Skip to content

Commit

Permalink
Merge branch 'main' of https://github.com/Laboratoria/digitaljumpstar…
Browse files Browse the repository at this point in the history 
…t-curriculum
  • Loading branch information
@diegovelezg
diegovelezg committed Aug 21, 2024
2 parents 7b01d70 + 534c7ec commit 07ba219
Show file tree
Hide file tree
Showing 5 changed files with 732 additions and 421 deletions.
2 changes: 1 addition & 1 deletion DEV/01_intro/02_learning_bydoing/activities/00_02_01_myfirst_CONFIG.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
"learning": 1,
"time": 3,
"directions": {
"ES": "<p>💡 Evaluación: Recuerda que puedes pedir la evaluación de una compañera antes de dar por terminado tu reto y compartir la URL en el hilo.</p><p>Al terminar, regresa a Discord, 💬 Comparte la URL de tu trabajo en el hilo y reacciona con ✅ para marcar tu progreso.</p>",
"ES": "<p>💡 Evaluación: Recuerda que puedes pedir la evaluación de una compañera antes de dar por terminado tu reto y compartir la URL en el hilo.</p><p>Al terminar, regresa a Discord, 💬 Comparte la URL de tu trabajo en el hilo y reacciona con ✅ para marcar tu progreso.",
"PT": "null"
},
"discord_URL": {
Expand Down
181 changes: 54 additions & 127 deletions generate_markdown_list.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,56 +6,34 @@
import logging

def clean_control_characters(json_str):
# Reemplazar caracteres de escape incorrectos
json_str = json_str.replace('\\_', '_')
# Eliminar caracteres de control y manejar caracteres de escape inválidos
json_str = re.sub(r'\\(?!["\\/bfnrtu])', r'\\\\', json_str) # Escapar correctamente las barras invertidas
return re.sub(r'[\x00-\x1F\x7F]', '', json_str) # Eliminar caracteres de control
return re.sub(r'[\x00-\x1F\x7F]', '', json_str.replace('\\_', '_').replace(r'\\(?!["\\/bfnrtu])', r'\\\\'))

def escape_json_config(config_file):
try:
with open(config_file, 'r', encoding='utf-8') as f:
content = f.read()
clean_content = clean_control_characters(content) # Limpiar contenido del archivo JSON
config = json.loads(clean_content) # Cargar el contenido limpio como un objeto JSON
config = json.loads(clean_control_characters(f.read())) # Limpiar y cargar JSON en una sola línea
with open(config_file, 'w', encoding='utf-8') as f:
json.dump(config, f, indent=2, ensure_ascii=False) # Escribir el objeto JSON limpio de nuevo en el archivo
except json.JSONDecodeError as e:
print(f"Error al procesar el archivo {config_file}: {e}") # Manejar errores de decodificación JSON
except Exception as e:
print(f"Error inesperado al procesar el archivo {config_file}: {e}") # Manejar cualquier otro error
json.dump(config, f, indent=2, ensure_ascii=False)
except (json.JSONDecodeError, Exception) as e:
print(f"Error procesando el archivo {config_file}: {e}")

def process_config_files(root_dir):
for subdir, _, files in os.walk(root_dir):
for file in files:
if file.endswith('_CONFIG.json'):
config_file = os.path.join(subdir, file)
escape_json_config(config_file) # Procesar cada archivo de configuración JSON
escape_json_config(os.path.join(subdir, file))

def extract_preview(file_path):
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
match = re.search(r'<div id="preview">(.*?)</div>', content, re.DOTALL)
match = re.search(r'<div id="preview">(.*?)</div>', f.read(), re.DOTALL)
return match.group(1).strip() if match else ""

def modify_activity_links(content, lang, track, skill, module):
pattern = r"//PATH_TO_THIS_SCRIPT:\?lang=XX&track=XXX&skill=XXXXXX&module=XXXXXX//"
replacement_base = f"?lang={lang}&track={track or ''}&skill={skill or ''}&module={module or ''}"

# Encontrar y reemplazar el patrón en el contenido sin modificar el parámetro 'path'
def replace_link(match):
original_link = match.group(0)
# Reemplazar la base del link sin modificar el path
updated_link = original_link.replace("//PATH_TO_THIS_SCRIPT:?lang=XX&track=XXX&skill=XXXXXX&module=XXXXXX//", replacement_base)
return updated_link

# Reemplazar el contenido del archivo usando la función de reemplazo personalizada
modified_content = re.sub(pattern, replace_link, content)

return modified_content, replacement_base
return re.sub(r"//PATH_TO_THIS_SCRIPT:\?lang=XX&track=XXX&skill=XXXXXX&module=XXXXXX//", replacement_base, content)

def generate_markdown_list(root_dir):
markdown_list = [] # Aseguramos que markdown_list siempre sea una lista
markdown_list = []
log_file = "modification_log.txt"

with open(log_file, 'w', encoding='utf-8') as log:
Expand All @@ -66,128 +44,79 @@ def generate_markdown_list(root_dir):
track, skill, module = get_levels(file_path, root_dir)
file_type = get_file_type(file_path, subdir, file)
lang = "ES" if file.endswith("_ES.md") else "PT" if file.endswith("_PT.md") else None

titles = get_title(file_path, file_type)
titles = get_title(file_path)

with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()

if file_type == "activity":
modified_content, replacement = modify_activity_links(content, lang, track, skill, module)

modified_content = modify_activity_links(content, lang, track, skill, module)
try:
with open(file_path, 'w', encoding='utf-8') as f:
f.write(modified_content)
f.flush()
os.fsync(f.fileno())
log.write(f"Archivo modificado: {file_path}\n")

