Pdftotext.Internal

Internal functions.

Types

newtype Document

Constructors

Document (ForeignPtr Poppler_Document)

data Layout

Layout of text extracted from PDF.

Constructors

Physical

Text emulates layout of PDF, including horizontal spaces, and preserves hyphenation; corresponds to calling pdftotext -layout

Raw

Discards horizontal spaces, preserves hyphenation; corresponds to calling pdftotext -raw

None

Discards horizontal spaces, removes hyphenation; corresponds to calling pdftotext without layout argument

Instances

Eq Layout

Defined in Pdftotext.Internal

Methods

(==) :: Layout -> Layout -> Bool

(/=) :: Layout -> Layout -> Bool

Show Layout

Defined in Pdftotext.Internal

Methods

showsPrec :: Int -> Layout -> ShowS

show :: Layout -> String

showList :: [Layout] -> ShowS

data Page

Constructors

Page

Fields

• pageNumber :: Int

  Number of this page in original document.

• pageOutOf :: Int

  Total number of pages in original document.

• pageDocumentPtr :: ForeignPtr Poppler_Document

  Pointer to document which created this page.

• pagePtr :: ForeignPtr Poppler_Page

  Pointer to this page.

Instances

Show Page

Defined in Pdftotext.Internal

Methods

showsPrec :: Int -> Page -> ShowS

show :: Page -> String

showList :: [Page] -> ShowS

data Properties

Document properties.

Since: 0.0.2.0

Constructors

Properties

Fields

• author :: Maybe Text
• creator :: Maybe Text
• keywords :: Maybe Text
• metadata :: Maybe Text
• producer :: Maybe Text
• subject :: Maybe Text
• title :: Maybe Text

Instances

Show Properties

Defined in Pdftotext.Internal

Methods

showsPrec :: Int -> Properties -> ShowS

show :: Properties -> String

showList :: [Properties] -> ShowS

Generic Properties

Defined in Pdftotext.Internal

Associated Types

type Rep Properties :: Type -> Type

Methods

from :: Properties -> Rep Properties x

to :: Rep Properties x -> Properties

type Rep Properties

Defined in Pdftotext.Internal

type Rep Properties = D1 ('MetaData "Properties" "Pdftotext.Internal" "pdftotext-0.1.0.1-inplace" 'False) (C1 ('MetaCons "Properties" 'PrefixI 'True) ((S1 ('MetaSel ('Just "author") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)) :*: (S1 ('MetaSel ('Just "creator") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "keywords") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)))) :*: ((S1 ('MetaSel ('Just "metadata") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "producer") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text))) :*: (S1 ('MetaSel ('Just "subject") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "title") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 (Maybe Text))))))

Loading PDF's

openByteStringIO :: ByteString -> IO (Maybe Document)

Open PDF represented as bytestring. If document cannot be parsed as valid PDF, Nothing is returned.

openFile :: FilePath -> IO (Maybe Document)

Open PDF from file. If file does not exist or cannot be parsed as valid PDF, Nothing is returned.

Document functions

pageIO :: Int -> Document -> IO (Maybe Page)

Return page number no from PDF document, if the page exists.

pagesIO :: Document -> IO [Page]

Return all pages from document.

pagesTotalIO :: Document -> IO Int

Return number of pages contained in document.

pdftotextIO :: Layout -> Document -> IO Text

Extract text from PDF document with given Layout.

propertiesIO :: Document -> IO Properties

Extract properties from the document.

Since: 0.0.2.0

Page functions

pageTextIO :: Layout -> Page -> IO Text

Extract text from a page with given Layout.