使用 Python 计算目录中的代码行数

Count lines of code in directory using Python

我有一个项目,我想计算它的代码行数。是否可以通过Python?

统计项目所在文件目录下的所有代码行数
from os import listdir
from os.path import isfile, join

def countLinesInPath(path,directory):
    count=0
    for line in open(join(directory,path), encoding="utf8"):
        count+=1
    return count

def countLines(paths,directory):
    count=0
    for path in paths:
        count=count+countLinesInPath(path,directory)
    return count

def getPaths(directory):
    return [f for f in listdir(directory) if isfile(join(directory, f))]

def countIn(directory):
    return countLines(getPaths(directory),directory)

要计算目录中文件的所有代码行数,调用“countIn”函数,将目录作为参数传递。

这是我编写的一个函数,用于计算 python 包中的所有代码行并打印信息输出。它将计算所有 .py

中的所有行
import os

def countlines(start, lines=0, header=True, begin_start=None):
    if header:
        print('{:>10} |{:>10} | {:<20}'.format('ADDED', 'TOTAL', 'FILE'))
        print('{:->11}|{:->11}|{:->20}'.format('', '', ''))

    for thing in os.listdir(start):
        thing = os.path.join(start, thing)
        if os.path.isfile(thing):
            if thing.endswith('.py'):
                with open(thing, 'r') as f:
                    newlines = f.readlines()
                    newlines = len(newlines)
                    lines += newlines

                    if begin_start is not None:
                        reldir_of_thing = '.' + thing.replace(begin_start, '')
                    else:
                        reldir_of_thing = '.' + thing.replace(start, '')

                    print('{:>10} |{:>10} | {:<20}'.format(
                            newlines, lines, reldir_of_thing))


    for thing in os.listdir(start):
        thing = os.path.join(start, thing)
        if os.path.isdir(thing):
            lines = countlines(thing, lines, header=False, begin_start=start)

    return lines

要使用它,只需传递您想要开始的目录。例如,计算某个包中的代码行数 foo:

countlines(r'...\foo')

这会输出如下内容:

     ADDED |     TOTAL | FILE               
-----------|-----------|--------------------
        5  |        5  | .\__init__.py       
       539 |       578 | .\bar.py          
       558 |      1136 | .\baz\qux.py         

这是从 Daniel 的回答中得出的(尽管重构得足够多以至于这不会很明显)。那个不通过子目录递归,这是我想要的行为。

from os import listdir
from os.path import isfile, isdir, join

def item_line_count(path):
    if isdir(path):
        return dir_line_count(path)
    elif isfile(path):
        return len(open(path, 'rb').readlines())
    else:
        return 0

def dir_line_count(dir):
    return sum(map(lambda item: item_line_count(join(dir, item)), listdir(dir)))

pygount 将显示文件夹中的所有文件,每个文件都有代码行数(不包括文档)

https://pypi.org/project/pygount/

pip install pygount

列出当前目录的结果运行:

pygount ~/path_to_directory

这有点家庭作业的味道:-) -- none不过,这是一个值得的练习,而且 Bryce93 的格式很好。我认为很多人不太可能为此使用 Python,因为它可以通过几个 shell 命令快速完成,例如:

cat $(find . -name "*.py") | grep -E -v '^\s*$|^\s*#' | wc -l

请注意,这些解决方案中有 none 个涉及多行 (''') 注释。

作为 pygount 答案的补充,他们刚刚添加了选项 --format=summary 以获取目录中不同文件类型的总行数。

pygount --format=summary ./your-directory

可以输出类似

的东西
  Language     Code    %     Comment    %
-------------  ----  ------  -------  ------
XML            1668   48.56       10    0.99
Python          746   21.72      150   14.90
TeX             725   21.11       57    5.66
HTML            191    5.56        0    0.00
markdown         58    1.69        0    0.00
JSON             37    1.08        0    0.00
INI              10    0.29        0    0.00
Text              0    0.00      790   78.45
__duplicate__     0    0.00        0    0.00
-------------  ----  ------  -------  ------
Sum total      3435             1007

基于 Bryce93 的回答,使用 code_only 选项从行数中排除注释、文档字符串和空行:

import os

def countlines(rootdir, total_lines=0, header=True, begin_start=None,
               code_only=True):
    def _get_new_lines(source):
        total = len(source)
        i = 0
        while i < len(source):
            line = source[i]
            trimline = line.lstrip(" ")

            if trimline.startswith('#') or trimline == '':
                total -= 1
            elif '"""' in trimline:  # docstring begin
                if trimline.count('"""') == 2:  # docstring end on same line
                    total -= 1
                    i += 1
                    continue
                doc_start = i
                i += 1
                while '"""' not in source[i]:  # docstring end
                    i += 1
                doc_end = i
                total -= (doc_end - doc_start + 1)
            i += 1
        return total

