| Server IP : 182.53.201.61 / Your IP : 216.73.217.175 Web Server : Apache/2.2.15 (Fedora) System : Linux km10.dyndns.org 2.6.31.5-127.fc12.i686.PAE #1 SMP Sat Nov 7 21:25:57 EST 2009 i686 User : apache ( 48) PHP Version : 5.3.3 Disable Function : NONE MySQL : ON | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /usr/share/doc/babl-0.1.0/ |
Upload File : |
=========================== 0.1.0 released ============================= 2009-05-20 Martin Nordholts <martinn@src.gnome.org> * configure.ac: Bump version to 0.1.0 and make sure the link name remains `babl-0.0'. 2009-05-20 Martin Nordholts <martinn@svn.gnome.org> * docs/Makefile.am: Also add .libs directories to the BABL_PATHs so that e.g. the BablFishPath introspection chart is properly generated when doing a build, at least on Linux. 2009-05-20 Martin Nordholts <martinn@src.gnome.org> * docs/index-static.html.in: Convert SVN references to git 2009-05-19 Martin Nordholts <martinn@src.gnome.org> Update for 0.1.0 release. * AUTHORS * NEWS 2009-05-16 Hubert Figuiere <hub@figuiere.net> Add extern "C" to the header for C++ friendliness. * babl/babl.h 2009-04-04 Martin Nordholts <martinn@svn.gnome.org> Bug 568576 – [PATCH] undefined operation fix Patch from Stanislav Brabec * babl/babl-fish-stats.c * tests/babl_fish_path_fitness.c 2009-04-04 Martin Nordholts <martinn@svn.gnome.org> * AUTHORS: Update for 0.1.0 release. 2009-04-04 Martin Nordholts <martinn@svn.gnome.org> * extensions/Makefile.am: extensions: util.h is part of the source. make distcheck passes now. 2009-04-04 Martin Nordholts <martinn@svn.gnome.org> * babl/Makefile.am: Add forgotten header files that needs to be distributed with a release. 2009-04-04 Martin Nordholts <martinn@svn.gnome.org> * Makefile.am: We don't have a COPYING.LESSER anymore 2009-04-03 Martin Nordholts <martinn@svn.gnome.org> * NEWS: Updated for 0.1.0 2009-03-31 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-internal.h: Patch from Gary V. Vaughan. Avoid the need for define __func__ "unknown" on some vendor compilers 2009-03-31 Martin Nordholts <martinn@svn.gnome.org> * configure.ac: Patch from Gary V. Vaughan. Don't try to pass gcc flags to vendor compilers 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Patch from Gary V. Vaughan. Rewrite xml-insert.sh in portable bourne-shell * docs/Makefile.am * docs/tools/xml_insert.sh 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Patch from Gary V. Vaughan. Don't use depecrated features or reduntant declarations in Makefile.am * babl/Makefile.am * babl/base/Makefile.am * docs/Makefile.am * tests/Makefile.am 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Patch from Gary V. Vaughan. Support hpux use of shl load/unload and dsos with .sl suffixes * babl/babl-extension.c * configure.ac * extensions/Makefile.am * tests/Makefile.am 2008-03-27 Kevin Cozens <kcozens@cvs.gnome.org> * configure.ac: * docs/graphics/Makefile.am: Applied patch from Matteo 'Peach' Pescarin which makes build use rsvg binary instead of inkscape to create pngs. Fixes bug 571516. 2009-03-26 Manish Singh <yosh@gimp.org> * configure.ac: BABL_VARIADIC_MACROS needs to be called before the libtool stuff (which implicitly calls AC_PROG_CXX) 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Patch from Gary V. Vaughan. NULL-statements caused by trailing commas are non-portable. * babl/base/type-u16.c * babl/base/type-u32.c * babl/base/type-u8.c * extensions/CIE-Lab.c 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Apply patch from Gary V. Vaughan that adds configure time checks for variadic macros and adapts the definitions of such macros in-code accordingly so that babl can be compiled on more platforms. * acinclude.m4 * babl/babl-internal.h * configure.ac 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-fish.c: Patch from Gary V. Vaughan. Some vendor compilers can't compile non-constant elements of compound struct initializers 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Patch from Gary V. Vaughan. Some vendor C compilers choke on C++ comments. * babl/babl-fish-path.c * babl/babl-fish-stats.c * babl/base/model-rgb.c * babl/base/rgb-constants.h * tests/babl_fish_path_fitness.c 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-cpuaccel.h: Patch from Gary V. Vaughan. enum values must be less than INT_MAX (sign bit is illegal) 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-ids.h: Patch from Gary V. Vaughan. Remove trailing comma in enum declaration. 2009-03-25 Martin Nordholts <martinn@svn.gnome.org> Apply patch from Gary V. Vaughan that includes config.h in some files that missed it. * babl/base/conversions-type.c * babl/base/model-cmyk.c 2009-02-24 Sven Neumann <sven@gimp.org> * */*.c: based on a patch from Gary V. Vaughan, include "config.h" before any other header file from all .c files. * babl/babl-internal.h * extensions/util.h: instead of including config.h from here, bail out if it wasn't included beforehand. 2009-02-20 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Include headers in babl.h as system headers 2009-01-26 Sven Neumann <sven@gimp.org> * babl/babl.h * babl/babl-format.c: renamed babl_format_get_num_of_components() to babl_format_get_n_components(). (babl_format_has_alpha): changed accordingly. 2009-01-24 Martin Nordholts <martinn@svn.gnome.org> Do a complete overhaul of the babl API. * babl/babl.h: Instead of including subsystem headers, declare the functions part of the API directly in the header. The public types, macros and the version header is still pulled in as includes but with inclusion guards that prevent them from being included separately by clients. Notable things removed from the API is internal class functions and the class instance structs. (babl_format_has_alpha) (babl_format_get_bytes_per_pixel) (babl_format_get_num_of_components) (babl_format_get_type): New getters to allow the Babl union to become opaque for clients. * babl/babl-types.h: New file with public types. Currently only the opaque Babl union and the linear and planar conversion function prototypes (which are not used in the API due to the use of varags but still part of the API for reference) are there. Make sure it's only included indirectly through babl.h. * babl/babl-macros.h * babl/babl-version.h.in: Make sure these are not included directly, only indirectly through babl.h. * babl/babl-main.h: Removed, function declarations are in babl.h now. * babl/babl-internal.h: Include the headers we now consider internal, mostly the different class headers. * babl/babl-class.h: The "named class" function declarations are now in the public header so move them away from this internal header. * babl/babl-image.h * babl/babl-format.h * babl/babl-fish.h * babl/babl-extension.h * babl/babl-conversion.h * babl/babl-component.h * babl/babl-classes.h * babl/babl-introspect.h * babl/babl-sampling.h * babl/babl-model.h * babl/babl-type.h: Adapt to above changes, move relevant things to babl.h * babl/base/formats.c * babl/base/model-gray.c * babl/base/model-rgb.c * babl/base/model-ycbcr.c * babl/base/type-float.c: Explicitly #include "babl-classes.h". * babl/babl-internal.c: s/babl_name/babl_get_name/ * babl/babl-format.c (babl_format_has_alpha) (babl_format_get_bytes_per_pixel) (babl_format_get_num_of_components) (babl_format_get_type): Implement these. * babl/Makefile.am: Don't install the now internal headers and add, remove and install the other headers according to above changes. 2009-01-18 Martin Nordholts <martinn@svn.gnome.org> Since babl_foo_from_id() will not be part of the public API we can revert to having the short variant babl_foo() instead of babl_foo_from_name(). * babl/babl-class.h * babl/babl-component.h * babl/babl-conversion.c * babl/babl-conversion.h * babl/babl-extension.h * babl/babl-fish-path.c * babl/babl-fish.c * babl/babl-format.c * babl/babl-format.h * babl/babl-image.c * babl/babl-internal.h * babl/babl-model.c * babl/babl-model.h * babl/babl-type.c * babl/babl-type.h * extensions/CIE-Lab.c * extensions/frequency.c * extensions/gegl-fixups.c * extensions/gggl-lies.c * extensions/gggl.c * extensions/gimp-8bit.c * extensions/naive-CMYK.c * extensions/sse-fixups.c * tests/grayscale_to_rgb.c * tests/rgb_to_bgr.c * tests/rgb_to_ycbcr.c 2009-01-18 Martin Nordholts <martinn@svn.gnome.org> Add include guards. * babl/babl-component.h * babl/babl-conversion.h * babl/babl-extension.h * babl/babl-fish.h * babl/babl-format.h * babl/babl-image.h * babl/babl-model.h * babl/babl-sampling.h * babl/babl-type.h 2009-01-18 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-db.h: Namespace the include guard. 2009-01-18 Martin Nordholts <martinn@svn.gnome.org> Do a s/babl_destroy/babl_exit since 'destroy' is better paired with a 'create' and other libraries also use the 'init'/'exit' pair, including GEGL. Keep a define for babl_destroy unless BABL_DISABLE_DEPRECATED is defined. * babl/babl-main.h * babl/babl.c * tests/babl-html-dump.c * tests/babl_class_name.c * tests/babl_fish_path_dhtml.c * tests/babl_fish_path_fitness.c * tests/conversions.c * tests/formats.c * tests/grayscale_to_rgb.c * tests/introspect.c * tests/models.c * tests/nop.c * tests/rgb_to_bgr.c * tests/rgb_to_ycbcr.c * tests/sanity.c * tests/srgb_to_lab_u8.c * tests/types.c 2009-01-18 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-classes.h: New file collecting the type constants, includes and the union for the babl classes. When adding a new class this is the only installed header file that requires modification. * babl/babl-class.h: Move the class type enums to the new file. * babl/babl.h: Include babl-classes.h instead of each class on its own, and move the Babl union to the new file. * babl/Makefile.am: Add the new file. 2009-01-18 Sven Neumann <sven@gimp.org> * babl/babl-component.h * babl/babl-conversion.h * babl/babl-extension.h * babl/babl-format.h * babl/babl-model.h * babl/babl-type.h: allow to disable the defines that were added for backward compatibility by definining BABL_DISABLE_DEPRECATED. * babl/babl-image.h: removed trailing whitespace. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> Add #define babl_foo babl_foo_from_name macros, that should fix most builds that broke due to the below refactoring. * babl/babl-component.h * babl/babl-conversion.h * babl/babl-extension.h * babl/babl-format.h * babl/babl-model.h * babl/babl-type.h 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> s/babl_image/babl_image_new/ * babl/babl-fish-reference.c * babl/babl-image.c * babl/babl-image.h 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> s/babl_foo_init/babl_foo_class_init/ s/babl_foo_destroy/babl_foo_class_destroy/ s/babl_foo_each/babl_foo_class_for_each/ s/babl_foo/babl_foo_from_name/ s/babl_foo_id/babl_foo_from_id/ * babl/babl-class.h * babl/babl-conversion.c * babl/babl-core.c * babl/babl-fish-path.c * babl/babl-fish-reference.c * babl/babl-fish-stats.c * babl/babl-fish.c * babl/babl-format.c * babl/babl-image.c * babl/babl-internal.h * babl/babl-introspect.c * babl/babl-model.c * babl/babl-sampling.c * babl/babl-sanity.c * babl/babl-type.c * babl/babl.c * babl/base/formats.c * babl/base/model-gray.c * babl/base/model-rgb.c * babl/base/model-ycbcr.c * babl/base/type-float.c * babl/base/type-u16.c * babl/base/type-u32.c * babl/base/type-u8.c * extensions/CIE-Lab.c * extensions/frequency.c * extensions/gegl-fixups.c * extensions/gggl-lies.c * extensions/gggl.c * extensions/gimp-8bit.c * extensions/naive-CMYK.c * extensions/sse-fixups.c * tests/babl-html-dump.c * tests/babl_fish_path_fitness.c * tests/conversions.c * tests/formats.c * tests/grayscale_to_rgb.c * tests/models.c * tests/rgb_to_bgr.c * tests/rgb_to_ycbcr.c * tests/types.c 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-class.h: Remove babl_name() and babl_introspect() which slipped in here. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Don't #include <stdlib.h> * babl/base/formats.c * babl/base/model-gray.c * babl/base/model-rgb.c * extensions/gegl-fixups.c * extensions/sse-fixups.c: #include <stdlib.h> 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> Make babl.h look clean. * babl/babl-introspect.h: New installed header for babl_name() and babl_introspect(). * babl/babl.h: Include it. * babl/Makefile.am: Add it. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-internal.h: Formating. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-class.h: New installed header file containing class and typesystem definitions and types. * babl/babl.h: Include it. * babl/Makefile.am: Add it. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Move up forward declaration of BablList. * babl/babl-list.h: Completely rely on that declaration. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Don't have BABL_ALPHA_THRESHOLD public yet. * babl/base/util.h: Put it here for now instead. