def check_input_dir(directory: str):
"""
Check the bootcamp directory file organization
Args:
directory (str): bootcamp day directory
"""
# check directory is in the format dayXX
while directory[-1] == '/':
directory = directory[:-1]
dir = directory.split('/')[-1]
regex = re.compile(r'^day[0-9]{2}$')
if not regex.search(dir):
error("'{}' invalid day directory (dayXX allowed)".format(directory))
# check if it is a directory
if not os.path.isdir(directory):
error("'{}' is not a directory !".format(directory))
# check directory has a dayXX.md
ls_day = sub_run("ls {}/day*.md".format(directory))
if ls_day.stderr:
error("markdown for day missing")
# check directory has exXX.md files
ls_ex = sub_run("ls {}/ex*/ex*.md".format(directory))
if ls_ex.stderr:
error("markdown for exercices missing")
def main():
args = get_arguments()
# CHECK PARAMETERS AND FILES
###############################
try:
params_check.check_bootcamp_title(args.bootcamp_title)
params_check.check_day_title(args.day_title)
if args.input_dir: # check and copy the day directory
params_check.check_input_dir(args.input_dir)
files_formatting.day_files_cpy(args.input_dir, args.template_file)
else: # check and copy the documentation file
params_check.check_input_file(args.input_file)
files_formatting.input_file_cpy(args.input_file,
args.template_file)
except Exception as e:
print(e)
sys.exit(-1)
# FILES FORMATTING
#####################
try:
files_formatting.insert_bootcamp_title(args)
files_formatting.insert_day_title(args)
files = sub_run("ls tmp/*.md").stdout.strip()
for f in files.decode().split('\n'):
content = None
files_formatting.files_format(f)
with open(f, 'r') as infile:
content = infile.read()
content = files_formatting.change_img_format(f, content)
content = files_formatting.change_header_format(f, content)
content = files_formatting.change_list_format(f, content)
content = files_formatting.change_empty_code_block_style(
f, content)
content = files_formatting.change_equations_format(f, content)
content = files_formatting.set_url_color(f, content)
with open(f + ".tmp", 'w') as outfile:
outfile.write(content)
sub_run("mv {0}.tmp {0}".format(f))
if args.debug:
files_formatting.run_pandoc(f)
# GENERATING PDF OUTPUT
files_formatting.run_pandoc_all(
args.output_file.split('/')[-1], args.debug)
print("Successfully built pdf !")
except Exception as e:
print(e)
sys.exit(-1)
def run_pandoc_all(outfile, debug):
"""
Build a pdf with all markdown files.
Args:
outfile (undefined): output file name
debug (undefined): debug option
"""
res = sub_run("pandoc tmp/*.md --to=pdf --pdf-engine=pdflatex --highlight-style=breezedark\
-t latex -o {} --template=tmp/template.latex".format(outfile))
if res.stderr:
error(res.stderr.decode().strip())
if not debug:
sub_run("rm -rf tmp")
def main():
repos = {
"bootcamp_python": "master",
"bootcamp_machine-learning": "master",
"bootcamp_data-engineering": "master"
}
for _dir, _branch in repos.items():
clone_branch(_dir, _branch)
for _dir in repos:
days = {}
res = sub_run("ls -d {}/day*/".format(_dir)).stdout.decode().strip()
for d in res.split('\n'):
days[d.split('/')[1]] = d
for k, v in days.items():
dd = "{}.{}.pdf".format(_dir, k)
res = sub_run("python3 pdf_builder -b \"{}\" -d {} -t \
\"Day00 - ddd\" -o {}".format(_dir.replace('_', ' ')
.replace('-', ' '),
v, dd))
pattern = re.compile(r'(Successfully.*?!)')
if pattern.findall(res.stderr.decode().strip()):
print("{}SUCCESS{} !".format(OKGREEN, ENDC))
else:
print("{}ERROR{} !".format(FAIL, ENDC))
print(res.stdout.decode().strip())
res = sub_run("python3 pdf_builder -b \"Data Engineering\" \
-f bootcamp_data-engineering/day00/ex03/psycopg2_basics.md \
-t \"Day00 - ddd\" -o \
bootcamp_data-engineering.psycopg2_doc.pdf")
pattern = re.compile(r'(Successfully.*?!)')
if pattern.findall(res.stderr.decode().strip()):
print("{}SUCCESS{} !".format(OKGREEN, ENDC))
else:
print("{}ERROR{} !".format(FAIL, ENDC))
print(res.stderr.decode())
pattern = re.compile(r'Detected !.*?$', re.DOTALL)
print("\n".join(pattern.findall(res.stderr.decode()
.strip())[0].split('\n')[1:]))
def run_pandoc(file_name):
"""
Build pdf file for each markdown.
Args:
file_name (undefined):
"""
res = sub_run("pandoc {} --to=pdf --pdf-engine=pdflatex --highlight-style=breezedark\
-t latex -o {} --template=tmp/template.latex"
.format(file_name, file_name + ".pdf"))
if res.stderr:
print(file_name)
error(res.stderr.decode().strip(), file_name)
def files_format(file_name):
"""
Add clearpages at the end of exercises.
Args:
file_name (undefined): file name
"""
def in_docker():
with open('/proc/self/cgroup', 'r') as procfile:
for line in procfile:
fields = line.strip().split('/')
if 'docker' in fields:
return True
return False
if in_docker():
sub_run(
"echo '\n\\clearpage' >> tmp/{}"
.format(file_name.split('/')[-1]))
else:
sub_run(
"echo '\n\\\\clearpage' >> tmp/{}"
.format(file_name.split('/')[-1]))
def clone_branch(repo, branch):
sub_run("git clone -b {} https://github.com/42-AI/{}.git".format(
branch, repo))
def input_file_cpy(input_file, template_file):
"""
Copy input file and create tmp directory.
Args:
input_file (undefined): input file
template_file (undefined): template file
"""
# create a tmp dir with a copy of all files
sub_run("rm -rf tmp")
sub_run("mkdir -p tmp")
# copy input_file into tmp
sub_run("cp {} tmp/".format(input_file))
sub_run("cp {} tmp/".format(template_file))
imgs_dir = sub_run(
"ls -d {}/assets".format("/".join(input_file.split('/')[:-1])))
if not imgs_dir.stderr:
sub_run("cp -rp {} tmp/".format(imgs_dir.stdout.decode().strip()))
def day_files_cpy(input_dir, template_file):
"""
Copy files of a day and create a temporary directory.
Args:
input_dir (undefined): input day directory
template_file (undefined): template file
"""
# retrieve file lists
day_f = sub_run("ls {}/day*.md".format(input_dir)).stdout.strip()
ex_list = sub_run("ls {}/**/ex*.md".format(input_dir)).stdout
imgs_dir = sub_run("ls -d {}/assets".format(input_dir))
# create a tmp dir with a copy of all files
sub_run("rm -rf tmp")
sub_run("mkdir -p tmp")
if not imgs_dir.stderr:
sub_run("cp -rp {} tmp/".format(imgs_dir.stdout.decode().strip()))
sub_run("cp {} tmp/".format(day_f.decode()))
sub_run("cp {} tmp/".format(day_f.decode()))
sub_run("cp {} tmp/".format(template_file))
for f in ex_list.split():
pattern = re.compile(r'(ex[0-9]{2}\.md)$')
for e in pattern.findall(f.decode()):
sub_run("cp {} tmp/{}".format(f.decode(), e[:-3] + "_master.md"))
pattern = re.compile(r'(ex[0-9]{2}_interlude.*)$')
for e in pattern.findall(f.decode()):
sub_run("cp {} tmp/".format(f.decode()))