Struct lopdf::Document

pub struct Document {
    pub version: String,
    pub trailer: Dictionary,
    pub reference_table: Xref,
    pub objects: BTreeMap<ObjectId, Object>,
    pub max_id: u32,
    pub max_bookmark_id: u32,
    pub bookmarks: Vec<u32>,
    pub bookmark_table: HashMap<u32, Bookmark>,
    pub xref_start: usize,
}

A PDF document.

This can both be a combination of multiple incremental updates or just one (the last) incremental update in a PDF file.

Fields

version: String

The version of the PDF specification to which the file conforms.

trailer: Dictionary

The trailer gives the location of the cross-reference table and of certain special objects.

reference_table: Xref

The cross-reference table contains locations of the indirect objects.

objects: BTreeMap<ObjectId, Object>

The objects that make up the document contained in the file.

max_id: u32

Current maximum object id within the document.

max_bookmark_id: u32

Current maximum object id within Bookmarks.

bookmarks: Vec<u32>

The bookmarks in the document. Render at the very end of document after renumbering objects.

bookmark_table: HashMap<u32, Bookmark>

used to locate a stored Bookmark so children can be appended to it via its id. Otherwise we need to do recursive lookups and returns on the bookmarks internal layout Vec

xref_start: usize

The byte the cross-reference table starts at. This value is only set during reading, but not when writing the file. It is used to support incremental updates in PDFs. Default value is 0.

Implementations

impl Document

pub fn new() -> Self

Create new PDF document.

pub fn new_from_prev(prev: &Document) -> Self

Create a new PDF document that is an incremental update to a previous document.

pub fn adjust_zero_pages(&mut self)

Adjusts the Parents that have a ObjectId of (0,_) to that of their first child. will recurse through all entries till all parents of children are set. This should be ran before building the final bookmark objects but after renumbering of objects.

pub fn dereference<'a>( &'a self, object: &'a Object ) -> Result<(Option<ObjectId>, &'a Object)>

Follow references if the supplied object is a reference.

Returns a tuple of an optional object id and final object. The object id will be None if the object was not a reference. Otherwise, it will be the last object id in the reference chain.

pub fn get_object(&self, id: ObjectId) -> Result<&Object>

Get object by object id, will iteratively dereference a referenced object.

pub fn has_object(&self, id: ObjectId) -> bool

Determines if an object exists in the current document (or incremental update.) with the given ObjectId. true if the object exists, false if it does not exist.

pub fn get_object_mut(&mut self, id: ObjectId) -> Result<&mut Object>

Get mutable reference to object by object id, will iteratively dereference a referenced object.

pub fn get_object_page(&self, id: ObjectId) -> Result<ObjectId>

Get page object_id of the specified object object_id

pub fn get_dictionary(&self, id: ObjectId) -> Result<&Dictionary>

Get dictionary object by id.

pub fn get_dictionary_mut(&mut self, id: ObjectId) -> Result<&mut Dictionary>

Get a mutable dictionary object by id.

pub fn get_dict_in_dict( &self, node: &Dictionary, key: &[u8] ) -> Result<&Dictionary>

Get dictionary in dictionary by key.

pub fn traverse_objects<A: Fn(&mut Object)>( &mut self, action: A ) -> Vec<ObjectId>

Traverse objects from trailer recursively, return all referenced object IDs.

pub fn get_encrypted(&self) -> Result<&Dictionary>

Return dictionary with encryption information

pub fn is_encrypted(&self) -> bool

Return true is PDF document is encrypted

pub fn decrypt<P: AsRef<[u8]>>(&mut self, password: P) -> Result<()>

Replaces all encrypted Strings and Streams with their decrypted contents

pub fn catalog(&self) -> Result<&Dictionary>

Return the PDF document catalog, which is the root of the document’s object graph.

pub fn catalog_mut(&mut self) -> Result<&mut Dictionary>

Return a mutable reference to the PDF document catalog, which is the root of the document’s object graph.

pub fn get_pages(&self) -> BTreeMap<u32, ObjectId>

Get page numbers and corresponding object ids.

pub fn page_iter(&self) -> impl Iterator<Item = ObjectId> + '_

pub fn get_page_contents(&self, page_id: ObjectId) -> Vec<ObjectId>

Get content stream object ids of a page.

pub fn add_page_contents( &mut self, page_id: ObjectId, content: Vec<u8> ) -> Result<()>

Add content to a page. All existing content will be unchanged.

pub fn get_page_content(&self, page_id: ObjectId) -> Result<Vec<u8>>

Get content of a page.

pub fn get_page_resources( &self, page_id: ObjectId ) -> (Option<&Dictionary>, Vec<ObjectId>)

Get resources used by a page.

pub fn get_page_fonts( &self, page_id: ObjectId ) -> BTreeMap<Vec<u8>, &Dictionary>

Get fonts used by a page.

pub fn get_page_annotations(&self, page_id: ObjectId) -> Vec<&Dictionary>

Get the PDF annotations of a page. The /Subtype of each annotation dictionary defines the annotation type (Text, Link, Highlight, Underline, Ink, Popup, Widget, etc.). The /Rect of an annotation dictionary defines its location on the page.