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> Instead of having BABL_CLASS() plus variants and making the macros expand to different things depending on if they are used in a header or a .c file, have two versions: BABL_CLASS_DECLARE() and BABL_CLASS_IMPLEMENT(). This enables further refactorisation of the babl.h header. * babl/babl.h: Do the name changes and remove the unpleasant #undefs at the bottom. * babl/babl-internal.h: Do the name changes. * babl/babl-component.[ch] * babl/babl-conversion.[ch] * babl/babl-extension.[ch] * babl/babl-fish.[ch] * babl/babl-format.[ch] * babl/babl-image.h * babl/babl-model.[ch] * babl/babl-sampling.h * babl/babl-type.[ch]: Adjust to changes. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> Don't redeclare functions declared with the BABL_CLASS() or BABL_NAMED_CLASS() macros. * babl/babl-component.h * babl/babl-conversion.h * babl/babl-extension.h * babl/babl-fish.h * babl/babl-format.h * babl/babl-image.h * babl/babl-model.h * babl/babl-sampling.h * babl/babl-type.h 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-main.h: New installed file with babl_init() and babl_destroy() declarations. * babl/babl.h: Include it. * babl/Makefile.am: Add it. 2009-01-17 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-macros.h: New installed header file that contains portability macros. * babl/babl.h: Include it and don't define portability macros here. * babl/Makefile.am: Add it. 2009-01-15 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Make BablClassType an int again, it doesn't make sense as an enum as the set of class types is not a natural predefined set. 2009-01-14 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Make BablClassType an enum instead of an unsigned int contaning enum values. 2009-01-14 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Use a lowercase 'a' in 0xbab100. 2009-01-14 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Don't document forward declarations and move them down a bit to make them less eminent. 2009-01-14 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h * babl/babl-internal.h: Remove BABL_HARD_MAX_PATH_LENGTH from here, it's only for internal use. * babl/babl-fish-path.c: #define BABL_HARD_MAX_PATH_LENGTH locally here. 2009-01-14 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h (BABL_ALPHA_THRESHOLD): Instead of an arbitrary threshold, use one hundredth of the channel intensity resolution when using 16 bit integers i.e. 0.01 / (2^16 - 1). 2008-12-08 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-internal.h (babl_assert): Don't just eek when an assertion fails, also say exactly what failed. 2008-11-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish-stats.c: (legal_error), (each_conv): show in red the conversions that are worse than the current BABL_TOLERANCE instead of the earlier arbitrary 0.01. 2008-11-16 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-fish-path.c: Use the default babl tolerance level if BABL_TOLERANCE is the empty string so that we don't get a tolerance level of 0.0 in that case. 2008-11-16 Martin Nordholts <martinn@svn.gnome.org> * babl/babl.h: Add #define BABL_ALPHA_THRESHOLD which is the alpha threshold used in the reference implementation for un-pre-multiplication of color data. * babl/base/model-rgb.c * babl/base/model-gray.c * extensions/gegl-fixups.c: Use the define, a consistent alpha threshold improves accurucy of conversions. 2008-11-16 Martin Nordholts <martinn@svn.gnome.org> * extensions/gegl-fixups.c (conv_rgbAF_sdl32) * babl/base/model-gray.c (premultiplied_to_non_premultiplied): Make un-pre-multiplication with close-to-zero alpha values result in complete black instead of a bit brigher than black. 2008-11-08 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (conv_rgbAF_lrgba8): use the lookup tables to speed up the conversion 8still error of 0.002677 though). 2008-11-06 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (conv_rgbAF_rgbaF), (conv_rgbAF_lrgba8): make all components 0.0 when alpha < 0.00001. 2008-11-04 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (conv_rgbAF_rgbaF), (conv_rgbAF_lrgba8), (init): added some more missing conversions. 2008-11-04 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (conv_rgbaF_rgbAF), (init): added missing, needed conversion. 2008-10-01 Øyvind Kolås <pippin@gimp.org> * COPYING.LESSER: renamed to .. * COPYING: 2008-07-09 Sven Neumann <sven@gimp.org> * babl/base/Makefile.am: `:='-style assignments are not portable 2008-07-04 Sven Neumann <sven@gimp.org> * extensions/Makefile.am: also use AM_CPPFLAGS and CPPFLAGS for building sse-fixups. 2008-07-01 Øyvind Kolås <pippin@gimp.org> * babl/babl-cpuaccel.c: added typedef size_t gsize to the set of gtypes lifted from glib. spotted by Marianne Gagnon. 2008-07-01 Øyvind Kolås <pippin@gimp.org> * extensions/Makefile.am: applied patch from dmacks at netspace.org cleaning up some of the build system. 2008-06-28 Zhang Junbo <zhangjb@svn.gnome.org> * extensions/frequency.c: changed RrRiG... back to RrGrBrArRiGiBiAi. 2008-06-27 Zhang Junbo <zhangjb@svn.gnome.org> * extensions/frequency.c: some work on frequency_to_rgba. 2008-06-27 Zhang Junbo <zhangjb@svn.gnome.org> * extensions/frequency.c: implemented frequency_to_rgba. 2008-06-22 Zhang Junbo <zhangjb@svn.gnome.org> * extensions/frequency.c: changed RrGrBr... into RrRiGrGiBrBiArAi. 2008-06-22 Zhang Junbo <zhangjb@svn.gnome.org> * extensions/frequency.c: added the format "frequency double". 2008-06-16 Sam Hocevar <sam@zoy.org> * Makefile.am: ensure that the "w3m must be available" message is properly displayed: dist-hook is only called after builddir is filled. 2008-06-13 Øyvind Kolås <pippin@gimp.org> * extensions/frequency.c: added dummy model "frequency" and dummy format "frequency float" to be used purely for creating, storing, accessing but not converting to and from normal tristimulus spaces. can be used by GeglBuffer to create frequency domain buffers that are processed in a similar manner to normal buffers. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * configure.ac: post release increment of version to 0.0.23 =========================== 0.0.22 released ============================= 2008-06-12 Øyvind Kolås <pippin@gimp.org> * configure.ac: incremented version. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: moved the babl directory overview here from the GEGL site. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: fixed indentation and misplaced ' spotted by Jan Heller. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: moved the BABL_TOLERANCE documentation paragraph in under Environment heading. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: removed markup mistake that introduced horizontal scrolling in gecko. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish-path.c: (legal_error): s/BABL_TOLERANCE/ * docs/index-static.html.in: s/BABL_ACCURACY/BABL_TOLERANCE/ 2008-06-12 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish-path.c: (legal_error): s/BABL_ERROR/BABL_ACCURACY/ * docs/index-static.html.in: s/BABL_ERROR/BABL_ACCURACY/ * AUTHORS: added a missing space. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * NEWS: added a html comment shortening the news shown. * docs/index-static.html.in: assed link to changelog in svn after news. Updated urls with s/viewcvs/viewvc/. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * Makefile.am: added TODO * docs/index-static.html.in: moved TODO list from here * TODO: to here, also edited it a bit. * docs/Makefile.am: include TODO in result. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: reindented code, documented BABL_ERROR. 2008-06-12 Øyvind Kolås <pippin@gimp.org> * AUTHORS: updated. * NEWS: updated. * docs/index-static.html.in: improved introduction and feature list. 2008-06-12 Jan Heller <jheller@svn.gnome.org> * extensions/sse-fixups.c (conv_rgbaF_linear_rgb8_linear), (conv_rgbaF_linear_rgba8_linear): Added fallback non-SSE routine if the input buffer is not aligned to 16 bytes. 2008-06-05 Jan Heller <jheller@svn.gnome.org> * AUTHORS: Updated contact info. 2008-06-03 Jan Heller <jheller@svn.gnome.org> * INSTALL.in: Updated download link. 2008-06-03 Jan Heller <jheller@svn.gnome.org> babl_get_version () moved into separate source file. * babl/Makefile.am: Added babl-version.c. * babl/babl-version.c (babl_get_version): Implemented. * babl/babl-version.h.in: Added babl_get_version () declaration. * babl/babl.c (babl_destroy): Removed babl_get_version (). * babl/babl.h: Removed babl_get_version () declaration. 2008-06-03 Jan Heller <jheller@svn.gnome.org> * babl/babl-version.h.in: Added. 2008-06-03 Jan Heller <jheller@svn.gnome.org> Added babl_get_version () to the public API. * babl/Makefile.am: Added babl-version.h to library_include_HEADERS. * babl/babl-version.h.in: Added macros to expand to babl version information. * babl/babl.c (babl_get_version): Implemented. * babl/babl.h: Include babl-version.h, declare babl_get_version (). * configure.ac: Added babl-version.h to AC_CONFIG_FILES. 2008-05-23 Jan Heller <jheller@svn.gnome.org> * extensions/sse-fixups.c (init): Fixed conditionally compiled code. 2008-05-23 Jan Heller <jheller@svn.gnome.org> Added support for CPU acceleration, RGBA float -> RGB u8 and RGBA float -> RGBA u8 SSE accelerated conversions. * babl/Makefile.am: Added babl-cpuaccel.[ch]. * babl/babl-cpuaccel.h: * babl/babl-cpuaccel.c (babl_cpu_accel_get_support), (babl_cpu_accel_set_use), (arch_get_vendor), (arch_accel_intel), (arch_accel_amd), (arch_accel_centaur), (arch_accel_cyrix), (sigill_handler), (arch_accel_sse_os_support), (arch_accel), (cpu_accel): Runtime CPU detection code. Ported from GIMP. * babl/babl-internal.h: Include babl-cpuaccel.h. * babl/babl-memory.c (babl_malloc): Make babl_malloc align memory to BABL_ALIGN==16 boundaries. * babl/babl.c (babl_init): Enabled CPU acceleration. * configure.ac: Added compile time MMX/SSE/AltiVec detection. Ported from GIMP. * extensions/Makefile.am: Added SSE_EXTRA_CFLAGS for sse-fixups.c compilation. * extensions/sse-fixups.c (conv_rgbaF_linear_rgb8_linear), (conv_rgbaF_linear_rgba8_linear), (init): Added RGBA float -> RGB u8 and RGBA float -> RGBA u8 SSE accelerated conversions. 2008-05-22 Jan Heller <jheller@svn.gnome.org> * extensions/util.h: changed fallback macro to have the same return type as rint(). 2008-05-21 Sven Neumann <sven@gimp.org> * babl/babl-internal.h (rint): changed fallback macro to have the same return type as rint(). 2008-05-21 Jan Heller <jheller@svn.gnome.org> * babl/babl-internal.h: * babl/base/type-u16.c: * babl/base/type-u32.c: * babl/base/type-u8.c: * extensions/CIE-Lab.c: * extensions/gegl-fixups.c: * extensions/gggl-lies.c: * extensions/gggl.c: * extensions/gimp-8bit.c: * extensions/util.h: fallback to floor function when rint function is not available. * configure.ac: added check for rint function. 2008-05-20 Jan Heller <jheller@svn.gnome.org> * extensions/gimp-8bit.c (conv_rgbaF_linear_rgb8_linear), (conv_rgbaF_linear_rgba8_linear), (init): added naive versions of respective conversions. 2008-05-14 Sven Neumann <sven@gimp.org> * babl/babl-format.c (format_new): initialize format.visited. * babl/babl-format.h * babl/babl-fish-path.c: formatting. 2008-04-16 Sven Neumann <sven@gimp.org> * babl/babl.h: formatting. 2008-04-16 Øyvind Kolås <pippin@gimp.org> * babl/babl.h: split up into ... Separate header files. * babl/babl-component.h: * babl/babl-conversion.h: * babl/babl-extension.h: * babl/babl-fish.h: * babl/babl-format.h: * babl/babl-image.h: * babl/babl-model.h: * babl/babl-sampling.h: * babl/babl-type.h: * babl/Makefile.am: install new headers. 2008-04-15 Øyvind Kolås <pippin@gimp.org> * babl/Makefile.am: removed babl-classes.h * babl/babl-classes.h: removed and mostly folded into ... * babl/babl.h: .. this file, which has been reorganized to contain each separate class by itself. * babl/babl-internal.h: simplified code renamed BABL_CLASS_TEMPLATE to be just BABL_CLASS or BABL_CLASS_MINIMAL. * babl/babl-fish.c: (babl_fish): do not accept varargs, use use BABL_CLASS_MINIMAL. * babl/babl-component.c: * babl/babl-conversion.c: * babl/babl-extension.c: * babl/babl-format.c: * babl/babl-model.c: * babl/babl-type.c: use BABL_CLASS instead of BABL_CLASS_TEMPLATE * babl/babl-hash-table.h: * babl/babl-list.h: * babl/babl-db.h: changed include warning since babl-classes doesn't exist anymore. 2008-04-15 Sven Neumann <sven@gimp.org> * extensions/util.h * babl/*.[ch]: removed trailing whitespace. 2008-04-15 Sven Neumann <sven@gimp.org> * babl/babl-fish-path.c (init_path_instrumentation): this function has no return value, declare it as void. 2008-04-13 Øyvind Kolås <pippin@gimp.org> Applied patch from Jan Heller. * babl/babl-fish-path.c: (get_conversion_path), (babl_fish_path), (test_create), (init_path_instrumentation), (destroy_path_instrumentation), (get_path_instrumentation): Improved fish path instrumentation during the search for a new one to optimize for speed. Added logic to disallow creation of a fish path that is actually slower than appropriate reference fish. * babl/babl-util.