest + octletters :: PSParser T.Text octletters = do char '(' @@ -374,14 +407,13 @@ hexletter :: PSParser T.Text hexletter = do st <- getState - let font = curfont st - cmap = Map.findWithDefault Map.empty font (cmaps st) - hexDigits <- choice [ try $ count 4 $ oneOf "0123456789ABCDEFabcdef" - , try $ count 2 $ oneOf "0123456789ABCDEFabcdef" + let cmap = Map.findWithDefault Map.empty (curfont st) (cmaps st) + -- Single code inside a hex string fragment (legacy path; prefer hexletters). + hexDigits <- choice [ try $ count 2 $ oneOf "0123456789ABCDEFabcdef" , try $ (:"0") <$> (oneOf "0123456789ABCDEFabcdef") ] case readHex hexDigits of - [(h,"")] -> lookupUcs cmap h + [(h, "")] -> lookupUcs cmap h _ -> return "????" octletter :: PSParser T.Text diff --git a/src/PDF/DocumentStructure.hs b/src/PDF/DocumentStructure.hs --- a/src/PDF/DocumentStructure.hs +++ b/src/PDF/DocumentStructure.hs @@ -47,7 +47,7 @@ import qualified Data.ByteString.Lazy.Char8 as BSL import qualified Data.ByteString.Builder as B import qualified Data.Text as T -import Data.Maybe (fromMaybe) +import Data.Maybe (fromMaybe, listToMaybe) import Numeric (readDec) import Data.Attoparsec.ByteString.Char8 hiding (take, isDigit) @@ -114,7 +114,7 @@ objs = M.mapWithKey resolve xref containerCache = M.fromList - [ (cnum, objStmEntries cnum) + [ (cnum, objStmBody cnum) | cnum <- nub [c | InObjStm c _ <- M.elems xref] ] resolve objNum (InFile off) = @@ -122,21 +122,19 @@ in snd (parsePDFObj msec (objNum, body)) resolve objNum (InObjStm cnum idx) = case M.lookup cnum containerCache of - Just entries -> - case lookup objNum entries of - Just o -> o - Nothing -> - case drop idx entries of - ((_, o) : _) -> o - _ -> [PdfNull] + Just (locations, body) -> + let off = case listToMaybe (drop idx locations) of + Just (_, o) -> Just o + Nothing -> lookup objNum locations + in maybe [PdfNull] (parseObjStmObject body) off Nothing -> [PdfNull] - objStmEntries cnum = + objStmBody cnum = case rawStream msec cnum (M.findWithDefault [PdfNull] cnum objs) of Right streamBytes -> - case pdfObjStm cnum (BSL.toStrict streamBytes) of - Right entries -> entries - Left _ -> [] - Left _ -> [] + case parseObjStmHeader (BSL.toStrict streamBytes) of + Right cache -> cache + Left _ -> ([], BS.empty) + Left _ -> ([], BS.empty) buildIndexEager :: BS.ByteString -> Maybe Security -> PdfResult PDFObjIndex buildIndexEager bytes msec = do @@ -672,20 +670,32 @@ _ -> fail "invalid object stream reference" pdfObjStm n s = - case parseOnly refOffset s of - Right (location, objstr) -> - mapM (\(r,o) -> (,) r <$> parseDict (BS.pack $ drop o objstr)) location + case parseObjStmHeader s of + Right (location, body) -> + Right [ (r, parseObjStmObject body o) | (r, o) <- location ] Left err -> Left (ParseError ("Failed to parse Object Stream: " ++ show err) (BS.take 80 s)) - where parseDict s' = case parseOnly pdfdictionary s' of - Right obj -> Right [obj] - Left _ -> case parseOnly pdfarray s' of - Right obj -> Right [obj] - Left _ -> case parseOnly pdfletters s' of - Right obj -> Right [obj] - Left err -> - Left (ParseError ((show err) ++ ": Failed to parse obj around") - (BS.take 100 s')) + +parseObjStmHeader :: BS.ByteString -> Either String ([(Int, Int)], BS.ByteString) +parseObjStmHeader s = + case parseOnly refOffset s of + Right (location, objstr) -> Right (location, BS.pack objstr) + Left err -> Left (show err) + +parseObjStmObject :: BS.ByteString -> Int -> [Obj] +parseObjStmObject body off = + case parseObjStmValue (BS.drop off body) of + Right obj -> obj + Left _ -> [PdfNull] + +parseObjStmValue :: BS.ByteString -> Either String [Obj] +parseObjStmValue s' = case parseOnly pdfdictionary s' of + Right obj -> Right [obj] + Left _ -> case parseOnly pdfarray s' of + Right obj -> Right [obj] + Left _ -> case parseOnly pdfletters s' of + Right obj -> Right [obj] + Left err -> Left (show err) -- make fontmap from page's /Resources (see 3.7.2 of PDF Ref.)