def get_paths_html(folder):
paths_html = []
folder_raw = os.path.join(folder,'raw')
if not os.path.isdir(folder_raw):
status.important(NAME,(
'Folder `{}` must contain a `raw/` subfolder'.format(folder)
))
status.stop(NAME)
for path_folder, subfolders, files in os.walk(folder_raw):
for subfolder in subfolders:
if subfolder == '__MACOSX':
path_MACOSX = os.path.join(path_folder, subfolder)
status.important(NAME,(
"Removing `{}`\n - Not needed (this is no big deal)"
).format(path_MACOSX))
shutil.rmtree(path_MACOSX)
for path_folder, subfolders, files in os.walk(folder_raw):
for f in files:
if f.endswith('.html'):
path_html = os.path.join(path_folder,f)
paths_html.append(path_html)
if not paths_html:
status.important(NAME,(
'No .html files located inside `{}`'.format(folder)
))
status.stop(NAME)
return paths_html
def get_paths_html(folder):
paths_html = []
folder_raw = os.path.join(folder, 'raw')
if not os.path.isdir(folder_raw):
status.important(
NAME,
('Folder `{}` must contain a `raw/` subfolder'.format(folder)))
status.stop(NAME)
for path_folder, subfolders, files in os.walk(folder_raw):
for subfolder in subfolders:
if subfolder == '__MACOSX':
path_MACOSX = os.path.join(path_folder, subfolder)
status.important(
NAME, ("Removing `{}`\n - Not needed (this is no big deal)"
).format(path_MACOSX))
shutil.rmtree(path_MACOSX)
for path_folder, subfolders, files in os.walk(folder_raw):
for f in files:
if f.endswith('.html'):
path_html = os.path.join(path_folder, f)
paths_html.append(path_html)
if not paths_html:
status.important(NAME,
('No .html files located inside `{}`'.format(folder)))
status.stop(NAME)
return paths_html
def get_args():
_args = sys.argv[1:]
if not _args:
print (
"[{NAME}]\n\n"
"Usage:\n"
"python {NAME}.py folder\n"
"python {NAME}.py path/to/folder\n"
"python {NAME}.py folder1 folder2 ... folderN\n"
).format(NAME=NAME)
status.stop(NAME)
elif not all(os.path.isdir(_arg) for _arg in _args):
dirs_available = [i for i in os.listdir(os.getcwd())
if (os.path.isdir(i) and
not i.startswith('.') and
not i.startswith('_'))]
status.important(NAME,(
'Arguments must be directories from the repo root.\n\n'
'The available directories are:\n'
' {}'.format('\n '.join(dirs_available))
))
status.stop(NAME)
else:
args = [os.path.dirname(_arg+'/') for _arg in _args]
return args
def get_args():
_args = sys.argv[1:]
if not _args:
print (
"[{NAME}]\n\n"
"Usage:\n"
"python {NAME}.py path/to/file\n"
"python {NAME}.py path/to/file1 path/to/file2 "
"... path/to/fileN\n"
).format(NAME=NAME)
status.stop(NAME)
return _args
def check_translate(folder, paths_html, translate_filename_url):
files_html_translate = translate_filename_url.keys()
files_html = [os.path.split(path_html)[1] for path_html in paths_html]
# Case 0: if .json and raw/ align, return paths_html
if set(files_html_translate) == set(files_html):
return paths_html
# Case 1: if .json < raw/, return part of paths_html contained in .json
elif len(files_html_translate) < len(files_html):
diff = list(set(files_html) - set(files_html_translate))
to_be = 'was' if len(diff) == 1 else 'were'
to_have = 'has' if len(diff) == 1 else 'have'
status.important(NAME,
("File(s): \n\n {diff}\n\n"
"{to_be} found from `{folder}/raw/` but {to_have} "
"no correspondence\n"
"in `{folder}/translate_filename_url.json`.\n\n"
"Note that files not listed in "
"`{folder}/translate_filename_url.json`\n"
"will NOT be published").format(diff='\n'.join(diff),
folder=folder,
to_be=to_be,
to_have=to_have))
return [
path_html for path_html in paths_html
if (os.path.split(path_html)[1] in files_html_translate)
]
# Case 2: if .json > raw/, stop execution
else:
diff = list(set(files_html_translate) - set(files_html))
to_be = 'is' if len(diff) == 1 else 'are'
to_have = 'has' if len(diff) == 1 else 'have'
status.important(
NAME,
("File(s): \n\n {diff}\n\n"
"{to_be} listed in "
"`{folder}/translate_filename_url.json` but {to_have} "