[ch]: (babl_process_cost): New function for unified timing formula for babl processings. * babl/babl-conversion.c: (babl_conversion_error): Make use of the new babl_process_cost function. * extensions/gimp-8bit.c: Added a function declaration to prevent compiler warning. 2008-04-08 Øyvind Kolås <pippin@gimp.org> Applied patch from Jan Heller that improves logic of go_fishing code in babl-fish.c. The current code searches list of all fishes while looking for suitable preexistent BABL_FISH_PATH instance. The new code only searches relevant part of database's hash table. Further, the current code searches for fish path every time such a babl fish is requested, even though the same fish path has been requested before and not found. The new code creates dummy BABL_FISH instance with appropriate source/destination formats and inserts it into the fish database to indicate that fish path has been searched for and not found. * babl/babl-fish.c: (find_fish_path), (find_memcpy_fish), (babl_fish_get_id), (babl_fish): * babl/babl-fish-path.c: (babl_fish_path): * babl/babl-fish-reference.c: (babl_fish_reference): * babl/babl-fish-simple.c: (babl_fish_simple): * babl/babl-internal.h: 2008-04-06 Sven Neumann <sven@gimp.org> * acinclude.m4: new file defining BABL_DETECT_CFLAGS() macro. * configure.ac: set CFLAGS to get some extra compiler warnings. * babl/babl-fish-stats.c (conversions): fixed old-style function definition. * Makefile.am: formatting. 2008-04-02 Mukund Sivaraman <muks@mukund.org> Sparse fixes. * babl/babl-internal.h: fflush() takes pointer. * babl/babl-conversion.c: Don't mix code and declarations. * babl/babl-fish-reference.c: Fixed array assignment. 2008-04-03 Øyvind Kolås <pippin@gimp.org> Applied patch from Jan Heller that ports BablFishPath class to the new list API and the list API is a bit expanded. Further, the algorithm for generating the shortest conversion path is reformulated to be more readable and comprehensible and thoroughly commented. The algorithm for processing the conversion paths is reformulated and commented. Also contains minor readability cleanups and speedups. * babl/babl-classes.h: * babl/babl-conversion.c: * babl/babl-db.c: * babl/babl-fish-path.c: * babl/babl-fish-stats.c: * babl/babl-fish.c: * babl/babl-list.c: * babl/babl-list.h: * tests/babl_fish_path_fitness.c: 2008-04-01 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: * babl/babl-conversion.c: * babl/babl-db.c: * babl/babl-fish-path.c: * babl/babl-fish.c: * babl/babl-format.c: * babl/babl-internal.h: * babl/babl-introspect.c: * babl/babl-list.c: * babl/babl-list.h: * babl/babl-model.c: * babl/babl-sampling.c: * babl/babl-sanity.c: * babl/babl-type.c: * babl/babl-util.[ch]: applied patch from Jan Heller that improves readability by using the newly introduced BablList structure. 2008-03-31 Sven Neumann <sven@gimp.org> * AUTHORS: added Jan Heller and obfuscated the email addresses. 2008-03-29 Sven Neumann <sven@gimp.org> * babl/babl-component.c * babl/babl-conversion.c * babl/babl-db.c * babl/babl-extension.c * babl/babl-fish-path.c * babl/babl-fish-reference.c * babl/babl-fish-simple.c * babl/babl-format.c * babl/babl-model.c * babl/babl-type.c: applied patch from Jan Heller that changes the code to test for a pre-existent instance of a babl class in the database before creating a new one. 2008-03-24 Tor Lillqvist <tml@novell.com> * babl/babl-type.c: Make the "test" array static. 2008-03-23 Martin Nordholts <martinn@svn.gnome.org> * babl/babl-memory.[ch]: typedef:ed BABL free and malloc function pointers. 2008-03-22 Sven Neumann <sven@gimp.org> Applied patch from Jan Heller that introduces list and hash table functionality and changes the babl database to use coalesced hashing (bug #523507). This considerably improves BABL performance. * babl/Makefile.am * babl/babl-list.[ch] * babl/babl-hash-table.[ch]: new files providing list and hash table functionality. * babl/babl-internal.h: include the new header files. * babl/babl-db.[ch]: use the new code. * babl/babl-fish.c: changed accordingly. 2008-03-16 Mukund Sivaraman <muks@mukund.org> * babl/babl-extension.c: getenv() can return NULL. * babl/babl-memory.c: Check for NULL in babl_strcat(). 2008-03-16 Mukund Sivaraman <muks@mukund.org> * babl/babl-image.c: Added missing va_end()s. 2008-03-16 Mukund Sivaraman <muks@mukund.org> * babl/babl-extension.c: Added missing dlclose()s. 2008-03-02 Øyvind Kolås <pippin@gimp.org> * babl.pc.in: do not add @DL_LIBS@ to link line of babl. 2008-03-02 Øyvind Kolås <pippin@gimp.org> * tests/Makefile.am: applied patch from dmacks@netspace.org for bug #519794. 2008-03-02 Øyvind Kolås <pippin@gimp.org> Applied patch from dmacks@netspace.org closing bug #519796 * configure.ac: * babl/Makefile.am: * tests/Makefile.am: Only -ldl if required, passed automatically via $LIBS 2008-02-27 Øyvind Kolås <pippin@gimp.org> * configure.ac: post release version increment to 0.0.21 =========================== 0.0.20 released ============================= 2008-02-27 Øyvind Kolås <pippin@gimp.org> * NEWS: updated for 0.0.20 release. * configure.ac: incremented version. 2008-02-27 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: use mktemp instead of tempfile. 2008-02-27 Øyvind Kolås <pippin@gimp.org> * extensions/Makefile.am: -I$(top_builddir) to be able to include config.h 2008-02-19 Sven Neumann <sven@gimp.org> * babl/babl-fish-path.c (test_create): add some extra pixels outside the valid range to fix issues with wrong clamping of conversions. 2008-02-19 Sven Neumann <sven@gimp.org> * babl/babl-fish-path.c: renamed test_pixels to num_test_pixels. 2008-02-19 Sven Neumann <sven@gimp.org> * babl/babl-fish-path.c (test_create): reverted previous change as it introduces the risk of not testing any values between 0.0 and 1.0. 2008-02-19 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish-path.c: (test_create): make the testbuffer contain values in the range -0.25 .. 1.75 instead of 0.0 .. 1.0, might fix issues with wrong clamping of float->8bit conversions. 2008-02-15 Øyvind Kolås <pippin@gimp.org> * configure.ac: cleaned up win32 detection vs plug-in compilation specifics, added DYNAMICLIB paramter for gcc which defaults to -shared for win32 and -dynamiclib for darwin. * extensions/Makefile.am: use $(DYNAMICLIB) instead of -shared. 2008-02-11 Kevin Cozens <kcozens@cvs.gnome.org> * configure.ac: Set shrext to ".dylib" for Darwin (ie. Mac OS). * babl/babl-extension.c: Use BABL_DIR_SEPARATOR instead of "/". 2008-01-22 Sven Neumann <sven@gimp.org> * extensions/gimp-8bit.c (u8_gamma_2_2_to_float_linear): use the correct lookup table. 2008-01-20 Øyvind Kolås <pippin@gimp.org> Always use BablFishPath's for accepted conversions. The path construction code is the location of the regression test, an earlier (now unneeded) optimization allowed using the first and best conversion available. The (not in bugzilla afair) bug manifest by this depended on the order of .so's on the file system to manifest itself. * babl/babl-fish.c: (go_fishing): only accepts paths when we go fishing for existing conversions. (babl_fish): elaborated a comment about why we avoid shortcut conversions and only paths. 2008-01-17 Øyvind Kolås <pippin@gimp.org> Applied patch from Deji Akingunola <dakingun@gmail.com> to make babl correctly pick up the path to the extensions on 64bit systems. Fixes bug #510038 * babl/Makefile.am: added -DLIBDIR * babl/babl-extension.c: use libdir and not PREFIX "/lib" when defining the default BABL_PATH. 2008-01-10 Sven Neumann <sven@gimp.org> * extensions/gimp-8bit.c: added extension to speed up code paths that are executed by the GIMP/GEGL hybrid. So far only 8bit to float conversions are handled. 2008-01-10 Sven Neumann <sven@gimp.org> * extensions/Makefile.am: extended CFLAGS so that config.h can be included. * extensions/*.c: fixed up includes. * extensions/gegl-fixups.c: use linear <-> gamma conversions from base/util.c. 2008-01-07 Kevin Cozens <kcozens@cvs.gnome.org> * babl/babl-extension.c (babl_extension_load_dir): Reverted previous change. BABL hasn't been updated to use gmodule (yet). 2008-01-07 Kevin Cozens <kcozens@cvs.gnome.org> * babl/babl-extension.c (babl_extension_load_dir): Use G_MODULE_SUFFIX instead of a hard-coded suffix. 2008-01-06 Sven Neumann <sven@gimp.org> * extensions/CIE-Lab.c: made internal functions static. 2007-12-30 Sven Neumann <sven@gimp.org> * extensions/gggl-lies.c (table_init): completely fill the lookup tables for conversion from float to integer. 2007-12-30 Kevin Cozens <kcozens@cvs.gnome.org> * extensions/Makefile.am: Use SHREXT instead of hard-coded ".so". 2007-12-30 Øyvind Kolås <pippin@gimp.org> * configure.ac: post release version increment to 0.0.19 =========================== 0.0.18 released ============================= 2007-12-30 Øyvind Kolås <pippin@gimp.org> * NEWS: updated for 0.0.18 release * configure.ac: increased version to 0.0.18 for release. 2007-12-29 Michael Natterer <mitch@gimp.org> * babl/babl-fish-path.c (chain_contains_fmt): one const was forgotten. 2007-12-29 Øyvind Kolås <pippin@gimp.org> * babl/babl.h: * babl/babl-classes.h: * babl/babl-fish-path.c: * babl/babl-fish-reference.c: * babl/babl-fish.c: * babl/babl-internal.[ch]: Const'ified code with Babl*'s refering to formats. 2007-02-17 Øyvind Kolås <pippin@gimp.org> * configure.ac: post release version increment to 0.0.17 =========================== 0.0.16 released ============================= 2007-02-17 Øyvind Kolås <pippin@gimp.org> * configure.ac: increased version to 0.0.16 for release. 2007-11-25 Øyvind Kolås <pippin@gimp.org> * babl/babl-image.c: (babl_image_from_linear): do additional casts to silence warnings from compiler. 2007-11-25 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: changed documentation to use babl_format instead of passing naked strings into babl_fish, (both will work, but using babl_format is a bit saner). 2007-11-25 Øyvind Kolås <pippin@gimp.org> * NEWS: updated. * Makefile.am: added COPYING and COPYING.LESSER * docs/Makefile.am: added COPYING and COPYING.LESSER 2007-11-13 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish.c: (babl_fish_process): swapped source and destination around in memcpy. 2007-11-13 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish.c: (go_fishing): optimized fishing when looking up existing fish (should perhaps be moved to lists going from given formats, similar to how conversions are added there instead.) Made go_fishing accept BABL_FISH_REFERENCE when source and desintation formats are equal. (babl_fish_process): removed most of the need for BablImage for linear buffers, do a memcpy when source and destination formats are equal (and we're a BABL_FISH_REFERENCE). * babl/babl-db.[ch]: moved the BablDb struct out into public to allow faster iteration through it. 2007-11-11 Øyvind Kolås <pippin@gimp.org> * Modified copyright statement to refer to an URL instead of a civic address for the Free Software Foundation and the text of the license. 2007-11-11 Øyvind Kolås <pippin@gimp.org> Keep a cache of the linear version of BablImage's needed for BablFormats around. This reduces the constant overhead for conversions. * babl/babl-classes.h: added .image_template field to BablFormat. * babl/babl-format.c: (format_new): make .image_template NULL by defualt. * babl/babl-image.c: (babl_image_from_linear): use .image_template if available instead of creating our own BablImage from scratch. * babl/babl-memory.c: (babl_free): special case freeing of BablImage and BablFormat to do the extra juggling needed for the image_template cache. 2007-11-10 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish-stats.c: (table_destination_each): improve visualization of results. 2007-11-10 Øyvind Kolås <pippin@gimp.org> * babl/babl-db.c: (babl_db_each_inline), (babl_db_exist): Optimized lookup by adding an inline version of babl_db_each specially for babl_db_exist. 2007-11-10 Øyvind Kolås <pippin@gimp.org> Do not accept BABL_FISH_REFERENCE as a valid result when fishing for existing fishes. * babl/babl-fish.c: (fishing_result_examine), (babl_fish): 2007-11-10 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: documented BABL_STATS environment variable. 2007-11-09 Øyvind Kolås <pippin@gimp.org> Upgraded babl from LGPLv2 to LGPLv3. Copyright statements in all files have been updated to reflect this change, the permission to use leter versions of the GNU licenses have been retained in all instances.) * COPYING: changed to GPLv3 * COPYING.LESSER: added (LGPLv3's overlay over GPLv3) 2007-10-30 Michael Schumacher <schumaml@cvs.gnome.org> * configure.ac: DIR_SEP='\' is evil, use DIR_SEP='\\' instead. 