160 lines
3.4 KiB
Python
160 lines
3.4 KiB
Python
"""Command-line interface for the text analyzer."""
|
|
|
|
import argparse
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
from typing import Final
|
|
|
|
from text_analyzer.core import TextStatistics, analyze_file
|
|
|
|
DEFAULT_TOP: Final[int] = 10
|
|
DEFAULT_MIN_LEN: Final[int] = 1
|
|
DEFAULT_ENCODING: Final[str] = "utf-8"
|
|
|
|
|
|
def build_parser() -> argparse.ArgumentParser:
|
|
"""Build command-line parser."""
|
|
parser = argparse.ArgumentParser(
|
|
prog="text-analyzer",
|
|
description="Analyze a text file.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"path",
|
|
type=Path,
|
|
help="Path to the text file.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--top",
|
|
type=int,
|
|
default=DEFAULT_TOP,
|
|
help="Number of most frequent words.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--min-len",
|
|
type=int,
|
|
default=DEFAULT_MIN_LEN,
|
|
help="Minimum word length.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--format",
|
|
choices=("text", "json"),
|
|
default="text",
|
|
help="Output format.",
|
|
)
|
|
|
|
parser.add_argument(
|
|
"--encoding",
|
|
default=DEFAULT_ENCODING,
|
|
help="Input file encoding.",
|
|
)
|
|
|
|
return parser
|
|
|
|
|
|
def format_text(statistics: TextStatistics) -> str:
|
|
"""Format statistics as text."""
|
|
lines = [
|
|
f"Lines: {statistics.lines}",
|
|
f"Words: {statistics.words}",
|
|
f"Characters: {statistics.characters}",
|
|
"Top words:",
|
|
]
|
|
|
|
if statistics.top_words:
|
|
for word, count in statistics.top_words:
|
|
lines.append(f" {word}: {count}")
|
|
else:
|
|
lines.append(" No words found.")
|
|
|
|
return "\n".join(lines)
|
|
|
|
|
|
def format_json(statistics: TextStatistics) -> str:
|
|
"""Format statistics as JSON."""
|
|
data = {
|
|
"lines": statistics.lines,
|
|
"words": statistics.words,
|
|
"characters": statistics.characters,
|
|
"top_words": [
|
|
{
|
|
"word": word,
|
|
"count": count,
|
|
}
|
|
for word, count in statistics.top_words
|
|
],
|
|
}
|
|
|
|
return json.dumps(
|
|
data,
|
|
ensure_ascii=True,
|
|
indent=2,
|
|
)
|
|
|
|
|
|
def main() -> int:
|
|
"""Run CLI application."""
|
|
parser = build_parser()
|
|
args = parser.parse_args()
|
|
|
|
if args.top < 0:
|
|
print(
|
|
"Error: --top must be non-negative.",
|
|
file=sys.stderr,
|
|
)
|
|
return 2
|
|
|
|
if args.min_len < 1:
|
|
print(
|
|
"Error: --min-len must be at least 1.",
|
|
file=sys.stderr,
|
|
)
|
|
return 2
|
|
|
|
try:
|
|
statistics = analyze_file(
|
|
args.path,
|
|
top=args.top,
|
|
min_len=args.min_len,
|
|
encoding=args.encoding,
|
|
)
|
|
except FileNotFoundError:
|
|
print(
|
|
f"Error: file not found: {args.path}",
|
|
file=sys.stderr,
|
|
)
|
|
return 1
|
|
except UnicodeError:
|
|
print(
|
|
f"Error: cannot decode file using encoding: {args.encoding}",
|
|
file=sys.stderr,
|
|
)
|
|
return 1
|
|
except OSError as exc:
|
|
print(
|
|
f"Error: cannot read file: {exc}",
|
|
file=sys.stderr,
|
|
)
|
|
return 1
|
|
except ValueError as exc:
|
|
print(
|
|
f"Error: {exc}",
|
|
file=sys.stderr,
|
|
)
|
|
return 2
|
|
|
|
if args.format == "json":
|
|
print(format_json(statistics))
|
|
else:
|
|
print(format_text(statistics))
|
|
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|