Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[Quietust]

There's something off with unit.status.current_soul.performance_skills.

The historical_figure_info structure claimed to contain a pointer to unit_personality, when it actually pointed to a structure containing a unit_personality plus an integer, so when that one reported a size mismatch, I updated the original and thus misaligned unit_soul. That should be fixed now.

- df.global.world.units.all[].job.mood_skill: Enum out of whack with 4-5 digit values.

Uninitialized memory - you can ignore that.

- df.global.world.units.all[].body.body_plan.interaction [].interaction.material_breath: Several values of 20, with current max = 19. The one I looked at was a cat and other data indicates it's a licking interaction, and also a head-bump interaction with the same value for the same cat.

The constructor for that class fills in a bogus value.

- df.global.world.entities.all[].armies[].controller: Following this pointer crashed both gui/gm-editor and my script. The pointer address looked reasonable.

Try again with the latest structures - army_controller was badly misaligned before.

[Clément]

There weren't Linux builds of DF for a while, so that's behind. You could run devel/dump-offsets and provide the output of that, but I'm not sure what else needs to be done.

Edit: looks like that was done already.

Thanks for the update.

I tried to compile DFHack before I saw it was already updated, and there was a compilation error. I am not sure if it is expected in the current state. I am posting it just in case.

Code: [Select]

/home/clement/projects/DFHack/dfhack/library/modules/Maps.cpp: In function 'const char* DFHack::sa_feature(df::enums::feature_type::feature_type)':
/home/clement/projects/DFHack/dfhack/library/modules/Maps.cpp:94:24: error: 'underworld_from_layer' is not a member of 'df::enums::feature_type'
     case feature_type::underworld_from_layer:
                        ^~~~~~~~~~~~~~~~~~~~~
/home/clement/projects/DFHack/dfhack/library/modules/Maps.cpp:94:24: note: suggested alternative: 'feature_underworld_from_layer'
     case feature_type::underworld_from_layer:
                        ^~~~~~~~~~~~~~~~~~~~~
                        feature_underworld_from_layer
make[2]: *** [library/CMakeFiles/dfhack.dir/build.make:1479: library/CMakeFiles/dfhack.dir/modules/Maps.cpp.o] Error 1

[PatrikLundell]

feature_underworld_from_layer was recently changed into underworld_from_layer. This suggests that your df structures sub repo may not be up to date.

However, the changes today to dfhack/develop and df structures/master do not compile for me (I compiled with a freshly pulled df structures/master yesterday without issues). It should be noted that I do not try to compile plugins. I wouldn't be surprised if my poor compatibility with git is the cause, though.

[Quietust]

However, the changes today to dfhack/develop and df structures/master do not compile for me (I compiled with a freshly pulled df structures/master yesterday without issues).

From what commit did you try to build? I made a fix last night for unit_personality, and I've confirmed that it builds correctly on both Windows (32-bit and 64-bit) and Linux (via Travis CI). If you're compiling on Windows, be sure to do a clean build, because there's a strange script bug that's preventing partial rebuilds from working correctly.

[surazal]

feature_underworld_from_layer was recently changed into underworld_from_layer. This suggests that your df structures sub repo may not be up to date.

However, the changes today to dfhack/develop and df structures/master do not compile for me (I compiled with a freshly pulled df structures/master yesterday without issues). It should be noted that I do not try to compile plugins. I wouldn't be surprised if my poor compatibility with git is the cause, though.

I think running "git submodule update" after doing a pull should resolve this issue (make sure to run a fresh cmake afterwards, just to be on the safe side). I was able to compile my version from the "develop" branch this morning without issues as well. If that doesn't work, you may need to clone a whole new copy of the repository as a last resort.

[PatrikLundell]

Thanks Quietust. The "clean" seems to do the trick ("Seems to" as I'm doing a 3 hour world gen, so I think the final error from the install-release script comes from the DLL being in use when trying to copy it. Compilation within VS itself didn't generate any errors, just the usual slew of warnings).

