Bringing your track in line with the latest changes to Problem Specifications (#978)

* Add tests.toml file for all exercises with canonical data

* update tests according to what's actually been implemented

Used a pretty simple heuristic for discovering what's been implemented;
this could likely use some refinement. Still, at least we're closer
now to accuracy.

* re-quote uuid keys to minimize diff

* update perfect-numbers readme

* use better formatting heuristics to detect which tests are implemented

```python3
import json
import re
import requests
import shlex
import string
import subprocess
import tomlkit

from base64 import b64decode
from collections import defaultdict
from pathlib import Path
from pprint import pprint

REPO_ROOT = Path(
    subprocess.run(["git", "rev-parse", "--show-toplevel"], capture_output=True)
    .stdout.strip()
    .decode()
)

FN_RE = re.compile(r"fn ([\w\d]+)")

CANONICAL_DATA_URL = "https://raw.githubusercontent.com/exercism/problem-specifications/master/exercises/{}/canonical-data.json"

ALPHANUMERIC = set(string.ascii_letters + string.digits + " ")

class CanonicalData(dict):
    def __getitem__(self, exercise: str):
        try:
            return super().__getitem__(exercise)
        except KeyError:
            response = requests.get(CANONICAL_DATA_URL.format(exercise), timeout=1)
            response.raise_for_status()
            data = json.loads(response.content)

            names = {}
            for case in walk_cases(data):
                names[case["uuid"]] = (
                    "".join(c for c in case["description"] if c in ALPHANUMERIC)
                    .lower()
                    .replace(" ", "_")
                )

            super().__setitem__(exercise, names)

        return super().__getitem__(exercise)

def walk_cases(data):
    if "cases" in data:
        for case in data["cases"]:
            yield from walk_cases(case)
            if "uuid" in case and "description" in case:
                yield case

CANONICAL_DATA = CanonicalData()

class Functions(dict):
    def __getitem__(self, exercise: Path):
        try:
            return super().__getitem__(exercise)
        except KeyError:
            super().__setitem__(exercise, test_names(exercise))

        return super().__getitem__(exercise)

def test_names(exercise: Path):
    names = set()
    for test_file in (exercise / "tests").glob("*.rs"):
        with test_file.open("rt") as fp:
            test_data = fp.read()
        for match in FN_RE.finditer(test_data):
            names.add(match.group(1))
    return names

FUNCTIONS = Functions()

def exercise_directories():
    return (ex for ex in (REPO_ROOT / "exercises").iterdir() if ex.is_dir())

def canonical_name_for(exercise: Path, uuid: str) -> str:
    return CANONICAL_DATA[exercise.name][uuid]

def categorize_implemented(exercise, canonical_tests):
    """
    Accepts an iterable of uuid

    Produces a tuple `(implemented, unimplemented)`.
    `implemented` is the set of all uuids of canonical tests which have definitely been implemented.
    `unimplemented` is the set of all uuids of canonical tests which have not definitely been implemented.
    """
    implemented = set()
    unimplemented = set()

    for test_uuid in canonical_tests:
        if is_implemented(exercise, test_uuid):
            implemented.add(test_uuid)
        else:
            unimplemented.add(test_uuid)

    return (implemented, unimplemented)

def is_implemented(exercise: Path, uuid: str) -> bool:
    canonical_name = canonical_name_for(exercise, uuid)
    return (
        canonical_name in FUNCTIONS[exercise]
        or generated_name(canonical_name) in FUNCTIONS[exercise]
    )

def generated_name(canonical_name: str) -> str:
    """
    see https://github.com/exercism/rust/blob/abdc94b6082a5cf63ff7f22b7420965e8755951b/util/exercise/src/lib.rs#L197-L204
    """
    name = "".join(c for c in canonical_name if c in ALPHANUMERIC)
    return "test_" + name.replace(" ", "_").lower()

def main():
    for exercise in exercise_directories():
        try:
            with (exercise / ".meta" / "tests.toml").open("rt") as tests_toml:
                tests_data = tomlkit.parse(tests_toml.read())

            print(f"{exercise.name}:")

            try:
                implemented, unimplemented = categorize_implemented(
                    exercise, tests_data["canonical-tests"].keys()
                )

                for test_uuid in tests_data["canonical-tests"].keys():
                    tests_data["canonical-tests"][test_uuid] = test_uuid in implemented
            except Exception as e:
                # even if one test doesn't work, keep going through all of them
                print(f"  {e}")
            else:
                # only modify the data if it passes, though
                with (exercise / ".meta" / "tests.toml").open("wt") as tests_toml:
                    tests_toml.write(tomlkit.dumps(tests_data))

                print("  unimplemented canonical functions:")
                for u in unimplemented:
                    print(f"    {u} => {canonical_name_for(exercise, u)}")

        except FileNotFoundError:
            pass

    # re-add quotes around uuid keys for minimal diffs
    subprocess.run(
        shlex.split(
            r"fd -uu tests.toml -x sed -i -E -e 's/^([-a-zA-Z0-9]+) =/\"\1\" =/'"
        ),
        cwd=REPO_ROOT / "exercises",
    ).check_returncode()

if __name__ == "__main__":
    main()
```

