Python实现多语言代码行数统计工具：从单文件到多语言支持

# type用于指定文件类型
python counter.py --type python

# -*- coding: utf-8 -*-
"""
只能统计单行注释的py文件
"""
def parse(path):
 comments = 0
 blanks = 0
 codes = 0
 with open(path, encoding='utf-8') as f:
 for line in f.readlines():
  line = line.strip()
  if line == "":
  blanks += 1
  elif line.startswith("#"):
  comments += 1
  else:
  codes += 1
 return {"comments": comments, "blanks": blanks, "codes": codes}
if __name__ == '__main__':
 print(parse("xxx.py"))

# -*- coding: utf-8 -*-
"""

"""
def parse(path):
 in_multi_comment = False # 多行注释符标识符号
 comments = 0
 blanks = 0
 codes = 0
 with open(path, encoding="utf-8") as f:
 for line in f.readlines():
  line = line.strip()
  # 多行注释中的空行当做注释处理
  if line == "" and not in_multi_comment:
  blanks += 1
  # 注释有4种
  # 1. # 井号开头的单行注释
  # 2. 多行注释符在同一行的情况
  # 3. 多行注释符之间的行
  elif line.startswith("#") or \
    (line.startswith('"""') and line.endswith('"""') and len(line)) > 3 or \
   (line.startswith("'''") and line.endswith("'''") and len(line) > 3) or \
   (in_multi_comment and not (line.startswith('"""') or line.startswith("'''"))):
  comments += 1
  # 4. 多行注释符的开始行和结束行
  elif line.startswith('"""') or line.startswith("'''"):
  in_multi_comment = not in_multi_comment
  comments += 1
  else:
  codes += 1
 return {"comments": comments, "blanks": blanks, "codes": codes}
if __name__ == '__main__':
 print(parse("xxx.py"))

CONF = {"py": {"start_comment": ['"""', "'''"], "end_comment": ['"""', "'''"], "single": "#"},
 "java": {"start_comment": ["/*"], "end_comment": ["*/"], "single": "//"}}
start_comment = CONF.get(exstansion).get("start_comment")
end_comment = CONF.get(exstansion).get("end_comment")
cond2 = False
cond3 = False
cond4 = False
for index, item in enumerate(start_comment):
 cond2 = line.startswith(item) and line.endswith(end_comment[index]) and len(line) > len(item)
 if cond2:
 break
for item in end_comment:
 if line.startswith(item):
 cond3 = True
 break
for item in start_comment+end_comment:
 if line.startswith(item):
 cond4 = True
 break
if line == "" and not in_multi_comment:
 blanks += 1
# 注释有4种
# 1. # 井号开头的单行注释
# 2. 多行注释符在同一行的情况
# 3. 多行注释符之间的行
elif line.startswith(CONF.get(exstansion).get("single")) or cond2 or \
 (in_multi_comment and not cond3):
 comments += 1
# 4. 多行注释符分布在多行时，开始行和结束行
elif cond4:
 in_multi_comment = not in_multi_comment
 comments += 1
else:
 codes += 1

def counter(path):
 """
 可以统计目录或者某个文件
 :param path:
 :return:
 """
 if os.path.isdir(path):
 comments, blanks, codes = 0, 0, 0
 list_dirs = os.walk(path)
 for root, dirs, files in list_dirs:
  for f in files:
  file_path = os.path.join(root, f)
  stats = parse(file_path)
  comments += stats.get("comments")
  blanks += stats.get("blanks")
  codes += stats.get("codes")
 return {"comments": comments, "blanks": blanks, "codes": codes}
 else:
 return parse(path)

# coding=utf-8
import os
import time
basedir = '/root/script'
filelists = []
# 指定想要统计的文件类型
whitelist = ['php', 'py']
#遍历文件, 递归遍历文件夹中的所有
def getFile(basedir):
 global filelists
 for parent,dirnames,filenames in os.walk(basedir):
  #for dirname in dirnames:
  # getFile(os.path.join(parent,dirname)) #递归
  for filename in filenames:
   ext = filename.split('.')[-1]
   #只统计指定的文件类型，略过一些log和cache文件
   if ext in whitelist:
    filelists.append(os.path.join(parent,filename))
#统计一个文件的行数
def countLine(fname):
 count = 0
 for file_line in open(fname).xreadlines():
  if file_line != '' and file_line != '\n': #过滤掉空行
   count += 1
 print fname + '----' , count
 return count
if __name__ == '__main__' :
 startTime = time.clock()
 getFile(basedir)
 totalline = 0
 for filelist in filelists:
  totalline = totalline + countLine(filelist)
 print 'total lines:',totalline
 print 'Done! Cost Time: %0.2f second' % (time.clock() - startTime)