vse_toolbox/file_utils.py

import importlib
import re
import subprocess
import platform
import sys
import unicodedata
from pathlib import Path
from os.path import expandvars
import json
import glob


def install_module(module_name, package_name=None):
    '''Install a python module with pip or return it if already installed'''
    try:
        module = importlib.import_module(module_name)
    except ModuleNotFoundError:
        print(f'Installing Module {module_name} ....')

        subprocess.call([sys.executable, '-m', 'ensurepip', '--upgrade'])
        subprocess.call([sys.executable, '-m', 'pip', 'install', package_name or module_name])
        
        module = importlib.import_module(module_name)
    
    return module

def import_module_from_path(path):
    from importlib import util

    try:
        path = Path(path)
        spec = util.spec_from_file_location(path.stem, str(path))
        mod = util.module_from_spec(spec)
        
        spec.loader.exec_module(mod)

        return mod

    except Exception as e:
        print(f'Cannot import file {path}')
        print(e)

def fuzzy_match(s1, s2, case_sensitive=False):
    '''Tell how much two passed strings are similar 1.0 being exactly similar'''
    from difflib import SequenceMatcher
    if case_sensitive:
        similarity = SequenceMatcher(None, s1, s2)
    else:
        similarity = SequenceMatcher(None, s1.lower(), s2.lower())
    return similarity.ratio()

def norm_str(string, separator='_', format=str.lower, padding=0):    
    string = str(string)
    string = string.replace('_', ' ')
    string = string.replace('-', ' ')
    string = re.sub('[ ]+', ' ', string)
    string = re.sub('[ ]+\/[ ]+', '/', string)
    string = string.strip()

    if format:
        string = format(string)
    
    # Padd rightest number
    string = re.sub(r'(\d+)(?!.*\d)', lambda x : x.group(1).zfill(padding), string)
    
    string = string.replace(' ', separator)
    string = unicodedata.normalize('NFKD', string).encode('ASCII', 'ignore').decode("utf-8")

    return string

def norm_name(string, separator='_', format=str.lower, padding=0):    
    string = str(string)
    string = string.split('/')[-1]  #used to remove first slash -> albert / albert_casque -> albert_casque
    string = string.replace('_', ' ')
    string = string.replace('-', ' ')
    string = re.sub('[ ]+', ' ', string)
    string = re.sub('[ ]+\/[ ]+', '/', string)
    string = string.strip()

    if format:
        string = format(string)
    
    # Padd rightest number
    string = re.sub(r'(\d+)(?!.*\d)', lambda x : x.group(1).zfill(padding), string)
    
    string = string.replace(' ', separator)
    string = unicodedata.normalize('NFKD', string).encode('ASCII', 'ignore').decode("utf-8")

    return string

def read_file(path):
    '''Read a file with an extension in (json, yaml, yml, txt, log)'''

    exts = ('.json', '.yaml', '.yml', '.txt', '.log')

    if not path:
        print('Try to read empty file')
    
    path = Path(path)
    if not path.exists():
        print('File not exist', path)
        return
    
    if path.suffix not in exts:
        print(f'Cannot read file {path}, extension must be in {exts}')
        return

    txt = path.read_text()
    data = None

    if path.suffix.lower() in ('.yaml', '.yml'):
        yaml = install_module('yaml')
        try:
            data = yaml.safe_load(txt)
        except Exception as e:
            print(e)
            print(f'Could not load yaml file {path}')
            return
    elif path.suffix.lower() == '.json':
        try:
            data = json.loads(txt)
        except Exception as e:
            print(e)
            print(f'Could not load json file {path}')
            return
    else:
        data = txt

    return data

def open_file(filepath, env=None, select=False):
    if platform.system() == 'Darwin':       # macOS
        cmd = ['open']
        if select:
            cmd += ['-R']

    elif platform.system() == 'Windows':    # Windows
        cmd = ['explorer']
        if select:
            cmd += ['/select,']
    else:                                   # linux variants
        cmd = ['xdg-open']
        if select:
            cmd = ['nemo']
    
    cmd += [str(filepath)]

    subprocess.Popen(cmd, env=env)

# def parse(string, template):
#     template = re.sub(r'{index:(.+?)}', r'(?P<index>.+)', template)
#     reg = re.sub(r'{(.+?)}', r'(?P<_\1>.+)', template)

#     values = list(re.search(reg, string).groups())
#     keys = re.findall(r'{(.+?)}', template) + ['index']

#     return dict(zip(keys, values))

def parse(template, string):
    reg = re.sub(r'{[^}]*}|\.', lambda m: m.group() if m.group().startswith('{') else r'\.', template)
    reg = re.sub(r'{(.+?)}', r'(?P<\1>.*)', reg)

    #print(string, template, reg)
    if result := re.match(reg, string):
        return result.groupdict()

def expand(template, **kargs):
    template = Path(template).as_posix()
    template = expandvars(template)

    for key, value in kargs.items():
        template = re.sub(r'\{%s\}'%key, value, template)
    
    return template

def find_last(template, **kargs):

    pattern = expand(template, **kargs)

    pattern = re.sub(r'{\w+:(\d{2})d}', lambda x : '?' * int(x.groups()[0]), pattern)
    pattern = re.sub(r'{.*?}', '*', pattern)
    
    filepaths = glob.glob(pattern)
    if filepaths:
        return Path(max(filepaths))
    else:
        print(f'No preview found for template {pattern}')