Spaces:
Sleeping
Sleeping
Update main.py
Browse files
main.py
CHANGED
|
@@ -12,30 +12,32 @@ app = FastAPI()
|
|
| 12 |
# Control de descargas por archivo
|
| 13 |
descargas = {}
|
| 14 |
|
| 15 |
-
|
| 16 |
class MarkdownInput(BaseModel):
|
| 17 |
content: str
|
| 18 |
|
| 19 |
-
|
| 20 |
def limpiar_lineas_hr(markdown_text: str) -> str:
|
| 21 |
return re.sub(r'^\s*---\s*$', '\n', markdown_text, flags=re.MULTILINE)
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
def save_markdown_to_file(content: str, path: str):
|
| 25 |
with open(path, "w", encoding="utf-8") as f:
|
| 26 |
f.write(content)
|
| 27 |
|
| 28 |
-
|
| 29 |
def convert_markdown_to_docx(input_md: str, output_docx: str):
|
| 30 |
pypandoc.convert_file(
|
| 31 |
source_file=input_md,
|
| 32 |
to="docx",
|
| 33 |
format="md",
|
| 34 |
outputfile=output_docx,
|
| 35 |
-
extra_args=["--
|
| 36 |
)
|
| 37 |
|
| 38 |
-
|
| 39 |
def limpieza():
|
| 40 |
for ext in ["*.docx", "*.md"]:
|
| 41 |
for file in glob.glob(ext):
|
|
@@ -44,7 +46,6 @@ def limpieza():
|
|
| 44 |
except Exception as e:
|
| 45 |
print(f"No se pudo eliminar {file}: {e}")
|
| 46 |
|
| 47 |
-
|
| 48 |
@app.post("/convert/")
|
| 49 |
def convert(data: MarkdownInput):
|
| 50 |
try:
|
|
@@ -54,17 +55,20 @@ def convert(data: MarkdownInput):
|
|
| 54 |
output_docx = f"{uid}.docx"
|
| 55 |
|
| 56 |
contenido_limpio = limpiar_lineas_hr(data.content)
|
|
|
|
| 57 |
save_markdown_to_file(contenido_limpio, input_md)
|
| 58 |
convert_markdown_to_docx(input_md, output_docx)
|
| 59 |
os.remove(input_md)
|
| 60 |
|
| 61 |
descargas[uid] = 0
|
| 62 |
-
return {
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
except Exception as e:
|
| 65 |
return JSONResponse(content={"error": str(e)}, status_code=500)
|
| 66 |
|
| 67 |
-
|
| 68 |
@app.get("/download/{file_id}")
|
| 69 |
def download(file_id: str):
|
| 70 |
output_docx = f"{file_id}.docx"
|
|
|
|
| 12 |
# Control de descargas por archivo
|
| 13 |
descargas = {}
|
| 14 |
|
|
|
|
| 15 |
class MarkdownInput(BaseModel):
|
| 16 |
content: str
|
| 17 |
|
| 18 |
+
# Reemplaza '---' por saltos de línea
|
| 19 |
def limpiar_lineas_hr(markdown_text: str) -> str:
|
| 20 |
return re.sub(r'^\s*---\s*$', '\n', markdown_text, flags=re.MULTILINE)
|
| 21 |
|
| 22 |
+
# Convierte \[...\] y \(...\) a $$...$$ y $...$
|
| 23 |
+
def normalizar_ecuaciones(md: str) -> str:
|
| 24 |
+
md = re.sub(r'\\\[\s*(.*?)\s*\\\]', r'$$\1$$', md, flags=re.DOTALL)
|
| 25 |
+
md = re.sub(r'\\\(\s*(.*?)\s*\\\)', r'$\1$', md, flags=re.DOTALL)
|
| 26 |
+
return md
|
| 27 |
|
| 28 |
def save_markdown_to_file(content: str, path: str):
|
| 29 |
with open(path, "w", encoding="utf-8") as f:
|
| 30 |
f.write(content)
|
| 31 |
|
|
|
|
| 32 |
def convert_markdown_to_docx(input_md: str, output_docx: str):
|
| 33 |
pypandoc.convert_file(
|
| 34 |
source_file=input_md,
|
| 35 |
to="docx",
|
| 36 |
format="md",
|
| 37 |
outputfile=output_docx,
|
| 38 |
+
extra_args=["--standalone"]
|
| 39 |
)
|
| 40 |
|
|
|
|
| 41 |
def limpieza():
|
| 42 |
for ext in ["*.docx", "*.md"]:
|
| 43 |
for file in glob.glob(ext):
|
|
|
|
| 46 |
except Exception as e:
|
| 47 |
print(f"No se pudo eliminar {file}: {e}")
|
| 48 |
|
|
|
|
| 49 |
@app.post("/convert/")
|
| 50 |
def convert(data: MarkdownInput):
|
| 51 |
try:
|
|
|
|
| 55 |
output_docx = f"{uid}.docx"
|
| 56 |
|
| 57 |
contenido_limpio = limpiar_lineas_hr(data.content)
|
| 58 |
+
contenido_limpio = normalizar_ecuaciones(contenido_limpio)
|
| 59 |
save_markdown_to_file(contenido_limpio, input_md)
|
| 60 |
convert_markdown_to_docx(input_md, output_docx)
|
| 61 |
os.remove(input_md)
|
| 62 |
|
| 63 |
descargas[uid] = 0
|
| 64 |
+
return {
|
| 65 |
+
"message": "Archivo generado exitosamente, para descargar acceder a la URL",
|
| 66 |
+
"url": f"https://jairodanielmt-markdown-docx.hf.space/download/{uid}"
|
| 67 |
+
}
|
| 68 |
|
| 69 |
except Exception as e:
|
| 70 |
return JSONResponse(content={"error": str(e)}, status_code=500)
|
| 71 |
|
|
|
|
| 72 |
@app.get("/download/{file_id}")
|
| 73 |
def download(file_id: str):
|
| 74 |
output_docx = f"{file_id}.docx"
|