Co-authored-by: Peter Goodspeed-Niklaus <[email protected]>

Author: ErikSchierboom

exercises/acronym/.meta/tests.toml

@@ -0,0 +1,28 @@
+[canonical-tests]
+
+# basic
+"1e22cceb-c5e4-4562-9afe-aef07ad1eaf4" = true
+
+# lowercase words
+"79ae3889-a5c0-4b01-baf0-232d31180c08" = true
+
+# punctuation
+"ec7000a7-3931-4a17-890e-33ca2073a548" = true
+
+# all caps word
+"32dd261c-0c92-469a-9c5c-b192e94a63b0" = true
+
+# punctuation without whitespace
+"ae2ac9fa-a606-4d05-8244-3bcc4659c1d4" = true
+
+# very long abbreviation
+"0e4b1e7c-1a6d-48fb-81a7-bf65eb9e69f9" = true
+
+# consecutive delimiters
+"6a078f49-c68d-4b7b-89af-33a1a98c28cc" = true
+
+# apostrophes
+"5118b4b1-4572-434c-8d57-5b762e57973e" = true
+
+# underscore emphasis
+"adc12eab-ec2d-414f-b48c-66a4fc06cdef" = true

exercises/affine-cipher/.meta/tests.toml

@@ -0,0 +1,49 @@
+[canonical-tests]
+
+# encode yes
+"2ee1d9af-1c43-416c-b41b-cefd7d4d2b2a" = true
+
+# encode no
+"785bade9-e98b-4d4f-a5b0-087ba3d7de4b" = true
+
+# encode OMG
+"2854851c-48fb-40d8-9bf6-8f192ed25054" = true
+
+# encode O M G
+"bc0c1244-b544-49dd-9777-13a770be1bad" = true
+
+# encode mindblowingly
+"381a1a20-b74a-46ce-9277-3778625c9e27" = true
+
+# encode numbers
+"6686f4e2-753b-47d4-9715-876fdc59029d" = true
+
+# encode deep thought
+"ae23d5bd-30a8-44b6-afbe-23c8c0c7faa3" = true
+
+# encode all the letters
+"c93a8a4d-426c-42ef-9610-76ded6f7ef57" = true
+
+# encode with a not coprime to m
+"0673638a-4375-40bd-871c-fb6a2c28effb" = true
+
+# decode exercism
+"3f0ac7e2-ec0e-4a79-949e-95e414953438" = true
+
+# decode a sentence
+"241ee64d-5a47-4092-a5d7-7939d259e077" = true
+
+# decode numbers
+"33fb16a1-765a-496f-907f-12e644837f5e" = true
+
+# decode all the letters
+"20bc9dce-c5ec-4db6-a3f1-845c776bcbf7" = true
+
+# decode with no spaces in input
+"623e78c0-922d-49c5-8702-227a3e8eaf81" = true
+
+# decode with too many spaces
+"58fd5c2a-1fd9-4563-a80a-71cff200f26f" = true
+
+# decode with a not coprime to m
+"b004626f-c186-4af9-a3f4-58f74cdb86d5" = true