2007-09-14 Kevin Cozens <kcozens@cvs.gnome.org> * configure.ac: Define name of babl library file. * babl/babl-extension.c: Use name of babl library defined when ./configure was run. 2007-09-14 Kevin Cozens <kcozens@cvs.gnome.org> Changes to let BABL find its extensions at run time when the BABL_PATH environment variable is not set. * configure.ac: Don't specify BABL_PATH in here. Renamed BABL_LIST_SEPERATOR to BABL_DIR_SEPARATOR. * babl/babl-extension.c: Include /lib as part of default BABL_PATH. Renamed #define's used to specify the path and directory separators. Use the values from config.h that were set when ./configure was run. 2007-09-11 Kevin Cozens <kcozens@cvs.gnome.org> * autogen.sh: Added check for existence of automake-1.10. Fixes bug #474507. 2007-09-10 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.c: (babl_process): return immediately if 0 pixels were requested to be processed. 2007-09-01 Øyvind Kolås <pippin@gimp.org> * MAINTAINERS: added. 2007-08-30 Øyvind Kolås <pippin@gimp.org> Applied patch from Kevin Cozens fixing bug #467652 * babl/Makefile.am: Use DL flag set by ./configure instead of hard-coding it in Makefile 2007-08-02 Kevin Cozens <kcozens@cvs.gnome.org> * extensions/gggl.c * extensions/gggl-lies.c: Only include math.h once. 2007-08-01 Øyvind Kolås <pippin@gimp.org> Fixed compiler abort on certain LDFLAGS values (-Wl,-z,defs) by applying patch from christopher taylor, closing bug #462536. * babl/Makefile.am: * extensions/Makefile.am: 2007-03-21 Øyvind Kolås <pippin@gimp.org> Reindented all of the code using uncrustify. 2007-03-21 Øyvind Kolås <pippin@gimp.org> * configure.ac: Make force the value of shrext to either .dll or .so (it seems like it wasn't defined for unixy systems after all). 2007-03-13 Michael Schumacher <schumaml@cvs.gnome.org> * configure.ac: use PATHSEP (platform-dependent, defined to ';' on win32) for BABL_LIST_SEPERATOR 2007-03-13 Michael Schumacher <schumaml@cvs.gnome.org> * configure.ac: AC_SUBST and AC_DEFINE $shrext into variables for Makefiles and source. * extension/Makefile.am: use $(SHREXT) instead of .$SOext. * babl/babl-extension.c: use SHREXT instead of a hardcoded ".so" and get rid of a dirent->d_ino > 0 check which has been there for reasons unknown. 2007-03-12 Michael Schumacher <schumaml@cvs.gnome.org> * Makefile.am: * extensions/Makefile.am: applied patch by John Marshall to make babl extensions build on Windows. They do not work yet, though. Fixes bug #409957. 2007-03-12 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish.c: (fishing_result_examine), (go_fishing), (babl_fish): go fishing for an existing fish for the source/destination combination before trying to create one. 2007-02-22 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: make _Babl be a typedef and not a union that gets included and defined for every single object generated. Fixes bug #409781. 2007-02-18 Øyvind Kolås <pippin@gimp.org> * configure.ac: post release increment to 0.0.15 =========================== 0.0.14 released ============================= 2007-02-17 Øyvind Kolås <pippin@gimp.org> * configure.ac: increased version to 0.0.14 for release. 2007-02-17 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: adds, reordering and trimming of information in webpage. 2007-02-17 Øyvind Kolås <pippin@gimp.org> * babl/base/model-gray.c: removed obsoleted FIXME. 2007-02-17 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: reincorporate NEWS, added link to extensions dir in subversion. 2007-02-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish-path.c: (legal_error), (max_path_length): cache the values looked up from BABL_ERROR and BABL_PATH_LENGTH environment variables, changed default maximum conversion path length from 3 to 4. 2007-02-16 Øyvind Kolås <pippin@gimp.org> * babl/base/formats.c: (babl_formats_init): specify Y'CbCrA model instead of Y'CbCr for Y'CbCrA float. 2007-02-15 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (conv_rgbAF_rgb8): simplified logic of code to speed it up. 2007-02-15 Øyvind Kolås <pippin@gimp.org> * babl/base/model-rgb.c: (premultiplied_to_non_premultiplied), (rgba_gamma_2_2_premultiplied2rgba): avoid divisions by zero, thus making the reference conversions correct. 2007-02-11 Øyvind Kolås <pippin@gimp.org> * NEWS: updated news for many versions. 2007-02-09 Kevin Cozens <kcozens@cvs.gnome.org> * autogen.sh: Changed CVS reference to SVN. * configure.ac: Set BABL_UNSTABLE to 1 for odd micro numbers when major and minor are both 0. * babl.pc.in * babl/Makefile.am * tests/Makefile.am: Use version number in library name. 2007-02-09 Kevin Cozens <kcozens@cvs.gnome.org> * babl/Makefile.am * babl/base/Makefile.am * docs/graphics/Makefile.am: Removed references to .cvsignore. * docs/Makefile.am: Removed reference to .cvsignore. Removed ^M from end of lines. 2007-01-31 Øyvind Kolås <pippin@gimp.org> Removed .cvsignore files. 2007-01-07 Øyvind Kolås <pippin@gimp.org> * configure.ac: set version to 0.0.13 =========================== 0.0.12 released ============================= 2007-01-07 Øyvind Kolås <pippin@gimp.org> * configure.ac: set version to 0.0.12 2007-01-28 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: things are not in CVS but SVN now. 2007-01-28 Øyvind Kolås <pippin@gimp.org> * babl/babl-conversion.c: (babl_conversion_new): shut up compiler warning. 2007-01-28 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (init): give names to the custom formats. 2007-01-28 Øyvind Kolås <pippin@gimp.org> * AUTHORS: added Michael Natterer as janitor. 2007-01-28 Øyvind Kolås <pippin@gimp.org> * AUTHORS: added Tim Mooney 2007-01-28 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: (conv_bgrA8_rgba8), (init): added optimized permutator for going from cairo's buffer format to RGBA byte order, as well as unpremultiplying. 2007-01-28 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: fixed gamma conversion. 2007-01-22 Michael Schumacher <schumaml@cvs.gnome.org> * docs/Makefile.am: declare the test programs used during doc creating as variables to keep the commands in targets readable. 2007-01-22 Øyvind Kolås <pippin@gimp.org> Applied patch from Tim Mooney fixing bug #392916 * extensions/Makefile.am: $(prefix)/lib/babl-0.0 for its extensions dir, which is incorrect for many 64 bit platforms. It should instead use $(libdir)/babl-0.0. 2007-01-22 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.h: applied patch from Tim Mooney fixing bug #392843, replacing _FUNCTION_ with _func_ which is the C99 equivalent of the gcc extension. 2007-01-16 Michael Schumacher <schumaml@cvs.gnome.org> * configure.ac: remove the check for dlopen again - didn't work as intended * babl/babl-extension.c: for #idfef WIN32, #define dl* functions to their Windows equivalents (LoadLibrary, GetProcAddress, FreeLibrary). 2007-01-08 Øyvind Kolås <pippin@gimp.org> * babl/babl-extension.c: define HAVE_DLOPEN if HAVE_DLFCN is set. 2007-01-07 Øyvind Kolås <pippin@gimp.org> * configure.ac: set version to 0.0.11 =========================== 0.0.10 released ============================= 2007-01-07 Øyvind Kolås <pippin@gimp.org> * configure.ac: set version to 0.0.10 * docs/index-static.html.in: reworded things due to the subversion switch. 2007-01-06 Michael Schumacher <schumaml@cvs.gnome.org> This change makes babl buildable on Windows. * configure.ac: Add a check for function dlopen and disabled static libs by default. Check for gettimeofday by using AC_REPLACE_FUNCS. * babl/babl-internal.h: Add definitions for srandom and radnom to srand and rand for the windows platform. * babl/babl-conversion.c * babl-model.c: Include babl-internal.h after math.h * babl/babl-extension.c: Use #ifdef HAVE_DLOPEN to hide dl* if it is not available. * babl/Makefile.am: Removed win32_libs and added @LTLIBOBJS@ to LIBADD to get the replacement for gettimeofday linked in if needed. * babl/gettimeofday.c: New file to provide a replacement for gettimeofday, only used on Windows yet. 2007-01-06 Michael Schumacher <schumaml@cvs.gnome.org> * Makefile.am: don't go into the extensions subdirectory on Windows * extensions/Makefile.am: removed the win32_libs definition, using libgw32c does more harm than good, apparently 2007-01-06 Michael Schumacher <schumaml@cvs.gnome.org> * docs/Makefile.am: added EXEEXT to the tools used in some commands * docs/tools/changelog2rss: remove unused SET_TITLE and LISTING_TYPE; the former did cause an error on Windows 2007-01-01 Kevin Cozens <kcozens@cvs.gnome.org> * docs/index-static.html.in: Fixes for various punctuation, grammar, and typographical errors. 2007-01-01 Kevin Cozens <kcozens@cvs.gnome.org> * configure.ac: Changes to properly (or at least better) version the babl library. * babl.pc.in: It is too soon to include version information in the name of the babl library at link time. 2007-01-01 Kevin Cozens <kcozens@cvs.gnome.org> Some changes to fix build problems in FreeBSD and Windows. * configure.ac: Added missing m4 defines specifying version numbers, and tests for libdl and libm (sets DL_LIB and MATH_LIB respectively). * babl.pc.in: Replaced several hard-coded items with ones defined when configure is run. * babl/base/Makefile.am: * extensions/Makefile.am: * tests/Makefile.am: Use $(DL_LIB) and $(MATH_LIB) instead of hard-coded options. 2006-12-29 Øyvind Kolås <pippin@gimp.org> * configure.ac: set the version of babl to 0.0.9 =========================== 0.0.8 released ============================= 2006-12-29 Øyvind Kolås <pippin@gimp.org> * configure.ac: set the version of babl to 0.0.8 2006-12-29 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: include changelog2rss script. 2006-11-17 Øyvind Kolås <pippin@gimp.org> Make babl compile with stricter compiler warnings, mostly related to changing pointer arith from void* to char*. * babl/babl-classes.h: * babl/babl-component.c: (component_new): * babl/babl-conversion.c: (conversion_new), (babl_conversion_planar_process), (babl_conversion_process): * babl/babl-core.c: (convert_double_double), (rgba_to_rgba): * babl/babl-extension.c: (extension_new): * babl/babl-fish-path.c: (babl_fish_path): * babl/babl-fish-reference.c: (babl_fish_reference), (convert_to_double), (convert_from_double), (process_same_model), (babl_fish_reference_process): * babl/babl-fish-simple.c: (babl_fish_simple): * babl/babl-fish.c: (babl_fish_process): * babl/babl-format.c: (format_new): * babl/babl-image.c: (image_new), (babl_image_from_linear), (babl_image): * babl/babl-internal.h: * babl/babl-memory.c: (babl_malloc): * babl/babl-model.c: (model_new): * babl/babl-type.c: (type_new), (r_interval), (test_init): * babl/base/babl-base.c: * babl/base/babl-base.h: * babl/base/formats.c: * babl/base/model-gray.c: (rgba_to_graya), (rgba_to_gray), (rgb_to_gray_2_2), (gray_2_2_to_rgb), (graya_to_rgba), (gray_to_rgba), (gray_alpha_premultiplied_to_rgba), (rgba_to_gray_alpha_premultiplied), (non_premultiplied_to_premultiplied), (premultiplied_to_non_premultiplied), (rgba2gray_gamma_2_2_premultiplied), (gray_gamma_2_2_premultiplied2rgba): * babl/base/model-rgb.c: (copy_strip_1), (g3_gamma_2_2), (g3_inv_gamma_2_2), (non_premultiplied_to_premultiplied), (premultiplied_to_non_premultiplied), (rgba2rgba_gamma_2_2_premultiplied), (rgba_gamma_2_2_premultiplied2rgba), (rgba2rgba_gamma_2_2), (rgba_gamma_2_22rgba): * babl/base/model-ycbcr.c: (rgba_to_ycbcra), (rgba_to_ycbcr), (ycbcra_to_rgba), (ycbcr_to_rgba): * babl/base/type-float.c: (convert_double_float), (convert_float_double): * babl/base/type-u16.c: (convert_double_u16_scaled), (convert_u16_double_scaled): * babl/base/type-u32.c: (convert_double_u32_scaled), (convert_u32_double_scaled): * babl/base/type-u8.c: (convert_double_u8_scaled), (convert_u8_double_scaled): * extensions/CIE-Lab.c: (rgba_to_lab), (lab_to_rgba), (rgba_to_laba), (laba_to_rgba), (convert_double_u8_scaled), (convert_u8_double_scaled), (convert_double_u16_scaled), (convert_u16_double_scaled): * extensions/gegl-fixups.c: (conv_F_8), (conv_8_F): * extensions/gggl-lies.c: (conv_F_8), (conv_F_16), (conv_8_F), (conv_16_F): * extensions/gggl.c: (conv_F_8), (conv_F_16), (conv_8_F), (conv_16_F): * extensions/naive-CMYK.c: (rgba_to_cmyk), (cmyk_to_rgba): * tests/babl-html-dump.c: (normalize): * tests/babl_class_name.c: * tests/formats.c: (format_check): * tests/grayscale_to_rgb.c: * tests/models.c: (model_check): * tests/rgb_to_bgr.c: * tests/rgb_to_ycbcr.c: * tests/srgb_to_lab_u8.c: * tests/types.c: (type_check): 2006-11-15 Øyvind Kolås <pippin@gimp.org> Set the default BABL_PATH based on the prefix babl is compiled for. * babl/Makefile.am: * babl/babl-extension.c: 2006-11-07 Øyvind Kolås <pippin@gimp.org> * extensions/CIE-Lab.c: (formats): added "CIE Lab alpha float" as a default format. 