* start
* hmm API doesn't seem great
* better
* rm line
* sendcan -> can_send callable for best static type coverage, list -> tuple msg
TODO: logcan
* more sendcan -> can_send references
* remove pandad's capnp from selfdrive/car
* fix and remove cereal from test_can_fingerprint
* test_fw_fingerprint: remove pandad, less cereal
* comment done too
* better comment
* fix test_models test
* niceeee it works
* move to can_definitions
* can't come up with a better name :(
* I think we can remove SimpleNamespace soon
* fix test_can_fingerprint.py
* maintain previous behavior
* Revert "maintain previous behavior"
This reverts commit f848fd3213.
* can test comment
* no need for get_one_can now!
* big clean up: no SimpleNamespace
* now self explanatory!
* not needed
* use empty can again since this is now real
* cmt
* ban params too with a callback
* all sorts of messed up
* use cloudlog
* consistent order
* order
* better type hint
* format
* this is a bit nicer
* hmm
* fix PLR1704
* no carvin
* fix process replay
* car logger
* try this
* fix double printing!
* clean up
* need to import where we actually use it (card won't be in submodule)
* NullHandler does not forward everything properly, need propagate=False to stop root logger from printing
* card is staying
* set up
* forward
* add function signature and behavior comment
* add test
* move chassis codes to platform config!
* add a shared chassis code test
* function
* test matching
* this commit isn't complete yet
* Revert "this commit isn't complete yet"
This reverts commit ae77d5cd54.
* need to check WMI
* TODO: test WMI
* test wmi
* radar FW sanity check
* fix test
* fixes from merge
fixes from merge
* whoops
* fix static analysis!
* do match_fw_to_car
match_fw_to_car takes vin
* makes sense to keep it one function, and we can return exact or fuzzy!
* clean up
* kinda pointless
* fix more tests
* back to function being only fuzzy
* revert test_fw_fingerprint
* revert test_fw_fingerprint
* simplify
* clean up/fixes
* rename test
* less duplicatey WMI descriptions
* fix
* convert to enum
* I am confident about these WMIs
* these are also good
* we support 5N AUS/NZ and NAR (North American) AX Tiguans
fixes
* Tiguan also Mexico
* only one user for caddy
* got from the test route
* check that the gateway type matches the platform (each platform has 1 or 2 types)
* ~gateway~ -> exact FW match
* remove re
* ensure WMIs are set
* actually no reason to delete
* move comment up to the platform config
* proper wmis typing
* spacing
* flip
* bump
* from https://github.com/commaai/openpilot/pull/27929
* get VIN on bolt!
* might as well try on other gms
* remove vin
* ugh gm is going to be slow
* fix
* should really fix this
* revert
* happy?1
* fix unit test
* bump
* functional addressing must be an OBD gateway feature, this does nothing
* fix vin response
* fix addr!
* finally fix fw_versions bugs since boardd IsOnroad refactor
* for
* only bus 0
* clean up
* Update selfdrive/car/gm/values.py
* ChatGPT re-write
* filter out did
* todo
* oof
* preview: what multiple DIDs per ECU would look like in the future
* Revert "preview: what multiple DIDs per ECU would look like in the future"
This reverts commit 88f0d8611e.
* function to get all ecus
* we can remove this!
* can also do this!
* and this one too :o
* consistency
* yay
* add tests
* revert GM stuff
* another PR
* reads better
* revert rest of gm
* use that
* interesting
* these are exactly the same (with ordering differences)
* Revert "these are exactly the same (with ordering differences)"
This reverts commit a9e918dc35.
* flip
* bump
* gm vin
* that's not right
* only check relevant buses
* instead try queries for each bus first
* clean up
* use default retry in function
* all
* put one subaddr in parallel_addrs
* p
* remove print
* update test refs
* test
* revert test changes
* do same in present ECU query, lower threshold to catch (~0.82 to ~0.72 right within bounds)
* type
* clean up
* update test ref
* debugging
* this test works, but find a better place
* make test more generic to start testing more than timings
no need to run again in another test function. eventually we
can simulate ECUs and have IsoTpParallelQuery work properly
* Revert "make test more generic to start testing more than timings"
This reverts commit 58e8536b1d.
* 2nd try
* clean up
* not even MappingProxyType works
* works
* test that too
* clean up
* refactor to avoid modification online
* revert tests
* more revert
* no longer needed
* clean up
* get gas/ev/hev from FW (not all correct, poc)
* add test for essential ecus for fuzzy fingerprinting
* kinda works
* stash
* clean up
* add code
* simpler
* use the function
* test it with our cars
* no re
no re
no re
* debugging
* handle empty dict
* simpl
* this is promising
start on making existing fingerprinting functions use the config, instead of entirely replacing them
* needs to allow 1 match
* lay out how this should look
* changes
* executable
* some work
* use config
* fuzzy ecus
* config test
* comment and some clean up
* test platform codes
* use regex, simpler and fixes bug
* in func
* rm bad func
* typing for new func and remove old from dc
* todo done
* tested!
* remove fake platform codes
* thought we needed this, but actually...
* not needed
* not applicable any more
* use config for essential ecus
* first draft of test to make adding/removing fuzzy FP platform intentional
* compile
* clean up test
* even cleaner
* fix default ecus type
* temp fix
* this is mostly in tests now
* test every fuzzy ecu fw returns one platform code
* experiment with dates
* Revert "experiment with dates"
This reverts commit 3251b9cc5c.