exercises/all-your-base/.meta/tests.toml

@@ -0,0 +1,64 @@
+[canonical-tests]
+
+# single bit one to decimal
+"5ce422f9-7a4b-4f44-ad29-49c67cb32d2c" = true
+
+# binary to single decimal
+"0cc3fea8-bb79-46ac-a2ab-5a2c93051033" = true
+
+# single decimal to binary
+"f12db0f9-0d3d-42c2-b3ba-e38cb375a2b8" = true
+
+# binary to multiple decimal
+"2c45cf54-6da3-4748-9733-5a3c765d925b" = true
+
+# decimal to binary
+"65ddb8b4-8899-4fcc-8618-181b2cf0002d" = true
+
+# trinary to hexadecimal
+"8d418419-02a7-4824-8b7a-352d33c6987e" = true
+
+# hexadecimal to trinary
+"d3901c80-8190-41b9-bd86-38d988efa956" = true
+
+# 15-bit integer
+"5d42f85e-21ad-41bd-b9be-a3e8e4258bbf" = false
+
+# empty list
+"d68788f7-66dd-43f8-a543-f15b6d233f83" = true
+
+# single zero
+"5e27e8da-5862-4c5f-b2a9-26c0382b6be7" = true
+
+# multiple zeros
+"2e1c2573-77e4-4b9c-8517-6c56c5bcfdf2" = true
+
+# leading zeros
+"3530cd9f-8d6d-43f5-bc6e-b30b1db9629b" = true
+
+# input base is one
+"a6b476a1-1901-4f2a-92c4-4d91917ae023" = true
+
+# input base is zero
+"e21a693a-7a69-450b-b393-27415c26a016" = true
+
+# input base is negative
+"54a23be5-d99e-41cc-88e0-a650ffe5fcc2" = false
+
+# negative digit
+"9eccf60c-dcc9-407b-95d8-c37b8be56bb6" = false
+
+# invalid positive digit
+"232fa4a5-e761-4939-ba0c-ed046cd0676a" = true
+
+# output base is one
+"14238f95-45da-41dc-95ce-18f860b30ad3" = true
+
+# output base is zero
+"73dac367-da5c-4a37-95fe-c87fad0a4047" = true
+
+# output base is negative
+"13f81f42-ff53-4e24-89d9-37603a48ebd9" = false
+
+# both bases are negative
+"0e6c895d-8a5d-4868-a345-309d094cfe8d" = false

