diff --git a/app/tools/convert.py b/app/tools/convert.py index 9f6215f..0a1d89f 100644 --- a/app/tools/convert.py +++ b/app/tools/convert.py @@ -13,9 +13,8 @@ def _clean(text: str) -> str: from PySide6.QtCore import Qt from PySide6.QtWidgets import ( QGroupBox, QFormLayout, QComboBox, QLabel, QFileDialog, - QMessageBox, QApplication, QProgressDialog, + QMessageBox, QProgressDialog, ) -from pypdf import PdfReader from app.base import BasePage from app.i18n import t @@ -253,32 +252,44 @@ def _convert_docx(self, pdf_path: str): filter_key="file_filter.docx") if not out_path: return - self._status("→ DOCX…") - QApplication.processEvents() + # Pre-flight on main thread: dep checks + page count + capture pwd. try: - import fitz + import fitz # noqa: F401 except ImportError: QMessageBox.critical(self, t("msg.missing_dep"), t("tool.ocr.dep_pymupdf")) return try: - from docx import Document + from docx import Document # noqa: F401 except ImportError: QMessageBox.critical(self, t("msg.missing_dep"), t("tool.convert.dep_docx")) return try: + with self._open_fitz(pdf_path) as _probe: + total = _probe.page_count + except Exception as e: + QMessageBox.critical(self, t("msg.error"), str(e)) + return + if total == 0: + QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) + return + pwd = self._pdf_password + + def do_work(worker): + import fitz from docx import Document from docx.shared import Pt, RGBColor, Inches import io, re as _re - doc = self._open_fitz(pdf_path) + doc = fitz.open(pdf_path) + if doc.needs_pass and pwd: + doc.authenticate(pwd) try: docx_doc = Document() - total = doc.page_count - for i, page in enumerate(doc): + if worker.is_cancelled(): + return None blocks = page.get_text("dict")["blocks"] for block in blocks: btype = block.get("type", 0) - # Image block — extract and embed if btype == 1: img_data = block.get("image") @@ -290,42 +301,30 @@ def _convert_docx(self, pdf_path: str): except Exception: pass continue - # Text block lines = block.get("lines", []) if not lines: continue - - # Collect all spans all_spans = [] for line in lines: all_spans.extend(line.get("spans", [])) if not all_spans: continue - - # Build full block text block_text = " ".join( _clean(s.get("text", "")) for s in all_spans ).strip() if not block_text: continue - - # Skip standalone page numbers: "42", "Page 3", "3 of 10" + # Skip standalone page numbers if _re.match(r"^\s*(?:page\s+)?\d{1,4}(?:\s+of\s+\d{1,4})?\s*$", block_text, _re.IGNORECASE): continue - # Skip TOC dot-leader lines if _re.search(r'\.[\s.]*\.[\s.]*\.[\s.]*\.', block_text): continue - - # Skip running headers like "2.3. COURSE BENEFITS & ANECDOTES 9" - # (short lines that are all caps + number at end, from page headers) - # Detect heading level by font size max_size = max(s.get("size", 12) for s in all_spans) any_bold = any(s.get("flags", 0) & 16 for s in all_spans) - if max_size >= 20: para = docx_doc.add_heading(level=1) elif max_size >= 16: @@ -336,8 +335,6 @@ def _convert_docx(self, pdf_path: str): para = docx_doc.add_heading(level=4) else: para = docx_doc.add_paragraph() - - # Add spans, merging lines within the block for li, line in enumerate(lines): spans = line.get("spans", []) for span in spans: @@ -355,44 +352,67 @@ def _convert_docx(self, pdf_path: str): g_val = (color >> 8) & 0xFF b_val = color & 0xFF run.font.color.rgb = RGBColor(r_val, g_val, b_val) - # Space between lines within same paragraph if li < len(lines) - 1: para.add_run(" ") - - self._status(f"{i + 1}/{total}…") - QApplication.processEvents() - + worker.progress.emit(i, f"{i + 1}/{total}…") + if worker.is_cancelled(): + return None docx_doc.save(out_path) finally: doc.close() + return total + + def on_done(result): self.lbl_result.setText(f" → {os.path.basename(out_path)}") self._status(f"✔ DOCX → {out_path}") QMessageBox.information(self, t("msg.done"), t("tool.convert.done_docx", path=out_path)) - except