* clean that up
* comment
* test
* work on all cars
* fix fuzz_fw_fingerprint
* comment
* get first by search
* bit more clean up
* and more
* use compiled pattern for nicer syntax
* default
* flip dat around, much cleaner
* clean up hyundai test a bit
* flip order
same here
* rename test and flip subTest
* fix pylint
* revert fw changes
revert fw changes
* line
* add original functions to test
* needs to be a list
* cmt
* draft (need to count one ecu as a match)
* tiny clean up
* todo: date range
* only in notebook
* remove comment (still can be either list or set)
* same, only notebook
* more consistent signature
* copilot inspired
* copilot no good
* test for date parsing
* better name
* good, now we don't have to worry about the dates mismatching in another test/logic
* comment up+
* some stuff
* clean up
fix test
fix test
* test
* comment
* use utils
* clean up (utils are cleaner and less buggy)
* clean up (utils are cleaner and less buggy)
* fixup test
* use a dash (prettier) and remove some platforms that can fingerprint now!
* compile global pattern
* same as what we do in values
* remove comments
* fuzzy_get_platform_codes is one or none here
* more clean up
* sort imports
* woah woah woah
* add comment
* fix reassigning different types
* add types
* adapt fuzzy test recently added (nice it caught this!)
* update lock
* options
comments
* stash
* comments and fixes
* better comments
* better
* test: run on exact fuzzy matching logic, same results!
* use match_fw_to_car
* test all fw
* ex
* unused random
* this is a possibility
* this is more clear
* fix
* revert
* revert to needing both ECUs to match to reduce false positives, test
* fix excluded platform test :( but it's ok
* add comment
* we actually want to only test fuzzy ecus to make it explicit
* fix mypy
* comment for tomorrow
* just add matches with fuzzy FP
* add comment
* this was the cleanest I could think of, but still working on it. not very easy to understand
* think this is better, but also worse...
* comment: reframing how this works
* revert back to what we did before
* was swapped
* else set
* remove old comment
* fixes from merge
* remove fuzzy_min_match_count from this pr
* fix static analysis
* also unused
* different method first draft
* copy existing fuzzy func
* check all possible ecus exist, only platform codes, slightly refactor main loop
* fix
* Revert recent
Revert "fix"
This reverts commit 5cdb7bda83.
Revert "check all possible ecus exist, only platform codes, slightly refactor main loop"
This reverts commit d3e918fa20.
Revert "copy existing fuzzy func"
This reverts commit 34c8c05450.
Revert "different method first draft"
This reverts commit b91139055d.
* new func
* fixup test
* remove changes from v1 from fw_versions.py
* clean up a bit
* return part as part of code
* fix test
* add original fuzzy function
* add an ecu match if the date is within range (or date doesn't exist)
* add format for what we're going to do
* not working stash
* the exact matching function does more of what we want with less code and less custom logic
* we don't care about found versions, only codes and dates
* actually we do have an exception
* this works pretty nicely now
* up here
* this is better
* some minor clean up
* old function=now junk
* fix platform code test
* remove old platform code function
* now rename _new to
* use FW_QUERY_CONFIG
* clean up imports
* rename that too
* one line
* correct typing
correct typing
* draft tests
* so that works
* fixup excluded platform test now too
* this is tested by excluded platform test
* test parts and dates
* remove old comment
* old import
* take platform code stuff out of FwQueryConfig
* fix test
* revert debug script
* flip order
* make this a set by default
* revert this part
* correct typing
* clean up comments
* clean that test up too/pylint
* combine these three tests ina clean way
* not right
* more general
* be consistent with quotes
* comment
* comment
* comment in fw_versions
* flip order
* this is more readable
* could test all this, but it's tested in test_hyundai and doesn't do a lot here
* only assert brands which use this
* invalidate all CAN FD ICE and hybrid
* tuple
* can get away without filtering
* add comment reasons
* fix
* some review suggestions
* this works (first draft)
* this is better
* script to print platform codes and dates
* sanity check for dates are in correct ecus and platforms
* mypy
* better variable name and comment
* rename
* same
* slightly better name
* subset
* exclude platforms and live car without dates
* consistent
* self explan
* better name
* test to make sure the functions agree
* clean that up
* comment
* we get other responses from queries not in DB, only check any
* not used or typed
* first attempt trying to do it implicitly bad
* back to lists and explicitly do this
* continue checking if candidate switches on these, that's fine to check
* debugging
* clean up
* more clean up
* spot free
* only need to create/update on change
* fix test
* draft
* Revert "draft"
This reverts commit dbe32f58b1.
* Revert "fix test"
This reverts commit 1d34269fe2.
* fix test for real
* first draft of test
* this should be good
* can replace existing fuzzy test
* rm
* matching
* test non-empty fws
* TEST DOWN HERE
* no test
* unique + fix skip message + comment + clean up
* less confusing
* ing
* better
* pass in brand
* needs to be flipped for exact matching since it's subtractive
* new helper
* makes more sense flipped
* clean up
* not that stuff here
* not here
* speed up fingerprinting for CAN fp cars
* add comment to describe this behavior
* more explicit, no defaultdict
* do this later
* fix
* a little more clear I think
Shane Smiskol
Adeeb Shihadeh
Cameron Clough
Justin Newberry