exercises/allergies/.meta/tests.toml

@@ -0,0 +1,148 @@
+[canonical-tests]
+
+# not allergic to anything
+"17fc7296-2440-4ac4-ad7b-d07c321bc5a0" = false
+
+# allergic only to eggs
+"07ced27b-1da5-4c2e-8ae2-cb2791437546" = false
+
+# allergic to eggs and something else
+"5035b954-b6fa-4b9b-a487-dae69d8c5f96" = false
+
+# allergic to something, but not eggs
+"64a6a83a-5723-4b5b-a896-663307403310" = false
+
+# allergic to everything
+"90c8f484-456b-41c4-82ba-2d08d93231c6" = true
+
+# not allergic to anything
+"d266a59a-fccc-413b-ac53-d57cb1f0db9d" = false
+
+# allergic only to peanuts
+"ea210a98-860d-46b2-a5bf-50d8995b3f2a" = false
+
+# allergic to peanuts and something else
+"eac69ae9-8d14-4291-ac4b-7fd2c73d3a5b" = false
+
+# allergic to something, but not peanuts
+"9152058c-ce39-4b16-9b1d-283ec6d25085" = false
+
+# allergic to everything
+"d2d71fd8-63d5-40f9-a627-fbdaf88caeab" = true
+
+# not allergic to anything
+"b948b0a1-cbf7-4b28-a244-73ff56687c80" = false
+
+# allergic only to shellfish
+"9ce9a6f3-53e9-4923-85e0-73019047c567" = false
+
+# allergic to shellfish and something else
+"b272fca5-57ba-4b00-bd0c-43a737ab2131" = false
+
+# allergic to something, but not shellfish
+"21ef8e17-c227-494e-8e78-470a1c59c3d8" = false
+
+# allergic to everything
+"cc789c19-2b5e-4c67-b146-625dc8cfa34e" = true
+
+# not allergic to anything
+"651bde0a-2a74-46c4-ab55-02a0906ca2f5" = false
+
+# allergic only to strawberries
+"b649a750-9703-4f5f-b7f7-91da2c160ece" = false
+
+# allergic to strawberries and something else
+"50f5f8f3-3bac-47e6-8dba-2d94470a4bc6" = false
+
+# allergic to something, but not strawberries
+"23dd6952-88c9-48d7-a7d5-5d0343deb18d" = false
+
+# allergic to everything
+"74afaae2-13b6-43a2-837a-286cd42e7d7e" = true
+
+# not allergic to anything
+"c49a91ef-6252-415e-907e-a9d26ef61723" = false
+
+# allergic only to tomatoes
+"b69c5131-b7d0-41ad-a32c-e1b2cc632df8" = false
+
+# allergic to tomatoes and something else
+"1ca50eb1-f042-4ccf-9050-341521b929ec" = false
+
+# allergic to something, but not tomatoes
+"e9846baa-456b-4eff-8025-034b9f77bd8e" = false
+
+# allergic to everything
+"b2414f01-f3ad-4965-8391-e65f54dad35f" = true
+
+# not allergic to anything
+"978467ab-bda4-49f7-b004-1d011ead947c" = false
+
+# allergic only to chocolate
+"59cf4e49-06ea-4139-a2c1-d7aad28f8cbc" = false
+
+# allergic to chocolate and something else
+"b0a7c07b-2db7-4f73-a180-565e07040ef1" = false
+
+# allergic to something, but not chocolate
+"f5506893-f1ae-482a-b516-7532ba5ca9d2" = false
+
+# allergic to everything
+"02debb3d-d7e2-4376-a26b-3c974b6595c6" = true
+
+# not allergic to anything
+"17f4a42b-c91e-41b8-8a76-4797886c2d96" = false
+
+# allergic only to pollen
+"7696eba7-1837-4488-882a-14b7b4e3e399" = false
+
+# allergic to pollen and something else
+"9a49aec5-fa1f-405d-889e-4dfc420db2b6" = false
+
+# allergic to something, but not pollen
+"3cb8e79f-d108-4712-b620-aa146b1954a9" = false
+
+# allergic to everything
+"1dc3fe57-7c68-4043-9d51-5457128744b2" = true
+
+# not allergic to anything
+"d3f523d6-3d50-419b-a222-d4dfd62ce314" = false
+
+# allergic only to cats
+"eba541c3-c886-42d3-baef-c048cb7fcd8f" = false
+
+# allergic to cats and something else
+"ba718376-26e0-40b7-bbbe-060287637ea5" = false
+
+# allergic to something, but not cats
+"3c6dbf4a-5277-436f-8b88-15a206f2d6c4" = false
+
+# allergic to everything
+"1faabb05-2b98-4995-9046-d83e4a48a7c1" = true
+
+# no allergies
+"f9c1b8e7-7dc5-4887-aa93-cebdcc29dd8f" = false
+
+# just eggs
+"9e1a4364-09a6-4d94-990f-541a94a4c1e8" = false
+
+# just peanuts
+"8851c973-805e-4283-9e01-d0c0da0e4695" = false
+
+# just strawberries
+"2c8943cb-005e-435f-ae11-3e8fb558ea98" = false
+
+# eggs and peanuts
+"6fa95d26-044c-48a9-8a7b-9ee46ec32c5c" = false
+
+# more than eggs but not peanuts
+"19890e22-f63f-4c5c-a9fb-fb6eacddfe8e" = false
+
+# lots of stuff
+"4b68f470-067c-44e4-889f-c9fe28917d2f" = false
+
+# everything
+"0881b7c5-9efa-4530-91bd-68370d054bc7" = false
+
+# no allergen score parts
+"12ce86de-b347-42a0-ab7c-2e0570f0c65b" = false