Exception as e: - QMessageBox.critical(self, t("msg.error"), str(e)) + + self._run_background(do_work, total, t("tool.convert.converting"), + on_done=on_done) def _convert_txt(self, pdf_path: str): out_path = self._resolve_output_file(self._drop_file, pdf_path, filter_key="file_filter.txt") if not out_path: return - self._status("→ TXT…") - QApplication.processEvents() try: + with self._open_fitz(pdf_path) as _probe: + total = _probe.page_count + except Exception as e: + QMessageBox.critical(self, t("msg.error"), str(e)) + return + if total == 0: + QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) + return + pwd = self._pdf_password + + def do_work(worker): import fitz - with self._open_fitz(pdf_path) as doc: + doc = fitz.open(pdf_path) + if doc.needs_pass and pwd: + doc.authenticate(pwd) + try: with open(out_path, 'w', encoding='utf-8') as f: for i, page in enumerate(doc): + if worker.is_cancelled(): + return None if i > 0: f.write(f'\n\n--- Page {i + 1} ---\n\n') f.write(page.get_text()) + worker.progress.emit(i, f"{i + 1}/{total}…") + finally: + doc.close() + return total + + def on_done(result): self.lbl_result.setText(f" → {os.path.basename(out_path)}") self._status(f"✔ TXT → {out_path}") QMessageBox.information(self, t("msg.done"), t("tool.convert.done_txt", path=out_path)) - except Exception as e: - QMessageBox.critical(self, t("msg.error"), str(e)) + + self._run_background(do_work, total, t("tool.convert.converting"), + on_done=on_done) # ── PDF → PPTX ────────────────────────────────────────────────────── @@ -401,40 +421,61 @@ def _convert_pptx(self, pdf_path: str): filter_key="file_filter.pptx") if not out_path: return - self._status("→ PPTX…") - QApplication.processEvents() try: - import fitz + from pptx import Presentation # noqa: F401 + except ImportError: + QMessageBox.critical(self, t("msg.missing_dep"), t("tool.convert.dep_pptx")) + return + try: + with self._open_fitz(pdf_path) as _probe: + total = _probe.page_count + first = _probe[0].rect if total else None + except Exception as e: + QMessageBox.critical(self, t("msg.error"), str(e)) + return + if total == 0: + QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) + return + slide_w_pt = first.width + slide_h_pt = first.height + pwd = self._pdf_password + + def do_work(worker): + import fitz, io from pptx import Presentation - from pptx.util import Inches, Pt, Emu - with self._open_fitz(pdf_path) as doc: - if doc.page_count == 0: - QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) - return + from pptx.util import Emu + doc = fitz.open(pdf_path) + if doc.needs_pass and pwd: + doc.authenticate(pwd) + try: prs = Presentation() - # Match slide size to first page aspect ratio - first = doc[0].rect - prs.slide_width = Emu(int(first.width * 12700)) - prs.slide_height = Emu(int(first.height * 12700)) - total = doc.page_count + prs.slide_width = Emu(int(slide_w_pt * 12700)) + prs.slide_height = Emu(int(slide_h_pt * 12700)) for i, page in enumerate(doc): - slide = prs.slides.add_slide(prs.slide_layouts[6]) # blank layout - # Render page as image and embed in slide + if worker.is_cancelled(): + return None + slide = prs.slides.add_slide(prs.slide_layouts[6]) pix = page.get_pixmap(matrix=fitz.Matrix(2, 2)) img_bytes = pix.tobytes("png") - import io slide.shapes.add_picture( io.BytesIO(img_bytes), Emu(0), Emu(0), prs.slide_width, prs.slide_height) - self._status(f"{i + 1}/{total}…") - QApplication.processEvents() + worker.progress.emit(i, f"{i + 1}/{total}…") + if worker.is_cancelled(): + return None prs.save(out_path) + finally: + doc.close() + return total + + def on_done(result): self.lbl_result.setText(f" → {os.path.basename(out_path)}") self._status(f"✔ PPTX → {out_path}") QMessageBox.information(self, t("msg.done"), t("tool.convert.done_pptx", path=out_path)) - except Exception as e: - QMessageBox.critical(self, t("msg.error"), str(e)) + + self._run_background(do_work, total, t("tool.convert.converting"), + on_done=on_done) # ── PDF → XLSX ────────────────────────────────────────────────────── @@ -443,42 +484,62 @@ def _convert_xlsx(self, pdf_path: str): filter_key="file_filter.xlsx") if not out_path: return - self._status("→ XLSX…") - QApplication.processEvents() try: + from openpyxl import Workbook # noqa: F401 + except ImportError: + QMessageBox.critical(self, t("msg.missing_dep"), t("tool.convert.dep_xlsx")) + return + try: + with self._open_fitz(pdf_path) as _probe: + total = _probe.page_count + except Exception as e: + QMessageBox.critical(self, t("msg.error"), str(e)) + return + if total == 0: + QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) + return + pwd = self._pdf_password + + def do_work(worker): import fitz from openpyxl import Workbook - doc = self._open_fitz(pdf_path) + doc = fitz.open(pdf_path) + if doc.needs_pass and pwd: + doc.authenticate(pwd) try: wb = Workbook() wb.remove(wb.active) - total = doc.page_count for i, page in enumerate(doc): + if worker.is_cancelled(): + return None ws = wb.create_sheet(title=f"Page {i + 1}") - # Extract text as table-like structure using blocks blocks = page.get_text("blocks") for row_idx, block in enumerate(blocks): if block[6] != 0: # skip image blocks continue text = _clean(block[4].strip()) if text: - # Split by common delimiters for table-like content cells = [c.strip() for c in text.replace("\t", "|").split("|") if c.strip()] if not cells: cells = [text] for col_idx, cell in enumerate(cells): ws.cell(row=row_idx + 1, column=col_idx + 1, value=cell) - self._status(f"{i + 1}/{total}…") - QApplication.processEvents() + worker.progress.emit(i, f"{i + 1}/{total}…") + if worker.is_cancelled(): + return None wb.save(out_path) finally: doc.close() + return total + + def on_done(result): self.lbl_result.setText(f" → {os.path.basename(out_path)}") self._status(f"✔ XLSX → {out_path}") QMessageBox.information(self, t("msg.done"), t("tool.convert.done_xlsx", path=out_path)) - except Exception as e: - QMessageBox.critical(self, t("msg.error"), str(e)) + + self._run_background(do_work, total, t("tool.convert.converting"), + on_done=on_done) # ── PDF → HTML ────────────────────────────────────────────────────── @@ -487,11 +548,22 @@ def _convert_html(self, pdf_path: str): filter_key="file_filter.html") if not out_path: return - self._status("→ HTML…") - QApplication.processEvents() try: + with self._open_fitz(pdf_path) as _probe: + total = _probe.page_count + except Exception as e: + QMessageBox.critical(self, t("msg.error"), str(e)) + return + if total == 0: + QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) + return + pwd = self._pdf_password + + def do_work(worker): import fitz - doc = self._open_fitz(pdf_path) + doc = fitz.open(pdf_path) + if doc.needs_pass and pwd: + doc.authenticate(pwd) try: parts = [ "", @@ -502,8 +574,9 @@ def _convert_html(self, pdf_path: str): "", ] for i, page in enumerate(doc): - parts.append(f'
') - # Use get_text("html") for rich content, fall back to blocks + if worker.is_cancelled(): + return None + parts.append('
') blocks = page.get_text("dict")["blocks"] for block in blocks: if block.get("type") != 0: @@ -514,7 +587,6 @@ def _convert_html(self, pdf_path: str): text = span["text"] if not text.strip(): continue - size = span.get("size", 12) flags = span.get("flags", 0) bold = flags & 16 italic = flags & 2 @@ -525,7 +597,6 @@ def _convert_html(self, pdf_path: str): tag_text = f"{tag_text}" spans_html += tag_text if spans_html: - # Detect headings by font size avg_size = max(s.get("size", 12) for s in line.get("spans", [{"size": 12}])) if avg_size >= 18: parts.append(f"

{spans_html}

") @@ -536,19 +607,24 @@ def _convert_html(self, pdf_path: str): else: parts.append(f"

{spans_html}

") parts.append("
