///|
/// Sentinel returned by legacy byte-reading helpers when the cursor is past the
/// end of input.
///
/// Newer APIs usually return `Byte?`, but this value preserves the CamlPDF-style
/// integer cursor contract used by parser code.
pub let pdf_no_more : Int = -1
///|
/// A mutable read cursor over a PDF byte view.
///
/// `ByteCursor` keeps a source label for diagnostics and supports an optional
/// logical offset. After `set_offset`, public positions are relative to that
/// offset while absolute positions still refer to the underlying byte view.
pub struct ByteCursor {
data : BytesView
mut position : Int
mut offset : Int
source : String
} derive(Debug, Eq, ToJson)
///|
/// Creates a cursor over owned PDF bytes.
///
/// The cursor borrows the byte storage through a view and does not copy it.
pub fn byte_cursor_of_bytes(
data : PdfBytes,
source? : String = "bytes",
) -> ByteCursor {
byte_cursor_of_view(data, source~)
}
///|
/// Creates a cursor over a byte view.
///
/// The optional `source` label appears in parse error messages.
pub fn byte_cursor_of_view(
data : BytesView,
source? : String = "bytes",
) -> ByteCursor {
{ data, position: 0, offset: 0, source, }
}
///|
/// Returns the diagnostic source label associated with this cursor.
pub fn ByteCursor::source(self : ByteCursor) -> String {
self.source
}
///|
/// Formats an input error message with the source label and current logical
/// position.
pub fn ByteCursor::input_pdf_error(
self : ByteCursor,
message : String,
) -> String {
message +
" whilst reading file " +
self.source +
" at position " +
self.position().to_string()
}
///|
/// Returns the total length of the underlying byte view.
pub fn ByteCursor::length(self : ByteCursor) -> Int {
self.data.length()
}
///|
/// Returns the underlying read-only byte view without copying.
pub fn ByteCursor::view(self : ByteCursor) -> BytesView {
self.data
}
///|
/// Copies the underlying byte view into owned PDF bytes.
pub fn ByteCursor::to_bytes(self : ByteCursor) -> PdfBytes {
self.data.to_owned()
}
///|
/// Returns the current logical position, relative to the configured offset.
pub fn ByteCursor::position(self : ByteCursor) -> Int {
self.position - self.offset
}
///|
/// Returns the current absolute position in the underlying byte view.
pub fn ByteCursor::absolute_position(self : ByteCursor) -> Int {
self.position
}
///|
/// Returns the byte at an absolute input position without advancing.
pub fn ByteCursor::byte_at_absolute(self : ByteCursor, position : Int) -> Byte? {
if position < 0 || position >= self.data.length() {
None
} else {
Some(self.data[position])
}
}
///|
/// Returns the byte at an absolute input position as an integer.
///
/// Returns `pdf_no_more` when `position` is outside the underlying byte view.
pub fn ByteCursor::byte_int_at_absolute(
self : ByteCursor,
position : Int,
) -> Int {
match self.byte_at_absolute(position) {
Some(byte) => byte.to_int()
None => pdf_no_more
}
}
///|
/// Moves the cursor to an absolute position in the underlying byte view.
pub fn ByteCursor::seek_absolute(
self : ByteCursor,
position : Int,
) -> Unit raise PdfError {
if position < 0 || position > self.data.length() {
raise InvalidCursorPosition(position)
}
self.position = position
}
///|
/// Returns the number of unread bytes remaining from the absolute cursor
/// position.
pub fn ByteCursor::remaining_length(self : ByteCursor) -> Int {
if self.position >= self.data.length() {
0
} else {
self.data.length() - self.position
}
}
///|
/// Sets the logical position offset used by `position` and `seek`.
///
/// The offset can only be set once and must be non-negative. This is used when
/// parsing substreams whose local position should start at zero while retaining
/// absolute positions for diagnostics.
pub fn ByteCursor::set_offset(
self : ByteCursor,
offset : Int,
) -> Unit raise PdfError {
if offset < 0 {
raise InvalidCursorPosition(offset)
}
if self.offset == 0 {
self.offset = offset
}
}
///|
/// Moves the cursor to a logical position.
///
/// The supplied position is interpreted relative to the configured offset.
/// Seeking past the end is allowed so callers can probe EOF behavior; negative
/// absolute positions raise `PdfError::InvalidCursorPosition`.
pub fn ByteCursor::seek(
self : ByteCursor,
position : Int,
) -> Unit raise PdfError {
let absolute = position + self.offset
if absolute < 0 {
raise InvalidCursorPosition(position)
}
self.position = absolute
}
///|
/// Returns a cursor copy with the same input, source label, offset, and
/// position.
pub fn ByteCursor::deep_copy(self : ByteCursor) -> ByteCursor {
{
data: self.data,
position: self.position,
offset: self.offset,
source: self.source,
}
}
///|
/// Reads one byte as an integer and advances the cursor.
///
/// Returns `pdf_no_more` when reading past the end. This method always advances
/// by one position, matching the historical parser cursor behavior.
pub fn ByteCursor::input_byte(self : ByteCursor) -> Int {
let value = if self.position > self.data.length() - 1 {
pdf_no_more
} else {
self.data[self.position].to_int()
}
self.position += 1
value
}
///|
/// Reads one byte and advances the cursor, returning `None` at end of input.
pub fn ByteCursor::read_byte(self : ByteCursor) -> Byte? {
if self.position >= self.data.length() {
None
} else {
let value = self.data[self.position]
self.position += 1
Some(value)
}
}
///|
/// Returns the next byte as an integer without consuming it.
///
/// Returns `pdf_no_more` at end of input.
pub fn ByteCursor::peek_byte(self : ByteCursor) -> Int {
let value = self.input_byte()
self.position -= 1
value
}
///|
/// Returns the next byte without consuming it, or `None` at end of input.
pub fn ByteCursor::peek(self : ByteCursor) -> Byte? {
let value = self.peek_byte()
if value == pdf_no_more {
None
} else {
Some(value.to_byte())
}
}