renato97/cbc2027
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Mejora parser de tablas LaTeX

Browse Source 
- Elimina líneas hline duplicadas
- Mejora limpieza de comandos LaTeX en celdas
- Usa regex para manejar {contenido}
- Filtra celdas vacías

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
renato97
2026-02-25 17:32:18 +00:00
parent d902203b59
commit d50772d962
1 changed files with 21 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
services/pdf_generator.py
View File

@@ -94,13 +94,20 @@ class PDFGenerator:
break break
if in_table: if in_table:
# Saltar líneas de hline
if "hline" in line.replace("\\", "").replace(" ", ""):
i += 1
continue
# Procesar línea de tabla # Procesar línea de tabla
# Reemplazar & por separador y eliminar \\ # Reemplazar & por separador
row_data = line.replace("&", "|").replace("\\", "").replace("\\\\", "") row_data = line.replace("&", "|")
# Limpiar formato LaTeX básico # Eliminar comandos LaTeX
row_data = row_data.replace("hline", "").replace("\\hline", "") row_data = row_data.replace("\\", "").replace("\\\\", "").replace("hline", "")
cells = [c.strip() for c in row_data.split("|") if c.strip()] cells = [c.strip() for c in row_data.split("|") if c.strip()]
if cells: # Filtrar celdas vacías
cells = [c for c in cells if c and c != "|"]
if cells and len(cells) > 1: # Al menos 2 columnas para ser tabla válida
table_lines.append({"type": "row", "data": cells}) table_lines.append({"type": "row", "data": cells})
i += 1 i += 1
@@ -118,12 +125,16 @@ class PDFGenerator:
row = [] row = []
for cell in tl["data"]: for cell in tl["data"]:
cell = cell.strip() cell = cell.strip()
# Eliminar comandos LaTeX restantes # Eliminar comandos LaTeX restantes (manejar {contenido})
cell = cell.replace("\\textbf{", "").replace("}", "") import re
cell = cell.replace("\\textit{", "") # Eliminar \textbf{...}, \textit{...}, \emph{...}
cell = cell.replace("\\emph{", "") cell = re.sub(r'\\textbf\{([^}]*)\}', r'\1', cell)
cell = re.sub(r'\\textit\{([^}]*)\}', r'\1', cell)
cell = re.sub(r'\\emph\{([^}]*)\}', r'\1', cell)
cell = cell.replace("\\", "").replace("{", "").replace("}", "")
cell = cell.strip() cell = cell.strip()
row.append(cell) if cell:
row.append(cell)
if row: if row:
data.append(row) data.append(row)