use crate::crypto::DecryptionTarget;
use crate::filter::Filter;
use crate::object;
use crate::object::Dict;
use crate::object::Name;
use crate::object::dict::keys::{DECODE_PARMS, DP, F, FILTER, LENGTH, TYPE};
use crate::object::{Array, ObjectIdentifier};
use crate::object::{Object, ObjectLike, ObjectRefLike};
use crate::reader::Reader;
use crate::reader::{Readable, ReaderContext, ReaderExt, Skippable};
use crate::trivia::is_white_space_character;
use crate::util::{OptionLog, find_needle};
use alloc::borrow::Cow;
use alloc::vec::Vec;
use core::fmt::{Debug, Formatter};
use smallvec::SmallVec;
struct FiltersAndParams<'a> {
filters: SmallVec<[Filter; 2]>,
params: SmallVec<[Dict<'a>; 2]>,
}
#[derive(Clone)]
pub struct Stream<'a> {
dict: Dict<'a>,
data: &'a [u8],
}
impl PartialEq for Stream<'_> {
fn eq(&self, other: &Self) -> bool {
self.dict == other.dict && self.data == other.data
}
}
#[derive(Clone, PartialEq, Default)]
pub struct ImageDecodeParams {
pub is_indexed: bool,
pub bpc: Option<u8>,
pub num_components: Option<u8>,
pub target_dimension: Option<(u32, u32)>,
pub width: u32,
pub height: u32,
}
impl<'a> Stream<'a> {
pub(crate) fn new(data: &'a [u8], dict: Dict<'a>) -> Self {
Self { dict, data }
}
fn filters_and_params(&self) -> FiltersAndParams<'a> {
let mut collected_filters = SmallVec::new();
let mut collected_params = SmallVec::new();
if let Some(filter) = self
.dict
.get::<Name<'_>>(F)
.or_else(|| self.dict.get::<Name<'_>>(FILTER))
.and_then(Filter::from_name)
{
let params = self
.dict
.get::<Dict<'_>>(DP)
.or_else(|| self.dict.get::<Dict<'_>>(DECODE_PARMS))
.unwrap_or_default();
collected_filters.push(filter);
collected_params.push(params);
} else if let Some(filters) = self
.dict
.get::<Array<'_>>(F)
.or_else(|| self.dict.get::<Array<'_>>(FILTER))
{
let filters = filters.iter::<Name<'_>>().map(Filter::from_name);
let mut params = self
.dict
.get::<Array<'_>>(DP)
.or_else(|| self.dict.get::<Array<'_>>(DECODE_PARMS))
.map(|a| a.iter::<Object<'_>>());
for filter in filters {
let params = params
.as_mut()
.and_then(|p| p.next())
.and_then(|p| p.into_dict())
.unwrap_or_default();
if let Some(filter) = filter {
collected_filters.push(filter);
collected_params.push(params);
}
}
}
FiltersAndParams {
filters: collected_filters,
params: collected_params,
}
}
pub fn raw_data(&self) -> Cow<'a, [u8]> {
let ctx = self.dict.ctx();
if ctx.xref().needs_decryption(ctx)
&& self
.dict
.get::<object::String<'_>>(TYPE)
.map(|t| t.as_ref() != b"XRef")
.unwrap_or(true)
{
Cow::Owned(
ctx.xref()
.decrypt(
self.dict.obj_id().unwrap(),
self.data,
DecryptionTarget::Stream,
)
.unwrap_or_default(),
)
} else {
Cow::Borrowed(self.data)
}
}
pub fn dict(&self) -> &Dict<'a> {
&self.dict
}
pub fn obj_id(&self) -> ObjectIdentifier {
self.dict.obj_id().unwrap()
}
pub fn filters(&self) -> SmallVec<[Filter; 2]> {
self.filters_and_params().filters
}
pub fn decoded(&self) -> Result<Cow<'a, [u8]>, DecodeFailure> {
self.decoded_image(&ImageDecodeParams::default())
.map(|r| r.data)
}
pub fn decoded_image(
&self,
image_params: &ImageDecodeParams,
) -> Result<FilterResult<'a>, DecodeFailure> {
let data = self.raw_data();
let filters_and_params = self.filters_and_params();
let mut current: Option<FilterResult<'a>> = None;
for (filter, params) in filters_and_params
.filters
.iter()
.zip(filters_and_params.params.iter())
{
let new = filter.apply(
current.as_ref().map(|c| c.data.as_ref()).unwrap_or(&data),
params,
image_params,
)?;
current = Some(new);
}
Ok(current.unwrap_or(FilterResult {
data,
image_data: None,
}))
}
}
impl Debug for Stream<'_> {
