0 Where it starts

@@ -0,0 +1,13 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
+# Artifacts that just setup makes: they are not in git
+data/

@@ -0,0 +1 @@
+3.12

@@ -0,0 +1,13 @@
+# tally
+
+Count the words in a text.
+
+## Run it
+
+Make the environment, the corpus and the report first. Then count the words of a file:
+
+    just setup
+    uv run tally data/corpus.txt
+
+`uv run tally --top 10 data/corpus.txt` prints only the ten most common words. `just test` runs the tests, and
+`just report` writes the ten most common words of the corpus to `build/top.txt`.

@@ -0,0 +1,22 @@
+# The recipes of tally. Each one runs through uv, in the project's own environment.
+default:
+    @just --list
+
+# Make the environment of this step: the first command of every step
+setup:
+    uv sync
+    uv run python scripts/corpus.py data/corpus.txt
+    test -f build/top.txt || just report
+
+# Count the words of a file
+run file:
+    uv run tally {{ file }}
+
+# Run the tests
+test:
+    uv run python -m unittest discover -s tests -q
+
+# Write the ten most common words of the corpus to build/top.txt
+report:
+    mkdir -p build
+    uv run tally --top 10 data/corpus.txt > build/top.txt

@@ -0,0 +1,22 @@
+[project]
+name = "tally"
+version = "0.1.0"
+description = "Count the words in a text"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = []
+
+[project.scripts]
+tally = "tally:main"
+
+[build-system]
+requires = ["uv_build>=0.12.13,<0.13.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "ruff>=0.17.0",
+]
+
+[tool.ruff]
+line-length = 100

@@ -0,0 +1,25 @@
+"""Write data/corpus.txt, a text of 2000 words to count, the same every time. Leave it alone if it is there."""
+
+import sys
+from pathlib import Path
+
+WORDS = "the a word count text tally test step move commit tag note slide class shell file line code".split()
+
+
+def main() -> None:
+    target = Path(sys.argv[1] if len(sys.argv) > 1 else "data/corpus.txt")
+    if target.exists():
+        print(f"{target} is there")
+        return
+    seed, words = 7, []
+    for _ in range(2000):
+        seed = (seed * 1103515245 + 12345) % 2**31
+        words.append(WORDS[seed % len(WORDS)])
+    target.parent.mkdir(parents=True, exist_ok=True)
+    lines = (" ".join(words[i : i + 12]) for i in range(0, len(words), 12))
+    target.write_text("\n".join(lines) + "\n")
+    print(f"wrote {target}: {len(words)} words")
+
+
+if __name__ == "__main__":
+    main()

@@ -0,0 +1,27 @@
+"""tally: count the words in a text."""
+
+import sys
+
+
+def count(text: str) -> dict[str, int]:
+    "How many times each word of `text` appears, ignoring case."
+    counts = {}
+    for word in text.lower().split():
+        counts[word] = counts.get(word, 0) + 1
+    return counts
+
+
+def top(counts: dict[str, int], n: int) -> list[tuple[str, int]]:
+    "The n most common words, most common first."
+    return sorted(counts.items(), key=lambda pair: (-pair[1], pair[0]))[:n]
+
+
+def main() -> None:
+    "Count the words of a file, or of the standard input. With --top N, only the N most common."
+    args, n = sys.argv[1:], None
+    if args[:1] == ["--top"]:
+        n, args = int(args[1]), args[2:]
+    text = open(args[0]).read() if args else sys.stdin.read()
+    counts = count(text)
+    for word, times in top(counts, n) if n else sorted(counts.items()):
+        print(times, word)

@@ -0,0 +1,3 @@
+from tally import main
+
+main()

@@ -0,0 +1,11 @@
+import unittest
+
+from tally import count
+
+
+class Count(unittest.TestCase):
+    def test_words(self):
+        self.assertEqual(count("a b a"), {"a": 2, "b": 1})
+
+    def test_case(self):
+        self.assertEqual(count("A a"), {"a": 2})

@@ -0,0 +1,8 @@
+import unittest
+
+from tally import count
+
+
+class Empty(unittest.TestCase):
+    def test_empty(self):
+        self.assertEqual(count(""), {})

@@ -0,0 +1,8 @@
+import unittest
+
+from tally import top
+
+
+class Top(unittest.TestCase):
+    def test_most_common_first(self):
+        self.assertEqual(top({"a": 1, "b": 3, "c": 2}, 2), [("b", 3), ("c", 2)])