rana-cli/wakatime/stats.py

183 lines
4.4 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
"""
wakatime.stats
~~~~~~~~~~~~~~
2013-09-22 20:41:13 +00:00
Stats about files
:copyright: (c) 2013 Alan Hamlett.
:license: BSD, see LICENSE for more details.
"""
import logging
import os
import sys
from .compat import u, open
2014-12-23 05:12:57 +00:00
from .languages import DependencyParser
if sys.version_info[0] == 2:
2014-12-01 06:10:30 +00:00
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), 'packages', 'pygments_py2'))
else:
2014-12-01 06:10:30 +00:00
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), 'packages', 'pygments_py3'))
from pygments.lexers import get_lexer_by_name, guess_lexer_for_filename
from pygments.modeline import get_filetype_from_buffer
2015-06-16 01:55:47 +00:00
from pygments.util import ClassNotFound
log = logging.getLogger('WakaTime')
def guess_language(file_name):
"""Guess lexer and language for a file.
Returns (language, lexer) tuple where language is a unicode string.
"""
language = get_language_from_extension(file_name)
if language:
return language, None
lexer = smart_guess_lexer(file_name)
language = u(lexer.name)
2014-12-23 05:12:57 +00:00
return language, lexer
def smart_guess_lexer(file_name):
"""Guess Pygments lexer for a file.
Looks for a vim modeline in file contents, then compares the accuracy
of that lexer with a second guess. The second guess looks up all lexers
matching the file name, then runs a text analysis for the best choice.
"""
lexer = None
text = get_file_contents(file_name)
lexer1, accuracy1 = guess_lexer_using_filename(file_name, text)
lexer2, accuracy2 = guess_lexer_using_modeline(text)
if lexer1:
lexer = lexer1
if (lexer2 and accuracy2 and
(not accuracy1 or accuracy2 > accuracy1)):
lexer = lexer2
return lexer
2015-06-16 01:55:47 +00:00
def guess_lexer_using_filename(file_name, text):
"""Guess lexer for given text, limited to lexers for this file's extension.
Returns a tuple of (lexer, accuracy).
"""
2015-06-16 01:55:47 +00:00
lexer, accuracy = None, None
2015-06-16 01:55:47 +00:00
try:
lexer = guess_lexer_for_filename(file_name, text)
except:
pass
2015-06-16 01:55:47 +00:00
if lexer is not None:
try:
accuracy = lexer.analyse_text(text)
except:
pass
return lexer, accuracy
def guess_lexer_using_modeline(text):
"""Guess lexer for given text using Vim modeline.
2015-06-16 01:55:47 +00:00
Returns a tuple of (lexer, accuracy).
"""
2015-06-16 01:55:47 +00:00
lexer, accuracy = None, None
file_type = None
try:
file_type = get_filetype_from_buffer(text)
except:
pass
if file_type is not None:
try:
2015-06-16 01:55:47 +00:00
lexer = get_lexer_by_name(file_type)
except ClassNotFound:
pass
if lexer is not None:
try:
accuracy = lexer.analyse_text(text)
except:
pass
2015-06-16 01:55:47 +00:00
return lexer, accuracy
def get_language_from_extension(file_name):
"""Returns a matching language for the given file extension.
2015-06-16 01:55:47 +00:00
"""
extension = file_name.rsplit('.', 1)[-1] if len(file_name.rsplit('.', 1)) > 1 else ''
file_minus_extension = file_name.rsplit('.', 1)[0] if len(file_name.rsplit('.', 1)) > 1 else file_name
2015-06-16 01:55:47 +00:00
if extension.lower() == 'h':
if os.path.isfile(file_minus_extension + '.cpp'):
return 'C++'
if os.path.isfile(file_minus_extension + '.c'):
return 'C'
2015-06-16 01:55:47 +00:00
return None
def number_lines_in_file(file_name):
lines = 0
try:
with open(file_name, 'r', encoding='utf-8') as fh:
for line in fh:
lines += 1
except:
return None
return lines
def get_file_stats(file_name, notfile=False, lineno=None, cursorpos=None):
if notfile:
stats = {
'language': None,
'dependencies': [],
'lines': None,
'lineno': lineno,
'cursorpos': cursorpos,
}
else:
language, lexer = guess_language(file_name)
parser = DependencyParser(file_name, lexer)
dependencies = parser.parse()
stats = {
'language': language,
'dependencies': dependencies,
'lines': number_lines_in_file(file_name),
'lineno': lineno,
'cursorpos': cursorpos,
}
return stats
def get_file_contents(file_name):
"""Returns the first 512000 bytes of the file's contents.
"""
text = None
try:
with open(file_name, 'r', encoding='utf-8') as fh:
text = fh.read(512000)
except:
pass
return text