Files
spice2x-r3d/src/spice2x/external/libjpeg-turbo/jdtrans.c
T
bicarusandGitHub 8b2f38307b graphics: rewrite screenshot and api capture image processing (#870)
## Link to GitHub Issue or related Pull Request, if one exists
#0

## Description of change
Significantly speeds up API screen capture and D3D9 screenshots saving.
Two reasons for doing this:

1. We now have a 4K game (GITADORA) and existing capture code was taking
multiple seconds.
2. Renewed user interest on streaming as we have a couple more companion
apps in active development.

**API screen capture (streaming), 1280x720:** 14.3ms -> 6.3ms per frame.
Back buffer copies go to pooled `D3DPOOL_SYSTEMMEM` surfaces via
`GetRenderTargetData` instead of allocating a lockable render target
every frame, and TooJpeg is replaced with libjpeg-turbo (encode 9.8ms ->
3.0ms). MSAA remains unsupported

**Screenshots for GITADORA arena model, across 4 screens with one of
them 4K**: 4068ms -> 124ms. `D3DXSaveSurfaceToFileA` is replaced with
fpng (encode 4043ms -> 76ms) and the screens encode in parallel.
Dropping D3DX also removes the `d3dx9_43.dll` ... `d3dx9_24.dll` probing
loop, so screenshots no longer fail outright on machines with no D3DX9
runtime installed.

Screenshot surfaces are read on the present thread, so no D3D call
reaches another thread for screenshots. This fixes a hang in DDR X2
introduced earlier in the branch: its device has no internal locking,
and reading the surface on a pool thread while the present thread sat
inside `GetRenderTargetData` left the game's own render thread
deadlocked.


## Testing

- **GITADORA** (arena model, D3D9Ex, 4K main plus three subscreens,
windowed) with
`-screenshotsub`: three sets of four screenshots, images verified
correct. Completion
order differs between sets, so the screens really are encoding in
parallel.
- **LovePlus** (KLP, plain D3D9, 768x1360): covers the inline path used
by games whose
  image processing must not leave the present thread. 
- **API screen capture** through a companion app: live video correct
throughout.
- **Print Screen** bound as the screenshot key: the clipboard copy
succeeded on every shot.
- Quitting the game after capturing leaves no `IDirect3DDevice9`
reference count warning,
  so the pooled readback surfaces are released along with the device.
2026-08-18 00:22:45 -07:00