"git submodule update" may very well be what's needed for Clément, but I haven't done it since my df structures sub repo has been detached from the release the download originally pointed to and instead refers to df-structures/master (or none of the df structure changes between DFHack releases can be accessed), so I update that with "git pull".

[lethosor]

(or none of the df structure changes between DFHack releases can be accessed), so I update that with "git pull".

The DFHack develop branch should usually point to something more recent in df-structures, although not necessarily the master branch.

[PatrikLundell]

(or none of the df structure changes between DFHack releases can be accessed), so I update that with "git pull".

The DFHack develop branch should usually point to something more recent in df-structures, although not necessarily the master branch.

True, of course, but when I started it was still on a 0.43.05 release, and I want to look at the latest changes. It those aren't compatible with the DFHack develop branch I have to wait for it to catch up anyway.

Edit:
Removing performance_skills and controller from the blacklist of my script do not cause any crashes now, i.e. following the pointers works as expected.

[surazal]

From what commit did you try to build? I made a fix last night for unit_personality, and I've confirmed that it builds correctly on both Windows (32-bit and 64-bit) and Linux (via Travis CI). If you're compiling on Windows, be sure to do a clean build, because there's a strange script bug that's preventing partial rebuilds from working correctly.

commit 1489e7db824cc6323de14772fbf0f121ecd0860b

Yes, I did perform a "make clean". When I did "make -j8 install" it rebuilt everything from source again so I know it appeared to have worked.

[Quietust]

From what commit did you try to build? I made a fix last night for unit_personality, and I've confirmed that it builds correctly on both Windows (32-bit and 64-bit) and Linux (via Travis CI). If you're compiling on Windows, be sure to do a clean build, because there's a strange script bug that's preventing partial rebuilds from working correctly.

commit 1489e7db824cc6323de14772fbf0f121ecd0860b

Yes, I did perform a "make clean". When I did "make -j8 install" it rebuilt everything from source again so I know it appeared to have worked.

Good to know that it works for you, but that question was directed specifically at PatrikLundell (who was complaining about build errors with my most recent commits).

[PatrikLundell]

I didn't answer the question as I thought it would no longer be relevant since "clean" worked, so no further trouble shooting was needed (and I still haven't looked up the answer, although I think it was listing of some *.inc files or something like that).

[Rusty_knight]

Is it possible to create mineral veins out of layer rock or thin air using DFHack? If so, how?

[PatrikLundell]

Yes, manipulation of the geo biome can be performed using the Biome Manipulator http://www.bay12forums.com/smf/index.php?topic=164658.0 contains geo biome manipulation functionality. Note that this tools has to be used before embarking as it manipulates the data DF uses to generate the embark details.

Creating rock out of thin air should be possible as well, and I think there are tools for that kind of manipulation, as well as morphing single tiles. There's a tool for water/magma manipulation that can also create obsidian.

[Rusty_knight]

Note that this tools has to be used before embarking as it manipulates the data DF uses to generate the embark details.

Thanks, but I want to do it post-embark.

Creating rock out of thin air should be possible as well, and I think there are tools for that kind of manipulation, as well as morphing single tiles. There's a tool for water/magma manipulation that can also create obsidian.

Yeah, I know that tiles can be manipulated into rock/obsidian/open space/water/magma. But I'm interested in another kind of manipulation: abundant, dumb layer rock -> mineable ore. I've seen a post somewhere where it was stated that new mineral veins can be injected via DFHack, but it had no details how to do that exactly.

[Warmist]

Note that this tools has to be used before embarking as it manipulates the data DF uses to generate the embark details.

Thanks, but I want to do it post-embark.

Creating rock out of thin air should be possible as well, and I think there are tools for that kind of manipulation, as well as morphing single tiles. There's a tool for water/magma manipulation that can also create obsidian.

Yeah, I know that tiles can be manipulated into rock/obsidian/open space/water/magma. But I'm interested in another kind of manipulation: abundant, dumb layer rock -> mineable ore. I've seen a post somewhere where it was stated that new mineral veins can be injected via DFHack, but it had no details how to do that exactly.

Ancient code warning: https://gist.github.com/warmist/11218191 but it should work on any version (?)