mirror of
https://github.com/kuhyx/WUT_Computer_Science.git
synced 2026-11-10 21:27:08 +01:00
Krzysztof kuhy Rudnicki
bd24dd57ea
kuhy overruled the "do not fix coursework to be better than it was submitted" rule: git history is the archive, so the working tree can be clean. This lands the config and the mechanical half of the cleanup -- 9,281 ruff findings under the fleet config down to 3,686, with no per-file-ignores anywhere. What is in here: - pyproject.toml, the first one in this repo. select = ["ALL"], mypy strict, and the vendored list mirrored into ruff exclude and coverage omit. Five rules are off and each says why; CPY001 is the only judgement call, because stamping a copyright header onto 137 university assignments would assert a licence that was never claimed. No hook is wired up yet -- a gate lands only once its subject is clean. - ruff format + the safe fixes, then a second pass over the docstring rules ruff marks unsafe (they only edit docstring text). 108 files. - TRAK/sightpy is vendored, not coursework: it is rafael-fuente/Python-Raytracer (BSD 3-Clause). Verified against a fresh upstream clone with line endings normalised -- 30 of 32 files byte-identical, ray.py and scene.py carrying a 12- and 13-line local patch that counts rays for the report. 35 files that should never have been linted, now excluded and restored. - WDWR, SPD, MOM and ECRYPT are fully clean, by hand and verified by running them: WDWR's three plot scripts print the same statistics as before, MOM's PuLP model solves to the same cost. WDWR's graph.py had a 342-character CSV header embedded as a string literal, which cannot be wrapped -- the data moved to data/pareto_front.csv. Two 0-byte .py stubs are deleted; an empty file is not a deliverable and git still has it. Three harness bugs found by actually running things: - `run` now forces MPLBACKEND=Agg. TRAK finished its ray trace in 37 seconds and then sat for 45 minutes: plt.show() had opened an image viewer and was waiting for someone to close the window. - TRAK's main.py only pops that viewer with --show now, and its runner writes to a gitignored build/ via the new --entry-args. The default output path is outputs/output.png, which is TRACKED -- a plain run overwrote a submitted deliverable. - course_lib.sh was 357 lines, over this repo's own cap. Split into course_probe.sh and course_run.sh. Verified: ECOTE 26 tests pass, ECRYPT_PROJECT 99 pass, TRAK renders cornell_box in 37s and exits 0, every module compiles, and every import ruff removed was checked to be genuinely unused. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0172dj34FDpao6wsix8ZuCzE
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
def reformat_sentence(sentence):
|
|
"""Reformats a sentence by replacing slashes '/' with ' ]'."""
|
|
return sentence.replace("/", " ]")
|
|
|
|
|
|
def insert_commas(sentence, reference_sentence):
|
|
"""Inserts commas into 'sentence' at the same positions as they appear in 'reference_sentence'."""
|
|
# Splitting the sentences into chunks
|
|
sentence_chunks = sentence.split(" ] [ ")
|
|
reference_chunks = reference_sentence.split(" ] [ ")
|
|
|
|
# Insert commas into the original sentence based on the reference sentence
|
|
for i, chunk in enumerate(reference_chunks):
|
|
if "," in chunk and i < len(sentence_chunks):
|
|
sentence_chunks[i] += ","
|
|
|
|
# Reconstruct the sentence with inserted commas
|
|
return " ] [ ".join(sentence_chunks)
|
|
|
|
|
|
def process_sentences(sentences1, sentences2):
|
|
"""Processes two lists of sentences according to the specified rules."""
|
|
processed_sentences = []
|
|
|
|
for sentence1, sentence2 in zip(sentences1, sentences2):
|
|
# Reformat the first sentence
|
|
reformatted_sentence1 = reformat_sentence(sentence1)
|
|
reformatted_sentence1 = insert_commas(reformatted_sentence1, sentence2)
|
|
# Splitting the sentences into words, ignoring the square brackets
|
|
words1 = set(
|
|
" ".join(reformatted_sentence1.strip().split("] ["))
|
|
.replace("[", "")
|
|
.replace("]", "")
|
|
.lower()
|
|
.split()
|
|
)
|
|
words2 = set(
|
|
" ".join(sentence2.strip().split("] ["))
|
|
.replace("[", "")
|
|
.replace("]", "")
|
|
.lower()
|
|
.split()
|
|
)
|
|
|
|
# Finding differences in words
|
|
diff = words2 - words1
|
|
|
|
# Preparing the output sentence
|
|
output_sentence = reformatted_sentence1.strip()
|
|
if "[ . ]" in sentence2:
|
|
output_sentence += " [ . ]"
|
|
|
|
# Adding the differences and the output sentence to the processed_sentences list
|
|
processed_sentences.append(
|
|
{
|
|
"sentence1": reformatted_sentence1.strip(),
|
|
"sentence2": sentence2.strip(),
|
|
"differences": diff,
|
|
"merged_sentence": output_sentence,
|
|
}
|
|
)
|
|
if diff and diff != {"."}:
|
|
print("Difference found!")
|
|
print("Sentence 1:", reformatted_sentence1.strip())
|
|
print("Sentence 2:", sentence2.strip())
|
|
print("Differences:", diff)
|
|
print("\n")
|
|
|
|
return processed_sentences
|
|
|
|
|
|
# First, let's open and read the contents of both files to understand their structure and content.
|
|
file_path_1 = "test_goldStandard/images/images-chunks-gpt-one.txt"
|
|
file_path_2 = "test_goldStandard/images/STSint.testinput.images.sent1.chunk.txt"
|
|
|
|
# Reading the files
|
|
with open(file_path_1) as file1, open(file_path_2) as file2:
|
|
sentences_file_1 = file1.readlines()
|
|
sentences_file_2 = file2.readlines()
|
|
|
|
# Process the sentences
|
|
processed_sentences = process_sentences(sentences_file_1, sentences_file_2)
|