") - self._status(f"{i + 1}/{doc.page_count}…") - QApplication.processEvents() + worker.progress.emit(i, f"{i + 1}/{total}…") parts.append("") + if worker.is_cancelled(): + return None with open(out_path, "w", encoding="utf-8") as f: f.write("\n".join(parts)) finally: doc.close() + return total + + def on_done(result): self.lbl_result.setText(f" → {os.path.basename(out_path)}") self._status(f"✔ HTML → {out_path}") QMessageBox.information(self, t("msg.done"), t("tool.convert.done_html", path=out_path)) - except Exception as e: - QMessageBox.critical(self, t("msg.error"), str(e)) + + self._run_background(do_work, total, t("tool.convert.converting"), + on_done=on_done) # ── PDF → EPUB ────────────────────────────────────────────────────── @@ -557,28 +633,46 @@ def _convert_epub(self, pdf_path: str): filter_key="file_filter.epub") if not out_path: return - self._status("→ EPUB…") - QApplication.processEvents() try: + from ebooklib import epub # noqa: F401 + except ImportError: + QMessageBox.critical(self, t("msg.missing_dep"), t("tool.convert.dep_epub")) + return + try: + with self._open_fitz(pdf_path) as _probe: + total = _probe.page_count + except Exception as e: + QMessageBox.critical(self, t("msg.error"), str(e)) + return + if total == 0: + QMessageBox.warning(self, t("msg.warning"), t("msg.select_valid_pdf")) + return + pwd = self._pdf_password + + def do_work(worker): import fitz from ebooklib import epub - doc = self._open_fitz(pdf_path) + doc = fitz.open(pdf_path) + if doc.needs_pass and pwd: + doc.authenticate(pwd) try: book = epub.EpubBook() book.set_identifier(f"pdfapps-{os.path.basename(pdf_path)}") book.set_title(os.path.splitext(os.path.basename(pdf_path))[0]) book.set_language("en") chapters = [] - total = doc.page_count for i, page in enumerate(doc): + if worker.is_cancelled(): + return None ch = epub.EpubHtml(title=f"Page {i + 1}", file_name=f"page_{i+1}.xhtml") text = page.get_text() paragraphs = [f"

{_clean(p)}

" for p in text.split("\n") if p.strip()] ch.content = f"

Page {i + 1}

{''.join(paragraphs)}" book.add_item(ch) chapters.append(ch) - self._status(f"{i + 1}/{total}…") - QApplication.processEvents() + worker.progress.emit(i, f"{i + 1}/{total}…") + if worker.is_cancelled(): + return None book.add_item(epub.EpubNcx()) book.add_item(epub.EpubNav()) book.spine = ["nav"] + chapters @@ -586,9 +680,13 @@ def _convert_epub(self, pdf_path: str): epub.write_epub(out_path, book) finally: doc.close() + return total + + def on_done(result): self.lbl_result.setText(f" → {os.path.basename(out_path)}") self._status(f"✔ EPUB → {out_path}") QMessageBox.information(self, t("msg.done"), t("tool.convert.done_epub", path=out_path)) - except Exception as e: - QMessageBox.critical(self, t("msg.error"), str(e)) + + self._run_background(do_work, total, t("tool.convert.converting"), + on_done=on_done) diff --git a/app/translations.json b/app/translations.json index 32cfab0..da1d3c9 100644 --- a/app/translations.json +++ b/app/translations.json @@ -338,6 +338,9 @@ "tool.convert.done_docx": "DOCX saved at:\n{path}", "tool.convert.done_txt": "TXT saved at:\n{path}", "tool.convert.dep_docx": "python-docx library required:\n\npip install python-docx", + "tool.convert.dep_pptx": "python-pptx library required:\n\npip install python-pptx", + "tool.convert.dep_xlsx": "openpyxl library required:\n\npip install openpyxl", + "tool.convert.dep_epub": "ebooklib library required:\n\npip install ebooklib", "tool.info.name": "Info", "tool.info.desc": "Show metadata, dimensions and properties of the PDF.", "tool.info.btn": "View info", @@ -869,6 +872,9 @@ "tool.convert.done_docx": "DOCX guardado em:\n{path}", "tool.convert.done_txt": "TXT guardado em:\n{path}", "tool.convert.dep_docx": "Instala a biblioteca python-docx:\n\npip install python-docx", + "tool.convert.dep_pptx": "Instala a biblioteca python-pptx:\n\npip install python-pptx", + "tool.convert.dep_xlsx": "Instala a biblioteca