2006-03-06 Sven Neumann <sven@gimp.org>
* app/display/gimpdisplay.c (gimp_display_reconnect): keep a
reference on the old image until the display is connected to the
new one. Fixes bug #333568.
* app/display/gimpdisplay-handlers.c: fixed typo in comment.
* app/actions/file-commands.c: cosmetics.
2004-02-07 Michael Natterer <mitch@gimp.org>
* app/display/gimpdisplayshell.[ch]: removed all drawing functions.
The file was still too large.
* app/display/Makefile.am
* app/display/gimpdisplayshell-draw.[ch]: new files containing
the drawing functions.
* app/display/gimpdisplayshell-callbacks.c
* app/display/gimpdisplayshell-handlers.c
* app/tools/gimpmovetool.c: changed #includes accordingly.
* app/display/gimpdisplay-handlers.c
(gimp_display_size_changed_handler): added some #if 0'ed code I'm
not sure about. Actually, some of the handlers in this file could
need the same code, so it could be abstracted as
gimp_display_stop_draw() or something. Please have a look.
2003-05-17 Michael Natterer <mitch@gimp.org>
Fixed File->Revert, which was completely broken before:
* app/gui/file-commands.c (file_revert_confirm_callback): set the
new image on all GimpContexts which had the old image set. Unref
the new image after the displays are reconnected.
Added some paranoia code for similar future situations (the
functions below were not broken, but affected by the above bug):
* app/display/gimpdisplay-handlers.c (gimp_display_disconnect):
set gdisp->gimage to NULL before unrefing the image.
* app/widgets/gimpimagedock.c (gimp_image_dock_image_changed):
unref the gimage pointer returned by g_object_get() only if it is
non-NULL. Cleanup.
2003-01-05 Manish Singh <yosh@gimp.org>
* many files in app, modules and libgimp*: cleanup, removed unecessary
G_OBJECT() casts. Should do the same for plug-ins, when more of them
get undeprecated.
2002-11-23 Michael Natterer <mitch@gimp.org>
* app/config/gimpconfig-utils.[ch]: removed
gimp_config_values_equal().
* app/config/gimpconfig-serialize.c
* app/config/gimpconfig.c: use g_param_values_cmp() instead so
our registered compare methods are used.
* app/config/gimpdisplayconfig.[ch]: added "canvas_padding_mode"
and "canvas_padding_color" properties.
* app/display/display-enums.[ch]: added enum GimpDisplayPaddingMode
which can be one of { theme, light check, dark check, custom }.
* app/display/gimpdisplay.h
* app/display/gimpdisplay-handlers.c: removed cached monitor
resolution values...
* app/display/gimpdisplayshell.[ch]: ...and added them here. Added
padding state as in GimpDisplayConfig. Added utility function
gimp_display_shell_set_padding() which hides all the details.
Added the new padding modes to the padding color button's context
menu.
* app/display/gimpdisplayshell-callbacks.[ch]: don't fiddle
with colors manually but use gimp_display_shell_set_padding()
in realize() and in the color button callbacks.
* app/display/gimpdisplayshell-handlers.c: connect to
notify::monitor-[xy]resolution and
notify::canvas-padding-[mode|color] and update accordingly.
* app/widgets/gimppropwidgets.[ch]: added
gimp_prop_color_button_new().
* app/widgets/gimpdialogfactory.[ch]: added
gimp_dialog_factories_session_clear() (unimplemented).
* app/gui/preferences-dialog.c: added widgets for padding mode and
color. Removed some callbacks by connecting the functions they
called directly. Cleanup.
2002-05-13 Michael Natterer <mitch@gimp.org>
* app/paint-funcs/paint-funcs.c commented out a warning in
initial_sub_region and a g_error() in combine_sub_region which
didn't expect to get chunks of pixels with a width of > 128
passed. I guess it was an assertion to ensure the integrity of
some higher level code (see gimpdisplay.c:
gimp_display_idlerenderer_callback()). The assertion went off
whenever we wanted to render a preview with a width of > 128,
which is however handled absolutely correctly by the two
functions. (fixes#26072)
* app/core/gimpcontext.c (gimp_context_get_by_type): unref objects
before returning them. Fixes our biggest memleak (whole images).
* app/display/gimpdisplay-handlers.c: commented out debugging
g_print()s which track the image's refcount.
2002-05-08 Michael Natterer <mitch@gimp.org>
Started to get rid of the gdisplays_foo() functions in
app/display/gimpdisplay-foreach.[ch]. Work in progress...
* app/core/gimp.[ch]: added the display list to the Gimp object
(as a GimpList of GimpObjects). This way we get more independent
from whether there is GUI or not, as gimp->displays will simply
be an empty list for the --no-interface case.
* app/display/gimpdisplay.[ch]: Removed the global "display_list"
and "display_num" variables. Use gimp->displays instead.