"no correspondence\n"
"in `{folder}/raw/`.\n\n"
"Note that files not found in "
"`{folder}/raw` CANNOT be published").format(diff='\n'.join(diff),
folder=folder,
to_be=to_be,
to_have=to_have))
status.stop(NAME)
return
def get_translate_filename_url(folder):
file_path = os.path.join(folder, 'translate_filename_url.json')
with open(file_path) as f:
translate = json.load(f)
translate_filename_url = dict()
translate_redirects = dict()
for k, v in translate.items():
if isinstance(v, list) and isinstance(v[-1], (str, unicode)):
translate_filename_url[k] = v[-1]
translate_redirects[v[-1]] = v[0:-1]
elif isinstance(v, (str, unicode)):
translate_filename_url[k] = v
else:
status.important(NAME, (
"object values in {}/translate_filename_url.json\n"
"must be either a string (the urls)\n"
"or a list of strings (to handle redirects)"
).format(folder))
status.stop(NAME)
return translate_filename_url, translate_redirects
def get_translate_filename_url(folder):
file_path = os.path.join(folder, 'translate_filename_url.json')
with open(file_path) as f:
translate = json.load(f, object_pairs_hook=OrderedDict)
translate_filename_url = OrderedDict()
translate_redirects = OrderedDict()
for k, v in translate.items():
if isinstance(v, list) and isinstance(v[-1], (str, unicode)):
translate_filename_url[k] = v[-1]
translate_redirects[v[-1]] = v[0:-1]
elif isinstance(v, (str, unicode)):
translate_filename_url[k] = v
else:
status.important(NAME, (
"object values in {}/translate_filename_url.json\n"
"must be either a string (the urls)\n"
"or a list of strings (to handle redirects)"
).format(folder))
status.stop(NAME)
return translate_filename_url, translate_redirects
def check_translate(folder, paths_html, translate_filename_url):
files_html_translate = translate_filename_url.keys()
files_html = [os.path.split(path_html)[1] for path_html in paths_html]
# Case 0: if .json and raw/ align, return paths_html
if set(files_html_translate) == set(files_html):
return paths_html
# Case 1: if .json < raw/, return part of paths_html contained in .json
elif len(files_html_translate) < len(files_html):
diff = list(set(files_html) - set(files_html_translate))
to_be = 'was' if len(diff)==1 else 'were'
to_have = 'has' if len(diff)==1 else 'have'
status.important(NAME,(
"File(s): \n\n {diff}\n\n"
"{to_be} found from `{folder}/raw/` but {to_have} "
"no correspondence\n"
"in `{folder}/translate_filename_url.json`.\n\n"
"Note that files not listed in "
"`{folder}/translate_filename_url.json`\n"
"will NOT be published"
).format(diff='\n'.join(diff),folder=folder,
to_be=to_be,to_have=to_have))
return [path_html
for path_html in paths_html
if (os.path.split(path_html)[1] in files_html_translate)]
# Case 2: if .json > raw/, stop execution
else:
diff = list(set(files_html_translate) - set(files_html))
to_be = 'is' if len(diff)==1 else 'are'
to_have = 'has' if len(diff)==1 else 'have'
status.important(NAME,(
"File(s): \n\n {diff}\n\n"
"{to_be} listed in "
"`{folder}/translate_filename_url.json` but {to_have} "
"no correspondence\n"
"in `{folder}/raw/`.\n\n"
"Note that files not found in "
"`{folder}/raw` CANNOT be published"
).format(diff='\n'.join(diff),folder=folder,
to_be=to_be,to_have=to_have))
status.stop(NAME)
return
def get_args():
_args = sys.argv[1:]
if not _args:
print(
"[{NAME}]\n\n"
"Usage:\n"
"python {NAME}.py folder\n"
"python {NAME}.py path/to/folder\n"
"python {NAME}.py folder1 folder2 ... folderN\n").format(NAME=NAME)
status.stop(NAME)
elif not all(os.path.isdir(_arg) for _arg in _args):
dirs_available = [
i for i in os.listdir(os.getcwd())
if (os.path.isdir(i) and not i.startswith('.')
and not i.startswith('_'))
]
status.important(
NAME, ('Arguments must be directories from the repo root.\n\n'
'The available directories are:\n'
' {}'.format('\n '.join(dirs_available))))
status.stop(NAME)
else:
args = [os.path.dirname(_arg + '/') for _arg in _args]
return args