exercises/alphametics/.meta/tests.toml

@@ -0,0 +1,31 @@
+[canonical-tests]
+
+# puzzle with three letters
+"e0c08b07-9028-4d5f-91e1-d178fead8e1a" = false
+
+# solution must have unique value for each letter
+"a504ee41-cb92-4ec2-9f11-c37e95ab3f25" = false
+
+# leading zero solution is invalid
+"4e3b81d2-be7b-4c5c-9a80-cd72bc6d465a" = false
+
+# puzzle with two digits final carry
+"8a3e3168-d1ee-4df7-94c7-b9c54845ac3a" = true
+
+# puzzle with four letters
+"a9630645-15bd-48b6-a61e-d85c4021cc09" = false
+
+# puzzle with six letters
+"3d905a86-5a52-4e4e-bf80-8951535791bd" = false
+
+# puzzle with seven letters
+"4febca56-e7b7-4789-97b9-530d09ba95f0" = false
+
+# puzzle with eight letters
+"12125a75-7284-4f9a-a5fa-191471e0d44f" = false
+
+# puzzle with ten letters
+"fb05955f-38dc-477a-a0b6-5ef78969fffa" = false
+
+# puzzle with ten letters and 199 addends
+"9a101e81-9216-472b-b458-b513a7adacf7" = false

exercises/anagram/.meta/tests.toml

@@ -0,0 +1,43 @@
+[canonical-tests]
+
+# no matches
+"dd40c4d2-3c8b-44e5-992a-f42b393ec373" = false
+
+# detects two anagrams
+"b3cca662-f50a-489e-ae10-ab8290a09bdc" = false
+
+# does not detect anagram subsets
+"a27558ee-9ba0-4552-96b1-ecf665b06556" = false
+
+# detects anagram
+"64cd4584-fc15-4781-b633-3d814c4941a4" = false
+
+# detects three anagrams
+"99c91beb-838f-4ccd-b123-935139917283" = false
+
+# detects multiple anagrams with different case
+"78487770-e258-4e1f-a646-8ece10950d90" = false
+
+# does not detect non-anagrams with identical checksum
+"1d0ab8aa-362f-49b7-9902-3d0c668d557b" = false
+
+# detects anagrams case-insensitively
+"9e632c0b-c0b1-4804-8cc1-e295dea6d8a8" = false
+
+# detects anagrams using case-insensitive subject
+"b248e49f-0905-48d2-9c8d-bd02d8c3e392" = false
+
+# detects anagrams using case-insensitive possible matches
+"f367325c-78ec-411c-be76-e79047f4bd54" = false
+
+# does not detect an anagram if the original word is repeated
+"7cc195ad-e3c7-44ee-9fd2-d3c344806a2c" = false
+
+# anagrams must use all letters exactly once
+"9878a1c9-d6ea-4235-ae51-3ea2befd6842" = false
+
+# words are not anagrams of themselves (case-insensitive)
+"85757361-4535-45fd-ac0e-3810d40debc1" = false
+
+# words other than themselves can be anagrams
+"a0705568-628c-4b55-9798-82e4acde51ca" = false

exercises/armstrong-numbers/.meta/tests.toml

@@ -0,0 +1,28 @@
+[canonical-tests]
+
+# Zero is an Armstrong number
+"c1ed103c-258d-45b2-be73-d8c6d9580c7b" = false
+
+# Single digit numbers are Armstrong numbers
+"579e8f03-9659-4b85-a1a2-d64350f6b17a" = false
+
+# There are no 2 digit Armstrong numbers
+"2d6db9dc-5bf8-4976-a90b-b2c2b9feba60" = false
+
+# Three digit number that is an Armstrong number
+"509c087f-e327-4113-a7d2-26a4e9d18283" = false
+
+# Three digit number that is not an Armstrong number
+"7154547d-c2ce-468d-b214-4cb953b870cf" = false
+
+# Four digit number that is an Armstrong number
+"6bac5b7b-42e9-4ecb-a8b0-4832229aa103" = false
+
+# Four digit number that is not an Armstrong number
+"eed4b331-af80-45b5-a80b-19c9ea444b2e" = false
+
+# Seven digit number that is an Armstrong number
+"f971ced7-8d68-4758-aea1-d4194900b864" = false
+
+# Seven digit number that is not an Armstrong number
+"7ee45d52-5d35-4fbd-b6f1-5c8cd8a67f18" = false