From 7ef5313d73370e556a9020458c8ead71c704157d Mon Sep 17 00:00:00 2001
From: vlitvintseva <24_LitvintsevaVD@iux.local>
Date: Sun, 6 Sep 2026 22:58:22 +0300
Subject: [PATCH] feat: initial commit with CLI, core logic and tests

---
 .gitignore                    |  5 +++
 README.md                     |  9 +++++
 pyproject.toml                | 22 ++++++++++++
 requirements.txt              |  0
 src/text_analyzer/__init__.py |  0
 src/text_analyzer/cli.py      | 40 ++++++++++++++++++++++
 src/text_analyzer/core.py     | 28 +++++++++++++++
 tests/__init__.py             |  0
 tests/test_core.py            | 64 +++++++++++++++++++++++++++++++++++
 9 files changed, 168 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 README.md
 create mode 100644 pyproject.toml
 create mode 100644 requirements.txt
 create mode 100644 src/text_analyzer/__init__.py
 create mode 100644 src/text_analyzer/cli.py
 create mode 100644 src/text_analyzer/core.py
 create mode 100644 tests/__init__.py
 create mode 100644 tests/test_core.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..a9b5d64
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,5 @@
+.venv/
+__pycache__/
+*.egg-info/
+.pytest_cache/
+.coverage
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..52f5c46
--- /dev/null
+++ b/README.md
@@ -0,0 +1,9 @@
+# Text Analyzer CLI
+
+CLI-инструмент на Python для анализа текстовых файлов (подсчёт строк, слов, символов и топ-N популярных слов).
+
+## Установка
+
+1. Клонируйте репозиторий и перейдите в папку проекта:
+```bash
+cd lb_1
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..768f9fa
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "text_analyzer"
+version = "0.1.0"
+description = "CLI tool for analyzing text files"
+requires-python = ">=3.12"
+dependencies = []
+
+[project.scripts]
+text-analyzer = "text_analyzer.cli:main"
+
+[tool.ruff]
+line-length = 88
+
+[tool.mypy]
+strict = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..e69de29
diff --git a/src/text_analyzer/__init__.py b/src/text_analyzer/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/text_analyzer/cli.py b/src/text_analyzer/cli.py
new file mode 100644
index 0000000..9ca9d15
--- /dev/null
+++ b/src/text_analyzer/cli.py
@@ -0,0 +1,40 @@
+import argparse
+import json
+import sys
+from pathlib import Path
+
+from text_analyzer.core import analyze_file
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Text Analyzer CLI tool")
+    parser.add_argument("file", type=Path, help="Path to text file")
+    parser.add_argument("--top", type=int, default=5, help="Top N words")
+    parser.add_argument("--min-len", type=int, default=1, help="Minimum word length")
+    parser.add_argument(
+        "--format", choices=["text", "json"], default="text", help="Output format"
+    )
+
+    args = parser.parse_args()
+
+    try:
+        results = analyze_file(args.file, top_n=args.top, min_len=args.min_len)
+    except FileNotFoundError as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if args.format == "json":
+        print(json.dumps(results, indent=2))
+    else:
+        print(f"Lines: {results['lines']}")
+        print(f"Words: {results['words']}")
+        print(f"Chars: {results['chars']}")
+        print("Top words:")
+        top_words = results["top_words"]
+        if isinstance(top_words, list):
+            for word, count in top_words:
+                print(f"  {word}: {count}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/src/text_analyzer/core.py b/src/text_analyzer/core.py
new file mode 100644
index 0000000..b5c2c49
--- /dev/null
+++ b/src/text_analyzer/core.py
@@ -0,0 +1,28 @@
+from collections import Counter
+from pathlib import Path
+
+
+def analyze_file(
+    file_path: Path, top_n: int = 5, min_len: int = 1
+) -> dict[str, object]:
+    # Чтение файла и сбор базовой статистики
+    if not file_path.exists():
+        raise FileNotFoundError(f"File not found: {file_path}")
+
+    text = file_path.read_text(encoding="utf-8")
+    lines = text.splitlines()
+    words = [
+        w.lower().strip(".,!?;:\"'()")
+        for w in text.split()
+        if len(w.strip(".,!?;:\"'()")) >= min_len
+    ]
+
+    counter = Counter(words)
+    top_words = counter.most_common(top_n)
+
+    return {
+        "lines": len(lines),
+        "words": len(words),
+        "chars": len(text),
+        "top_words": top_words,
+    }
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/test_core.py b/tests/test_core.py
new file mode 100644
index 0000000..28774db
--- /dev/null
+++ b/tests/test_core.py
@@ -0,0 +1,64 @@
+from pathlib import Path
+
+import pytest
+
+from text_analyzer.core import analyze_file
+
+
+def test_basic_analysis(tmp_path: Path) -> None:
+    test_file = tmp_path / "test.txt"
+    test_file.write_text("hello world\nhello python")
+
+    res = analyze_file(test_file)
+    assert res["lines"] == 2
+    assert res["words"] == 4
+    assert res["top_words"] == [("hello", 2), ("world", 1), ("python", 1)]
+
+
+def test_file_not_found() -> None:
+    with pytest.raises(FileNotFoundError):
+        analyze_file(Path("non_existent_file_123.txt"))
+
+
+def test_empty_file(tmp_path: Path) -> None:
+    test_file = tmp_path / "empty.txt"
+    test_file.write_text("")
+
+    res = analyze_file(test_file)
+    assert res["lines"] == 0
+    assert res["words"] == 0
+    assert res["top_words"] == []
+
+
+@pytest.mark.parametrize(
+    "min_len,expected_words",
+    [
+        (1, 4),
+        (3, 2),
+        (4, 1),
+    ],
+)
+def test_min_length_filter(tmp_path: Path, min_len: int, expected_words: int) -> None:
+    test_file = tmp_path / "filter.txt"
+    test_file.write_text("a ab abc abcd")
+
+    res = analyze_file(test_file, min_len=min_len)
+    assert res["words"] == expected_words
+
+
+def test_top_n_param(tmp_path: Path) -> None:
+    test_file = tmp_path / "top.txt"
+    test_file.write_text("one two two three three three")
+
+    res = analyze_file(test_file, top_n=2)
+    top_words = res["top_words"]
+    assert isinstance(top_words, list)
+    assert len(top_words) == 2
+
+
+def test_punctuation_stripping(tmp_path: Path) -> None:
+    test_file = tmp_path / "punct.txt"
+    test_file.write_text("hello, world! hello...")
+
+    res = analyze_file(test_file)
+    assert res["top_words"] == [("hello", 2), ("world", 1)]