2006-08-31 Øyvind Kolås <pippin@gimp.org> * configure.ac: set the version of babl to 0.0.7 =========================== 0.0.6 released ============================= 2006-08-31 Øyvind Kolås <pippin@gimp.org> * configure.ac: set the version of babl to 0.0.6 2006-10-09 Øyvind Kolås <pippin@gimp.org> Cleaned up the typedef for Babl, fixes issues with g++. * babl/babl-classes.h: * babl/babl-conversion.c: (conversion_new): * babl/babl-fish-path.c: (babl_fish_path): * babl/babl-fish-reference.c: (babl_fish_reference): * babl/babl-fish-simple.c: (babl_fish_simple): 2006-09-26 Dominik Ernst <dernst@gmx.de> * babl/babl-classes.h: fixed an issue with g++ 2006-09-23 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: output the conversion grid when building on crucible. 2006-09-14 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.c: (babl_process): added global babl_total_usecs, not exported through headers, but useful to be able to substract the babl conversion time from other algorithms using babl. 2006-09-12 Øyvind Kolås <pippin@gimp.org> * autogen.sh: decreased required automake version to 1.7.9. (It could probably be decreased even further, but this is at least known to work.) 2006-09-12 Michael Schumacher <schumaml@cvs.gnome.org> * autogen.sh: use the autogen.sh of GIMP as a base for babl's autogen.sh. Among other things, this enables maintainer mode by default. 2006-09-10 Kevin Cozens <kcozens@cvs.gnome.org> * babl/babl-classes.h * babl/babl-conversion.c * babl/babl-fish-path.c * babl/babl-fish-stats.c * babl/babl-internal.c: Tick times are in usecs not msecs. Use longs to hold tick values. * babl/babl-util.h: * babl/babl-util.c (babl_ticks): Fixed calculation of time (usecs not msecs). Changed declaration to return a long not unsigned int. 2006-09-09 Øyvind Kolås <pippin@gimp.org> * extensions/Makefile.am: moved -fPIC from LD_FLAGS to CFLAGS. 2006-09-08 Øyvind Kolås <pippin@gimp.org> * extensions/Makefile.am: added -fPIC to LD_FLAGS, thus making it compile on 64bit archs as well. 2006-09-04 Michael Schumacher <schumaml@cvs.gnome.org> * extensions/Makefile.am: have to link with libbabl.a, at least on the Windows platforms 2006-08-31 Øyvind Kolås <pippin@gimp.org> * extensions/.cvsignore: added Makefile.in 2006-08-31 Øyvind Kolås <pippin@gimp.org> * configure.ac: set the version of babl to 0.0.5 (odd micro indicating that it is a CVS version). =========================== 0.0.4 released ============================= 2006-08-31 Øyvind Kolås <pippin@gimp.org> * configure.ac: set the version of babl to 0.0.4 * docs/index-static.html.in: added downloading location for tarballs of babl. * AUTHORS: Added Kevin Cozens 2006-08-31 Øyvind Kolås <pippin@gimp.org> * Makefile.am: added a dependency on all for README, making it possible to do ./autogen.sh && make distcheck #from a clean CVS checkout. 2006-08-28 Kevin Cozens <kcozens@cvs.gnome.org> * configure.ac: Added AM_MAINTAINER_MODE. * docs/Makefile.am: Moved BablFishPath.txt to BUILT_EXTRA_DIST. * tests/Makefile.am: Removed .cvsignore from EXTRA_DIST. 2006-08-28 Kevin Cozens <kcozens@cvs.gnome.org> Changes to get 'make distcheck' working properly. * docs/Makefile.am: Added BablFishPath.txt to DISTCLEANFILES. * extensions/Makefile.am: Added. * extensions/Makefile.in: Removed (replaced by Makefile.am). 2006-08-25 Michael Schumacher <schumaml@cvs.gnome.org> * configure.ac: added AC_LIBTOOL_WIN32_DLL as a preparation for proper builds of shared libs on win32 & there's no need to define OS_WIN32 here... * babl/babl-extension.c: ...if the only place where it is needed can be handled by HAVE_DLFCN_H 2006-08-24 Øyvind Kolås <pippin@gimp.org> * extensions/Makefile.in: do not add libbabl.a into plug-ins 2006-07-06 Øyvind Kolås <pippin@gimp.org> * babl.pc.in: Added -lm to the list of libraries that need to be linked along with babl. 2006-06-24 Øyvind Kolås <pippin@gimp.org> * babl.pc.in: stripped trailing /babl from CFLAGS include path. 2006-06-12 Øyvind Kolås <pippin@gimp.org> Do not expect the user to pass in BablImages (existance of babl pointer decorations should not be allowed to be used to implement type checking for provided buffers/bablimages) * babl/babl-fish.c: (babl_fish_process): * babl/babl-fish-reference.c: (babl_fish_reference_process): * docs/index-static.html.in: removed section about planar BablImages since the API is now disabled. 2006-06-06 Øyvind Kolås <pippin@gimp.org> Register all the formats that the gggl based conversions use in babl-base. This allows a string based short hand vocabulary of format names that can be expected to exist. * babl/base/Makefile.am: added formats.c * babl/base/babl-base.c: (babl_base_init): initialize formats. 2006-06-06 Øyvind Kolås <pippin@gimp.org> Added conversions based on gggl that assume no gamma in their conversions. * extensions/gggl-lies.c: Added. 2006-06-06 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: redirect the check for tempfile to /dev/null * docs/tools/xml_insert.sh: Add tempfile workaround here as well. 2006-06-06 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: Do not rely that a command calle tempfile exists. 2006-06-05 Øyvind Kolås <pippin@gimp.org> * extensions/gegl-fixups.c: A babl extension to make the testing of gegl faster. 2006-06-02 Øyvind Kolås <pippin@gimp.org> * extensions/gggl.c: (table_init): Fix some compile warnings. 2006-06-02 Øyvind Kolås <pippin@gimp.org> I'm not entirely sure about installing babl-classes.h like this, it might make more sense to create setters/getters to be used. Thus making it possible to extend the structs at a later stage without breaking binary compatibility. * babl/Makefile.am: Added babl-classes.h to the installed headers * babl/babl-classes.h: Made the magic number fit in 32bit int. * babl/babl.h: include babl-classes.h 2006-02-22 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: added a link to the DHTML version of the coverage map. 2006-02-22 Øyvind Kolås <pippin@gimp.org> * extensions/gggl.c: (conv_rgbaF_rgb8), (conv_rgbAF_rgbF), (init): added two more conversions for gggl usage. 2005-12-17 Michael Schumacher <schumaml@cvs.gnome.org> * extensions/Makefile.in: add libgw32 and its dependencies to LDADD for the win32 platform 2005-11-10 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: Minor reformulations and spelling fixes. 2005-11-08 Sven Neumann <sven@gimp.org> * configure.ac: use AM_CONFIG_HEADER instead of AC_CONFIG_HEADERS. 2005-11-04 Øyvind Kolås <pippin@gimp.org> * babl/babl-format.c: (create_name): fixed an invalid memory access in comparision of component order (and now also length.) 2005-10-08 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: Fixed the second processing example. ( added missing pixel_count) 2005-09-27 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: Added time consumption instrumentation to BablFish. * babl/babl-fish-path.c: (babl_fish_path), (babl_fish_path_process): intialization of instrumentation data. * babl/babl-fish-stats.c: (table_destination_each), (each_conv), (conversions), (babl_fish_stats): Output timing data, as well as a list of all conversions with the obviously bad ones marked in red. * babl/babl-internal.c: (babl_process): update instrumentation. * babl/babl-introspect.c: (conversion_introspect): only query error from conversions where that is legal. * babl/babl-util.c: changed from msecs to nsecs (might be some more places in the code to change names of variables.) * extensions/gggl.c: (conv_gF_gaF), (conv_gF_rgbF), (conv_rgbF_gF), (conv_rgbaF_rgb8): Changes to increase sanity. 2005-09-27 Øyvind Kolås <pippin@gimp.org> * tests/srgb_to_lab_u8.c: (test): renamed format (srgb -> R'G'B' u8) 2005-09-27 Øyvind Kolås <pippin@gimp.org> Updates done due to improvements gotten from BablFishStat feedback. * babl/base/model-gray.c: (components), (models), (rgba2gray_gamma_2_2_premultiplied), (gray_gamma_2_2_premultiplied2rgba), (conversions): * babl/base/model-rgb.c: (components), (models), (copy_strip_1), (g3_gamma_2_2), (g3_inv_gamma_2_2), (non_premultiplied_to_premultiplied), (premultiplied_to_non_premultiplied), (rgba2rgba_gamma_2_2_premultiplied), (rgba_gamma_2_2_premultiplied2rgba), (rgba2rgba_gamma_2_2), (rgba_gamma_2_22rgba), (conversions), (formats): * babl/base/model-ycbcr.c: (models), (formats): * docs/index-static.html.in: * extensions/gggl.c: (conv_F_8), (conv_8_F), (conv_F_D), (conv_D_F), (conv_rgba8_rgbaF), (conv_rgb8_rgbF), (conv_ga8_gaF), (conv_rgbaF_rgbaD), (conv_rgbaD_rgbaF), (conv_rgbAF_rgbaF), (conv_rgbaF_rgbAF), (conv_rgbaF_rgbF), (conv_rgbF_rgbaF), (conv_rgbaF_gaF), (conv_rgbaF_rgb8), (conv_rgbA16_rgbaF), (conv_rgb8_rgba8), (conv_rgbA8_rgb8), (init): 2005-09-27 Øyvind Kolås <pippin@gimp.org> Upgrade of BablFishPath. * babl/babl-fish-path.c: (legal_error), (max_path_length), (get_conversion_chain), (chain_contains_fmt), (chain_gen_each), (babl_fish_path), (chain_process), (babl_fish_path_process), (test_create), (chain_error): Various updates, needed instrumentation and error data is now calculated and cached. * babl/babl-fish-reference.c: (babl_fish_reference): do not update instrumentation for internal calls. * babl/babl-fish-simple.c: (babl_fish_simple): do not update instrumentation for internal calls. * babl/babl-introspect.c: (conversion_introspect): some more information. * babl/babl-model.c: (test_create), (babl_model_is_symmetric): use comparion function from babl-util * babl/babl-conversion.c: (test_create), (babl_conversion_cost), (babl_conversion_error): use comparion function from babl-util. * babl/babl.c: (babl_init): no need to do post extension tricks anymore. * babl/babl-core.c: (babl_core_init): added PAD component. 2005-09-27 Øyvind Kolås <pippin@gimp.org> * babl/babl-util.h, * babl/babl-util.c: (babl_rel_avg_error): moved buffer comparison function to one place. * babl/babl-classes.h: Added error field to fishes, made path length dynamic. * babl/babl-internal.h: added misc global constants. * babl/babl-internal.c: created caching accessors in classes, to avoid very large bootstrapping time. * babl/babl-conversion.c: (test_create), (babl_conversion_cost), (babl_conversion_error): * babl/babl-format.c: (test_create), (babl_format_loss): * babl/babl-type.c: (babl_type_is_symmetric): 2005-09-27 Øyvind Kolås <pippin@gimp.org> Moved html generator stats code into a seperate source fil in core, babl now creates /tmp/babl-stats.txt when the BABL_STATS enviroment variable is set. * babl/Makefile.am: * babl/babl.c: * tests/babl_fish_path_dhtml.c: (main): * babl/babl-fish-stats.c: (table_destination_each). 2005-09-19 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: s/DHTML/interactive/ 2005-09-19 Øyvind Kolås <pippin@gimp.org> BablFishPath touchups. * babl/babl-conversion.c: cost = cost * 10 + 1, makes the overhead of actually running a conversion 1. Removed stupid long pats from created conversions. * babl/babl-fish-path.c: (chain_gen_each): Ensure the chain doesn't take us through larger loss than allowed. * babl/babl-internal.c: (babl_extension_post_load): do not autogenerate formats. * docs/index-static.html.in: updating documentation. * tests/babl_fish_path_dhtml.c: (table_destination_each), (table_source_each), (main): recoded to use CSS tricks instead of javascript, reduced generated file size by 50%; * extensions/gggl.c: (conv_labF_xyzF), (conv_xyzF_labF): added missing return value. 2005-09-19 Øyvind Kolås <pippin@gimp.org> * extensions/gggl.c: Added the bulk of gggl based conversions as an extension. Many of these don't live up to the quality requirements of babl, but some do, and provide a good base for further BablFishPath coverage. 2005-09-18 Øyvind Kolås <pippin@gimp.org> * docs/tools/changelog2rss: tool to create RSS feed of ChangeLog. 2005-09-18 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: Included BablFishPath.[html|txt] * docs/index-static.html.in: included some ramblings about the background and purpose of babl. 2005-09-18 Øyvind Kolås <pippin@gimp.org> * tests/Makefile.am: * tests/babl_fish_path_dhtml.c, * tests/babl_fish_path_fitness.c: new introspection outputters, that report on the conversion matrix of BablFishPath. * tests/babl-html-dump.c: (main): removed conversions, since it is now used as "Vocabulary" in the documentation,. * tests/conversions.c: (each_conversion), (main): * tests/formats.c: (format_check), (main): * tests/models.c: (model_check), (main): * tests/types.c: (type_check), (main): Moved the logic into BablCore in previous commit. 2005-09-18 Øyvind Kolås <pippin@gimp.org> Updating test suite, conversion and format quality testing code folded into babl-core in previous commit. 2005-09-18 Øyvind Kolås <pippin@gimp.org> * babl/base/model-cmyk.c: (rgb_to_cmyk), (cmyk_to_rgb), (conversions), (formats): * babl/base/model-gray.c: (rgba_to_graya), (rgba_to_gray), (graya_to_rgba), (gray_to_rgba), (conversions): * babl/base/model-rgb.c: (formats): * babl/base/model-ycbcr.c: (rgba_to_ycbcra), (rgba_to_ycbcr), (ycbcra_to_rgba), (ycbcr_to_rgba), (conversions), (formats): * extensions/CIE-Lab.c: (rgba_to_lab), (lab_to_rgba), (rgba_to_laba), (laba_to_rgba), (conversions): * extensions/naive-CMYK.c: (init), (rgba_to_cmyk), (cmyk_to_rgba): register linear reference conversions instead, since they can be used in BablFishPath chains. 