Python script to retrieve sample codes from Rosetta project

get_samples_rosetta.py

#!/usr/bin/env python
import os
import yaml
import shutil
import re
import glob
import sys
from subprocess import call

# Extensions to replace: format: Language_name_in_Rosetta: [to_replace, new_extension].
extension_replacements = {'OCaml': ['.ocaml', '.ml'], 'Oxygene': ['.oxy', '.oxygene'], 'Perl': ['.pl', '.perl'], 'Verilog': ['.v', '.veo'], 'Forth': ['.fth', '.forth'], 'Clean': ['.clean', '.icl'], 'CLIPS': ['.clips', '.clp'], 'Frege': ['.frege', '.fr'], 'J': ['.j', '.ijs'], 'Ioke': ['.ioke', '.ik'], 'Julia': ['.julia', '.jl'], 'BlitzMax': ['.blitz', '.bmx'], 'PureBasic': ['.purebasic', '.pb'], 'Component-Pascal': ['.component', '.cp'], 'Fancy': ['.fancy', '.fy'], 'Chapel': ['.chapel', '.chpl'], 'SuperCollider': ['.supercollider', '.scd'], 'Gosu': ['.gosu', '.gs'], 'E': ['.e', '.E'], 'NSIS': ['.nsis', '.nsi'], 'Scilab': ['.scilab', '.sci'], 'Mathematica': ['.math', '.m'], 'Befunge': ['.bf', '.befunge'], 'Rust': ['.rust', '.rs'], 'Kotlin': ['.kotlin', '.kt'], 'Haxe': ['.haxe', '.hx'], 'NetLogo': ['.netlogo', '.nlogo'], 'Nemerle': ['.nemerle', '.n'], 'Elixir': ['.elixir', '.ex'], 'ANTLR': ['.antlr', '.g4'], 'Turing': ['.turing', '.tu'], 'SystemVerilog': ['.v', '.sv'], 'LabVIEW': ['.labview', '.lvproj'], 'Mercury': ['.mercury', '.moo'], 'LLVM': ['.llvm', '.ll'], 'Fantom': ['.fantom', '.fan'], 'REALbasic': ['.realbasic', '.rbbas'], 'AutoIt': ['.autoit', '.au3']}

# Associations of names between Rosetta Code and Linguist.
associations = {'Component-Pascal': 'Component Pascal', 'Brainf---': 'Brainfuck', 'GML': 'Game Maker Language'}

languages_yml = open('linguist/lib/linguist/languages.yml', 'r')
linguist_languages = list(yaml.load(languages_yml).keys())

for example_dir in os.listdir('RosettaCodeData/Task/'):
	print example_dir
	for rosetta_language in os.listdir(os.path.join('RosettaCodeData/Task/', example_dir)):
		if not rosetta_language in associations:
			# Tries to match the language name in Rosetta with a language in Linguist:
			for linguist_language in linguist_languages:
				if linguist_language.lower() == rosetta_language.lower() or linguist_language.lower() == rosetta_language.replace('-', ' ').lower():
					if not linguist_language in associations.values():
						associations[linguist_language] = rosetta_language

		if rosetta_language in associations:
			src = 'RosettaCodeData/Task/' + example_dir + '/' + rosetta_language + '/'
			dest = 'linguist/samples/' + associations[rosetta_language] + '/'
			if not os.path.isdir(dest):
				# Creates the samples/[Language] if it doesn't already exists.
				os.mkdir(dest)
			for filepath in glob.glob(src + '*.*'):
				if os.path.isfile(filepath):
					filename = os.path.basename(filepath)
					# Replaces extensions for certain languages:
					if rosetta_language in extension_replacements:
						filename = filename.replace(extension_replacements[rosetta_language][0], extension_replacements[rosetta_language][1])

					# Checks that we won't overwrite a file.
					if os.path.isfile(dest + filename):
						print("File %s already exists." % (filename))
					elif not re.search(r"-\d+\.\w+$", filename):
						shutil.copy(filepath, dest + filename)