Spaces:
Running on Zero
Running on Zero
| """ | |
| Document Parser supporting TXT, Markdown, PDF, DOCX, and raw strings. | |
| """ | |
| from pathlib import Path | |
| from typing import Union | |
| import pymupdf # PyMuPDF | |
| import docx | |
| import pptx | |
| import openpyxl | |
| def extract_text_from_file(file_path: Union[str, Path]) -> str: | |
| """Extract plain text from various file formats (.txt, .md, .pdf, .docx).""" | |
| path = Path(file_path) | |
| if not path.is_file(): | |
| raise FileNotFoundError(f"File not found: {path}") | |
| ext = path.suffix.lower() | |
| if ext in [".txt", ".md", ".markdown", ".rtf", ".rst", ".py", ".json", ".csv"]: | |
| return path.read_text(encoding="utf-8", errors="replace") | |
| elif ext == ".pdf": | |
| text_parts = [] | |
| with pymupdf.open(str(path)) as doc: | |
| for page in doc: | |
| t = page.get_text() | |
| if t: | |
| text_parts.append(t) | |
| return "\n\n".join(text_parts).strip() | |
| elif ext in [".docx", ".doc"]: | |
| if ext == ".doc": | |
| # Best effort try python-docx or raw read | |
| try: | |
| doc = docx.Document(str(path)) | |
| return "\n".join([p.text for p in doc.paragraphs if p.text]).strip() | |
| except Exception: | |
| return path.read_text(encoding="utf-8", errors="replace") | |
| doc = docx.Document(str(path)) | |
| paragraphs = [p.text for p in doc.paragraphs if p.text] | |
| # Also parse tables if present | |
| for table in doc.tables: | |
| for row in table.rows: | |
| row_text = " | ".join([cell.text.strip() for cell in row.cells if cell.text.strip()]) | |
| if row_text: | |
| paragraphs.append(row_text) | |
| return "\n".join(paragraphs).strip() | |
| elif ext in [".pptx", ".ppt"]: | |
| prs = pptx.Presentation(str(path)) | |
| text_runs = [] | |
| for slide_idx, slide in enumerate(prs.slides, 1): | |
| slide_texts = [] | |
| for shape in slide.shapes: | |
| if shape.has_text_frame: | |
| for paragraph in shape.text_frame.paragraphs: | |
| p_text = "".join(run.text for run in paragraph.runs).strip() | |
| if p_text: | |
| slide_texts.append(p_text) | |
| elif shape.has_table: | |
| for row in shape.table.rows: | |
| row_text = " | ".join(cell.text.strip() for cell in row.cells if cell.text.strip()) | |
| if row_text: | |
| slide_texts.append(row_text) | |
| if slide_texts: | |
| text_runs.append(f"--- Slide {slide_idx} ---\n" + "\n".join(slide_texts)) | |
| return "\n\n".join(text_runs).strip() | |
| elif ext in [".xlsx", ".xlsm", ".xltx"]: | |
| wb = openpyxl.load_workbook(str(path), data_only=True) | |
| sheet_texts = [] | |
| for sheet_name in wb.sheetnames: | |
| ws = wb[sheet_name] | |
| rows_text = [] | |
| for row in ws.iter_rows(values_only=True): | |
| non_empty = [str(cell).strip() for cell in row if cell is not None and str(cell).strip()] | |
| if non_empty: | |
| rows_text.append(" | ".join(non_empty)) | |
| if rows_text: | |
| sheet_texts.append(f"--- Sheet: {sheet_name} ---\n" + "\n".join(rows_text)) | |
| return "\n\n".join(sheet_texts).strip() | |
| else: | |
| # Default fallback to plain text read | |
| return path.read_text(encoding="utf-8", errors="replace") | |