2005-09-18 Øyvind Kolås <pippin@gimp.org> Adding BablFishPath, as well as splittin out Simple and Reference from babl-fish.c. (lazy commit of large changes :d ) * babl/babl-internal.h: * babl/babl-core.c: (rgba_to_rgba), (babl_core_init): * babl/babl-db.c: (babl_db_count): * babl/babl-db.h: * babl/babl-fish.c: (match_conversion), (babl_conversion_find), (babl_fish_db), (babl_fish), (babl_fish_process), (each_babl_fish_destroy): * babl/babl-format.c: (babl_format_new), (babl_formats_count), (babl_format_with_model_as_type), (test_create), (babl_format_loss): * babl/babl-internal.c: (babl_process), (each_conversion), (each_format), (gen_type_format_for_model), (gen_formats_for_model), (babl_extension_post_load): * babl/babl-introspect.c: (conversion_introspect): * babl/babl-model.c: (babl_model_new), (test_create), (reference_format), (construct_double_format), (babl_model_is_symmetric): * babl/babl-sanity.c: (id_sanity): * babl/babl-type.c: (babl_type_new), (r_interval), (test_init), (double_vector_format), (babl_type_is_symmetric): 2005-09-18 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: added BablFishPath * babl/babl-util.c: (babl_list_each), (init_ticks), (babl_ticks): * babl/babl-util.h: 2005-09-18 Øyvind Kolås <pippin@gimp.org> * babl/babl.c: (babl_init), * babl/babl.h: made babl_fish variadic. 2005-09-18 Øyvind Kolås <pippin@gimp.org> * babl/babl-memory.[ch]: (babl_free), (babl_realloc): made babl_free variadic, and added the potential for a clearing realloc. 2005-09-12 Øyvind Kolås <pippin@gimp.org> * tests/conversions.c: (test_init): code simplification. 2005-09-12 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: add loss field to format class. * babl/babl-format.c: (format_new): set loss field to -1 as initial value. * tests/conversions.c: (reference_format): simplify * tests/formats.c: (test_init), (format_check), (main): code simplification. 2005-09-11 Øyvind Kolås <pippin@gimp.org> * babl/babl.h: use gcc 4.x attribute for NULL sentinel. * babl/babl-format.c: (babl_format_new): added missing enumeration values to switch. * babl/babl-model.c: (babl_model_new): added missing enumeration values to switch. 2005-09-11 Øyvind Kolås <pippin@gimp.org> * tests/formats.c: new test (that might form the basis of loss calculations done for ranking of formats). * tests/Makefile.am: added new test 2005-09-11 Øyvind Kolås <pippin@gimp.org> * extensions/CIE-Lab.c: (formats): s/cie-lab-u16/CIE Lab u16/ 2005-09-11 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: Removed unused list of conversions to types/models/formats. * babl/babl-conversion.c: (conversion_new): * babl/babl-format.c: (each_babl_format_destroy), (format_new): * babl/babl-image.c: (babl_image_from_linear): * babl/babl-introspect.c: (item_conversions_introspect): * babl/babl-memory.c: (babl_realloc): * babl/babl-model.c: (each_babl_model_destroy), (model_new): * babl/babl-sampling.c: (each_babl_sampling_destroy): * babl/babl-sanity.c: (type_sanity), (model_sanity), (babl_sanity): * babl/babl-type.c: (each_babl_type_destroy), (type_new): 2005-09-09 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: set BABL_PATH to builddir for creating the documentation * docs/index-static.html.in: various updates. 2005-09-09 Øyvind Kolås <pippin@gimp.org> * babl/base/type-u16.c: (convert_double_u16_scaled): * babl/base/type-u32.c: (convert_double_u32_scaled): * babl/base/type-u8.c: (convert_double_u8_scaled), (babl_base_type_u8): * extensions/CIE-Lab.c: (convert_double_u8_scaled), (convert_double_u16_scaled): uintval = rint (dval * MAXINT) 2005-09-09 Øyvind Kolås <pippin@gimp.org> * tests/conversions.c: (validate_conversion): do relative average error calculations. * tests/srgb_to_lab_u8.c: update values. * tests/types.c: set a very low tolerance. 2005-09-09 Øyvind Kolås <pippin@gimp.org> * babl/babl-format.c: (create_name): Create shorter names when the format uses a single datatype and the components are listed in model order. * babl/base/model-lab.c: removed. * babl/base/model-rgb.c: (formats), * babl/base/model-ycbcr.c: (formats): Use automatic names for formats. 2005-09-09 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: added error to BablConversion. * babl/babl-conversion.c: (conversion_new), (babl_conversion_new): track changes to fields in constructors. 2005-09-08 Øyvind Kolås <pippin@gimp.org> * Makefile.am: build extensions before tests. * extensions/Makefile.in: build extensions when check is done. * tests/Makefile.am: removed erroniously added foo test. 2005-09-08 Øyvind Kolås <pippin@gimp.org> * babl/base/type-float.c: * babl/base/type-u16.c: * babl/base/type-u8.c: s/"linear"/"plane"/ * babl/base/Makefile.am, * babl/base/babl-base.c, * babl/base/type-u32.c: new type. * extensions/CIE-Lab.c: * extensions/Makefile.in: changes needed (for not yet added) lcms extension. * tests/Makefile.am: added new test. * tests/conversions.c: new test to check fast paths against reference fish. 2005-09-08 Øyvind Kolås <pippin@gimp.org> Made simple fishes work in the core. * babl/babl-classes.h: reduced number of conversion classes. removed unused from and to members in struct. * babl/babl-conversion.c: (conversion_new), (babl_conversion_new), (babl_conversion_linear_process), (babl_conversion_plane_process), (babl_conversion_planar_process), (babl_conversion_process): * babl/babl-component.c: (each_babl_component_destroy), (component_new): removed unused from and to members. * babl/babl-fish.c: (babl_conversion_find2), (babl_conversion_find), (babl_fish_reference), (babl_fish_simple), (babl_fish), (convert_to_double), (convert_from_double), (babl_fish_reference_process): use fast path if found directly in a simple fishes. * babl/babl-format.c: (babl_format_new): * babl/babl-internal.c: (babl_process): * babl/babl-internal.h: * babl/babl-introspect.c: (each_introspect): * babl/babl-model.c: (babl_model_new): * babl/babl-core.c: (babl_core_init): s/linear/plane/ * tests/babl_class_name.c: update according to class changes. 2005-09-08 Øyvind Kolås <pippin@gimp.org> * AUTHORS: Added Micahel Schumacher, and email addresses. * docs/index-static.html.in: * docs/babl.css: * tests/babl-html-dump.c: (main), (normalize), (show_item), (hide_item), (each_item), (model_html), (type_html), (conversion_html), (format_html): Use DHTML for expandable display of registered data structures. * docs/graphics/Makefile.am: added web target, and .SILENT option. * docs/Makefile.am: added .SILENT option. * configure.ac: added website location. 2005-09-01 Michael Schumacher <schumaml@cvs.gnome.org> * configure.ac: added a check for OS_WIN32 * babl/Makefile.am: link with libgw32c to provide dl* functions on win32 * babl/babl-extension.c: added definitions of dl* function forwin32 * tests/Makefile.am: removed -ldl for win32 2005-09-01 Sven Neumann <sven@gimp.org> * Makefile.am: don't dist the generated babl.pc file. 2005-09-01 Sven Neumann <sven@gimp.org> * tests/Makefile.am (TESTS_ENVIRONMENT): set BABL_PATH to include extension from the builddir. 2005-09-01 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.h: HACK statically define BablDb *db, for all internal translation units. 2005-09-01 Øyvind Kolås <pippin@gimp.org> Added a 128 item hashtable to each object list. * babl/Makefile.am: added new file 'babl-db.c' * babl/babl-db.h: moved static function ... * babl/babl-db.c: ... here in a new file, also implemented a hashing optimization based on the strings of names. * babl/babl-internal.h: changed API in base class templates. * babl/babl-component.c, * babl/babl-extension.c, * babl/babl-fish.c, * babl/babl-format.c, * babl/babl-image.c, * babl/babl-model.c, * babl/babl-sampling.c, * babl/babl-type.c: changed db_insert(..) to babl_db_insert(db, ...) * babl/babl.c: added babl_fish_init () 2005-08-31 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: Changed ChangeLog link in NEWS section. 2005-08-31 Øyvind Kolås <pippin@gimp.org> * babl/babl-component.h, * babl/babl-core.h, * babl/babl-conversion.h, * babl/babl-extension.h, * babl/babl-format.h, * babl/babl-instance.h, * babl/babl-introspect.h, * babl/babl-image.h, * babl/babl-fish.h, * babl/babl-model.h, * babl/babl-sampling.h, * babl/babl-sanity.h, * babl/babl-type.h: DELETED * babl/babl.h: defines moved from deleted headers. Added documentation. * babl/babl-internal.h: defines moved from deleted headers. * babl/Makefile.am: Reflect above changes. * babl/babl-classes.h: redefined conversion functions to return long, and take number of pixels as long. * babl/babl-component.c, * babl/babl-conversion.c, * babl/babl-core.c, * babl/babl-db.h, * babl/babl-extension.c, * babl/babl-fish.c, * babl/babl-format.c, * babl/babl-image.c, * babl/babl-instance.h, * babl/babl-internal.c, * babl/babl-internal.h, * babl/babl-introspect.c, * babl/babl-memory.c, * babl/babl-model.c, * babl/babl-sampling.c, * babl/babl-sanity.c, * babl/babl-type.c, * babl/babl.c, * babl/base/model-cmyk.c, * babl/base/model-gray.c, * babl/base/model-rgb.c, * babl/base/model-ycbcr.c, * babl/base/type-float.c, * babl/base/type-u16.c, * babl/base/type-u8.c, * docs/index-static.html.in, * extensions/CIE-Lab.c, * extensions/naive-CMYK.c, * tests/babl-html-dump.c, * tests/babl_class_name.c, * tests/grayscale_to_rgb.c, * tests/introspect.c, * tests/models.c, * tests/nop.c, * tests/rgb_to_bgr.c, * tests/rgb_to_ycbcr.c, * tests/sanity.c, * tests/srgb_to_lab_u8.c, * tests/types.c: reflect changes in headers. 2005-08-31 Øyvind Kolås <pippin@gimp.org> * Makefile.am, * babl.pc.in, * configure.ac, * extensions/Makefile.in: Fixed build of extensions. (awaiting fix of babl/babl-extension.c to use new #defines) 2005-08-30 Øyvind Kolås <pippin@gimp.org> * babl/base/model-gray.c: (rgba_to_gray_alpha_premultiplied): fixed array index error. * extensions/Makefile.in: Added -I../babl to include path. * extensions/naive-CMYK.c: (init), (rgb_to_cmyk), (cmyk_to_rgb): reordered the code, fixed a component swapping issue discovered by tests/model.c 2005-08-30 Øyvind Kolås <pippin@gimp.org> * tests/srgb_to_lab_u8.c: updated values. * tests/types.c: rewritten. * tests/models.c: added, a test to test that reference conversions registered for a BablModel are symmetrical. * tests/float_to_u8.c, * tests/u8_to_float.c, * tests/rgb_to_lab_to_rgb.c, * tests/rgb_to_ycbcr_to_rgb.c: removed. * tests/Makefile.am: updated. 2005-08-30 Øyvind Kolås <pippin@gimp.org> * babl/babl-introspect.c: (model_introspect), (format_introspect), (each_introspect): use double quotes for strings. (conversion_introspect): new, show instrumentation data. (fish_introspect): new, show instrumentation data. 2005-08-30 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: Added instrumentation variables to BablConversion and BablFish. * babl/babl-conversion.c: (babl_conversion_new): Handle re-registration. (conversion_new), (babl_conversion_process): instrumentation variables * babl/babl-component.c: (babl_component_new): Handle re-registration. * babl/babl-extension.c: Code cleanup. (babl_extension_base): Handle re-registration. (babl_extension_load_dir): close dir handle when done. * babl/babl-fish.c: (create_name) (babl_fish_new): instrumentation variables, autogenerated name. (babl_fish_reference_new): instrumentation variables, autogenerated name. (babl_process): instrumentation variables. (babl_conversion_find): use the lists of the source type for the search (speed improvement). (babl_fish): (process_same_model): reference process with fewer steps. (babl_fish_reference_process): use fast path when models are the same. * babl/babl-format.c: (babl_format_new): Handle re-registration. * babl/babl-model.c: (babl_model_new): handle re-registration. * babl/babl-type.c: (babl_type_new): handle re-registration. 2005-08-30 Øyvind Kolås <pippin@gimp.org> * babl/babl-memory.c: (babl_free): freeing of non babl allocated memory is fatal. 2005-08-29 Øyvind Kolås <pippin@gimp.org> * tests/types.c: added test that tests the symmetry of reference conversions for registered types. 2005-08-29 Øyvind Kolås <pippin@gimp.org> * babl/babl-format.c: (each_babl_format_destroy), (format_new), (create_name), (babl_format_new): New API, name is now a key/value pair, and if not set the name will be autogenerated. * babl/base/model-rgb.c, * babl/base/model-ycbcr.c, * extensions/CIE-Lab.c, * extensions/naive-CMYK.c, * tests/Makefile.am, * tests/float_to_u8.c, * tests/grayscale_to_rgb.c, * tests/rgb_to_bgr.c, * tests/rgb_to_lab_to_rgb.c, * tests/rgb_to_ycbcr.c, * tests/rgb_to_ycbcr_to_rgb.c, * tests/u8_to_float.c: update to new API. 2005-08-29 Øyvind Kolås <pippin@gimp.org> * babl/babl-db.h: Do nor warn about collision during db_insert * babl/babl-extension.