    if header:
        print('{:>10} |{:>10} | {:<20}'.format('ADDED', 'TOTAL', 'FILE'))
        print('{:->11}|{:->11}|{:->20}'.format('', '', ''))

    for name in os.listdir(rootdir):
        file = os.path.join(rootdir, name)
        if os.path.isfile(file) and file.endswith('.py'):
            with open(file, 'r') as f:
                source = f.readlines()

            if code_only:
                new_lines = _get_new_lines(source)
            else:
                new_lines = len(source)
            total_lines += new_lines

            if begin_start is not None:
                reldir_of_file = '.' + file.replace(begin_start, '')
            else:
                reldir_of_file = '.' + file.replace(rootdir, '')

            print('{:>10} |{:>10} | {:<20}'.format(
                    new_lines, total_lines, reldir_of_file))

    for file in os.listdir(rootdir):
        file = os.path.join(rootdir, file)
        if os.path.isdir(file):
            total_lines = countlines(file, total_lines, header=False,
                                     begin_start=rootdir, code_only=code_only)
    return total_lines

如果您想计算项目中有多少行,请在项目文件夹中创建一个脚本并将以下内容粘贴到其中:

import os

directory = "[project_directory]"
directory_depth = 100 # How deep you would like to go
extensions_to_consider = [".py", ".css"]  # Change to ["all"] to include all extensions
exclude_filenames = ["venv", ".idea", "__pycache__", "cache"]
skip_file_error_list = True

this_file_dir = os.path.realpath(__file__)

print("Path to ignore:", this_file_dir)
print("=====================================")
def _walk(path, depth):
    """Recursively list files and directories up to a certain depth"""
    depth -= 1
    with os.scandir(path) as p:
        for entry in p:

            skip_entry = False
            for fName in exclude_filenames:
                if entry.path.endswith(fName):
                    skip_entry = True
                    break

            if skip_entry:
                print("Skipping entry", entry.path)
                continue

            yield entry.path
            if entry.is_dir() and depth > 0:
                yield from _walk(entry.path, depth)

print("Caching entries")
files = list(_walk(directory, directory_depth))
print("=====================================")

print("Counting Lines")
file_err_list = []
line_count = 0
len_files = len(files)
for i, file_dir in enumerate(files):

    if file_dir == this_file_dir:
        print("=[Rejected file directory", file_dir, "]=")
        continue

    if not os.path.isfile(file_dir):
        continue

    skip_File = True
    for ending in extensions_to_consider:
        if file_dir.endswith(ending) or ending == "all":
            skip_File = False

    if not skip_File:
        try:
            file = open(file_dir, "r")
            local_count = 0
            for line in file:
                if line != "\n":
                    local_count += 1
            print("({:.1f}%)".format(100*i/len_files), file_dir, "|", local_count)
            line_count += local_count
            file.close()
        except:
            file_err_list.append(file_dir)
            continue
print("=====================================")
print("File Count Errors:", len(file_err_list))
if not skip_file_error_list:
    for file in file_err_list:
        print(file_err_list)

print("=====================================")
print("Total lines |", line_count)

可能有更快、更有效的方法来做到这一点,但这是一个不错的开始。

可变信息

directory是你要统计的项目目录

directory_depth 是项目基础结构中的深度 即深度为 3 意味着它只会扫描以下深度:

  • project_dir
    • sub_dir
      • sub2_dir

extensions_to_consider是文件扩展名计数代码。如果你只想计算.py文件,你设置extensions_to_consider = [".py"]

exclude_filenames 是一个文件名(和目录)数组,您不希望脚本为其计算代码。

skip_file_error_list 是一个布尔变量。如果您希望在计数时看到所有错误的打印输出,请设置为 True。否则设置为 False。

如何运行

运行 脚本使用 Python 编译器。 在终端运行

python path_to_file.py

python3 path_to_file.py

这是另一个,使用 pathlib。列出单个(相对)文件路径以及行数、文件总数和总行数。

import pathlib


class LoC(object):
    suffixes = ['.py']

    def count(self, path: pathlib.Path, init=True):
        if init:
            self.root = path
            self.files = 0
            self.lines = 0
        if path.is_dir():
            # recursive case
            for item in path.iterdir():
                self.count(path=item, init=False)
        elif path.is_file() and path.suffix in self.suffixes:
            # base case
            with path.open(mode='r') as f:
                line_count = len(f.readlines())
            print(f'{path.relative_to(self.root)}: {line_count}')
            self.files += 1
            self.lines += line_count
        if init:
            print(f'\n{self.lines} lines in {self.files} files')

请注意,为了清楚起见,我跳过了 __init__ 方法。

用法示例:

loc = LoC()
loc.count(path=pathlib.Path('/path/to/your/project/directory'))