fn fmt(&self, f: &mut Formatter<'_>) -> core::fmt::Result {
write!(f, "Stream (len: {:?})", self.data.len())
}
}
impl Skippable for Stream<'_> {
fn skip(_: &mut Reader<'_>, _: bool) -> Option<()> {
warn!("attempted to skip a stream object");
None
}
}
impl<'a> Readable<'a> for Stream<'a> {
fn read(r: &mut Reader<'a>, ctx: &ReaderContext<'a>) -> Option<Self> {
let dict = r.read_with_context::<Dict<'_>>(ctx)?;
if dict.contains_key(F) {
warn!("encountered stream referencing external file, which is unsupported");
return None;
}
let offset = r.offset();
parse_proper(r, &dict)
.or_else(|| {
warn!("failed to parse stream, trying to parse it manually");
r.jump(offset);
parse_fallback(r, &dict)
})
.error_none("was unable to manually parse the stream")
}
}
#[derive(Debug, Copy, Clone)]
pub enum DecodeFailure {
ImageDecode,
StreamDecode,
Decryption,
Unknown,
}
#[derive(Debug, Copy, Clone)]
pub enum ImageColorSpace {
Gray,
Rgb,
Cmyk,
Unknown(u8),
}
pub struct ImageData {
pub alpha: Option<Vec<u8>>,
pub color_space: Option<ImageColorSpace>,
pub bits_per_component: u8,
pub width: u32,
pub height: u32,
}
pub struct FilterResult<'a> {
pub data: Cow<'a, [u8]>,
pub image_data: Option<ImageData>,
}
impl FilterResult<'_> {
pub(crate) fn from_data(data: Vec<u8>) -> Self {
Self {
data: Cow::Owned(data),
image_data: None,
}
}
}
fn parse_proper<'a>(r: &mut Reader<'a>, dict: &Dict<'a>) -> Option<Stream<'a>> {
let length = dict.get::<u32>(LENGTH)?;
r.skip_white_spaces_and_comments();
r.forward_tag(b"stream")?;
r.forward_tag(b"\n")
.or_else(|| r.forward_tag(b"\r\n"))
.or_else(|| r.forward_tag(b"\r"))?;
let data = r.read_bytes(length as usize)?;
r.skip_white_spaces();
r.forward_tag(b"endstream")?;
Some(Stream::new(data, dict.clone()))
}
fn parse_fallback<'a>(r: &mut Reader<'a>, dict: &Dict<'a>) -> Option<Stream<'a>> {
let stream_offset = find_needle(r.tail()?, b"stream")?;
r.read_bytes(stream_offset)?;
r.forward_tag(b"stream")?;
r.forward_tag(b"\n")
.or_else(|| r.forward_tag(b"\r\n"))
.or_else(|| r.forward_tag(b"\r"))?;
let tail = r.tail()?;
let endstream_offset = find_needle(tail, b"endstream")?;
let data_end = trim_trailing_ascii_whitespace(&tail[..endstream_offset]);
let data = tail.get(..data_end)?;
r.read_bytes(endstream_offset)?;
r.skip_white_spaces();
r.forward_tag(b"endstream")?;
Some(Stream::new(data, dict.clone()))
}
fn trim_trailing_ascii_whitespace(data: &[u8]) -> usize {
let mut end = data.len();
while data
.get(end.wrapping_sub(1))
.copied()
.is_some_and(is_white_space_character)
{
end -= 1;
}
end
}
impl<'a> TryFrom<Object<'a>> for Stream<'a> {
type Error = ();
fn try_from(value: Object<'a>) -> Result<Self, Self::Error> {
match value {
Object::Stream(s) => Ok(s),
_ => Err(()),
}
}
}
impl<'a> ObjectLike<'a> for Stream<'a> {}
impl<'a> ObjectRefLike<'a> for Stream<'a> {
fn cast_ref<'b>(obj: &'b Object<'a>) -> Option<&'b Self> {
match obj {
Object::Stream(stream) => Some(stream),
_ => None,
}
}
}
#[cfg(test)]
mod tests {
use crate::object::Stream;
use crate::reader::Reader;
use crate::reader::{ReaderContext, ReaderExt};
#[test]
fn stream() {
let data = b"<< /Length 10 >> stream\nabcdefghij\nendstream";
let mut r = Reader::new(data);
let stream = r
.read_with_context::<Stream<'_>>(&ReaderContext::dummy())
.unwrap();
assert_eq!(stream.data, b"abcdefghij");
}
#[test]
fn stream_fallback() {
let data = b"<< /Length 999 >> stream\nabcdefghij\nendstream";
let mut r = Reader::new(data);
let stream = r
.read_with_context::<Stream<'_>>(&ReaderContext::dummy())
.unwrap();
assert_eq!(stream.data, b"abcdefghij");
}
}