[ch]: Implemented fs traversal based on BABL_PATH. added babl_set_extender to API. * babl/babl-instance.h: Changed signature of type_name##_new. * babl/babl-introspect.c: (babl_introspect): use new babl_extender 2005-08-29 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.c: (babl_internal_init): set memory functions. * babl/babl-memory.c: (babl_set_malloc), (babl_set_free), (functions_sanity), (babl_malloc), (babl_free), (babl_realloc), (babl_calloc), (babl_sizeof), (babl_strdup), (babl_strcat), (babl_memory_sanity), * babl/babl-memory.h: Added babl_str* functions, that behave slightly different from the standard ones. * babl/babl-util.c: (babl_add_ptr_to_list): made error fatal. * babl/babl.c: (babl_init), (babl_destroy): added babl_internal 2005-08-28 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.[ch]: (babl_die): A function to call from babl_fatal (...), invokes commands resulting in a backtrace, thus giving context to where things broke. * babl/babl-component.c: (babl_component_new): * babl/babl-conversion.c: (babl_conversion_new): * babl/babl-fish.c: (babl_conversion_find): * babl/babl-format.c: (format_new), (babl_format_new): * babl/babl-model.c: (babl_model_new): * babl/babl-type.c: (babl_type_new): use babl_fatal() instead of babl_log () on API mistakes. 2005-08-28 Øyvind Kolås <pippin@gimp.org> * babl/babl-pixel-format.c: removed * babl/babl-format.c: readded under new name. * babl/babl-pixel-format.h: removed * babl/babl-format.h: readded under new name. * babl/babl-classes.c: removed * babl/babl-internal.c: readded under new name. * babl/babl.h, * babl/Makefile.am, * babl/babl-fish.c: Accomodate changes. 2005-08-28 Øyvind Kolås <pippin@gimp.org> * babl/babl-component.c: (babl_component_new): s/parameter/argument/ * babl/babl-extension.[ch]: the extension class. * babl/babl-model.c: (create_name), (babl_model_new): generate automatic name, allow override with key/value pair. s/parameter/argument/ * babl/babl-pixel-format.c: (babl_format_new): s/parameter/argument/ * babl/babl-sampling.c: (babl_sampling): s/parameter/argument/ * babl/babl-type.c: (babl_type_new): s/paramter/argument/ * babl/babl-conversion.c, (create_name), (babl_conversion_new): * babl/babl-conversion.h: Changed API, first two parameters are now source and destination. * babl/babl-instance.h: Added _NO_NEW variation of declarative name. * babl/babl-internal.h: exit (-1) when a name lookup fails. * babl/babl.h: do not export babl-ids.h * babl/base/Makefile.am: Files removed * babl/base/babl-base.c: (models): removed model-lab * babl/base/cpercep.[ch], * babl/base/models.c, * babl/base/model-lab.c, * babl/base/types.c: removed * babl/base/model-gray.c, * babl/base/model-rgb.c, * babl/base/model-ycbcr.c: (models), (conversions): changed to new model_new and conversion_new api. * babl/base/type-float.c, * babl/base/type-u16.c, * babl/base/type-u8.c: new conversion API * configure.ac, * Makefile.am: added extensions subdir * extensions/Makefile.in: NB: hard-coded installpath to /home/pippin/.babl/ * extensions/CIE-Lab.c: moved here from BablBase, contains cpercep.c and cpercep.h * extensions/naive-CMYK.c: moved here from BablBase. * extensions/util.h: convenience functions for babl extensions. * babl/babl-core.[ch]: double and RGBA originating from BablBase. * docs/index-static.html.in: updated TODO list. * tests/float_to_u8.c, * tests/grayscale_to_rgb.c, * tests/rgb_to_bgr.c, * tests/rgb_to_lab_to_rgb.c, * tests/rgb_to_ycbcr.c, * tests/rgb_to_ycbcr_to_rgb.c, * tests/srgb_to_lab_u8.c, * tests/u8_to_float.c: follow naming changed. 2005-08-27 Øyvind Kolås <pippin@gimp.org> * Makefile.am: * babl.pc.in: added -dl * babl/babl-classes.c: Added BablExtension to string list of types. * babl/babl-classes.h: Added BablExtension, some reordering in union. * babl/babl-conversion.c: (create_name), (babl_conversion_new): compute the name of the conversion instead of explicitly having to provide it. * babl/babl-core.c: (convert_double_double), (copy_strip_1), (babl_core_init): Moved double datatype and RGBA model from base into core. * babl/babl-core.h: new file * babl/babl-db.h: improved logging, print current extender as well. * babl/babl-ids.h: removed some non central ids. * babl/babl-internal.h: new varargs based logger. * babl/babl-introspect.c: (babl_introspect): use quiet "fake" extender. Allow introspection of single objects. * babl/babl-introspect.h: Allow introspection of single objects. * babl/babl-memory.c: (babl_memory_sanity): use babl_log instead of fprintf. * babl/babl-sanity.c: (id_sanity): only complain about id==0 in BablBase / BablCore. * babl/babl.c: (babl_init), (babl_destroy): added core and extension to build up/tear down lists. * babl/babl.h: removed babl_introspect which doesn't belong here anymore. * babl/base/Makefile.am: Removed type-double.c * babl/base/babl-base.c: (types), (models): removed babl_base_type_double () * babl/base/model-rgb.c: (components), (models): removed RGBA model. * babl/base/type-double.c: removed * docs/index-static.html.in: * tests/Makefile.am: LDADD += -ldl * tests/introspect.c: (main): pass NULL as argument to babl_introspect () to do full objectspace traversal. * babl/babl-fish.h: * babl/babl-model.h: * babl/babl-pixel-format.h: * babl/babl-sampling.h: * babl/babl-conversion.h: * babl/babl-component.h: cosmetic rearrangement of lines. 2005-08-27 Øyvind Kolås <pippin@gimp.org> * babl/babl-component.c: (babl_component_new): * babl/babl-conversion.c: (conversion_new), (babl_conversion_new), (babl_conversion_process): * babl/babl-db.h: * babl/babl-fish.c: (babl_conversion_find), (babl_fish), (babl_fish_reference_process), (babl_fish_process), (babl_process): * babl/babl-image.c: (babl_image_from_linear), (babl_image): * babl/babl-internal.h: * babl/babl-introspect.c: (babl_introspect), (model_introspect): * babl/babl-memory.c: (babl_malloc), (babl_strdup), (babl_realloc), (babl_calloc): * babl/babl-model.c: (babl_model_new): * babl/babl-pixel-format.c: (format_new), (babl_format_new): * babl/babl-type.c: (babl_type_new): * babl/babl-util.c: (babl_add_ptr_to_list): * babl/base/type-u8.c: * tests/babl_class_name.c: (test): Made babl_log(...) print the file, line and function by itself. 2005-08-27 Øyvind Kolås <pippin@gimp.org> * docs/graphics/Makefile.am: s/INSCAPE/INKSCAPE/ 2005-08-27 Sven Neumann <sven@gimp.org> * configure.ac * Makefile.am * docs/Makefile.am * docs/graphics/Makefile.am: check for inkscape and w3m which are needed to build the documentation. Compile without them but bail out on 'make dist'. 2005-08-26 Øyvind Kolås <pippin@gimp.org> * tests/rgb_to_bgr.c: added component shuffling test * tests/Makefile.am: added rgb_to_bgr to TESTS 2005-08-25 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: removed done things from TODO list. 2005-08-25 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish.c: (babl_to_double),(babl_from_double): new functions. (babl_fish_reference_process): made type a component shuffling work for linear buffers * tests/rgb_to_lab_u8.c: filled in calculated values. 2005-08-25 Øyvind Kolås <pippin@gimp.org> * tests/rgb_to_ycbcr.c, * tests/rgb_to_ycbcr_to_rgb.c: fix Y' component name 2005-08-25 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: BablFormat: added .bytes_per_pixel BablImage: s/bands/components/ * babl/babl-conversion.c: s/bands/components/ * babl/babl-image.c: s/bands/components/ * babl/babl-pixel-format.c: (format_new) check if provided pixel format matches model. Calculate .bytes_per_pixel. * tests/babl-html-dump.c: use format.bytes_per_pixel 2005-08-25 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: BablModel: added .type BablFormat: reordered BablImage: added .format, .model, .sampling and .type BablFishReference: removed implementation details * babl/babl-component.c: (component_new): use malloc instead of calloc * babl/babl-conversion.c: (conversion_new): use malloc instead of calloc (babl_conversion_linear_process) (babl_conversion_process): pass pitch to functions. (babl_conversion_planar_process): duplicate data pointers in image before passing them on. * babl/babl-db.h: (db_each): indentation fix. * babl/babl-fish.c: (babl_fish_reference_new), (babl_fish_reference_process), (babl_fish_process), (babl_process): restructuring of the reference bablfish, approaching data and component shuffling functionality. * babl/babl-image.c: (image_new): use malloc instead of calloc (babl_image_from_linear), (babl_image): Added more information to structure. * babl/babl-image.h: s/_new// * babl/babl-internal.h: #define BABL_MAX_COMPONENTS 32 * babl/babl-introspect.c: (format_introspect): s/bands/components/ * babl/babl-model.c: (model_new): use malloc instead of calloc * babl/babl-pixel-format.c: (format_new): use malloc instead of calloc (babl_format_new): s/bands/components/ * babl/babl-type.c: (type_new): use malloc instead of calloc * babl/base/type-double.c, * babl/base/type-float.c, * babl/base/type-u16.c, * babl/base/type-u8.c: more parameters to conversion functions, added a codewriting macro for different scale / min/max factors. * docs/index-static.html.in: reindent. * tests/babl-html-dump.c: (format_html): s/bands/components/ * tests/srgb_to_lab_u8.c: (test): use absolute error in check. 2005-08-24 Øyvind Kolås <pippin@gimp.org> * tests/sanity.c: Added a test that fails if the internal sanity checks are failing. 2005-08-24 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.c, * babl/babl-classes.h, * babl/babl-component.c, * babl/babl-conversion.c, * babl/babl-db.h, * babl/babl-fish.c, * babl/babl-fish.h, * babl/babl-image.c, * babl/babl-image.h, * babl/babl-internal.h, * babl/babl-introspect.c, * babl/babl-model.c, * babl/babl-model.h, * babl/babl-pixel-format.c, * babl/babl-pixel-format.h, * babl/babl-sanity.c, * babl/babl-sanity.h, * babl/babl-type.c, * babl/babl.c, * babl/babl.h, * babl/base/model-cmyk.c, * babl/base/model-gray.c, * babl/base/model-lab.c, * babl/base/model-rgb.c, * babl/base/model-ycbcr.c, * tests/Makefile.am, * tests/babl-html-dump.c, * tests/babl_class_name.c, * tests/float_to_u8.c, * tests/grayscale_to_rgb.c, * tests/rgb_to_lab_to_rgb.c, * tests/rgb_to_ycbcr.c, * tests/rgb_to_ycbcr_to_rgb.c, * tests/u8_to_float.c: s/PixelFormat/Format/ (etc in other cases), Made BablFish be more polymorphic (accept format names as well as BablFormats). * babl/babl-ids.h: reorganized, some renames. * tests/srgb_to_lab_u8.c: new test for 8bit CIE Lab format (reference data not correct yet). * babl/base/type-u16.c, * babl/base/type-u8.c: Added CIE fixed point data types. 2005-08-24 Øyvind Kolås <pippin@gimp.org> * docs/babl.css: Added code highlighting classes. 2005-08-24 Øyvind Kolås <pippin@gimp.org> * NEWS: remove draft for news release, at initial release everything will be new. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: use `tempfile` to create name of temporary file * docs/tools/xml_insert.sh: use `tempfile` to create name of temporary file. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.c, * babl/babl-classes.h, * babl/babl-conversion.c, * babl/babl-fish.h, * babl/babl-image.c, * babl/babl-image.h, * babl/babl-instance.h: Indentation, comments and other cleanup. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * docs/index-static.html.in: update webdocs. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * babl/babl-instance.h: babl_class_name is moved to babl-classes.h * babl/babl-conversion.h: add a method to the conversion class for the processing with registered functions. * babl/babl-fish.c: Use above functions. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * babl/babl-memory.[ch]: added additonal sanity checking (only handling babl-memory allocated memory in free and realloc.) And added new function babl_dup (void*), which duplicates an allocation. * babl/babl-db.h: have an initial database size. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.c: Update class names to be in sync with enum in babl-classes.h 2005-08-23 Øyvind Kolås <pippin@gimp.org> * babl/babl.c: implement ref counting to avoid unneccesary destruction of static data when multiple instances of babl is used in an adressspace. 2005-08-23 Øyvind Kolås <pippin@gimp.org> * tests/Makefile.am: * tests/babl_class_name.c: new test. 2005-08-22 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: (BabPixelFormat): only a single BablModel. * babl/babl-pixel-format.h, * tests/babl-html-dump.c: accomodate change. 2005-08-21 Øyvind Kolås <pippin@gimp.org> * docs/.cvsignore: added Makefile and Makefile.in * docs/graphics/.cvsignore: added Makefile and Makefile.in * tests/.cvsignore: added babl_html_dump 2005-08-21 Øyvind Kolås <pippin@gimp.org> * babl/base/Makefile.am: Typo, s/babl-grays/babl-gray/ 2005-08-21 Øyvind Kolås <pippin@gimp.org> * docs/Makefile.am: Changed which html file is piped through w3m to generate README. 2005-08-21 Øyvind Kolås <pippin@gimp.org> * babl/base/model-grayscale.c: removed * babl/base/model-gray.c: added * babl/base/Makefile.am: * docs/graphics/index.html: fixed spelling. 