mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-25 09:38:06 +02:00
Code Activity

Attempt to detect inline images which contain "EI" sequence in the actual image data (issue 11124)

Browse source 
This should reduce the possibility of accidentally truncating some inline images, while *not* causing the "EI" detection to become significantly slower.[1]
There's obviously a possibility that these added checks are not sufficient to catch *every* single case of "EI" sequences within the actual inline image data, but without specific test-cases I decided against over-engineering the solution here.

*Please note:* The interpolation issues are somewhat orthogonal to the main issue here, which is the truncated image, and it's already tracked elsewhere.

---
[1] I've looked at the issue a few times, and this is the first approach that I was able to come up with that didn't cause *unacceptable* performance regressions in e.g. issue 2618.
This commit is contained in:
Jonas Jenwald 2020-06-26 12:36:28 +02:00
parent 276d917b7c
commit 28d2ada59c
4 changed files with 85 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

48
src/core/parser.js
View file

@ -203,10 +203,11 @@ class Parser {
I = 0x49,
SPACE = 0x20,
LF = 0xa,
CR = 0xd;
const n = 10,
CR = 0xd,
NUL = 0x0;
const startPos = stream.pos;
const lexer = this.lexer,
startPos = stream.pos,
n = 10;
let state = 0,
ch,
maybeEIPos;
@ -243,6 +244,25 @@ class Parser {
break;
}
}
if (state !== 2) {
continue;
}
// Check that the "EI" sequence isn't part of the image data, since
// that would cause the image to be truncated (fixes issue11124.pdf).
if (lexer.knownCommands) {
const nextObj = lexer.peekObj();
if (nextObj instanceof Cmd && !lexer.knownCommands[nextObj.cmd]) {
// Not a valid command, i.e. the inline image data *itself*
// contains an "EI" sequence. Resetting the state.
state = 0;
}
} else {
warn(
"findDefaultInlineStreamEnd - `lexer.knownCommands` is undefined."
);
}
if (state === 2) {
break; // Finished!
}
@ -1276,6 +1296,28 @@ class Lexer {
return Cmd.get(str);
}
peekObj() {
const streamPos = this.stream.pos,
currentChar = this.currentChar,
beginInlineImagePos = this.beginInlineImagePos;
let nextObj;
try {
nextObj = this.getObj();
} catch (ex) {
if (ex instanceof MissingDataException) {
throw ex;
}
warn(`peekObj: ${ex}`);
}
// Ensure that we reset *all* relevant `Lexer`-instance state.
this.stream.pos = streamPos;
this.currentChar = currentChar;
this.beginInlineImagePos = beginInlineImagePos;
return nextObj;
}
skipToNextLine() {
let ch = this.currentChar;
while (ch >= 0) {