163 lines
5.5 KiB
C

/*
* jdtrans.c
*
* This file was part of the Independent JPEG Group's software:
* Copyright (C) 1995-1997, Thomas G. Lane.
* libjpeg-turbo Modifications:
* Copyright (C) 2020, 2022, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
* This file contains library routines for transcoding decompression,
* that is, reading raw DCT coefficient arrays from an input JPEG file.
* The routines in jdapimin.c will also be needed by a transcoder.
*/
#define JPEG_INTERNALS
#include "jinclude.h"
#include "jpeglib.h"
#include "jpegapicomp.h"
/* Forward declarations */
LOCAL(void) transdecode_master_selection(j_decompress_ptr cinfo);
/*
* Read the coefficient arrays from a JPEG file.
* jpeg_read_header must be completed before calling this.
*
* The entire image is read into a set of virtual coefficient-block arrays,
* one per component. The return value is a pointer to the array of
* virtual-array descriptors. These can be manipulated directly via the
* JPEG memory manager, or handed off to jpeg_write_coefficients().
* To release the memory occupied by the virtual arrays, call
* jpeg_finish_decompress() when done with the data.
*
* An alternative usage is to simply obtain access to the coefficient arrays
* during a buffered-image-mode decompression operation. This is allowed
* after any jpeg_finish_output() call. The arrays can be accessed until
* jpeg_finish_decompress() is called. (Note that any call to the library
* may reposition the arrays, so don't rely on access_virt_barray() results
* to stay valid across library calls.)
*
* Returns NULL if suspended. This case need be checked only if
* a suspending data source is used.
*/
GLOBAL(jvirt_barray_ptr *)
jpeg_read_coefficients(j_decompress_ptr cinfo)
{
if (cinfo->master->lossless)
ERREXIT(cinfo, JERR_NOTIMPL);
if (cinfo->global_state == DSTATE_READY) {
/* First call: initialize active modules */
transdecode_master_selection(cinfo);
cinfo->global_state = DSTATE_RDCOEFS;
}
if (cinfo->global_state == DSTATE_RDCOEFS) {
/* Absorb whole file into the coef buffer */
for (;;) {
int retcode;
/* Call progress monitor hook if present */
if (cinfo->progress != NULL)
(*cinfo->progress->progress_monitor) ((j_common_ptr)cinfo);
/* Absorb some more input */
retcode = (*cinfo->inputctl->consume_input) (cinfo);
if (retcode == JPEG_SUSPENDED)
return NULL;
if (retcode == JPEG_REACHED_EOI)
break;
/* Advance progress counter if appropriate */
if (cinfo->progress != NULL &&
(retcode == JPEG_ROW_COMPLETED || retcode == JPEG_REACHED_SOS)) {
if (++cinfo->progress->pass_counter >= cinfo->progress->pass_limit) {
/* startup underestimated number of scans; ratchet up one scan */
cinfo->progress->pass_limit += (long)cinfo->total_iMCU_rows;
}
}
}
/* Set state so that jpeg_finish_decompress does the right thing */
cinfo->global_state = DSTATE_STOPPING;
}
/* At this point we should be in state DSTATE_STOPPING if being used
* standalone, or in state DSTATE_BUFIMAGE if being invoked to get access
* to the coefficients during a full buffered-image-mode decompression.
*/
if ((cinfo->global_state == DSTATE_STOPPING ||
cinfo->global_state == DSTATE_BUFIMAGE) && cinfo->buffered_image) {
return cinfo->coef->coef_arrays;
}
/* Oops, improper usage */
ERREXIT1(cinfo, JERR_BAD_STATE, cinfo->global_state);
return NULL; /* keep compiler happy */
}
/*
* Master selection of decompression modules for transcoding.
* This substitutes for jdmaster.c's initialization of the full decompressor.
*/
LOCAL(void)
transdecode_master_selection(j_decompress_ptr cinfo)
{
/* This is effectively a buffered-image operation. */
cinfo->buffered_image = TRUE;
#if JPEG_LIB_VERSION >= 80
/* Compute output image dimensions and related values. */
jpeg_core_output_dimensions(cinfo);
#endif
/* Entropy decoding: either Huffman or arithmetic coding. */
if (cinfo->arith_code) {
#ifdef D_ARITH_CODING_SUPPORTED
jinit_arith_decoder(cinfo);
#else
ERREXIT(cinfo, JERR_ARITH_NOTIMPL);
#endif
} else {
if (cinfo->progressive_mode) {
#ifdef D_PROGRESSIVE_SUPPORTED
jinit_phuff_decoder(cinfo);
#else
ERREXIT(cinfo, JERR_NOT_COMPILED);
#endif
} else
jinit_huff_decoder(cinfo);
}
/* Always get a full-image coefficient buffer. */
if (cinfo->data_precision == 12)
j12init_d_coef_controller(cinfo, TRUE);
else
jinit_d_coef_controller(cinfo, TRUE);
/* We can now tell the memory manager to allocate virtual arrays. */
(*cinfo->mem->realize_virt_arrays) ((j_common_ptr)cinfo);
/* Initialize input side of decompressor to consume first scan. */
(*cinfo->inputctl->start_input_pass) (cinfo);
/* Initialize progress monitoring. */
if (cinfo->progress != NULL) {
int nscans;
/* Estimate number of scans to set pass_limit. */
if (cinfo->progressive_mode) {
/* Arbitrarily estimate 2 interleaved DC scans + 3 AC scans/component. */
nscans = 2 + 3 * cinfo->num_components;
} else if (cinfo->inputctl->has_multiple_scans) {
/* For a nonprogressive multiscan file, estimate 1 scan per component. */
nscans = cinfo->num_components;
} else {
nscans = 1;
}
cinfo->progress->pass_counter = 0L;
cinfo->progress->pass_limit = (long)cinfo->total_iMCU_rows * nscans;
cinfo->progress->completed_passes = 0;
cinfo->progress->total_passes = 1;
}
}