vim-rana/plugin/packages/wakatime/stats.py

228 lines
5.4 KiB
Python
Raw Normal View History

2013-09-22 23:22:11 +00:00
# -*- coding: utf-8 -*-
"""
wakatime.stats
~~~~~~~~~~~~~~
Stats about files
:copyright: (c) 2013 Alan Hamlett.
:license: BSD, see LICENSE for more details.
"""
import logging
import os
import sys
2014-09-30 16:23:17 +00:00
from .compat import u, open
2014-12-23 11:22:49 +00:00
from .languages import DependencyParser
2014-09-30 16:23:17 +00:00
2013-09-22 23:22:11 +00:00
if sys.version_info[0] == 2:
2014-12-01 06:19:45 +00:00
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), 'packages', 'pygments_py2'))
2013-09-22 23:22:11 +00:00
else:
2014-12-01 06:19:45 +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 01:56:44 +00:00
from pygments.util import ClassNotFound
2013-09-22 23:22:11 +00:00
2014-07-25 09:45:35 +00:00
log = logging.getLogger('WakaTime')
2013-09-22 23:22:11 +00:00
# extensions taking priority over lexer
2013-10-26 04:32:30 +00:00
EXTENSIONS = {
'j2': 'HTML',
2013-11-03 19:35:59 +00:00
'markdown': 'Markdown',
'md': 'Markdown',
'mdown': 'Markdown',
'twig': 'Twig',
2013-10-26 04:32:30 +00:00
}
# lexers to human readable languages
2013-10-27 00:55:10 +00:00
TRANSLATIONS = {
'CSS+Genshi Text': 'CSS',
2013-10-27 00:59:02 +00:00
'CSS+Lasso': 'CSS',
'HTML+Django/Jinja': 'HTML',
'HTML+Lasso': 'HTML',
'JavaScript+Genshi Text': 'JavaScript',
'JavaScript+Lasso': 'JavaScript',
2013-10-27 00:55:10 +00:00
'Perl6': 'Perl',
'RHTML': 'HTML',
2013-10-27 00:55:10 +00:00
}
2013-10-26 04:32:30 +00:00
# extensions for when no lexer is found
AUXILIARY_EXTENSIONS = {
'vb': 'VB.net',
}
2013-10-26 04:32:30 +00:00
2013-09-22 23:22:11 +00:00
def guess_language(file_name):
"""Guess lexer and language for a file.
Returns (language, lexer) tuple where language is a unicode string.
"""
lexer = smart_guess_lexer(file_name)
language = None
# guess language from file extension
2014-12-23 11:22:49 +00:00
if file_name:
language = get_language_from_extension(file_name, EXTENSIONS)
# get language from lexer if we didn't have a hard-coded extension rule
if language is None and lexer:
language = u(lexer.name)
if language is None:
language = get_language_from_extension(file_name, AUXILIARY_EXTENSIONS)
if language is not None:
language = translate_language(language)
2014-12-23 11:22:49 +00:00
return language, lexer
2013-09-22 23:22:11 +00:00
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)
2015-06-16 01:56:44 +00:00
lexer_1, accuracy_1 = guess_lexer_using_filename(file_name, text)
lexer_2, accuracy_2 = guess_lexer_using_modeline(text)
2015-06-16 01:56:44 +00:00
if lexer_1:
lexer = lexer_1
if (lexer_2 and accuracy_2 and
(not accuracy_1 or accuracy_2 > accuracy_1)):
2015-06-16 01:56:44 +00:00
lexer = lexer_2
return lexer
2015-06-16 01:56:44 +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 01:56:44 +00:00
lexer, accuracy = None, None
2015-06-16 01:56:44 +00:00
try:
lexer = guess_lexer_for_filename(file_name, text)
except:
pass
2015-06-16 01:56:44 +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 01:56:44 +00:00
Returns a tuple of (lexer, accuracy).
"""
2015-06-16 01:56:44 +00:00
lexer, accuracy = None, None
2015-07-03 21:25:22 +00:00
file_type = None
try:
file_type = get_filetype_from_buffer(text)
except:
pass
if file_type is not None:
try:
2015-06-16 01:56:44 +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 01:56:44 +00:00
return lexer, accuracy
def get_language_from_extension(file_name, extension_map):
"""Returns a matching language for the given file_name using extension_map.
"""
extension = file_name.rsplit('.', 1)[-1] if len(file_name.rsplit('.', 1)) > 1 else None
if extension:
if extension in extension_map:
return extension_map[extension]
if extension.lower() in extension_map:
return extension_map[extension.lower()]
2013-10-26 04:32:30 +00:00
return None
2013-10-27 00:55:10 +00:00
def translate_language(language):
"""Turns Pygments lexer class name string into human-readable language.
"""
2013-10-27 00:55:10 +00:00
if language in TRANSLATIONS:
language = TRANSLATIONS[language]
return language
2013-09-22 23:22:11 +00:00
def number_lines_in_file(file_name):
lines = 0
try:
2014-09-30 16:23:17 +00:00
with open(file_name, 'r', encoding='utf-8') as fh:
for line in fh:
2013-09-22 23:22:11 +00:00
lines += 1
except:
2013-09-22 23:22:11 +00:00
return None
return lines
2015-05-12 22:02:09 +00:00
def get_file_stats(file_name, notfile=False, lineno=None, cursorpos=None):
if notfile:
stats = {
'language': None,
'dependencies': [],
'lines': None,
2015-05-12 22:02:09 +00:00
'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),
2015-05-12 22:02:09 +00:00
'lineno': lineno,
'cursorpos': cursorpos,
}
2013-09-22 23:22:11 +00:00
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