* app/display/gimpdisplay-foreach.[ch]: renamed most functions
from gdisplays_foo() to gimp_displays_foo() and pass them a Gimp
pointer.
* app/core/gimpimage.[ch]: added a "flush" signal.
* app/display/gimpdisplay-handlers.c: connect to "flush" and call
gimp_display_flush() in the callback.
* tools/pdbgen/pdb/display.pdb: use gimp_displays_flush(gimp)
here and only here.
* app/pdb/display_cmds.c: regenerated.
* app/app_procs.c
* app/gui/gui.c
* app/gui/preferences-dialog.c:
s/gdislays_foo()/gimp_displays_foo(gimp)/
* app/image_map.c
* app/undo_history.c
* app/display/gimpdisplayshell-callbacks.c
* app/display/gimpdisplayshell-dnd.c
* app/display/gimpdisplayshell-layer-select.c
* app/display/gimpdisplayshell-scale.c
* app/gui/channels-commands.c
* app/gui/colormap-editor-commands.c
* app/gui/convert-dialog.c
* app/gui/drawable-commands.c
* app/gui/edit-commands.c
* app/gui/file-commands.c
* app/gui/image-commands.c
* app/gui/layers-commands.c
* app/gui/offset-dialog.c
* app/gui/qmask-commands.c
* app/gui/select-commands.c
* app/gui/vectors-commands.c
* app/paint/gimpairbrush.c
* app/tools/gimpbezierselecttool.c
* app/tools/gimpblendtool.c
* app/tools/gimpbrightnesscontrasttool.c
* app/tools/gimpbucketfilltool.c
* app/tools/gimpbycolorselecttool.c
* app/tools/gimpcolorbalancetool.c
* app/tools/gimpcurvestool.c
* app/tools/gimpeditselectiontool.c
* app/tools/gimpfreeselecttool.c
* app/tools/gimpfuzzyselecttool.c
* app/tools/gimphuesaturationtool.c
* app/tools/gimpinktool.c
* app/tools/gimpiscissorstool.c
* app/tools/gimplevelstool.c
* app/tools/gimpmeasuretool.c
* app/tools/gimpmovetool.c
* app/tools/gimppainttool.c
* app/tools/gimpposterizetool.c
* app/tools/gimprectselecttool.c
* app/tools/gimptexttool.c
* app/tools/gimpthresholdtool.c
* app/tools/gimptransformtool.c
* app/tools/gimpvectortool.c
* app/widgets/gimpbufferview.c
* app/widgets/gimpchannellistview.c
* app/widgets/gimpcomponentlistitem.c
* app/widgets/gimpdocumentview.c
* app/widgets/gimpdrawablelistitem.c
* app/widgets/gimpdrawablelistview.c
* app/widgets/gimpimageview.c
* app/widgets/gimpitemlistitem.c
* app/widgets/gimpitemlistview.c
* app/widgets/gimplayerlistitem.c
* app/widgets/gimplayerlistview.c
* app/widgets/gimpvectorslistview.c: replaced gdisplays_flush()
with calls to gimp_image_flush(gimage). Removed inclusion of
"display/gimpdisplay-foreach.h" from most files.
2001-12-14 Michael Natterer <mitch@gimp.org>
* app/core/gimpimage.[ch]: added
GIMP_IMAGE_TYPE_IS_[RGB|GRAY|INDEXED]() and
GIMP_IMAGE_TYPE_BASE_TYPE() macros.
* app/plug-in/plug-in.[ch]: new enum PlugInImageType instead of
multiple #defines.
* app/gui/file-dialog-utils.[ch]: file_dialog_update_menus(): take
a GimpImageType instead of the PlugInImageType.
* app/core/gimpdrawable-preview.c
* app/core/gimpdrawable-transform.c
* app/core/gimpdrawable.c
* app/core/gimpimage-contiguous-region.c
* app/core/gimpimage-mask.c
* app/core/gimpimage-merge.c
* app/core/gimplayermask.c
* app/core/gimppalette-import.c
* app/display/gimpdisplay-handlers.c
* app/display/gimpdisplayshell-render.c
* app/gui/file-save-dialog.c
* app/gui/toolbox.c
* app/tools/gimpclonetool.c
* app/tools/gimpcolorpickertool.c
* tools/pdbgen/pdb/convert.pdb
* tools/pdbgen/pdb/image.pdb: use the new macros, cleanups like
storing GimpImageType in GimpImageType variables, not just gint.
* app/pdb/convert_cmds.c
* app/pdb/image_cmds.c: regenerated.
* app/widgets/gimpdialogfactory.c: save the state of the "Auto"
button in sessionrc.
2001-11-20 Michael Natterer <mitch@gimp.org>
* app/core/gimp.c: put a g_object_ref() on a different line.