pub fn decode_text(encoding: Option<&str>, bytes: &[u8]) -> String

pub fn encode_text(encoding: Option<&str>, text: &str) -> Vec<u8>

impl Document

pub fn add_bookmark(&mut self, bookmark: Bookmark, parent: Option<u32>) -> u32

pub fn build_outline(&mut self) -> Option<ObjectId>

impl Document

pub fn get_outline( &self, node: &Dictionary, named_destinations: &mut BTreeMap<Vec<u8>, Destination> ) -> Result<Option<Outline>>

pub fn get_outlines( &self, node: Option<Object>, outlines: Option<Vec<Outline>>, named_destinations: &mut BTreeMap<Vec<u8>, Destination> ) -> Result<Option<Vec<Outline>>>

impl Document

pub fn get_named_destinations( &self, tree: &Dictionary, named_destinations: &mut BTreeMap<Vec<u8>, Destination> ) -> Result<()>

impl Document

pub fn get_toc(&self) -> Result<Toc>

impl Document

pub fn with_version<S: Into<String>>(version: S) -> Document

Create new PDF document with version.

pub fn new_object_id(&mut self) -> ObjectId

Create an object ID.

pub fn add_object<T: Into<Object>>(&mut self, object: T) -> ObjectId

Add PDF object into document’s object list.

pub fn set_object<T: Into<Object>>(&mut self, id: ObjectId, object: T)

pub fn remove_object(&mut self, object_id: &ObjectId) -> Result<()>

Remove PDF object from document’s object list.

pub fn get_or_create_resources( &mut self, page_id: ObjectId ) -> Result<&mut Object>

Get the pages resources.

Get Object that has the key “Resources”.

pub fn add_xobject<N: Into<Vec<u8>>>( &mut self, page_id: ObjectId, xobject_name: N, xobject_id: ObjectId ) -> Result<()>

Add XObject to a page.

Get Object that has the key Resources -> XObject.

pub fn add_graphics_state<N: Into<Vec<u8>>>( &mut self, page_id: ObjectId, gs_name: N, gs_id: ObjectId ) -> Result<()>

Add Graphics State to a page.

Get Object that has the key Resources -> ExtGState.

impl Document

pub fn get_and_decode_page_content( &self, page_id: ObjectId ) -> Result<Content<Vec<Operation>>>

Get decoded page content;

pub fn add_to_page_content( &mut self, page_id: ObjectId, content: Content<Vec<Operation>> ) -> Result<()>

Add content to a page. All existing content will be unchanged.

pub fn extract_text(&self, page_numbers: &[u32]) -> Result<String>

pub fn replace_text( &mut self, page_number: u32, text: &str, other_text: &str ) -> Result<()>

pub fn insert_image( &mut self, page_id: ObjectId, img_object: Stream, position: (f32, f32), size: (f32, f32) ) -> Result<()>

pub fn insert_form_object( &mut self, page_id: ObjectId, form_obj: Stream ) -> Result<()>

impl Document

pub fn change_producer(&mut self, producer: &str)

Change producer of document information dictionary.

pub fn compress(&mut self)

Compress PDF stream objects.

pub fn decompress(&mut self)

Decompress PDF stream objects.

pub fn delete_pages(&mut self, page_numbers: &[u32])

Delete pages.

pub fn prune_objects(&mut self) -> Vec<ObjectId>

Prune all unused objects.

pub fn delete_object(&mut self, id: ObjectId) -> Option<Object>

Delete object by object ID.

pub fn delete_zero_length_streams(&mut self) -> Vec<ObjectId>

Delete zero length stream objects.

pub fn renumber_objects(&mut self)

Renumber objects, normally called after delete_unused_objects.

pub fn renumber_bookmarks(&mut self, old: &ObjectId, new: &ObjectId)

pub fn renumber_objects_with(&mut self, starting_id: u32)

Renumber objects with a custom starting id, this is very useful in case of multiple document objects insertion in a single main document

pub fn change_content_stream(&mut self, stream_id: ObjectId, content: Vec<u8>)

pub fn change_page_content( &mut self, page_id: ObjectId, content: Vec<u8> ) -> Result<()>

pub fn extract_stream( &self, stream_id: ObjectId, decompress: bool ) -> Result<()>

impl Document

pub fn load<P: AsRef<Path>>(path: P) -> Result<Document>

Load a PDF document from a specified file path.

pub fn load_filtered<P: AsRef<Path>>( path: P, filter_func: fn(_: (u32, u16), _: &mut Object) -> Option<((u32, u16), Object)> ) -> Result<Document>

pub fn load_from<R: Read>(source: R) -> Result<Document>

Load a PDF document from an arbitrary source.

pub fn load_mem(buffer: &[u8]) -> Result<Document>

Load a PDF document from a memory slice.

impl Document

pub fn save<P: AsRef<Path>>(&mut self, path: P) -> Result<File>

Save PDF document to specified file path.

pub fn save_to<W: Write>(&mut self, target: &mut W) -> Result<()>

Save PDF to arbitrary target

Trait Implementations

impl Clone for Document

fn clone(&self) -> Document

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Document

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Document

fn default() -> Self

Returns the “default value” for a type.

impl TryInto<Document> for &[u8]

type Error = Error

The type returned in the event of a conversion error.

fn try_into(self) -> Result<Document>

Performs the conversion.