# Verificación de escritura
with open(file_path, 'r', encoding='utf-8') as f_verify:
verify_content = f_verify.read()
if replacement in verify_content:
log.write(f"Verificación exitosa en: {file_path}\n")
else:
log.write(f"Fallo en la verificación: {file_path} no fue modificado correctamente.\n")

except Exception as e:
log.write(f"Error al escribir en el archivo {file_path}: {e}\n")
else:
log.write(f"Sin cambios en: {file_path}\n")

# Obtener la ruta del archivo de configuración correspondiente
config_file = os.path.splitext(file_path.replace("_ES", "").replace("_PT", ""))[0] + "_CONFIG.json"
config_data = read_config_data(config_file)

discord_url = config_data.get("discord_URL", {}).get(lang, "")
discord_channel_id = discord_url.split('/')[-2] if discord_url else ""
discord_message_id = discord_url.split('/')[-1] if discord_url else ""
discord_channel_id, discord_message_id = discord_url.split('/')[-2:], ["", ""]

slug = f"{track or ''}{'-' + skill if skill else ''}{'-' + module if module else ''}-{os.path.splitext(file)[0]}"

# Extraer contenido del div con id preview solo para archivos README
if file_type in ["program", "skill", "module"]:
directions = extract_preview(file_path)
else:
directions = config_data.get("directions", {}).get(lang, "")
directions = extract_preview(file_path) if file_type in ["program", "skill", "module"] else config_data.get("directions", {}).get(lang, "")

markdown_dict = {
"track": track,
"skill": skill,
"module": module,
"title": titles[0]["title"] if titles else "Sin título",
"title": titles.get("title", "Sin título"),
"type": file_type,
"path": file_path[2:], # Quitar "./" del comienzo de la ruta del archivo
"lang": lang if lang else titles[0]["lang"],
"lang": lang or titles.get("lang"),
"difficulty": config_data.get("difficulty", ""),
"learning": config_data.get("learning", ""),
"time": config_data.get("time", ""),
"directions": directions, # Utilizar contenido extraído del div preview si aplica, o del JSON
"directions": directions,
"discord_URL": discord_url,
"discord_channel_id": discord_channel_id,
"discord_message_id": discord_message_id,
"slug": slug
}

# Ajustar track, skill y module según el tipo y longitud de path_parts
path_parts = os.path.relpath(file_path, root_dir).split(os.sep)
if file_type == "program" and len(path_parts) >= 1:
markdown_dict["track"] = path_parts[0]
markdown_dict["skill"] = None
markdown_dict["module"] = None
elif file_type == "skill" and len(path_parts) >= 2:
markdown_dict["track"] = path_parts[0]
markdown_dict["skill"] = path_parts[1]
markdown_dict["module"] = None
elif file_type == "module" and len(path_parts) >= 3:
markdown_dict["track"] = path_parts[0]
markdown_dict["skill"] = path_parts[1]
markdown_dict["module"] = path_parts[2]
else:
# Manejar casos en los que no hay suficientes niveles en path_parts
markdown_dict["track"] = path_parts[0] if len(path_parts) > 0 else None
markdown_dict["skill"] = path_parts[1] if len(path_parts) > 1 else None
markdown_dict["module"] = path_parts[2] if len(path_parts) > 2 else None
if file_type == "program":
markdown_dict.update({"track": path_parts[0], "skill": None, "module": None})
elif file_type == "skill":
markdown_dict.update({"track": path_parts[0], "skill": path_parts[1], "module": None})
elif file_type == "module":
markdown_dict.update({"track": path_parts[0], "skill": path_parts[1], "module": path_parts[2]})

markdown_list.append(markdown_dict)

print(f"Log de modificaciones creado en {log_file}")
return markdown_list # Aseguramos que siempre retorna una lista válida
return markdown_list

def get_levels(file_path, root_dir):
# Obtener los niveles de la ruta del archivo
parts = os.path.relpath(file_path, root_dir).split(os.sep)
if len(parts) == 1: # Primer nivel
return None, None, None
elif len(parts) == 2: # Segundo nivel
return parts[0], None, None
elif len(parts) >= 3: # Tercer nivel o más profundo
return parts[0], parts[1], parts[2]
return None, None, None
return (parts[0], None, None) if len(parts) == 2 else (parts[0], parts[1], parts[2]) if len(parts) >= 3 else (None, None, None)