* app/core/gimpdrawable-bucket-fill.c
* app/core/gimpmodules.c: ne need to #include "core/..." here.
* app/display/gimpdisplay-handlers.c: added debugging output
because we have an image refcounting problem :(
* app/display/gimpdisplayshell-handlers.c: fixed a signal
disconnection.
* app/tools/gimpbezierselecttool.[ch]
* app/tools/gimpblendtool.c
* app/tools/gimpbucketfilltool.c
* app/tools/gimpbycolorselecttool.c
* app/tools/gimpclonetool.c
* app/tools/gimpcolorpickertool.c
* app/tools/gimpcroptool.c
* app/tools/gimpellipseselecttool.c
* app/tools/gimpfreeselecttool.c
* app/tools/gimpfuzzyselecttool.c
* app/tools/gimpinktool.c
* app/tools/gimpiscissorstool.c
* app/tools/gimpmagnifytool.c
* app/tools/gimpmeasuretool.c
* app/tools/gimprectselecttool.c
* app/tools/gimpsmudgetool.c: get the tool's options via
tool->tool_info->tool_options, not from the local statis pointer.
Some minor cleanups & function reordering.
* app/widgets/gimpdockbook.c: return TRUE from the notebook tabs'
"button_press" handler, connect DND before cnnecting to
"button_press" because we now stop it's emission.
2001-11-10 Michael Natterer <mitch@gimp.org>
* app/Makefile.am
* app/qmask.[ch]: removed.
* app/core/gimpimage.[ch]: added "qmask_changed" signal and
gimp_image_[set|get]_qmask_state().
* app/display/Makefile.am
* app/display/gimpdisplayshell-qmask.[ch]: put the stuff here.
* app/display/gimpdisplayshell-handlers.[ch]: new files: handlers
for GimpImage signals handled by GimpDisplayShell.
* app/display/gimpdisplay-handlers.c: removed some of them here.
Don't include any GimpDisplayShell stuff any more.
* app/display/gimpdisplay.c: no need to update the qmask buttons
in gimp_display_flush_whenever().
* app/display/gimpdisplayshell.c: call gimp_display_shell_connect()
and disconnect().
2001-11-01 Michael Natterer <mitch@gimp.org>
* app/display/Makefile.am
* app/display/gimpdisplay-callbacks.[ch]
* app/display/gimpdisplay-render.[ch]
* app/display/gimpdisplay-scale.[ch]
* app/display/gimpdisplay-scroll.[ch]: removed and added as
gimpdisplayshell-foo.[ch] because they are all methods of the
shell.
* app/display/gimpdisplay.[ch]
* app/display/gimpdisplayshell.[ch]: moved the "offset" and "size"
variables from GimpDisplay to GimpDisplayShell. GimpDisplay
should know nothing about screen coordinates.
The gdisplay_[un]transform_foo() methods are still part of
GimpDisplay but will be moved to GimpDisplayShell as soon as the
tools' vitrual functions speak in image coordinates instead of
GdkEvents.
* app/display/gimpdisplayshell-callbacks.[ch]: prefixed all
functions with gimp_display_shell_*. Moved some stuff to a
"realize" callback File still has to be renamed.
* app/display/gimpdisplay-foreach.[ch]: removed
gdisplays_shrink_wrap().
* app/gui/menus.c
* app/gui/view-commands.[ch]
* app/display/gimpdisplayshell-scale.[ch]: implemented "Zoom to
Fit Window" function (#57670).
* app/nav_window.c
* app/display/gimpdisplay-handlers.c
* app/display/gimpdisplayshell-render.[ch]
* app/display/gimpdisplayshell-scale.[ch]
* app/display/gimpdisplayshell-scroll.[ch]
* app/gui/colormap-dialog.c
* app/gui/gui.c
* app/gui/preferences-dialog.c
* app/tools/gimpmagnifytool.c
* app/tools/gimpmovetool.c
* app/widgets/gimppreview.c: changed according to variable
and filename changes.
* app/tools/tool_manager.c: tool_manager_select_tool(): send the
active tool a "HALT" command before selecting the new one. Fixes
stale tool dialogs which were there because some other hack was
removed (This is IMHO the right place to shut down the active
tool).
* app/tools/gimpcroptool.c: don't shrink wrap after cropping but
let gimprc.allow_resize_windows decide.
* app/tools/gimpselectiontool.c: gimage_mask_value() takes image,
not screen coordinates. A good example of how braindead it is to
pass GdkEvents to tools :-) Fixes incorrect cursor and oper
update of the selection tools.
* app/tools/gimptransformtool.c
* app/undo.c: removed (#if 0 for now) some strange code which did
manual exposing of GimpDisplayShell areas. This was definitely a
hack and should not be there given the image emits correct
"update" signals.
Sven Neumann