2005-08-21 Øyvind Kolås <pippin@gimp.org> * docs/LGPL: added (hopefully as a link to ../COPYING) 2005-08-21 Øyvind Kolås <pippin@gimp.org> * Makefile.am, * NEWS, * autogen.sh, * babl/Makefile.am, * configure.ac, * docs/.cvsignore, * docs/Makefile.am, * docs/babl.css, * docs/graphics/.cvsignore, * docs/graphics/Makefile.am, * docs/graphics/babl-16x16.svg, * docs/graphics/babl-48x48.svg, * docs/graphics/babl-a4poster.svg, * docs/graphics/index.html, * README.in, * docs/index-static.html.in, * docs/tools/xml_insert.sh, * tests/babl-html-dump.c, * tests/Makefile.am: Added HTML based documentation as part of build process. 2005-08-21 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: reindent, some documentation. * babl/babl-fish.c: (babl_fish_reference_new): assertions for arguments. * babl/babl-ids.h: cleanup. * babl/base/babl-base.c: (models): grayscale->gray * babl/base/model-grayscale.c: (babl_base_model_gray), (components), (models), (rgb_to_gray), (rgb_to_gray_2_2), (gray_2_2_to_rgb), (gray_to_rgb), (gray_alpha_premultiplied_to_rgba), (rgba_to_gray_alpha_premultiplied), (conversions): grayscale->gray, added gamma-2.2 with alpha. * babl/base/model-lab.c: * babl/base/model-rgb.c: * babl/base/model-ycbcr.c: Name normalizations * tests/float_to_u8.c: (test_float_to_rgb_u8): * tests/grayscale_to_rgb.c: (test): * tests/rgb_to_lab_to_rgb.c: (test): * tests/rgb_to_ycbcr.c: (test): * tests/rgb_to_ycbcr_to_rgb.c: (test): * tests/u8_to_float.c: (test): Name synchronization. 2005-08-18 Øyvind Kolås <pippin@gimp.org> * babl/base/util.h: added new and hopefully correct gamma correction and uncorrection functions. * babl/base/model-grayscale.c: (components), (rgb_to_grayscale_2_2), (grayscale_2_2_to_rgb): register "luminance-gamma2.2" component, and use new gamma functions. * babl/base/model-rgb.c: (g3_gamma_2_2), (g3_inv_gamma_2_2): use new gamma functions. * babl/base/model-ycbcr.c: (components), (models), (rgb_to_ycbcr), (ycbcr_to_rgb): use gamma corrected luminance, and correct gamma. (pixel_formats): uncomment until a new data type exist with headroom/footrom in 8bit for proper rescaling of 0..255 to 16..235 for luma and +/-112 range with offset of 128 for chroma (16 thorugh 240 inclusive). * babl/base/rgb-constants.h: more digits as well as some #if 0' dead code for reference. * tests/rgb_to_lab_to_rgb.c: add more colors to the test buffer. * tests/rgb_to_ycbcr.c: set TOLERANCE to a more meaningful value, updated the ycbcr version of 50% gray. 2005-08-17 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.h: (type_name##_id) babl_log upon failed lookups. 2005-08-17 Øyvind Kolås <pippin@gimp.org> * Makefile-mini * babl/Makefile-mini: removed 2005-08-17 Øyvind Kolås <pippin@gimp.org> * configure.ac: added babl/Makefile to AC_CONFIG_FILES(). 2005-08-17 Sven Neumann <sven@gimp.org> * README.in: spelling. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/base/pixel-formats.c: removed 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-model.c: (model_new) * babl/babl-pixel-format.c: (pixel_format_new): reordered allocation to place string (to avoid placing pointers in non aligned adresses). 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-component.c: (component_new, each_babl_component_destroy) allocate larger chunk, (babl_component_new) removed Babl* switch, * babl/babl-conversion.c: (conversion_new): removed superflous runtime warnings. * babl/babl-fish.c: (babl_fish_process): reindent, added assert for instance. * babl/babl-image.c: (image_new, babl_image_new): reindent, , (babl_image_new_from_linear): added asserts for parameters. * babl/babl-model.c: (each_babl_model_destroy, model_new): allocate larger chunk. * babl/babl-pixel-format.c: (each_babl_pixel_format_destroy, pixel_format_new): allocate larger chunk. * babl/babl-sanity.c: (babl_conversion_source): removed FIXME comment used for helper function just used to make code more readable. * babl/babl-type.c: (each_babl_type_destroy, type_new): allocate larger chunk. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: (BablSampling) added static name. * babl/babl-sampling.c: (babl_sampling_init): initialize names * babl/babl-introspect.c: (pixel_format_introspect): display sampling name as well. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-component.[ch] * babl/babl-conversion.[ch] * babl/babl-fish.[ch] * babl/babl-image.[ch] * babl/babl-instance.h * babl/babl-internal.h * babl/babl-introspect.c * babl/babl-model.[ch] * babl/babl-pixel-format.[ch] * babl/babl-sampling.[ch] * babl/babl-sanity.c * babl/babl-type.[ch] * tests/float_to_u8.c * tests/grayscale_to_rgb.c * tests/rgb_to_lab_to_rgb.c * tests/rgb_to_ycbcr.c * tests/rgb_to_ycbcr_to_rgb.c * tests/u8_to_float.c: Changed to use polymorph Babl * union's instead of class specific structs in most cases, and in all cases for the public API. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * AUTHORS: Fixed spelling of Sven Neumann. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * tests/.cvsignore: added the test binaries. * .cvsignore: added *.tar.gz and *.tar.bz2 2005-08-16 Øyvind Kolås <pippin@gimp.org> * AUTHORS: added Sven Neuman. 2005-08-16 Sven Neumann <sven@gimp.org> * configure.ac: add -Wall to CFLAGS if gcc is being used. Use AC_CONFIG_FILES() to define the files that need to be generated. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/base/mode-ycbcr.c: use coefficients from Charles Poyntons color FAQ. * tests/rgb_to_ycbcr_to_rgb.c: changed TOLERANCE to 0.00000000000001 * tests/rgb_to_ycbcr.c: changed TOLERANCE as well as reference values. 2005-08-16 Øyvind Kolås <pippin@gimp.org> * babl/babl-fish.c: reindentation, no naming of fishes. * babl/babl-ids.h: reordering, added YCBCRA, LAB and LAB_ALPHA * babl/base/Makefile.am: added cpercep.[ch] model-lab.c and model-ycbcr.c * babl/base/cpercep.[ch]: *NEW* * babl/base/model-lab.c: *NEW* CIE Lab color model, backed by a slightly modified version of cpercep from gimp sources (no gamma correction and normalized RGB values) * babl/base/model-ycbcr: made ycbcr work, numbers still need to be verified. * babl/base/babl-base.c: initialize CIE Lab and YCbCr * babl/base/model-cmyk.c: slight changes, it still doesn't pass rgb->cmyk->rgb testing so not included yet. * babl/base/model-rgb.c: make rgba-double use BABL_DOUBLE instead of BABL_FLOAT * babl/base/type-u16: fix conversion to double. * tests/Makefile.am: added rgb_to_lab_to_rgb , rgb_to_ycbcr_to_rgb and rgb_to_ycbcr * tests/rgb_to_lab_to_rgb.c * tests/rgb_to_ycbcr_to_rgb.c * tests/rgb_to_ycbcr.c: *NEW* tests 2005-08-15 Øyvind Kolås <pippin@gimp.org> * babl/base/model-cmyk.c * babl/base/model-ycbcr.c: added stubs 2005-08-15 Øyvind Kolås <pippin@gimp.org> * configure.ac: add rule to generate babl/base/Makefile * babl/base: new directory * babl/base/Makefile.am * babl/base/babl-base.[ch] * babl/base/type-double.c * babl/base/type-float.c * babl/base/type-u8.c * babl/base/type-u16.c * babl/base/model-rgb.c * babl/base/model-grayscale.c * babl/base/.cvsignore: added code removed in previous commit, in a more oragnised manner. 2005-08-15 Øyvind Kolås <pippin@gimp.org> * babl/babl-base/babl-base.[ch] * babl/babl-base/babl-base-components.c * babl/babl-base/babl-base-conversions.c * babl/babl-base/babl-base-conversions-model.c * babl/babl-base/babl-base-conversions-type.c * babl/babl-base/babl-base-models.c * babl/babl-base/babl-base-pixel-formats.c * babl/babl-base/babl-base-types.c * babl/babl-base/Makefile.am * babl/babl-base/: removed 2005-08-15 Øyvind Kolås <pippin@gimp.org> * babl/babl-classes.h: BablPixelFormat: changed order of attributes to match BablModel. BablFish: removed **from and **to lists, since they were added at a wrong offset from the instance start anyways. * babl/babl-fish.c: Made the reference fish work for linear buffers with constant datatype * babl/babl-ids.h: added BABL_RGBA_DOUBLE * babl/babl-image.[ch]: made BablImage be allocated in a single chunk, added babl_image_new_from_linear() * babl/babl-type.c: added assertion about bits%8==0 * babl/babl-base/babl-base-conversions-model.c: made BABL_PLANAR_SANITY accept single band buffers. added conversions for premultiplied grayscale. * babl/babl-base/babl-base-pixel-formats.c: added "rgba-double" 2005-08-15 Øyvind Kolås <pippin@gimp.org> * Makefile-mini: compile both the nop and introspect programs by default. * babl/Makefile-mini: link with standard math library 2005-08-14 Øyvind Kolås <pippin@gimp.org> * tests/float_to_u8.c * tests/u8_to_float.c * tests/grayscale_to_rgb.c: new files * tests/Makefile.am: including preceding tests 2005-08-14 Øyvind Kolås <pippin@gimp.org> * babl/Makefile.am: added babl-instance.h, removed wilcard from EXTRA_DIST * babl/babl-classes.h: added BablModel **model to BablPixelFormat, renamed BablReferenceFish to BablFishReference. Moved some logic out to babl-instance.h. * babl/babl-instance.h: new file. * babl/babl-db.h: include babl-instance instead of babl-classes to reduce amount of headers included by headers. * babl/babl-fish.c: Added code to make it work for type conversions * babl/babl-fish.h: Added babl_fish (source, destination) prototype * babl/babl-internal.h: reindentation, include babl-conversion.h * babl/babl-pixel-format.c: add model for each band * babl/babl.c: destroy all fishes at finish 2005-08-14 Øyvind Kolås <pippin@gimp.org> * babl/babl-base/Makefile.am: LDADD = -lm * babl/babl-base/babl-base-conversions-model.c: reindentation, added gamma functions. * babl/babl-base/babl-base-conversions-type.c: corrected reference versions of u8, u16 and float. * babl/babl-base/babl-base-models.c: ifdef'ed out some of the more arcane models. * babl/babl-base/babl-base-pixel-formats.c: added the corresponding model used to all pixel formats. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/Makefile-mini: CFLAGS = -Werror -Wall .... * babl/babl-classes.[ch]: BablPixelFormat removed unused pointers to lists of conversions. Added BablReferenceFish. Renamed kind/ instance.type to class_type/instance.class_type. Removed mostly unused macro's and expanded them in source * babl/babl-component.c * babl/babl-conversion.c * babl/babl-db.h * babl/babl-fish.c * babl/babl-image.c * babl/babl-introspect.c * babl/babl-model.c * babl/babl-pixel-format.c * babl/babl-sampling.c * babl/babl-type.c: removed switch statement since all enums are handled equally. * babl/tests/Makefile.am: added nop and introspect to TESTS, not actual tests yet, but at least a segfault will cause make check to fail. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * autogen.sh: make autogen also run make * babl/babl-classes.h: added define macro usable for sampling and fish. * babl/babl-fish.[ch]: cleanup of stub class * babl/babl-sampling.h: simplification of header using a define. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/babl-conversion.c: indentation cleanup. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/babl-ids: added BABL_LUMINANCE_GAMMA_2_2, BABL_LUMINANCE_MUL_ALPHA, BABL_GRAYSCALE_GAMMA_2_2, BABL_GRAYSCALE_ALPHA_PREMULTIPLIED. * babl/babl-base/babl-base-components: added "luminance*alpha" * babl/babl-base/babl-base-components.conversions-model.c: Sprinked asserts, added generic premultiplification operation. * babl/babl-base-models.c: added gamma corrected and premultiplied variations of grayscale. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/babl-internal.h: issue a babl_log when the named object is not found during string based lookup. * babl/babl-pixel-format.c: added BABL_IMAGE to var_args switch. * babl/babl-classes.c: set babl_hmpf_on_name_lookups initial value to 0, to make it hmpf only in babl-base. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/Makefile-mini: added babl-image.o. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/babl-sampling.h: removed reference to non existant function babl_sampling_introspect (). 2005-08-09 Øyvind Kolås <pippin@gimp.org> * babl/Makefile.am * babl/babl-image.c * babl/babl-image.h * babl/babl-classes.h: Added BablImage class. * babl/babl-component.c * babl/babl-conversion.c * babl/babl-model.c: Handle BABL_IMAGE in switches. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * .cvsignore: added INSTALL and README. 2005-08-09 Øyvind Kolås <pippin@gimp.org> * depcomp * install-sh * missing: erroniously included in first import. 2005-08-09 Øyvind Kolås <pippin@gimp.org> Imported into GNOME CVS. 2005-08-09 Øyvind Kolås <pippin@gimp.org> - seperate babl-base into separate subdir. 2005-08-09 Øyvind Kolås <pippin@gimp.org> - Renamed class to model. - Auto toolification 2005-08-08 Øyvind Kolås <pippin@gimp.org> - Completed data model - Added sanity checker 2005-08-07 Øyvind Kolås <pippin@gimp.org> - Introspection 2005-08-05 Øyvind Kolås <pippin@gimp.org> - Initial ChangeLog 2005-07-31 Øyvind Kolås <pippin@gimp.org> - Type system 2005-07-29 Øyvind Kolås <pippin@gimp.org> - Babl's inception in the 'Chaos Village' at WhatTheHack.