def get_file_type(file_path, subdir, file):
if "topics" in subdir and file.endswith(".md"):
if "topics" in subdir:
return "topic"
if "activities" in subdir and file.endswith(".md") and not file.endswith("README_ES.md") and not file.endswith("README_PT.md"):
if "activities" in subdir and not file.endswith(("README_ES.md", "README_PT.md")):
return "activity"
if file.endswith("README_ES.md") or file.endswith("README_PT.md"):
relative_path = os.path.relpath(subdir, root_dir)
depth = len(relative_path.split(os.sep))
if depth == 1:
return "program"
elif depth == 2:
return "skill"
elif depth == 3:
return "module"
return "module" # Asumimos que los demás archivos .md son de tipo "module"

def get_title(file_path, file_type):
depth = len(os.path.relpath(subdir, root_dir).split(os.sep))
return "program" if depth == 1 else "skill" if depth == 2 else "module"

def get_title(file_path):
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
title_match = re.search(r'#\s*(.+)', content) # Busca el primer h1
if title_match:
return [{"title": title_match.group(1).strip(), "lang": "ES" if file_path.endswith("_ES.md") else "PT"}]
else:
return [{"title": "Sin título", "lang": "ES" if file_path.endswith("_ES.md") else "PT"}]
match = re.search(r'#\s*(.+)', f.read())
return {"title": match.group(1).strip(), "lang": "ES" if file_path.endswith("_ES.md") else "PT"} if match else {"title": "Sin título", "lang": "ES" if file_path.endswith("_ES.md") else "PT"}

def read_config_data(config_file):
try:
Expand All @@ -196,40 +125,38 @@ def read_config_data(config_file):
except (json.JSONDecodeError, FileNotFoundError):
return {}

def save_to_csv(data, filename):
fieldnames = ["track", "skill", "module", "title", "type", "lang", "path", "difficulty", "learning", "time", "directions", "discord_URL", "discord_channel_id", "discord_message_id", "slug"]
with open(filename, 'w', newline='', encoding='utf-8') as output_file:
dict_writer = csv.DictWriter(output_file, fieldnames)
dict_writer.writeheader()
dict_writer.writerows(data)

def save_to_json(data, filename):
with open(filename, 'w', encoding='utf-8') as f:
json.dump(data, f, indent=2, ensure_ascii=False)
def save_data(data, filename, format="csv"):
if format == "csv":
fieldnames = ["track", "skill", "module", "title", "type", "lang", "path", "difficulty", "learning", "time", "directions", "discord_URL", "discord_channel_id", "discord_message_id", "slug"]
with open(filename, 'w', newline='', encoding='utf-8') as output_file:
dict_writer = csv.DictWriter(output_file, fieldnames)
dict_writer.writeheader()
dict_writer.writerows(data)
elif format == "json":
with open(filename, 'w', encoding='utf-8') as f:
json.dump(data, f, indent=2, ensure_ascii=False)

def send_data_to_endpoint(url, data):
try:
headers = {'Content-Type': 'application/json'}
response = requests.post(url, json=data, headers=headers)
response = requests.post(url, json=data, headers={'Content-Type': 'application/json'})
if response.status_code == 200:
logging.info("Data successfully sent to endpoint.") # Datos enviados correctamente al endpoint
logging.info("Data successfully sent to endpoint.")
else:
logging.error(f"Failed to send data to endpoint. Status code: {response.status_code}, Response: {response.text}") # Error al enviar datos
logging.error(f"Failed to send data to endpoint. Status code: {response.status_code}, Response: {response.text}")
except Exception as e:
logging.error(f"Error sending data to endpoint: {e}") # Manejar cualquier otro error al enviar datos
logging.error(f"Error sending data to endpoint: {e}")

if __name__ == "__main__":
root_dir = "."
process_config_files(root_dir) # Procesar archivos de configuración
markdown_list = generate_markdown_list(root_dir) # Generar lista de archivos Markdown
save_to_csv(markdown_list, "markdown_files.csv") # Guardar la lista en un archivo CSV
save_to_json(markdown_list, "markdown_files.json") # Guardar la lista en un archivo JSON
process_config_files(root_dir)
markdown_list = generate_markdown_list(root_dir)
save_data(markdown_list, "markdown_files.csv", format="csv")
save_data(markdown_list, "markdown_files.json", format="json")

# Enviar datos al endpoint
endpoint_url = "https://us-central1-laboratoria-prologue.cloudfunctions.net/dj-curriculum-get"
endpoint_url = "https://us-central1-laboratoria-prologue.cloudfunctions.net/dj-curriculum-get"
if endpoint_url:
send_data_to_endpoint(endpoint_url, markdown_list)
else:
logging.error("ENDPOINT_URL variable not set.") # Error si la URL del endpoint no está configurada
logging.error("ENDPOINT_URL variable not set.")

logging.info("All files have been saved and data sent to endpoint.") # Información de que todos los archivos han sido guardados y los datos enviados
logging.info("All files have been saved and data sent to endpoint.")
Loading

0 comments on commit 07ba219

Please sign in to comment.