openpyxl:\n\npip install openpyxl", + "tool.convert.dep_epub": "Instala a biblioteca ebooklib:\n\npip install ebooklib", "tool.info.name": "Informação", "tool.info.desc": "Mostra metadados, dimensões e propriedades do PDF.", "tool.info.btn": "Ver informação", @@ -1400,6 +1406,9 @@ "tool.convert.done_docx": "DOCX guardado en:\n{path}", "tool.convert.done_txt": "TXT guardado en:\n{path}", "tool.convert.dep_docx": "Biblioteca python-docx requerida:\n\npip install python-docx", + "tool.convert.dep_pptx": "Se requiere la biblioteca python-pptx:\n\npip install python-pptx", + "tool.convert.dep_xlsx": "Se requiere la biblioteca openpyxl:\n\npip install openpyxl", + "tool.convert.dep_epub": "Se requiere la biblioteca ebooklib:\n\npip install ebooklib", "tool.info.name": "Información", "tool.info.desc": "Muestra metadatos, dimensiones y propiedades del PDF.", "tool.info.btn": "Ver información", @@ -1931,6 +1940,9 @@ "tool.convert.done_docx": "DOCX enregistré dans :\n{path}", "tool.convert.done_txt": "TXT enregistré dans :\n{path}", "tool.convert.dep_docx": "Bibliothèque python-docx requise :\n\npip install python-docx", + "tool.convert.dep_pptx": "Bibliothèque python-pptx requise :\n\npip install python-pptx", + "tool.convert.dep_xlsx": "Bibliothèque openpyxl requise :\n\npip install openpyxl", + "tool.convert.dep_epub": "Bibliothèque ebooklib requise :\n\npip install ebooklib", "tool.info.name": "Infos", "tool.info.desc": "Affiche les métadonnées, dimensions et propriétés du PDF.", "tool.info.btn": "Voir les infos", @@ -2462,6 +2474,9 @@ "tool.convert.done_docx": "DOCX gespeichert unter:\n{path}", "tool.convert.done_txt": "TXT gespeichert unter:\n{path}", "tool.convert.dep_docx": "Bibliothek python-docx erforderlich:\n\npip install python-docx", + "tool.convert.dep_pptx": "Bibliothek python-pptx erforderlich:\n\npip install python-pptx", + "tool.convert.dep_xlsx": "Bibliothek openpyxl erforderlich:\n\npip install openpyxl", + "tool.convert.dep_epub": "Bibliothek ebooklib erforderlich:\n\npip install ebooklib", "tool.info.name": "Info", "tool.info.desc": "Zeigt Metadaten, Abmessungen und Eigenschaften des PDF.", "tool.info.btn": "Info anzeigen", @@ -2993,6 +3008,9 @@ "tool.convert.done_docx": "DOCX 已保存至：\n{path}", "tool.convert.done_txt": "TXT 已保存至：\n{path}", "tool.convert.dep_docx": "需要 python-docx 库：\n\npip install python-docx", + "tool.convert.dep_pptx": "需要 python-pptx 库：\n\npip install python-pptx", + "tool.convert.dep_xlsx": "需要 openpyxl 库：\n\npip install openpyxl", + "tool.convert.dep_epub": "需要 ebooklib 库：\n\npip install ebooklib", "tool.info.name": "信息", "tool.info.desc": "显示 PDF 的元数据、尺寸和属性。", "tool.info.btn": "查看信息", @@ -3524,6 +3542,9 @@ "tool.convert.done_docx": "DOCX salvato in:\n{path}", "tool.convert.done_txt": "TXT salvato in:\n{path}", "tool.convert.dep_docx": "Libreria python-docx richiesta:\n\npip install python-docx", + "tool.convert.dep_pptx": "È richiesta la libreria python-pptx:\n\npip install python-pptx", + "tool.convert.dep_xlsx": "È richiesta la libreria openpyxl:\n\npip install openpyxl", + "tool.convert.dep_epub": "È richiesta la libreria ebooklib:\n\npip install ebooklib", "tool.info.name": "Info", "tool.info.desc": "Mostra metadati, dimensioni e proprietà del PDF.", "tool.info.btn": "Visualizza info", @@ -4055,6 +4076,9 @@ "tool.convert.done_docx": "DOCX opgeslagen op:\n{path}", "tool.convert.done_txt": "TXT opgeslagen op:\n{path}", "tool.convert.dep_docx": "python-docx-bibliotheek vereist:\n\npip install python-docx", + "tool.convert.dep_pptx": "python-pptx-bibliotheek vereist:\n\npip install python-pptx", + "tool.convert.dep_xlsx": "openpyxl-bibliotheek vereist:\n\npip install openpyxl", + "tool.convert.dep_epub": "ebooklib-bibliotheek vereist:\n\npip install ebooklib", "tool.info.name": "Info", "tool.info.desc": "Toon metadata, afmetingen en eigenschappen van de PDF.", "tool.info.btn": "Info bekijken",